Multi-dimensional Feature Extraction Research Articles

SD-YOLOv8: An Accurate Seriola dumerili Detection Model Based on Improved YOLOv8.

Accurate identification of Seriola dumerili (SD) offers crucial technical support for aquaculture practices and behavioral research of this species. However, the task of discerning S. dumerili from complex underwater settings, fluctuating light conditions, and schools of fish presents a challenge. This paper proposes an intelligent recognition model based on the YOLOv8 network called SD-YOLOv8. By adding a small object detection layer and head, our model has a positive impact on the recognition capabilities for both close and distant instances of S. dumerili, significantly improving them. We construct a convenient S. dumerili dataset and introduce the deformable convolution network v2 (DCNv2) to enhance the information extraction process. Additionally, we employ the bottleneck attention module (BAM) and redesign the spatial pyramid pooling fusion (SPPF) for multidimensional feature extraction and fusion. The Inner-MPDIoU bounding box regression function adjusts the scale factor and evaluates geometric ratios to improve box positioning accuracy. The experimental results show that our SD-YOLOv8 model achieves higher accuracy and average precision, increasing from 89.2% to 93.2% and from 92.2% to 95.7%, respectively. Overall, our model enhances detection accuracy, providing a reliable foundation for the accurate detection of fishes.

GS-DeepLabV3+: A mountain tea disease segmentation network based on improved shuffle attention and gated multidimensional feature extraction

The prevention and control of Camellia Oleifera diseases can produce significantly comprehensive economic benefits. And precisely identifying the types of diseases on oil tea leaves can enhance the effectiveness of pest and disease control. Currently, the most effective deep learning methods for segmentation are suffering from the challenges such as indistinct disease spots on the actual oil tea leaves that are difficult to differentiate from the background, the high similarities in characteristics between different diseases, and the small target area of disease regions that are easily ignored. In this paper, GS-DeepLabV3+ network is proposed, which is an improvement upon DeepLabV3+ and aims to effectively enhance disease identification and segmentation rates. Initially, a gated pyramid feature fusion structure is proposed, utilizing a special module to merge features of different dimensions to enhance differentiation of similar features. Secondly, an improved grouped attention fusion mechanism is introduced, which allocates channel and spatial weights to different feature groups, enhancing the extraction of detailed features. Lastly, we substituted the backbone network of DeepLabV3+ with the more lightweight MobileNetV2, which significantly reduces the number of parameters while more stably extracting multidimensional features. In comparison with the existing segmentation networks on a self-created oil tea leaf disease data set, GS-DeepLabV3+ achieved a mIoU of 87.77% and an average pixel accuracy of 94.55%. Compared to the base DeepLabV3+ network, there was a 4.14% improvement in mIoU, a 3.58% increase in mPA, and a 1.4% rise in precision. The improved attention mechanism contributed to a 1.98% increase in mIoU, and the gated multidimensional fusion mechanism resulted in a 1.03% improvement. These enhancements can provide technical references for crop protection and pest disease segmentation.

Multidimensional Feature Extraction Based Minutely Solar Irradiance Forecasting Method Using All-Sky Images

Multidimensional Feature Extraction Based Minutely Solar Irradiance Forecasting Method Using All-Sky Images

Crash severity analysis: A data-enhanced double layer stacking model using semantic understanding

The crash severity analysis is of significant importance in traffic crash prevention and emergency resource allocation. A range of innovations offers potential traffic crash severity prediction models to improve road safety. However, the semantic information inherent in traffic crash data, which is crucial in enabling a deeper understanding of its underlying factors and impacts, has yet to be fully utilized. Moreover, traffic crash data are commonly characterized by a small sample size, which leads to sample imbalance problem resulting in prediction performance decline. To tackle these problems, we propose a semantic understanding-based data-enhanced double-layer stacking model, named EnLKtreeGBDT, for crash severity prediction. Specifically, to fully leverage the inherent semantic information within traffic crash data and analyze the factors influencing crashes, we design a semantic enhancement module for multi-dimensional feature extraction. This module aims to enhance the understanding of crash semantics and improve prediction accuracy. Then we introduce a data enhancement module that utilizes data denoising and migration techniques to address the challenge of data imbalance, reducing the prediction model's dependence on large sample crash data. Furthermore, we construct a two-layer stacking model that combines multiple linear and nonlinear classifiers. This model is designed to augment the capability of learning linear and nonlinear mixed relationships, thereby improving the accuracy of predicting the severity of crashes on complex urban roads. Experiments on historical datasets of UK road safety crashes validate the effectiveness of the proposed model, and superior performance of prediction precision is achieved compared with the state-of-the-arts. The ablation experiments on both semantic and data enhancement modules further confirm the indispensability of each module in the proposed model.

An epilepsy detection method based on multi-dimensional feature extraction and dual-branch hypergraph convolutional network.

Epilepsy is a disease caused by abnormal neural discharge, which severely harms the health of patients. Its pathogenesis is complex and variable with various forms of seizures, leading to significant differences in epilepsy manifestations among different patients. The changes of brain network are strongly correlated with related pathologies. Therefore, it is crucial to effectively and deeply explore the intrinsic features of epilepsy signals to reveal the rules of epilepsy occurrence and achieve accurate detection. Existing methods have faced the following issues: 1) single approach for feature extraction, resulting in insufficient classification information due to the lack of rich dimensions in captured features; 2) inability to deeply analyze the essential commonality of epilepsy signal after feature extraction, making the model susceptible to data distribution and noise interference. Thus, we proposed a high-precision and robust model for epileptic seizure detection, which, for the first time, applies hypergraph convolution to the field of epilepsy detection. Through a hypergraph network structure constructed based on relationships between channels in electroencephalogram (EEG) signals, the model explores higher-order characteristics of epilepsy EEG data. Specifically, we use the Conv-LSTM module and Power spectral density (PSD), a two-branch parallel method, to extract channel features from space-time and frequency domains to solve the problem of insufficient feature extraction, and can adequately describe the data structure and distribution from multiple perspectives through double-branch parallel feature extraction. In addition, we construct a hypergraph on the captured features to explore the intrinsic features in the high-dimensional space in an attempt to reveal the essential commonality of epileptic signal feature extraction. Finally, using the ensemble learning concept, we accomplished epilepsy detection on the dual-branch hypergraph convolution. The model underwent leave-one-out cross-validation on the TUH dataset, achieving an average accuracy of 96.9%, F1 score of 97.3%, Pre of 98.2% and Re of 96.7%. In addition, the model was generalized performance tested on CHB-MIT scalp EEG dataset with leave-one-out cross-validation, and the average ACC, F1 score, Pre and Re were 94.4%, 95.1%, 95.8%, and 93.9% respectively. Experimental results indicate that the model outperforms related literature, providing valuable reference for the clinical application of epilepsy detection.

Z2F: Heterogeneous graph-based Android malware detection.

Android malware is becoming more common, and its invasion of smart devices has brought immeasurable losses to people's lives. Most existing Android malware detection methods extract Android features from the original application files without considering the high-order hidden information behind them, but these hidden information can reflect malicious behaviors. To solve this problem, this paper proposes Z2F, a detection framework based on multidimensional Android feature extraction and graph neural networks for Android applications. Z2F first extracts seven types of Android features from the original Android application and then embeds them into a heterogeneous graph. On this basis, we design 12 kinds of meta-structures to analyze different semantic spaces of heterogeneous graphs, mine high-order hidden semantic information, and adopt a multi-layer graph attention mechanism to iteratively embed and update information. In this paper, a total of 14429 Android applications were detected and 1039726 Android features were extracted, with a detection accuracy of 99.7%.

Long-term series wetland classification of Guangdong-Hong Kong-Macao Greater Bay Area based on APSMnet

Wetlands play a crucial role in achieving carbon peak and carbon neutrality goals. Exploring spatiotemporal distribution is one of the fundamental task in wetland research. However, existing large-scale and long-term series wetland mapping methods have challenges related to classification accuracy and obtaining inter-annual wetland samples. Therefore, a rapid sample collection and precise classification method are needed to support wetland resource assessment, conservation, and ecological restoration. In this paper, we propose a novel deep learning method suitable for large-scale and long-term series wetland classification. First, we acquire and preprocess the long-term series remote sensing data on the Google Earth Engine (GEE) platform. Second, the maximum wetland extent is extracted using decision trees and the Otsu algorithm (OTSU). Third, the attention and pyramid structure-based multidimensional feature extraction network (APSMnet) and the inter-annual sample migration algorithm (ISM) are proposed for realizing inter-annual wetland classification and wetland change analysis. Experiments conducted on Landsat 7 data of the Guangdong-Hong Kong-Macao Greater Bay Area (GBA) from 2000 to 2022 demonstrate that the overall accuracy (OA), average accuracy (AA), and kappa coefficient (Kappa) achieved by the proposed wetland classification method are 0.9664, 0.9396, and 0.9570, respectively. Long-term series trend analysis reveals that mangrove/swamp areas experience fluctuations influenced by urbanization and ecological policies, ultimately undergoing restoration and becoming stable. The codes and datasets are made available publicly at https://github.com/louanjun/APSMnet.

Optical fiber vibration signal recognition based on an efficient multidimensional feature extraction network.

In the field of optical fiber vibration signal recognition, one-dimensional signals have few features. People often used the shallow layer of a one-dimensional convolutional neural network (1D-CNN), which results in fewer features being learned by the network, leading to a poor recognition rate. There are also many complex algorithms and data processing methods, which make the whole signal recognition process more complicated. Therefore, an optical vibration signal recognition method based on an efficient multidimensional feature extraction network was proposed. Based on ResNet-50, efficient channel attention (ECA) was used to improve image features extraction ability, and a long short-term memory (LSTM) network was used to enhance the extraction of temporal features. Three different vibration signals were collected using a phase-sensitive optical time-domain reflectometry (Φ-OTDR) optical fiber sensing system. Vibration signals were converted into 128×128 grayscale images, which have more effective vibration information. The experimental results show that the three types of signals can be recognized and classified effectively by the network, and the average recognition rate is 98.67%.

Multi-Feature Decision Fusion Network for Heart Sound Abnormality Detection and Classification.

The heart sound reflects the movement status of the cardiovascular system and contains the early pathological information of cardiovascular diseases. Automatic heart sound diagnosis plays an essential role in the early detection of cardiovascular diseases. In this study, we aim to develop a novel end-to-end heart sound abnormality detection and classification method, which can be adapted to different heart sound diagnosis tasks. Specifically, we developed a Multi-feature Decision Fusion Network (MDFNet) composed of a Multi-dimensional Feature Extraction (MFE) module and a Multi-dimensional Decision Fusion (MDF) module. The MFE module extracted spatial features, multi-level temporal features and spatial-temporal fusion features to learn heart sound characteristics from multiple perspectives. Through deep supervision and decision fusion, the MDF module made the multi-dimensional features extracted by the MFE module more discriminative, and fused the decision results of multi-dimensional features to integrate complementary information. Furthermore, attention modules were embedded in the MDFNet to emphasize the fundamental heart sounds containing effective feature information. Finally, we proposed an efficient data augmentation method to circumvent the diagnosis performance degradation caused by the lack of cardiac cycle segmentation in other end-to-end methods. The developed method achieved an overall accuracy of 94.44% and a F1-score of 86.90% on the binary classification task and a F1-score of 99.30% on the five-classification task. Our method outperformed other state-of-the-art methods and had good clinical application prospects.

Multi-Identity Recognition of Darknet Vendors Based on Metric Learning

Dark web vendor identification can be seen as an authorship aliasing problem, aiming to determine whether different accounts on different markets belong to the same real-world vendor, in order to locate cybercriminals involved in dark web market transactions. Existing open-source datasets for dark web marketplaces are outdated and cannot simulate real-world situations, while data labeling methods are difficult and suffer from issues such as inaccurate labeling and limited cross-market research. The problem of identifying vendors’ multiple identities on the dark web involves a large number of categories and a limited number of samples, making it difficult to use traditional multiclass classification models. To address these issues, this paper proposes a metric learning-based method for dark web vendor identification, collecting product data from 21 currently active English dark web marketplaces and using a multi-dimensional feature extraction method based on product titles, descriptions, and images. Using pseudo-labeling technology combined with manual labeling improves data labeling accuracy compared to previous labeling methods. The proposed method uses a Siamese neural network with metric learning to learn the similarity between vendors and achieve the recognition of vendors’ multiple identities. This method achieved better performance with an average F1-score of 0.889 and an accuracy rate of 97.535% on the constructed dataset. The contributions of this paper lie in the proposed method for collecting and labeling data for dark web marketplaces and overcoming the limitations of traditional multiclass classifiers to achieve effective recognition of vendors’ multiple identities.

Retracted: Attention Layer-Based Multidimensional Feature Extraction for Diagnosis of Lung Cancer.

[This retracts the article DOI: 10.1155/2022/3947434.].

Research on multi-dimensional micro-motion feature extraction of moving targets

The micro-Doppler effect is a physical phenomenon generated by the micro-motion of objects and their components, which have a significant influence on improving radar detection and resolution capability and also enhancing the radar imaging and target recognition performance. The extraction of micro-Doppler frequency, as a commonly used time-frequency analysis tool, is of great significance in extracting and reconstructing the signal with micro-motion targets. The micro-motion characteristics for moving targets can be verified by using simulation through combining the theory of micro-Doppler effect with the frequency domain model of electromagnetic waves. The simulation research on the micro-motion characteristics of a three-dimensional target is conducted by using the finite element method. The influences of environmental conditions such as relative humidity, visibility, and the presence or absence of turbulence on echo intensity and time-frequency relationship are investigated theoretically. The simulation results indicate that parameters such as relative humidity and visibility, which affect the atmospheric attenuation coefficient, can reduce echo intensity and the period of time-frequency curve. By triggering off beam drift in the transmission path, turbulence can lead to “frequency shift deformation” of the time-frequency curve, degrading the extraction of target motion attitude. A motion attitude classification method is proposed in order to study the micro-Doppler effect better. According to whether the frequency shift changes with time, the motion attitude can be divided into frequency shift time-invariant motion and time-variant motion. Frequency shift time-variant motion includes translation, rolling and vibration. Vibration and rolling are motions that periodically change with time, requiring the comparison of instantaneous frequency shifts at any three times within a cycle. Translation is a time-variant motion with irregular frequency shifts over time, which involves studying instantaneous frequency shifts at any three times. Transient frequency shifts should be analyzed and compared at different times for these motions. The frequency shift time-invariant motion is mainly rotation obtained experimental results indicate that the amplitude, plus-minus, and spectral width of frequency shift at different positions are aimed at inverting the target shape, attitude, direction and velocity. Demodulating one-dimensional data obtained from the FFTshift function can obtain the time-frequency-intensity relationship. This multi-parameter analysis method is a multi-dimensional processing method widely used in the fields of radar, sonar, and communication. The above research is conductive to the measurement of target macroscopic shape properties and the extraction of microscopic motion information, which lays the foundation for radar detection and recognition.

A Multitask Integrated Deep-Learning Probabilistic Prediction for Load Forecasting

Spinning reserve without accurate load forecasting can lead to automatic disconnection of critical loads by under-frequency load shedding devices. Such a predicament poses a grave threat to the economic and social welfare of the affected region, and in extreme scenarios, can result in a debilitating grid collapse. However, existing models lack the deep feature extraction capability and cannot accurately predict the uncertainty of electricity demand. Thus, a multitask integrated deep-learning probabilistic prediction with multidimensional feature extraction based on granularity information and quantile regression is explored in this study to solve the insufficient feature extraction problem in probabilistic prediction. In the proposed scheme, we designed a multi-layer feature extraction framework, which information granularity based on fuzzy rough sets to extract time-domain features, multilayer Laplace operators to extract features globally, and quantile regression recurrent neural network variants to extract time context information. In addition, the Pareto integration method is extended to capture better individuals. The experimental results demonstrate that the proposed system can effectively improve deterministic forecasting and uncertainty analysis of electricity demand and manage daily fluctuations.

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.