Aim To detect sensor failure in control system using a single sensor signal. Methods A neural predictor was designed based on a radial basis function network(RBFN), and the neural predictor learned the sensor sig...Aim To detect sensor failure in control system using a single sensor signal. Methods A neural predictor was designed based on a radial basis function network(RBFN), and the neural predictor learned the sensor signal on line with a hybrid algorithm composed of n means clustering and Kalman filter and then gave the estimation of the sensor signal at the next step. If the difference between the estimation and the actural values of the sensor signal exceeded a threshold, the sensor could be declared to have a failure. The choice of the failure detection threshold depends on the noise variance and the possible prediction error of neural predictor. Results and Conclusion\ The computer simulation results show the proposed method can detect sensor failure correctly for a gyro in an automotive engine.展开更多
A study is given on the application of BP neural network (BPNN) in sensorfailure detection in control systems, and on the networ architecture desgn, the redun-dancy,the quickness and the insensitivity to sensor noise ...A study is given on the application of BP neural network (BPNN) in sensorfailure detection in control systems, and on the networ architecture desgn, the redun-dancy,the quickness and the insensitivity to sensor noise of the BPNN based sensor detec-tion methed. Besules, an exploration is made into tbe factors accounting for the quality ofsignal recovery for failed sensor using BPNN. The results reveal clearly that BPNN can besuccessfully used in sensor failure detection and data recovery.展开更多
This paper proposes a sensor failure detection method based on artificial neural network and signal processing,in comparison with other methods,which does not need any redundancy information among sensor outputs and d...This paper proposes a sensor failure detection method based on artificial neural network and signal processing,in comparison with other methods,which does not need any redundancy information among sensor outputs and divides the output of a sensor into'Signal dominant component'and'Noise dominant component'because the pattern of sensor failure often appears in the'Noise dominant component'.With an ARMA model built for'Noise dominant component'using artificial neural network,such sensor failures as bias failure,hard failure,drift failure,spike failure and cyclic failure may be detected through residual analysis,and the type of sensor failure can be indicated by an appropriate indicator.The failure detection procedure for a temperature sensor in a hovercraft engine is simulated to prove the applicability of the method proposed in this paper.展开更多
In this work, a total of 322 tests were taken on young volunteers by performing 10 different falls, 6 different Activities of Daily Living (ADL) and 7 Dynamic Gait Index (DGI) tests using a custom-designed Wireless Ga...In this work, a total of 322 tests were taken on young volunteers by performing 10 different falls, 6 different Activities of Daily Living (ADL) and 7 Dynamic Gait Index (DGI) tests using a custom-designed Wireless Gait Analysis Sensor (WGAS). In order to perform automatic fall detection, we used Back Propagation Artificial Neural Network (BP-ANN) and Support Vector Machine (SVM) based on the 6 features extracted from the raw data. The WGAS, which includes a tri-axial accelerometer, 2 gyroscopes, and a MSP430 microcontroller, is worn by the subjects at either T4 (at back) or as a belt-clip in front of the waist during the various tests. The raw data is wirelessly transmitted from the WGAS to a near-by PC for real-time fall classification. The BP ANN is optimized by varying the training, testing and validation data sets and training the network with different learning schemes. SVM is optimized by using three different kernels and selecting the kernel for best classification rate. The overall accuracy of BP ANN is obtained as 98.20% with LM and RPROP training from the T4 data, while from the data taken at the belt, we achieved 98.70% with LM and SCG learning. The overall accuracy using SVM was 98.80% and 98.71% with RBF kernel from the T4 and belt position data, respectively.展开更多
A forest fire is a severe threat to forest resources and human life, In this paper, we propose a forest-fire detection system that has an artificial neural network algorithm implemented in a wireless sensor network （...A forest fire is a severe threat to forest resources and human life, In this paper, we propose a forest-fire detection system that has an artificial neural network algorithm implemented in a wireless sensor network （WSN）. The proposed detection system mitigates the threat of forest fires by provide accurate fire alarm with low maintenance cost. The accuracy is increased by the novel multi- criteria detection, referred to as an alarm decision depends on multiple attributes of a forest fire. The multi-criteria detection is implemented by the artificial neural network algorithm. Meanwhile, we have developed a prototype of the proposed system consisting of the solar batter module, the fire detection module and the user interface module.展开更多
Wireless sensor networks(WSNs)are considered promising for applications such as military surveillance and healthcare.The security of these networks must be ensured in order to have reliable applications.Securing such ...Wireless sensor networks(WSNs)are considered promising for applications such as military surveillance and healthcare.The security of these networks must be ensured in order to have reliable applications.Securing such networks requires more attention,as they typically implement no dedicated security appliance.In addition,the sensors have limited computing resources and power and storage,which makes WSNs vulnerable to various attacks,especially denial of service(DoS).The main types of DoS attacks against WSNs are blackhole,grayhole,flooding,and scheduling.There are two primary techniques to build an intrusion detection system(IDS):signature-based and data-driven-based.This study uses the data-driven approach since the signature-based method fails to detect a zero-day attack.Several publications have proposed data-driven approaches to protect WSNs against such attacks.These approaches are based on either the traditional machine learning(ML)method or a deep learning model.The fundamental limitations of these methods include the use of raw features to build an intrusion detection model,which can result in low detection accuracy.This study implements entity embedding to transform the raw features to a more robust representation that can enable more precise detection and demonstrates how the proposed method can outperform state-of-the-art solutions in terms of recognition accuracy.展开更多
In this paper, we present an approach to improve the accuracy of environmental sound event detection in a wireless acoustic sensor network for home monitoring. Wireless acoustic sensor nodes can capture sounds in the ...In this paper, we present an approach to improve the accuracy of environmental sound event detection in a wireless acoustic sensor network for home monitoring. Wireless acoustic sensor nodes can capture sounds in the home and simultaneously deliver them to a sink node for sound event detection. The proposed approach is mainly composed of three modules, including signal estimation, reliable sensor channel selection, and sound event detection. During signal estimation, lost packets are recovered to improve the signal quality. Next, reliable channels are selected using a multi-channel cross-correlation coefficient to improve the computational efficiency for distant sound event detection without sacrificing performance. Finally, the signals of the selected two channels are used for environmental sound event detection based on bidirectional gated recurrent neural networks using two-channel audio features. Experiments show that the proposed approach achieves superior performances compared to the baseline.展开更多
As fundamental components of consumer electronics, medical devices, and aerospace precision instruments, circuit modules require fault detection analysis to ensure operational stability and safety, which remains a cri...As fundamental components of consumer electronics, medical devices, and aerospace precision instruments, circuit modules require fault detection analysis to ensure operational stability and safety, which remains a critical challenge. Conventional contact-based electrical signal detection methods for printed circuit board(PCB) fault analysis often induce contact damage and suffer from slow detection and analysis speeds due to massive redundant data transmission and processing. Here, we propose a diamond-neural-network quantum magnetic sensor that enables non-contact circuit fault analysis by detecting far-field weak magnetic signals from PCBs. The sensor comprises a diamond array where each diamond functions as a nitrogen-vacancy(NV) center quantum magnetic sensor with tunable responsivity regulated by positive and negative voltage follower units. This diamond array inherently constitutes an artificial neural network(ANN), capable of simultaneous magnetic signal detection and real-time processing with ultra-low latency. Through training the sensor for fault classification, we achieve a response time superior to 137.1 ns.展开更多
Ever since the research in machine learning gained traction in recent years,it has been employed to address challenges in a wide variety of domains,including mechanical devices.Most of the machine learning models are ...Ever since the research in machine learning gained traction in recent years,it has been employed to address challenges in a wide variety of domains,including mechanical devices.Most of the machine learning models are built on the assumption of a static learning environment,but in practical situations,the data generated by the process is dynamic.This evolution of the data is termed concept drift.This research paper presents an approach for predictingmechanical failure in real-time using incremental learning based on the statistically calculated parameters of mechanical equipment.The method proposed here is applicable to allmechanical devices that are susceptible to failure or operational degradation.The proposed method in this paper is equipped with the capacity to detect the drift in data generation and adaptation.The proposed approach evaluates the machine learning and deep learning models for their efficacy in handling the errors related to industrial machines due to their dynamic nature.It is observed that,in the settings without concept drift in the data,methods like SVM and Random Forest performed better compared to deep neural networks.However,this resulted in poor sensitivity for the smallest drift in the machine data reported as a drift.In this perspective,DNN generated the stable drift detection method;it reported an accuracy of 84%and an AUC of 0.87 while detecting only a single drift point,indicating the stability to performbetter in detecting and adapting to new data in the drifting environments under industrial measurement settings.展开更多
A neural network fire detection method was developed using detection information for temperature smoke density, and CO concentration to determine the probability of three representative fire conditions. The method ove...A neural network fire detection method was developed using detection information for temperature smoke density, and CO concentration to determine the probability of three representative fire conditions. The method overcomes the shortcomings of domestic fire alarm systems using single sensor information. Test results show that the identification error rates for fires, smoldering fires, and no fire are less than 5%, which greatly reduces leak-check rates and false alarms. This neural network fire alarm system can fuse a variety of sensor data and improve the ability of systems to adapt in the environment and accurately predict fires, which has great significance for life and property safety.展开更多
A wireless sensor network(WSN)consists of several tiny sensor nodes to monitor,collect,and transmit the physical information from an environment through the wireless channel.The node failure is considered as one of th...A wireless sensor network(WSN)consists of several tiny sensor nodes to monitor,collect,and transmit the physical information from an environment through the wireless channel.The node failure is considered as one of the main issues in the WSN which creates higher packet drop,delay,and energy consumption during the communication.Although the node failure occurred mostly due to persistent energy exhaustion during transmission of data packets.In this paper,Artificial Neural Network(ANN)based Node Failure Detection(NFD)is developed with cognitive radio for detecting the location of the node failure.The ad hoc on-demand distance vector(AODV)routing protocol is used for transmitting the data from the source node to the base station.Moreover,the Mahalanobis distance is used for detecting an adjacent node to the node failure which is used to create the routing path without any node failure.The performance of the proposed ANN-NFD method is analysed in terms of throughput,delivery rate,number of nodes alive,drop rate,end to end delay,energy consumption,and overhead ratio.Furthermore,the performance of the ANN-NFD method is evaluated with the header to base station and base station to header(H2B2H)protocol.The packet delivery rate of the ANN-NFD method is 0.92 for 150 nodes that are high when compared to the H2B2H protocol.Hence,the ANN-NFD method provides data consistency during data transmission under node and battery failure.展开更多
A fuzzy neural network (FNN) model is developed to predict the 4-CBA concentration of the oxidation unit in purified terephthalic acid process. Several technologies are used to deal with the process data before modeli...A fuzzy neural network (FNN) model is developed to predict the 4-CBA concentration of the oxidation unit in purified terephthalic acid process. Several technologies are used to deal with the process data before modeling.First,a set of preliminary input variables is selected according to prior knowledge and experience. Secondly,a method based on the maximum correlation coefficient is proposed to detect the dead time between the process variables and response variables. Finally, the fuzzy curve method is used to reduce the unimportant input variables.The simulation results based on industrial data show that the relative error range of the FNN model is narrower than that of the American Oil Company (AMOCO) model. Furthermore, the FNN model can predict the trend of the 4-CBA concentration more accurately.展开更多
Optical sensors provide a fast and real-time approach to detect benzene,toluene,ethylbenzene,and xylenes(BTEX)in environmental monitoring and industrial safety.However,detecting the concentration of a particular gas i...Optical sensors provide a fast and real-time approach to detect benzene,toluene,ethylbenzene,and xylenes(BTEX)in environmental monitoring and industrial safety.However,detecting the concentration of a particular gas in a mixture can be challenging.Here,we develop a machine-learning model that can precisely measure BTEX concentrations simultaneously based on an absorption spectroscopy gas sensing system.The convolutional neural network(CNN)is utilized to identify the absorbance spectra for each volatile,along with their concentrations in a mixture.A synthetic data set is generated using a series of physics-based simulations to create the predictive model.The data set consists of the overall absorbance of numerous random BTEX mixtures over time,based on various percentages of the permissible exposure limit(PEL).It is worth noting that benzene has a negligible absorbance(very low PEL,1–5 ppm)compared to other volatile gases,which makes it difficult to detect.To address this challenge,we introduce a 3-stage solution to accurately discriminate between all BTEX species,regardless of their concentration levels.As a result,the R-squared above 0.99 for toluene,ethylbenzene,and oxylene,and the R-squared above 0.96 for benzene,is achieved,indicating the model's capability to predict BTEX concentrations.展开更多
Lower limb motion recognition techniques commonly employ Surface Electromyographic Signal(sEMG)as input and apply a machine learning classifier or Back Propagation Neural Network(BPNN)for classification.However,this a...Lower limb motion recognition techniques commonly employ Surface Electromyographic Signal(sEMG)as input and apply a machine learning classifier or Back Propagation Neural Network(BPNN)for classification.However,this artificial feature engineering technique is not generalizable to similar tasks and is heavily reliant on the researcher’s subject expertise.In contrast,neural networks such as Convolutional Neural Network(CNN)and Long Short-term Memory Neural Network(LSTM)can automatically extract features,providing a more generalized and adaptable approach to lower limb motion recognition.Although this approach overcomes the limitations of human feature engineering,it may ignore the potential correlation among the sEMG channels.This paper proposes a spatial–temporal graph neural network model,STGNN-LMR,designed to address the problem of recognizing lower limb motion from multi-channel sEMG.STGNN-LMR transforms multi-channel sEMG into a graph structure and uses graph learning to model spatial–temporal features.An 8-channel sEMG dataset is constructed for the experimental stage,and the results show that the STGNN-LMR model achieves a recognition accuracy of 99.71%.Moreover,this paper simulates two unexpected scenarios,including sEMG sensors affected by sweat noise and sudden failure,and evaluates the testing results using hypothesis testing.According to the experimental results,the STGNN-LMR model exhibits a significant advantage over the control models in noise scenarios and failure scenarios.These experimental results confirm the effectiveness of the STGNN-LMR model for addressing the challenges associated with sEMG-based lower limb motion recognition in practical scenarios.展开更多
Wireless sensor networks are susceptible to failures of nodes and links due to various physical or computational reasons.Some physical reasons include a very high temperature,a heavy load over a node,and heavy rain.Co...Wireless sensor networks are susceptible to failures of nodes and links due to various physical or computational reasons.Some physical reasons include a very high temperature,a heavy load over a node,and heavy rain.Computational reasons could be a third-party intrusive attack,communication conflicts,or congestion.Automated fault diagnosis has been a well-studied problem in the research community.In this paper,we present an automated fault diagnosis model that can diagnose multiple types of faults in the category of hard faults and soft faults.Our proposed model implements a feed-forward neural network trained with a hybrid metaheuristic algorithm that combines the principles of exploration and exploitation of the search space.The proposed methodology consists of different phases,such as a clustering phase,a fault detection and classification phase,and a decision and diagnosis phase.The implemented methodology can diagnose composite faults,such as hard permanent,soft permanent,intermittent,and transient faults for sensor nodes as well as for links.The proposed implementation can also classify different types of faulty behavior for both sensor nodes and links in the network.We present the obtained theoretical results and computational complexity of the implemented model for this particular study on automated fault diagnosis.The performance of the model is evaluated using simulations and experiments conducted using indoor and outdoor testbeds.展开更多
A system of impact damage detection for composite material structures by using an intelligent sensor embedded in composite material is described. In the course of signal processing, wavelet transform has the exception...A system of impact damage detection for composite material structures by using an intelligent sensor embedded in composite material is described. In the course of signal processing, wavelet transform has the exceptional property of temporal frequency localization, whereas Kohonen artificial neural networks have excellent characteristics of self-learning and fault-tolerance. By combining the merits of abstracting time-frequency domain eigenvalues and improving the ratio of signal to noise in this system, impact damage in composite material can be properly recognized.展开更多
文摘Aim To detect sensor failure in control system using a single sensor signal. Methods A neural predictor was designed based on a radial basis function network(RBFN), and the neural predictor learned the sensor signal on line with a hybrid algorithm composed of n means clustering and Kalman filter and then gave the estimation of the sensor signal at the next step. If the difference between the estimation and the actural values of the sensor signal exceeded a threshold, the sensor could be declared to have a failure. The choice of the failure detection threshold depends on the noise variance and the possible prediction error of neural predictor. Results and Conclusion\ The computer simulation results show the proposed method can detect sensor failure correctly for a gyro in an automotive engine.
文摘A study is given on the application of BP neural network (BPNN) in sensorfailure detection in control systems, and on the networ architecture desgn, the redun-dancy,the quickness and the insensitivity to sensor noise of the BPNN based sensor detec-tion methed. Besules, an exploration is made into tbe factors accounting for the quality ofsignal recovery for failed sensor using BPNN. The results reveal clearly that BPNN can besuccessfully used in sensor failure detection and data recovery.
文摘This paper proposes a sensor failure detection method based on artificial neural network and signal processing,in comparison with other methods,which does not need any redundancy information among sensor outputs and divides the output of a sensor into'Signal dominant component'and'Noise dominant component'because the pattern of sensor failure often appears in the'Noise dominant component'.With an ARMA model built for'Noise dominant component'using artificial neural network,such sensor failures as bias failure,hard failure,drift failure,spike failure and cyclic failure may be detected through residual analysis,and the type of sensor failure can be indicated by an appropriate indicator.The failure detection procedure for a temperature sensor in a hovercraft engine is simulated to prove the applicability of the method proposed in this paper.
文摘In this work, a total of 322 tests were taken on young volunteers by performing 10 different falls, 6 different Activities of Daily Living (ADL) and 7 Dynamic Gait Index (DGI) tests using a custom-designed Wireless Gait Analysis Sensor (WGAS). In order to perform automatic fall detection, we used Back Propagation Artificial Neural Network (BP-ANN) and Support Vector Machine (SVM) based on the 6 features extracted from the raw data. The WGAS, which includes a tri-axial accelerometer, 2 gyroscopes, and a MSP430 microcontroller, is worn by the subjects at either T4 (at back) or as a belt-clip in front of the waist during the various tests. The raw data is wirelessly transmitted from the WGAS to a near-by PC for real-time fall classification. The BP ANN is optimized by varying the training, testing and validation data sets and training the network with different learning schemes. SVM is optimized by using three different kernels and selecting the kernel for best classification rate. The overall accuracy of BP ANN is obtained as 98.20% with LM and RPROP training from the T4 data, while from the data taken at the belt, we achieved 98.70% with LM and SCG learning. The overall accuracy using SVM was 98.80% and 98.71% with RBF kernel from the T4 and belt position data, respectively.
文摘A forest fire is a severe threat to forest resources and human life, In this paper, we propose a forest-fire detection system that has an artificial neural network algorithm implemented in a wireless sensor network （WSN）. The proposed detection system mitigates the threat of forest fires by provide accurate fire alarm with low maintenance cost. The accuracy is increased by the novel multi- criteria detection, referred to as an alarm decision depends on multiple attributes of a forest fire. The multi-criteria detection is implemented by the artificial neural network algorithm. Meanwhile, we have developed a prototype of the proposed system consisting of the solar batter module, the fire detection module and the user interface module.
基金This publication was supported by the Deanship of Scientific Research at Prince Sattam bin Abdulaziz University。
文摘Wireless sensor networks(WSNs)are considered promising for applications such as military surveillance and healthcare.The security of these networks must be ensured in order to have reliable applications.Securing such networks requires more attention,as they typically implement no dedicated security appliance.In addition,the sensors have limited computing resources and power and storage,which makes WSNs vulnerable to various attacks,especially denial of service(DoS).The main types of DoS attacks against WSNs are blackhole,grayhole,flooding,and scheduling.There are two primary techniques to build an intrusion detection system(IDS):signature-based and data-driven-based.This study uses the data-driven approach since the signature-based method fails to detect a zero-day attack.Several publications have proposed data-driven approaches to protect WSNs against such attacks.These approaches are based on either the traditional machine learning(ML)method or a deep learning model.The fundamental limitations of these methods include the use of raw features to build an intrusion detection model,which can result in low detection accuracy.This study implements entity embedding to transform the raw features to a more robust representation that can enable more precise detection and demonstrates how the proposed method can outperform state-of-the-art solutions in terms of recognition accuracy.
基金supported by Basic Science Research Program through the National Research Foundation of Korea(NRF) funded by the Ministry of Education (NRF2015R1D1A1A01059804)the MSIP (Ministry of Science,ICT and Future Planning),Korea,under the ITRC(Information Technology Research Center) support program (IITP-2016-R2718-16-0011) supervised by the IITP(Institute for Information & communications Technology Promotion)the present Research has been conducted by the Research Grant of Kwangwoon University in 2017
文摘In this paper, we present an approach to improve the accuracy of environmental sound event detection in a wireless acoustic sensor network for home monitoring. Wireless acoustic sensor nodes can capture sounds in the home and simultaneously deliver them to a sink node for sound event detection. The proposed approach is mainly composed of three modules, including signal estimation, reliable sensor channel selection, and sound event detection. During signal estimation, lost packets are recovered to improve the signal quality. Next, reliable channels are selected using a multi-channel cross-correlation coefficient to improve the computational efficiency for distant sound event detection without sacrificing performance. Finally, the signals of the selected two channels are used for environmental sound event detection based on bidirectional gated recurrent neural networks using two-channel audio features. Experiments show that the proposed approach achieves superior performances compared to the baseline.
基金National Natural Science Foundation of China(62175219,52275576,U21A20141)Natural Science Foundation of Shanxi Province(202403021223007)Sanjin Talent Program of Shanxi Province.
文摘As fundamental components of consumer electronics, medical devices, and aerospace precision instruments, circuit modules require fault detection analysis to ensure operational stability and safety, which remains a critical challenge. Conventional contact-based electrical signal detection methods for printed circuit board(PCB) fault analysis often induce contact damage and suffer from slow detection and analysis speeds due to massive redundant data transmission and processing. Here, we propose a diamond-neural-network quantum magnetic sensor that enables non-contact circuit fault analysis by detecting far-field weak magnetic signals from PCBs. The sensor comprises a diamond array where each diamond functions as a nitrogen-vacancy(NV) center quantum magnetic sensor with tunable responsivity regulated by positive and negative voltage follower units. This diamond array inherently constitutes an artificial neural network(ANN), capable of simultaneous magnetic signal detection and real-time processing with ultra-low latency. Through training the sensor for fault classification, we achieve a response time superior to 137.1 ns.
文摘Ever since the research in machine learning gained traction in recent years,it has been employed to address challenges in a wide variety of domains,including mechanical devices.Most of the machine learning models are built on the assumption of a static learning environment,but in practical situations,the data generated by the process is dynamic.This evolution of the data is termed concept drift.This research paper presents an approach for predictingmechanical failure in real-time using incremental learning based on the statistically calculated parameters of mechanical equipment.The method proposed here is applicable to allmechanical devices that are susceptible to failure or operational degradation.The proposed method in this paper is equipped with the capacity to detect the drift in data generation and adaptation.The proposed approach evaluates the machine learning and deep learning models for their efficacy in handling the errors related to industrial machines due to their dynamic nature.It is observed that,in the settings without concept drift in the data,methods like SVM and Random Forest performed better compared to deep neural networks.However,this resulted in poor sensitivity for the smallest drift in the machine data reported as a drift.In this perspective,DNN generated the stable drift detection method;it reported an accuracy of 84%and an AUC of 0.87 while detecting only a single drift point,indicating the stability to performbetter in detecting and adapting to new data in the drifting environments under industrial measurement settings.
基金Supported by the Key Technologies Research and Development Program of the Eleventh Five-Year Plan of China(No. 2007BAK22B04)2008 Independent Task(No. SKLCRSM08B12)
文摘A neural network fire detection method was developed using detection information for temperature smoke density, and CO concentration to determine the probability of three representative fire conditions. The method overcomes the shortcomings of domestic fire alarm systems using single sensor information. Test results show that the identification error rates for fires, smoldering fires, and no fire are less than 5%, which greatly reduces leak-check rates and false alarms. This neural network fire alarm system can fuse a variety of sensor data and improve the ability of systems to adapt in the environment and accurately predict fires, which has great significance for life and property safety.
文摘A wireless sensor network(WSN)consists of several tiny sensor nodes to monitor,collect,and transmit the physical information from an environment through the wireless channel.The node failure is considered as one of the main issues in the WSN which creates higher packet drop,delay,and energy consumption during the communication.Although the node failure occurred mostly due to persistent energy exhaustion during transmission of data packets.In this paper,Artificial Neural Network(ANN)based Node Failure Detection(NFD)is developed with cognitive radio for detecting the location of the node failure.The ad hoc on-demand distance vector(AODV)routing protocol is used for transmitting the data from the source node to the base station.Moreover,the Mahalanobis distance is used for detecting an adjacent node to the node failure which is used to create the routing path without any node failure.The performance of the proposed ANN-NFD method is analysed in terms of throughput,delivery rate,number of nodes alive,drop rate,end to end delay,energy consumption,and overhead ratio.Furthermore,the performance of the ANN-NFD method is evaluated with the header to base station and base station to header(H2B2H)protocol.The packet delivery rate of the ANN-NFD method is 0.92 for 150 nodes that are high when compared to the H2B2H protocol.Hence,the ANN-NFD method provides data consistency during data transmission under node and battery failure.
基金Supported by the National Outstanding Youth Science Foundation of China (No. 60025308).
文摘A fuzzy neural network (FNN) model is developed to predict the 4-CBA concentration of the oxidation unit in purified terephthalic acid process. Several technologies are used to deal with the process data before modeling.First,a set of preliminary input variables is selected according to prior knowledge and experience. Secondly,a method based on the maximum correlation coefficient is proposed to detect the dead time between the process variables and response variables. Finally, the fuzzy curve method is used to reduce the unimportant input variables.The simulation results based on industrial data show that the relative error range of the FNN model is narrower than that of the American Oil Company (AMOCO) model. Furthermore, the FNN model can predict the trend of the 4-CBA concentration more accurately.
基金supported by the National Institute of Environmental Health Sciences(NIEHS)under award number:1R41ES034936-01-02。
文摘Optical sensors provide a fast and real-time approach to detect benzene,toluene,ethylbenzene,and xylenes(BTEX)in environmental monitoring and industrial safety.However,detecting the concentration of a particular gas in a mixture can be challenging.Here,we develop a machine-learning model that can precisely measure BTEX concentrations simultaneously based on an absorption spectroscopy gas sensing system.The convolutional neural network(CNN)is utilized to identify the absorbance spectra for each volatile,along with their concentrations in a mixture.A synthetic data set is generated using a series of physics-based simulations to create the predictive model.The data set consists of the overall absorbance of numerous random BTEX mixtures over time,based on various percentages of the permissible exposure limit(PEL).It is worth noting that benzene has a negligible absorbance(very low PEL,1–5 ppm)compared to other volatile gases,which makes it difficult to detect.To address this challenge,we introduce a 3-stage solution to accurately discriminate between all BTEX species,regardless of their concentration levels.As a result,the R-squared above 0.99 for toluene,ethylbenzene,and oxylene,and the R-squared above 0.96 for benzene,is achieved,indicating the model's capability to predict BTEX concentrations.
文摘Lower limb motion recognition techniques commonly employ Surface Electromyographic Signal(sEMG)as input and apply a machine learning classifier or Back Propagation Neural Network(BPNN)for classification.However,this artificial feature engineering technique is not generalizable to similar tasks and is heavily reliant on the researcher’s subject expertise.In contrast,neural networks such as Convolutional Neural Network(CNN)and Long Short-term Memory Neural Network(LSTM)can automatically extract features,providing a more generalized and adaptable approach to lower limb motion recognition.Although this approach overcomes the limitations of human feature engineering,it may ignore the potential correlation among the sEMG channels.This paper proposes a spatial–temporal graph neural network model,STGNN-LMR,designed to address the problem of recognizing lower limb motion from multi-channel sEMG.STGNN-LMR transforms multi-channel sEMG into a graph structure and uses graph learning to model spatial–temporal features.An 8-channel sEMG dataset is constructed for the experimental stage,and the results show that the STGNN-LMR model achieves a recognition accuracy of 99.71%.Moreover,this paper simulates two unexpected scenarios,including sEMG sensors affected by sweat noise and sudden failure,and evaluates the testing results using hypothesis testing.According to the experimental results,the STGNN-LMR model exhibits a significant advantage over the control models in noise scenarios and failure scenarios.These experimental results confirm the effectiveness of the STGNN-LMR model for addressing the challenges associated with sEMG-based lower limb motion recognition in practical scenarios.
文摘Wireless sensor networks are susceptible to failures of nodes and links due to various physical or computational reasons.Some physical reasons include a very high temperature,a heavy load over a node,and heavy rain.Computational reasons could be a third-party intrusive attack,communication conflicts,or congestion.Automated fault diagnosis has been a well-studied problem in the research community.In this paper,we present an automated fault diagnosis model that can diagnose multiple types of faults in the category of hard faults and soft faults.Our proposed model implements a feed-forward neural network trained with a hybrid metaheuristic algorithm that combines the principles of exploration and exploitation of the search space.The proposed methodology consists of different phases,such as a clustering phase,a fault detection and classification phase,and a decision and diagnosis phase.The implemented methodology can diagnose composite faults,such as hard permanent,soft permanent,intermittent,and transient faults for sensor nodes as well as for links.The proposed implementation can also classify different types of faulty behavior for both sensor nodes and links in the network.We present the obtained theoretical results and computational complexity of the implemented model for this particular study on automated fault diagnosis.The performance of the model is evaluated using simulations and experiments conducted using indoor and outdoor testbeds.
基金Funded by Hubei Natural Science Foundation ( No. 2000J161)
文摘A system of impact damage detection for composite material structures by using an intelligent sensor embedded in composite material is described. In the course of signal processing, wavelet transform has the exceptional property of temporal frequency localization, whereas Kohonen artificial neural networks have excellent characteristics of self-learning and fault-tolerance. By combining the merits of abstracting time-frequency domain eigenvalues and improving the ratio of signal to noise in this system, impact damage in composite material can be properly recognized.
