Multi-dimensional Feature Extraction Research Articles

EEG-based affective computing in virtual reality with a balancing of the computational efficiency and recognition accuracy

The field of VR-EEG affective computing is rapidly progressing. However, it faces challenges such as lacking a solid psychological theory foundation, limited classification accuracy, and high computational costs. This study established a standardized VR video library to elicit emotions. Participants viewed positive, negative, and neutral VR videos while EEG data was collected. Grounded in the Affective Style Theory, this research proposes an emotion valence recognition strategy in VR that balances computational efficiency and classification accuracy through multidimensional complementary feature extraction from EEG signals, feature selection or dimensionality reduction coupled with classifiers, and optimal frequency band selection. The research findings indicate that multidimensional complementary feature extraction in frequency and spatial domains can enhance recognition performance. Notably, the theta frequency band features are pivotal in emotion valence recognition within VR environments. Strategies like PCA-RF and RBFNN outperform existing methods, achieving an average classification accuracy of up to 95.6% while maintaining computational efficiency. In terms of theoretical contributions, the study enhances our understanding of emotional perception consistency and variability under the Affective Style Theory, offering insights into individual emotional state recognition. In practical terms, it emphasizes efficiency-accuracy balance, making integrating VR-EEG affective computation technology into a broader range of applications feasible.

Speech emotion recognition based on multi-dimensional feature extraction and multi-scale feature fusion

In recent years, convolutional neural networks have been widely applied in the research of speech emotion recognition. However, most existing methods treat speech spectrogram features as images to learn the emotion features, which makes it difficult to capture rich emotion information at different scales. In this paper, a speech emotion recognition method based on multi-dimensional feature extraction and multi-scale feature fusion is proposed. Multi-dimensional features are extracted from Mel-frequency cepstral coefficients using parallel convolutional layers, emotion feature representations are learned at different scales using multi-scale residual convolutional layers, and a global feature fusion module is finally used to integrate local multi-scale emotion features to obtain key global emotion features. Experiments are conducted on the IEMOCAP, CREMA-D, and RAVDESS dataset, and the results show that our proposed network achieves a 3.5%-4% improvement in four commonly used evaluation metrics, including unweighted accuracy and weighted accuracy, compared with the state-of-the-art methods.

RCA-GAN: An Improved Image Denoising Algorithm Based on Generative Adversarial Networks

Image denoising, as an essential component of image pre-processing, effectively reduces noise interference to enhance image quality, a factor of considerable research importance. Traditional denoising methods often lead to the blurring of image details and a lack of realism at the image edges. To deal with these issues, we propose an image denoising algorithm named Residual structure and Cooperative Attention mechanism based on Generative Adversarial Networks (RCA-GAN). This algorithm proficiently reduces noise while focusing on preserving image texture details. To maximize feature extraction, this model first employs residual learning within a portion of the generator’s backbone, conducting extensive multi-dimensional feature extraction to preserve a greater amount of image details. Secondly, it introduces a simple yet efficient cooperative attention module to enhance the representation capacity of edge and texture features, further enhancing the preservation of intricate image details. Finally, this paper constructs a novel loss function—the Multimodal Loss Function—for the network training process. The experimental results were evaluated using Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity (SSIM) as evaluation metrics. The experimental results demonstrate that the proposed RCA-GAN image denoising algorithm has increased the average PSNR from 24.71 dB to 33.76 dB, achieving a 36.6% improvement. Additionally, the average SSIM value has risen from 0.8451 to 0.9503, indicating a 12.4% enhancement. It achieves superior visual outcomes, showcasing the ability to preserve image texture details to a greater extent and excel in edge preservation and noise suppression.

AC Series Arc Fault Diagnosis Method Based on AO-VMD Multidimensional Feature Extraction

In view of the difficulty in determining the number of mode components K and penalty factor α in VMD, which leads to poor signal decomposition effect and low diagnosis and recognition rate due to insufficient feature extraction in AC arc fault, an arc fault diagnosis method based on the Aquila algorithm was proposed to optimize the multivariate feature extraction of variational mode decomposition. First of all, the arc fault test platform was set up to consider the resistive, inductive, capacitive, and other household loads were considered to obtain the normal and fault current data. Second, the optimal K and α parameters were obtained by AO-VMD optimization and then decomposed into intrinsic mode functions (IMFs) by substituting them into VMD. Then, the time domain characteristics of the IMF2 component, the Energy Entropy of IMFs, and the Fuzzy Entropy of the kurtosis maximum IMFk component were extracted respectively, and the multidimensional fault characteristic matrix was constructed. Finally, the random forest (RF) model was used to accurately identify arc faults. The experiment shows that the average fault recognition rate of each type of load is above 99%, which has an excellent diagnostic effect.

Early detection and identification of white spot syndrome in shrimp using an improved deep convolutional neural network

White Spot Syndrome Virus (WSSV) is a major virus found in shrimp that causes huge economic loss in shrimp farms. A selective diagnostic approach for WSSV is required for the early diagnosis and protection of farms. This work proposes a novel recognition method based on improved Convolutional Neural Network (CNN) namely Dense Inception Convolutional Neural Network (DICNN) for diagnoses of WSSV disease. Initially, the process of data acquisition and data augmentation is carried out. The Inception structure is then used to improve the performance of multi-dimensional feature extraction. As a result, the proposed work has the highest accuracy of 97.22% when compared to other traditional models. The proposed work is targeted to Litopenaeus Vannamei (LV), and Penaeus Monodon (PM) diversities for major threats detection of White Spot Syndrome (WSS). Performance metrics related to accuracy have been compared with other traditional models, which demonstrate that our model will efficiently recognize shrimp WSSV disease.

Deep Learning-Based Geomagnetic Navigation Method Integrated with Dead Reckoning

Accurate location information has significant commercial and economic value as they are widely used in intelligent manufacturing, material localization and smart homes. Magnetic sequence-based approaches show great promise mainly due to their pervasiveness and stability. However, existing geomagnetic indoor localization methods are facing the problems of location ambiguity and feature extraction deficiency, which will lead to large localization errors. To address these issues, we propose a coarse-to-fine geomagnetic indoor localization method based on deep learning. First, a multidimensional geomagnetic feature extraction method is presented which can extract magnetic features from spatial and temporal aspects. Then, a hierarchical deep neural network model is devised to extract more accurate geomagnetic information and corresponding location clues for more accurate localization. Finally, localization is achieved through a particle filter combined with IMU localization. To evaluate the performance of the proposed methods, we carried out several experiments at three trial paths with two heterogeneous devices, Vivo X30 and Huawei Mate30. Experimental results demonstrate that the proposed algorithm can achieve more accurate localization performance than the state-of-the-art methods. Meanwhile, the proposed algorithm has low cost and good pervasiveness for different devices.

A Refined Multiscale Symbolic Diverse Entropy Technique for Detecting Weak Faults in Rotating Machinery

In rotating machinery components, it is difficult to extract incipient weak fault features directly from vibration signals. A fault feature extraction method based on refined multiscale symbolic dispersion entropy (RMSDE) is proposed. This method mainly combines symbolic coding and dynamic complexity evaluation to achieve multi-dimensional feature extraction. By constructing multiple sets of simulation signals to evaluate the correlation performance of the proposed method, the superior performance in complexity estimation, anti-noise interference and computational efficiency is mainly demonstrated. When RMSDE is combined with a self-organizing fuzzy logic classifier (SOF), the results show that the proposed RMSDE-SOF method can achieve high-precision fault diagnosis of rotating machinery. The effectiveness and robustness of the proposed method in fault feature extraction and diagnosis are verified by using the rolling bearing dataset and gear dataset, which contain multiple fault types, and the comprehensive performance of the proposed method is better than that of similar feature extraction methods. The final results show that the proposed method is superior to the other methods in rotating machinery fault diagnosis.

Multi-dimensional feature extraction method for distributed optical fiber sensing signals

Multi-dimensional feature extraction method for distributed optical fiber sensing signals

Privacy Protection Method Based On Multidimensional Feature Fusion Under 6G Networks

6G networks can flexibly arrange network resources in multiple areas through integration with edge computing and cloud computing. However, devices at the edge of the network generate large quantities of multimodal data (e.g., user behaviour records, audio, and video), creating new challenges for data security and privacy, which has led to research and practical applications of privacy protection methods based on information hiding. In this article, we propose an information hiding method based on multidimensional feature fusion for privacy protection in 6G networks. This method is based on the strong attack resistance of carriers carrying private information; we study multidimensional feature fusion arbitration methods and construct an efficient and accurate feature-based information hiding technology. In this paper, we first perform private information preprocessing to encrypt private information and make it more secure. Then, we perform multidimensional feature extraction on the carrier and fuse these features to obtain the final feature region. Finally, the step of hiding or extracting private information is performed. A large number of experiments show that the performance of the proposed method is superior to those of existing methods.

A multidimensional interpretation of Marxist theory based on a decentralized Internet perspective

Abstract Constantly promoting theoretical innovation is the key to the perpetual vitality and vigor of Marxism. Marxist theory interpretation can provide new perspectives, new assertions, and new requirements for adhering to the basic principles of Marxism in line with the requirements of the times, national characteristics, and practical needs, and is the main basis for the formation, development, and renewal of the theoretical paradigm. Therefore, Spring+SpringMVC+Mybatis is used as the back-end development framework of the decentralized Internet to establish the decentralized Internet model used for interpreting Marxist theories. It is realized through the stages of theoretical semantic representation, multi-dimensional feature extraction, and classification. According to the multidimensional interpretation effect, the classification recall of the theoretical interpretation dimensions obtained after using the decentralized Internet model increases from 59.15%, 58.84%, 61.21%, 62.79% to 69.49%, 72.03%, 71.87%, 72.9%, and the average running speed of 9.21s decreases significantly to 3.84s. Portability, accessibility, interpretation completeness and contextual integration, depth of understanding indexes of ranking, accessibility, interpretive completeness, and contextual integration, depth of understanding, interpretive adequacy, and six-theory coverage reached 89.26%, 91.45%, 90.75%, 92.84%, 93.23%, 96.29%, and 99.12%. It shows that the decentralized Internet interpretation method of Marxist theory can grasp the scientific connotation and inner mechanism of theoretical development, trace the origin from ideas and perspectives related to the concept and summarize and interpret the background, reality, gist, content structure, and its contemporary significance under the new era discourse, so as to better implement and practice Marxist theory.

Research on education management system based on machine learning and multidimensional data modeling

Abstract With the rapid development of modern information technology, especially the continuous improvement of computer network technology, the application of education management system in teaching is becoming more and more extensive. Therefore, education management system and machine learning will become an important combination direction of education. First, design and implement a complete network education management system based on B/S architecture, and design from the overall system design, detailed design and database design. Among them, the computer language combined with the SQL Server database realizes the network teaching function and the education system management function. Then, PSO-SVM machine learning is adopted to make personalized learning course recommendation for students. Multi-dimensional data analysis and feature extraction. Finally, the PSO-SVM proposed in this paper is applied to the education management system for modeling training, and compared with other traditional machine learning personalized recommendation accuracy and likeness of learning course recommendation. The experimental results show that the PSO-SVM proposed in this paper is superior to other traditional machine learning models in terms of personalized learning course recommendation and favorability, with an accuracy rate of 94.7%.

A non-contact continuous blood pressure measurement method based on video stream

Hypertension is the primary disease that endangers human health. A convenient and accurate blood pressure measurement method can help to prevent the hypertension. This paper proposed a continuous blood pressure measurement method based on facial video signal. Firstly, color distortion filtering and independent component analysis were used to extract the video pulse wave of the region of interest in the facial video signal, and the multi-dimensional feature extraction of the pulse wave was preformed based on the time-frequency domain and physiological principles; Secondly, an integrated feature selection method was designed to extract the universal optimal feature subset; After that, we compared the single person blood pressure measurement models established by Elman neural network based on particle swarm optimization, support vector machine (SVM) and deep belief network; Finally, we used SVM algorithm to build a general blood pressure prediction model, which was compared and evaluated with the real blood pressure value. The experimental results showed that the blood pressure measurement results based on facial video were in good agreement with the standard blood pressure values. Comparing the estimated blood pressure from the video with standard blood pressure value, the mean absolute error (MAE) of systolic blood pressure was 4.9 mm Hg with a standard deviation (STD) of 5.9 mm Hg, and the MAE of diastolic blood pressure was 4.6 mm Hg with a STD of 5.0 mm Hg, which met the AAMI standards. The non-contact blood pressure measurement method based on video stream proposed in this paper can be used for blood pressure measurement.

Recognition of Riding Feeling From EEG Based on Neural Network

In order to identify the riding feeling in an autonomous vehicle through electroencephalogram (EEG), a recognition model based on multidimensional feature extraction and recurrent neural network (RNN) is proposed. After the effective training of the dataset, the system can realize the recognition of passengers’ riding feelings through real-time acquisition of passengers’ EEG signals and sending them into this recognition model. After preprocessing the collected raw EEG signals, we conducted an in- depth study of the preprocessed EEG data and proposed an algorithm to identify riding feeling from EEG signals. In order to improve the classification ability of RNN, a feature extraction method based on time segments is designed. Applying this method, multidimensional features with spatial, temporal, and frequency-domain features are obtained. The experimental results show that this feature extraction method can effectively suppress the overfitting of the RNN and improve the recognition ability of the network. Finally, the recognition of riding feeling is recognized through the RNN. Through the verification of the a dataset for emotion analysis using EEG, physiological and video signals (DEAP) dataset and the self-built dataset, the average recognition accuracy rate of 89.22% and 94.27% was obtained, respectively, which provides a feasible solution for the recognition of riding feeling based on physiological signals such as EEG.

Accurate multi-objective prediction of CO2 emission performance indexes and industrial structure optimization using multihead attention-based convolutional neural network

The establishment of specific targets for the global carbon peaking and neutrality raises urgent requirements for prediction of CO2 emission performance indexes (CEPIs) and industrial structure optimization. However, accurate multi-objective prediction of CEPIs is still a knotty problem. In the present study, multihead attention-based convolutional neural network (MHA–CNN) model was proposed for accurate prediction of 4 CEPIs and further provided the rational suggestions for further industrial structure optimization. The proposed MHA–CNN model introduces deep learning mechanism with efficient resolution strategies for training model overfitting, feature extraction, and self-supervised learning to acquire the adaptability for CEPIs. Multihead attention (MHA) mechanism plays important roles in influence weight interpretation of variables to facilitate the prediction performance of CNN on CEPIs. The MHA–CNN model presented its overwhelmingly superior performance to CNN model and long short-term memory (LSTM) model, two frequently-used models, in multi-objective prediction of CEPIs using 8 influence variables, which highlighted advantages of MHA module in multi-dimensional feature extraction. Additionally, contributions of influence variables to CEPIs based on MHA analyses presented relatively high consistency with the geographical distribution analyses, indicating the excellent capacity of the MHA module in variable weights identification and contribution dissection. Based on the more accurate prediction results by MHA–CNN than those by CNN and LSTM model, the increase in the tertiary industry and the decreases in the first and secondary industries are conducive to improvement of total-factor carbon emission efficiency and further enhancement of effective energy utilization in regions with inefficient carbon emissions. This study provides insights towards the critical roles of the proposed MHA–CNN model in accurate multi-objective prediction of CEPIs and further industrial structure optimization for improvement of total-factor carbon emission efficiency.

A Novel Classification Algorithm Based on Multidimensional F1 Fuzzy Transform and PCA Feature Extraction

The bi-dimensional F1-Transform was applied in image analysis to improve the performances of the F-transform method; however, due to its high computational complexity, the multidimensional F1-transform cannot be used in data analysis problems, especially in the presence of a large number of features. In this research, we proposed a new classification method based on the multidimensional F1-Transform in which the Principal Component Analysis technique is applied to reduce the dataset size. We test our method on various well-known classification datasets, showing that it improves the performances of the F-transform classification method and of other well-known classification algorithms; furthermore, the execution times of the F1-Transform classification method is similar to the ones obtained executing F-transform and other classification algorithms.

A Multi-Task-Based Deep Multi-Scale Information Fusion Method for Intelligent Diagnosis of Bearing Faults

The use of deep learning for fault diagnosis is already a common approach. However, integrating discriminative information of fault types and scales into deep learning models for rich multitask fault feature diagnosis still deserves attention. In this study, a deep multitask-based multiscale feature fusion network model (MEAT) is proposed to address the limitations and poor adaptability of traditional convolutional neural network models for complex jobs. The model performed multidimensional feature extraction through convolution at different scales to obtain different levels of fault information, used a hierarchical attention mechanism to weight the fusion of features to achieve an accuracy of 99.95% for the total task of fault six classification, and considered two subtasks in fault classification to discriminate fault size and fault type through multi-task mapping decomposition. Of these, the highest accuracy of fault size classification reached 100%. In addition, Precision, ReCall, and Sacore F1 all reached the index of 1, which achieved the accurate diagnosis of bearing faults.

Trends in EEG signal feature extraction applications.

This paper will focus on electroencephalogram (EEG) signal analysis with an emphasis on common feature extraction techniques mentioned in the research literature, as well as a variety of applications that this can be applied to. In this review, we cover single and multi-dimensional EEG signal processing and feature extraction techniques in the time domain, frequency domain, decomposition domain, time-frequency domain, and spatial domain. We also provide pseudocode for the methods discussed so that they can be replicated by practitioners and researchers in their specific areas of biomedical work. Furthermore, we discuss artificial intelligence applications such as assistive technology, neurological disease classification, brain-computer interface systems, as well as their machine learning integration counterparts, to complete the overall pipeline design for EEG signal analysis. Finally, we discuss future work that can be innovated in the feature extraction domain for EEG signal analysis.

Identification of Malicious Encrypted Traffic Through Feature Fusion

The popularity of encrypted communication has grown due to increased security awareness and rapid internet development. End-to-end encryption can prevent data attacks but also poses new cybersecurity threats. Thus, identifying malicious encrypted traffic is a focus of research in network behavior analysis and anomaly detection. Recently, deep learning has brought new directions for the development of traffic classification and anomaly detection. Based on deep learning technology, this paper starts from the two directions of data preprocessing and model selection, studies and analyzes multi-dimensional traffic characteristics and multi-granularity carrier characteristics, and proposes corresponding solutions, and finally designs and proposes a malware-oriented Identification scheme for encrypted traffic. This paper first proposes a malicious encrypted traffic identification scheme MET-FMF based on fine-grained multi-feature fusion. Two sets of comparative experiments were designed to compare the multi-dimensional traffic features and the multi-branch network model on the recognition results. The results show that the combination of three-dimensional traffic characteristics and three-branch network model has the best results, with an average accuracy rate of 95.08%.Finally, compared with other schemes, it is found that this scheme has multi-dimensional traffic feature extraction, multi-granularity carrier feature Features such as early session detection and end-to-end transferable learning.

Driver distraction detection based on lightweight networks and tiny object detection.

Real-time and efficient driver distraction detection is of great importance for road traffic safety and assisted driving. The design of a real-time lightweight model is crucial for in-vehicle edge devices that have limited computational resources. However, most existing approaches focus on lighter and more efficient architectures, ignoring the cost of losing tiny target detection performance that comes with lightweighting. In this paper, we present MTNet, a lightweight detector for driver distraction detection scenarios. MTNet consists of a multidimensional adaptive feature extraction block, a lightweight feature fusion block and utilizes the IoU-NWD weighted loss function, all while considering the accuracy gain of tiny target detection. In the feature extraction component, a lightweight backbone network is employed in conjunction with four attention mechanisms strategically integrated across the kernel space. This approach enhances the performance limits of the lightweight network. The lightweight feature fusion module is designed to reduce computational complexity and memory access. The interaction of channel information is improved through the use of lightweight arithmetic techniques. Additionally, CFSM module and EPIEM module are employed to minimize redundant feature map computations and strike a better balance between model weights and accuracy. Finally, the IoU-NWD weighted loss function is formulated to enable more effective detection of tiny targets. We assess the performance of the proposed method on the LDDB benchmark. The experimental results demonstrate that our proposed method outperforms multiple advanced detection models.

An FPGA-implemented Method for Real-time Multi-dimensional Feature Extraction of Sequence Image Targets

An FPGA-implemented Method for Real-time Multi-dimensional Feature Extraction of Sequence Image Targets