Multi-feature Fusion Method Research Articles

Fault-tolerant reconfiguration estimation and control of vehicle state under sensor fault

Purpose The purpose of this study proposes a strategy based on vehicle kinematics, dynamics and fusion estimation. The estimation signal of vehicle driving state is crucial for vehicle driving safety and stability control, and the issue of fault-tolerant reconstruction estimation of vehicle driving state under the failure of yaw rate or lateral acceleration sensors is a significant research topic. Design/methodology/approach A strategy based on vehicle kinematics, dynamics and fusion estimation is proposed. To address the issue of inaccurate calculation of tire forces because of sensor failure, a method combining adaptive sliding mode observer, genetic algorithm and particle swarm optimization algorithm is proposed to accurately calculate tire forces, and the Square Root Cubature Kalman Filter algorithm is used to reconstruct the estimation of vehicle driving state under sensor failure. To improve the accuracy of fault-tolerant reconstruction estimation of vehicle driving state, an error-weighted multi-method fusion estimation strategy for vehicle driving state is proposed. A fast terminal sliding mode control algorithm is proposed to control the stability of the fault-tolerant reconstruction estimation signal of vehicle driving state. Findings Simulation results show that the proposed fault-tolerant reconstruction estimation algorithm for vehicle driving state can accurately estimate the actual driving state of the vehicle and stably participate in the vehicle stability control system, achieving fault-tolerant reconstruction estimation and control of vehicle driving state under sensor failure. Originality/value The problem of vehicle motion state estimation under yaw velocity sensor fault or lateral acceleration sensor fault is solved, and fault tolerance control under sensor state is realized.

Exercise ECG Classification Based on Novel R-Peak Detection Using BILSTM-CNN and Multi-Feature Fusion Method

Excessive exercise is a primary cause of sports injuries and sudden death. Therefore, it is vital to develop an effective monitoring technology for exercise intensity. Based on the noninvasiveness and real-time nature of an electrocardiogram (ECG), exercise ECG classification based on ECG features could be used for detecting exercise intensity. However, current R-peak detection algorithms still have limitations, especially in high-intensity exercise scenarios and in the presence of noise interference. Additionally, the features utilized for exercise ECG classification are not comprehensive. To address these issues, the following tasks have been accomplished: (1) a hybrid time–frequency-domain model, BILSTM-CNN, is proposed for R-peak detection by utilizing BILSTM, multi-scale convolution, and an attention mechanism; (2) to enhance the robustness of the detector, a preprocessing data generator and a post-processing adaptive filter technique are proposed; (3) to improve the reliability of exercise intensity detection, the accurate heart rate variability (HRV) features derived from the proposed BILSTM-CNN and comprehensive features are constructed, which include various descriptive features (wavelets, local binary patterns (LBP), and higher-order statistics (HOS)) tested by the feasibility experiments and optimized deep learning features extracted from the continuous wavelet transform (CWT) of exercise ECG signals. The proposed system is evaluated by real ECG datasets, and it shows remarkable effectiveness in classifying five types of motion states, with an accuracy of 99.1%, a recall of 99.1%, and an F1 score of 99.1%.

Enhanced Protein Secondary Structure Prediction Through Multi-View Multi-Feature Evolutionary Deep Fusion Method

Enhanced Protein Secondary Structure Prediction Through Multi-View Multi-Feature Evolutionary Deep Fusion Method

Multilingual pretrained based multi-feature fusion model for English text classification

Deep learning methods have been widely applied to English text classification tasks in recent years, achieving strong performance. However, current methods face two significant challenges: (1) they struggle to effectively capture long-range contextual structure information within text sequences, and (2) they do not adequately integrate linguistic knowledge into representations for enhancing the performance of classifiers. To this end, a novel multilingual pre-training based multi-feature fusion method is proposed for English text classification (MFFMP-ETC). Specifically, MFFMP-ETC consists of the multilingual feature extraction, the multilevel structure learning, and the multi-view representation fusion. MFFMP-ETC utilizes the Multilingual BERT as deep semantic extractor to introduce language information into representation learning, which significantly endows text representations with robustness. Then, MFFMP-ETC integrates Bi-LSTM and TextCNN into multilingual pre-training architecture to capture global and local structure information of English texts, via modelling bidirectional contextual semantic dependencies and multi-granularity local semantic dependencies. Meanwhile, MFFMP-ETC devises the multi-view representation fusion within the invariant semantic learning of representations to aggregate consistent and complementary information among views. MFFMP-ETC synergistically integrates Multilingual BERT?s deep semantic features, Bi-LSTM?s bidirectional context processing, and TextCNN local feature extraction, offering a more comprehensive and effective solution for capturing long-distance dependencies and nuanced contextual information in text classification. Finally, results on three datasets show MFFMP-ETC conducts a new baseline in terms of accuracy, sensitivity, and precision, verifying progressiveness and effectiveness of MFFMP-ETC in the text classification.

Graph-Based Multi-Feature Fusion Method for Speech Emotion Recognition

Exploring proper way to conduct multi-speech feature fusion for cross-corpus speech emotion recognition is crucial as different audio features could provide complementary cues reflecting human emotion status. Speech emotion recognition allows computers to analyze the specific emotional condition of the speaker through speech, which is of great significance to the development of human–computer interaction technology. While most previous approaches only extract a single speech feature for emotion recognition, existing fusion methods such as concatenation, parallel connection, and splicing ignore heterogeneous patterns in the interaction between features and features, resulting in performance of existing systems. In this paper, we propose a novel graph-based fusion method to explicitly model the relationships between every pair of audio features, which provides a new research idea for speech feature fusion. Specifically, we propose a multi-dimensional edge features learning strategy called graph-based multi-feature fusion method for speech emotion recognition. It represents each speech feature as a node and learns multi-dimensional edge features to explicitly describe the relationship between each feature-feature pair in the context of emotion recognition. This way, the learned multi-dimensional edge features encode speech feature-level information from both the vertex and edge dimensions. Our approach consists of three modules: an Audio Feature Generation (AFG) module, an Audio-Feature Multi-dimensional Edge Feature (AMEF) module and a Speech Emotion Recognition (SER) module. The proposed methodology yielded satisfactory outcomes on the SEWA dataset. Furthermore, the method demonstrated enhanced performance compared to the baseline in the AVEC 2019 Workshop and Challenge. We used data from two cultures as our training and validation sets: two cultures containing German and Hungarian on the SEWA dataset, the CCC scores for German are improved by 17.28% for arousal and 7.93% for liking, and for Hungarian, the CCC scores are improved by 11.15% for arousal and 131.11% for valence. The outcomes of our methodology demonstrate a 13% improvement over alternative fusion techniques, including those employing one-dimensional edge-based feature fusion approach. The experiments on some parts of the Aff-Wild 2 dataset demonstrate that our approach exhibits a certain degree of generalizability and robustness. Code is available at https://github.com/ChaosWang666/Graph-based-multi-Feature-fusion-method .

Risk coupling analysis of miners’ health-compromising behaviors: A multimethod fusion with practical application

Risk analysis of miners’ health-compromising behaviors is essential for advancing their overall health and well-being. This paper proposed a method for quantifying the risk coupling of miners’ health-compromising behaviors based on the Bayesian network (BN) model, N-K model, and cumulative risk (CR) model. First, the causation of miners’ health-compromising behaviors was analyzed, and the risk factors were systematically classified. Second, the types of risk coupling resulting from physical environmental risk factors, psychosocial environmental risk factors, and individual characteristics risk factors were delineated. Third, the BN model was constructed through a comprehensive risk analysis of miners’ health-compromising behaviors. Leveraging both the N-K model and the CR model, calculations were applied to the questionnaire data to identify the parameters influencing the risk coupling nodes within the developed BN. Finally, the established model undergoes validation through a three-axiom-based method. Subsequently, a sensitivity analysis of risk coupling types was conducted, and the influences of risk factors were quantified using mutual information. Employing the developed model, an uncertainty analysis was performed to explore the effects of failure rates of risk factors on the primary risk coupling types.

Research on Road Rage Detection System Based on Multi-feature Fusion

The influence of driver's rage on driving safety is one of the centers of traffic accident research. Road rage is a common potential factor affecting driving safety. Real-time monitoring of driver's emotional state and timely intervention measures can effectively reduce the incidence of traffic accidents. At present, the reliability of driver emotion recognition based on single consistent factor for road rage needs to be further improved. Therefore, based on the multi-feature fusion method, this paper proposes a recognition method of driver's road rage emotional state that integrates facial expression, driving control, voice text and physiological characteristics, and proposes the analysis of fusion strategy. In order to improve the reliability and implementability of road rage symptom judgment, this paper studies the state identification methods of road rage and integrates the characteristics of road rage. The focus of this study is to solve the key problem of insufficient reliability of road rage recognition based on facial expressions through the combination of multiple features and multiple data, aiming at the defects of the study on the single feature of road rage, and effectively improve the accuracy of road rage state emotion detection.

A Multi-Feature Fusion Method for Life Prediction of Automotive Proton Exchange Membrane Fuel Cell Based on TCN-GRU.

The Proton Exchange Membrane Fuel Cell (PEMFC) is a fast-developing battery technology, and the key to its reliability and lifespan improvement lies in the accurate assessment of durability. However, the degradation mechanism of the PEMFC is hard to determine and its internal parameters are highly coupled. Thus, the development of a more accurate life prediction model that meets the actual scenarios is to be investigated urgently. To solve this problem, a multi-feature fusion life prediction method based on the Temporal Convolutional Network-Gated Recurrent Unit (TCN-GRU) is proposed. A TCN algorithm is used as the prediction base model, and two GRU modules are included with the model to strengthen the model's expression ability and improve its predictive accuracy. Two widely recognized datasets and two operating conditions are utilized for model training and prediction, respectively. Comparisons are made with single-feature parameter models in terms of Root Mean Square Error (RMSE) and the Determination Coefficient (R2). The results show that the prediction accuracy of the TCN-GRU multi-feature fusion model is higher than that of the single-feature models in terms of stability and anti-interference under both operating conditions. The accuracy of the TCN-GRU (three-feature) model is the most optimal in a steady-state condition at 80% of the training set ratio (RMSE = 3.27 × 10-3, R2 = 0.965). Furthermore, with the increase in the input feature parameter, the TCN-GRU model is closer to the real value, which proves once again that the proposed model can meet the accuracy requirements of the life prediction of the PEMFC.

EMFSA: Emoji-based multifeature fusion sentiment analysis

Short texts on social platforms often suffer from insufficient emotional semantic expressions, sparse features, and polysemy. To enhance the accuracy achieved by sentiment analysis for short texts, this paper proposes an emoji-based multifeature fusion sentiment analysis model (EMFSA). The model mines the sentiments of emojis, topics, and text features. Initially, a pretraining method for feature extraction is employed to enhance the semantic expressions of emotions in text by extracting contextual semantic information from emojis. Following this, a sentiment- and emoji-masked language model is designed to prioritize the masking of emojis and words with implicit sentiments, focusing on learning the emotional semantics contained in text. Additionally, we proposed a multifeature fusion method based on a cross-attention mechanism by determining the importance of each word in a text from a topic perspective. Next, this method is integrated with the original semantic information of emojis and the enhanced text features, attaining improved sentiment representation accuracy for short texts. Comparative experiments conducted with the state-of-the-art baseline methods on three public datasets demonstrate that the proposed model achieves accuracy improvements of 2.3%, 10.9%, and 2.7%, respectively, validating its effectiveness.

Hybrid network via key feature fusion for image restoration

In the field of artificial intelligence, combining transformers and convolutional neural networks (CNNs) to improve performance has become a popular solution for various image restoration tasks. However, the hyperparameters related to feature levels are empirical, leading to the inevitable presence of redundant features that hinder effective image restoration. Additionally, the current method of fusing global and local information is simple and direct, failing to fully exploit the potential of hybrid architectures. To address this issue, we propose a key feature fusion hybrid network (KF2H-Net) that reduces redundancy and dynamically fuses key features. On one hand, we create different learnable selection mechanisms within the hybrid network’s various units to choose global key features and local key features, enhancing the depth perception and selection capabilities for different features. On the other hand, through a parameter fusion module for dynamic feature fusion, we refine the multi-feature fusion method to emphasize the more critical features for image restoration. In order to verify the general performance of the proposed KF2H-Net, we specially selected three typical scenarios (underwater, low-light, and haze) for testing. KF2H-Net represents a novel approach to hybrid models addressing practical applications in the field of artificial intelligence. Extensive experiments show that KF2H-Net achieves state-of-the-art performance across different scenarios.

Federated Learning with Multi-Method Adaptive Aggregation for Enhanced Defect Detection in Power Systems

The detection and identification of defects in transmission lines using computer vision techniques is essential for maintaining the safety and reliability of power supply systems. However, existing training methods for transmission line defect detection models predominantly rely on single-node training, potentially limiting the enhancement of detection accuracy. To tackle this issue, this paper proposes a server-side adaptive parameter aggregation algorithm based on multi-method fusion (SAPAA-MMF) and formulates the corresponding objective function. Within the federated learning framework proposed in this paper, each client executes distributed synchronous training in alignment with the fundamental process of federated learning. The hierarchical difference between the global model, aggregated using the improved joint mean algorithm, and the global model from the previous iteration is computed and utilized as the pseudo-gradient for the adaptive aggregation algorithm. This enables the adaptive aggregation to produce a new global model with improved performance. To evaluate the potential of SAPAA-MMF, comprehensive experiments were conducted on five datasets, involving comparisons with several algorithms. The experimental results are analyzed independently for both the server and client sides. The findings indicate that SAPAA-MMF outperforms existing federated learning algorithms on both the server and client sides.

Multifeature Fusion Method with Metaheuristic Optimization for Automated Voice Pathology Detection

Voice pathologies occur due to various factors, such as malfunction of the vocal cords. Computerized acoustic examination-based vocal pathology detection is crucial for early diagnosis, efficient follow-up, and improving problematic speech. Different acoustic measurements provide it. Executing this process requires expert monitoring and is not preferred by patients because it is time-consuming and costly. This paper is aimed at detecting metaheuristic-based automatic voice pathology. First, feature maps of ten common diseases, including cordectomy, dysphonia, front lateral partial resection, contact pachyderma, laryngitis, lukoplakia, pure breath, recurrent laryngeal paralysis, vocal fold polyp, and vox senilis, were obtained from the Zero-Crossing Rate (ZCR), Root-Mean-Square Energy (RMSE), and Mel-frequency Cepstral Coefficients (MFCCs) using a thousand voice signals from the Saarbruecken Voice Database (SVD) dataset. Hybridizations of different features obtained from the voices of the same diseases using these three methods were used to increase the model's performance. The Grey Wolf Optimizer (MELGWO) algorithm based on local search, evolutionary operator, and concatenated feature maps derived from various approaches was employed to minimize the number of features, implement the models faster, and produce the best result. The fitness values of the metaheuristic algorithms were then determined using supervised machine learning techniques such as Support Vector Machine (SVM) and K-nearest neighbors (KNN). The F1 score, sensitivity, specificity, accuracy, and other assessment criteria were compared with the experimental data. The best accuracy result was achieved with 99.50% from the SVM classifier using the feature maps optimized by the improved MELGWO algorithms.

Co-estimation of state-of-charge and capacity for series-connected battery packs based on multi-method fusion and field data

Accurate state-of-charge (SOC) and capacity estimations are of great importance for the performance management, predictive maintenance, and safe operation of lithium-ion battery packs in electric vehicles (EVs). However, it is quite challenging to estimate real-world large-sized EV battery packs due to the unpredictable operating profiles and large measurement disturbances. This article proposes an adaptive onboard SOC and capacity co-estimation framework, which incorporates a multi-timescale hierarchy and integrates multiple individual methods adaptively to practical driving profiles. First, this framework considers the most evident inconsistency between battery cells and periodically screens the weakest cells in a long timescale (week-level). Subsequently, the SOC of the battery pack is accurately estimated in a short timescale (in real-time) based on multi-method fusion. Finally, the capacity of the battery pack is periodically calibrated in a medium timescale (minute-level) based on an adaptive state filter and reliable SOC estimation. Both the laboratory and field data were used for validation, and the results demonstrated the proposed method achieved accurate SOC and capacity estimations of large-sized EV battery packs, with the maximum root mean squared errors of <0.7 % and <3.2 %, respectively, and it was run five times faster than the multi-cell model-based method.

A Water Demand Forecasting Model Based on Generative Adversarial Networks and Multivariate Feature Fusion

Accurate long-term water demand forecasting is beneficial to the sustainable development and management of cities. However, the randomness and nonlinear nature of water demand bring great challenges to accurate long-term water demand forecasting. For accurate long-term water demand forecasting, the models currently in use demand the input of extensive datasets, leading to increased costs for data gathering and higher barriers to entry for predictive projects. This situation underscores the pressing need for an effective forecasting method that can operate with a smaller dataset, making long-term water demand predictions more feasible and economically sensible. This study proposes a framework to delineate and analyze long-term water demand patterns. A forecasting model based on generative adversarial networks and multivariate feature fusion (the water demand forecast-mixer, WDF-mixer) is designed to generate synthetic data, and a gradient constraint is introduced to overcome the problem of overfitting. A multi-feature fusion method based on temporal and channel features is then derived, where a multi-layer perceptron is used to capture temporal dependencies and non-negative matrix decomposition is applied to obtain channel dependencies. After that, an attention layer receives all those features associated with the water demand forecasting, guiding the model to focus on important features and representing correlations across them. Finally, a fully connected network is constructed to improve the modeling efficiency and output the forecasting results. This approach was applied to real-world datasets. Our experimental results on four water demand datasets show that the proposed WDF-mixer model can achieve high forecasting accuracy and robustness. In comparison to the suboptimal models, the method introduced in this study demonstrated a notable enhancement, with a 62.61% reduction in the MSE, a 46.85% decrease in the MAE, and a 69.15% improve in the R2 score. This research could support decision makers in reducing uncertainty and increasing the quality of water resource planning and management.

A remaining useful life prediction framework with adaptive dynamic feedback

Remaining useful life (RUL) prediction of components is a crucial aspect of mechanical systems prognostic and health management. However, during the online RUL prediction of components, the existing method cannot use the prediction results for feedback and optimize the prediction model. To address this issue, this paper proposes a framework for RUL prediction with adaptive dynamic feedback. First, a feedback multi-feature fusion (FMFF) method is designed. It introduces a series of non-exceeding threshold positive constants, that is fraction thresholds (FT), to perform division of the degradation state dimension. Besides, the first hitting time (FHT) from the current moment to FT is the fraction remaining useful life (FRUL). It is used to construct and update the fusion factors. Then, the feedback multi-model selection (FMMS) method is proposed for adaptive feedback and to select the degradation model based on the FRUL prediction results in different stages. The probability density function of RUL based on the FHT is calculated based on the FMMS method to realize the RUL prediction of the component. Finally, the effectiveness and superiority of the proposed framework are validated based on XJTU-SY dataset and run-to-failure test.

Research on the PDC rock cuttings image instance segmentation method based on improved U-Net++ network and multi-feature fusion

Currently, PDC bits dominate the petroleum bit market. It is a small cut of polycrystalline diamond, which is embedded in the body of the drill bit. Due to the small number of cuttings generated through the PDC bit, the individual cuttings are small, and the cuttings edge is blurred, which results in poor effect and low precision of traditional image segmentation. Therefore, this paper proposes an image segmentation method regarding deep learning. Firstly, a multi-task learning method is introduced based on the U-Net segmentation model. A multi-task-learning-U-Net++ instance segmentation model is proposed. The results of semantic segmentation and edge segmentation are obtained by this segmentation model. Then, the cuttings are segmented by superpixel to obtain the sub-blocks of superpixel. Finally, a multi-feature fusion method is proposed, which integrates semantic information, edge information and superpixel sub-blocks to obtain the segmentation result of cuttings image. Experimental results show that the proposed method can effectively segment each cutting in the image and this method has certain robustness. Compared with the segmentation algorithms such as U-Net and U-Net++, this algorithm performs better in multiple image segmentation performance indexes.

Damage effect evaluation of CCD irradiated by laser based on multi-source information fusion

This study introduces an advanced approach for assessing the damage state of charge-coupled devices (CCDs) caused by laser interactions, leveraging a multi-source and multi-feature information fusion technique. We established an experimental system that simulates laser damage on CCDs and collects diverse data types including echo information from active laser detection based on the ‘cat's eye’ effect, plasma flash data, and surface image characteristics of the CCD. A probabilistic neural network (PNN) was utilized to integrate these data sources effectively. Our analysis demonstrated that using multiple features from single sources significantly improves the accuracy of the damage assessment compared to single-feature evaluations. The error rates using dual features from each information type were 10.65% for cat's eye echo, 7.3% for plasma flash, and 7.17% for surface image analysis. By combining all three information sources and six features, we successfully reduced the error rate to 0.85%, with the evaluation time under 60 milliseconds. These findings confirm that our multi-source, multi-feature fusion method is highly effective for the online and real-time evaluation of CCD damage, offering significant improvements in the operational reliability and safety of devices in high-energy environments.

Defect identification of bare printed circuit boards based on Bayesian fusion of multi-scale features.

The aim of this article is to propose a defect identification method for bare printed circuit boards (PCB) based on multi-feature fusion. This article establishes a description method for various features of grayscale, texture, and deep semantics of bare PCB images. First, the multi-scale directional projection feature, the multi-scale grey scale co-occurrence matrix feature, and the multi-scale gradient directional information entropy feature of PCB were extracted to build the shallow features of defect images. Then, based on migration learning, the feature extraction network of the pre-trained Visual Geometry Group16 (VGG-16) convolutional neural network model was used to extract the deep semantic feature of the bare PCB images. A multi-feature fusion method based on principal component analysis and Bayesian theory was established. The shallow image feature was then fused with the deep semantic feature, which improved the ability of feature vectors to characterize defects. Finally, the feature vectors were input as feature sequences to support vector machines for training, which completed the classification and recognition of bare PCB defects. Experimental results show that the algorithm integrating deep features and multi-scale shallow features had a high recognition rate for bare PCB defects, with an accuracy rate of over 99%.

Optimized Demand Forecasting for Bike-Sharing Stations Through Multi-Method Fusion and Gated Graph Convolutional Neural Networks

Optimized Demand Forecasting for Bike-Sharing Stations Through Multi-Method Fusion and Gated Graph Convolutional Neural Networks

Enhanced Object Detection and Classification via Multi-Method Fusion

Enhanced Object Detection and Classification via Multi-Method Fusion