Time Frequency Domain Features Research Articles

Smart cushion-based non-invasive mental fatigue assessment of construction equipment operators: A feasible study

Mental fatigue has a considerable influence on the completion of work as well as the safety and health of construction equipment operators who have been exposed to human–machine interaction for an extended period of time. Existing techniques of monitoring and measuring mental fatigue among construction equipment operators are either invasive or rely on subjective judgements, limiting their applicability on construction sites. Therefore, this paper developed a non-invasive smart cushion to evaluate the mental fatigue of construction equipment operators through real-time continuous monitoring of the heartbeat and respiration signals. A laboratory experiment was designed, and twelve participants were recruited to conduct the simulated excavator operation for data acquisition. First, wearable sensors were used as a reference to verify the monitoring accuracy of heartbeat and respiration signals. Excellent correlations were realized between the results of the two monitoring methods. Second, the relevant time domain and frequency domain features were extracted to construct a random forest classification model to discover the relationship between vital signs and subjectively reported mental fatigue status. The results demonstrated that the random forest model had a classification accuracy of 92%, better than other commonly used machine learning algorithms. A combination of heartbeat and respiration features is more effective than a single feature in identifying and classifying mental fatigue among construction equipment operators. The study's findings indicate that it is feasible to apply the smart cushion to identify and classify the mental fatigue of construction equipment operators, therefore contributing to the improvement of their health and safety.

Identification of Solid and Liquid Materials Using Acoustic Signals and Frequency-Graph Features.

Material identification is playing an increasingly important role in various sectors such as industry, petrochemical, mining, and in our daily lives. In recent years, material identification has been utilized for security checks, waste sorting, etc. However, current methods for identifying materials require direct contact with the target and specialized equipment that can be costly, bulky, and not easily portable. Past proposals for addressing this limitation relied on non-contact material identification methods, such as Wi-Fi-based and radar-based material identification methods, which can identify materials with high accuracy without physical contact; however, they are not easily integrated into portable devices. This paper introduces a novel non-contact material identification based on acoustic signals. Different from previous work, our design leverages the built-in microphone and speaker of smartphones as the transceiver to identify target materials. The fundamental idea of our design is that acoustic signals, when propagated through different materials, reach the receiver via multiple paths, producing distinct multipath profiles. These profiles can serve as fingerprints for material identification. We captured and extracted them using acoustic signals, calculated channel impulse response (CIR) measurements, and then extracted image features from the time-frequency domain feature graphs, including histogram of oriented gradient (HOG) and gray-level co-occurrence matrix (GLCM) image features. Furthermore, we adopted the error-correcting output code (ECOC) learning method combined with the majority voting method to identify target materials. We built a prototype for this paper using three mobile phones based on the Android platform. The results from three different solid and liquid materials in varied multipath environments reveal that our design can achieve average identification accuracies of 90% and 97%.

Application of EMD ANN and DNN for Self-Aligning Bearing Fault Diagnosis

Self-aligning roller bearings are an integral part of the industrial machinery. The proper analysis and prediction of the various faults that may happen to the bearing beforehand contributes to an increase in the working life of the bearing. This study aims at developing a novel method for the analysis of the various faults in self-aligning bearings as well as the automatic classification of faults using artificial neural network (ANN) and deep neural network (DNN). The vibration data is collected for six different faults as well as for the healthy bearing. Empirical mode decomposition (EMD) followed by Hilbert Huang transform is used to extract instantaneous frequency peaks which are used for fault analysis. Time domain and time-frequency domain features are then extracted which are used to implement the neural networks through the pattern recognition tool in MATLAB. A comparative study of the outputs from the two neural networks is also performed. From the confusion matrix, the efficiency of the ANN has been found to be 95.7% and using DNN has been found to be 100%.

Environmental sound classification based on improved compact bilinear attention network

Aiming at the difficulty in effectively extracting representative features from environmental sounds characterized by the complicated and considerable variation in the time-frequency domain characteristics, an improved compact bilinear attention network (ICBA-Net) is proposed to more precisely focus on the regions that need attention in feature maps in this paper. Firstly, log-mel spectrogram (LMS) extracted from environmental sound is fed into two parallel pre-trained densely connected convolutional network (DenseNet) for deep feature extraction. Afterwards, a coordinate attention module (CAM) is utilized in each branch to integrate key information in both horizontal and vertical directions to achieve a more accurate focus on global feature salient regions. Finally, two-stream enhanced global representations are integrated into a compact bilinear vector, followed by the full connection layer with activation function softmax to output the final prediction result. Experiments on two publicly available datasets (ESC-10 and ESC-50) and some environmental sounds collected from common scenarios in our real life are used to verify the validity of the proposed method. Through comparison and verification, the results show that the proposed network outperformed almost all state-of-the-art systems regarding classification accuracy, and the feasibility and effectiveness of CAM have also been verified.

Ensemble machine learning approach to identify excitation failure in synchronous generators

Loss of Excitation (LOE) is a significant failure that occurs in synchronous generators, affecting both generator and power grid. The conventional LOE protection relays work based on the impedance measurement at generator terminal but they tend to mal-operate other than excitation failure like Stable Power Swing (SPoS). To achieve more reliable and accurate protection, a proper speedy discrimination of LOE failure from SPoS is indeed. This paper deals an ensemble machine learning methodology to identify LOE.In order to analyse LOE failure, generator dynamic model is considered and simulation is performed on IEEE-9 bus system. In this, various observations are formed for LOE, SPoS and other events under various loading scenarios. Discrete Wavelet Transform (DWT) analysis is employed on generator terminal voltage signal and Time-Frequency Domain (TFD) features are extracted to define unique characteristics of LOE failure. The ensemble Adaboost binary classifier is trained with feature matrix and tested. Finally, the ensemble model is established and identified LOE failure from SPoS in 1.517 s. Comprehensive simulation analysis confirmed the supremacy of the proposed method than other compared methods.

Gait parameter fitting and adaptive enhancement based on cerebral blood oxygen information.

Accurate recognition of patients' movement intentions and real-time adjustments are crucial in rehabilitation exoskeleton robots. However, some patients are unable to utilize electromyography (EMG) signals for this purpose due to poor or missing signals in their lower limbs. In order to address this issue, we propose a novel method that fits gait parameters using cerebral blood oxygen signals. Two types of walking experiments were conducted to collect brain blood oxygen signals and gait parameters from volunteers. Time domain, frequency domain, and spatial domain features were extracted from brain hemoglobin. The AutoEncoder-Decoder method is used for feature dimension reduction. A regression model based on the long short-term memory (LSTM) model was established to fit the gait parameters and perform incremental learning for new individual data. Cross-validation was performed on the model to enhance individual adaptivity and reduce the need for individual pre-training. The coefficient of determination (R2) for the gait parameter fit was 71.544%, with a mean square error (RMSE) of less than 3.321%. Following adaptive enhancement, the coefficient of R2 increased by 6.985%, while the RMSE decreased by 0.303%. These preliminary results indicate the feasibility of fitting gait parameters using cerebral blood oxygen information. Our research offers a new perspective on assisted locomotion control for patients who lack effective myoelectricity, thereby expanding the clinical application of rehabilitation exoskeleton robots. This work establishes a foundation for promoting the application of Brain-Computer Interface (BCI) technology in the field of sports rehabilitation.

Unsupervised Feature Representation of Sleep EEG Data with Transient Deep Boltzmann Machine.

The supervised sleep staging methods are challenged by their strict requirements of a labelled and large dataset. This study considers an unsupervised dimensionality reduction method, the Deep Boltzmann Machine (DBM), trained to a transient state for binary classification of sleep stages. First, the joint time-frequency domain features from the polysomnographic recordings are extracted. Second, the extracted features are smoothed using 2 min rolling window to include contextual temporal information, and finally, they serve as an input for unsupervised training of DBM_transient. The results show that our method effectively separates the sleep stages in two-dimensional feature space with a large Fisher's discriminant value. The classification performance by the DBM_transient achieves a 96.1% F1 score, which is higher than DBM converged to an equilibrium state (95.2%), Principal Component Analysis (92.5%), Isometric Feature Mapping (95.9%), t-distributed Stochastic Neighbor Embedding (94.9%), and Uniform Manifold Approximation (95.0%) on the widely used sleep-EDF database. Additionally, Fisher's discriminant function demonstrates the superiority of the DBM_transient. The significance of the DBM transient lies in its ease of interpretability in two-dimensional space, and future multi-class implementation of the method may facilitate its usage in clinical applications.

Brain Computer Interface Based on Motor Imagery for Mechanical Arm Grasp Control

This paper puts forward a brain computer interface (BCI) system to realize the hand and wrist control using the ABB Mechanical Arm. This BCI system gathers four kinds of motor imaginary (MI) tasks (hand grasp, hand spread, wrist flexion and wrist extension) electroencephalogram (EEG) signals from 30 electrodes. It utilizes two fifth-order Butterworth Band-Pass Filter (BPF) with different bandwidths and normalization method to achieve the raw MI tasks EEG signals preprocessing. The main challenge of feature extraction is to extract enough representative features from MI tasks to classify them. This proposed BCI system extracts eleven kinds of features in time domain and time-frequency domain and uses mutual information method to reduce the large dimension of the extracted features. In addition, the BCI system applies a single convolutional layer Convolutional neural networks (CNN) with 30 filters to implement the quaternary classification of MI tasks. Compared with early researches, the classification accuracy of this BCI system is increased by about 35%. The actual mechanical arm grasping control experiments verifies that this BCI system has good adaptability.

A deep feature learning method for remaining useful life prediction of drilling pumps

Remaining Useful Life (RUL) prediction of drilling pumps, pivotal components in fossil energy production, is essential for efficient maintenance and safe operation of such facilities. This paper introduces a deep feature learning method that combines a Convolutional Neural Network (CNN)-Convolutional Block Attention Module (CBAM) and a Transformer network into a parallel channel method to predict the RUL of drilling pumps. Specifically, two parallel channels independently extract time-frequency domain and time-domain features from strain signals and then proceed with degradation estimation through feature learning. The deep features derived independently from the two channels are subsequently amalgamated to predict the RUL of the drilling pump. The proposed method is validated by the operational data from four operating drilling pumps. The comparative analysis confirms the higher accuracy of the proposed method over several existing state-of-the-art approaches. Overall, the proposed method supports the safe and cost-saving-oriented operation and maintenance of drilling pumps.

An EEG-based attention recognition method: fusion of time domain, frequency domain, and non-linear dynamics features.

Attention is a complex cognitive function of human brain that plays a vital role in our daily lives. Electroencephalogram (EEG) is used to measure and analyze attention due to its high temporal resolution. Although several attention recognition brain-computer interfaces (BCIs) have been proposed, there is a scarcity of studies with a sufficient number of subjects, valid paradigms, and reliable recognition analysis across subjects. In this study, we proposed a novel attention paradigm and feature fusion method to extract features, which fused time domain features, frequency domain features and nonlinear dynamics features. We then constructed an attention recognition framework for 85 subjects. We achieved an intra-subject average classification accuracy of 85.05% ± 6.87% and an inter-subject average classification accuracy of 81.60% ± 9.93%, respectively. We further explored the neural patterns in attention recognition, where attention states showed less activation than non-attention states in the prefrontal and occipital areas in α, β and θ bands. The research explores, for the first time, the fusion of time domain features, frequency domain features and nonlinear dynamics features for attention recognition, providing a new understanding of attention recognition.

Statistically significant features improve binary and multiple Motor Imagery task predictions from EEGs.

In recent studies, in the field of Brain-Computer Interface (BCI), researchers have focused on Motor Imagery tasks. Motor Imagery-based electroencephalogram (EEG) signals provide the interaction and communication between the paralyzed patients and the outside world for moving and controlling external devices such as wheelchair and moving cursors. However, current approaches in the Motor Imagery-BCI system design require effective feature extraction methods and classification algorithms to acquire discriminative features from EEG signals due to the non-linear and non-stationary structure of EEG signals. This study investigates the effect of statistical significance-based feature selection on binary and multi-class Motor Imagery EEG signal classifications. In the feature extraction process performed 24 different time-domain features, 15 different frequency-domain features which are energy, variance, and entropy of Fourier transform within five EEG frequency subbands, 15 different time-frequency domain features which are energy, variance, and entropy of Wavelet transform based on five EEG frequency subbands, and 4 different Poincare plot-based non-linear parameters are extracted from each EEG channel. A total of 1,364 Motor Imagery EEG features are supplied from 22 channel EEG signals for each input EEG data. In the statistical significance-based feature selection process, the best one among all possible combinations of these features is tried to be determined using the independent t-test and one-way analysis of variance (ANOVA) test on binary and multi-class Motor Imagery EEG signal classifications, respectively. The whole extracted feature set and the feature set that contain statistically significant features only are classified in this study. We implemented 6 and 7 different classifiers in multi-class and binary (two-class) classification tasks, respectively. The classification process is evaluated using the five-fold cross-validation method, and each classification algorithm is tested 10 times. These repeated tests provide to check the repeatability of the results. The maximum of 61.86 and 47.36% for the two-class and four-class scenarios, respectively, are obtained with Ensemble Subspace Discriminant among all these classifiers using selected features including only statistically significant features. The results reveal that the introduced statistical significance-based feature selection approach improves the classifier performances by achieving higher classifier performances with fewer relevant components in Motor Imagery task classification. In conclusion, the main contribution of the presented study is two-fold evaluation of non-linear parameters as an alternative to the commonly used features and the prediction of multiple Motor Imagery tasks using statistically significant features.

Research on Coal Gangue Recognition Based on Multi-source Time-Frequency Domain Feature Fusion.

The over-exploitation of resources caused by the increasing coal demand has resulted in a sharp increase in solid waste emissions mainly gangue, which has made the burden on the environment, economy, resources, and society of our country heavier. In order to achieve a balance between energy consumption and solid waste emission in the process of top coal caving, this study carried out coal gangue recognition research based on multi-source time-frequency domain feature fusion (MS-TFDF-F). First, the process of coal gangue symbiosis and the harm of gangue in top coal caving are analyzed, and the fundamental method of comprehensive treatment of gangue is put forward, which is the accurate recognition of the coal gangue interface. Second, by building a top coal caving simulation test bed, the MS signals generated in the caving process of the coal gangue mixture with a gangue content of 0-100% are collected and the TFDFs are extracted. Third, the MS-TFDF-F-based coal gangue recognition model is established. Then, the recognition effect of the two TFDF-F sample sets was compared, and the results show that the time-frequency domain feature selection fusion method (TFDFS-FM) has higher accuracy. On this basis, this paper studies the variation law of the number of sensors on the coal gangue recognition accuracy of MS information fusion. Finally, the economic, social, environmental, and resource benefits of the model are qualitatively described. The final results show that the MS-TFDF-F-based coal gangue recognition model has the strongest recognition ability when fusing six sensor signals, and the recognition accuracy reaches 99% under the AdaBoost algorithm. The establishment of this model brings huge benefits to China's environment, economy, resources, and society, and it is helpful to realize the balance between loss reduction mining and solid waste emission reduction in the process of top coal caving.

Fault type identification of arc grounding based on time-frequency domain characteristics of zero sequence current

Different types of faults pose different degrees of threat to the distribution network. Accurate identification of fault types is essential for distribution network maintenance and hazard prevention. The simulation of a typical single-phase arc grounding fault in a distribution network is carried out based on a 10 kV test platform, and the zero-sequence current of cable fault, tree touch, line break, and insulator flashover is obtained. The BP neural network is established and trained to recognize the feature data, which is extracted by Fourier transform and wavelet transform. The identification results prove the effectiveness of the proposed method for single-phase arc grounding fault type identification in distribution networks.

Optimal Feature Analysis for Identification Based on Intracranial Brain Signals with Machine Learning Algorithms.

Biometrics, e.g., fingerprints, the iris, and the face, have been widely used to authenticate individuals. However, most biometrics are not cancellable, i.e., once these traditional biometrics are cloned or stolen, they cannot be replaced easily. Unlike traditional biometrics, brain biometrics are extremely difficult to clone or forge due to the natural randomness across different individuals, which makes them an ideal option for identity authentication. Most existing brain biometrics are based on an electroencephalogram (EEG), which typically demonstrates unstable performance due to the low signal-to-noise ratio (SNR). Thus, in this paper, we propose the use of intracortical brain signals, which have higher resolution and SNR, to realize the construction of a high-performance brain biometric. Significantly, this is the first study to investigate the features of intracortical brain signals for identification. Specifically, several features based on local field potential are computed for identification, and their performance is compared with different machine learning algorithms. The results show that frequency domain features and time-frequency domain features are excellent for intra-day and inter-day identification. Furthermore, the energy features perform best among all features with 98% intra-day and 93% inter-day identification accuracy, which demonstrates the great potential of intracraial brain signals to be biometrics. This paper may serve as a guidance for future intracranial brain researches and the development of more reliable and high-performance brain biometrics.

Automatic sleep staging model based on single channel electroencephalogram signal

Sleep staging is the basis for solving sleep problems. There's an upper limit for the classification accuracy of sleep staging models based on single-channel electroencephalogram (EEG) data and features. To address this problem, this paper proposed an automatic sleep staging model that mixes deep convolutional neural network (DCNN) and bi-directional long short-term memory network (BiLSTM). The model used DCNN to automatically learn the time-frequency domain features of EEG signals, and used BiLSTM to extract the temporal features between the data, fully exploiting the feature information contained in the data to improve the accuracy of automatic sleep staging. At the same time, noise reduction techniques and adaptive synthetic sampling were used to reduce the impact of signal noise and unbalanced data sets on model performance. In this paper, experiments were conducted using the Sleep-European Data Format Database Expanded and the Shanghai Mental Health Center Sleep Database, and achieved an overall accuracy rate of 86.9% and 88.9% respectively. When compared with the basic network model, all the experimental results outperformed the basic network, further demonstrating the validity of this paper's model, which can provide a reference for the construction of a home sleep monitoring system based on single-channel EEG signals.

Remaining Useful-Life Prediction of the Milling Cutting Tool Using Time–Frequency-Based Features and Deep Learning Models

The milling machine serves an important role in manufacturing because of its versatility in machining. The cutting tool is a critical component of machining because it is responsible for machining accuracy and surface finishing, impacting industrial productivity. Monitoring the cutting tool’s life is essential to avoid machining downtime caused due to tool wear. To prevent the unplanned downtime of the machine and to utilize the maximum life of the cutting tool, the accurate prediction of the remaining useful life (RUL) cutting tool is essential. Different artificial intelligence (AI) techniques estimate the RUL of cutting tools in milling operations with improved prediction accuracy. The IEEE NUAA Ideahouse dataset has been used in this paper for the RUL estimation of the milling cutter. The accuracy of the prediction is based on the quality of feature engineering performed on the unprocessed data. Feature extraction is a crucial phase in RUL prediction. In this work, the authors considers the time–frequency domain (TFD) features such as short-time Fourier-transform (STFT) and different wavelet transforms (WT) along with deep learning (DL) models such as long short-term memory (LSTM), different variants of LSTN, convolutional neural network (CNN), and hybrid models that are a combination of CCN with LSTM variants for RUL estimation. The TFD feature extraction with LSTM variants and hybrid models performs well for the milling cutting tool RUL estimation.

Lightning Risk Warning Method Using Atmospheric Electric Field Based on EEWT-ASG and Morpho

The current methods for lightning risk warnings that are based on atmospheric electric field (AEF) data have a tendency to rely on single features, which results in low robustness and efficiency. Additionally, there is a lack of research on canceling warning signals, contributing to the high false alarm rate (FAR) of these methods. To overcome these limitations, this study proposes a lightning risk warning method that incorporates enhanced empirical Wavelet transform-Adaptive Savitzky–Golay filter (EEWT-ASG) and one-dimensional morphology, using time-frequency domain features obtained through the Wavelet transform (WT). The proposed method achieved a probability of detection (POD) of 77.11%, miss alarm rate (MAR) of 22.89%, FAR of 40.19%, and critical success index (CSI) of 0.51, as evaluated on 83 lightning events. This method can issue a warning signal up to 22 min in advance for lightning processes.

Real-time signal processing method of ultra-wideband fuze using LSTM

The extraction of target features from the ultra-wideband (UWB) fuze echo signal and target recognition and distance determination are the key to controlling the precise detonation of the fuze. In this paper, a real-time signal processing method of UWB fuze based on Long Short-Term Memory (LSTM) network is proposed. The time domain and frequency domain features of echo signal are recognized through a small-scale LSTM network. Matlab is used to build the network model and simulation results show that the method can effectively avoid noise interference, correctly recognize the target signal, and avoid false alarm.

Real-time online unstart prediction of supersonic inlet based on pressure fluctuations

Supersonic inlet unstart prediction is one of the most critical components in supersonic flight technology, because inlet unstart may cause unexpected damage to the engine. However, due to the nonlinear and nonstationary property of pressure signals, effective supersonic inlet unstart prediction based on pressure signals remains a challenging problem. In this paper, change-point detection (CD), wavelet packet transform (WPT), and deep learning (DL) are combined to realize real-time online unstart prediction for supersonic inlet. The combination of the water cycle algorithm (WCA) and penalized contrast change-point detection (PCCD) will accurately divide the signal into two different flow states based on global characteristics, providing a reliable dataset for training the subsequent convolutional neural network (CNN). Then, a novel network named WPT-CNN is applied and it will take pressure signals as input to implement time-frequency domain feature extraction. To improve the accuracy of the classification model, a multi-channel unstart prediction model is proposed, which can simultaneously receive real-time pressure from multiple sensors to obtain detailed information inside the supersonic inlet. Results indicate that WCA-PCCD and multi-channel model can achieve better real-time online unstart prediction in comparison with other change-point detection algorithms and single-channel model.

A COMPARATIVE ANALYSIS OF EDA DECOMPOSITION METHODS FOR IMPROVED EMOTION RECOGNITION

This study analyzed five decomposition algorithms for separating electrodermal activity (EDA) into tonic and phasic components to identify different emotions using machine learning algorithms. We used EDA signals from the Continuously Annotated Signals of Emotion dataset for this analysis. First, we decomposed the EDA signals into tonic and phasic components using five decomposition methods: continuous deconvolution analysis, discrete deconvolution analysis, convex optimization-based EDA, nonnegative sparse deconvolution (SparsEDA), and BayesianEDA. We extracted time, frequency, and time-frequency domain features from each decomposition method’s tonic and phasic components. Finally, various machine learning algorithms such as logistic regression (LR), support vector machine, random forest, extreme gradient boosting, and multilayer perceptron were applied to evaluate the performance of the decomposition methods. Our results show that the considered decomposition methods successfully split the EDA signal into tonic and phasic components. The SparsEDA decomposition method outperforms the other decomposition methods considered in the study. In addition, LR with features extracted from the tonic component of the SparsEDA achieved highest average classification accuracy of 95.83%. This study can be used to identify the optimal decomposition methods suitable for emotion recognition applications.