Feature Analysis Method Research Articles

Spectral Zones-Based SHAP/LIME: Enhancing Interpretability in Spectral Deep Learning Models Through Grouped Feature Analysis.

Interpretability is just as important as accuracy when it comes to complex models, especially in the context of deep learning models. Explainable artificial intelligence (XAI) approaches have been developed to address this problem. The literature on XAI for spectroscopy mainly emphasizes independent feature analysis with limited application of zone analysis. Individual feature analysis methods, such as shapley additive explanations (SHAP) and local interpretable model-agnostic explanations (LIME), have limitations due to their dependence on perturbations. These methods measure how AI models respond to sudden changes in the individual feature values. While they can help identify the most impactful features, the abrupt shifts introduced by replacing these values with zero or the expected ones may not accurately represent real-world scenarios. This can lead to mathematical and computational interpretations that are neither physically realistic nor intuitive to humans. Our proposed method does not rely on individual disturbances. Instead, it targets "spectral zones" to directly estimate the effect of group disturbances on a trained model. Consequently, factors such as sample size, hyperparameter selection, and other training-related considerations are not the primary focus of the XAI methods. To achieve this, we have developed a modified version of LIME and SHAP capable of performing group perturbations, enhancing explainability and realism while minimizing noise in the plots used for interpretability. Additionally, we employed an efficient approach to calculate spectral zones for complex spectra with indistinct spectral boundaries. Users can also define the zones themselves using their domain-specific knowledge.

Enhancing deep learning-based slope stability classification using a novel metaheuristic optimization algorithm for feature selection

The evaluation of slope stability is of crucial importance in geotechnical engineering and has significant implications for infrastructure safety, natural hazard mitigation, and environmental protection. This study aimed to identify the most influential factors affecting slope stability and evaluate the performance of various machine learning models for classifying slope stability. Through correlation analysis and feature importance evaluation using a random forest regressor, cohesion, unit weight, slope height, and friction angle were identified as the most critical parameters influencing slope stability. This research assessed the effectiveness of machine learning techniques combined with modern feature selection algorithms and conventional feature analysis methods. The performance of deep learning models, including recurrent neural networks (RNNs), long short-term memory (LSTM) networks, and generative adversarial networks (GANs), in slope stability classification was evaluated. The GAN model demonstrated superior performance, achieving the highest overall accuracy of 0.913 and the highest area under the ROC curve (AUC) of 0.9285. Integration of the binary bGGO technique for feature selection with the GAN model led to significant improvements in classification performance, with the bGGO-GAN model showing enhanced sensitivity, positive predictive value, negative predictive value, and F1 score compared to the classical GAN model. The bGGO-GAN model achieved 95% accuracy on a substantial dataset of 627 samples, demonstrating competitive performance against other models in the literature while offering strong generalizability. This study highlights the potential of advanced machine learning techniques and feature selection methods for improving slope stability classification and provides valuable insights for geotechnical engineering applications.

Physics-informed probabilistic slow feature analysis

This paper presents a novel approach called physics-informed probabilistic slow feature analysis. The probabilistic slow feature analysis method has been employed to extract slowly varying latent patterns from high-dimensional measured data. The extracted slow features have proven effective in industrial applications such as soft sensing and process monitoring. However, industrial processes come with various physical constraints that must be taken into account, such as energy requirements, equipment limitations, and safety considerations. The conventional black-box nature of the slow feature model often leads to physically inconsistent or unacceptable results. To address this issue, we propose integrating physics principles into the probabilistic slow feature model, ensuring that the extracted features adhere to physics laws. Our formulation incorporates two types of physical constraints: linear algebraic equality and inequality constraints. Through an industrial case study, we demonstrate the effectiveness of our methodology, showcasing the advantages of incorporating physics in feature extraction. These advantages include improved interpretability, reduced data dimensionality, and enhanced generalization performance.

Surface roughness analysis of side-polished fiber based on the importance of texture features

In order to explore the use of side-polished fibre (SPF) for microprobe-type "lab-on-fibre", this study presents an analysis of the surface roughness in side-polished fiber (SPF) using the gray level co-occurrence matrix (GLCM) texture feature analysis method. Experimental results show that the flat areas of the SPF polished surface exhibit texture characteristics with high mean values in contrast and entropy, and low mean values in the angular second moment (ASM), homogeneity, and correlation. Employing the random forest (RF) feature importance ranking method based on the Gini coefficient and out-of-bag (OOB) error estimation, this study assesses the sensitivity of various GLCM texture parameters in classifying different roughness levels of the SPF polished surfaces. A feature subset comprising variance, ASM, entropy, and contrast is identified as optimal. Utilizing this subset, the paper conducts an RF classification validation experiment on the roughness of the SPF polished surfaces, with results showing an RF classification accuracy of 95.65%.This research provides evidence for exploring the impact of rough polished surfaces in SPF optic sensors on the light coupling mechanism with environmental materials and its influence on sensor sensitivity. It lays the foundation for exploring the precise identification of high-sensitivity areas on SPF polished surfaces.

Machine Learning Predicts Peripherally Inserted Central Catheters-Related Deep Vein Thrombosis Using Patient Features and Catheterization Technology Features.

This study aims to use patient feature and catheterization technology feature variables to train the corresponding machine learning (ML) models to predict peripherally inserted central catheters-deep vein thrombosis (PICCs-DVT) and analyze the importance of the two types of features to PICCs-DVT from the aspect of "input-output" correlation. To comprehensively and systematically summarize the variables used to describe patient features and catheterization technical features, this study combined 18 literature involving the two types of features in predicting PICCs-DVT. A total of 21 variables used to describe the two types of features were summarized, and feature values were extracted from the data of 1,065 PICCs patients from January 1, 2021 to August 31, 2022, to construct a data sample set. Then, 70% of the sample set is used for model training and hyperparameter optimization, and 30% of the sample set is used for PICCs-DVT prediction and feature importance analysis of three common ML classification models (i.e. support vector classifier [SVC], random forest [RF], and artificial neural network [ANN]). In terms of prediction performance, this study selected four metrics to evaluate the prediction performance of the model: precision (P), recall (R), accuracy (ACC), and area under the curve (AUC). In terms of feature importance analysis, this study chooses a single feature analysis method based on the "input-output" sensitivity principle-Permutation Importance. For the mean model performance, the three ML models on the test set are P = 0.92, R = 0.95, ACC = 0.88, and AUC = 0.81. Specifically, the RF model is P = 0.95, R = 0.96, ACC = 0.92, AUC = 0.86; the ANN model is P = 0.92, R = 0.95, ACC = 0.88, AUC = 0.81; the SVC model is P = 0.88, R = 0.94, ACC = 0.85, AUC = 0.77. For feature importance analysis, Catheter-to-vein rate (RF: 91.55%, ANN: 82.25%, SVC: 87.71%), Zubrod-ECOG-WHO score (RF: 66.35%, ANN: 82.25%, SVC: 44.35%), and insertion attempt (RF: 44.35%, ANN: 37.65%, SVC: 65.80%) all occupy the top three in the ML models prediction task of PICCs-DVT, showing relatively consistent ranking results. The ML models show good performance in predicting PICCs-DVT and reveal a relatively consistent ranking of feature importance from the data. The important features revealed might help clinical medical staff to better understand and analyze the formation mechanism of PICCs-DVT from a data-driven perspective.

Coupled Multimodal Emotional Feature Analysis Based on Broad-Deep Fusion Networks in Human-Robot Interaction.

A coupled multimodal emotional feature analysis (CMEFA) method based on broad-deep fusion networks, which divide multimodal emotion recognition into two layers, is proposed. First, facial emotional features and gesture emotional features are extracted using the broad and deep learning fusion network (BDFN). Considering that the bi-modal emotion is not completely independent of each other, canonical correlation analysis (CCA) is used to analyze and extract the correlation between the emotion features, and a coupling network is established for emotion recognition of the extracted bi-modal features. Both simulation and application experiments are completed. According to the simulation experiments completed on the bimodal face and body gesture database (FABO), the recognition rate of the proposed method has increased by 1.15% compared to that of the support vector machine recursive feature elimination (SVMRFE) (without considering the unbalanced contribution of features). Moreover, by using the proposed method, the multimodal recognition rate is 21.22%, 2.65%, 1.61%, 1.54%, and 0.20% higher than those of the fuzzy deep neural network with sparse autoencoder (FDNNSA), ResNet-101 + GFK, C3D + MCB + DBN, the hierarchical classification fusion strategy (HCFS), and cross-channel convolutional neural network (CCCNN), respectively. In addition, preliminary application experiments are carried out on our developed emotional social robot system, where emotional robot recognizes the emotions of eight volunteers based on their facial expressions and body gestures.

Estimation of Li-ion battery SOH based on factors combination of FBG wavelength shift and charge-discharge process

For the purpose of daily battery maintenance, safety forecasting, and energy ladder use, it is crucial to accurately estimate the state of health (SOH) of Li-ion batteries. The external fiber Bragg grating (FBG) sensor is used in this work to collect the signal fluctuations of the wavelength shift in different areas during the Li-ion battery's charge-discharge cycle using a combination of feature analysis and data-driven method, and the characteristics of the wavelength shift and the charge- discharge process in different regions under 125 cycles are statistically analyzed. The reaction degree of Li-ion battery in different areas was compared by wavelength shift value. The wavelength shift factor and charge-discharge process factor related to battery SOH were extracted and trained in the NGO-BP regression model. The experimental results show that the combination of fiber Bragg grating wavelength shift factor and charge-discharge process factor can accurately estimate the SOH of Li-ion battery, and the prediction effect of three areas combination is the best, the goodness of fit R2 is 0.99958, the mean square error MSE is 2.71 × 10−4, the mean absolute error MAE is 1.3373 × 10−2, the root mean square error RMSE is 1.6462 × 10−2, and the mean absolute percentage error MAPE is 1.3679 × 10−2%.The combination of negative electrode and middle area uses fewer sensors to obtain higher prediction accuracy, and its cost performance is the highest. The utilization of fiber Bragg grating wavelength shift factor and charge-discharge process factor has essentially led to the accurate calculation of Li-ion battery SOH, which holds significance for battery health monitoring as well as the design and development of battery management systems.

A method to assist designers in optimizing the exterior styling of vehicles based on key features

Aiming to assist the design and management personnel of automotive products to make correct judgments and give optimization solutions for the design of exterior styling, and to solve the defects of the traditional method which relies too much on experience and personal ability, a neural network-based key feature analysis and optimization method of styling is proposed. Firstly, the user attributes are analyzed and quantified, and the weighted optimization of user evaluation data is completed based on the multidimensional Gaussian distribution function to construct a more objective car styling evaluation dataset. Secondly, a particle swarm algorithm is proposed to optimize the prediction model of radial basis function neural network (PSO-RBFNN) which deeply analyzes the mapping relationship between different car perspectives and users’ perceptual preferences. The identification of styling components is completed with the annotation of feature points, and a parametric expression method of styling feature data with multi-viewpoint weight optimization is proposed. Third, the model interpretation is based on the embedded feature selection method to discover the key feature points affecting user perception, and the key common features of styling are obtained through the coupling relationship analysis of feature points. Finally, the optimal distribution range of key features is given based on statistical analysis, and the application process is shown by an example of optimization to verify the feasibility of the theory. Compared with the traditional methods, PSO-RBFNN has better prediction accuracy. Meanwhile, the modeling optimization method based on key features has the great advantages of objective accuracy and high efficiency compared with the traditional theory.

Monitoring method and application of transition process with nonstationary conditions based on stability factor partitioning and RSFA

It is common for the working conditions to change with time in actual industrial processes. However, the transition modes of complex industrial processes under different working conditions often have various degrees of dynamic nonstationarity, which makes the traditional process monitoring model based on the stationarity assumption ineffective. In this paper, a Recursive Slow Feature Analysis method based on Stability Factor Partitioning (SFP-RSFA) is proposed for fine process monitoring of transition modes under dynamic nonstationarity characteristics. First, we calculate the stability factor according to the different stationarity characteristics of the production process variables. Then, K-means clustering is carried out according to the stability factor of each variable, and the stability factor of the cluster center is mapped to the interval [0,1] as the smoothing coefficient of the exponential weighted moving average (EWMA), which is applied to each data subblock respectively to highlight the steady-state and dynamic characteristics of the monitoring data subblock. In the online monitoring stage, the monitored data are fed into the subblock recursive slow feature analysis (RSFA) monitoring model. Finally, a comprehensive statistic method is proposed to integrate the subblock monitoring statistics. The Tennessee Eastman (TE) process and actual cement clinker production process were tested and compared with existing RPCA, RCA and RSFA methods. The effectiveness and superiority of the proposed method in the problem of nonstationary transition mode process monitoring are verified.

A slow feature analysis approach for the optimization of collective variables.

Molecular dynamics simulations have become increasingly important in understanding the microscopic mechanisms of various molecular systems. However, the high energy barriers in complicated molecules often make it difficult to observe events of interest within a reasonable timescale. To address this issue, researchers have developed a variety of enhanced sampling methods to explore configuration space by adding bias potentials along the slowly changing collective variables (CVs). In this study, we have developed a new tool that combines slow feature analysis and biasing-enhanced sampling methods to identify effective CVs and enhance the sampling efficiency of configuration space. We have demonstrated the effectiveness of this tool through three general examples.

Fault Diagnosis and Detection for Battery System in Real-World Electric Vehicles Based on Long-Term Feature Outlier Analysis

Accurate detection and diagnosis battery faults are increasingly important to guarantee safety and reliability of battery systems. Developed methods for battery early fault diagnosis concentrate on short-term data to analyze the deviation of external features without considering the long-term latent period of faults. This work proposes a novel data-driven method to detect long-term latent fault and abnormality for electric vehicles based on real-world operation data. Specifically, the battery fault features are extracted from the incremental capacity curves, which are smoothed by advanced filter algorithms. Secondly, principal component analysis algorithm is utilized to reduce dimensionality and the cumulative percent variance is to determine the number of significant features. Based on the features, a cluster algorithm is employed to capture the battery potential failure information. Moreover, the cumulative root-mean-square-deviation is introduced to quantificationally analyze the degree of the battery failures using large-scale battery data to avoid the missing fault reports using short-term data. In addition, a battery system failure index is proposed to evaluate battery fault conditions. The results indicate that the proposed long-term feature analysis method can effectively detect and diagnose faults.

Detecting bulbar amyotrophic lateral sclerosis (ALS) using automatic acoustic analysis

Automatic speech assessments have the potential to dramatically improve ALS clinical practice and facilitate patient stratification for ALS clinical trials. Acoustic speech analysis has demonstrated the ability to capture a variety of relevant speech motor impairments, but implementation has been hindered by both the nature of lab-based assessments (requiring travel and time for patients) and also by the opacity of some acoustic feature analysis methods. These challenges and others have obscured the ability to distinguish different ALS disease stages/severities. Validation of automated acoustic analysis tools could enable detection of early signs of ALS, and these tools could be deployed to screen and monitor patients without requiring clinic visits. Here, we sought to determine whether acoustic features gathered using an automated assessment app could detect ALS as well as different levels of speech impairment severity resulting from ALS. Speech samples (readings of a standardized, 99-word passage) from 119 ALS patients with varying degrees of disease severity as well as 22 neurologically healthy participants were analyzed, and 53 acoustic features were extracted. Patients were stratified into early and late stages of disease (ALS-early/ALS-E and ALS-late/ALS-L) based on the ALS Functional Ratings Scale-Revised bulbar score (FRS-bulb) (median [interquartile range] of FRS-bulbar scores: 11[3]). The data were analyzed using a sparse Bayesian logistic regression classifier. It was determined that the current relatively small set of acoustic features could distinguish between ALS and controls well (area under receiver-operating characteristic curve/AUROC = 0.85), that the ALS-E patients could be separated well from control participants (AUROC = 0.78), and that ALS-E and ALS-L patients could be reasonably separated (AUROC = 0.70). These results highlight the potential for automated acoustic analyses to detect and stratify ALS.

Feature Extraction With Stacked Autoencoders for EEG Channel Reduction in Emotion Recognition.

Emotion recognition by electroencephalogram (EEG) signals is one of the complex methods because the extraction and recognition of the features hidden in the signal are sophisticated and require a significant number of EEG channels. Presenting a method for feature analysis and an algorithm for reducing the number of EEG channels fulfills the need for research in this field. Accordingly, this study investigates the possibility of utilizing deep learning to reduce the number of channels while maintaining the quality of the EEG signal. A stacked autoencoder network extracts optimal features for emotion classification in valence and arousal dimensions. Autoencoder networks can extract complex features to provide linear and non- linear features which are a good representative of the signal. The accuracy of a conventional emotion recognition classifier (support vector machine) using features extracted from SAEs was obtained at 75.7% for valence and 74.4% for arousal dimensions, respectively. Further analysis also illustrates that valence dimension detection with reduced EEG channels has a different composition of EEG channels compared to the arousal dimension. In addition, the number of channels is reduced from 32 to 12, which is an excellent development for designing a small-size EEG device by applying these optimal features.

Secure key generation and distribution scheme based on historical fiber channel state information with LSTM.

In this paper, a scheme to realize unclonable physical-layer security key generation and distribution (PL-SKGD) based on historical fiber channel state information (HFCSI) is proposed. PL-SKGD schemes based on channel characteristics for enhancing the physical-layer security of optical networks have been proposed in recent years. However, there are potential disadvantages in these schemes, such as 1) low key generation rate (KGR): the slow frequency of the analog waveform change of the channel characteristic leading to low KGR; 2) incompatibility with existing infrastructure: active scrambling to increase the frequency of channel characteristic changes, or tracking changes of channel characteristics requires additional devices; 3)easy to be cloned: all of the optical channel state information is reflected in the signal transmitted inside the fiber, which makes it easy to reproduce by illegal eavesdropper through features analysis and other methods. In order to solve the above problems, a PL-SKGD scheme is designed which uses the chain structure composed of long short-term memory neural network (LSTM-NN) units to learn and store the unique mapping relationship between historical channel time series and provides unclonability based on the fundamental fact that the eavesdropper Eve can never obtain the full HFCSI. The simulation conducted in a quadrature phase shift keying point-to-point optical link system verified successfully that KGR = 0.82 Gbit/s error-free SKGD. The loss function of LSTM-NN drops sharply in the early stages of training and remains a small value. The security of the SKGD system is analyzed, which effectively improves the unclonability of the system. Finally, it is verified that the optimal fiber channel length for error-free SKGD of the proposed scheme is 150 km considering the error correction capability of information reconciliation and weighing key sequence error rate and valid bit generation rate.

AN EFFICIENT FEATURE ANALYSIS METHOD OF BIOLOGICAL DATA FOR IMPROVING CATTLE CONCEPTION RATE

In this paper, we show an efficient feature analysis method of body surface temperature (ST) data so as to develop accurate prediction systems for artificial insemination (AI) timing of cattle. In the proposed analysis method, by using the fundamental waveform synthesis method based on the Fourier transform, approximate waveforms for the target waveform were derived. Additionally, reconstructed waveforms which does not correspond to both high frequency noise and circadian rhythm were generated. The two reconstructed waveforms derived from the approximate waveforms were used to predict the optimal AI timing and to discriminate the normal phase, respectively.

A novel parallel series data-driven model for IATA-coded flight delays prediction and features analysis

Predicting and analysing flight delays is essential for successful air traffic management and control. We propose a novel parallel-series model and novel adaptive bidirectional extreme learning machine (AB-ELM) method for prediction and feature analysis to better understand the causes of flight delays as stated by the International Air Transport Association (IATA). The IATA-coded flight delays are rarely examined in the existing studies. The IATA-coded flight delay subcategories decision boundaries are improved by the proposed parallel-series model. In application areas, where multiclass-multilabel classification may produce erroneous performance, the parallel-series model can be regarded as an alternate strategy. To improve network generalization performance, the proposed AB-ELM optimizes the covariance objective function by altering the learning rate adaptively during gradient ascent as opposed to gradient descent. The historical data from one of Hong Kong's international airlines, which contains information about the airport, flight, aircraft, weather, and IATA flight delay subcategories is considered a case study. Using fourteen different sampling approaches, the influence of imbalanced and noisy data was reduced. The results showed that employing proper sampling approaches in conjunction with the parallel-series model and AB-ELM method is effective for uncovering hidden patterns in the complicated IATA-coded flight delay subcategories system. When compared to other data-driven approaches, AB-ELM attained a high accuracy of 80.66 percent. This study enables airlines to develop adequate contingency measures in advance based on potential flight delay reasons and duration.

The Effect of COVID-19 on Chinas Real Estate Market via Different Angles

The trend of the real estate industry has become a hot topic of concern in contemporary society, and some studies have shown that after the epidemic, real estate has been conducted. The profitability of enterprises has declined significantly since there are many different opinions. This article aims to find the reasons from the three different perspectives of home buyers, housing enterprises, and governments based on the feature analysis method. The trend analysis method investigates the sales and pending sales of real estate products in the country. According to the analysis, real estate has indeed been on a downward spiral in recent years. The buyer does not have sufficient funds to buy a house. The cash flow of housing enterprises is also extremely tight, and in the year of the outbreak of the new crown epidemic, the volume of sales almost fell exponentially. Governments also need to continue to issue policies in a changing economic environment spectator control. In summary, China's real estate is still full of difficulties. These results shed light on guiding further exploration of real estate market.

Simulation and Reconstruction of Runoff in the High-Cold Mountains Area Based on Multiple Machine Learning Models

Runoff from the high-cold mountains area (HCMA) is the most important water resource in the arid zone, and its accurate forecasting is key to the scientific management of water resources downstream of the basin. Constrained by the scarcity of meteorological and hydrological stations in the HCMA and the inconsistency of the observed time series, the simulation and reconstruction of mountain runoff have always been a focus of cold region hydrological research. Based on the runoff observations of the Yurungkash and Kalakash Rivers, the upstream tributaries of the Hotan River on the northern slope of the Kunlun Mountains at different time periods, and the meteorological and atmospheric circulation indices, we used feature analysis and machine learning methods to select the input elements, train, simulate, and select the preferences of the machine learning models of the runoffs of the two watersheds, and reconstruct the missing time series runoff of the Kalakash River. The results show the following. (1) Air temperature is the most important driver of runoff variability in mountainous areas upstream of the Hotan River, and had the strongest performance in terms of the Pearson correlation coefficient (ρXY) and random forest feature importance (FI) (ρXY = 0.63, FI = 0.723), followed by soil temperature (ρXY = 0.63, FI = 0.043), precipitation, hours of sunshine, wind speed, relative humidity, and atmospheric circulation were weakly correlated. A total of 12 elements were selected as the machine learning input data. (2) Comparing the results of the Yurungkash River runoff simulated by eight machine learning methods, we found that the gradient boosting and random forest methods performed best, followed by the AdaBoost and Bagging methods, with Nash–Sutcliffe efficiency coefficients (NSE) of 0.84, 0.82, 0.78, and 0.78, while the support vector regression (NSE = 0.68), ridge (NSE = 0.53), K-nearest neighbor (NSE = 0.56), and linear regression (NSE = 0.51) were simulated poorly. (3) The application of four machine learning methods, gradient boosting, random forest, AdaBoost, and bagging, to simulate the runoff of the Kalakash River for 1978–1998 was generally outstanding, with the NSE exceeding 0.75, and the results of reconstructing the runoff data for the missing period (1999–2019) could well reflect the characteristics of the intra-annual and inter-annual changes in runoff.

A Method of User Travel Mode Recognition Based on Convolutional Neural Network and Cell Phone Signaling Data

As urbanization accelerates, traffic congestion in cities has become a problem. Therefore, accurately identifying urban residents’ travel patterns is crucial for urban traffic planning and intelligent transportation systems. In this study, a convolutional neural network (CNN) approach based on multichannel feature extraction using mobile phone signaling data to identify user travel modes is proposed. Here, a trajectory generation method was designed for five types of travel modes. By designing a spatiotemporal threshold screening method, anomalies were identified and processed, combined with the feature analysis method, key points in the signaling extracted, the travel trajectory sliced, and travel sub-trajectory data generated. Next, in the travel mode identification stage, road network information was introduced to improve localization accuracy, and the method for calculating feature values improved. A user travel feature dataset was generated by calculating the feature values, and the travel modes represented by each class were classified and recognized based on the CNN method. Satisfactory results were achieved through experiments using mobile phone signaling and field research data in Kunming, China. The experimental results showed that analysis based on mobile phone signaling data could classify, identify, and obtain different travel category modes. This method’s accuracy was 84.7%. The method provided a feasible way of identifying travel patterns in the context of smart cities and big data, providing strong support for urban transport planning and management, and has the potential for wider application.

Retracted: Feature Extraction and Analysis Method of Trombone Timbre Based on CNN Model

Retracted: Feature Extraction and Analysis Method of Trombone Timbre Based on CNN Model