An Algorithm of Voice Activity Detection Based on EMD and Wavelet Entropy Ratio

A new method was proposed to identify speech-segment endpoints based on the empirical mode decomposition（EMD） and a new wavelet entropy ratio with improving the accuracy of voice activity detection.With the EMD, the noise signals can be decomposed into several intrinsic mode functions（IMFs）. Then the proposed wavelet energy entropy ratio can be used to extract the desired feature for each IMFs component. In view of the question that the method of voice endpoint detection based on the original wavelet entropy ratio cannot adapt to the low signal-to-noise ratio（SNR）condition, an appropriate positive constant was introduced to the basic wavelet energy entropy ratio with effectively improved discriminability between the speech and noise. After comparing the traditional wavelet energy entropy ratio with the proposed wavelet energy entropy ratio, the experiment results show that the proposed method is simple and fast. The speech endpoints can be accurately detected in low SNR environments.

Alcoholism Detection by Wavelet Energy Entropy and Linear Regression Classifier

Alcoholism is an unhealthy lifestyle associated with alcohol dependence.Not only does drinking for a long time leads to poor mental health and loss of self-control,but alcohol seeps into the bloodstream and shortens the lifespan of the body’s internal organs.Alcoholics often think of alcohol as an everyday drink and see it as a way to reduce stress in their lives because they cannot see the damage in their bodies and they believe it does not affect their physical health.As their drinking increases,they become dependent on alcohol and it affects their daily lives.Therefore,it is important to recognize the dangers of alcohol abuse and to stop drinking as soon as possible.To assist physicians in the diagnosis of patients with alcoholism,we provide a novel alcohol detection system by extracting image features of wavelet energy entropy from magnetic resonance imaging(MRI)combined with a linear regression classifier.Compared with the latest method,the 10-fold cross-validation experiment showed excellent results,including sensitivity 91.54±1.47%,specificity 93.66±1.34%,Precision 93.45±1.27%,accuracy 92.61±0.81%,F1 score 92.48±0.83%and MCC 85.26±1.62%.

Least-Square Support Vector Machine and Wavelet Selection for Hearing Loss Identification

Hearing loss(HL)is a kind of common illness,which can significantly reduce the quality of life.For example,HL often results in mishearing,misunderstanding,and communication problems.Therefore,it is necessary to provide early diagnosis and timely treatment for HL.This study investigated the advantages and disadvantages of three classical machine learning methods:multilayer perceptron(MLP),support vector machine(SVM),and least-square support vector machine(LS-SVM)approach andmade a further optimization of the LS-SVM model via wavelet entropy.The investigation illustrated that themultilayer perceptron is a shallowneural network,while the least square support vector machine uses hinge loss function and least-square optimizationmethod.Besides,a wavelet selection method was proposed,and we found db4 can achieve the best results.The experiments showed that the LS-SVM method can identify the hearing loss disease with an overall accuracy of three classes as 84.89±1.77,which is superior to SVM andMLP.The results show that the least-square support vector machine is effective in hearing loss identification.

WACPN:A Neural Network for Pneumonia Diagnosis

Community-acquired pneumonia(CAP)is considered a sort of pneumonia developed outside hospitals and clinics.To diagnose community-acquired pneumonia(CAP)more efficiently,we proposed a novel neural network model.We introduce the 2-dimensional wavelet entropy(2d-WE)layer and an adaptive chaotic particle swarm optimization(ACP)algorithm to train the feed-forward neural network.The ACP uses adaptive inertia weight factor(AIWF)and Rossler attractor(RA)to improve the performance of standard particle swarm optimization.The final combined model is named WE-layer ACP-based network(WACPN),which attains a sensitivity of 91.87±1.37%,a specificity of 90.70±1.19%,a precision of 91.01±1.12%,an accuracy of 91.29±1.09%,F1 score of 91.43±1.09%,an MCC of 82.59±2.19%,and an FMI of 91.44±1.09%.The AUC of this WACPN model is 0.9577.We find that the maximum deposition level chosen as four can obtain the best result.Experiments demonstrate the effectiveness of both AIWF and RA.Finally,this proposed WACPN is efficient in diagnosing CAP and superior to six state-of-the-art models.Our model will be distributed to the cloud computing environment.

Quantitative Diagnosis of Fault Severity Trend of Rolling Element Bearings

The condition monitoring and fault diagnosis of rolling element bearings are particularly crucial in rotating mechanical applications in industry. A bearing fault signal contains information not only about fault condition and fault type but also the severity of the fault. This means fault severity quantitative analysis is one of most active and valid ways to realize proper maintenance decision. Aiming at the deficiency of the research in bearing single point pitting fault quantitative diagnosis, a new back-propagation neural network method based on wavelet packet decomposition coefficient entropy is proposed. The three levels of wavelet packet coefficient entropy（WPCE） is introduced as a characteristic input vector to the BPNN. Compared with the wavelet packet decomposition energy ratio input vector, WPCE shows more sensitive in distinguishing from the different fault severity degree of the measured signal. The engineering application results show that the quantitative trend fault diagnosis is realized in the different fault degree of the single point bearing pitting fault. The breakthrough attempt from quantitative to qualitative on the pattern recognition of rolling element bearings fault diagnosis is realized.

A Fault Diagnosis Method Based on Wavelet Singular Entropy and SVM for VSC-HVDC Converter

The converter is the core component of voltage source converter-high voltage direct current(VSC-HVDC),which is related to the stable operation of the system.The converter has a complex structure where the accuracy of feature extraction is low,and the computation speed of traditional fault diagnosis strategies is slow.To solve this problem,a fault diagnosis strategy based on wavelet singular entropy(WSE)and support vector machine(SVM)was proposed.This method includes fault and label setting,converter fault feature extraction based on wavelet singular entropy,and converter fault classification based on support vector machine.The DC-side voltage signal was used as the detection signal,and the wavelet singular entropy was used for feature extraction to avoid noise interference.The classification is based on SVM.The experimental verification in PSCAD simulation proved that the method has better fault diagnosis ability for various faults and meets the needs of converter fault diagnosis.

Fault Feeder Identification in Non-effectively Grounded Distribution Network with Secondary Earth Fault

Secondary earth faults occur frequently in power distribution networks under harsh weather conditions.Owing to its characteristics,a secondary earth fault is typically hidden within the transient of the first fault.Therefore,most researchers tend to focus on a feeder with single fault while disregarding secondary faults.This paper presents a fault feeder identification method that considers secondary earth faults in a non-effectively grounded distribution network.First,the wavelet singular entropy method is used to detect a secondary fault event.This method can identify the moment at which a secondary fault occurs.The zero-sequence current data can be categorized into two fault stages.The first and second fault stages correspond to the first and secondary faults,respectively.Subsequently,a similarity matrix containing the time-frequency transient information of the zero-sequence current at the two fault stages is defined to identify the fault feeders.Finally,to confirm the effectiveness and reliability of the proposed method,we conduct simulation experiments and an adaptability analysis based on an electromagnetic transient program.

Pressure Analysis of the Initial Process of Diffusion Combustion Surge in a 350 kW Gas Boiler

In order to meet the increasingly stringent requirements for nitrogen oxides(NOx)emissions from gas boilers,flue gas recirculation(FGR)technology is commonly used to achieve ultra-low NOx emissions.However,under some ultra-low NOx combustion conditions with FGR,a surge phenomenon occurs in the boiler,which causes a flameout and should be avoided.In this study,the diffusion combustion surge of gas boiler with a rated power of 350 k W and equipped with FGR device was investigated.Pressure characteristic analysis results of the initial process of combustion surge showed that the high-frequency component of pressure is closely related to combustion stability and its change can provide reference for the occurrence of surge.Besides,the initial process of surge was analyzed by wavelet packet entropy method.Results indicated that the wavelet packet entropy of pressure signals could effectively reflect the stability of combustion in the furnace,and it could also be used to study the occurrence of surge.