Device and method for integrated monitoring of aquatic ecosystem based on IoT technology and machine learning technology

Abstract

The present invention relates to a device and a method for integrated monitoring of an aquatic ecosystem based on IoT technology and machine learning technology. The device comprises: an underwater state monitoring unit for acquiring water quality information, aquatic organism community information, and habitat state information through a mobile monitoring device and a fixed monitoring device remotely installed underwater, and then wirelessly transmitting the acquired information using an IoT communication method; an environment monitoring unit for collecting environment information by accessing an external environment monitoring device via the Internet; a data collection unit for preprocessing the water quality information, the aquatic organism community information, the habitat state information, and the environment information into a data form recognizable by a machine learning model, and then collecting and storing the preprocessed data as aquatic ecosystem information; a data analysis unit including a machine learning model in which a correlation between aquatic ecosystem information and aquatic ecosystem health state has been pre-trained, the data analysis unit predicting an aquatic ecosystem health state corresponding to currently acquired aquatic ecosystem information through the machine learning model and then providing guidance to a user; and a power supply unit for generating driving power from commercial power and directly supplying the driving power to the data collection unit and the data analysis unit through an internal power line, and wirelessly supplying the driving power to the underwater state monitoring unit through Power over Ethernet communication.

Description

Integrated aquatic ecosystem monitoring device and method based on IoT technology and machine learning technology

[0001] The present invention relates to an integrated aquatic ecosystem monitoring device and method that solves power supply problems while enabling simpler and more accurate monitoring of the aquatic ecosystem status in a remote location using IoT technology and machine learning technology.

[0002] Aquatic ecosystem monitoring is an activity that observes and evaluates the state and changes of aquatic ecosystems, such as rivers, lakes, wetlands, and oceans. It is utilized to determine the health status of ecosystems by investigating water quality, biodiversity, and pollution levels, and to assess the impact of environmental changes or human activities.

[0003] However, conventional methods for analyzing and predicting information for monitoring aquatic ecosystems have been performed using numerical modeling, which has problems such as limitations on development and input due to the need for vast input data, specialized knowledge and experience, and integrated data, and requires observational data that requires a lot of time and effort for accurate analysis and prediction of aquatic ecosystems, which have three-dimensional spatial dynamics and characteristics of mutually organic changes.

[0004] In addition, it has the problem that long-term use is impossible due to limited power supply, and data collection and analysis are not performed in real time.

[0005] Therefore, there are limitations in formulating effective and realistic countermeasures because it is difficult to conduct timely analysis and future predictions regarding major issues in the marine environment and ecosystem, such as interactions between environmental factors, hypoxia, the appearance of harmful substances like red tides, and water quality deterioration.

[0006] Accordingly, in order to solve the aforementioned problems, the present invention relates to an integrated aquatic ecosystem monitoring device and method that enables more simple and accurate monitoring of the aquatic ecosystem status in a remote location.

[0007] In addition, this relates to an integrated aquatic ecosystem monitoring device and method based on IoT technology and machine learning technology that enables direct power supply to a remote location.

[0008] The objectives of the present invention are not limited to those mentioned above, and other unmentioned objectives will be clearly understood by those skilled in the art to which the present invention pertains from the description below.

[0009] As a means to solve the above problem, according to one embodiment of the present invention, an underwater state monitoring unit acquires water quality information, aquatic organism community information, and habitat status information through a mobile monitoring device and a fixed monitoring device remotely installed underwater, and then wirelessly transmits them via an IoT communication method; an environmental monitoring unit collects environmental information by connecting to the Internet of an external environmental monitoring device; a data collection unit preprocesses the water quality information, the aquatic organism community information, the habitat status information, and the environmental information into a data format recognizable by a machine learning model, and then aggregates and stores them as aquatic ecosystem information; and a data analysis unit equipped with a machine learning model having a correlation between aquatic ecosystem information and aquatic ecosystem health status that has been pre-learned, and then predicts the aquatic ecosystem health status corresponding to the currently acquired aquatic ecosystem information through the machine learning model and provides guidance to the user. An integrated aquatic ecosystem monitoring device based on IoT technology and machine learning technology is provided, comprising a power supply unit that generates driving power through commercial power and supplies it directly to the data collection unit and the data analysis unit via internal power lines, while wirelessly supplying driving power to the underwater state monitoring unit via a Power over Ethernet communication method.

[0010] The above-described mobile monitoring device is characterized by including at least one of an underwater drone equipped with a camera, sonar, and a water quality sensor.

[0011] The above fixed monitoring device is characterized by including at least one of an underwater camera, sonar, and a water quality sensor.

[0012] The above machine learning model is characterized by the fact that the correlation between aquatic ecosystem information and aquatic ecosystem health status is pre-learned through multiple training data that have aquatic ecosystem information as input conditions and aquatic ecosystem health status as output conditions.

[0013] The above data analysis unit is characterized by further including a function that supports the search and viewing of aquatic ecosystem information.

[0014] In addition, the above data analysis unit is characterized by pre-defining the normal range value for each piece of information included in the aquatic ecosystem information, and further including a function to provide guidance on information that deviates from the normal range value.

[0015] In addition, the data analysis unit further includes a function to notify the user of the occurrence of an event when aquatic ecosystem information satisfying the event detection condition is obtained, after pre-defining at least one event detection condition.

[0016]

[0017] As a means to solve the above problem, according to another embodiment of the present invention, a method for integrated monitoring of an aquatic ecosystem based on IoT technology and machine learning technology is provided, comprising the steps of: wirelessly supplying driving power to a mobile monitoring device and a fixed monitoring device remotely installed underwater to drive them, and then receiving water quality information, aquatic organism community information, and habitat status information acquired by the mobile monitoring device and the fixed monitoring device via an IoT communication method; connecting to the internet of an external environmental monitoring device to acquire environmental information; preprocessing each of the water quality information, aquatic organism community information, habitat status information, and environmental information and then compiling them into aquatic ecosystem information; and analyzing the aquatic ecosystem information through a machine learning model in which the correlation between the aquatic ecosystem information and the aquatic ecosystem health status is pre-trained to predict the aquatic ecosystem health status and then providing guidance to the user.

[0018] The present invention enables more simple and accurate monitoring of aquatic ecosystem information in remote areas using IoT technology and machine learning technology, thereby significantly reducing the effort and cost required for system implementation and maintenance.

[0019] In addition, by directly supplying driving power to mobile and fixed monitoring devices located in remote areas through the Power over Ethernet communication method, it ensures stable operation of the mobile and fixed monitoring devices.

[0020] FIG. 1 is a diagram illustrating an aquatic ecosystem integrated monitoring device based on IoT technology and machine learning technology according to one embodiment of the present invention.

[0021] FIG. 2 is a diagram illustrating the configuration of a mobile monitoring device according to one embodiment of the present invention.

[0022] FIG. 3 is a diagram illustrating the configuration of a fixed monitoring device according to one embodiment of the present invention.

[0023] FIG. 4 is a diagram illustrating an integrated aquatic ecosystem monitoring method based on IoT technology and machine learning technology according to an embodiment of the present invention.

[0024] Before specifically describing the present disclosure, the method of description in the specification and drawings is described.

[0025] First, the terms used in this specification and claims have been selected based on general terms considering their functions in the various embodiments of this disclosure. However, these terms may vary depending on the intent of those skilled in the art, legal or technical interpretations, and the emergence of new technologies. Additionally, some terms have been arbitrarily selected by the applicant. Such terms may be interpreted according to the meanings defined in this specification; in the absence of specific definitions, they may be interpreted based on the overall content of this specification and common technical knowledge in the relevant field.

[0026] In addition, the same reference numbers or symbols described in each drawing attached to this specification represent parts or components that perform substantially the same function. For convenience of explanation and understanding, the same reference numbers or symbols are used to describe different embodiments. That is, even if components having the same reference number are all depicted in multiple drawings, the multiple drawings do not imply a single embodiment.

[0027] Additionally, in this specification and claims, terms including ordinal numbers, such as "first," "second," etc., may be used to distinguish between components. These ordinal numbers are used to distinguish identical or similar components from one another, and the meaning of the terms should not be limited by the use of such ordinal numbers. For example, the order of use or arrangement of components combined with such ordinal numbers should not be restricted by the number. If necessary, each ordinal number may be used interchangeably.

[0028] In this specification, singular expressions include plural expressions unless the context clearly indicates otherwise. In this application, terms such as "comprising" or "consisting of" are intended to specify the existence of the features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, and should be understood as not precluding the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.

[0029] In the embodiments of the present disclosure, terms such as "module," "unit," "part," etc. are used to refer to a component that performs at least one function or operation, and such component may be implemented in hardware or software, or a combination of hardware and software. Additionally, a plurality of "modules," "units," "parts," etc. may be integrated into at least one part or chip and implemented as at least one processor, except where each needs to be implemented in specific individual hardware.

[0030] Furthermore, in the embodiments of the present disclosure, when a part is described as being connected to another part, this includes not only a direct connection but also an indirect connection through another medium. Additionally, the meaning that a part includes a certain component implies that, unless specifically stated otherwise, it does not exclude other components but may include additional components.

[0031]

[0032] FIGS. 1 to 3 are drawings illustrating an aquatic ecosystem integrated monitoring device based on IoT technology and machine learning technology according to an embodiment of the present invention, where FIG. 1 shows the overall configuration of the aquatic ecosystem integrated monitoring device, FIG. 2 shows a mobile monitoring device, and FIG. 3 shows a fixed monitoring device.

[0033] As illustrated in FIG. 1, the device of the present invention includes an underwater state monitoring unit (100), an environment monitoring unit (200), a data collection unit (300), a data analysis unit (400), and a power supply unit (500), etc.

[0034]

[0035] The underwater condition monitoring unit (100) is equipped with a mobile monitoring device (110) and a fixed monitoring device (120) installed underwater, and acquires water quality information, aquatic organism community information, and habitat condition information of a target location through these devices and then transmits them wirelessly via IoT communication.

[0036] At this time, the IoT communication method can be implemented using Wi-Fi, Bluetooth and BLE (Bluetooth Low Energy), LoRa (Long Range), NB-IoT (Narrowband IoT), Zigbee, Sigfox, etc., and can be selected and used according to requirements such as usage environment, power consumption, data transmission volume, and distance.

[0037] In addition, water quality information includes information on dissolved oxygen (DO), biochemical oxygen demand (BOD), chemical oxygen demand (COD), hydrogen ion concentration (pH), turbidity, nutrients, etc., and aquatic community information includes information on the types of aquatic organisms, community density, behavioral patterns, etc., and habitat status information may include information on underwater depth, underwater topography, etc., but is not limited thereto.

[0038]

[0039] A mobile monitoring device (110) is a device that collects at least one of water quality information, aquatic organism community information, and habitat status information while moving underwater, and may be equipped with at least one of an underwater drone (111), sonar (112), and water quality sensor (113) as shown in FIG. 2.

[0040] The underwater drone (111) is a mobile body capable of moving underwater and is equipped with a camera (111a) for capturing an image of a target location, an image processing unit (model (M)) for analyzing the captured image, and an IoT communication unit (111c) for wirelessly transmitting the image processing result via IoT communication.

[0041] That is, based on an image of a target location, aquatic organisms such as fish, aquatic plants, and benthic organisms are detected, and the movement trajectory of each aquatic organism is tracked and monitored to obtain aquatic organism community information including the type and number of aquatic organisms, behavioral patterns, and community status, and wirelessly transmit it to a data collection unit (300) located at a remote location.

[0042] Sonar (112) uses sound waves to measure the distance and direction to the underwater bottom, thereby obtaining habitat condition information including underwater depth, underwater topography, etc.

[0043] The water quality sensor (113) is equipped with a water temperature sensor, a salinity sensor, a turbidity sensor, a pH sensor, an oxygen sensor, etc., and uses these sensors to sense and collect water temperature, salinity, turbidity, pH, oxygen density, etc., to generate and output water quality information.

[0044] At this time, the sonar (112) and water quality sensor (113) are implemented in a form attached to the underwater drone (111) so that they can move together with the underwater drone (111). Additionally, the sonar (112) and water quality sensor (113) may have a separate IoT communication unit to wirelessly transmit acquired information to the data collection unit (300), but if necessary, they may also wirelessly transmit to the data collection unit (300) using the IoT communication unit (111c) of the underwater drone (111).

[0045]

[0046] Unlike the mobile monitoring device (110), the fixed monitoring device (120) is fixedly installed at a specific location and is also equipped with at least one of a camera (121), a sonar (122), and a water quality sensor (123) and an IoT communication unit (124) so ​​that it can collect at least one of water quality information, aquatic organism community information, and habitat status information of a target location and then wirelessly transmit it to the data collection unit (300).

[0047]

[0048] The environmental monitoring unit (200) connects to an external data server via the Internet to obtain additional environmental information regarding the target location. At this time, the environmental information may include information regarding the season, weather, river flow, inflow of pollutants, etc., but is not limited thereto.

[0049]

[0050] The data collection unit (300) preprocesses the information wirelessly transmitted by the underwater state monitoring unit (100) via IoT communication and the information acquired by the environment monitoring unit (200) into a data format recognizable by each machine learning model (M), and then collects and stores them as aquatic ecosystem information.

[0051] In this case, data preprocessing improves the quality and consistency of the data and enables the machine learning model (M) to learn and analyze more efficiently and accurately. It may be performed through at least one of the following operations: missing value processing, outlier removal, data normalization and standardization, and feature extraction, but is not limited thereto.

[0052]

[0053] The data analysis unit (400) has a machine learning model (M) that has been pre-learned of the correlation between aquatic ecosystem information and the health status of the aquatic ecosystem.

[0054] The machine learning model (M) is implemented as a recurrent neural network (RNN), a convolutional neural network (CNN), a graph neural network (GNN), or a mixed model, and is capable of pre-learning the correlation between aquatic ecosystem information and aquatic ecosystem health status by repeatedly deep learning large-scale training data that has aquatic ecosystem information as input conditions and aquatic ecosystem health status as output conditions. Then, through the machine learning model (M), the aquatic ecosystem health status corresponding to the currently acquired aquatic ecosystem information is classified into Healthy, Moderate, Degraded, etc., and then the user is informed of this.

[0055]

[0056] The power supply unit (500) generates driving power through commercial power and supplies it directly to the environment monitoring unit (200), data collection unit (300), and data analysis unit (400) through internal power lines.

[0057] In addition, by wirelessly supplying driving power to an underwater state monitoring unit (100) located at a remote location through a Power over Ethernet communication method, the underwater state monitoring unit (100) can stably secure the power required for operation without having to provide a separate power supply device.

[0058]

[0059] FIG. 4 is a diagram illustrating an integrated aquatic ecosystem monitoring method based on IoT technology and machine learning technology according to an embodiment of the present invention.

[0060] First, the mobile monitoring device (110) and the fixed monitoring device (120), which are remotely installed underwater, are powered wirelessly by supplying power via a Power over Ethernet communication method. When the mobile monitoring device (110) and the fixed monitoring device (120) start to operate and wirelessly transmit water quality information, aquatic organism community information, and habitat status information via an IoT communication method, the information is received and stored via an IoT communication method (S1, S2).

[0061] While performing steps S1 and S2, an external environment monitoring device is connected to the Internet to additionally obtain and store environment information of the target location (S3).

[0062] Then, each piece of information obtained through steps S1 to S3 is preprocessed into a data format recognizable by a machine learning model (M) and combined into a single piece of aquatic ecosystem information. Then, the aquatic ecosystem information is analyzed through the machine learning model (M) to predict whether the current health status of the aquatic ecosystem belongs to Healthy, Moderate, or Degraded, and this is provided to the user (S4).

[0063]

[0064] In addition, the present invention supports the search and viewing of aquatic ecosystem information obtained through a mobile monitoring device (110), a fixed monitoring device (120), and an environment monitoring unit (200), in addition to the aquatic ecosystem health status analyzed by a machine learning model (M), thereby enabling the user to verify the basis for judging the aquatic ecosystem health status.

[0065] In particular, user convenience can be maximized by providing aquatic ecosystem information in the form of raw data or edited and provided in the form of graphics, tables, etc., as needed.

[0066]

[0067] In addition, the present invention predefines a normal range value for each piece of information included in the aquatic ecosystem information and provides guidance on information that deviates from the normal range value, or predefines at least one event detection condition and notifies the user of the occurrence of an event whenever aquatic ecosystem information satisfying the event detection condition is acquired.

[0068] In other words, the present invention goes beyond simply dividing the health status of an aquatic ecosystem into three stages—Healthy, Moderate, and Degraded—to provide a general overview, and further enables the user to confirm and be notified of the occurrence of a state of interest in detail.

[0069]

[0070] Meanwhile, the various embodiments described above may be implemented in a recording medium readable by a computer or a similar device using software, hardware, or a combination thereof.

[0071] According to hardware implementation, the embodiments described in this disclosure may be implemented using at least one of ASICs (Application Specific Integrated Circuits), DSPs (digital signal processors), DSPDs (digital signal processing devices), PLDs (programmable logic devices), FPGAs (field programmable gate arrays), processors, controllers, microcontrollers, microprocessors, and other electrical units for performing functions.

[0072] In some cases, the embodiments described herein may be implemented as the processor itself. In a software implementation, embodiments such as the procedures and functions described herein may be implemented as separate software parts. Each of the aforementioned software parts may perform one or more functions and operations described herein.

[0073] Meanwhile, computer instructions for performing processing operations in electronic devices, etc., according to the various embodiments of the present disclosure described above may be stored in a non-transitory computer-readable medium. When computer instructions stored in such a non-transitory computer-readable medium are executed by a processor of a specific device, they cause the specific device described above to perform processing operations according to the various embodiments described above.

[0074] A non-transient computer-readable medium refers to a medium that stores data semi-permanently and can be read by a device, unlike media that store data for a short period of time such as registers, caches, and memory. Specific examples of non-transient computer-readable media include CDs, DVDs, hard disks, Blu-ray discs, USBs, memory cards, and ROMs.

[0075] Although preferred embodiments of the present disclosure have been illustrated and described above, the present disclosure is not limited to the specific embodiments described above. It is understood that various modifications can be made by those skilled in the art without departing from the essence of the present disclosure as claimed in the claims, and such modifications should not be understood individually from the technical spirit or perspective of the present disclosure.

[0076] 100: Underwater condition monitoring unit

[0077] 110: Mobile monitoring device

[0078] 111 : Underwater Drone

[0079] 112: Sona

[0080] 113: Water quality sensor

[0081] 120 : Fixed monitoring device

[0082] 121 : Underwater Drone

[0083] 122: Sona

[0084] 123: Water quality sensor

[0085] 124: IOT Communications Department

[0086] 200 : Environmental Monitoring Department

[0087] 300: Data Collection Unit

[0088] 400: Data Analysis Department

[0089] 500: Power supply

Claims

1. An underwater condition monitoring unit that acquires water quality information, aquatic organism community information, and habitat status information through a mobile monitoring device and a fixed monitoring device remotely installed underwater, and then wirelessly transmits them using an IoT communication method; An environmental monitoring unit that collects environmental information by connecting to an external environmental monitoring device via the Internet; A data collection unit that preprocesses the above water quality information, the above aquatic organism community information, the above habitat status information, and the above environmental information into a data format recognizable by a machine learning model, and then collects and stores them as aquatic ecosystem information; A data analysis unit equipped with a machine learning model that has been pre-trained on the correlation between aquatic ecosystem information and the health status of an aquatic ecosystem, and which predicts the health status of an aquatic ecosystem corresponding to the currently acquired aquatic ecosystem information through the machine learning model and then provides guidance to the user; and An aquatic ecosystem integrated monitoring device based on IoT technology and machine learning technology, comprising a power supply unit that generates driving power through commercial power and supplies it directly to the data collection unit and the data analysis unit through internal power lines, while wirelessly supplying driving power to the underwater state monitoring unit via a Power over Ethernet communication method.

2. In paragraph 1, the mobile monitoring device An aquatic ecosystem integrated monitoring device based on IoT technology and machine learning technology, characterized by including at least one of an underwater drone equipped with a camera, sonar, and a water quality sensor.

3. In paragraph 1, the fixed monitoring device An aquatic ecosystem integrated monitoring device based on IoT technology and machine learning technology, characterized by including at least one of an underwater camera, sonar, and a water quality sensor.

4. In paragraph 1, the machine learning model An integrated aquatic ecosystem monitoring device based on IoT technology and machine learning technology, characterized by pre-learning the correlation between aquatic ecosystem information and aquatic ecosystem health status through multiple learning data that have aquatic ecosystem information as input conditions and aquatic ecosystem health status as output conditions.

5. In paragraph 1, the data analysis unit An integrated aquatic ecosystem monitoring device based on IoT technology and machine learning technology, characterized by further including a function that supports the search and viewing of aquatic ecosystem information.

6. In paragraph 1, the data analysis unit An integrated aquatic ecosystem monitoring device based on IoT technology and machine learning technology, characterized by pre-defining normal range values ​​for each piece of information included in aquatic ecosystem information and further including a function to provide guidance on information that deviates from the normal range values.

7. In paragraph 1, the data analysis unit An integrated aquatic ecosystem monitoring device based on IoT technology and machine learning technology, characterized by further including a function to notify a user of the occurrence of an event when aquatic ecosystem information satisfying the event detection condition is obtained, after pre-defining at least one event detection condition.

8. A step of wirelessly supplying power to a mobile monitoring device and a fixed monitoring device remotely installed underwater to operate them, and then wirelessly receiving water quality information, aquatic organism community information, and habitat status information acquired by the mobile monitoring device and the fixed monitoring device via IoT communication; A step of obtaining environmental information by connecting to the internet of an external environmental monitoring device; A step of preprocessing each of the above water quality information, above aquatic organism community information, above habitat status information, and above environmental information, and then combining them as aquatic ecosystem information; and An integrated aquatic ecosystem monitoring method based on IoT technology and machine learning technology, comprising the step of predicting the aquatic ecosystem health status by analyzing the above aquatic ecosystem information through a machine learning model in which the correlation between the aquatic ecosystem information and the aquatic ecosystem health status is pre-trained, and then providing guidance to the user.

Images