A potential concept that could be effective for multiple applications is a“cyber-physical system”(CPS).The Internet of Things(IoT)has evolved as a research area,presenting new challenges in obtaining valuable data t...A potential concept that could be effective for multiple applications is a“cyber-physical system”(CPS).The Internet of Things(IoT)has evolved as a research area,presenting new challenges in obtaining valuable data through environmental monitoring.The existing work solely focuses on classifying the audio system of CPS without utilizing feature extraction.This study employs a deep learning method,CNN-LSTM,and two-way feature extraction to classify audio systems within CPS.The primary objective of this system,which is built upon a convolutional neural network(CNN)with Long Short Term Memory(LSTM),is to analyze the vocalization patterns of two different species of anurans.It has been demonstrated that CNNs,when combined with mel-spectrograms for sound analysis,are suitable for classifying ambient noises.Initially,the data is augmented and preprocessed.Next,the mel spectrogram features are extracted through two-way feature extraction.First,Principal Component Analysis(PCA)is utilized for dimensionality reduction,followed by Transfer learning for audio feature extraction.Finally,the classification is performed using the CNN-LSTM process.This methodology can potentially be employed for categorizing various biological acoustic objects and analyzing biodiversity indexes in natural environments,resulting in high classification accuracy.The study highlights that this CNNLSTM approach enables cost-effective and resource-efficient monitoring of large natural regions.The dissemination of updated CNN-LSTM models across distant IoT nodes is facilitated flexibly and dynamically through the utilization of CPS.展开更多
Wind turbine blades are prone to failure due to high tip speed,rain,dust and so on.A surface condition detecting approach based on wind turbine blade aerodynamic noise is proposed.On the experimental measurement data,...Wind turbine blades are prone to failure due to high tip speed,rain,dust and so on.A surface condition detecting approach based on wind turbine blade aerodynamic noise is proposed.On the experimental measurement data,variational mode decomposition filtering and Mel spectrogram drawing are conducted first.The Mel spectrogram is divided into two halves based on frequency characteristics and then sent into the convolutional neural network.Gaussian white noise is superimposed on the original signal and the output results are assessed based on score coefficients,considering the complexity of the real environment.The surfaces of Wind turbine blades are classified into four types:standard,attachments,polishing,and serrated trailing edge.The proposed method is evaluated and the detection accuracy in complicated background conditions is found to be 99.59%.In addition to support the differentiation of trained models,utilizing proper score coefficients also permit the screening of unknown types.展开更多
枪声识别技术在军事环境下可以快速准确地提供战场信息,但是目前大部分枪声识别系统均部署在服务器端,实用性和可行性不高,针对这一问题,本文设计了一种基于ZYNQ的枪声识别系统。该系统以ZYNQ7020芯片为核心,充分利用ZYNQ芯片集ARM与FPG...枪声识别技术在军事环境下可以快速准确地提供战场信息,但是目前大部分枪声识别系统均部署在服务器端,实用性和可行性不高,针对这一问题,本文设计了一种基于ZYNQ的枪声识别系统。该系统以ZYNQ7020芯片为核心,充分利用ZYNQ芯片集ARM与FPGA于一体的特性,首先在芯片的FPGA部分设计了多通道数据传输链路和声场特征参数提取模块;其次在芯片的ARM部分部署经过PC端训练后的轻量化网络模型,对经过FPGA提取的特征参数进行处理,进而实现对枪声种类的识别;最后使用枪声数据集NIJ Grant 2016-DN-BX-0183中的3种枪声在外场进行试验。试验结果表明,该系统能够准确地对枪声进行分类,枪声的平均识别率达到91.67%。该成果在枪声识别领域具有较强的应用价值。展开更多
基金Funded by Institutional Fund Projects under Grant No.IFPIP:236-611-1442 by Ministry of Education and King Abdulaziz University,Jeddah,Saudi Arabia(A.O.A.).
文摘A potential concept that could be effective for multiple applications is a“cyber-physical system”(CPS).The Internet of Things(IoT)has evolved as a research area,presenting new challenges in obtaining valuable data through environmental monitoring.The existing work solely focuses on classifying the audio system of CPS without utilizing feature extraction.This study employs a deep learning method,CNN-LSTM,and two-way feature extraction to classify audio systems within CPS.The primary objective of this system,which is built upon a convolutional neural network(CNN)with Long Short Term Memory(LSTM),is to analyze the vocalization patterns of two different species of anurans.It has been demonstrated that CNNs,when combined with mel-spectrograms for sound analysis,are suitable for classifying ambient noises.Initially,the data is augmented and preprocessed.Next,the mel spectrogram features are extracted through two-way feature extraction.First,Principal Component Analysis(PCA)is utilized for dimensionality reduction,followed by Transfer learning for audio feature extraction.Finally,the classification is performed using the CNN-LSTM process.This methodology can potentially be employed for categorizing various biological acoustic objects and analyzing biodiversity indexes in natural environments,resulting in high classification accuracy.The study highlights that this CNNLSTM approach enables cost-effective and resource-efficient monitoring of large natural regions.The dissemination of updated CNN-LSTM models across distant IoT nodes is facilitated flexibly and dynamically through the utilization of CPS.
基金funded by the National Nature Science Founda-tion of China(Grant Nos.51905469 and 11672261)the National key research and development program of China under grant number(Grant No.2019YFE0192600)。
文摘Wind turbine blades are prone to failure due to high tip speed,rain,dust and so on.A surface condition detecting approach based on wind turbine blade aerodynamic noise is proposed.On the experimental measurement data,variational mode decomposition filtering and Mel spectrogram drawing are conducted first.The Mel spectrogram is divided into two halves based on frequency characteristics and then sent into the convolutional neural network.Gaussian white noise is superimposed on the original signal and the output results are assessed based on score coefficients,considering the complexity of the real environment.The surfaces of Wind turbine blades are classified into four types:standard,attachments,polishing,and serrated trailing edge.The proposed method is evaluated and the detection accuracy in complicated background conditions is found to be 99.59%.In addition to support the differentiation of trained models,utilizing proper score coefficients also permit the screening of unknown types.
文摘枪声识别技术在军事环境下可以快速准确地提供战场信息,但是目前大部分枪声识别系统均部署在服务器端,实用性和可行性不高,针对这一问题,本文设计了一种基于ZYNQ的枪声识别系统。该系统以ZYNQ7020芯片为核心,充分利用ZYNQ芯片集ARM与FPGA于一体的特性,首先在芯片的FPGA部分设计了多通道数据传输链路和声场特征参数提取模块;其次在芯片的ARM部分部署经过PC端训练后的轻量化网络模型,对经过FPGA提取的特征参数进行处理,进而实现对枪声种类的识别;最后使用枪声数据集NIJ Grant 2016-DN-BX-0183中的3种枪声在外场进行试验。试验结果表明,该系统能够准确地对枪声进行分类,枪声的平均识别率达到91.67%。该成果在枪声识别领域具有较强的应用价值。
