Extract Multi-dimensional Features Research Articles

Damage identification based on the inner product matrix and parallel convolution neural network for frame structure

Structural health monitoring based on vibration signal analysis has been extensively employed for damage identification. Mainstream machine learning techniques, such as convolutional neural networks (CNN), often rely on single-domain inputs, which may provide limited information for accurate damage identification. To overcome this limitation, this study proposes a novel approach that combines an inner product matrix (IPM) with a parallel CNN (IPM-PCNN) to extract multidimensional features for detecting structural damage in a steel frame structure. The proposed IPM-PCNN framework consists of a one-dimensional (1D) CNN branch for processing time series data, a two-dimensional (2D) CNN branch for handling structural modal data, and several fully connected layers. This unique combination leverages the strengths of both 1D and 2D CNNs to capture temporal and modal features of the signal effectively. To validate the effectiveness and superiority of the proposed method, a five-story steel frame model is used as the research object, and five comparative methods are evaluated under the same experimental conditions. The results demonstrate that the IPM-PCNN model can automatically extract relevant features from the signals to accurately identify structural damage, achieving an accuracy of 96.60% on the test set, outperforming machine learning methods in performance. Furthermore, the internal inference processes of these methods are explored and visualized to provide insights into their decision-making mechanisms.

Prediction of protein interactions between pine and pine wood nematode using deep learning and multi-dimensional feature fusion.

Pine Wilt Disease (PWD) is a devastating forest disease that has a serious impact on ecological balance ecological. Since the identification of plant-pathogen protein interactions (PPIs) is a critical step in understanding the pathogenic system of the pine wilt disease, this study proposes a Multi-feature Fusion Graph Attention Convolution (MFGAC-PPI) for predicting plant-pathogen PPIs based on deep learning. Compared with methods based on single-feature information, MFGAC-PPI obtains more 3D characterization information by utilizing AlphaFold and combining protein sequence features to extract multi-dimensional features via Transform with improved GCN. The performance of MFGAC-PPI was compared with the current representative methods of sequence-based, structure-based and hybrid characterization, demonstrating its superiority across all metrics. The experiments showed that learning multi-dimensional feature information effectively improved the ability of MFGAC-PPI in plant and pathogen PPI prediction tasks. Meanwhile, a pine wilt disease PPI network consisting of 2,688 interacting protein pairs was constructed based on MFGAC-PPI, which made it possible to systematically discover new disease resistance genes in pine trees and promoted the understanding of plant-pathogen interactions.

Species-specific model based on sequence and structural information for ubiquitination sites prediction

Ubiquitination is a common post-translational modification of proteins in eukaryotic cells, and it is also a significant method of regulating protein biological function. Computational methods for predicting ubiquitination sites can serve as a cost-effective and time-saving alternative to experimental methods. Existing computational methods often build classifiers based on protein sequence information, physical and chemical properties of amino acids, evolutionary information, and structural parameters. However, structural information about most proteins cannot be found in existing databases directly. The features of proteins differ among species, and some species have small amounts of ubiquitinated proteins. Therefore, it is necessary to develop species-specific models that can be applied to datasets with small sample sizes. To solve these problems, we propose a species-specific model (SSUbi) based on a capsule network, which integrates proteins’ sequence and structural information. In this model, the feature extraction module is composed of two sub-modules that extract multi-dimensional features from sequence and structural information respectively. In the submodule, the convolution operation is used to extract encoding dimension features, and the channel attention mechanism is used to extract feature map dimension features. After integrating the multi-dimensional features from both types of information, the species-specific capsule network further converts the features into capsule vectors and classifies species-specific ubiquitination sites. The experimental results show that SSUbi can effectively improve the prediction performance of species with small sample sizes and outperform other models.

Censorship data-driven DNS resolution anomaly detection: An ensemble algorithm model with multivariate feature fusion

The Domain Name System (DNS), as a critical component of Internet infrastructure, is crucial for maintaining network stability and security. However, vulnerabilities in the DNS resolution process make it susceptible to various network attacks. Current DNS resolution anomaly detection methods are challenged by the scarcity of diverse anomalous sample data and the difficulty in accurately capturing such anomalies. To address those challenges, we firstly introduce a proactive anomaly detection method based on bidirectional national censorship behavior, abbreviated as CB-BiDAM. This method can collect diverse anomalous resolution data from multiple network spaces, covering common types of resolution anomalies and effectively solving the problem of sample scarcity. Further, we extract multidimensional features from four key aspects: response content, DNS attributes, resolution paths, and timing, to gain a deeper understanding of the relationship between multifaceted information in the DNS resolution process and anomalous events. Finally, based on these multidimensional features, we construct a DNS resolution anomaly detection model named DRADC, using a stacked ensemble approach. Through a series of comparative experiments, the DRADC model significantly outperforms existing machine learning algorithms in key metrics such as accuracy (97.48%), recall (96.87%), and F1 score (97.09%). Feature ablation experiments further demonstrates that incorporating multidimensional features significantly improves model performance, with a 3% increase in accuracy and a 3.5% increase in precision compared to models relying solely on response content features. By providing an accurate detection model for DNS resolution anomalies, this study aids network administrators in more effectively identifying and countering network attacks. Additionally, our research also contributes to the detection and response to domain censorship mechanisms, which is crucial for maintaining the openness and free flow of the Internet.

PMF-CNN: parallel multi-band fusion convolutional neural network for SSVEP-EEG decoding

Steady-state visual evoked potential (SSVEP) is a key technique of electroencephalography (EEG)-based brain-computer interfaces (BCI), which has been widely applied to neurological function assessment and postoperative rehabilitation. However, accurate decoding of the user’s intended based on the SSVEP-EEG signals is challenging due to the low signal-to-noise ratio and large individual variability of the signals. To address these issues, we proposed a parallel multi-band fusion convolutional neural network (PMF-CNN). Multi frequency band signals were served as the input of PMF-CNN to fully utilize the time-frequency information of EEG. Three parallel modules, spatial self-attention (SAM), temporal self-attention (TAM), and squeeze-excitation (SEM), were proposed to automatically extract multi-dimensional features from spatial, temporal, and frequency domains, respectively. A novel spatial-temporal-frequency representation were designed to capture the correlation of electrode channels, time intervals, and different sub-harmonics by using SAM, TAM, and SEM, respectively. The three parallel modules operate independently and simultaneously. A four layers CNN classification module was designed to fuse parallel multi-dimensional features and achieve the accurate classification of SSVEP-EEG signals. The PMF-CNN was further interpreted by using brain functional connectivity analysis. The proposed method was validated using two large publicly available datasets. After trained using our proposed dual-stage training pattern, the classification accuracies were 99.37% and 93.96%, respectively, which are superior to the current state-of-the-art SSVEP-EEG classification algorithms. The algorithm exhibits high classification accuracy and good robustness, which has the potential to be applied to postoperative rehabilitation.

Prediction of SOC for lead-acid battery based on LSTM-Attention and LightGBM

Abstract Accurately estimating the SOC of batteries is crucial for the objective of extending battery life and enhancing power supply reliability. Currently, machine learning methods are commonly used to predict the SOC of batteries, however, their accuracy in capturing the sequential nature of battery charging and discharging is insufficient. To address the problem of SOC prediction, a deep learning model that employs Long Short-Term Memory (LSTM) with Attention mechanism is proposed. The LSTM model is designed to connect the current SOC with historical time data and to extract multi-dimensional features from groups of batteries. Additionally, introducing the Attention mechanism allows for the model to prioritize key information while disregarding insignificant data. This work utilizes two different approaches to the multi-cell case and the single-cell case for several reasons. Considering that the failure of a single cell can affect the entire group of batteries, SOC prediction models for individual batteries need not take a long training time. Thus, the LightGBM model is developed to predict the SOC of a single battery whose training speed surpasses that of the deep learning model and has superior prediction accuracy and greater speed when employed with small-scale data, error within 3%. Conversely, the LSTM-Attention model yields higher prediction accuracy when processing large-scale datasets, error within 5%.Two models are proposed: one for predicting the SOC of groups of batteries and another for a single battery.

Towards automatically identifying the co‐change of production and test code

AbstractIn software evolution, keeping the test code co‐change with the production code is important, because the outdated test code may not work and is ineffective in revealing faults in the production code. However, due to the tight development time, the production and test code may not be co‐changed immediately by developers. For example, we analysed the top 1003 popular Java projects on GitHub and found that nearly 9.3% of cases (i.e., 464,417) did not update their production and test code at the same time, that is, the production code is updated first, and then the test code is updated at intervals. The result indicates that much test code will not be updated in time. In this paper, we propose a novel approach, Jtup, to remind developers to co‐change the production code and test code in time. Specifically, we first define the co‐changed production and test code as a positive instance, while unchanged test code (i.e., production code changed and test code unchanged) as a negative instance. Then, we extract multidimensional features from the production code to characterize the possibility of their co‐change, including code change features, code complexity features, and code semantic features. Finally, several machine learning‐based methods are employed to identify the co‐changed production and test code. We conduct comprehensive experiments on 20 datasets, and the results show that the Accuracy, Precision, and Recall achieved by Jtup are 76.7%, 78.1%, and 77.4%, which outperforms the state‐of‐the‐art method.

A novel mechanical fault diagnosis for high-voltage circuit breakers with zero-shot learning

In recent years, data-driven methods have been widely used in the field of high-voltage circuit breakers (HVCBs) fault diagnosis. However, due to the complex mechanical structure of HVCBs and the special operating environment, it is difficult to obtain a large amount of fault samples and exhaust all fault types. The lack of fault samples and fault types typically results in significant degradation of diagnostic performance. To address this problem, we design a novel method named R-MLL for zero-shot HVCB fault diagnosis. R-MLL tries to identify unseen fault types only by training seen fault types. First, to focus on all the details of the HVCB mechanical vibration signal, the wavelet transform is used to multi-scale refine the fault data. Second, a new network (RDSCNN) is designed to extract multidimensional features based on convolutional neural network incorporating residual block and depthwise separable convolution. Third, a multi-label attribute learning network is designed, enabling the fusion of fault features and attributes and allowing attribute labels to assist fault diagnosis tasks. Extensive experiments show that R-MLL gets average accuracy of 86.2% for compound fault diagnosis without the need of using target fault samples for building the diagnostic model. Comparisons with a number of state-of-the-art techniques show the superiority of the proposed method for zero-shot HVCB diagnosis.

Abnormal traffic detection system in SDN based on deep learning hybrid models

Software defined network (SDN) provides technical support for network construction of smart cities. However, the openness of SDN is also prone to more network attacks. Traditional abnormal traffic detection algorithms are complex and time-consuming, so it is difficult to find abnormalities in the network in time and unable to satisfy the requirements of abnormal traffic detection in the SDN environment. Therefore, we propose an abnormal traffic detection system based on deep learning hybrid model. The system adopts a hierarchical detection method. Firstly, it completes the rough detection of abnormal traffic in the network according to the statistical information of switch ports and then uses wavelet transform and deep learning technology to extract multi-dimensional features of all traffic data flowing through suspicious switches, so as to realize the fine detection of abnormal traffic from the surface. The experimental results show that the proposed detection method based on port information can quickly locate the source of abnormal traffic. Compared with the traditional abnormal traffic detection method in SDN, the fine detection method based on multi-dimensional features improves the accuracy by 1.7 %, the recall rate by 1.6 %, and the false positive rate by 91.3 %.

A Deep Anomaly Detection With Same Probability Distribution and Its Application in Rolling Bearing

Abstract An innovative deep-learning-based model, namely, deep anomaly detection with the same probability distribution (DADSPD) is proposed to improve the accuracy of anomaly detection (AD) of rolling bearings driven only by normal data. First, the main framework of feature extraction based on a residual network was established, and a three-layer encoder structure was used to extract multidimensional features. Second, a new loss function based on the same probability distribution is designed, and the function of its probability distribution is to complete the training of the model by calculating the similarity between the outputs. Subsequently, the vibration data were preprocessed using wavelet and envelope analysis, and the processed data are converted into two-dimensional image signals and used as the input of the DADSPD. Finally, the model is verified on three sets of run-to-failure experimental datasets of rolling bearing. The results demonstrate that the proposed DADSPD model reaches more than 99%, which indicates that the DADSPD model has a high fault early warning and AD capability.

A Malicious Mining Code Detection Method Based on Multi-Features Fusion

With the continuous increase in the economic value of new digital currencies represented by Bitcoin, more and more cybercriminals use malicious code to occupy victims system resources and network resources for mining without the victims permission, thereby obtaining cryptocurrency. This type of malicious code named malicious mining code has brought considerable influence and harm to society, enterprises and users. The mining code always conceals the fact that it consumes computer resources in a way that is difficult for ordinary people to discover. This paper proposes a malicious mining code detection method based on feature fusion and machine learning. First, we analyze from static analysis methods and statistical analysis methods to extract multi-dimensional features. Then for multi-dimensional text features, feature vectors are extracted through the n-gram model and TF-IDF, and best feature vectors are selected through the classifier and we fuse these best feature vectors with other statistic features to train our detection model. Finally, automatic detection is performed based on the machine learning framework. The experimental results show that the recognition accuracy of our method can reach 98.0%, its f1 score reach 0.969, and the ROCs AUC reach 0.973.

MHL-Net: A Multistage Hierarchical Learning Network for Head and Neck Multiorgan Segmentation.

Accurate segmentation of head and neck organs at risk is crucial in radiotherapy. However, the existing methods suffer from incomplete feature mining, insufficient information utilization, and difficulty in simultaneously improving the performance of small and large organ segmentation. In this paper, a multistage hierarchical learning network is designed to fully extract multidimensional features, combined with anatomical prior information and imaging features, using multistage subnetworks to improve the segmentation performance. First, multilevel subnetworks are constructed for primary segmentation, localization, and fine segmentation by dividing organs into two levels-large and small. Different networks both have their own learning focuses and feature reuse and information sharing among each other, which comprehensively improved the segmentation performance of all organs. Second, an anatomical prior probability map and a boundary contour attention mechanism are developed to address the problem of complex anatomical shapes. Prior information and boundary contour features effectively assist in detecting and segmenting special shapes. Finally, a multidimensional combination attention mechanism is proposed to analyze axial, coronal, and sagittal information, capture spatial and channel features, and maximize the use of structural information and semantic features of 3D medical images. Experimental results on several datasets showed that our method was competitive with state-of-the-art methods and improved the segmentation results for multiscale organs.

FCDM: An Improved Forest Fire Classification and Detection Model Based on YOLOv5

Intense, large-scale forest fires are damaging and very challenging to control. Locations, where various types of fire behavior occur, vary depending on environmental factors. According to the burning site of forest fires and the degree of damage, this paper considers the classification and identification of surface fires and canopy fires. Deep learning-based forest fire detection uses convolutional neural networks to automatically extract multidimensional features of forest fire images with high detection accuracy. To accurately identify different forest fire types in complex backgrounds, an improved forest fire classification and detection model (FCDM) based on YOLOv5 is presented in this paper, which uses image-based data. By changing the YOLOv5 bounding box loss function to SIoU Loss and introducing directionality in the cost of the loss function to achieve faster convergence, the training and inference of the detection algorithm are greatly improved. The Convolutional Block Attention Module (CBAM) is introduced in the network to fuse channel attention and spatial attention to improve the classification recognition accuracy. The Path Aggregation Network (PANet) layer in the YOLOv5 algorithm is improved into a weighted Bi-directional Feature Pyramid Network (BiFPN) to fuse and filter forest fire features of different dimensions to improve the detection of different types of forest fires. The experimental results show that this improved forest fire classification and identification model outperforms the YOLOv5 algorithm in both detection performances. The mAP@0.5 of fire detection, surface fire detection, and canopy fire detection was improved by 3.9%, 4.0%, and 3.8%, respectively. Among them, the mAP@0.5 of surface fire reached 83.1%, and the canopy fire detection reached 90.6%. This indicates that the performance of our proposed improved model has been effectively improved and has some application prospects in forest fire classification and recognition.

Remaining Useful Life Prediction of Gear Pump Based on Deep Sparse Autoencoders and Multilayer Bidirectional Long–Short–Term Memory Network

Prediction of remaining useful life is crucial for mechanical equipment operation and maintenance. It ensures safe equipment operation, reduces maintenance costs and economic losses, and promotes development. Most of the remaining useful life prediction studies focus on bearings, gearboxes, and engines; however, research on hydraulic pumps remains limited. This study focuses on gear pumps that are commonly used in the hydraulic field and develops a practical method of predicting remaining useful life. The deep sparse autoencoder is used to extract multi–dimensional features. Subsequently, the feature vectors are inputted to the support vector data description to calculate the machine degradation degree at the corresponding time and obtain the health indicator curve of the machine’s life cycle. In building the health state degradation curve, data are processed in an unsupervised manner to avoid the influence of artificial feature selection on the test. The method is validated on the public bearing and self–collected gear pump datasets. The results are better than those of the comparative algorithms: (1) commonly used time–frequency characteristics with principal component analysis and (2) deep sparse autoencoder with self–organizing mapping. Next, the multilayer bidirectional long–short–term memory network is trained as a prediction model using the gear pump health indicator curves obtained previously and applied to the test data. Finally, the proposed method is compared with two others of the same type and the evaluation indexes are calculated based on the prediction results of the three algorithms. From the evaluation indexes, the mean absolute error of the proposed method is reduced by 2.53, and the normalized mean squared error is reduced by 0.36. This result indicates that the prediction results of the method for the remaining useful life of the gear pump are closer to the actual situation.

Deep learning of complex process data for fault classification based on sparse probabilistic dynamic network

BackgroundThe dynamic and nonlinear characteristics of process data have become the major issue in data-driven process monitoring. Traditional data-driven methods are often only able to extract a single feature in process data. Therefore, how to effectively extract multi-dimensional features has become the focus of current research. MethodsSparse probabilistic dynamic network (SPDN) is a deep learning model proposed in this paper for the purpose of fault classification. The method mainly takes the advantages of the sparse Gaussian-Bernoulli Restricted Boltzmann Machine (GRBM) and the recurrent neural network (RNN) with long-short term memory (LSTM) units. First, the sparse GRBM is used for nonlinear feature extraction in an unsupervised way. Then, LSTM is introduced to realize the modeling of sequence data which can effectively handle the dynamic feature of the data. FindingsIn the Tennessee-Eastman benchmark process, the classification accuracies of the proposed method are proved to be far superior to MLP, RNN and PDN. Meanwhile, in order to prove the influence of the data dynamics and the internal parameters of the structure on the fault classification results, two additional experiments were carried out.

The popularity of contradictory information about COVID-19 vaccine on social media in China

To eliminate the impact of contradictory information on vaccine hesitancy on social media, this research developed a framework to compare the popularity of information expressing contradictory attitudes towards COVID-19 vaccine or vaccination, mine the similarities and differences among contradictory information's characteristics, and determine which factors influenced the popularity mostly. We called Sina Weibo API to collect data. Firstly, to extract multi-dimensional features from original tweets and quantify their popularity, content analysis, sentiment computing and k-medoids clustering were used. Statistical analysis showed that anti-vaccine tweets were more popular than pro-vaccine tweets, but not significant. Then, by visualizing the features' centrality and clustering in information-feature networks, we found that there were differences in text characteristics, information display dimension, topic, sentiment, readability, posters' characteristics of the original tweets expressing different attitudes. Finally, we employed regression models and SHapley Additive exPlanations to explore and explain the relationship between tweets' popularity and content and contextual features. Suggestions for adjusting the organizational strategy of contradictory information to control its popularity from different dimensions, such as poster's influence, activity and identity, tweets' topic, sentiment, readability were proposed, to reduce vaccine hesitancy.

Wheat head counting in the wild by an augmented feature pyramid networks-based convolutional neural network

• Multi-scale and dense wheat heads in a wild environment were counted in this study. • Contrast adjustment and Gaussian blur were used to increase image features. • AugFPN and cascaded IoU threshold were used to extract multi-dimensional features. • These features could be used to detect wheat heads with a precision of 95.17%. • The error rate was 3.7% so it could provide reliable data for yield estimation. Wheat head counting plays an important role in crop yield estimation, which also meets great challenges of high density, scale variation, and illumination difference. In this paper, an improved wheat head counting network (WHCnet) was proposed to count wheat heads from the top view in the wild, with a novel object counting by detection pipeline. Firstly, data enhancement such as contrast adjustment and Gaussian blur were conducted to improve the generalization ability. Secondly, the Augmented Feature Pyramid Networks (AugFPN) was used to pool the original information adaptively, which made full use of the underlying information and solved the problem of poor detection of small wheat heads. Finally, cascaded Intersection over Union (IoU) threshold was used to make the IoU of the training model as close as possible to the input target, which could effectively remove negative samples in the complex background, reduce the noise bounding box and improve the target positioning accuracy of occluded wheat heads. Experiments on the test set image showed that the proposed method had an average error rate of 3.7% and an AP of 95.17%, which was significantly better than other state-of-the-art methods. Besides, the average counting time for a single wheat field image (3968 × 2976) obtained by an unmanned aerial vehicle was 87 ms, and the counting accuracy was 95.8%, which effectively verified the generalization ability of the model. These results indicate that the proposed method can meet the requirements of wheat head counting in the field environment and provide reliable reference data for wheat yield estimation.

User Recognition System Based on Spectrogram Image Conversion Using EMG Signals

Recently, user recognition methods to authenticate personal identity has attracted significant attention especially with increased availability of various internet of things (IoT) services through fifth-generation technology (5G) based mobile devices. The EMG signals generated inside the body with unique individual characteristics are being studied as a part of next-generation user recognition methods. However, there is a limitation when applying EMG signals to user recognition systems as the same operation needs to be repeated while maintaining a constant strength of muscle over time. Hence, it is necessary to conduct research on multidimensional feature transformation that includes changes in frequency features over time. In this paper, we propose a user recognition system that applies EMG signals to the short-time fourier transform (STFT), and converts the signals into EMG spectrogram images while adjusting the time-frequency resolution to extract multidimensional features. The proposed system is composed of a data pre-processing and normalization process, spectrogram image conversion process, and final classification process. The experimental results revealed that the proposed EMG spectrogram image-based user recognition system has a 95.4% accuracy performance, which is 13% higher than the EMG signal-based system. Such a user recognition accuracy improvement was achieved by using multidimensional features, in the time-frequency domain.

Machine learning-assisted high-content analysis of pluripotent stem cell-derived embryos in vitro

SummaryStem cell-based embryo models by cultured pluripotent and extra-embryonic lineage stem cells are novel platforms to model early postimplantation development. We showed that induced pluripotent stem cells (iPSCs) could form ITS (iPSCs and trophectoderm stem cells) and ITX (iPSCs, trophectoderm stem cells, and XEN cells) embryos, resembling the early gastrula embryo developed in vivo. To facilitate the efficient and unbiased analysis of the stem cell-based embryo model, we set up a machine learning workflow to extract multi-dimensional features and perform quantification of ITS embryos using 3D images collected from a high-content screening system. We found that different PSC lines differ in their ability to form embryo-like structures. Through high-content screening of small molecules and cytokines, we identified that BMP4 best promoted the morphogenesis of the ITS embryo. Our study established an innovative strategy to analyze stem cell-based embryo models and uncovered new roles of BMP4 in stem cell-based embryo models.

HybNet: a hybrid network structure for pain intensity estimation

Automatic pain intensity estimation has great potential in current rehabilitation medicine, and patients’ health status information can be obtained through the analysis of facial images. At present, deep convolutional neural networks (CNNs) have made great progress in many fields, including natural language processing, image classification and action recognition. Motivated by the current achievements, a novel end-to-end hybrid network is proposed to extract multidimensional features from image sequences, which is composed of 3D convolution, 2D convolution and 1D convolution. Specifically, the 3D convolutional neural network (3D CNN) is designed to capture the spatiotemporal features, and the 2D convolutional neural network (2D CNN) is designed to capture the spatial features, while the 1D convolutional neural network (1D CNN) is mainly used to capture the geometric information from facial landmarks. Finally, the features obtained by the three different networks are fused together for regression. The proposed HybNet is evaluated on UNBC-McMaster Shoulder Pain Expression Archive Database, and the experimental results show that it can effectively extract the discriminative high-level features and can achieve competitive performance with the state-of-the-art methods.