Personalized heat stress monitoring system based on vulnerable group and the operation method
The heat stress monitoring system classifies workers based on heart rate and body parameters, using a Case-Based Reasoning algorithm to predict heat stress, addressing individual variability and reducing accident risks by providing personalized warnings.
Patent Information
- Application Number
- KR1020230002407
- Authority / Receiving Office
- KR · KR
- Patent Type
- Patents
- Current Assignee / Owner
- Filing Date
- 2023-01-06
- Publication Date
- 2026-11-11
- Estimated Expiration
- 2043-01-06
AI Technical Summary
Existing heat stress monitoring systems fail to account for individual differences in workload and climate adaptability, making it difficult to effectively classify workers into high-risk and low-risk groups and predict heat stress levels, thereby increasing the risk of accidents.
A heat stress monitoring system that includes a wearable device, a measuring device, and a monitoring device, which classifies workers based on heart rate and body parameters, calculates metabolic rate changes, and uses a Case-Based Reasoning algorithm to predict heat stress output indices, transmitting these to the wearable device for real-time monitoring and risk assessment.
The system effectively classifies workers into high-risk and low-risk groups, predicting heat stress levels and allowing for proactive measures to prevent accidents and enhance work efficiency by providing personalized heat stress warnings.
Smart Images

Figure 112023002469886-PAT00009_ABST
Abstract
Description
Technology Field
[0001] The present invention relates to a risk group-based personalized heat stress monitoring system and a method of operation thereof. More specifically, it relates to a risk group-based personalized heat stress monitoring system and a method of operation thereof that classifies each worker performing work in a workplace into high-risk and low-risk groups, monitors the degree of heat stress according to the classified risk group, and can reduce the risk of accidents. Background Technology
[0002] In general, heat stress is known to be influenced by temperature, humidity, exercise load, and adaptation to climate. In hot environments above 25 degrees Celsius, the human body attempts to maintain thermal balance through a mechanism in which it sweats to remove heat from the skin via the evaporation of sweat. Since the efficiency of this mechanism depends on environmental humidity, high humidity reduces the efficiency of the mechanism for cooling by evaporation.
[0003] In addition, the condition of the clothing is also closely related to the efficiency of this mechanism because it restricts airflow around the skin.
[0004] The harmful effects of heat stress on the human body can result in immediate or chronic health consequences. Examples of immediate effects include heatstroke, exhaustion, cramps, and confusion, while examples of chronic effects include intolerance to heat, high blood pressure, heart muscle damage, decreased libido, and erectile dysfunction.
[0005] Representative occupations involving dangerous heat stress include police officers, soldiers, farmers, construction workers, and blast furnace workers.
[0006] In addition to occupational environments, such as those involving firefighters suppressing wildfires, athletes also die from heat stress during training, and many people lose their lives due to heat stress caused by environmental factors like heatwaves. Therefore, to prevent such occupational heat stress and various forms of hazardous situations, a method is required to measure the amount of exposure to heat stress and provide users with advance warnings.
[0007] In particular, periodic detection of heat stress is essential in workplaces exposed to heat stress or when performing tasks involving high heat stress.
[0008] The Wet Bulb Globe Temperature (WBGT) meter, which is widely used, is a useful instrument capable of measuring the amount of direct heat stress. By comparing the temperature of a naturally circulating wet ball with that of a dry ball, it can measure four environmentally important factors: temperature, relative humidity, solar radiation, and airflow. The WBGT index is used as the standard for measuring heat stress in ISO 7243, the working rules for hot environments.
[0009] Heat stress monitoring primarily involves using WBGT systems installed in the workplace. Although these systems can measure environmental impacts, it is difficult to account for individual differences in workload and climate adaptability.
[0010] Recently, research is being conducted on methods to prevent accidents by classifying workers into heat risk groups based on their InBody and environmental data prior to deployment to the workplace, and by monitoring the level of heat stress for each worker. Prior art literature
[65535] Republic of Korea Published Patent Application No. 10-2020-0035844 (Published April 6, 2020) The problem to be solved
[0011] The objective of the present invention is to provide a heat stress monitoring system and a method of operation thereof that can reduce the risk of accidents by classifying each worker performing work in a workplace into high-risk and low-risk groups and monitoring the degree of heat stress according to the classified risk group.
[0012] The purpose of the embodiments of the present disclosure is not limited to the problems mentioned above, and other unmentioned purposes and advantages of the present invention may be understood from the following description and will be more clearly understood by the embodiments of the present invention. Furthermore, it will be understood that the purposes and advantages of the present invention can be realized by the means and combinations thereof set forth in the claims. means of solving the problem
[0013] A heat stress monitoring system according to the present invention comprises: a wearable device worn by a worker; a measuring device for measuring the body parameters of the worker; and a monitoring device that classifies the worker into a high-risk group or a low-risk group based on the heart rate information of the worker stored in the wearable device and the body parameters, calculates the amount of change in metabolic rate based on the worker's metabolic rate and past metabolic rate based on the body parameters, predicts the heat stress output index of the worker through a Case-Based Reasoning (CBR) algorithm that searches for a result corresponding to the amount of change in metabolic rate in a group heat stress output index set for the risk group to which the worker is classified, and transmits the predicted heat stress output index to the wearable device; wherein the monitoring device comprises a communication module that communicates with the wearable device and the measuring device. The apparatus includes a control module that controls the communication module, wherein the control module comprises: a classification unit that classifies whether a person belongs to a high-risk group or a low-risk group based on heart rate information and body parameters; a first calculation unit that calculates the metabolic rate based on body parameters; a second calculation unit that calculates the change in metabolic rate based on the metabolic rate and the past metabolic rate; and a prediction operation unit that sets a group heat stress calculation index corresponding to the risk group classified by the classification unit as a search target and predicts the heat stress calculation index through the case-based reasoning algorithm, wherein if the worker is classified into the high-risk group, the prediction operation unit sets a high-risk group heat stress calculation index set for each change in metabolic rate of other workers belonging to the high-risk group as the search target.If the above worker is classified into the above low-risk group, the low-risk group heat stress calculation indicator, set according to the metabolic rate change amount of each other worker belonging to the above low-risk group, is set as the above search target; the above prediction operation unit calculates the attribute similarity (AS) between a test case including the metabolic rate change amount and a search case included in the above search target, calculates the case similarity (CS) using the attribute similarity (AS) and attribute weight (AW), and selects candidate similar cases according to the case similarity (CS), wherein the case similarity (CS) is calculated by dividing the sum of the values obtained by multiplying the attribute similarity (AS) and attribute weight (AW) for each attribute by the sum of the attribute weights (AW); the above prediction operation unit calculates the predicted value of the heat stress calculation indicator for the above test case by MRA (Multiple Regression Analysis) and ANN (Artificial Neural Network), respectively, and based on the predicted value (PV) and mean absolute percentage error (MAPE) of the MRA and ANN, the MRA prediction range and ANN A prediction range is calculated, and an intersection range in which the MRA prediction range and the ANN prediction range overlap, or an enlarged intersection range obtained by expanding the intersection range by an allowable range index (TR), is set as a filtering range. The prediction operation unit selects a case among the candidate similar cases in which the heat stress calculation index is included in the filtering range as a final similar case, and can calculate the heat stress calculation index including at least one of the worker's workplace temperature and allowable working time based on the heat stress calculation index of the final similar cases.
[0014] Before the worker enters the workplace, the measuring device can measure the body parameters including at least one of the worker's age, height, body weight, skeletal muscle mass, body water content, and body fat percentage.
[0015] delete
[0016] The communication module can communicate with the measurement device and the wearable device via a low-power communication network (LORA) or Bluetooth.
[0017] delete
[0018] The above classification unit can classify into the above high-risk group or the above low-risk group by comparing the amount of change in heart rate according to the above heart rate information and the variable value according to the above body parameter with the set reference amount of change in heart rate and reference variable value.
[0019] The above classification unit may classify as a high-risk group if the change in heart rate is greater than the reference change in heart rate, or if the change in heart rate is less than the reference change in heart rate and the variable value is greater than the reference variable value, and classify as a low-risk group if the change in heart rate is less than the reference change in heart rate and the variable value is less than the reference variable value.
[0020] delete
[0021] delete
[0022] A method of operation of a heat stress monitoring system according to the present invention comprises: a step in which a monitoring device receives physical parameters of a worker measured by a measuring device and heart rate information of the worker stored from a wearable device worn by the worker before the worker enters a workplace; a step in which the monitoring device classifies the worker into a high-risk group or a low-risk group based on the heart rate information and the physical parameters; a step in which the monitoring device calculates the metabolic rate of the worker using the physical parameters; and a step in which the monitoring device calculates the amount of change in metabolic rate based on the metabolic rate and the worker's past metabolic rate. The monitoring device includes the step of predicting the heat stress output indicator of the worker through a Case-Based Reasoning (CBR) algorithm that searches for results corresponding to the change in metabolic rate in the group heat stress output indicator set for the risk group to which the worker is classified, and transmitting the predicted heat stress output indicator to the wearable device; the step of predicting the heat stress output indicator and transmitting it to the wearable device comprises, if the worker is classified into the high-risk group, setting the high-risk group heat stress output indicator set for each change in metabolic rate of other workers belonging to the high-risk group as the search target, and if the worker is classified into the low-risk group, setting the low-risk group heat stress output indicator set for each change in metabolic rate of other workers belonging to the low-risk group as the search target, calculating the attribute similarity (AS) between a test case including the change in metabolic rate and a search case included in the search target, and using the attribute similarity (AS) and attribute weight (AW) to case Calculate the similarity (CS) and select candidate similar cases based on the above case similarity (CS),The above case similarity (CS) is calculated by dividing the sum of the values obtained by multiplying the attribute similarity (AS) and attribute weight (AW) for each attribute by the sum of the attribute weights (AW); the predicted values of the heat stress calculation index for the above test case are each calculated by MRA (Multiple Regression Analysis) and ANN (Artificial Neural Network); the MRA prediction range and the ANN prediction range are calculated based on the respective prediction values (PV) and mean absolute percentage error (MAPE) of the MRA and ANN; the intersection range where the MRA prediction range and the ANN prediction range overlap, or the expanded intersection range obtained by expanding the intersection range by the allowable range index (TR), is set as the filtering range; among the candidate similar cases, cases in which the heat stress calculation index is included in the filtering range are selected as final similar cases; and based on the heat stress calculation index of the final similar cases, the heat stress calculation index including at least one of the worker's workplace temperature and allowable working time can be calculated.
[0023] The step of classifying the above worker into a high-risk group or a low-risk group can be performed by comparing the amount of change in heart rate according to the heart rate information and the variable value according to the body parameter with the set reference amount of change in heart rate and reference variable value to classify the worker into the high-risk group or the low-risk group.
[0024] The step of classifying the above worker into a high-risk group or a low-risk group may be to classify him / her into the high-risk group if the change in heart rate is greater than the reference change in heart rate, or if the change in heart rate is less than the reference change in heart rate and the variable value is greater than the reference variable value, and to classify him / her into the low-risk group if the change in heart rate is less than the reference change in heart rate and the variable value is less than the reference variable value.
[0025] delete Effects of the invention
[0026] The heat stress monitoring system and method of operation according to the present invention have the advantage of preventing safety accidents of workers in advance by classifying whether a worker is in a high-risk group or a low-risk group based on the worker's physical parameters measured before entering the workplace, predicting the worker's metabolic rate, and predicting the degree of heat stress of the worker according to the classified risk group.
[0027] In addition, the heat stress monitoring system and the method of operation according to the present invention have the advantage of preventing safety accidents and increasing work efficiency by predicting a heat stress calculation index representing the degree of heat stress of a worker and transmitting it to the worker, thereby allowing the worker to take a rest according to the heat stress calculation index.
[0028] The effects of the present invention are not limited to those mentioned above, and other unmentioned effects will be clearly understood by a person skilled in the art from the description below. Brief explanation of the drawing
[0029] FIG. 1 is a control block diagram showing the control configuration of a heat stress monitoring system according to a first embodiment of the present invention. Figure 2 is a figure showing an example of a monitoring screen of the monitoring device shown in Figure 1. FIG. 3 is a flowchart illustrating the operation method of a heat stress monitoring system according to a first embodiment of the present invention. FIG. 4 is a control block diagram showing the control configuration of a heat stress monitoring system according to a second embodiment of the present invention. FIG. 5 is a flowchart illustrating the operation method of a heat stress monitoring system according to a second embodiment of the present invention. FIG. 6 is a control block diagram showing the control configuration of a heat stress monitoring system according to a third embodiment of the present invention. FIGS. 7 to 9 are flowcharts illustrating the operation method of a heat stress monitoring system according to a third embodiment of the present invention. Specific details for implementing the invention
[0030] Throughout this disclosure, the same reference numerals denote the same components. This disclosure does not describe all elements of the embodiments, and general content in the art to which this disclosure pertains or content that overlaps between embodiments is omitted. The terms 'part, module, component, block' as used in the specification may be implemented in software or hardware, and depending on the embodiments, a plurality of 'parts, modules, components, blocks' may be implemented as a single component, or a single 'part, module, component, block' may include a plurality of components.
[0031] Throughout the specification, when a part is described as being "connected" to another part, this includes not only cases where they are directly connected but also cases where they are indirectly connected, and indirect connections include connections made via a wireless communication network.
[0032] Furthermore, when it is stated that a part "includes" a certain component, this means that, unless specifically stated otherwise, it does not exclude other components but may include additional components.
[0033] Throughout the specification, when it is stated that a component is located "on" another component, this includes not only cases where a component is in contact with another component, but also cases where another component exists between the two components.
[0034] The terms first, second, etc. are used to distinguish one component from another, and the components are not limited by the aforementioned terms.
[0035] Singular expressions include plural expressions unless there is an obvious exception in the context.
[0036] In each step, identification codes are used for convenience of explanation and do not describe the order of the steps; the steps may be performed differently from the specified order unless a specific order is clearly indicated in the context.
[0037] The operating principles and embodiments of the present disclosure will be described below with reference to the attached drawings.
[0038] FIG. 1 is a control block diagram showing the control configuration of a heat stress monitoring system according to a first embodiment of the present invention.
[0039] Referring to FIG. 1, the heat stress monitoring system (100) may include a wearable device (110), a measuring device (120), and a monitoring device (150).
[0040] The wearable device (110) may be a device worn or carried by a user (hereinafter referred to as "worker"), and may be, for example, a watch-type device, a ring-type device, a necklace-type device, a smart device, etc., but is not limited thereto.
[0041] Here, the wearable device (110) can store heart rate information (hf) regarding the worker's heart rate and heart rate change amount in real time.
[0042] In an embodiment, the heart rate information (hf) may include the heart rate and the amount of heart rate change measured when the worker performed work at the workplace at a past time prior to the current time.
[0043] The wearable device (110) can transmit heart rate information (hf) to the monitoring device (150).
[0044] The measuring device (120) can measure the worker's body parameters (cf) in a space where the worker wears safety equipment, such as a work entrance door or a work waiting room, before the worker enters or exits the workplace.
[0045] That is, the measuring device (120) may be, for example, an InBody device and can measure body parameters (cf) including at least one of the worker's body weight, skeletal muscle mass, body water content, and body fat percentage.
[0046] The measuring device (120) can measure body parameters (cf) and transmit them to the monitoring device (150), such as a unique number that can identify the worker.
[0047] At this time, the measuring device (120) can transmit body parameters (cf) and the unique number to the monitoring device (150) and the low-power communication network (LORA).
[0048] The monitoring device (150) may include a communication module (152) and a control module (154).
[0049] The communication module (152) can communicate with the wearable device (110) and the measurement device (120).
[0050] That is, the communication module (152) receives body parameters (cf) transmitted from the measurement device (120) and transmits them to the control module (154), and can transmit the heat stress calculation index (hf) transmitted from the control module (154) to the wearable device (110).
[0051] In the embodiment, the communication module (152) is shown to perform communication with a low-power communication network (LORA), but it can perform communication with 3G, 4G, and 5G communication systems, and is not limited thereto.
[0052] The control module (154) may include a classification unit (160), first and second calculation units (162, 164) and a prediction operation unit (166).
[0053] The classification unit (160) can classify whether the worker belongs to a high-risk group or a low-risk group based on heart rate information (hf) and body parameters (cf).
[0054] That is, the classification unit (160) can classify into the high-risk group or the low-risk group by using a set classification model, for example, a case-based inference (CBR) algorithm, to compare the change in heart rate according to heart rate information (hf) and the variable value according to body parameter (cf) with the set reference change in heart rate and reference variable value.
[0055] The classification unit (160) can classify the above-mentioned heart rate change amount as a high-risk group if the above-mentioned heart rate change amount is greater than the above-mentioned standard heart rate change amount, or if the above-mentioned heart rate change amount is less than the above-mentioned standard heart rate change amount and the above-mentioned variable value is greater than the above-mentioned standard variable value.
[0056] Additionally, the classification unit (160) can classify the above-mentioned heart rate change amount as smaller than the above-mentioned reference heart rate change amount and the above-mentioned variable value as smaller than the above-mentioned reference variable value as a low-risk group.
[0057] The classification unit (160) can classify the risk group to predict the heat stress output indicator of the worker by classifying whether the worker belongs to the high-risk group or the low-risk group indicating the heat stress risk before the worker enters the workplace.
[0058] The first output unit (162) can calculate the metabolic rate (mr) of the worker based on body parameters (cf).
[0059] That is, the first output unit (162) can calculate the metabolic rate (mr) using at least one of the body weight, skeletal muscle mass, body water content, and body fat percentage included in the body parameters (cf), and the set body information of the worker, e.g., gender, age, height, etc., and a set regression model, e.g., a case-based inference (CBR) algorithm.
[0060] The metabolic rate (MR) can be calculated based on at least one of body weight, skeletal muscle mass, body water content, and body fat percentage, which vary depending on the worker's gender, age, and height.
[0061] The second calculation unit (164) can calculate the metabolic rate (mr) and the change in metabolic rate (dmr) based on the previously calculated past metabolic rate.
[0062] Here, the change in metabolic rate (dmr) may be the change between the aforementioned past metabolic rates and the average change between the metabolic rate (mr) and the aforementioned past metabolic rate calculated immediately prior, but is not limited thereto.
[0063] In addition, the change in metabolic rate (dmr) is the change in metabolic rate per set hour, which can predict an increase in metabolic rate.
[0064] The prediction operation unit (166) can predict a heat stress output index (hp) based on the change in metabolic rate (dmr) and transmit it to a wearable device (110).
[0065] Here, the heat stress output index (hp) may include at least one of the workplace temperature and the allowable working time.
[0066] The above rectal temperature may be the body temperature inside the worker's rectum, and the above work allowance time may represent the future time during which the worker can perform work based on the above rectal temperature.
[0067] When classified as a high-risk group in the classification unit (160), the prediction operation unit (166) can predict the heat stress output index (hp) corresponding to the change in metabolic rate (dmr) in the high-risk group heat stress output index set for each of the other workers belonging to the high-risk group.
[0068] Additionally, if classified as a low-risk group in the classification unit (160), the prediction operation unit (166) can predict the heat stress output index (hp) corresponding to the change in metabolic rate (dmr) in the low-risk group heat stress output index set for each of the other workers belonging to the low-risk group.
[0069] That is, the predictive operation unit (166) can predict the rectal temperature corresponding to the change in metabolic rate (dmr) and the allowable time for the rectal temperature to reach the set reference rectal temperature.
[0070] For example, if the above rectal temperature is 36 ℃ and the above reference rectal temperature is 38 ℃, the prediction operation unit (166) can predict the above allowable operation time through the learned temperature rise time for the above rectal temperature to reach the above reference rectal temperature.
[0071] The prediction operation unit (166) transmits a heat stress calculation index (hp), including the workplace temperature and the allowable working time, to a wearable device (110), thereby allowing the worker to check the heat stress calculation index (hp) and take a rest, which can prevent accidents, i.e., accidents caused by heat-related illnesses.
[0072] For example, the prediction operation unit (166) can predict the heat stress output index (hp) using similar cases retrieved from a case database using the case-based reasoning (CBR) methodology.
[0073] [Table 1] below shows similar cases for the test case.
[0074]
[0075] The rectal temperature of the test case can be calculated from the rectal temperatures included in the heat stress output index (hp) of six similar cases using statistical representative values such as the arithmetic mean, median, mode, and weighted mean. When calculated using the arithmetic mean, the rectal temperature of the test case can be estimated to be 36.67 ℃. Below, the Case-Based Inference (CBR) methodology is briefly explained. The Case-Based Inference (CBR) methodology applied in this invention is a Hybrid CBR methodology that incorporates other quantitative prediction techniques—such as Multiple Regression Analysis (MRA), Artificial Neural Network (ANN), and Genetic Algorithm—which generally exhibit high accuracy and low deviation, into the CBR technique. This is done to improve the general disadvantages of CBR, such as low accuracy and large deviation, while maintaining the advantage of presenting evidence through cases.
[0076] Generally, Case-Based Reasoning (CBR) is a methodology for selecting project cases with high similarity through comparative analysis between projects based on project characteristics. The core of the CBR methodology consists of attribute similarity (AS), attribute weight (AW), and case similarity (CS), and they have the relationship shown in [Equation 1] below. The case similarity (CS) between a real case and a test case can be quantified as the sum of the products of attribute similarities (AS) and attribute weights (AW).
[0077]
[0078] Here, AS is attribute similarity, AW is attribute weight, CS is case similarity, n is the number of attributes, and m is the number of cases.
[0079] Attribute similarity (AS) is calculated for each project characteristic, that is, for each independent variable (in some cases, dependent variables may also be included), based on the difference between independent variables of the same type between the actual case and the test case. If the data of the independent variable is nominal, the attribute similarity is 1 when they are identical and 0 otherwise. If the data of the independent variable is numerical, the attribute similarity (AS) can be expressed as follows [Equation 2].
[0080]
[0081] f AS refers to the attribute similarity calculation formula, and AV Test_Case is a specific attribute value of the test case, and AV Retrieved_Case is a specific attribute value of the retrieved case. f AS MCAS has a value closer to 100% as the attributes become more similar. MCAS is the minimum criterion for scoring the attribute similarity; an attribute similarity value is maintained as valid only if it is higher than the MCAS, otherwise, the value is discarded. MCAS can be set to, for example, 10% and can be optimized as described below.
[0082] Case Similarity (CS) can quantify how similar a test case is to each search case by utilizing the attribute similarity and attribute weights of all independent variables between a test case and a search case, as shown in the following [Equation 3].
[0083]
[0084] f CS is a function for calculating case similarity (CS), and f AW is a function for calculating attribute weights (AW) or the result thereof, and f ASis a function or result that calculates attribute similarity (AS), and n is the number of attributes. Attribute similarity (AS) is calculated as in [Equation 2], and attribute weights (AW) can be determined empirically or optimized mathematically through other optimization methods. Case similarity (CS) can be exemplified by the value obtained by dividing the sum of attribute similarities multiplied by attribute weights by the sum of the weighted attribute similarities.
[0085] In this case, the case selection range (RCS) is a value that determines up to which rank of case similarity (CS) to select as similar cases, and can be optimized by a genetic algorithm.
[0086] The tolerance range index (TR) is a value that defines the ratio for expanding the upper and lower limits of the filtering range, respectively, obtained by overlapping the prediction ranges according to two or more types of prediction techniques, and can likewise be optimized by a genetic algorithm.
[0087] First, the error rate of the dependent variable prediction, e.g., the mean absolute percentage error (MAPE), can be calculated from the difference between the actual values (AV) of the dependent variable and the previously calculated predicted values (PV) in m cases, as shown in [Equation 4] below.
[0088]
[0089] Here f MAPE is a function that calculates MAPE, AV is the actual value of the dependent variable, PV is the predicted value of the dependent variable, and m is the number of cases.
[0090] From the error rate, prediction accuracy (PA) is 1-f MAPE It can be obtained as.
[0091] Since the error rate calculated in this way is based on a large number of actual cases, it is reasonable to assume that the same or similar level of error rate will occur in new test cases if the same methodology is applied. Furthermore, because the error rates of MRA or ANN methodologies are typically smaller than those of CBR methodologies, if the actual value of a case identified as similar by the CBR methodology falls outside the range of predicted values considering the errors of MRA or ANN methodologies—so-called the prediction range—it is desirable to remove that CBR case from the similar case candidate group. In this specification, the setting of a filtering range based on these prediction ranges and the removal of unsuitable CBR cases using it are referred to as filtering.
[0092] The specific filtering operation computes predicted values for each dependent variable for test cases based on at least two quantitative prediction methodologies, such as MRA and ANN.
[0093] Next, based on the previously calculated error rate (MAPE) and the calculated predicted value (PV) of the dependent variable, the predicted ranges (PR) where the actual value may exist are calculated for each forecasting methodology.
[0094] Specifically, for example, the prediction range (PR) in the MRA methodology as shown in the following [Equation 5] MRA ) and prediction range in ANN methodology (PR ANN ) can be defined.
[0095]
[0096] [Equation 5] defines each prediction range (PR) to have an upper and lower limit equal to the mean absolute percentage error (MAPE) centered on each prediction value (PV), but depending on the embodiment, the upper and lower limits may be defined by other parameters.
[0097] The filtering range is determined based on the prediction ranges of at least two quantitative prediction methodologies, such as MRA and ANN. Here, the filtering range is applied to the filtering of search cases to be performed later.
[0098] Specifically, for example, the prediction range of MRA (PR MRA ) and ANN's prediction range (PR ANN The range where the prediction ranges of the two methodologies overlap, i.e., the cross-range, can be determined as the filtering range as shown in the following mathematical equations 6 and 7.
[0099]
[0100] The filtering range (CRMA: cross-range between predicted values of MRA and ANN models) in [Equation 6] is the prediction range of MRA (PR MRA ) and ANN's prediction range (PR ANN It can be exemplarily specified as a cross range between the maximum of the lower limits and the minimum of the upper limits.
[0101]
[0102] The expanded filtering range (CRMA*) of [Equation 7] can be exemplarily specified as an expanded cross-range that is expanded by the allowable range index (TR), namely TRCRMA (TR of CRMA), for the filtering range (CRMA) of [Equation 6].
[0103] The filtering range specified in this way can be applied to cases retrieved through the CBR methodology for the relevant test case.
[0104] The computer determines whether the Average Prediction Accuracy (APA) and Significance Level (SL) for the selected candidate similar types satisfy specific conditions.
[0105] For example, if the significance level (SL) is 5% and the average prediction accuracy (APA) is maximized, the case-based reasoning (CBR) model can be said to be validated.
[0106] Accordingly, if both the Average Predicted Accuracy (APA) condition and the Significance Level (SL) condition are satisfied, a Case-Based Inference (CBR) model can be established with at least one of the Minimum Attribute Similarity criterion, Attribute Weight Range, Case Selection Range, and Acceptance Range Index when the Average Predicted Accuracy and Significance Level satisfy predetermined conditions for the primary or secondary selected candidate similar types. In addition, otherwise, the Minimum Attribute Similarity criterion (MCAS), Attribute Weight Range (RAW), Case Selection Range (RCS), and Acceptance Range Index (TR) can be adjusted.
[0107] According to an embodiment, at least one of the Minimum Attribute Similarity Standard (MCAS), Attribute Weight Range (RAW), Case Selection Range (RCS), and Acceptance Range Index (TR) can be optimized by a genetic algorithm.
[0108] After at least one of the Minimum Attribute Similarity Criterion (MCAS), Attribute Weight Range (RAW), Case Selection Range (RCS), and Acceptance Range Index (TR) is optimized by a genetic algorithm, candidate similar types can be secondarily selected using at least one of the adjusted Minimum Attribute Similarity Criterion, Attribute Weight Range, Case Selection Range, and Acceptance Range Index.
[0109] Subsequently, the process may be repeated for the candidate similar buildings selected in the first or second stage until the average prediction accuracy (APA) and significance level (SL) satisfy all specified conditions.
[0110] Additionally, the monitoring device (150) may further include a display module (158).
[0111] The control module (154) can transmit the heat stress output index (hp) to the display module (158) for each worker.
[0112] At this time, the display module (158) can display the heat stress output index (hp) for each worker, and the monitoring manager can monitor and manage each worker.
[0113] Figure 2 is a figure showing an example of a monitoring screen of the monitoring device shown in Figure 1.
[0114] Referring to FIG. 2, the monitoring device (150) can display at least one of the worker's body parameters (cf), body information, metabolic rate (mr), metabolic rate change amount (dmr), and heat stress output index (hp) on the screen of the display module (158).
[0115] That is, when the monitoring device (150) receives the worker's body parameters (cf) transmitted from the measuring device (120), it can display at least one of the metabolic rate (mr), the change in metabolic rate (dmr), and the heat stress calculation index (hp) calculated based on the preset body information and body parameters (cf) corresponding to the worker on the display module (158).
[0116] Here, the monitoring device (150) can calculate a metabolic rate (mr) by considering at least one of body weight, skeletal muscle mass, body water content, and body fat percentage included in the body parameters (cf), and the body information, e.g., gender, age, height, etc., and the metabolic rate (mr) can be calculated by at least one of body weight, skeletal muscle mass, body water content, and body fat percentage that varies according to the worker's gender, age, and height.
[0117] Subsequently, the monitoring device (150) can calculate the metabolic rate (mr) and the change in metabolic rate (dmr) based on the previously calculated past metabolic rate.
[0118] Here, the change in metabolic rate (dmr) may be the change between the aforementioned past metabolic rates and the average change between the metabolic rate (mr) and the aforementioned past metabolic rate calculated immediately prior, but is not limited thereto.
[0119] In addition, the change in metabolic rate (dmr) is the change in metabolic rate per set hour, which can predict an increase in metabolic rate.
[0120] The monitoring device (150) can predict a heat stress output index (hp), including rectal temperature and working allowable time, based on the change in metabolic rate (dmr) and transmit it to a wearable device (110).
[0121] The monitoring device (150) can predict the rectal temperature set according to the change in metabolic rate (dmr) and the allowable working time until the rectal temperature reaches the set reference rectal temperature.
[0122] FIG. 3 is a flowchart illustrating the operation method of a heat stress monitoring system according to a first embodiment of the present invention.
[0123] Referring to FIG. 3, a monitoring device (150) included in a heat stress monitoring system (100) can receive the worker's body parameters (cf) measured from a measuring device (120) before the worker enters the workplace and the worker's heart rate information (hf) stored from a wearable device (110) worn by the worker (S110).
[0124] That is, the wearable device (110) can store heart rate information (hf) regarding the worker's heart rate and changes in heart rate in real time.
[0125] In an embodiment, the heart rate information (hf) may include the heart rate and the amount of heart rate change measured when the worker performed work at the workplace at a past time prior to the current time.
[0126] The wearable device (110) can transmit heart rate information (hf) to the monitoring device (150).
[0127] The measuring device (120) can measure body parameters (cf), including at least one of the worker's body weight, skeletal muscle mass, body water content, and body fat percentage, and transmit them to the monitoring device (150) before the worker enters the workplace.
[0128] At this time, the communication module (152) included in the monitoring device (150) can communicate with the wearable device (110) and the measurement device (120) via a low-power communication network (LORA) to receive heart rate information (hf) and body parameters (cf).
[0129] The monitoring device (150) can classify the worker into a high-risk group or a low-risk group based on heart rate information (hf) and physical parameters (cf) (S120).
[0130] That is, the control module (154) included in the monitoring device (150) can classify whether the worker belongs to a high-risk group or a low-risk group based on heart rate information (hf) and body parameters (cf).
[0131] The control module (154) can classify into the high-risk group or the low-risk group by using a set classification model, for example, a case-based reasoning (CBR) algorithm, to compare the change in heart rate information (hf) and the variable value according to body parameters (cf) with the set reference change in heart rate and reference variable value.
[0132] The control module (154) can classify the high-risk group if the change in heart rate is greater than the reference change in heart rate, or if the change in heart rate is less than the reference change in heart rate and the variable value is greater than the reference variable value.
[0133] Additionally, the control module (154) can classify the low-risk group if the change in heart rate is smaller than the reference change in heart rate and the variable value is smaller than the reference variable value.
[0134] The control module (154) can classify the risk group to predict the heat stress output indicator of the worker by classifying whether the worker belongs to the high-risk group or the low-risk group indicating the heat stress risk before the worker enters the workplace.
[0135] The monitoring device (150) can calculate the metabolic rate (mr) of the worker based on body parameters (cf) (S130).
[0136] That is, the control module (154) can calculate the metabolic rate (mr) using at least one of body weight, skeletal muscle mass, body water content, and body fat percentage included in the body parameters (cf), and set body information of the worker, e.g., gender, age, height, etc., using a set regression model, e.g., a case-based inference (CBR) algorithm.
[0137] The metabolic rate (MR) can be calculated based on at least one of body weight, skeletal muscle mass, body water content, and body fat percentage, which vary depending on the worker's gender, age, and height.
[0138] The monitoring device (150) can calculate the metabolic rate (mr) and the change in metabolic rate (dmr) based on the past metabolic rate (S140).
[0139] That is, the control module (154) can calculate the metabolic rate (mr) and the change in metabolic rate (dmr) based on the previously calculated past metabolic rate.
[0140] Here, the change in metabolic rate (dmr) may be the change between the aforementioned past metabolic rates and the average change between the metabolic rate (mr) and the aforementioned past metabolic rate calculated immediately prior, but is not limited thereto.
[0141] In addition, the change in metabolic rate (dmr) is the change in metabolic rate per set hour, which can predict an increase in metabolic rate.
[0142] The monitoring device (150) can predict a heat stress output index (hp) corresponding to a change in metabolic rate (dmr) based on a group heat stress output index set for the risk group classified by the worker, and transmit it to a wearable device (110) (S150).
[0143] That is, the control module (154) can predict the heat stress output index (hp) corresponding to the change in metabolic rate (dmr) in the high-risk group heat stress output index set for each of the other workers belonging to the high-risk group when classified as the high-risk group.
[0144] Additionally, the control module (154) can predict the heat stress output index (hp) corresponding to the change in metabolic rate (dmr) in the low-risk group heat stress output index set for each of the other workers belonging to the low-risk group when classified into the low-risk group.
[0145] That is, the control module (154) can predict the corresponding rectal temperature and the allowable working time until the rectal temperature reaches a set reference rectal temperature according to the change in metabolic rate (dmr).
[0146] The control module (154) transmits a heat stress output index (hp), including the workplace temperature and the allowable working time, to a wearable device (110), thereby allowing the worker to check the heat stress output index (hp) and take a rest, which can prevent accidents, i.e., accidents caused by heat-related illnesses.
[0147] The control module (154) can transmit the heat stress output index (hp) to the display module (158) for each worker.
[0148] At this time, the display module (158) can display the heat stress output index (hp) for each worker, and the monitoring manager can monitor and manage each worker.
[0149] FIG. 4 is a control block diagram showing the control configuration of a heat stress monitoring system according to a second embodiment of the present invention.
[0150] Referring to FIG. 4, the heat stress monitoring system (200) may include a wearable device (210), a measuring device (220), a sensor device (230), and a monitoring device (250).
[0151] The wearable device (210) may be a device worn or carried by a user (hereinafter referred to as "worker"), and may be, for example, a watch-type device, a ring-type device, a necklace-type device, a smart device, etc., but is not limited thereto.
[0152] Here, the wearable device (210) can store heart rate information (hf) regarding the worker's heart rate and heart rate change amount in real time.
[0153] In an embodiment, the heart rate information (hf) may include the heart rate and the amount of heart rate change measured when the worker performed work at the workplace at a past time prior to the current time.
[0154] The wearable device (210) can transmit heart rate information (hf) to the monitoring device (250).
[0155] The measuring device (220) can measure the worker's body parameters (cf) in a space where the worker wears safety equipment, such as a work entrance door or a work waiting room, before the worker enters or exits the workplace.
[0156] That is, the measuring device (220) may be, for example, an InBody device and can measure body parameters (cf) including at least one of the worker's body weight, skeletal muscle mass, body water content, and body fat percentage.
[0157] The measuring device (220) can measure body parameters (cf) and transmit them to the monitoring device (250), such as a unique number that can identify the worker.
[0158] At this time, the measuring device (220) can transmit body parameters (cf) and the unique number to the monitoring device (250) and the low-power communication network (LORA).
[0159] The sensor device (230) can measure the environmental information (df) of the workplace and transmit it to the monitoring device (230).
[0160] That is, the sensor device (230) may include sensors capable of measuring the temperature and humidity of the workplace, and may measure wind direction, wind volume, etc. in addition to the temperature and humidity, but is not limited thereto.
[0161] The sensor device (230) can communicate with the monitoring device (250) via a low-power communication network (LORA), just like the wearable device (210).
[0162] The monitoring device (250) may include a communication module (262) and a control module (264).
[0163] The communication module (262) can communicate with the wearable device (210), the measurement device (220), and the sensor device (230).
[0164] That is, the communication module (262) receives heart rate information (hf) transmitted from the wearable device (210), body parameters (cf) transmitted from the measurement device (220), and environmental information (df) transmitted from the sensor device (230), and transmits them to the control module (254), and can transmit the heat stress calculation index (hf) transmitted from the control module (254) to the wearable device (210).
[0165] In the embodiment, the communication module (252), wearable device (210), measurement device (220), and sensor device (230) are shown to communicate via a low-power communication network (LORA), but they can communicate via 3G, 4G, and 5G communication systems, and are not limited thereto.
[0166] The control module (254) may include a classification unit (260), first and second calculation units (262, 264) and a prediction operation unit (266).
[0167] The classification unit (260) can classify whether the worker belongs to a high-risk group or a low-risk group based on heart rate information (hf) and body parameters (cf).
[0168] That is, the classification unit (260) can classify into the high-risk group or the low-risk group by using a set classification model, for example, a case-based inference (CBR) algorithm, to compare the change in heart rate according to heart rate information (hf) and the variable value according to body parameter (cf) with the set reference change in heart rate and reference variable value.
[0169] The classification unit (260) can classify the above-mentioned heart rate change amount as a high-risk group if the above-mentioned heart rate change amount is greater than the above-mentioned reference heart rate change amount, or if the above-mentioned heart rate change amount is smaller than the above-mentioned reference heart rate change amount and the above-mentioned variable value is greater than the above-mentioned reference variable value.
[0170] Additionally, the classification unit (260) can classify the above-mentioned heart rate change amount as smaller than the above-mentioned reference heart rate change amount and the above-mentioned variable value as smaller than the above-mentioned reference variable value as a low-risk group.
[0171] The classification unit (260) can classify the risk group to predict the heat stress output indicator of the worker by classifying whether the worker belongs to the high-risk group or the low-risk group indicating the heat stress risk before the worker enters the workplace.
[0172] The first output unit (262) can calculate the metabolic rate (mr) of a worker based on body parameters (cf) and environmental information (df).
[0173] That is, the first output unit (262) can calculate the metabolic rate (mr) based on the reception time of receiving environmental information (df), the temperature and humidity included in the environmental information (df), and at least one of the body weight, skeletal muscle mass, body water content, and body fat percentage included in the body parameters (cf) using a set regression model, for example, a case-based inference (CBR) algorithm.
[0174] The first calculation unit (262) can predict the temperature and humidity of a future time set at the location coordinates of the workplace based on the reception time, and predict a change in at least one of body weight, skeletal muscle mass, body water content, and body fat percentage according to the predicted temperature and humidity, thereby calculating the metabolic rate (mr) according to the future time.
[0175] That is, the first calculation unit (262) can calculate the metabolic rate (mr) based on the temperature and humidity included in the environmental information (df), taking into account at least one of the body weight, skeletal muscle mass, body water content, and body fat percentage included in the body parameters (cf), and the set body information of the worker, e.g., gender, age, height, etc.
[0176] The second calculation unit (264) can calculate the metabolic rate (mr) and the change in metabolic rate (dmr) based on the previously calculated past metabolic rate.
[0177] Here, the change in metabolic rate (dmr) may be the change between the aforementioned past metabolic rates and the average change between the metabolic rate (mr) and the aforementioned past metabolic rate calculated immediately prior, but is not limited thereto.
[0178] In addition, the change in metabolic rate (dmr) is the change in metabolic rate per set hour, which can predict an increase in metabolic rate.
[0179] The prediction operation unit (266) can predict a heat stress output index (hp) based on the change in metabolic rate (dmr) and transmit it to a wearable device (210).
[0180] Here, the heat stress output index (hp) may include workplace temperature and allowable working time.
[0181] The above rectal temperature may be the body temperature inside the worker's rectum, and the above work allowance time may represent the future time during which the worker can perform work based on the above rectal temperature.
[0182] When classified as a high-risk group in the classification unit (260), the prediction operation unit (266) can predict the heat stress output index (hp) corresponding to the change in metabolic rate (dmr) in the high-risk group heat stress output index set for each of the other workers belonging to the high-risk group.
[0183] Additionally, if classified as a low-risk group in the classification unit (260), the prediction operation unit (266) can predict the heat stress output index (hp) corresponding to the change in metabolic rate (dmr) in the low-risk group heat stress output index set for each of the other workers belonging to the low-risk group.
[0184] The prediction operation unit (266) can predict the rectal temperature corresponding to the change in metabolic rate (dmr) and the allowable time for the rectal temperature to reach a set reference rectal temperature.
[0185] The prediction operation unit (266) transmits a heat stress calculation index (hp), including the workplace temperature and the allowable working time, to a wearable device (210), thereby allowing the worker to check the heat stress calculation index (hp) and take a rest, which can prevent accidents, i.e., accidents caused by heat-related illnesses.
[0186] Additionally, the monitoring device (250) may further include a display module (258).
[0187] The control module (254) can transmit the heat stress output index (hp) to the display module (258) for each worker.
[0188] At this time, the display module (258) can display the heat stress output index (hp) for each worker, and the monitoring manager can monitor and manage each worker.
[0189] FIG. 5 is a flowchart illustrating the operation method of a heat stress monitoring system according to a second embodiment of the present invention.
[0190] Referring to FIG. 5, a monitoring device (230) included in a heat stress monitoring system (200) can receive the worker's body parameters (cf) measured from a measuring device (220) before the worker enters the workplace and the worker's heart rate information (hf) stored from a wearable device (210) worn by the worker (S210).
[0191] That is, the wearable device (210) can store heart rate information (hf) regarding the worker's heart rate and heart rate change amount in real time.
[0192] In an embodiment, the heart rate information (hf) may include the heart rate and the amount of heart rate change measured when the worker performed work at the workplace at a past time prior to the current time.
[0193] The wearable device (210) can transmit heart rate information (hf) to the monitoring device (150).
[0194] The measuring device (220) can measure body parameters (cf), including at least one of the worker's body weight, skeletal muscle mass, body water content, and body fat percentage, and transmit them to the monitoring device (250) before the worker enters the workplace.
[0195] At this time, the communication module (252) included in the monitoring device (250) can communicate with the wearable device (210) and the measurement device (220) via a low-power communication network (LORA) to receive heart rate information (hf) and body parameters (cf).
[0196] The monitoring device (250) can classify the worker into a high-risk group or a low-risk group based on heart rate information (hf) and physical parameters (cf) (S220).
[0197] That is, the control module (254) included in the monitoring device (250) can classify whether the worker belongs to a high-risk group or a low-risk group based on heart rate information (hf) and physical parameters (cf) using a set classification model, for example, a case-based reasoning (CBR) algorithm.
[0198] The control module (254) can classify the high-risk group or the low-risk group by comparing the change in heart rate according to heart rate information (hf) and the variable value according to body parameter (cf) with the set reference change in heart rate and reference variable value.
[0199] The control module (254) can classify the high-risk group if the change in heart rate is greater than the reference change in heart rate, or if the change in heart rate is less than the reference change in heart rate and the variable value is greater than the reference variable value.
[0200] Additionally, the control module (254) can classify the low-risk group if the change in heart rate is smaller than the reference change in heart rate and the variable value is smaller than the reference variable value.
[0201] The control module (254) can classify the risk group to predict the heat stress output indicator of the worker by classifying whether the worker belongs to the high-risk group or the low-risk group indicating the heat stress risk before the worker enters the workplace.
[0202] The monitoring device (250) can receive environmental information (df) transmitted from a sensor device (230) installed in the workplace where the worker is located (S230).
[0203] That is, the communication module (252) can receive environmental information (df) of the workplace through the sensor device (230) and the low-power communication network (LORA).
[0204] At this time, the environmental information (df) may include sensors capable of measuring the temperature and humidity of the workplace, and may further include wind direction, airflow, etc. in addition to the temperature and humidity, but is not limited thereto.
[0205] The monitoring device (250) can calculate the metabolic rate (mr) of the worker based on body parameters (cf) and environmental information (df) (S240).
[0206] That is, the control module (234) included in the monitoring device (230) can calculate the metabolic rate (mr) using a set regression model, for example, a case-based inference (CBR) algorithm, based on the reception time of receiving environmental information (df), the temperature and humidity included in the environmental information (df), and at least one of the body weight, skeletal muscle mass, body water content, and body fat percentage included in the body parameters (cf).
[0207] The control module (234) can predict the temperature and humidity of a future time set at the location coordinates of the workplace based on the received time, and predict the change in heart rate according to the predicted temperature and humidity to calculate the metabolic rate (mr) according to the future time.
[0208] That is, the control module (234) can calculate the metabolic rate (mr) based on the temperature and humidity included in the environmental information (df), taking into account at least one of the body weight, skeletal muscle mass, body water content, and body fat percentage included in the body parameters (cf), and the set body information of the worker, e.g., gender, age, height, etc.
[0209] The monitoring device (250) can calculate the metabolic rate (mr) and the change in metabolic rate (dmr) based on the past metabolic rate (S250).
[0210] That is, the control module (234) can calculate the metabolic rate (mr) and the change in metabolic rate (dmr) based on the previously calculated past metabolic rate.
[0211] Here, the change in metabolic rate (dmr) can be calculated based on the metabolic rate (mr) and the previously calculated past metabolic rate.
[0212] Here, the change in metabolic rate (dmr) may be the change between the aforementioned past metabolic rates and the average change between the metabolic rate (mr) and the aforementioned past metabolic rate calculated immediately prior, but is not limited thereto.
[0213] In addition, the change in metabolic rate (dmr) is the change in metabolic rate per set hour, which can predict an increase in metabolic rate.
[0214] The monitoring device (250) can predict a heat stress output index (hp) corresponding to a change in metabolic rate (dmr) based on a group heat stress output index set for the risk group classified by the worker, and transmit it to a wearable device (210) (S260).
[0215] That is, the control module (254) can predict the heat stress output index (hp) corresponding to the change in metabolic rate (dmr) in the high-risk group heat stress output index set for each of the other workers belonging to the high-risk group when classified as the high-risk group.
[0216] Additionally, the control module (254) can predict the heat stress output index (hp) corresponding to the change in metabolic rate (dmr) in the low-risk group heat stress output index set for each of the other workers belonging to the low-risk group when classified into the low-risk group.
[0217] The control module (254) can predict the corresponding rectal temperature and the allowable working time until the rectal temperature reaches a set reference rectal temperature according to the change in metabolic rate (dmr).
[0218] The control module (254) transmits a heat stress output index (hp), including the workplace temperature and the allowable working time, to a wearable device (110), thereby allowing the worker to check the heat stress output index (hp) and take a rest, which can prevent accidents, i.e., accidents caused by heat-related illnesses.
[0219] Additionally, the monitoring device (250) may further include a display module (258).
[0220] The control module (254) can transmit the heat stress output index (hp) to the display module (258) for each worker.
[0221] At this time, the display module (258) can display the heat stress output index (hp) for each worker, and the monitoring manager can monitor and manage each worker.
[0222] FIG. 6 is a control block diagram showing the control configuration of a heat stress monitoring system according to a third embodiment of the present invention.
[0223] Referring to FIG. 6, the heat stress monitoring system (300) may include a wearable device (310), a measuring device (320), a sensor device (330), an external server (340), and a monitoring device (350).
[0224] The wearable device (310) may be a device worn or carried by a user (hereinafter referred to as "worker"), and may be, for example, a watch-type device, a ring-type device, a necklace-type device, a smart device, etc., but is not limited thereto.
[0225] Here, the wearable device (310) can store heart rate information (hf) regarding the worker's heart rate and heart rate change amount in real time.
[0226] In an embodiment, the heart rate information (hf) may include the heart rate and the amount of heart rate change measured when the worker performed work at the workplace at a past time prior to the current time.
[0227] The wearable device (310) can transmit heart rate information (hf) to the monitoring device (150).
[0228] The measuring device (320) can measure the worker's body parameters (cf) in a space where the worker wears safety equipment, such as a work entrance door or a work waiting room, before the worker enters or exits the workplace.
[0229] That is, the measuring device (320) may be, for example, an InBody device and can measure body parameters (cf) including at least one of the worker's body weight, skeletal muscle mass, body water content, and body fat percentage.
[0230] The measuring device (320) can measure body parameters (cf) and transmit them to the monitoring device (350), such as a unique number that can identify the worker.
[0231] At this time, the measuring device (320) can transmit body parameters (cf) and the unique number to the monitoring device (350) and the low-power communication network (LORA).
[0232] The sensor device (330) can measure the environmental information (df) of the workplace and transmit it to the monitoring device (350).
[0233] That is, the sensor device (330) may include sensors capable of measuring the temperature and humidity of the workplace, and may measure wind direction, wind volume, etc. in addition to the temperature and humidity, but is not limited thereto.
[0234] The sensor device (330) can communicate with the monitoring device (350) via a low-power communication network (LORA), just like the wearable device (310).
[0235] The external server (340) can transmit weather information (pf), including local temperature and local humidity for the area where the workplace is located, to the monitoring device (350).
[0236] The external server (340) may be a weather agency server capable of transmitting weather information (pf), but is not limited thereto.
[0237] The monitoring device (350) may include a communication module (362) and a control module (364).
[0238] The communication module (362) can communicate with the wearable device (310), the measurement device (320), the sensor device (330), and the external server (340).
[0239] That is, the communication module (362) receives heart rate information (hf) transmitted from the wearable device (310), body parameters (cf) transmitted from the measurement device (320), environmental information (df) transmitted from the sensor device (330), and weather information (pf) transmitted from the external server (340), and transmits them to the control module (354), and can transmit the heat stress calculation index (hf) transmitted from the control module (354) to the wearable device (210).
[0240] In the embodiment, the communication module (352), wearable device (310), measurement device (320), sensor device (330) and external server (340) are shown to communicate via a low-power communication network (LORA), but they can communicate via 3G, 4G, and 5G communication systems, and are not limited thereto.
[0241] The control module (354) may include a classification unit (360), first and second calculation units (362, 364) and a prediction operation unit (366).
[0242] The classification unit (360) can classify whether the worker belongs to a high-risk group or a low-risk group based on heart rate information (hf) and body parameters (cf).
[0243] That is, the classification unit (360) can classify into the high-risk group or the low-risk group by using a set classification model, for example, a case-based inference (CBR) algorithm, to compare the change in heart rate according to heart rate information (hf) and the variable value according to body parameter (cf) with the set reference change in heart rate and reference variable value.
[0244] The classification unit (360) can classify the above-mentioned heart rate change amount as a high-risk group if the above-mentioned heart rate change amount is greater than the above-mentioned standard heart rate change amount, or if the above-mentioned heart rate change amount is less than the above-mentioned standard heart rate change amount and the above-mentioned variable value is greater than the above-mentioned standard variable value.
[0245] Additionally, the classification unit (360) can classify the above-mentioned heart rate change amount as smaller than the above-mentioned reference heart rate change amount and the above-mentioned variable value as smaller than the above-mentioned reference variable value as a low-risk group.
[0246] The classification unit (360) can classify the risk group to predict the heat stress output indicator of the worker by classifying whether the worker belongs to the high-risk group or the low-risk group indicating the heat stress risk before the worker enters the workplace.
[0247] The first output unit (362) can calculate the worker's metabolic rate (mr) based on body parameters (cf), environmental information (df) and weather information (pf).
[0248] That is, the first output unit (362) can calculate the metabolic rate (mr) based on at least one of the following: the reception time of receiving environmental information (df), the local temperature and local humidity included in weather information (pf), the temperature and humidity included in environmental information (df), and the body weight, skeletal muscle mass, body water content, and body fat percentage included in body parameters (cf), using a set regression model, for example, a case-based inference (CBR) algorithm.
[0249] First, the first calculation unit (362) can calculate the metabolic rate (mr) based on either weather information (pf) and environmental information (df) and body parameters (cf) if the temperature deviation between the local temperature and the temperature and the humidity deviation between the local humidity and the humidity each fall within the allowed first deviation range.
[0250] Additionally, the first output unit (362) can calculate the metabolic rate (mr) based on environmental information (df) and body parameters (cf) if either of the temperature deviation and the humidity deviation falls within a second deviation range that is higher than the first deviation range.
[0251] Finally, the first calculation unit (362) can determine that the sensor device (320) is malfunctioning if either the temperature deviation or the humidity deviation falls into a third deviation range that is higher than the second deviation range, and can calculate the metabolic rate (mr) based on weather information (pf) and body parameters (cf).
[0252] The first calculation unit (362) can predict the temperature and humidity for the workplace at a future time set at the location coordinates based on the reception time, and predict changes in body parameters (cf) according to the predicted temperature and humidity to calculate the metabolic rate (mr) according to the future time.
[0253] That is, the first calculation unit (362) can calculate the metabolic rate (mr) based on the temperature and humidity included in the environmental information (df) or the local temperature and local humidity included in the weather information (pf), taking into account at least one of the body weight, skeletal muscle mass, body water content, and body fat percentage included in the body parameters (cf) and the set body information of the worker, e.g., gender, age, height, etc.
[0254] The wearable device (310) can transmit biometric information (sf), including the heart rate and location coordinates of the worker working in the workplace, to the monitoring device (350).
[0255] At this time, when the monitoring device (250) receives both biometric information (sf) and body parameters (cf), the first calculation unit (362) included in the monitoring device (250) can calculate the first metabolic rate of the worker based on the body parameters (cf) and environmental information (df), and calculate the second metabolic rate of the worker based on the biometric information (sf) and environmental information (df).
[0256] Afterwards, the first output unit (362) can calculate the average value of the first and second metabolic rates as the metabolic rate (mr).
[0257] The first calculation unit (362) can calculate the second metabolic rate based on the reception time of receiving the bio-information (sf) and environmental information (df), the local temperature and local humidity included in the weather information (pf), the temperature and humidity included in the environmental information (df), and the heart rate and location coordinates included in the bio-information (sf).
[0258] First, the first calculation unit (362) can calculate the second metabolic rate based on either weather information (pf) and environmental information (df) and bio-information (sf) if the temperature deviation between the local temperature and the temperature and the humidity deviation between the local humidity and the humidity each fall within the allowed first deviation range.
[0259] Additionally, the first calculation unit (362) can calculate the second metabolic rate based on environmental information (df) and biological information (sf) if either of the temperature deviation and the humidity deviation falls within a second deviation range that is higher than the first deviation range.
[0260] Finally, the first calculation unit (362) can determine that the sensor device (320) is malfunctioning if either the temperature deviation or the humidity deviation falls into a third deviation range that is higher than the second deviation range, and can calculate the second metabolic rate based on weather information (pf) and bio-information (sf).
[0261] The above first metabolic rate can be calculated in the same way as the metabolic rate (mr) calculated by receiving only body parameters (cf) without receiving bio-information (sf), so the explanation is omitted.
[0262] The second calculation unit (364) can calculate the metabolic rate (mr) and the change in metabolic rate (dmr) based on the previously calculated past metabolic rate.
[0263] Here, the change in metabolic rate (dmr) may be the change between the aforementioned past metabolic rates and the average change between the metabolic rate (mr) and the aforementioned past metabolic rate calculated immediately prior, but is not limited thereto.
[0264] In addition, the change in metabolic rate (dmr) is the change in metabolic rate per set hour, which can predict an increase in metabolic rate.
[0265] The prediction operation unit (366) can predict a heat stress output index (hp) based on the change in metabolic rate (dmr) and transmit it to a wearable device (310).
[0266] Here, the heat stress output index (hp) may include workplace temperature and allowable working time.
[0267] The above rectal temperature may be the body temperature inside the worker's rectum, and the above work allowance time may represent the future time during which the worker can perform work based on the above rectal temperature.
[0268] When classified as a high-risk group in the classification unit (360), the prediction operation unit (366) can predict the heat stress output index (hp) corresponding to the change in metabolic rate (dmr) in the high-risk group heat stress output index set for each of the other workers belonging to the high-risk group.
[0269] Additionally, if classified as a low-risk group in the classification unit (360), the prediction operation unit (366) can predict the heat stress output index (hp) corresponding to the change in metabolic rate (dmr) in the low-risk group heat stress output index set for each of the other workers belonging to the low-risk group.
[0270] The prediction operation unit (366) can predict the rectal temperature corresponding to the change in metabolic rate (dmr) and the allowable time for the rectal temperature to reach the set reference rectal temperature.
[0271] For example, if the above rectal temperature is 36 ℃ and the above reference rectal temperature is 38 ℃, the prediction operation unit (366) can predict the above allowable operation time through the learned temperature rise time for the above rectal temperature to reach the above reference rectal temperature.
[0272] The prediction operation unit (366) transmits a heat stress calculation index (hp), including the workplace temperature and the allowable working time, to a wearable device (310), thereby allowing the worker to check the heat stress calculation index (hp) and take a rest, which can prevent accidents, i.e., accidents caused by heat-related illnesses.
[0273] Additionally, the monitoring device (310) may further include a display module (358).
[0274] The control module (350) can transmit the heat stress output index (hp) to the display module (358) for each worker.
[0275] At this time, the display module (358) can display the heat stress output index (hp) for each worker, and the monitoring manager can monitor and manage each worker.
[0276] FIGS. 7 to 9 are flowcharts illustrating the operation method of a heat stress monitoring system according to a third embodiment of the present invention.
[0277] Referring to FIGS. 7 to 9, a monitoring device (350) included in a heat stress monitoring system (300) can receive the worker's body parameters (cf) measured by a measuring device (320) before the worker enters the workplace and the worker's heart rate information (hf) stored by a wearable device (310) worn by the worker (S310).
[0278] That is, the wearable device (310) can store heart rate information (hf) regarding the worker's heart rate and changes in heart rate in real time.
[0279] In an embodiment, the heart rate information (hf) may include the heart rate and the amount of heart rate change measured when the worker performed work at the workplace at a past time prior to the current time.
[0280] The wearable device (310) can transmit heart rate information (hf) to the monitoring device (350).
[0281] The measuring device (320) can measure body parameters (cf), including at least one of the worker's body weight, skeletal muscle mass, body water content, and body fat percentage, and transmit them to the monitoring device (350) before the worker enters the workplace.
[0282] At this time, the communication module (352) included in the monitoring device (350) can communicate with the wearable device (310) and the measurement device (320) via a low-power communication network (LORA) to receive heart rate information (hf) and body parameters (cf).
[0283] The monitoring device (350) can classify the worker into a high-risk group or a low-risk group based on heart rate information (hf) and physical parameters (cf) (S320).
[0284] That is, the control module (354) included in the monitoring device (350) can classify whether the worker belongs to a high-risk group or a low-risk group based on heart rate information (hf) and body parameters (cf).
[0285] The control module (234) can classify into the high-risk group or the low-risk group by using a set classification model, for example, a case-based reasoning (CBR) algorithm, to compare the change in heart rate information (hf) and the variable value according to body parameters (cf) with the set reference change in heart rate and reference variable value.
[0286] The control module (354) can classify the high-risk group if the change in heart rate is greater than the reference change in heart rate, or if the change in heart rate is less than the reference change in heart rate and the variable value is greater than the reference variable value.
[0287] Additionally, the control module (354) can classify the low-risk group if the change in heart rate is smaller than the reference change in heart rate and the variable value is smaller than the reference variable value.
[0288] The control module (354) can classify the risk group to predict the heat stress output indicator of the worker by classifying whether the worker belongs to the high-risk group or the low-risk group indicating the heat stress risk before the worker enters the workplace.
[0289] The monitoring device (350) can receive environmental information (df) transmitted from a sensor device (330) installed in the workplace where the worker is located (S330).
[0290] That is, the communication module (352) can receive environmental information (df) of the workplace through the sensor device (330) and the low-power communication network (LORA).
[0291] At this time, the environmental information (df) may include sensors capable of measuring the temperature and humidity of the workplace, and may further include wind direction, airflow, etc. in addition to the temperature and humidity, but is not limited thereto.
[0292] The monitoring device (350) can receive weather information (pf) including local temperature and local humidity for the area where the workplace is located, transmitted from an external server (340) (S340).
[0293] The monitoring device (350) can determine whether to receive biometric information (sf) including the heart rate and location coordinates of the worker working in the workplace measured from the wearable device (310) (S350).
[0294] (S350) In the step, if the biological information (sf) is not received, the monitoring device (350) can calculate the temperature difference between the temperature included in the environmental information (df) and the local temperature included in the weather information (pf), and the humidity difference between the humidity included in the environmental information (df) and the local humidity included in the weather information (pf) (S360).
[0295] That is, the control module (354) included in the monitoring device (350) can calculate the temperature deviation by subtracting the local temperature included in the weather information (pf) from the temperature included in the environmental information (df), and can calculate the humidity deviation by subtracting the local humidity included in the weather information (pf) from the humidity included in the environmental information (df).
[0296] At this time, the temperature deviation may output a positive value (+) if the temperature is greater than the local temperature, and the humidity deviation may output a positive value (+) if the humidity is greater than the local humidity.
[0297] The monitoring device (350) determines whether the temperature deviation and the humidity deviation fall within a set first deviation range (S370), and if they fall within the first deviation range, it can calculate the metabolic rate (mr) based on either environmental information (df) and weather information (pf) and body parameters (cf) (S380).
[0298] Additionally, at step (S370), if it does not fall within the first deviation range, the monitoring device (350) determines whether the temperature deviation and the humidity deviation fall within a second deviation range higher than the first deviation range (S390), and if it falls within the second deviation range, it can calculate the first metabolic rate (mr) based on environmental information (df) and body parameters (cf) (S400).
[0299] Additionally, in step (S390), if it does not fall within the second deviation range, the monitoring device (350) confirms that the sensor device (330) is faulty because the temperature deviation and the humidity deviation fall within a third deviation range higher than the second deviation range (S410), and can calculate the first metabolic rate (mr) based on weather information (pf) and body parameters (cf) (S420).
[0300] That is, the control module (354) can calculate a first metabolic rate (mr) based on either weather information (pf) and environmental information (df) and body parameters (cf) when each of the temperature deviation between the local temperature and the temperature and the humidity deviation between the local humidity and the humidity falls within an allowed first deviation range.
[0301] Additionally, the control module (354) can calculate a first metabolic rate (mr) based on environmental information (df) and body parameters (cf) if either of the temperature deviation and the humidity deviation falls within a second deviation range that is higher than the first deviation range.
[0302] Finally, if either the temperature deviation or the humidity deviation falls within a third deviation range higher than the second deviation range, the control module (354) determines that the sensor device (320) is malfunctioning and can calculate a first metabolic rate (mr) based on weather information (pf) and body parameters (cf).
[0303] The control module (354) can predict the temperature and humidity for the workplace at a future time set at the location coordinates based on the reception time, and predict changes in body parameters (cf) according to the predicted temperature and humidity to calculate the first metabolic rate (mr) according to the future time.
[0304] That is, the control module (354) can calculate a first metabolic rate (mr) based on the temperature and humidity included in environmental information (df) or the local temperature and local humidity included in weather information (pf), taking into account at least one of the body weight, skeletal muscle mass, body water content, and body fat percentage included in body parameters (cf) and the set body information of the worker, e.g., gender, age, height, etc.
[0305] (S350) In step, when receiving bio-information (sf), the monitoring device (350) can calculate the temperature difference between the temperature included in the environmental information (df) and the local temperature included in the weather information (pf), and the humidity difference between the humidity included in the environmental information (df) and the local humidity included in the weather information (pf) (S430).
[0306] That is, the control module (354) included in the monitoring device (350) can calculate the temperature deviation by subtracting the local temperature included in the weather information (pf) from the temperature included in the environmental information (df), and can calculate the humidity deviation by subtracting the local humidity included in the weather information (pf) from the humidity included in the environmental information (df).
[0307] At this time, the temperature deviation may output a positive value (+) if the temperature is greater than the local temperature, and the humidity deviation may output a positive value (+) if the humidity is greater than the local humidity.
[0308] The monitoring device (350) determines whether the temperature deviation and the humidity deviation fall within a set first deviation range (S440), and if they fall within the first deviation range, it can calculate a second metabolic rate (mr) based on either environmental information (df) and weather information (pf) and biological information (sf) (S450).
[0309] Additionally, in step (S440), if it does not fall within the first deviation range, the monitoring device (350) determines whether the temperature deviation and the humidity deviation fall within a second deviation range higher than the first deviation range (S460), and if it falls within the second deviation range, it can calculate a second metabolic rate (mr) based on environmental information (df) and biological information (sf) (S470).
[0310] Additionally, in step (S460), if it does not fall within the second deviation range, the monitoring device (350) confirms that the sensor device (330) is faulty because the temperature deviation and the humidity deviation fall within a third deviation range higher than the second deviation range (S480), and can calculate the second metabolic rate (mr) based on weather information (pf) and bio-information (sf) (S490).
[0311] That is, the control module (354) can calculate a second metabolic rate (mr) based on either weather information (pf) and environmental information (df) and bio-information (sf) if the temperature deviation between the local temperature and the temperature and the humidity deviation between the local humidity and the humidity each fall within an allowed first deviation range.
[0312] Additionally, the control module (354) can calculate a second metabolic rate (mr) based on environmental information (df) and biological information (sf) if either of the temperature deviation and the humidity deviation falls within a second deviation range that is higher than the first deviation range.
[0313] Finally, if either the temperature deviation or the humidity deviation falls within a third deviation range higher than the second deviation range, the control module (354) determines that the sensor device (320) is malfunctioning and can calculate a second metabolic rate (mr) based on weather information (pf) and bio-information (sf).
[0314] The control module (354) can predict the temperature and humidity for the workplace at a future time set at the location coordinates based on the reception time, and predict changes in the heart rate and location coordinates included in the bio-information (sf) according to the predicted temperature and humidity to calculate a second metabolic rate (mr) according to the future time.
[0315] That is, the control module (354) can calculate a second metabolic rate (mr) based on the temperature and humidity included in the environmental information (df) or the local temperature and local humidity included in the weather information (pf), taking into account the heart rate included in the bio-information (sf) and the set physical information of the worker, such as gender, age, height, etc.
[0316] The monitoring device (350) can calculate the average value of the first and second metabolic rates or the first metabolic rate as the metabolic rate (mr) (S500), and can calculate the metabolic rate (mr) and the metabolic rate change amount (dmr) based on the past metabolic rate (S510).
[0317] That is, the control module (354) can calculate the metabolic rate (mr) and the change in metabolic rate (dmr) based on the previously calculated past metabolic rate.
[0318] Here, the change in metabolic rate (dmr) may be the change between the aforementioned past metabolic rates and the average change between the metabolic rate (mr) and the aforementioned past metabolic rate calculated immediately prior, but is not limited thereto.
[0319] In addition, the change in metabolic rate (dmr) is the change in metabolic rate per set hour, which can predict an increase in metabolic rate.
[0320] The monitoring device (350) can predict a heat stress output index (hp) corresponding to a change in metabolic rate (dmr) and transmit it to a wearable device (310) (S520).
[0321] That is, the control module (354) can predict the heat stress output index (hp) corresponding to the change in metabolic rate (dmr) in the high-risk group heat stress output index set for each of the other workers belonging to the high-risk group when classified as the high-risk group.
[0322] Additionally, the control module (354) can predict the heat stress output index (hp) corresponding to the change in metabolic rate (dmr) in the low-risk group heat stress output index set for each of the other workers belonging to the low-risk group when classified into the low-risk group.
[0323] Here, the heat stress output index (hp) may include workplace temperature and allowable working time.
[0324] The above rectal temperature may be the body temperature inside the worker's rectum, and the above work allowance time may represent the future time during which the worker can perform work based on the above rectal temperature.
[0325] The control module (354) can predict the corresponding rectal temperature and the allowable working time until the rectal temperature reaches a set reference rectal temperature according to the change in metabolic rate (dmr).
[0326] The control module (354) transmits a heat stress output index (hp), including the workplace temperature and the allowable working time, to a wearable device (310), thereby allowing the worker to check the heat stress output index (hp) and take a rest, which can prevent accidents, i.e., accidents caused by heat-related illnesses.
[0327] The control module (354) can transmit the heat stress output index (hp) to the display module (358) for each worker.
[0328] In FIGS. 7 to 9, step (S320) classifies into high-risk and low-risk groups using a classification model, for example, a case-based inference (CBR) algorithm, and steps (S380), (S400), (S450), and (S470) can calculate metabolic rates using a regression model, for example, a case-based inference (CBR) algorithm.
[0329] At this time, the prediction operation unit (166, 266, 366) can apply the independent variable equally as shown in [Table 1] and finally predict the rectal temperature as the dependent variable.
[0330] At this time, the display module (358) can display the heat stress output index (hp) for each worker, and the monitoring manager can monitor and manage each worker.
[0331] The embodiments according to the present disclosure described above may be implemented in the form of a computer program that can be executed through various components on a computer, and such a computer program may be recorded on a computer-readable medium. In this case, the medium may include a magnetic medium such as a hard disk, a floppy disk, and a magnetic tape, an optical recording medium such as a CD-ROM and a DVD, a magneto-optical medium such as a floptical disk, and a hardware device specifically configured to store and execute program instructions, such as a ROM, RAM, or flash memory.
[0332] Meanwhile, the above computer program may be one specifically designed and configured for the present disclosure, or one known and available to a person skilled in the art of computer software. Examples of computer programs may include machine code, such as that produced by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc.
[0333] In the specification of this disclosure (particularly in the claims), the use of the term "above" and similar descriptive terms may be in both singular and plural. Furthermore, where a range is described in this disclosure, it is to include an invention to which individual values belonging to said range are applied (unless otherwise stated), as is equivalent to describing each individual value constituting said range in the detailed description of the invention.
[0334] Unless explicitly stated otherwise, the steps constituting the method according to the present disclosure may be performed in a suitable order. The present disclosure is not necessarily limited by the order in which the steps are described. The use of any examples or exemplary terms (e.g., etc.) in the present disclosure is merely for the purpose of describing the present disclosure in detail and, unless limited by the claims, the scope of the present disclosure is not limited by such examples or exemplary terms. Furthermore, a person skilled in the art will understand that various modifications, combinations, and changes may be made according to design conditions and factors within the scope of the claims or equivalents to which they are added.
[0335] As described above, the disclosed embodiments have been explained with reference to the attached drawings. Those skilled in the art will understand that the present disclosure may be practiced in forms different from the disclosed embodiments without changing the technical spirit or essential features of the present disclosure. The disclosed embodiments are illustrative and should not be interpreted restrictively.
Claims
Claim 1 A wearable device worn by a worker; a measuring device for measuring the worker's physical parameters; and a monitoring device that classifies the worker into a high-risk group or a low-risk group based on the worker's heart rate information and physical parameters stored in the wearable device, calculates the amount of change in metabolic rate based on the worker's metabolic rate and past metabolic rate based on the physical parameters, predicts the worker's heat stress output index through a Case-Based Reasoning (CBR) algorithm that searches for a result corresponding to the amount of change in metabolic rate in the group heat stress output index set for the risk group to which the worker is classified, and transmits the predicted heat stress output index to the wearable device; wherein the monitoring device includes a communication module that communicates with the wearable device and the measuring device; and a control module that controls the communication module, and the control module includes a classification unit that classifies whether the worker belongs to the high-risk group or the low-risk group based on the heart rate information and physical parameters; A first calculation unit that calculates the metabolic rate based on the above body parameters; a second calculation unit that calculates the change in the metabolic rate based on the above metabolic rate and the above past metabolic rate; and a prediction operation unit that sets a group heat stress calculation indicator corresponding to a risk group classified by the above classification unit as a search target and predicts the heat stress calculation indicator through the above case-based reasoning algorithm, wherein the prediction operation unit sets a high-risk group heat stress calculation indicator set for each change in the metabolic rate of other workers belonging to the high-risk group as the search target when the worker is classified into the above high-risk group, and sets a low-risk group heat stress calculation indicator set for each change in the metabolic rate of other workers belonging to the above low-risk group as the search target when the worker is classified into the above low-risk group.The prediction operation unit calculates the attribute similarity (AS) between a test case including the change in metabolic rate and a search case included in the search target, calculates the case similarity (CS) using the attribute similarity (AS) and attribute weights (AW), and selects candidate similar cases according to the case similarity (CS), wherein the case similarity (CS) is calculated by dividing the sum of the values obtained by multiplying the attribute similarity (AS) and attribute weights (AW) for each attribute by the sum of the attribute weights (AW), and the prediction operation unit calculates the predicted value of the heat stress calculation index for the test case by MRA (Multiple Regression Analysis) and ANN (Artificial Neural Network), respectively, calculates the MRA prediction range and the ANN prediction range based on the prediction values (PV) and the mean absolute percentage error (MAPE) of the MRA and ANN, respectively, sets the intersection range where the MRA prediction range and the ANN prediction range overlap, or the expanded intersection range obtained by expanding the intersection range by the allowable range index (TR), as the filtering range, and the prediction A heat stress monitoring system, wherein the operating unit selects a case among the candidate similar cases in which the heat stress calculation index is included in the filtering range as a final similar case, and calculates the heat stress calculation index including at least one of the worker's workplace temperature and working allowable time based on the heat stress calculation index of the final similar cases. Claim 2 A heat stress monitoring system according to claim 1, wherein, prior to the worker entering the workplace, the measuring device measures the body parameters including at least one of the worker's age, height, body weight, skeletal muscle mass, body water content, and body fat percentage. Claim 3 delete Claim 4 A thermal stress monitoring system according to claim 1, wherein the communication module communicates with the measurement device and the wearable device via a low-power communication network (LORA) or Bluetooth. Claim 5 delete Claim 6 A heat stress monitoring system according to claim 1, wherein the classification unit compares the amount of change in heart rate according to the heart rate information and the variable value according to the body parameter with the set reference amount of change in heart rate and reference variable value to classify into the high-risk group or the low-risk group. Claim 7 A heat stress monitoring system according to claim 6, wherein the classification unit classifies into the high-risk group if the change in heart rate is greater than the reference change in heart rate, or if the change in heart rate is less than the reference change in heart rate and the variable value is greater than the reference variable value, and classifies into the low-risk group if the change in heart rate is less than the reference change in heart rate and the variable value is less than the reference variable value. Claim 8 delete Claim 9 delete Claim 10 A monitoring device receives the worker's body parameters measured by a measuring device and the worker's heart rate information stored by a wearable device worn by the worker prior to the worker entering the workplace; the monitoring device classifies the worker into a high-risk group or a low-risk group based on the heart rate information and the body parameters; the monitoring device calculates the worker's metabolic rate using the body parameters; and the monitoring device calculates the change in metabolic rate based on the metabolic rate and the worker's past metabolic rate. The monitoring device includes the step of predicting the heat stress output indicator of the worker through a Case-Based Reasoning (CBR) algorithm that searches for results corresponding to the change in metabolic rate in the group heat stress output indicator set for the risk group to which the worker is classified, and transmitting the predicted heat stress output indicator to the wearable device; the step of predicting the heat stress output indicator and transmitting it to the wearable device comprises, if the worker is classified into the high-risk group, setting the high-risk group heat stress output indicator set for each change in metabolic rate of other workers belonging to the high-risk group as the search target, and if the worker is classified into the low-risk group, setting the low-risk group heat stress output indicator set for each change in metabolic rate of other workers belonging to the low-risk group as the search target, calculating the attribute similarity (AS) between a test case including the change in metabolic rate and a search case included in the search target, and using the attribute similarity (AS) and attribute weight (AW) to case Calculate the similarity (CS) and select candidate similar cases based on the above case similarity (CS),A method of operation of a heat stress monitoring system, wherein the above case similarity (CS) is calculated by dividing the sum of the values obtained by multiplying the attribute similarity (AS) and attribute weight (AW) for each attribute by the sum of the attribute weights (AW); the predicted value of the heat stress output indicator for the above test case is calculated by MRA (Multiple Regression Analysis) and ANN (Artificial Neural Network), respectively; the MRA prediction range and the ANN prediction range are calculated based on the prediction value (PV) and the mean absolute percentage error (MAPE) of the MRA and ANN, respectively; the filtering range is set as an intersection range where the MRA prediction range and the ANN prediction range overlap, or an expanded intersection range obtained by expanding the intersection range by an allowable range index (TR); among the above candidate similar cases, cases in which the heat stress output indicator is included in the filtering range are selected as final similar cases; and the heat stress output indicator, which includes at least one of the worker's workplace temperature and allowable working time, is calculated based on the heat stress output indicators of the above final similar cases. Claim 11 In claim 10, the step of classifying the worker into a high-risk group or a low-risk group comprises comparing the amount of change in heart rate according to the heart rate information and the variable value according to the body parameter with the set reference amount of change in heart rate and reference variable value to classify the worker into the high-risk group or the low-risk group. Claim 12 A method of operation of a heat stress monitoring system, wherein the step of classifying the worker into a high-risk group or a low-risk group comprises classifying the worker into the high-risk group if the change in heart rate is greater than the reference change in heart rate, or if the change in heart rate is less than the reference change in heart rate and the variable value is greater than the reference variable value, and classifying the worker into the low-risk group if the change in heart rate is less than the reference change in heart rate and the variable value is less than the reference variable value. Claim 13 delete
Citation Information
Patent Citations
System and method for managing heat stress using the same
KR1020070060968A
Predictive Systems for Body Activities and Overall Stress Index
KR1020120053481A
Stress management apparatus for the emotional worker and operation method thereof
KR1020200080494A
Helmet for monitoring worker and working environment and work site monitoring system using it
KR1020200095630A
Method of monitoring user's disease based on heart rate information and server performing the same
KR102462245B1
