In order to identify the multi-carrier orthogonal frequency division multiplexing(OFDM) and the single-carrier signal in the non-Gaussian noise environment, different features of the two signals are analyzed in terms ...In order to identify the multi-carrier orthogonal frequency division multiplexing(OFDM) and the single-carrier signal in the non-Gaussian noise environment, different features of the two signals are analyzed in terms of five parameters: generalized normalized fourth-order cumulant, the maximum value of the instantaneous amplitude power spectral density, absolute standard deviation of instantaneous phase on the section with weak signals, and position and numbers of the generalized cyclic spectrum's peak. The recognition method of the multi-carrier OFDM and single-carrier signal is proposed in the environment with alpha-stable distribution noise. Simulation results show that the recognition rate of the multi-carrier OFDM can reach 100% when the mixed signal to noise ratio(MSNR) is greater than-5 dB and the recognition rate can reach 90% for the single-carrier when the MSNR is greater than 2 dB.展开更多
Unlike the existing resonance region radar systems （RRRS ） that transmit the orthogonal frequency division multiplexing （OFDM）multi-carrier waveform,the dense multi-carrier （DMC）radar waveform which has a narrow...Unlike the existing resonance region radar systems （RRRS ） that transmit the orthogonal frequency division multiplexing （OFDM）multi-carrier waveform,the dense multi-carrier （DMC）radar waveform which has a narrower frequency interval than the traditional OFDM waveform is proposed.Therefore,in the same frequency bandwidth,the DMC waveform contains more sub-carriers and provides more frequency diversity.Additionally,to further improve detection performance,a novel optimal weight accumulation target detection （OWATD）method is proposed,where the echo electromagnetic waves at different frequencies are accumulated with the optimal weight coefficients.Then,with the signal-to-noise ratio （SNR）of echo waveform approaching infinity,the asymptotic detection performance is analyzed, and the condition that the OWATD method with the DMC outperforms the matched filter with the OFDM is presented.Simulation results show that the DMC outperforms the OFDM in the target detection performance,and the OWATD method can further improve the detection performance of the traditional methods with both the OFDM and DMC radar waveform.展开更多
Recognition methods of electromagnetic transients(EMT)have been widely used in power systems with the assumption that training and testing data are drawn from the same probability distribution.However,that assumption ...Recognition methods of electromagnetic transients(EMT)have been widely used in power systems with the assumption that training and testing data are drawn from the same probability distribution.However,that assumption is hard to satisfy in industrial applications because the distribution of measured EMT testing data generally changes over time.The performance of these methods gradually deteriorates with the distribution shift.The phenomenon limits application of EMT recognition methods.Therefore,this paper proposes a transfer learning-based recognition network(TLRN)for EMT to break the limitation.It consists of a feature extractor,EMT recognizer,domain recognizer,and maximum mean discrepancy(MMD).The feature extractor is constructed to learn features of EMT automatically.The domain recognizer and MMD make features learned by the feature extractor domain invariant.Based on domain invariant features,the EMT recognizer achieves accurate EMT recognition,despite the distribution discrepancy between EMT training and testing data.TLRN maintains satisfactory EMT recognition performance by updating periodically with an unsupervised learning strategy.Using EMT datasets measured from different substations,scenario experiments,and experiment comparisons are conducted,and the recognition performance of the proposed TLRN is demonstrated.展开更多
In deeply buried tunneling projects,geological conditions are often complex and varied.Microseismic monitoring systems are extensively deployed to enhance construction safety.However,when the current geological condit...In deeply buried tunneling projects,geological conditions are often complex and varied.Microseismic monitoring systems are extensively deployed to enhance construction safety.However,when the current geological conditions differ from those present during the signal collection for model training,recognition accuracy tends to decline significantly.Therefore,improving the applicability and stability of microseismic waveform recognition models across varying geological conditions has emerged as a critical challenge.To address this issue,we first analyze the impact of lithological changes and the development of structural planes on the features of microseismic waveforms.Subsequently,we propose a category-domain-aligned transfer learning method that enables the transfer of recognition capabilities across geological conditions by facilitating similar feature extraction and the recognition of cross-geological fracture waveforms.In this model,feature separation modeling enhances the extraction of category features of waveforms under different geological conditions.A deep transfer learning mechanism distinguishes between unique and common features,allowing for the capture of essential features necessary for model parameter updates.Through comparative experiments and feature distribution alignment and visualization,we demonstrate that the accuracy of microseismic waveform recognition across geological conditions achieves 90%.Additionally,the performance of our method is validated using microseismic signals collected from different sections of the construction site.展开更多
Target recognition performance can be affected by radar waveform parameters.In this paper,we established rigorous relationship between target recognition efficiency and the parameters of a repeatedly transmitted wavef...Target recognition performance can be affected by radar waveform parameters.In this paper,we established rigorous relationship between target recognition efficiency and the parameters of a repeatedly transmitted waveform.It is based on Kullback-Leibler Information Number of single observation(KLINs),which measures the dissimilarity between targets depicted by a range-velocity double spread density function in frequency domain.We considered two signal models which are different in the coherence of the observations.The method we proposed takes advantage of the methodology of sequential hypothesis test,and then the recognition performance in terms of correct classification rate is expressed by Receiver Operating Characteristic(ROC).Simulation results about the parameters of LFM signal show the validity of the method.展开更多
Underwater pulse waveform recognition is an important method for underwater object detection.Most existing works focus on the application of traditional pattern recognition methods,which ignore the time-and space-vary...Underwater pulse waveform recognition is an important method for underwater object detection.Most existing works focus on the application of traditional pattern recognition methods,which ignore the time-and space-varying characteristics in sound propagation channels and cannot easily extract valuable waveform features.Sound propagation channels in seawater are time-and space-varying convolutional channels.In the extraction of the waveform features of underwater acoustic signals,the effect of high-accuracy underwater acoustic signal recognition is identified by eliminating the influence of time-and space-varying convolutional channels to the greatest extent possible.We propose a hash aggregate discriminative network(HADN),which combines hash learning and deep learning to minimize the time-and space-varying effects on convolutional channels and adaptively learns effective underwater waveform features to achieve high-accuracy underwater pulse waveform recognition.In the extraction of the hash features of acoustic signals,a discrete constraint between clusters within a hash feature class is introduced.This constraint can ensure that the influence of convolutional channels on hash features is minimized.In addition,we design a new loss function called aggregate discriminative loss(AD-loss).The use of AD-loss and softmax-loss can increase the discriminativeness of the learned hash features.Experimental results show that on pool and ocean datasets,which were collected in pools and oceans,respectively,by using acoustic collectors,the proposed HADN performs better than other comparative models in terms of accuracy and mAP.展开更多
Terahertz(THz)wireless communication has been recognized as a powerful technology to meet the everincreasing demand of ultra-high rate services.In order to achieve efficient and reliable wireless communications over T...Terahertz(THz)wireless communication has been recognized as a powerful technology to meet the everincreasing demand of ultra-high rate services.In order to achieve efficient and reliable wireless communications over THz bands,it is extremely necessary to find an appropriate waveform for THz communications.In this paper,performance comparison of various single-carrier and multi-carrier waveforms over THz channels will be provided.Specifically,first,a system model for terahertz communication is briefly described,which includes amplifier nonlinearity,propagation characteristic,phase noise,etc.Then,the transceiver architectures related to both single-carrier and multi-carrier waveforms are presented,as well as their corresponding signal processing techniques.To evaluate the suitability of the waveforms,key performance metrics concerning power efficiency,transmission performance,and computational complexity are provided.Simulation results are provided to compare and validate the performance of different waveforms,which demonstrate the outstanding performance of Discrete-Fourier-Transform spread Orthogonal Frequency Division Multiplexing(DFT-s-OFDM)to THz communications when compared to Cyclic Prefix-OFDM(CP-OFDM)and other single-carrier waveforms.展开更多
Flying plots detection has been the focus of relay protection in power system for a long time. With the promotion of Smart substation in our country, the number of SV devices is greatly increased. Abnormal data (flyin...Flying plots detection has been the focus of relay protection in power system for a long time. With the promotion of Smart substation in our country, the number of SV devices is greatly increased. Abnormal data (flying plot) caused by sampling device itself has brought tremendous pressure to the power system. The traditional flying plot detection algorithm has plenty of defects, such as low pertinence, low sensitivity and long sampling period. This paper proposes a new algorithm to identify flying plot by analyzing the wave form characteristics of sampling data. The traditional waveform recognition methods are combined in this algorithm. It has the concept of standard wave window and can distinguish flying plot in a short time. In addition, sine recovery algorithm is used to recover the flying plot. This paper uses PSCAD software to verify the validity of this algorithm. Simulation results show that the proposed method has high reliability.展开更多
Fifth Generation(5G)systems aim to improve flexibility,coexistence and diverse service in several aspects to achieve the emerging applications requirements.Windowing and filtering of the traditional multicarrier wavef...Fifth Generation(5G)systems aim to improve flexibility,coexistence and diverse service in several aspects to achieve the emerging applications requirements.Windowing and filtering of the traditional multicarrier waveforms are now considered common sense when designing more flexible waveforms.This paper proposed a Universal Windowing Multi-Carrier(UWMC)waveform design platform that is flexible,providing more easily coexists with different pulse shapes,and reduces the Out of Band Emissions(OOBE),which is generated by the traditional multicarrier methods that used in the previous generations of the mobile technology.The novel proposed approach is different from other approaches that have been proposed,and it is based on applying a novel modulation approach for the Quadrature-Amplitude Modulation(64-QAM)which is considered very popular in mobile technology.This new approach is done by employing flexible pulse shaping windowing,by assigning windows to various bands.This leads to decreased side-lobes,which are going to reduce OOBE and boost the spectral efficiency by assigning them to edge subscribers only.The new subband windowing(UWMC)will also maintain comprehensively the non-orthogonality by a variety of windowing and make sure to keep window time the same for all subbands.In addition,this paper shows that the new approach made the Bit Error Rate(BER)equal to the conventional Windowed-Orthogonal Frequency Division Multiplexing(W-OFDM).This platform achieved great improvement for some other Key Performance Indicators(KPI),such as the Peak to Average Power Ratio(PAPR)compared with the conventional(W-OFDM)and the conventional Universal Filtered Multicarrier(UFMC)approaches.In particular,the proposed windowing scheme outperforms previous designs in terms of the Power Spectral Density(PSD)by 58%and the(BER)by 1.5 dB and reduces the Complementary Cumulative Distribution Function Cubic Metric(CCDF-CM)by 24%.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
基金Supported by the National Natural Science Foundation of China(No.61561031,61562058)the Natural Science Foundation of Gansu Province(No.1508RJZA054)
文摘In order to identify the multi-carrier orthogonal frequency division multiplexing(OFDM) and the single-carrier signal in the non-Gaussian noise environment, different features of the two signals are analyzed in terms of five parameters: generalized normalized fourth-order cumulant, the maximum value of the instantaneous amplitude power spectral density, absolute standard deviation of instantaneous phase on the section with weak signals, and position and numbers of the generalized cyclic spectrum's peak. The recognition method of the multi-carrier OFDM and single-carrier signal is proposed in the environment with alpha-stable distribution noise. Simulation results show that the recognition rate of the multi-carrier OFDM can reach 100% when the mixed signal to noise ratio(MSNR) is greater than-5 dB and the recognition rate can reach 90% for the single-carrier when the MSNR is greater than 2 dB.
基金The National Natural Science Foundation of China(No.61271204)the National Key Technology R&D Program during the 12th Five-Year Plan Period(No.2012BAH15B00)
文摘Unlike the existing resonance region radar systems （RRRS ） that transmit the orthogonal frequency division multiplexing （OFDM）multi-carrier waveform,the dense multi-carrier （DMC）radar waveform which has a narrower frequency interval than the traditional OFDM waveform is proposed.Therefore,in the same frequency bandwidth,the DMC waveform contains more sub-carriers and provides more frequency diversity.Additionally,to further improve detection performance,a novel optimal weight accumulation target detection （OWATD）method is proposed,where the echo electromagnetic waves at different frequencies are accumulated with the optimal weight coefficients.Then,with the signal-to-noise ratio （SNR）of echo waveform approaching infinity,the asymptotic detection performance is analyzed, and the condition that the OWATD method with the DMC outperforms the matched filter with the OFDM is presented.Simulation results show that the DMC outperforms the OFDM in the target detection performance,and the OWATD method can further improve the detection performance of the traditional methods with both the OFDM and DMC radar waveform.
基金supported by National Natural Science Foundation of China(51837002).
文摘Recognition methods of electromagnetic transients(EMT)have been widely used in power systems with the assumption that training and testing data are drawn from the same probability distribution.However,that assumption is hard to satisfy in industrial applications because the distribution of measured EMT testing data generally changes over time.The performance of these methods gradually deteriorates with the distribution shift.The phenomenon limits application of EMT recognition methods.Therefore,this paper proposes a transfer learning-based recognition network(TLRN)for EMT to break the limitation.It consists of a feature extractor,EMT recognizer,domain recognizer,and maximum mean discrepancy(MMD).The feature extractor is constructed to learn features of EMT automatically.The domain recognizer and MMD make features learned by the feature extractor domain invariant.Based on domain invariant features,the EMT recognizer achieves accurate EMT recognition,despite the distribution discrepancy between EMT training and testing data.TLRN maintains satisfactory EMT recognition performance by updating periodically with an unsupervised learning strategy.Using EMT datasets measured from different substations,scenario experiments,and experiment comparisons are conducted,and the recognition performance of the proposed TLRN is demonstrated.
基金supported by the National Natural Science Foundation of China(Grant Nos.U23A20297,52222810,52309126 and 52109116).
文摘In deeply buried tunneling projects,geological conditions are often complex and varied.Microseismic monitoring systems are extensively deployed to enhance construction safety.However,when the current geological conditions differ from those present during the signal collection for model training,recognition accuracy tends to decline significantly.Therefore,improving the applicability and stability of microseismic waveform recognition models across varying geological conditions has emerged as a critical challenge.To address this issue,we first analyze the impact of lithological changes and the development of structural planes on the features of microseismic waveforms.Subsequently,we propose a category-domain-aligned transfer learning method that enables the transfer of recognition capabilities across geological conditions by facilitating similar feature extraction and the recognition of cross-geological fracture waveforms.In this model,feature separation modeling enhances the extraction of category features of waveforms under different geological conditions.A deep transfer learning mechanism distinguishes between unique and common features,allowing for the capture of essential features necessary for model parameter updates.Through comparative experiments and feature distribution alignment and visualization,we demonstrate that the accuracy of microseismic waveform recognition across geological conditions achieves 90%.Additionally,the performance of our method is validated using microseismic signals collected from different sections of the construction site.
文摘Target recognition performance can be affected by radar waveform parameters.In this paper,we established rigorous relationship between target recognition efficiency and the parameters of a repeatedly transmitted waveform.It is based on Kullback-Leibler Information Number of single observation(KLINs),which measures the dissimilarity between targets depicted by a range-velocity double spread density function in frequency domain.We considered two signal models which are different in the coherence of the observations.The method we proposed takes advantage of the methodology of sequential hypothesis test,and then the recognition performance in terms of correct classification rate is expressed by Receiver Operating Characteristic(ROC).Simulation results about the parameters of LFM signal show the validity of the method.
基金partially supported by the National Key Research and Development Program of China(No.2018 AAA0100400)the Natural Science Foundation of Shandong Province(Nos.ZR2020MF131 and ZR2021ZD19)the Science and Technology Program of Qingdao(No.21-1-4-ny-19-nsh).
文摘Underwater pulse waveform recognition is an important method for underwater object detection.Most existing works focus on the application of traditional pattern recognition methods,which ignore the time-and space-varying characteristics in sound propagation channels and cannot easily extract valuable waveform features.Sound propagation channels in seawater are time-and space-varying convolutional channels.In the extraction of the waveform features of underwater acoustic signals,the effect of high-accuracy underwater acoustic signal recognition is identified by eliminating the influence of time-and space-varying convolutional channels to the greatest extent possible.We propose a hash aggregate discriminative network(HADN),which combines hash learning and deep learning to minimize the time-and space-varying effects on convolutional channels and adaptively learns effective underwater waveform features to achieve high-accuracy underwater pulse waveform recognition.In the extraction of the hash features of acoustic signals,a discrete constraint between clusters within a hash feature class is introduced.This constraint can ensure that the influence of convolutional channels on hash features is minimized.In addition,we design a new loss function called aggregate discriminative loss(AD-loss).The use of AD-loss and softmax-loss can increase the discriminativeness of the learned hash features.Experimental results show that on pool and ocean datasets,which were collected in pools and oceans,respectively,by using acoustic collectors,the proposed HADN performs better than other comparative models in terms of accuracy and mAP.
基金supported in part by the National Key R&D Program of China under Grant 2018YFB1801501in part by the National Natural Science Foundation of China under Grant 62101306supported by OPPO Research Fund。
文摘Terahertz(THz)wireless communication has been recognized as a powerful technology to meet the everincreasing demand of ultra-high rate services.In order to achieve efficient and reliable wireless communications over THz bands,it is extremely necessary to find an appropriate waveform for THz communications.In this paper,performance comparison of various single-carrier and multi-carrier waveforms over THz channels will be provided.Specifically,first,a system model for terahertz communication is briefly described,which includes amplifier nonlinearity,propagation characteristic,phase noise,etc.Then,the transceiver architectures related to both single-carrier and multi-carrier waveforms are presented,as well as their corresponding signal processing techniques.To evaluate the suitability of the waveforms,key performance metrics concerning power efficiency,transmission performance,and computational complexity are provided.Simulation results are provided to compare and validate the performance of different waveforms,which demonstrate the outstanding performance of Discrete-Fourier-Transform spread Orthogonal Frequency Division Multiplexing(DFT-s-OFDM)to THz communications when compared to Cyclic Prefix-OFDM(CP-OFDM)and other single-carrier waveforms.
文摘Flying plots detection has been the focus of relay protection in power system for a long time. With the promotion of Smart substation in our country, the number of SV devices is greatly increased. Abnormal data (flying plot) caused by sampling device itself has brought tremendous pressure to the power system. The traditional flying plot detection algorithm has plenty of defects, such as low pertinence, low sensitivity and long sampling period. This paper proposes a new algorithm to identify flying plot by analyzing the wave form characteristics of sampling data. The traditional waveform recognition methods are combined in this algorithm. It has the concept of standard wave window and can distinguish flying plot in a short time. In addition, sine recovery algorithm is used to recover the flying plot. This paper uses PSCAD software to verify the validity of this algorithm. Simulation results show that the proposed method has high reliability.
基金supported in part by the Ministry of Higher Education Malaysia through the Fundamental Research Grant Scheme(FRGS/1/2019/TK04/UTHM/02/8)the University Tun Hussein Onn Malaysia.
文摘Fifth Generation(5G)systems aim to improve flexibility,coexistence and diverse service in several aspects to achieve the emerging applications requirements.Windowing and filtering of the traditional multicarrier waveforms are now considered common sense when designing more flexible waveforms.This paper proposed a Universal Windowing Multi-Carrier(UWMC)waveform design platform that is flexible,providing more easily coexists with different pulse shapes,and reduces the Out of Band Emissions(OOBE),which is generated by the traditional multicarrier methods that used in the previous generations of the mobile technology.The novel proposed approach is different from other approaches that have been proposed,and it is based on applying a novel modulation approach for the Quadrature-Amplitude Modulation(64-QAM)which is considered very popular in mobile technology.This new approach is done by employing flexible pulse shaping windowing,by assigning windows to various bands.This leads to decreased side-lobes,which are going to reduce OOBE and boost the spectral efficiency by assigning them to edge subscribers only.The new subband windowing(UWMC)will also maintain comprehensively the non-orthogonality by a variety of windowing and make sure to keep window time the same for all subbands.In addition,this paper shows that the new approach made the Bit Error Rate(BER)equal to the conventional Windowed-Orthogonal Frequency Division Multiplexing(W-OFDM).This platform achieved great improvement for some other Key Performance Indicators(KPI),such as the Peak to Average Power Ratio(PAPR)compared with the conventional(W-OFDM)and the conventional Universal Filtered Multicarrier(UFMC)approaches.In particular,the proposed windowing scheme outperforms previous designs in terms of the Power Spectral Density(PSD)by 58%and the(BER)by 1.5 dB and reduces the Complementary Cumulative Distribution Function Cubic Metric(CCDF-CM)by 24%.
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。
