Feature Vector Research Articles

CAM: a novel aid system to analyse the coloration quality of thick blood smears using image processing and machine learning techniques.

Battling malaria's morbidity and mortality rates demands innovative methods related to malaria diagnosis. Thick blood smears (TBS) are the gold standard for diagnosing malaria, but their coloration quality is dependent on supplies and adherence to standard protocols. Machine learning has been proposed to automate diagnosis, but the impact of smear coloration on parasite detection has not yet been fully explored. To develop Coloration Analysis in Malaria (CAM), an image database containing 600 images was created. The database was randomly divided into training (70%), validation (15%), and test (15%) sets. Nineteen feature vectors were studied based on variances, correlation coefficients, and histograms (specific variables from histograms, full histograms, and principal components from the histograms). The Machine Learning Matlab Toolbox was used to select the best candidate feature vectors and machine learning classifiers. The candidate classifiers were then tuned for validation and tested to ultimately select the best one. This work introduces CAM, a machine learning system designed for automatic TBS image quality analysis. The results demonstrated that the cubic SVM classifier outperformed others in classifying coloration quality in TBS, achieving a true negative rate of 95% and a true positive rate of 97%. An image-based approach was developed to automatically evaluate the coloration quality of TBS. This finding highlights the potential of image-based analysis to assess TBS coloration quality. CAM is intended to function as a supportive tool for analyzing the coloration quality of thick blood smears.

An SCA-based classifier for motor imagery EEG classification

Efficient and accurate multi-class classification of electroencephalogram (EEG) signals poses a significant challenge in the development of motor imagery-based brain–computer interface (MI-BCI). Drawing inspiration from the sine cosine algorithm (SCA), a widely employed swarm intelligence algorithm for optimization problems, we proposed a novel population-based classification algorithm for EEG signals in this article. To fully leverage the characteristics contained in EEG signals, multi-scale sub-signals were constructed in terms of temporal windows and spectral bands simultaneously, and the common spatial pattern (CSP) features were extracted from each sub-signal. Subsequently, we integrated the multi-center optimal vectors mechanism into the classical SCA, resulting in the development of a multi-center SCA (MCSCA) classifier. During the classification stage, the label was assigned to the test trials by evaluating the Euclidean distance between their feature vectors and each optimal vector in MCSCA. Additionally, the weights of feature vectors were exploited to select the sub-signal of specific temporal windows and spectral bands for feature reduction, thereby declining computational effort and eliminating data redundancy. To validate the performance of the MCSCA classifier, we conducted four-class classification experiments using the BCI Competition IV dataset 2a, achieving an average classification accuracy of 71.89%. The experimental results show that the proposed algorithm offers a novel and effective approach for EEG classification.

Motif discovery in hospital ward vital signs observation networks

Vital signs observations are regular measurements used by healthcare staff to track a patient’s overall health status on hospital wards. We look at the potential in re-purposing aggregated and anonymised hospital data sources surrounding vital signs recording to provide new insights into how care is managed and delivered on wards. In this paper, we conduct a retrospective longitudinal observational study of 770,720 individual vital signs recordings across 20 hospital wards in South Wales (UK) and present a network modelling framework to explore and extract behavioural patterns via analysis of the resulting network structures at a global and local level. Self-loop edges, dyad, triad, and tetrad subgraphs were extracted and evaluated against a null model to determine individual statistical significance, and then combined into ward-level feature vectors to provide the means for determining notable behaviours across wards. Modelling data as a static network, by aggregating all vital sign observation data points, resulted in high uniformity but with the loss of important information which was better captured when modelling the static-temporal network, highlighting time’s crucial role as a network element. Wards mostly followed expected patterns, with chains or stand-alone supplementary observations by clinical staff. However, observation sequences that deviate from this are revealed in five identified motif subgraphs and 6 anti-motif subgraphs. External ward characteristics also showed minimal impact on the relative abundance of subgraphs, indicating a ‘superfamily’ phenomena that has been similarly seen in complex networks in other domains. Overall, the results show that network modelling effectively captured and exposed behaviours within vital signs observation data, and demonstrated uniformity across hospital wards in managing this practice.

Computer Modelling of Textures on Images with Human Skin Wound Areas

In this paper, we concentrate on the images of the wounds on the human skin and propose to consider each image as a set of smaller pieces – crops or patches containing different textures. We overview, develop and compare deep learning feature extraction methods to model image crops as 200-dimensional feature vectors using various artificial neural network architectures: convolutional autoencoders, variational convolutional autoencoders, and Siamese convolutional networks trained in the contrastive learning manner. Also, we develop a custom convolutional encoder and decoder, use them in the aforementioned architectures and compare them with the ResNet encoder and decoder alternatives. Finally, we train and evaluate k-nearest neighbors and Multi-Layer Perceptron classifiers on the features extracted with the model above options to discriminate skin, wound, and background image patches. Classification evaluation results on the features, extracted with the Siamese network, show the best test accuracy for all implementations without a significant shift between model versions (accuracy > 93%); variational autoencoders show random results for all options (accuracy around 33%), and convolutional autoencoders reached good results (accuracy > 77%) but with a noticeable difference between the custom and ResNet versions; the latter is better. Custom encoder and decoder implementations are faster and smaller than the ResNet alternatives but may be less stable on larger datasets, which still needs investigation. Possible applications of the feature vectors include an area of interest extraction during wound segmentation or classification and usage as patch embeddings while training vision transformer architectures.

A cardiac audio classification method based on image expression of multidimensional features.

Heart sound auscultation plays a crucial role in the early diagnosis of cardiovascular diseases. In recent years, great achievements have been made in the automatic classification of heart sounds, but most methods are based on segmentation features and traditional classifiers and do not fully exploit existing deep networks. This paper proposes a cardiac audio classification method based on image expression of multidimensional features (CACIEMDF). First, a 102-dimensional feature vector is designed by combining the characteristics of heart sound data in the time domain, frequency domain and statistical domain. Based on the feature vector, a two-dimensional feature projection space is constructed by PCA dimensionality reduction and the convex hull algorithm, and 102 pairs of coordinate representations of the feature vector in the two-dimensional space are calculated. Each one-dimensional component of the feature vector corresponds to a pair of 2D coordinate representations. Finally, the one-dimensional feature component value and its divergence into categories are used to fill the three channels of a color image, and a Gaussian model is used to dye the image to enrich its content. The color image is sent to a deep network such as ResNet50 for classification. In this paper, three public heart sound datasets are fused, and experiments are conducted using the above methods. The results show that for the two-classification/five-classification task of heart sounds, the method in this paper can achieve a classification accuracy of 95.68%/94.53% when combined with the current deep network.

Automated EEG-based language detection using directed quantum pattern technique

Electroencephalogram (EEG) signals contain complex useful information about brain activities. These EEG signals are noisy, highly varying and nonstationary in nature. Hence, extracting meaningful information from these signals is challenging. The existing machine learning systems struggle to capture the minute changes from the signals and yield high performance.This study introduces a novel quantum-inspired feature extraction technique called Directed Quantum Pattern (DQP), designed to address these challenges by using a lattice structure to capture directional binary features. These directions (paths) are computed using a maximum function providing a dynamic and adaptive feature representation.This paper presents a novel DQP-LangNet developed using DQP for automated classification of two- languages using EEG signals. We have proposed a hybrid approach, combining DQP, statistical features, and multi-level discrete wavelet transform (MDWT) to extract salient features similar to the deep learning approach. The EEG dataset consisting of 14 channels, produces 7 feature vectors per channel, yielding 98 feature vectors. Neighborhood component analysis and Chi-square (Chi2) feature selection approaches generated 196 feature vectors.In addition to the innovative feature extraction a new classification structure called “t” is proposed k-nearest neighbor (tkNN) and support vector machine (tSVM) classifiers are employed. Using the proposed tkNN and tSVM classifiers, 392 (=196×2) classifier-based outcomes are obtained. To further improve classification performance, we applied the iterative majority voting (IMV) technique to automatically select the best result.Our DQP-based model achieved a classification accuracy of 95.68 %using EEG language dataset with leave-one-subject-out (LOSO) cross-validation strategy. Also, an explainable feature engineering (XFE) structure of DQP-LangNet is employed to obtain channel-specific explainable results. Our proposed DQP-LangNet model can be employed for other applications in neuroscience.

Deep Learning with Crested Porcupine Optimizer for Detection and Classification of Paddy Leaf Diseases for Sustainable Agriculture

India has a vast number of inhabitants and the main food source distribution is from agriculture. Agricultural lands are being demolished generally owing to plant and crop illnesses. The detection of plant diseases by using image processing models can aid agriculturalists in defending the farming area from damaging or affecting it. Paddy is the main harvest worldwide. Early recognition of the paddy diseases at dissimilar phases of development is very vital in paddy production. However, the present manual technique in identifying and classifying paddy diseases needs a very educated farmer and is time-consuming. Deep learning (DL) is an effectual research area in the classification of agriculture patterns where it can efficiently solve the problems of diseases identification. Therefore, the articles focus on the design and expansion of Deep Learning based Crested Porcupine Optimizer for the Detection and Classification of Paddy Leaf Diseases (DLCPO-DCPLD) method for Sustainable Agriculture. The main aim of the DLCPO-DCPLD method use DL method for the recognition and identification of rice plant leaf diseases. To accomplish this, the DLCPO-DCPLD technique performs the image pre-processing using Median Filtering (MF) to recover the excellence of the input frames. Next, the ConvNeXt-L method is applied for extraction of feature vectors from the pre-processed images. Also, the Conditional Variational Autoencoder (CVAE) model is utilized for the automated classification of Paddy Leaf diseases. Eventually, the hyperparameter tuning of the CVAE technique is accomplished by implementing the Crested Porcupine Optimizer (CPO) technique. To safeguard the enhanced predictive results of the DLCPO-DCPLD method, a sequence of experimentations is implemented on the benchmark dataset. The experimental validation of the DLCPO-DCPLD method portrayed a superior accuracy value of 99.12% over existing approaches.

A Lightweight Model Enhancing Facial Expression Recognition with Spatial Bias and Cosine-Harmony Loss

This paper proposes a facial expression recognition network called the Lightweight Facial Network with Spatial Bias (LFNSB). The LFNSB model effectively balances model complexity and recognition accuracy. It has two key components: a lightweight feature extraction network (LFN) and a Spatial Bias (SB) module for aggregating global information. The LFN introduces combined channel operations and depth-wise convolution techniques, effectively reducing the number of parameters while enhancing feature representation capability. The Spatial Bias module enables the model to focus on local facial features while capturing the dependencies between different facial regions. Additionally, a new loss function called Cosine-Harmony Loss is designed. This function optimizes the relative positions of feature vectors in high-dimensional space, resulting in better feature separation and clustering. Experimental results on the AffectNet and RAF-DB datasets demonstrate that the LFNSB model achieves competitive recognition accuracy, with 63.12% accuracy on AffectNet-8, 66.57% accuracy on AffectNet-7, and 91.07% accuracy on RAF-DB, while significantly reducing the model complexity.

Beyond Granularity: Enhancing Continuous Sign Language Recognition with Granularity-Aware Feature Fusion and Attention Optimization

The advancement of deep learning techniques has significantly propelled the development of the continuous sign language recognition (cSLR) task. However, the spatial feature extraction of sign language videos in the RGB space tends to focus on the overall image information while neglecting the perception of traits at different granularities, such as eye gaze and lip shape, which are more detailed, or posture and gestures, which are more macroscopic. Exploring the efficient fusion of visual information of different granularities is crucial for accurate sign language recognition. In addition, applying a vanilla Transformer to sequence modeling in cSLR exhibits weak performance because specific video frames could interfere with the attention mechanism. These limitations constrain the capability to understand potential semantic characteristics. We introduce a feature fusion method for integrating visual features of disparate granularities and refine the metric of attention to enhance the Transformer’s comprehension of video content. Specifically, we extract CNN feature maps with varying receptive fields and employ a self-attention mechanism to fuse feature maps of different granularities, thereby obtaining multi-scale spatial features of the sign language framework. As for video modeling, we first analyze why the vanilla Transformer failed in cSLR and observe that the magnitude of the feature vectors of video frames could interfere with the distribution of attention weights. Therefore, we utilize the Euclidean distance among vectors to measure the attention weights instead of scaled-dot to enhance dynamic temporal modeling capabilities. Finally, we integrate the two components to construct the model MSF-ET (Multi-Scaled feature Fusion–Euclidean Transformer) for cSLR and train the model end-to-end. We perform experiments on large-scale cSLR benchmarks—PHOENIX-2014 and Chinese Sign Language (CSL)—to validate the effectiveness.

Fall Detection Based on Data-Adaptive Gaussian Average Filtering Decomposition and Machine Learning

Falls are a significant health concern leading to increased morbidity and healthcare costs, especially for the elderly. Early and accurate detection of fall events is critical for timely intervention and preventing severe complications. This study presents a novel approach to triaxial accelerometer signals by employing data-adaptive Gaussian average filtering (DAGAF) decomposition in conjunction with machine learning techniques for fall detection. The triaxial accelerometer signals from the FallAllD dataset were decomposed into intrinsic mode functions (IMFs) and a residual component, from which feature vectors were extracted to train support vector machine (SVM) and k-nearest neighbor (kNN) classifiers. Experimental results demonstrate that the combination of the first and the third IMFs with the residual component yields the highest classification accuracy of 96.34%, with SVM outperforming kNN across all performance metrics. This approach significantly improves fall detection accuracy compared to using raw accelerometer signals, highlighting its potential in enhancing wearable fall detection systems. The proposed DAGAF decomposition method not only enhances feature extraction but also provides a promising advancement in the field, suggesting its potential to increase the reliability and accuracy of fall detection in practical applications.

A NOVEL HYBRID DEEP LEARNING APPROACH FOR 3D OBJECT DETECTION AND TRACKING IN AUTONOMOUS DRIVING

Recently Object detection and tracking using fusion of LiDAR and RGB camera for the autonomous vehicle environment is a challenging task. The existingworks initiates several object detection and tracking frameworks using ArtificialIntelligence (AI) algorithms. However, they were limited with high false positives and computation time issues thus lacking the performance of autonomousdriving environment. The existing issues are resolved by proposing HybridDeep Learning based Multi Object Detection and Tracking (HDL-MODT) using sensor fusion methods. The proposed work performs fusion of solid stateLiDAR, Pseudo LiDAR, and RGB camera for improving detection and trackingquality. At first, the multi-stage preprocessing is done in which noise removal isperformed using Adaptive Fuzzy Filter (A-Fuzzy). The pre-processed fused image is then provided for instance segmentation to reduce the classification andtracking complexity. For that, the proposed work adopts Lightweight GeneralAdversarial Networks (LGAN). The segmented image is provided for objectdetection and tracking using HDL. For reducing the complexity, the proposedwork utilized VGG-16 for feature extraction which forms the feature vectors.The features vectors are then provided for object detection using YOLOv4.Finally, the detected objects were tracked using Improved Unscented KalmanFilter (IUKF) and mapping the vehicles using time based mapping by considering their RFID, velocity, location, dimension and unique ID. The simulation ofthe proposed work is carried out using MATLAB R2020a simulation tool andperformance of the proposed work is compared with several metrics that showthat the proposed work outperforms than the existing works.

Research on Rotating Machinery Fault Diagnosis Based on Multi-Strategy Feature Extraction

This study proposes a novel feature extraction method that leverages multi-strategy optimization algorithms to enhance the accuracy and efficiency of rotating machinery fault diagnosis. By introducing an improved slime mold algorithm (LTSSMA), it optimizes the penalty factor and decomposition layers in variational mode decomposition (VMD), achieving more precise signal decomposition. The sample entropy generated by VMD forms the basis of the feature vector, and the nonlinear dimensionality reduction algorithm (t-SNE) is applied to reduce dimensions. Finally, the optimized features are classified using a random forest (RF) model, resulting in an 11.3% improvement in fault diagnosis accuracy compared to traditional methods. This method not only accelerates the diagnostic process but also significantly improves fault identification reliability.

Enhancing human computer interaction with coot optimization and deep learning for multi language identification

Human-Computer Interaction (HCI) is a multidisciplinary field focused on designing and utilizing computer technology, underlining the interaction interface between computers and humans. HCI aims to generate systems that allow consumers to relate to computers effectively, efficiently, and pleasantly. Multiple Spoken Language Identification (SLI) for HCI (MSLI for HCI) denotes the ability of a computer system to recognize and distinguish various spoken languages to enable more complete and handy interactions among consumers and technology. SLI utilizing deep learning (DL) involves using artificial neural networks (ANNs), a subset of DL models, to automatically detect and recognize the language spoken in an audio signal. DL techniques, particularly neural networks (NNs), have succeeded in various pattern detection tasks, including speech and language processing. This paper develops a novel Coot Optimizer Algorithm with a DL-Driven Multiple SLI and Detection (COADL-MSLID) technique for HCI applications. The COADL-MSLID approach aims to detect multiple spoken languages from the input audio regardless of gender, speaking style, and age. In the COADL-MSLID technique, the audio files are transformed into spectrogram images as a primary step. Besides, the COADL-MSLID technique employs the SqueezeNet model to produce feature vectors, and the COA is applied to the hyperparameter range of the SqueezeNet method. The COADL-MSLID technique exploits the SLID process’s convolutional autoencoder (CAE) model. To underline the importance of the COADL-MSLID technique, a series of experiments were conducted on the benchmark dataset. The experimentation validation of the COADL-MSLID technique exhibits a greater accuracy result of 98.33% over other techniques.

A new texture-based labeling framework for hyper-reflective foci identification in retinal optical coherence tomography images

An important abnormality in Optical Coherence Tomography (OCT) images is Hyper-Reflective Foci (HRF). This anomaly can be interpreted as a biomarker of serious retinal diseases such as Age-related Macular Degeneration (AMD) and Diabetic Macular Edema (DME) or the progression of disease from an early stage to a late one. In this paper, a new method is proposed for the identification of HRFs. The new method divides the OCT B-scan into patches and separately verifies each patch to determine whether or not the patch contains an HRF. The procedure of patch verification contains a texture-based framework which assigns appropriate labels according to intensity changes to each column and row. Then, a feature vector is extracted for each patch based on the assigned labels. The feature vectors are utilized in the training step of well-known classifiers like Support Vector Machine (SVM). Then, the classifiers are used to produce the labels for the test OCT images. The new method is evaluated on a public dataset including HRF labels. The experimental results show that the new method is capable of providing outstanding results in terms of speed and accuracy.

Emotion recognition using cross-modal attention from EEG and facial expression

The fusion of facial expression and Electroencephalogram (EEG) signals in a multi-modal framework is a comprehensive and accurate method for emotion recognition. However, current methods often tend to directly concatenate two modalities, thereby overlooking the interplay between modalities. Furthermore, the selection of single static facial images for extracting facial features neglected the dynamic changes in facial expressions. These limitations have been identified as factors that constrain the accuracy and stability of the model. In this study, an innovative multimodal emotion recognition network was introduced, which using continuous facial expressions and EEG signals. It incorporated the cross-modal attention fusion mechanism to establish robust correlations between modal feature vectors, thereby generating amalgamated vectors with mutual information. Additionally, a Self-Attention Convolutional Long Short-Term Memory (SA-ConvLSTM) was employed to capture spatiotemporal information from facial expression images. The model proposed in this paper was experimentally evaluated on the DEAP and MAHNOB-HCI datasets. Its recognition accuracy was higher than the existing advanced research methods. At the same time, it still performed well in the Leave-One-Subject-Out (LOSO) experiment based on DEAP dataset. The experimental results showed the effectiveness of the proposed model in the task of multimodal emotion recognition.

Forecasting masked‐load with invisible distributed energy resources based on transfer learning and Bayesian tuning

AbstractLoad forecasting with distributed energy resources (DERs) behind‐the‐meter is more challenging owing to transformed data patterns. Traditional forecasting method which is only based on unmasked‐load could not suit the present limited masked‐load. To bridge the divergence between unmasked‐load and masked‐load, this article proposes a masked‐load forecasting (MLF) method based on transfer learning technique and Bayesian optimization, which is Maximum Mean Discrepancy‐Neural Network with Bayesian optimization (MMD‐NNb). At first, common feature vectors between unmasked‐load and masked‐load are extracted and an outcome predictor could be established based on feature vectors from historical unmasked‐load. The feature vectors from masked‐load could therefore accommodate to the outcome predictor, and the masked‐load could be forecast. Owing to the excessive hyperparameters involved in training, Bayesian optimization is adopted for hyperparameters fine‐tuning. MMD‐NNb was tested and compared with four related models. The improvements from MMD‐NNb were observed in all comparison scenarios. Also, MMD‐NNb was proved to have high resilience to the different DERs and not requiring additional DERs‐data.

Face Recognition with Siamese Networks

Abstract Face recognition method is a common problem in modern Internet life. In this paper, face recognition will be designed based on Siamese network. The traditional methods have some problems, such as being greatly affected by environmental factors, insufficient processing of individual differences, lack of robustness and adaptability. However, the existing Siamese network based method has better recognition effect. In this paper, a face recognition technology based on Siamese network will be proposed. In this method, the features of two face images are extracted by the same neural network, and then these feature vectors are input into a distance metric model to calculate the similarity or distance between them, which is used to compare the similarity between faces. This method reduces the training parameters of the model, improves the utilization of parameters, and the average accuracy can reach 98%. Contrasted with traditional face recognition techniques, it offers enhanced accuracy and resilience, delivering favourable outcomes in real-world applications.

Advanced trust classification in social networks using a triple generative adversarial network-assisted capsule network enhanced by gannet optimization

Over the past ten years, social networks (SN) have evolved into the primary infrastructure for people's everyday activities. Trust classification in social networks involves evaluating the trustworthiness of users or the information they share. Traditional trust classification methods often rely on explicit features, such as user ratings, reviews, and social ties. These methods utilize rule-based to assign trust scores for users or entities. However, they face challenges in capturing the exact nature of trust. In this manuscript, Advanced Trust Classification in Social Networks using a Triple Generative Adversarial Network-Assisted Capsule Network Enhanced by Gannet Optimization (Trust-TripleGAN-CapsNet-GOA) is proposed. In this manuscript, the feature vector has computed to every social network users pair after the raw data from the Sentiment140 dataset, is analysed. The membership of trust is then ranked according to five-class classifications by incorporating Tanimoto Trust Similarity coefficient. Then, Triple Generative Adversarial Network-Assisted Capsule Network (TripleGAN-CapsNet) is used to categorise the trust values of users. Finally, the weight parameters of TripleGAN-CapsNet is optimized by the Gannet Optimization Algorithm (GOA) to enhance the accuracy of the trust behaviour in SN. The proposed Trust-TripleGAN-CapsNet-GOA method attains 22.94 %, 32.36 % and 21.96 % higher accuracy, 30.27 %, 19.46 % and 12.39 %, higher precision when analyzed with the existing models, such as a method for trust mirroring assessment under social networks parameters with fuzzy system (Trust-SNP-FS), deep matrix factorization in social networks for trust-aware recommendation (Trust-DMF-SN) and towards time-aware context-aware deep trust prediction on the online social networks (TACADTrust-SN). The simulation outcomes exhibit that the proposed method attains 99 % accuracy.

GraNDe: Efficient Near-Data Processing Architecture for Graph Neural Networks

Graph Neural Network (GNN) models have attracted attention, given their high accuracy in interpreting graph data. One of the primary building blocks of a GNN model is aggregation, which gathers and averages the feature vectors corresponding to the nodes adjacent to each node. Aggregation works by multiplying the adjacency and feature matrices. The size of both matrices exceeds the on-chip cache capacity for many realistic datasets, and the adjacency matrix is highly sparse. These characteristics lead to little data reuse, causing intensive main-memory accesses during the aggregation process. Thus, aggregation exhibits memory-intensive characteristics and dominates most of the total execution time. In this paper, we propose GraNDe, an NDP architecture that accelerates memory-intensive aggregation operations by locating NDP modules near DRAM datapath to exploit rank-level parallelism. GraNDe maximizes bandwidth utilization by separating the memory channel path with the buffer chip in between so that pre-/post-processing in the host processor and reduction in NDP modules operate simultaneously. By exploring the preferred data mappings of the operand matrices to DRAM ranks, we architect GraNDe to support adaptive matrix mapping that applies the optimal mapping for each layer depending on the dimension of the layer and the configuration of a memory system. We also propose adj-bundle broadcasting and re-tiling optimizations to reduce the transfer time for adjacency matrix data and to improve feature vector data reusability by exploiting tiling with consideration of adjacency between nodes. GraNDe achieves 3.01× and 1.69× on average, and up to <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$4.00\times$</tex-math></inline-formula> and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$1.98\times$</tex-math></inline-formula> speedups of GCN aggregation over the baseline system and the state-of-the-art NDP architecture for GCN, respectively.

Network Data Intrusion Detection and Data Feature Extraction of Electromechanical Facilities from Machine Learning

With the rapid development of Internet technology, network security issues have become more complex and changeable. Various intrusion methods threaten the information network environment in the Electromechanical Facility (EF) system. This paper focuses on EF to study the relevant detection methods and data feature extraction in complex network intrusions. Firstly, four common machine learning algorithms are used to calculate the data set. The advantages and disadvantages of each algorithm are analyzed after tuning and comparison. Secondly, a network intrusion detection algorithm is proposed based on Recursive Feature Elimination (RFE) principal component analysis. It uses RFE to reduce the number of features and improve the elimination judgment index to align with the detection requirements of information network datasets. Finally, a fault diagnosis method is proposed based on empirical pattern decomposition and support vector machine under Renyi entropy complexity measurement. This method trains and identifies the Renyi entropy of several basic pattern components obtained by decomposing empirical patterns as feature vectors. The results show that the RFE method judged by random forest removes irrelevant features, and the evaluation index is improved to align with the network dataset’s detection requirements. It reduces the data dimension, reduces the operation time, and improves the accuracy of a few attack types. The comprehensive final detection effect is better than other algorithms. Additionally, the embedded operating system construction method based on the protection mechanism realizes the separate storage of the operating system and key data. Also, it can prevent the network system from being maliciously invaded, ensuring the stability of the instrument operation under harsh working conditions.