Feature Extraction Parameters Research Articles

A predictive framework for PEMFC dynamic load performance degradation based on feature parameter analysis

Accurate and swift estimation of the future performance degradation of Proton Exchange Membrane Fuel Cells (PEMFCs) is crucial for the health management of PEMFC. However, most existing studies primarily concentrate on uncovering the inherent patterns of performance degradation parameters, neglecting the fundamental relationships and pattern variations between performance degradation and other characteristic parameters (such as flow rate, temperature, and pressure). This paper seeks to address this research gap. To that end, we delve into feature parameters, extracting underlying patterns of feature evolution to construct a feature exploration-based framework for predicting PEMFC performance degradation. Initially, Time-Varying Filtered Empirical Mode Decomposition (TVF-EMD) is employed to decompose each feature variable, isolating the core information of the features. Furthermore, to reduce the computational burden caused by redundant features, Uniform Manifold Approximation and Projection (UMAP) is used to perform dimensionality reduction on the decomposed feature subsequences, ensuring the efficiency and representativeness of the extracted features. Finally, to overcome the shortcomings of long short-term memory networks (LSTM) in terms of convergence and the effective use of time series information, we introduce an innovative Mogrifier LSTM (M-LSTM) model to enhance the accuracy of PEMFC performance degradation predictions. The experimental and validation results demonstrate that the extraction of feature parameters significantly enhances the predictive precision of the baseline model. Relative to the compared models, there was an improvement of at least 16.859% in Root Mean Square Error (RMSE), a minimum increase of 23.333% in Mean Absolute Error (MAE), and a boost of no less than 0.913% in the coefficient of determination (R2). Simultaneously, the proposed predictive framework demonstrates good stability and accuracy in predicting PEMFC performance degradation.

A Study on Speech Recognition by a Neural Network Based on English Speech Feature Parameters

In this study, from the perspective of English speech feature parameters, two feature parameters, the mel-frequency cepstral coefficient (MFCC) and filter bank (Fbank), were selected to identify English speech. The algorithms used for recognition employed the classical back-propagation neural network (BPNN), recurrent neural network (RNN), and long short-term memory (LSTM) that were obtained by improving RNN. The three recognition algorithms were compared in the experiments, and the effects of the two feature parameters on the performance of the recognition algorithms were also compared. The LSTM model had the best identification performance among the three neural networks under different experimental environments; the neural network model using the MFCC feature parameter outperformed the neural network using the Fbank feature parameter; the LSTM model had the highest correct rate and the highest speed, while the RNN model ranked second, and the BPNN model ranked worst. The results confirm that the application of the LSTM model in combination with MFCC feature parameter extraction to English speech recognition can achieve higher speech recognition accuracy compared to other neural networks.

Intelligent speech elderly rehabilitation learning assistance system based on deep learning and sensor networks

Recently, deep learning has been proved to significantly improve the quality of speech recognition. Convolutional neural networks are often used in speech recognition tasks because of their special network structure and powerful learning function. In order to solve the problem that the traditional convolutional neural network can not reflect the one-dimensional basic attributes of speech signal, this paper proposes to set the number of frames for one dimension of convolution kernel, and use one-dimensional model and two-dimensional convolutional network model for speech recognition. By moving the convolution kernel of time axis and frequency band, it can adapt to the time change of speech signal and maintain the correlation between frequency bands to a great extent. At the same time, this paper also discusses the speech signal preprocessing, feature parameter extraction and regularization algorithm. Due to the lack of hospital resources, the lag of information technology, the poor ability of accompanying and other reasons, the current accompanying service for elderly rehabilitation can not meet the needs of elderly patients. The rapid development and wide use of information technology provide opportunities for the optimization of health services for the elderly. In view of the difficulty of word memory and interpretation in current rehabilitation courses, a VR intelligent teaching system based on intelligent voice technology is developed. The application results show that the system can effectively improve the ability of language expression and word writing. At present, the system of intelligent speech function has not been completed, and lacks speech synthesis function. The next research will focus on the use of speech synthesis technology, in order to realize the man-machine dialogue between people and the system, and show a more real training situation.

Research Progress and Prospect of Condition Assessment Techniques for Oil–Paper Insulation Used in Power Systems: A Review

Oil–paper insulation is the critical insulation element in the modern power system. Under a harsh operating environment, oil–paper insulation will deteriorate gradually, resulting in electrical accidents. Thus, it is important to evaluate and monitor the insulation state of oil–paper insulation. Firstly, this paper introduces the geometric structure and physical components of oil–paper insulation and shows the main reasons and forms of oil–paper insulation’s degradation. Then, this paper reviews the existing condition assessment techniques for oil–paper insulation, such as the dissolved gas ratio analysis, aging kinetic model, cellulose–water adsorption isotherm, oil–paper moisture balance curve, and dielectric response technique. Additionally, the advantages and limitations of the above condition assessment techniques are discussed. In particular, this paper highlights the dielectric response technique and introduces its evaluation principle in detail: (1) collecting the dielectric response data, (2) extracting the feature parameters from the collected dielectric response data, and (3) establishing the condition assessment models based on the extracted feature parameters and the machine learning techniques. Finally, two full potential studies are proposed, which research hotspots’ oil–paper insulation and the electrical–chemical joint evaluation technique. In summary, this paper concludes the principles, advantages and limitation of the existing condition assessment techniques for oil–paper insulation, and we put forward two potential research avenues.

Generation of meter-scale nanosecond pulsed DBD and the intelligent evaluation based on multi-dimensional feature parameter extraction

This study introduces a novel meter-scale dielectric barrier discharge (m-DBD) reactor designed to generate large-scale, low-temperature nanosecond pulsed discharge plasma. By employing a modularized gas path, this reactor enables a comprehensive analysis of discharge patterns and uniformity using multi-dimensional discharge parameters. Simulation results reveal optimal gas distribution with ten gas holes in the variable plate and a 40 mm slit depth in the main reactor. Besides, a diagnosis method based on electro-acoustic-spectrum-image (E-A-S-I) parameters is developed to evaluate nanosecond pulsed m-DBD discharge states. It is found that the discharge states are closely related to the consistency of segmental discharge currents, the fluctuation of acoustic signals and the distribution of active particles. Machine learning methods are established to realize the diagnosis of m-DBD discharge pattern and uniformity by E-A-S-I parameters, where the optimized BPNN has a best recognition accuracy of 97.5%. Furthermore, leveraging nanosecond pulse power in Ar/m-DBD enables stable 1120 × 70 mm2 discharge, uniformly enhancing hydrophobicity of large-scale materials from a 67° to 122° water contact angle with maximal fluctuations below 7%. The modularized m-DBD reactor and its intelligent analysis based on multi-dimensional parameter provide a crucial foundation for advancing large-scale nanosecond pulsed plasma and their industrial applications.

Unconventional Wells Interference: Supervised Machine Learning for Detecting Fracture Hits

The primary objective of the study was development of a machine learning (ML)-based workflow for fracture hit (“frac hit”) detection and monitoring using shale oil-field data such as drilling surveys, production history (oil and produced water), pressure, and fracking start time and duration records. The ML method takes advantage of long short-term memory (LSTM) and multilayer perceptron (MLP) neural networks to identify the frac hits due to hydraulic communication between the fracking child well(s) and the producing parent well(s) within the same pad (intra-pad interaction) and/or on different pads (inter-pad interaction). It utilizes time series of pressure and production data from within a pad and from adjacent pads. The workflow can capture time variable features of frac hits when the model architecture is deep and wide enough, with enough trainable parameters for deep learning and feature extraction, as demonstrated in this paper by using training and testing subsets of the field data from selected neighboring pads with over a couple of hundred wells. The study was focused on frac-hit interaction among paired wells and demonstrated that the ML model, once trained, can predict the frac-hit probability.

Acoustic tunnel lining cavity detection using cepstral coefficients with optimized filter bank

Tunnels are an essential component of modern transportation infrastructure, and their structural health is critical to traffic safety, which can be seriously affected by tunnel lining cavities. In this paper, an acoustic-based detection approach for assessing the integrity of tunnel linings is studied. By tapping the tunnel lining surface, acoustic signals are sampled and analyzed using a novel feature parameter extraction algorithm-the energy-frequency cepstral coefficient, which uses wavelet packet decomposition to obtain energy distribution statistics in the frequency domain of the signal, and constructs a signal-dependent filter bank to achieve the cepstral coefficient extraction. Compared with the traditional Mel filter bank, this method can adaptively adjust the resolution of the filter bank according to the frequency characteristics of the classified samples. This allows for higher frequency resolution in regions where the energy distribution is concentrated. As a result, the extracted feature parameters achieve both dimensional compression and superior information retention. Experimental results show that the proposed energy-frequency cepstral coefficient feature outperforms the traditional Mel-frequency cepstral coefficient feature, resulting in a higher accuracy of tunnel lining detection. The convolutional neural network model achieves an accuracy of 99.2%, with a 78.9% reduction in error rate compared with the traditional Mel-frequency cepstral coefficient feature parameters. Additionally, a particle swarm optimization support vector machine model is trained to achieve an accuracy rate of 99.6% and an error rate reduction of 76.5%.

Extraction and recognition of breast morphological feature parameters based on machine learning models

Extraction and recognition of breast morphological feature parameters based on machine learning models

Wavelet Transform and SVM Based Heart Disease Monitoring for Flexible Wearable Devices

INTRODUCTION: Heart disease has been a major health challenge globally, therefore the development of reliable and real-time heart disease monitoring methods is crucial for the prevention and management of heart health. The aim of this study is to explore a flexible wearable device approach based on wavelet transform and support vector machine (SVM) to improve the accuracy and portability of heart disease monitoring. OBJECTIVES: The main objective of this study is to develop a wearable device that combines wavelet transform and SVM techniques to achieve accurate monitoring of physiological signals of heart diseases. METHODS: An integrated method for heart disease monitoring was constructed using flexible sensor technology combined with a wavelet transform and support vector machine. The Marr wavelet transform was applied to the ECG signals, and the feature vectors were constructed by feature parameter extraction. Then, the radial basis kernel SVM was utilized to identify the three ECG signals. The performance of the algorithm was optimized by adjusting the SVM parameters to improve the accurate monitoring of heart diseases. RESULTS: The experimental results show that the proposed wavelet transform and SVM-based approach for flexible wearable devices achieves satisfactory results in heart disease monitoring. In particular, the algorithm successfully extracted feature vectors and accurately classified different ECG signals by skillfully combining the wavelet transform and SVM techniques for the processing of premature beat signals. CONCLUSION: The potential application value of the wavelet transform and SVM-based flexible wearable device approach in heart disease monitoring is emphasized. By efficiently processing ECG signals, the method provides an innovative and comfortable solution for real-time monitoring of cardiac diseases.

Lithium-Ion Battery Capacity Estimation Based on Incremental Capacity Analysis and Deep Convolutional Neural Network

Accurate estimation of Li-ion battery capacity is critical for a battery management system (BMS). This paper proposes an innovative method which combines a convolutional neural network and incremental capacity analysis (ICA). In the present approach, the voltage and temperature, which significantly affect the ICA curve during the discharging process, are adopted as the inputs for CNN. Rather than extracting feature parameters of an IC curve, as is carried out in the available research, the present method uses the whole ICA curve as the input to avoid complicated feature extraction and correlation analysis. The results show that the maximum error of capacity estimation is less than 4.7%, the rectified mean squared error is less than 1.3% for each battery, and the overall RMSE is below 1.12%.

Optimizing Support Vector Machine Performance for Parkinson's Disease Diagnosis Using GridSearchCV and PCA-Based Feature Extraction

Background: Parkinson's disease (PD) is a critical neurodegenerative disorder affecting the central nervous system and often causing impaired movement and cognitive function in patients. In addition, its diagnosis in the early stages requires a complex and time-consuming process because all existing tests such as electroencephalography or blood examinations lack effectiveness and accuracy. Several studies explored PD prediction using sound, with a specific focus on the development of classification models to enhance accuracy. The majority of these neglected crucial aspects including feature extraction and proper parameter tuning, leading to low accuracy. Objective: This study aims to optimize performance of voice-based PD prediction through feature extraction, with the goal of reducing data dimensions and improving model computational efficiency. Additionally, appropriate parameters will be selected for enhancement of the ability of the model to identify both PD cases and healthy individuals. Methods: The proposed new model applied an OpenML dataset comprising voice recordings from 31 individuals, namely 23 PD patients and 8 healthy participants. The experimental process included the initial use of the SVM algorithm, followed by implementing PCA for feature extraction to enhance machine learning accuracy. Subsequently, data balancing with SMOTE was conducted, and GridSearchCV was used to identify the best parameter combination based on the predicted model characteristics. Result: Evaluation of the proposed model showed an impressive accuracy of 97.44%, sensitivity of 100%, and specificity of 85.71%. This excellent result was achieved with a limited dataset and a 10-fold cross-validation tuning, rendering the model sensitive to the training data. Conclusion: This study successfully enhanced the prediction model accuracy through the SVM+PCA+GridSearchCV+CV method. However, future investigations should consider an appropriate number of folds for a small dataset, explore alternative cross-validation methods, and expand the dataset to enhance model generalizability. Keywords: GridSearchCV, Parkinson Disaese, SVM, PCA, SMOTE, Voice/Speech

Health assessment of an electro-hydraulic servo pump control system for servomotor based on LGA deep neural network

Due to its advantages of having a high power-to-weight ratio and being energy-efficient, the electro-hydraulic servo pump control system (abbreviated as EHSPCS) is frequently employed in the industrial field, such as the electro-hydraulic servo pump control (EHSPC) servomotor for steam turbine valve regulation control. However, the EHSPCS has strong nonlinearity and time-varying features, and the factors that cause system performance degradation are complex. Once a system failure occurs, it may lead to serious accidents, causing serious casualties and economic losses. To address the above issues, a system health assessment method based on LSTM-GRNN-ANN (LGA) deep neural network is proposed in this paper. Firstly, with oil volume gas content, servo motor air-gap flux density, and system leakage coefficient as the health assessment performance indicators, a health assessment performance index system for the EHSPCS is built, Furthermore, the system performance index threshold is set. Secondly, an LGA deep neural network is constructed by combining LSTM, GRNN and ANN, and a deep neural network based on the LGA is used to create an EHSPCS health assessment model. Subsequently, system feature parameter extraction, algorithm design, and parameter debugging are carried out. Finally, an EHSPCS experimental platform is established, typical system failure simulation experiments are designed, and comparative experimental analysis is conducted. The experimental findings demonstrate that the average accuracy of the system health assessment model based on the LGA deep neural network suggested in this paper is 96.37%, compared to 89.84%, 87.99% for LSTM and GRNN, which validates the accuracy of the system health assessment model based on the LGA deep neural network.

A Comparative Study of Vehicle Velocity Prediction for Hybrid Electric Vehicles Based on a Neural Network

Vehicle velocity prediction (VVP) plays a pivotal role in determining the power demand of hybrid electric vehicles, which is crucial for establishing effective energy management strategies and, subsequently, improving the fuel economy. Neural networks (NNs) have emerged as a powerful tool for VVP, due to their robustness and non-linear mapping capabilities. This paper describes a comprehensive exploration of NN-based VVP methods employing both qualitative theory analysis and quantitative numerical simulations. The used methodology involved the extraction of key feature parameters for model inputs through the utilization of Pearson correlation coefficients and the random forest (RF) method. Subsequently, three distinct NN-based VVP models were constructed comprising the following: a backpropagation neural network (BPNN) model, a long short-term memory (LSTM) model, and a generative pre-training (GPT) model. Simulation experiments were conducted to investigate various factors, such as the feature parameters, sliding window length, and prediction horizon, and the prediction accuracy and computation time were identified as key performance metrics for VVP. Finally, the relationship between the model inputs and velocity prediction performance was revealed through various comparative analyses. This study not only facilitated the identification of an optimal NN model configuration to balance prediction accuracy and computation time, but also serves as a foundational step toward enhancing the energy efficiency of hybrid electric vehicles.

Classification of Partial Discharge in Vehicle-Mounted Cable Termination of High-Speed Electric Multiple Unit: A Machine Learning-Based Approach

This paper presents a machine learning-based approach to identify and separate partial discharge (PD) and two typical pulse interference (PI) signals in the vehicle-mounted cable terminations of high-speed electric multiple units (EMUs). First, a test platform was established to capture PD and two typical PI signals in these terminations. The acquired signals were then processed using the square envelope method to extract feature parameters, such as the rise time proportion, the left–right symmetry, and the upper–lower symmetry. PD signal classification was carried out on these signals, utilizing waveform parameters derived from a hierarchical clustering algorithm. The results validate that the extracted feature components effectively classify and separate PD and two typical PI signals in the vehicle-mounted cable terminations of high-speed EMUs.

Research on guided wave propagation characteristics of quartz ceramic thermal protection structure for ablation monitoring

ABSTRACT Monitoring the thermal protection structure (TPS) of hypersonic vehicles is vital for ensuring safe flight. The guided wave(GW) structure health monitoring（SHM）method is promising for TPS health monitoring due to its high sensitivity, ability to detect small damages, and wide monitoring coverage, both online and offline. However, there is currently a clear research gap in monitoring hypersonic aircraft TPS in real-service environments. This paper addresses this gap by conducting GW monitoring research on hypersonic vehicles TPS under simulated real-service conditions, involving high-temperature and high-speed airflow ablation. This study takes quartz ceramic TPS as the object, undertaking a preliminary investigation into its GW propagation characteristics. Subsequently, the TPS underwent high-temperature and high-speed oxygen-acetylene ablation at 2100°C to induce damages. GW monitoring was then conducted to capture GW signals in both undamaged and various damage scenarios. Through signal analysis, characteristic parameter extraction, and application of the damage index method, rules governing how GW signals respond to damage were established. Results indicate significant impacts on amplitude and phase of GW signals with increasing damage severity, validating the feasibility of the GW monitoring method for detecting high-temperature and high-speed airflow damage to TPS and supporting its expansion for damage monitoring.

Image Recognition and Parameter Analysis of Concrete Vibration State Based on Support Vector Machine.

In this paper, the directional gradient histogram technology is employed to extract the features of concrete image samples captured under different vibration states. The support vector machine (SVM) is utilized to learn the relationship between image features and vibration state. The machine learning results are subsequently used to assess the feasibility of the concrete vibration state. Simultaneously, the influence mechanism of the calculation parameters of the directional gradient histogram on the recognition accuracy is analyzed. The results demonstrate the feasibility of using the directional gradient histogram-SVM technology to identify the vibration state of concrete. The recognition accuracy initially increases and then decreases as the block size of the directional gradient, or the number of statistical intervals increases. The recognition accuracy also decreases linearly with the increase of the binarization threshold. By using sample images with a resolution of 1024 pixels x 1024 pixels and optimizing the feature extraction parameters, a recognition accuracy of 100% can be attained.

A novel switchgear state assessment framework based on improved fuzzy C-means clustering method with deep belief network

Due to the problems such as fuzzy state assessment grading boundaries, the recognition accuracy is low when using traditional fuzzy techniques to grade the switchgear state. To address this problem, this paper proposes a switchgear state assessment and grading method based on deep belief network (DBN) and improved fuzzy C-means clustering (IFCM). Firstly, the switchgear state information data are processed by normalization method; then the feature parameters are extracted from the switchgear state information data by using DBN, and finally the extracted feature parameters are categorised according to the condition of switchgear equipment through clustering using IFCM. The experimental results show that the accuracy of the method in assessing the switchgear state under small sample conditions reaches 94, which exceeds the accuracy of other switchgear state assessment grading methods currently in use.

Application of Big Data-based Information Technology in Business English Courses in Colleges and Universities

Abstract In this paper, after using Cool Edit Pro2.1 software to complete the speech signal acquisition work, the DTW method is used to pre-emphasize the speech signal. Due to the small continuous correlation between adjacent frames, the use of windowing and frame-splitting operation makes the amplitude change of the speech signal smooth and obtains the spectral envelope of the speech signal. The negative impact of MFCC feature parameter extraction is optimized by parameterizing the volume intensity and fundamental trajectory, and the application of the English scoring mechanism in business English education is explored. According to the current situation of business English teaching in colleges and universities, research problems and sampling objects are identified, and statistical analysis is applied to analyze the teaching effect of business English informatization by example. The results show that the speech evaluation system of spoken business English based on DTW does not differ much from the similar results of the scoring of the master’s degree of English majors in our university, and its difference value always stays between 1 and 10. In terms of the simple correlation coefficient and significance level (0.01), the simple correlation coefficient between teaching effectiveness and the use of technological media is 0.385 (P=0.00), which means that there is a significant correlation between both teaching effectiveness and the use of technological media. This study improves the standardization of English pronunciation among students, which is important for the development of business English in colleges and universities.

Integrating Surrounding Vehicle Information for Vehicle Trajectory Representation and Abnormal Lane-Change Behavior Detection.

The detection of abnormal lane-changing behavior in road vehicles has applications in traffic management and law enforcement. The primary approach to achieving this detection involves utilizing sensor data to characterize vehicle trajectories, extract distinctive parameters, and establish a detection model. Abnormal lane-changing behaviors can lead to unsafe interactions with surrounding vehicles, thereby increasing traffic risks. Therefore, solely focusing on individual vehicle perspectives and neglecting the influence of surrounding vehicles in abnormal lane-changing behavior detection has limitations. To address this, this study proposes a framework for abnormal lane-changing behavior detection. Initially, the study introduces a novel approach for representing vehicle trajectories that integrates information from surrounding vehicles. This facilitates the extraction of feature parameters considering the interactions between vehicles and distinguishing between different phases of lane-changing. The Light Gradient Boosting Machine (LGBM) algorithm is then employed to construct an abnormal lane-changing behavior detection model. The results indicate that this framework exhibits high detection accuracy, with the integration of surrounding vehicle information making a significant contribution to the detection outcomes.

A Technique for Bearing Fault Diagnosis Using Novel Wavelet Packet Transform-Based Signal Representation and Informative Factor LDA

This paper proposes a new method for bearing fault diagnosis using wavelet packet transform (WPT)-based signal representation and informative factor linear discriminant analysis (IF-LDA). Time–frequency domain approaches for analyzing bearing vibration signals have gained wide acceptance due to their effectiveness in extracting information related to bearing health. WPT is a prominent method in this category, offering a balanced approach between short-time Fourier transform and empirical mode decomposition. However, the existing methods for bearing fault diagnosis often overlook the limitations of WPT regarding its dependence on the mother wavelet parameters for feature extraction. This work addresses this issue by introducing a novel signal representation method that employs WPT with a new rule for selecting the mother wavelet based on the power spectrum energy-to-entropy ratio of the reconstructed coefficients and a combination of the nodes from different WPT trees. Furthermore, an IF-LDA feature preprocessing technique is proposed, resulting in a highly sensitive set of features for bearing condition assessment. The k-nearest neighbors algorithm is employed as the classifier, and the proposed method is evaluated using datasets from Paderborn and Case Western Reserve universities. The performance of the proposed method demonstrates its effectiveness in bearing fault diagnosis, surpassing existing techniques in terms of fault identification and diagnosis performance.