121 results about "Feedback analysis" patented technology

The present invention provides a system and a method for real time monitoring and identifying defects occurring in a three dimensional object build via an additive manufacturing process. Further, the present invention provides in-situ correction of such defects by a plurality of functional tool heads possessing freedom of motion in arbitrary planes and approach, where the functional tool heads are automatically and independently controlled based on a feedback analysis from the printing process, implementing analyzing techniques. Furthermore, the present invention provides a mechanism for analyzing defected data collected from detection devices and correcting tool path instructions and object model in-situ during construction of a 3D object. A build report is also generated that displays, in 3D space, the structural geometry and inherent properties of a final build object along with the features of corrected and uncorrected defects. Advantageously, the build report helps in improving 3D printing process for subsequent objects.

The invention discloses a classroom quality bi-directional evaluation system based on depth learning, which comprises a classroom terminal, a teacher terminal, an educational administration terminal,a student terminal and a cloud server. The teacher terminal collects, processes and sends classroom pictures and videos. The teacher terminal sends text information and images to the cloud server to release the job, notify the examination time and place, and receive and display the analysis results. The educational administration terminal receives and displays the basic information of each teacher's class, history teaching situation and students' learning situation; The student terminal receives and displays the notification of class assignment, the notification of examination time and place,the individual classroom performance and the teaching quality evaluation results of each teacher. Based on the received classroom pictures and frames, the cloud server uses the object detection model,face detection model and face segmentation model to analyze the attendance, the listening rate, classroom behaviors, classroom expression, classroom seating and feedback analysis results.

The invention discloses a quick feedback analyzing system in a tunnel constructing process. The system adopts a scheme: understanding currently adopted designing construction parameters; establishing a tunnel excavation three-dimensional finite element numerical grid calculation model; acquiring surrounding rock layering and convergent displacement monitoring information after a tunnel is excavated; establishing a non-linear support vector machine model; fixing an anchoring parameter according to the actual construction parameter, and optimally identifying rock mechanic parameters by adoptinga differential optimization algorithm; optimizing the construction parameter of an anchoring scheme by adopting a differential evolution algorithm; and optimizing the rock mechanic parameters by calling the differential evolution and optimization algorithms to further solve the construction parameter of the anchoring scheme, and outputting the construction parameter of the optimized anchoring scheme as a construction scheme through a computer display screen to guide the constructors to construct. The quick feedback analyzing system ensures that the monitoring information is used for optimizing the anchoring parameter while being used for identifying the surrounding rock parameters, so that the dynamic information construction is improved to a level of quantitative analysis.

A consulting system helps a user on collecting information, building object model, and creating virtual environment, produces animated images, captures feedback from the user, analyzes user's response, and provides advices in various formats. First, the system provides interfaces for guiding the user to collect, manipulate, organize, search, and retrieve advices and their related examples. Next, the system provides interfaces for the user to build object models, which consist of the general object model for describing regular objects and human object model for describing human characteristics and behaviors. Further, the system provides interfaces for the user to build virtual environment from object models and creates animated images according to the events described in the related examples, properties associated with objects, and event templates. Further, the system captures user's feedback, which can be verbal requirement, facial expression, and keyboard input. Then the system analyzes user's response, compares to predetermined goals or expert's requirement, and provides user advices in various desired formats.

Methods and apparatus providing a patient digital twin are disclosed. An example apparatus including an example patient digital twin includes a data structure created from a combination of patient electronic medical record data and historical information, the combination extracted from information system(s) and arranged in the data structure to form a digital representation of the patient. The example patient digital twin is arranged for query and simulation. The example patient digital twin is to receive feedback regarding the patient following a procedure conducted on the patient. The example patient digital twin is to incorporate the feedback into the patient digital twin when elements for the procedure have been completed. The example patient digital twin is to process the incorporated feedback to generate and output a recommendation for follow-up with respect to the patient based on the digital representation of the patient including the incorporated feedback with respect to the procedure conducted.

A self-contained automated exercise system attaches to a monitor to allow a user to engage in a tailored exercise routine to provide feedback analysis. The exercise system includes a foldable pad having pressure sensors, adjustable dumbbells, ankle and wrist weights, resistance bands, a telescoping pull-up bar and an adjustable band worn on the user (containing blood pressure, pulse and body temperature thermo-sensors) to wirelessly communicate to a computer that determines exercise performance by the user.

The present invention provides an advanced adaptive predistortion linearization technique to dramatically reduce nonlinear distortion in power amplifiers over a very wide instantaneous bandwidth (up to 2 GHz) and over a wide range of amplifier types, input frequencies, signal types, amplitudes, temperature, and other environmental and signal conditions. In an embodiment of the invention, the predistortion linearization circuitry comprises (1) a higher-order polynomial model of an amplifier's gain and phase characteristics—higher than a third-order polynomial model; (2) an adaptive calibration technique; and (3) a heuristic calibration technique. The higher-order polynomial model is generated by introducing, for example, a plurality of multi-tone test signals with varying center frequency and spacing into the power amplifier. From the power amplifier's corresponding output, the nonlinearities are modeled by employing a higher-order curve fit to capture the irregularities in the nonlinear transfer function. Different distortion transfer functions can be implemented for different operating conditions. The adaptive calibration technique is based on a feedback analysis technique, which updates the applicable distortion transfer function by analyzing the error signal between the introduced input signal and the output signal in real-time. The heuristic calibration technique implements different distortion transfer functions based on historical operating conditions and optimal configurations of the power amplifier.

The invention provides a gastroscope-operation real-time auxiliary system based on deep learning. The system comprises at least one client and a service end, wherein the client is used for monitoringand uploading a gastroscope image collected by current gastroscope equipment through a network, and receiving and displaying a feedback analysis result; and the service end uses an REST configurationto instantly determine a position corresponding to the gastroscope image and a position characteristic according to the gastroscope image collected from the client and feeds back an analysis result tothe client. The service end includes a sample database, a convolution neural network model and a web service module. In the invention, image quality identification, position identification and position characteristic identification are performed on the collected image and identification results are displayed on the client; a reliable reference basis is provided for an operator; detection accuracyand validity are increased; the system is simple and is easy to use; and a condition that a patient suffers twice because of an unsuccessful check is avoided.

Systems, methods and computer products for querying for an interactive assistant for communication over a network via the set-top box. Communications are initiated between a subscriber and an interactive assistant. A diagnostic data log is uploaded from the set-top box to the interactive assistant. Based on the communications between the subscriber an interactive assistant and the diagnostic data log, diagnostic protocols are executed within the set-top box to generate a diagnostic report. The interactive assistant provides feedback analytics via the set-top box based on the communications between the subscriber and the interactive assistant, the diagnostic data log and the diagnostic report. Firmware solutions are downloaded to the set-top box based on results from the diagnostic report.

A method of conditioning an environment includes generating, by a group feedback analysis system, a first comfort limit based on a first plurality of data points corresponding to user feedback of a group of users in an environment conditioned by an environmental conditioning system to identify the first comfort limit at a first extreme; generating, by the group feedback analysis system, a second comfort limit based on a second plurality of data points corresponding to user feedback of the group of users in the environment conditioned by the environmental conditioning system to identify the second comfort limit at a second extreme, the second extreme being opposite the first extreme; identifying, by the group feedback analysis system, a comfort region defined by the first comfort limit and the second comfort limit; and controlling the environmental conditioning system to maintain at least one environmental criterion within the comfort region.

The invention discloses a method for forecasting the displacement of surrounding rocks of a tunnel by utilizing a neural network, which comprises the following steps: an appropriate neural network model is selected, a training sample of the displacement data of the surrounding rocks is input, training is carried out to the neural network , the neural network model with the precision which meets the requirements is obtained, the forecast of the displacement of the surrounding rocks is further carried out by utilizing the trained neural network, the neural network calculates and outputs the forecasted displacement of the surrounding rocks within the following 3 to 5 days of the construction time according to the input measuring point input vector, thereby realizing pre-warning of the displacement of the surrounding rocks. The method utilizes the credible monitoring data in the actual construction, considers the geological features and the related influencing factors of the construction region and carries out the forecast of the deformation and the internal force, etc., of the rocks in the next stage by the feedback analysis of the neural network, thereby guiding the construction, optimizing the construction parameters and reasonably arranging the working procedure.

The invention discloses a feedback analytical method and a feedback analytical device during tunnel construction and based on an extreme learning machine. The feedback analytical method comprises the following steps: the optimal input layer weight and the optimal hidden layer offset are utilized to train and learn a training sample set I and a training sample set II through the extreme learning machine so as to obtain a rock classification evolution extreme learning machine model and a rock parameter identification evolution extreme learning machine model; rock classification influence factors disclosed during the tunnel construction process are obtained; the rock classification influence factors are inputted, and a rock classification result is outputted through the rock classification evolution extreme learning machine model; the rock displacement of a tunnel is monitored and obtained; according to the rock classification result, and within different rock classification ranges, the obtained rock displacement is combined, and the rock mechanical parameter is obtained by utilizing the differential evolution algorithm and the rock parameter identification evolution extreme learning machine model. According to the invention, the rock classification result and the rock mechanical parameter can be rapidly obtained, the predication is accurate, and the accuracy is high.

The invention provides an intelligent massaging machine capable of conditioning and improving psychosomatic health comprehensively, and aims at the defects that the conventional massaging machine has single massage mode, is simple in program setting, is just restricted to body massage while neglecting health problems on mental health and spirit level, and the like. The intelligent massaging machine comprises a psychosomatic health evaluation module, a feedback analysis module, as well as a psychosomatic health conditioning and improving system, wherein the psychosomatic health evaluation module provides psychosomatic health condition testing service for a user, collects health condition information of the user in various aspects such as psychology, physiology, social adaptability and the like, and transmits data to the feedback analysis module; the feedback analysis module performs quantitative evaluation on the information, works out an individualized adjustment service scheme, and transmits to the psychosomatic health conditioning and improving system via a control circuit; and finally, various service is finished on the user. The intelligent massaging machine has the advantages that multiple means including traditional Chinese medical acupoint massage, mental relaxation guidance, music conditioning and the like are effectively combined and integrated for application, the user is treated in various aspects such as body relaxation, psychological adjustment, emotion improvement, social adaptation ability improvement and the like, and finally, the overall level of the individual psychosomatic health is improved.

The invention discloses an estimating method for stratum deformation induced by shield subway construction and the influence of stratum deformation on ancient buildings. The estimating method comprises an induction back analysis and value inversion analysis method based on actually-measured data, the calculation method, based on the stratum loss principle, of ground surface settlement induced by shield construction and an ancient building foundation deformation characteristic evaluation method based on the stiffness correction method. Through the induction back analysis and value inversion analysis method based on the actually-measured data in engineering practice, the characteristic parameters and the characteristic parameter rules of stratum displacement induced by shield subway construction are obtained; based on the stratum loss principle and the Peck formula, the ground surface settlement predicting formula of shield construction parameters is provided; and finally, the stiffness correction method principle is introduced into the formula to estimate the deformation characteristics of the ancient building foundations, so that the systematic evaluation of stratum displacement and the influence of the stratum displacement on the ancient buildings is achieved, and a feedback analysis method is provided for prediction of stratum displacement induced by shield subway construction and the control measures of the construction technique.

The invention discloses a data collection method and system based on streaming real-time distributed big data. Data collection is processed in a mode of a distributed cloud cluster, so the processing performance of the data collection is improved and certain expandability is provided. A subarea associated task queue is established. Data accumulation and landing do not need to be finished firstly. The change of business data is detected in real time. Incrementally collected data is stored efficiently through adoption of a memory model. The space occupied when local temporary files are stored is reduced. Data stacking and loss can be avoided. On the basis of the memory model, streaming processing is carried out on data blocks. Parallel processing is directly carried out on data streams in the memory. The data streams are updated to an analysis data set in real time. According to the method and the system, the efficient processing performance of the cloud cluster is exerted fully; moreover, the data is collected and classified through utilization of an efficient storage model based on the memory; the data basis for follow-up real-time data analysis is provided; the real-time data collection is ensured; and a real-time feedback analysis result can be obtained.

The present invention provides an advanced adaptive predistortion linearization technique to dramatically reduce nonlinear distortion in power amplifiers over a very wide instantaneous bandwidth (up to 2 GHz) and over a wide range of amplifier types, input frequencies, signal types, amplitudes, temperature, and other environmental and signal conditions. In an embodiment of the invention, the predistortion linearization circuitry comprises (1) a higher-order polynomial model of an amplifier's gain and phase characteristics—higher than a third-order polynomial model; (2) an adaptive calibration technique; and (3) a heuristic calibration technique. The higher-order polynomial model is generated by introducing, for example, a plurality of multi-tone test signals with varying center frequency and spacing into the power amplifier. From the power amplifier's corresponding output, the nonlinearities are modeled by employing a higher-order curve fit to capture the irregularities in the nonlinear transfer function. Different distortion transfer functions can be implemented for different operating conditions. The adaptive calibration technique is based on a feedback analysis technique, which updates the applicable distortion transfer function by analyzing the error signal between the introduced input signal and the output signal in real-time. The heuristic calibration technique implements different distortion transfer functions based on historical operating conditions and optimal configurations of the power amplifier.

Systems, apparatus and methods are provided. An example method includes gathering healthcare data and analyzing care paths currently in use by a healthcare organization, the analyzing including analyzing patterns and variances with respect to the care paths; defining one or more evidence-based clinical pathways based on the gathered healthcare data and analyzed care paths in conjunction with practitioner review and supporting metrics; facilitating implementation of the defined one or more evidence-based clinical pathways using computerized orders, computer-facilitated workflows and clinical dashboards; tracking usage of the one or more evidence-based clinical pathways and providing reminders to users to encourage compliance; monitoring deviations from the one or more evidence-based clinical pathways; accepting feedback from at least one of patients and practitioners; and analyzing deviations and feedback with respect to the one or more evidence-based clinical pathways to determine modification of the one or more evidence-based clinical pathways.

The present invention provides an advanced adaptive predistortion linearization technique to dramatically reduce nonlinear distortion in power amplifiers over a very wide instantaneous bandwidth (up to 2 GHz) and over a wide range of amplifier types, input frequencies, signal types, amplitudes, temperature, and other environmental and signal conditions. In an embodiment of the invention, the predistortion linearization circuitry comprises (1) a higher-order polynomial model of an amplifier's gain and phase characteristics—higher than a third-order polynomial model; (2) an adaptive calibration technique; and (3) a heuristic calibration technique. The higher-order polynomial model is generated by introducing, for example, a plurality of multi-tone test signals with varying center frequency and spacing into the power amplifier. From the power amplifier's corresponding output, the nonlinearities are modeled by employing a higher-order curve fit to capture the irregularities in the nonlinear transfer function. Different distortion transfer functions can be implemented for different operating conditions. The adaptive calibration technique is based on a feedback analysis technique, which updates the applicable distortion transfer function by analyzing the error signal between the introduced input signal and the output signal in real-time. The heuristic calibration technique implements different distortion transfer functions based on historical operating conditions and optimal configurations of the power amplifier.

A feedback system including a controller configured to: register a system account for each of a plurality of users, wherein the feedback system account includes a unique identification code for each of the plurality of users; provide a graphic user interface through which a first user: generates a request for feedback; selects one or more groups to which to communicate the request for feedback, where in the selection of the groups includes associating one or more unique identification codes with each of the groups; receives feedback from at least a second user associated with a unique identification code associated with one of the groups, wherein, upon receipt of the feedback from the second user, the first user is automatically authorized to reply to the second user; and accesses feedback analytics related to the feedback received in response to the request for feedback.

The present invention discloses a feedback audio output detection method. The method comprises: emitting digital audio signals to be played; performing digital-to-analogue conversion of the digital audio signals, amplifying the obtained analog audio signals and outputting and playing the analog audio signals after performing low-pass filtering processing; performing filtering and digital sampling of the output and played analog audio signals, performing feedback analysis of the obtained sampling audio signals, and determining whether an audio player system works abnormally or not; and closing a power supply and emitting fault alarm signals when the audio player system works abnormally. The present invention further provides a feedback audio output detection device. The device comprises an information processing module, an audio processing module, a power amplification module, a first low-pass filtering module, an audio output module and a second low-pass filtering module. The feedback audio output detection device is able to rapidly detect the work state of an audio output circuit and close a power supply and emit alarm signals when the exception of audio output happens so as to guarantee the normal work of the audio output circuit.

The present application provides a data processing method under a Hadoop platform, and belongs to the field of data processing. The method comprises: acquiring Hive table structure information of inventory data of a Hadoop platform, comparing structure information of to-be-stored data with the Hive table structure information, and obtaining data structure change information; updating a Hive table structure according to the obtained data structure change information and the acquired Hive table structure information of the inventory data; and formatting the to-be-stored data according to the updated Hive table structure, and storing the formatted to-be-stored data. With adoption of the method disclosed by the present application, compatibility of the data structure of the stored data is effectively ensured, and when the archived and stored data needs to be analyzed and queried, the data format does not need to be counted and converted, so that not only are computing resources saved, but also analysis and query results can be rapidly fed back, and data query and analysis efficiency is improved.

The invention discloses a personalized learning and intelligent training management system and method, and belongs to the technical field of enterprise employee safety training. The system comprises astudent terminal, a teacher terminal, a management terminal and a background, and the student terminal is used for checking personal information of students, recommending learning resources to the students and assessing learned knowledge points; the teacher end is used for answering questions raised by students, selecting course resources or providing related information of training tasks; the management end is used for training task management, resource auditing and feedback analysis; and the background is used for information acquisition, data processing analysis, resource library storage,reading and updating. The student terminal comprises a registration login module, a user information module, a learning training module, a capability test module, a teacher application module and an information feedback module. The teacher end comprises a knowledge question answering module, a training task module, a test question resource uploading module, a learning resource uploading module andan integral module. The training management system is used for training learning and training management, and the training effect can be improved.

The invention discloses an anchor rod body damage position identifying method based on a neural network, and belongs to the field of anchor rod body damage position identifying method. According to the identifying method, the data observed in real engineering is inputted into a training sample of anchor rod body damage position data so as to train a neural network; then the trained neural network is used to detect the anchor rod bodies for supporting tunnels; according to inputted index parameters, through the feedback and analysis of the neutral network, the neutral network will predict the anchor rod body damage positions according to the prediction requirements; proper support parameters are chosen to carry out support control on the tunnels; and the obtained anchor rod body damage position data is utilized to judge the anchoring quality of the anchor rods so as to avoid the safety accidents caused by instable rocks. The provided method has the advantages that the nondestructive detection of anchor rods is realized, if the training sample is enough, the detection results are accurate, the operation is simple, and under the situation that the size of the rod body is known, only the anchor rod frequency of the supporting naked end of the anchor rods needs to be tested.

The invention discloses a tunnel dynamic feedback analysis system based on an IFC standard, and the system comprises a BIM model library operation module for establishing a tunnel model, a model analysis module, a data reading module, an analysis report module, and a surrounding rock classification module. The BIM model library operation module is used for creating a typical tunnel model and a parameterized component library and exporting the typical tunnel model into an IFC format file to form an IFC model; the model analysis module, the surrounding rock classification module and the analysis report module obtain surrounding rock dynamic classification and surrounding rock identification parameters through extracting the IFC format file related attribute data and performing calculation, and generate a report form; a feedback analysis calculation program is called to obtain an excavation construction scheme and support parameters, the data reading module writes dynamical classification of the surrounding rock and the surrounding rock identification parameters into the IFC model. According to the invention, comprehensive rapid analysis and accurate processing of various data and information are ensured, feedback analysis is carried out on the data, and accurate presentation of the data is realized.

The invention discloses a vehicle damage determination method based on a mobile terminal. According to the method, a mobile terminal shoots the image of the damaged part of a vehicle through a camera; the shot image and vehicle type information are uploaded to a damage determination analysis platform, such that the damage determination analysis platform performs analysis comparison on the image and the standard image corresponding to the vehicle type information and feeds back the analysis result; and in a preset display area, the analysis result fed back by the damage determination analysis platform is displayed. The invention discloses a vehicle damage determination apparatus based on a mobile terminal and a vehicle damage determination system based on a mobile terminal. According to the present invention, the image and the vehicle type information are shot by the mobile terminal in the scene of the vehicle and are uploaded to to the damage determination analysis platform, and the damage determination analysis platform performs the damage determination analysis on the vehicle, such that the convenience and the intelligence of the vehicle damage determination analysis are improved.

The invention relates to a low temperature-seepage-force coupling effect tunnel model test system and a test method. The test system mainly comprises a steel structure main loading frame portion, a seepage portion, a low-temperature refrigeration equipment portion and an automatic monitoring-feedback analysis portion. An overall counterforce frame is formed by welding H section steel, jacks used for simulating vertical loads are respectively arranged at two sides of the upper part of a model, a load is applied through pressure transmitting I-steel, and openable baffle plates are arranged in front and back. A stainless steel water tank is arranged on the steel structure main loading frame, the whole body is composed of a hydraulic pump, a water storage tank, a stop valve and the like, and the lower part of the stainless steel water tank is provided with a hole. Variations in the temperature of a cavity are realized by adopting an evaporator with a special form. Data real-time acquisition and feedback analysis are carried out based on technologies such as automatic monitoring and wireless transmission technologies and an intelligent optimization algorithm. Similar materials are proportioned according to actual rock physical and mechanical indexes, the similar materials are loaded into the overall loading frame, a vertical load is applied, and excavation for a tunnel cavity is carried out.

The present invention provides a system and a method for real time monitoring and identifying defects occurring in a three dimensional object build via an additive manufacturing process. Further, the present invention provides in-situ correction of such defects by a plurality of functional tool heads possessing freedom of motion in arbitrary planes and approach, where the functional tool heads are automatically and independently controlled based on a feedback analysis from the printing process, implementing analyzing techniques. Furthermore, the present invention provides a mechanism for analyzing defected data collected from detection devices and correcting tool path instructions and object model in-situ during construction of a 3D object. A build report is also generated that displays, in 3D space, the structural geometry and inherent properties of a final build object along with the features of corrected and uncorrected defects. Advantageously, the build report helps in improving 3D printing process for subsequent objects.

The invention discloses a system for monitoring the electricity capacity of electric equipment and an electricity consumption feedback analysis processing method. The system comprises a power consumption measurement system and an information storage and processing system. The power consumption measurement system is connected with the information storage and processing system. The power consumption measurement system comprises a power consumption collection module and a plurality of measurement circuits. The measurement circuits are corresponding to electric equipment, and are used for measuring the electricity consumed by the electric equipment in a time unit. The information storage and processing system comprises a local communication module, a processing module, a display module and a storage module. The processing module is connected with the local communication module and the storage module. The electric equipment is provided with the measurement circuits, and the electricity consumed by each piece of electric equipment can be calculated through the power consumption collection module. The processing module can provide the recorded electricity consumed by the electric equipment in a certain time period for a user to make comparison with the electricity consumed by other users. The user can know the utilization state of the electric equipment through comparison, and checks the utilization state of the electric equipment.