The efficient processing of large amounts of data collected by the microseismic monitoring system(MMS),especially the rapid identification of microseismic events in explosions and noise,is essential for mine disaster ...The efficient processing of large amounts of data collected by the microseismic monitoring system(MMS),especially the rapid identification of microseismic events in explosions and noise,is essential for mine disaster prevention.Currently,this work is primarily performed by skilled technicians,which results in severe workloads and inefficiency.In this paper,CNN-based transfer learning combined with computer vision technology was used to achieve automatic recognition and classification of multichannel microseismic signal waveforms.First,data collected by MMS was generated into 6-channel original waveforms based on events.After that,sample data sets of microseismic events,blasts,drillings,and noises were established through manual identification.These datasets were split into training sets and test sets according to a certain proportion,and transfer learning was performed on AlexNet,GoogLeNet,and ResNet50 pre-training network models,respectively.After training and tuning,optimal models were retained and compared with support vector machine classification.Results show that transfer learning models perform well on different test sets.Overall,GoogLeNet performed best,with a recognition accuracy of 99.8%.Finally,the possible effects of the number of training sets and the imbalance of different types of sample data on the accuracy and effectiveness of classification models were discussed.展开更多
Manually picking regularly and densely distributed first breaks(FBs)are critical for shallow velocitymodel building in seismic data processing.However,it is time consuming.We employ the fullyconvolutional Seg Net to a...Manually picking regularly and densely distributed first breaks(FBs)are critical for shallow velocitymodel building in seismic data processing.However,it is time consuming.We employ the fullyconvolutional Seg Net to address this issue and present a fast automatic seismic waveform classification method to pick densely-sampled FBs directly from common-shot gathers with sparsely distributed traces.Through feeding a large number of representative shot gathers with missing traces and the corresponding binary labels segmented by manually interpreted fully-sampled FBs,we can obtain a welltrained Seg Net model.When any unseen gather including the one with irregular trace spacing is inputted,the Seg Net can output the probability distribution of different categories for waveform classification.Then FBs can be picked by locating the boundaries between one class on post-FBs data and the other on pre-FBs background.Two land datasets with each over 2000 shots are adopted to illustrate that one well-trained 25-layer Seg Net can favorably classify waveform and further pick fully-sampled FBs verified by the manually-derived ones,even when the proportion of randomly missing traces reaches50%,21 traces are missing consecutively,or traces are missing regularly.展开更多
Waveforms of artificially induced explosions and collapse events recorded by the seismic network share similarities with natural earthquakes.Failure to identify and screen them in a timely manner can introduce confusi...Waveforms of artificially induced explosions and collapse events recorded by the seismic network share similarities with natural earthquakes.Failure to identify and screen them in a timely manner can introduce confusion into the earthquake catalog established using these recordings,thereby impacting future seismological research.Therefore,the identification and separation of natural earthquakes from continuous seismic signals contribute to the monitoring and early warning of destructive tectonic earthquakes.A 1D convolutional neural network(CNN)is proposed for seismic event classification using an efficient channel attention mechanism and an improved light inception block.A total of 9937 seismic sample records are obtained after waveform interception,filtering,and normalization.The proposed model can obtain better classification performance than other major existing methods,exhibiting 96.79%overall classification accuracy and 96.73%,94.85%,and 96.35%classification accuracy for natural seismic events,collapse events,and blasting events,respectively.Meanwhile,the proposed model is lighter than the 2D convolutional and common inception networks.We also apply the proposed model to the seismic data recorded at the University of Utah seismograph stations and compare its performance with that of the CNN-waveform model.展开更多
A variable-bit-rate characteristic waveform interpolation （VBR-CWI） speech codec with about 1.8 kbit/s average bit rate which integrates phonetic classification into characteristic waveform （CW） decomposition is p...A variable-bit-rate characteristic waveform interpolation （VBR-CWI） speech codec with about 1.8 kbit/s average bit rate which integrates phonetic classification into characteristic waveform （CW） decomposition is proposed. Each input frame is classified into one of 4 phonetic classes. Non-speech frames are represented with Bark-band noise model. The extracted CWs become rapidly evolving waveforms （REWs） or slowly evolving waveforms （SEWs） in the cases of unvoiced or stationary voiced frames respectively, while mixed voiced frames use the same CW decomposition as that in the conventional CWI. Experimental results show that the proposed codec can eliminate most buzzy and noisy artifacts existing in the fixed-bit-rate characteristic waveform interpolation （FBR-CWI） speech codec, the average bit rate can be much lower, and its reconstructed speech quality is much better than FS 1 016 CELP at 4.8 kbit/s and similar to G. 723.1 ACELP at 5.3 kbit/s.展开更多
Microseismic monitoring system is one of the effective methods for deep mining geo-stress monitoring.The principle of microseismic monitoring system is to analyze the mechanical parameters contained in microseismic ev...Microseismic monitoring system is one of the effective methods for deep mining geo-stress monitoring.The principle of microseismic monitoring system is to analyze the mechanical parameters contained in microseismic events for providing accurate information of rockmass.The accurate identification of microseismic events and blasts determines the timeliness and accuracy of early warning of microseismic monitoring technology.An image identification model based on Convolutional Neural Network(CNN)is established in this paper for the seismic waveforms of microseismic events and blasts.Firstly,the training set,test set,and validation set are collected,which are composed of 5250,1500,and 750 seismic waveforms of microseismic events and blasts,respectively.The classified data sets are preprocessed and input into the constructed CNN in CPU mode for training.Results show that the accuracies of microseismic events and blasts are 99.46%and 99.33%in the test set,respectively.The accuracies of microseismic events and blasts are 100%and 98.13%in the validation set,respectively.The proposed method gives superior performance when compared with existed methods.The accuracies of models using logistic regression and artificial neural network(ANN)based on the same data set are 54.43%and 67.9%in the test set,respectively.Then,the ROC curves of the three models are obtained and compared,which show that the CNN gives an absolute advantage in this classification model when the original seismic waveform are used in training the model.It not only decreases the influence of individual differences in experience,but also removes the errors induced by source and waveform parameters.It is proved that the established discriminant method improves the efficiency and accuracy of microseismic data processing for monitoring rock instability and seismicity.展开更多
目的训练多种机器学习模型用于听性脑干反应(auditory brainstem response,ABR)波形的自动识别,并确定准确率最高的模型,使ABR自动识别技术更好地应用于临床实践。方法选取2021年6月至2022年6月北京清华长庚医院收治的100例听力正常和...目的训练多种机器学习模型用于听性脑干反应(auditory brainstem response,ABR)波形的自动识别,并确定准确率最高的模型,使ABR自动识别技术更好地应用于临床实践。方法选取2021年6月至2022年6月北京清华长庚医院收治的100例听力正常和伴有听力损伤人群的受试者(200耳)为研究对象,根据年龄和听力水平将受试者分为组1(年龄18~59岁,500、1000、2000、4000 Hz频率平均听阈≤25 dB HL)、组2(年龄≥60岁,500、1000、2000、4000 Hz频率平均听阈≤25 dB HL)、组3(年龄18~59岁,500、1000、2000、4000 Hz频率平均听阈>25 dB HL)、组4(年龄≥60岁,500、1000、2000、4000 Hz频率平均听阈>25 dB HL),每组25例。收集受试者纯音测听和ABR数据,提取ABR信号时域和频域特征,与受试者年龄、性别、纯音听阈,刺激声强度以及原始信号序列拼接得到特征向量。分别使用逻辑回归、支持向量机分类、伯努利朴素贝叶斯分类、高斯朴素贝叶斯分类、高斯过程分类、决策树、随机森林、表格网络、轻量化梯度提升框架、极致梯度提升框架和局部级联集成。等机器学习模型对ABR波形进行识别训练,并对整体数据和分组数据分别计算不同模型下波形识别的准确率。结果高斯过程分类模型的整体准确率达到了94.89%,超过了其他机器学习模型。其中95.62%为<60岁听力正常受试者、92.19%为≥60岁听力正常受试者、92.92%为<60岁伴有听力损失受试者、92.50%为≥60岁且伴有听力损失受试者。结论机器学习技术在ABR波形的自动识别方面具有良好的应用前景,高斯过程分类模型优于其他机器学习模型。展开更多
Automotive radar has emerged as a critical component in Advanced Driver Assistance Systems(ADAS)and autonomous driving,enabling robust environmental perception through precise range-Doppler and angular measurements.It...Automotive radar has emerged as a critical component in Advanced Driver Assistance Systems(ADAS)and autonomous driving,enabling robust environmental perception through precise range-Doppler and angular measurements.It plays a pivotal role in enhancing road safety by supporting accurate detection and localization of surrounding objects.However,real-world deployment of automotive radar faces significant challenges,including mutual interference among radar units and dense clutter due to multiple dynamic targets,which demand advanced signal processing solutions beyond conventional methodologies.This paper presents a comprehensive review of traditional signal processing techniques and recent advancements specifically designed to address contemporary operational challenges in automotive radar.Emphasis is placed on direction-of-arrival(DoA)estimation algorithms such as Bartlett beamforming,Minimum Variance Distortionless Response(MVDR),Multiple Signal Classification(MUSIC),and Estimation of Signal Parameters via Rotational Invariance Techniques(ESPRIT).Among these,ESPRIT offers superior resolution for multi-target scenarios with reduced computational complexity compared to MUSIC,making it particularly advantageous for real-time applications.Furthermore,the study evaluates state-of-the-art tracking algorithms,including the Kalman Filter(KF),Extended KF(EKF),Unscented KF,and Bayesian filter.EKF is especially suitable for radar systems due to its capability to linearize nonlinear measurement models.The integration of machine learning approaches for target detection and classification is also discussed,highlighting the trade-off between the simplicity of implementation in K-Nearest Neighbors(KNN)and the enhanced accuracy provided by Support Vector Machines(SVM).A brief overview of benchmark radar datasets,performance metrics,and relevant standards is included to support future research.The paper concludes by outlining ongoing challenges and identifying promising research directions in automotive radar signal processing,particularly in the context of increasingly complex traffic scenarios and autonomous navigation systems.展开更多
基金the National Key R&D Program of China(No.2021YFC2900500).
文摘The efficient processing of large amounts of data collected by the microseismic monitoring system(MMS),especially the rapid identification of microseismic events in explosions and noise,is essential for mine disaster prevention.Currently,this work is primarily performed by skilled technicians,which results in severe workloads and inefficiency.In this paper,CNN-based transfer learning combined with computer vision technology was used to achieve automatic recognition and classification of multichannel microseismic signal waveforms.First,data collected by MMS was generated into 6-channel original waveforms based on events.After that,sample data sets of microseismic events,blasts,drillings,and noises were established through manual identification.These datasets were split into training sets and test sets according to a certain proportion,and transfer learning was performed on AlexNet,GoogLeNet,and ResNet50 pre-training network models,respectively.After training and tuning,optimal models were retained and compared with support vector machine classification.Results show that transfer learning models perform well on different test sets.Overall,GoogLeNet performed best,with a recognition accuracy of 99.8%.Finally,the possible effects of the number of training sets and the imbalance of different types of sample data on the accuracy and effectiveness of classification models were discussed.
基金financially supported by the National Key R&D Program of China(2018YFA0702504)the Fundamental Research Funds for the Central Universities(2462019QNXZ03)+1 种基金the National Natural Science Foundation of China(42174152 and 41974140)the Strategic Cooperation Technology Projects of CNPC and CUPB(ZLZX 2020-03)。
文摘Manually picking regularly and densely distributed first breaks(FBs)are critical for shallow velocitymodel building in seismic data processing.However,it is time consuming.We employ the fullyconvolutional Seg Net to address this issue and present a fast automatic seismic waveform classification method to pick densely-sampled FBs directly from common-shot gathers with sparsely distributed traces.Through feeding a large number of representative shot gathers with missing traces and the corresponding binary labels segmented by manually interpreted fully-sampled FBs,we can obtain a welltrained Seg Net model.When any unseen gather including the one with irregular trace spacing is inputted,the Seg Net can output the probability distribution of different categories for waveform classification.Then FBs can be picked by locating the boundaries between one class on post-FBs data and the other on pre-FBs background.Two land datasets with each over 2000 shots are adopted to illustrate that one well-trained 25-layer Seg Net can favorably classify waveform and further pick fully-sampled FBs verified by the manually-derived ones,even when the proportion of randomly missing traces reaches50%,21 traces are missing consecutively,or traces are missing regularly.
基金supported by the Jiangsu Provincial Key R&D Programme 261(BE2020116,BE2022154).
文摘Waveforms of artificially induced explosions and collapse events recorded by the seismic network share similarities with natural earthquakes.Failure to identify and screen them in a timely manner can introduce confusion into the earthquake catalog established using these recordings,thereby impacting future seismological research.Therefore,the identification and separation of natural earthquakes from continuous seismic signals contribute to the monitoring and early warning of destructive tectonic earthquakes.A 1D convolutional neural network(CNN)is proposed for seismic event classification using an efficient channel attention mechanism and an improved light inception block.A total of 9937 seismic sample records are obtained after waveform interception,filtering,and normalization.The proposed model can obtain better classification performance than other major existing methods,exhibiting 96.79%overall classification accuracy and 96.73%,94.85%,and 96.35%classification accuracy for natural seismic events,collapse events,and blasting events,respectively.Meanwhile,the proposed model is lighter than the 2D convolutional and common inception networks.We also apply the proposed model to the seismic data recorded at the University of Utah seismograph stations and compare its performance with that of the CNN-waveform model.
文摘A variable-bit-rate characteristic waveform interpolation （VBR-CWI） speech codec with about 1.8 kbit/s average bit rate which integrates phonetic classification into characteristic waveform （CW） decomposition is proposed. Each input frame is classified into one of 4 phonetic classes. Non-speech frames are represented with Bark-band noise model. The extracted CWs become rapidly evolving waveforms （REWs） or slowly evolving waveforms （SEWs） in the cases of unvoiced or stationary voiced frames respectively, while mixed voiced frames use the same CW decomposition as that in the conventional CWI. Experimental results show that the proposed codec can eliminate most buzzy and noisy artifacts existing in the fixed-bit-rate characteristic waveform interpolation （FBR-CWI） speech codec, the average bit rate can be much lower, and its reconstructed speech quality is much better than FS 1 016 CELP at 4.8 kbit/s and similar to G. 723.1 ACELP at 5.3 kbit/s.
基金Projects(51822407,51774327,51664016)supported by the National Natural Science Foundation of China。
文摘Microseismic monitoring system is one of the effective methods for deep mining geo-stress monitoring.The principle of microseismic monitoring system is to analyze the mechanical parameters contained in microseismic events for providing accurate information of rockmass.The accurate identification of microseismic events and blasts determines the timeliness and accuracy of early warning of microseismic monitoring technology.An image identification model based on Convolutional Neural Network(CNN)is established in this paper for the seismic waveforms of microseismic events and blasts.Firstly,the training set,test set,and validation set are collected,which are composed of 5250,1500,and 750 seismic waveforms of microseismic events and blasts,respectively.The classified data sets are preprocessed and input into the constructed CNN in CPU mode for training.Results show that the accuracies of microseismic events and blasts are 99.46%and 99.33%in the test set,respectively.The accuracies of microseismic events and blasts are 100%and 98.13%in the validation set,respectively.The proposed method gives superior performance when compared with existed methods.The accuracies of models using logistic regression and artificial neural network(ANN)based on the same data set are 54.43%and 67.9%in the test set,respectively.Then,the ROC curves of the three models are obtained and compared,which show that the CNN gives an absolute advantage in this classification model when the original seismic waveform are used in training the model.It not only decreases the influence of individual differences in experience,but also removes the errors induced by source and waveform parameters.It is proved that the established discriminant method improves the efficiency and accuracy of microseismic data processing for monitoring rock instability and seismicity.
文摘目的训练多种机器学习模型用于听性脑干反应(auditory brainstem response,ABR)波形的自动识别,并确定准确率最高的模型,使ABR自动识别技术更好地应用于临床实践。方法选取2021年6月至2022年6月北京清华长庚医院收治的100例听力正常和伴有听力损伤人群的受试者(200耳)为研究对象,根据年龄和听力水平将受试者分为组1(年龄18~59岁,500、1000、2000、4000 Hz频率平均听阈≤25 dB HL)、组2(年龄≥60岁,500、1000、2000、4000 Hz频率平均听阈≤25 dB HL)、组3(年龄18~59岁,500、1000、2000、4000 Hz频率平均听阈>25 dB HL)、组4(年龄≥60岁,500、1000、2000、4000 Hz频率平均听阈>25 dB HL),每组25例。收集受试者纯音测听和ABR数据,提取ABR信号时域和频域特征,与受试者年龄、性别、纯音听阈,刺激声强度以及原始信号序列拼接得到特征向量。分别使用逻辑回归、支持向量机分类、伯努利朴素贝叶斯分类、高斯朴素贝叶斯分类、高斯过程分类、决策树、随机森林、表格网络、轻量化梯度提升框架、极致梯度提升框架和局部级联集成。等机器学习模型对ABR波形进行识别训练,并对整体数据和分组数据分别计算不同模型下波形识别的准确率。结果高斯过程分类模型的整体准确率达到了94.89%,超过了其他机器学习模型。其中95.62%为<60岁听力正常受试者、92.19%为≥60岁听力正常受试者、92.92%为<60岁伴有听力损失受试者、92.50%为≥60岁且伴有听力损失受试者。结论机器学习技术在ABR波形的自动识别方面具有良好的应用前景,高斯过程分类模型优于其他机器学习模型。
基金supported in part by the National Science and Technology Council,Taiwan:NSTC 113-2410-H-030-077-MY2.
文摘Automotive radar has emerged as a critical component in Advanced Driver Assistance Systems(ADAS)and autonomous driving,enabling robust environmental perception through precise range-Doppler and angular measurements.It plays a pivotal role in enhancing road safety by supporting accurate detection and localization of surrounding objects.However,real-world deployment of automotive radar faces significant challenges,including mutual interference among radar units and dense clutter due to multiple dynamic targets,which demand advanced signal processing solutions beyond conventional methodologies.This paper presents a comprehensive review of traditional signal processing techniques and recent advancements specifically designed to address contemporary operational challenges in automotive radar.Emphasis is placed on direction-of-arrival(DoA)estimation algorithms such as Bartlett beamforming,Minimum Variance Distortionless Response(MVDR),Multiple Signal Classification(MUSIC),and Estimation of Signal Parameters via Rotational Invariance Techniques(ESPRIT).Among these,ESPRIT offers superior resolution for multi-target scenarios with reduced computational complexity compared to MUSIC,making it particularly advantageous for real-time applications.Furthermore,the study evaluates state-of-the-art tracking algorithms,including the Kalman Filter(KF),Extended KF(EKF),Unscented KF,and Bayesian filter.EKF is especially suitable for radar systems due to its capability to linearize nonlinear measurement models.The integration of machine learning approaches for target detection and classification is also discussed,highlighting the trade-off between the simplicity of implementation in K-Nearest Neighbors(KNN)and the enhanced accuracy provided by Support Vector Machines(SVM).A brief overview of benchmark radar datasets,performance metrics,and relevant standards is included to support future research.The paper concludes by outlining ongoing challenges and identifying promising research directions in automotive radar signal processing,particularly in the context of increasingly complex traffic scenarios and autonomous navigation systems.
