Entropy Features Research Articles

Entropy Feature Fusion-Based Diagnosis for Railway Point Machines Using Vibration Signals Based on Kernel Principal Component Analysis and Support Vector Machine

Entropy Feature Fusion-Based Diagnosis for Railway Point Machines Using Vibration Signals Based on Kernel Principal Component Analysis and Support Vector Machine

Recent Progress in Application‐Oriented Self‐Powered Microelectronics

AbstractWith the rapid development of the Internet of Things (IoTs), numerous distributed wide‐area low‐power electronic devices have been utilized in various fields, such as wireless monitoring sensors and wearable electronics. Due to the dispersion and mobility of microelectronic devices, their energy supply faces serious challenges. The inconvenience and non‐environmental friendliness of using traditional centralized low entropy energy and chemical batteries to power distributed microelectronic devices are becoming increasingly prominent. Environmental energy harvesting technology with high entropy characteristics is considered an effective solution for low‐power electronic devices. This paper comprehensively reviews the recent progress in microelectronic technologies based on energy harvesting and signal sensing. First, state‐of‐the‐art micro‐power electronic devices in humans, animals, and the environment are introduced. Secondly, the available micro‐energy sources in the environmentare elaborated and summarized. Then, the principles and characteristics of ambient microenergy harvesting technologies based on different mechanisms are classified, summarized, and analyzed. In addition, this work comprehensively summarizes the applications of self‐powered micro‐electronics technology in 11 different fields, including human, animal, and environment. Finally, research challenges, technical difficulties, and research gaps in self‐powered microelectronics based on micro‐energy harvesting technology are discussed and summarized.

Brain tumor image identification and classification on the internet of medical things using deep learning

The health services research network is showing a lot of interest in the Internet of Medical Things (IoMT). In IoMT, the Internet is used to help compile important health-related data. A brain tumor is caused by a mass of random cells inside the brain, which is dangerous and harmful to the brain. Today, it is difficult to accurately recognise brain images. In order to find and correctly categorize malignant cells in recognizing brain pictures, this research offers a support value-based deep neural network (SDNN) in e-Health care administration utilizing the IoMT innovation. As a starting point, a database of investigation is created using picture data based on IoT innovation and clinical images. The input brain picture is subjected to skull stripping during the preprocessing stage in order to isolate the desired brain area. The preprocessed output pictures are then used to extract the useful characteristics, such as entropy, geometric, and texture features. Finally, based on the collected characteristics, the proposed support value based adaptive deep neural network (SDNN) identification classifies the brain pictures as normal or abnormal. The results of the experiments are examined to show how the suggested recognition approach outperforms the ones already in use.

An Improved Canonical Correlation Analysis for EEG Inter-Band Correlation Extraction.

(1) Background: Emotion recognition based on EEG signals is a rapidly growing and promising research field in affective computing. However, traditional methods have focused on single-channel features that reflect time-domain or frequency-domain information of the EEG, as well as bi-channel features that reveal channel-wise relationships across brain regions. Despite these efforts, the mechanism of mutual interactions between EEG rhythms under different emotional expressions remains largely unexplored. Currently, the primary form of information interaction between EEG rhythms is phase-amplitude coupling (PAC), which results in computational complexity and high computational cost. (2) Methods: To address this issue, we proposed a method of extracting inter-bands correlation (IBC) features via canonical correlation analysis (CCA) based on differential entropy (DE) features. This approach eliminates the need for surrogate testing and reduces computational complexity. (3) Results: Our experiments verified the effectiveness of IBC features through several tests, demonstrating that the more correlated features between EEG frequency bands contribute more to emotion classification accuracy. We then fused IBC features and traditional DE features at the decision level, which significantly improved the accuracy of emotion recognition on the SEED dataset and the local CUMULATE dataset compared to using a single feature alone. (4) Conclusions: These findings suggest that IBC features are a promising approach to promoting emotion recognition accuracy. By exploring the mutual interactions between EEG rhythms under different emotional expressions, our method can provide valuable insights into the underlying mechanisms of emotion processing and improve the performance of emotion recognition systems.

The Question of Studying Information Entropy in Poetic Texts

One of the approaches to quantitative text analysis is to represent a given text in the form of a time series, which can be followed by an information entropy study for different text representations, such as “symbolic entropy”, “phonetic entropy” and “emotional entropy” of various orders. Studying authors’ styles based on such entropic characteristics of their works seems to be a promising area in the field of information analysis. In this work, the calculations of entropy values of the first, second and third order for the corpus of poems by A.S. Pushkin and other poets from the Golden Age of Russian Poetry were carried out. The values of “symbolic entropy”, “phonetic entropy” and “emotional entropy” and their mathematical expectations and variances were calculated for given corpora using the software application that automatically extracts statistical information, which is potentially applicable to tasks that identify features of the author’s style. The statistical data extracted could become the basis of the stylometric classification of authors by entropy characteristics.

Hand gesture classification framework leveraging the entropy features from sEMG signals and VMD augmented multi-class SVM

To improve the classification accuracy of hand movements from sEMG signals, this paper puts forward a unified hand gesture classification framework which exploits the potentials of variational mode decomposition (VMD) and multi-class support vector machine (SVM). Acquiring the sEMG signals from 25 intact subjects for ten functional activities in real-time, we implement a non-recursive adaptive decomposition technique to sEMG signals and perform power spectral analysis to identify the dominant narrow-band intrinsic mode functions (IMFs) that contain prominent biomarkers. Subsequently, to compute the optimal feature vectors from a set of entropy measures, this work investigates the performance of two techniques namely minimum redundancy and maximum relevance (MRMR) technique and kernel principal component analysis (kPCA). After extracting the optimal set of entropy features, the proposed approach implements a multi-class SVM based on one-vs-one (OVO) strategy to classify the hand gestures. The performance of the multi-class SVM compared with those of the K-nearest neighbor (KNN) and naïve bayes (NB) classifiers highlight that multi-class SVM offers superior performance with an average classification accuracy of 99.98%. Moreover, for statistical analysis of the experimental results, this work performs Friedman test to analyze the significance of the SVM, KNN and NB classifier performances. Finally, the performance comparison of the proposed approach with those of the state-of-the-art techniques highlights the superiority of the proposed framework to improve the hand gesture classification accuracy.

Leading and following: Noise differently affects semantic and acoustic processing during naturalistic speech comprehension

Despite the distortion of speech signals caused by unavoidable noise in daily life, our ability to comprehend speech in noisy environments is relatively stable. However, the neural mechanisms underlying reliable speech-in-noise comprehension remain to be elucidated. The present study investigated the neural tracking of acoustic and semantic speech information during noisy naturalistic speech comprehension. Participants listened to narrative audio recordings mixed with spectrally matched stationary noise at three signal-to-ratio (SNR) levels (no noise, 3 dB, -3 dB), and 60-channel electroencephalography (EEG) signals were recorded. A temporal response function (TRF) method was employed to derive event-related-like responses to the continuous speech stream at both the acoustic and the semantic levels. Whereas the amplitude envelope of the naturalistic speech was taken as the acoustic feature, word entropy and word surprisal were extracted via the natural language processing method as two semantic features. Theta-band frontocentral TRF responses to the acoustic feature were observed at around 400 ms following speech fluctuation onset over all three SNR levels, and the response latencies were more delayed with increasing noise. Delta-band frontal TRF responses to the semantic feature of word entropy were observed at around 200 to 600 ms leading to speech fluctuation onset over all three SNR levels. The response latencies became more leading with increasing noise and decreasing speech comprehension and intelligibility. While the following responses to speech acoustics were consistent with previous studies, our study revealed the robustness of leading responses to speech semantics, which suggests a possible predictive mechanism at the semantic level for maintaining reliable speech comprehension in noisy environments.

Elevator Fault Diagnosis Method Based on IAO-XGBoost under Unbalanced Samples

Elevators are essential tools in daily life; timely and accurate fault diagnosis plays a crucial role in ensuring their safe operation. However, the existing elevator fault diagnosis methods often neglect the imbalance between the actual collected normal samples and the fault samples, resulting in low diagnostic accuracy. In this study, we propose an improved Aquila optimizer (IAO) extreme gradient boosting tree (XGBoost)-based elevator fault diagnosis method under unbalanced samples. The proposed method includes three main components: multi-domain feature extraction, sample balancing, and fault diagnosis. In the feature extraction phase, the time domain, frequency domain and entropy features of the vibration signal are extracted. In the sample balance phase, aiming at the problem of unbalanced fault samples, after feature selection using recursive feature elimination (RFE), the minority class samples are oversampled by applying SMOTE-Tomek. In the fault diagnosis phase, IAO is used to optimize the hyperparameters in the XGBoost, and the optimized hyperparameters are brought into XGBoost for fault diagnosis. The fault diagnosis accuracy of the method proposed in this study can reach 99.06%, and the method can accurately identify the fault state of the elevator.

Wearable Sleep Monitoring System Based on Machine Learning Using Snoring Sound Signal

Abstract According to the obstructive sleep apnea Syndrome (OSAS), a wearable sleep monitoring system is designed based on machine learning using snoring sound signal. The system picks up snoring signal via bone conduction sensor, and calculates the apnea-hypopnea index (AHI). By analyzing the snoring signal in frequency domain, spectral entropy and other frequency-domain features are selected. Finally, the neural network classifier model is established. In the model, the input variables are eight frequency-domain features, and the output response is related to AHI value. Trained by machine learning, the result shows that the average accuracy in identifying the severity of the four kinds of OSAS categories is 59%. The system uses the measured data of snoring to analyze the symptoms of OSAS, so as to realize the preliminary forecast based on the snoring data. The system proposed in this paper has a good application development prospect in intelligent monitoring and medical instruments.

Experimental investigations of particle sizes effects on exergy and entropy characteristics of AL2O3 - MWCNT hybrid nanofluid along the transitional flow regime

Experimental investigation on particle size effect on entropy and exergy characteristics of AL2O3 - MWCNT hybrid nanofluid in transitional flow Regime was carried out with four different particle sizes (i.e., for Aluminum oxide (AL2O3), 20 nm, and 5 nm used while Multiwalled Carbon Nanotubes (MWCNT) <7 nm and 30–50 nm particles). 0.3 vol concentrations of three hybrid nanofluids with different particle size combinations (i.e., Al2O3(20 nm) – MWCNT(20–30 nm), Al2O3(20 nm) – MWCNT(<7 nm), and then Al2O3(5 nm) – MWCNT(<7 nm)) are prepared using a two-step method, at a percentage weight composition (PWC) of 60:40. Results shows that Nanofluid with Al2O3 (20 nm) and MWCNT (<7 nm) have shown the best performance. It has an exergy efficiency of 54.12% at turbulent Reynold number of 4500, while in the transitional flow regime, it records an exergy efficiency of 47.85%. Frictional entropy and thermal entropy in the transitional regime were reduced with hybrid nanofluid of Al2O3 (20 nm) and MWCNT (<7 nm) by 6.78% and 13.53%, respectively, as compared to Al2O3 (5)- MWCNT (<7) nanofluid. Both thermal and frictional entropy effects were better minimized in the turbulent regime than in the lamina and transitional regime, as they were reduced by 16.66 and 24.7%, respectively. The study also recommends that for further investigations, more samples need to be taken to reach a clearer conclusion the effect of particle size, and since this is a hybrid nanofluid the samples should be of different sizes from both nanoparticles.

Morphological features of the photoplethysmographic signal: a new approach to characterize the microcirculatory response to photobiomodulation.

Introduction and Objectives: Advanced analysis of the morphological features of the photoplethysmographic (PPG) waveform may provide greater understanding of mechanisms of action of photobiomodulation (PBM). Photobiomodulation is a non-ionizing, red to near-infrared irradiation shown to induce peripheral vasodilatation, promote wound healing, and reduce pain. Using laser Doppler flowmetry combined with thermal imaging we found previously in a clinical study that PBM stimulates microcirculatory blood flow and that baseline palm skin temperature determines, at least in part, why some individuals respond favorably to PBM while others do not. "Responders" (n = 12) had a skin temperature range of 33°C-37.5°C, while "non-responders" (n = 8) had "cold" or "hot" skin temperature (<33°C or >37.5°C respectively). The continuous PPG signals recorded from the index fingers of both hands in the original clinical study were subjected to advanced post-acquisitional analysis in the current study, aiming to identify morphological features that may improve the accuracy of discrimination between potential responders and non-responders to PBM. Methods: The PPG signals were detrended by subtracting the lower envelope from the raw signal. The Root Mean Square (RMS) and Entropy features were extracted as were two additional morphological features -- Smoothness and number of local extrema per PPG beat (#Extrema). These describe the signal jaggedness and were developed specifically for this study. The Wilcoxon test was used for paired comparisons. Correlations were determined by the Spearman correlation test (rs). Results: The PPG waveforms of responders to PBM had increased amplitude and decreased jaggedness (Baseline vs. 10' post-irradiation: Entropy, 5.0 ± 1.3 vs. 3.9 ± 1.1, p = 0.012; #Extrema, 4.0 ± 1.1 vs. 3.0 ± 1.6, p = 0.009; RMS, 1.6 ± 0.9 vs. 2.3 ± 1.2, p = 0.004; Smoothness, 0.10 ± 0.05 vs. 0.19 ± 0.16, p = 0.016). In addition, unilateral irradiation resulted in a bilateral response, although the response of the contralateral, non-irradiated hand was shorter in duration and lower in magnitude. Although subjects with 'cold,' or 'hot,' baseline skin temperature appeared to have morphologically distinct PPG waveforms, representing vasoconstriction and vasodilatation, these were not affected by PBM irradiation. Conclusion: This pilot study indicates that post-acquisitional analysis of morphological features of the PPG waveform provides new measures for the exploration of microcirculation responsiveness to PBM.

Chirplet transform based time frequency analysis of speech signal for automated speech emotion recognition

Nowadays, the recognition of emotion using the speech signal has gained popularity because of its vast number of applications in different fields like medicine, online marketing, online search engines, the education system, criminal investigations, traffic collisions, etc. Many researchers have adopted different methodologies to improve emotion classification accuracy using speech signals. In our study, time–frequency (TF) analysis-based features were used to analyze the emotion classification performance. We used a novel TF analysis method called the chirplet transform (CT) to find the TF matrix of the speech signal. We then calculated the proposed TF-based permutation entropy (TFPE) feature using the TF matrix of the speech signal. To reduce the feature dimension and select the most informative emotional feature, we employed the genetic algorithm (GA) feature selection method. Then, the selected TFPE features are used as input to machine learning classifiers such as SVM, RF, DT, and KNN to classify the emotions in the speech signal. We obtained classification accuracy of 77.2%, 69.57%, 68.78%, 56.9%, and 99.1% for the EMO-DB, EMOVO, SAVEE, IEMOCAP, and TESS datasets without the GA feature selection method. The emotion classification accuracy increased to 85.6%, 78.33%, 77.76%, 63.15%, and 100% with the GA feature selection method. We compared our results with other methods and found that our method performed better in emotion classification than the state-of-the-art methods.

DNA Chromatogram Classification Using Entropy-Based Features and Supervised Dimension Reduction Based on Global and Local Pattern Information

Gene sequence classification can be seen as a challenging task due to the nonstationary, noisy and nonlinear characteristics of sequential data. The primary goal of this research is to develop a general solution approach for supervised DNA chromatogram (DNAC) classification in the absence of sufficient training data. Today, deep learning comes to the fore with its achievements, however this requires a lot of training data. Finding enough training data can be exceedingly challenging, particularly in the medical area and for rare disorders. In this paper, a novel supervised DNAC classification method is proposed, which combines three techniques to classify hepatitis virus DNA trace files as HBV and HCV. The features that are capable of reflecting the complex-structured sequential data are extracted based on both embedding and spectral entropies. After the supervised dimension reduction step, not only global behavior of the entropy features but also local behavior of the entropy features is taken into account for classification purpose. A memory-based learning, which cannot lose any information coming from training data as its nature, is being used as a classifier. Experimental results show that the proposed method achieves good results that although 19% training data is used, a performance of 92% is obtained.

Daily precipitation concentration and Shannon’s entropy characteristics: spatial and temporal variability in Iran, 1966–2018

Daily precipitation concentration and Shannon’s entropy characteristics: spatial and temporal variability in Iran, 1966–2018

Using chemosensory-induced EEG signals to identify patients with de novo Parkinson’s disease

ObjectiveParkinson’s disease (PD) patients generally exhibit an olfactory loss. Hence, psychophysical or electrophysiological tests are used for diagnosis. However, these tests are susceptible to the subjects’ behavioral response bias and require advanced techniques for an accurate analysis. Proposed ApproachUsing well-known feature extraction methods, we characterized chemosensory-induced EEG responses of the participants to classify whether they have PD. The classification was performed for different time intervals after chemosensory stimulation to see which temporal segment better separates healthy controls and subjects with de novo PD. ResultsThe performances show that entropy and connectivity features discriminate effectively PD and HC participants when olfactory-induced EEG signals were used. For these methods, discrimination is over 80% for segments 100–700 and 200–800 milliseconds after stimulus onset. Comparison with Existing MethodsWe compared the performance of our framework with linear predictive coding, bispectrum, wavelet entropy-based methods, and TDI score-based classification. While the entropy- and connectivity-based methods elicited the highest classification performances for olfactory stimuli, the linear predictive coding-based method elicited slightly higher performance than our framework when the trigeminal stimuli were used. ConclusionThis is one of the first studies that use chemosensory-induced EEG signals along with different feature extraction methods to classify healthy subjects and subjects with de novo PD. Our results show that entropy and functional connectivity methods unravel the chemosensory-induced neural dynamics encapsulating critical information about the subjects’ olfactory performance. Furthermore, time- and frequency-resolved feature analysis is beneficial for capturing disease-affected neural patterns.

Research on Electric Vehicle Braking Intention Recognition Based on Sample Entropy and Probabilistic Neural Network

The accurate identification of a driver’s braking intention is crucial to the formulation of regenerative braking control strategies for electric vehicles. In this paper, a braking intention recognition model based on the sample entropy of the braking signal and a probabilistic neural network (PNN) is proposed to achieve the accurate recognition of different braking intentions. Firstly, the brake pedal travel signal is decomposed to extract the effective components via variational modal decomposition (VMD); then, the features of the decomposed signal are extracted using sample entropy to obtain the multidimensional feature vector of the braking signal; finally, the sparrow search algorithm (SSA) and probabilistic neural network are combined to optimize the smoothing factor with the sparrow search algorithm and the cross-entropy loss function as the fitness function to establish a braking intention recognition model. The experimental validation results show that combining the sample entropy features of the braking signal with the probabilistic neural network can effectively identify the braking intention, and the SSA-PNN algorithm has higher recognition accuracy compared with the traditional machine learning algorithm.

Real-space observation of ergodicity transitions in artificial spin ice

Ever since its introduction by Ludwig Boltzmann, the ergodic hypothesis became a cornerstone analytical concept of equilibrium thermodynamics and complex dynamic processes. Examples of its relevance range from modeling decision-making processes in brain science to economic predictions. In condensed matter physics, ergodicity remains a concept largely investigated via theoretical and computational models. Here, we demonstrate the direct real-space observation of ergodicity transitions in a vertex-frustrated artificial spin ice. Using synchrotron-based photoemission electron microscopy we record thermally-driven moment fluctuations as a function of temperature, allowing us to directly observe transitions between ergodicity-breaking dynamics to system freezing, standing in contrast to simple trends observed for the temperature-dependent vertex populations, all while the entropy features arise as a function of temperature. These results highlight how a geometrically frustrated system, with thermodynamics strictly adhering to local ice-rule constraints, runs back-and-forth through periods of ergodicity-breaking dynamics. Ergodicity breaking and the emergence of memory is important for emergent computation, particularly in physical reservoir computing. Our work serves as further evidence of how fundamental laws of thermodynamics can be experimentally explored via real-space imaging.

Can multi-modal radiomics using pretreatment ultrasound and tomosynthesis predict response to neoadjuvant systemic treatment in breast cancer?

ObjectivesResponse assessment to neoadjuvant systemic treatment (NAST) to guide individualized treatment in breast cancer is a clinical research priority. We aimed to develop an intelligent algorithm using multi-modal pretreatment ultrasound and tomosynthesis radiomics features in addition to clinical variables to predict pathologic complete response (pCR) prior to the initiation of therapy.MethodsWe used retrospective data on patients who underwent ultrasound and tomosynthesis before starting NAST. We developed a support vector machine algorithm using pretreatment ultrasound and tomosynthesis radiomics features in addition to patient and tumor variables to predict pCR status (ypT0 and ypN0). Findings were compared to the histopathologic evaluation of the surgical specimen. The main outcome measures were area under the curve (AUC) and false-negative rate (FNR).ResultsWe included 720 patients, 504 in the development set and 216 in the validation set. Median age was 51.6 years and 33.6% (242 of 720) achieved pCR. The addition of radiomics features significantly improved the performance of the algorithm (AUC 0.72 to 0.81; p = 0.007). The FNR of the multi-modal radiomics and clinical algorithm was 6.7% (10 of 150 with missed residual cancer). Surface/volume ratio at tomosynthesis and peritumoral entropy characteristics at ultrasound were the most relevant radiomics. Hormonal receptors and HER-2 status were the most important clinical predictors.ConclusionA multi-modal machine learning algorithm with pretreatment clinical, ultrasound, and tomosynthesis radiomics features may aid in predicting residual cancer after NAST. Pending prospective validation, this may facilitate individually tailored NAST regimens.Clinical relevance statementMulti-modal radiomics using pretreatment ultrasound and tomosynthesis showed significant improvement in assessing response to NAST compared to an algorithm using clinical variables only. Further prospective validation of our findings seems warranted to enable individualized predictions of NAST outcomes.Key Points• We proposed a multi-modal machine learning algorithm with pretreatment clinical, ultrasound, and tomosynthesis radiomics features to predict response to neoadjuvant breast cancer treatment.• Compared with the clinical algorithm, the AUC of this integrative algorithm is significantly higher.• Used prior to the initiative of therapy, our algorithm can identify patients who will experience pathologic complete response following neoadjuvant therapy with a high negative predictive value.

Inspection of Couette and pressure-driven Poiseuille entropy-optimized dissipated flow in a suction/injection horizontal channel: Analytical solutions

Abstract The main aim of this study is to analyse the electrically conductive flow of compressible liquids by two infinitely permeable surfaces. The distance between the two surfaces is h h . Thermal relation consists of viscous dissipation. The entropy features along with magnetic force and dissipation are taken into account. The x-axis extends in the flow path along the bottom stationary plate, whereas the y-axis is orthogonal to the surfaces. The channel plates are subjected to a consistent transverse magnetic field that is implemented perpendicularly. Herein, two scenarios are investigated: the first is the Couette flow, and in the second scenario, both porous surfaces are parallel and fixed at a distance of 2h, and the motion is a Poiseuille flow controlled by pressure. The flow across the x x -axis is supposed to be generated and dependent on y y exclusively. The governed system is solved using analytical solutions. It is found that the entropy formation is higher near the cloud porous plate in comparison to the hot porous plate and the increasing values of the suction/injection parameter increase the fluid temperature. The increase in the magnetic field parameter decreases the momentum boundary layer thickness. The Brinkman number improves the thermal boundary thickness. The magnetic field parameter, suction/injection, and the Brinkman number accelerate the entropy formation in both cases.

EEG Emotion Recognition by Fusion of Multi-Scale Features.

Electroencephalogram (EEG) signals exhibit low amplitude, complex background noise, randomness, and significant inter-individual differences, which pose challenges in extracting sufficient features and can lead to information loss during the mapping process from low-dimensional feature matrices to high-dimensional ones in emotion recognition algorithms. In this paper, we propose a Multi-scale Deformable Convolutional Interacting Attention Network based on Residual Network (MDCNAResnet) for EEG-based emotion recognition. Firstly, we extract differential entropy features from different channels of EEG signals and construct a three-dimensional feature matrix based on the relative positions of electrode channels. Secondly, we utilize deformable convolution (DCN) to extract high-level abstract features by replacing standard convolution with deformable convolution, enhancing the modeling capability of the convolutional neural network for irregular targets. Then, we develop the Bottom-Up Feature Pyramid Network (BU-FPN) to extract multi-scale data features, enabling complementary information from different levels in the neural network, while optimizing the feature extraction process using Efficient Channel Attention (ECANet). Finally, we combine the MDCNAResnet with a Bidirectional Gated Recurrent Unit (BiGRU) to further capture the contextual semantic information of EEG signals. Experimental results on the DEAP dataset demonstrate the effectiveness of our approach, achieving accuracies of 98.63% and 98.89% for Valence and Arousal dimensions, respectively.