Enhance Classification Accuracy Research Articles

Innovative Framework for Thyroid Disease Detection by Leveraging Hybrid AGTEO Feature Selection and GRU Classification Model

Thyroid disease remains a significant health concern, necessitating advanced diagnostic tools for swift and accurate identification. The initial step involves preprocessing datasets, employing an Outlier Detection Method with Isolated Forest in conjunction with data normalization techniques to eliminate noise and standardize the data, laying a robust groundwork for subsequent analysis. Subsequently, feature extraction is conducted utilizing an Enhanced AlexNet architecture augmented by a more intricate Chameleon Swarm Algorithm (CSA) model to discern finer patterns within the data, enhancing the discriminative nature of the extracted features. Following this, a feature selection strategy employing hybrid optimization is deployed, amalgamating the strengths of Equilibrium Optimizer and Artificial Gorilla Troops Optimizer (AGTO) into a hybrid model named HAGTEO, aiming to identify the most informative features, thus reducing dimensionality and enhancing classifier efficiency. Ultimately, the Gated Recurrent Unit (GRU) classifier is employed for thyroid disease classification based on the extracted and selected features. Renowned for its capability to capture temporal dependencies, the GRU model further enhances classification accuracy. The proposed framework is subjected to testing on two distinct datasets, demonstrating its efficacy in thyroid disease detection. Experimental outcomes reveal superior performance compared to conventional methods, achieving accuracies of 98.07% and 98.00% for dataset 1 and dataset 2, respectively. As an advanced diagnostic solution for thyroid disease, it holds promising potential.

Simulation of a Mathematical Model of Rail Transportation Scheduling Based on Bp Neural Network

Rail transportation, a cornerstone of modern logistics and passenger transit systems, plays a pivotal role in facilitating the efficient movement of goods and people across vast distances. Operating on a network of interconnected tracks, rail systems offer a reliable and environmentally sustainable mode of transportation, particularly for long-distance travel and freight shipments. The paper presents a comprehensive investigation into the application of advanced computational techniques in the realm of rail transportation management. Specifically, Mamdani fuzzy logic and Backpropagation (BP) Neural Networks are employed to address critical challenges in scheduling and classification within rail networks. The utilization of Mamdani fuzzy logic facilitates nuanced decision-making in scheduling processes, considering uncertainties and complexities inherent in rail operations. Through linguistic rules and fuzzy sets, the scheduling system can effectively adapt to various operational constraints and disruptions, leading to more resilient and efficient scheduling solutions. Additionally, the integration of BP Neural Network enhances classification accuracy and prediction capabilities, enabling precise forecasting of train movements, passenger flows, and other key variables.

Analysis of Logistic Regression Regularization in Wild Elephant Classification with VGG-16 Feature Extraction

The research article explores the intersection of image-based wildlife classification and logistic regression regularization, focusing on the classification of wild elephant species. It begins by highlighting the significance of ecological research in biodiversity monitoring and conservation and introduces Convolutional Neural Networks (CNNs) as potent tools for feature extraction from images. The VGG-16 model is particularly emphasized for its ability to capture hierarchical representations of visual features crucial for classification tasks. The integration of VGG-16 feature extraction with logistic regression regularization is proposed as a compelling approach, offering a balance between sophisticated feature representation and efficient classification algorithms. The literature review delves into image-based wildlife classification, emphasizing the role of CNNs, especially VGG-16, in extracting discriminative features. It discusses the fusion of VGG-16 features with logistic regression and the challenges in this field, such as dataset annotation and environmental variability. The method section outlines the dataset acquisition, feature extraction using the VGG-16 architecture, and model configuration using logistic regression with lasso and ridge regularization. The process of finding the optimal regularization parameter (lambda) and model evaluation through cross-validation is detailed. Results showcase the optimal lambda values for lasso and ridge regularization and compare the performance of logistic lasso and logistic ridge models. Misclassification analysis reveals factors influencing classification accuracy, including feature variability and contextual complexity. The discussion reflects on the implications of the findings, emphasizing the importance of lambda selection and addressing challenges in wildlife classification. It suggests avenues for further research, such as advanced modeling techniques and feature engineering approaches. In conclusion, the study contributes to advancing wildlife classification efforts by leveraging state-of-the-art techniques and sheds light on opportunities to enhance classification accuracy in wildlife conservation.

Pre-training CNN model Several Methods of Comparative Analysis

In recent years, the rapid evolution of neural networks, exemplified by models such as VGG and GoogLeNet, has reshaped the landscape of artificial intelligence. This comparative exploration, focusing on transfer learning and attention mechanisms, not only reveals subtle performance distinctions but also provides crucial insights for refining these models in practical applications. This paper delves into the comparative analysis of two prominent neural network models, VGG and GoogLeNet, within the context of image classification. VGG, known for its deep structure, and GoogLeNet, incorporating innovative inception modules, are evaluated through experiments involving flower image datasets. The study includes transfer learning and explores the integration of attention mechanisms, specifically CBAM attention, into both models. Results indicate GoogLeNet's superior performance in terms of parameter efficiency, convergence speed, and overall accuracy. Furthermore, the addition of attention mechanisms enhances classification accuracy for both models. The paper concludes with insights into potential areas for further research, emphasizing optimal attention mechanism placement and a comparison with traditional methods in future studies.

A hybrid 1D CNN-BiLSTM model for epileptic seizure detection using multichannel EEG feature fusion

Epilepsy, a chronic non-communicable disease is characterized by repeated unprovoked seizures, which are transient episodes of abnormal electrical activity in the brain. While Electroencephalography (EEG) is considered as the gold standard for diagnosis in current clinical practice, manual inspection of EEG is time consuming and biased. This paper presents a novel hybrid 1D CNN-Bi LSTM feature fusion model for automatically detecting seizures. The proposed model leverages spatial features extracted by one dimensional convolutional neural network and temporal features extracted by bi directional long short-term memory network. Ictal and inter ictal data is first acquired from the long multichannel EEG record. The acquired data is segmented and labelled using small fixed windows. Signal features are then extracted from the segments concurrently by the parallel combination of CNN and Bi-LSTM. The spatial and temporal features thus captured are then fused to enhance classification accuracy of model. The approach is validated using benchmark CHB-MIT dataset and 5-fold cross validation which resulted in an average accuracy of 95.90%, with precision 94.78%, F1 score 95.95%. Notably model achieved average sensitivity of 97.18% with false positivity rate at 0.05/hr. The significantly lower false positivity and false negativity rates indicate that the proposed model is a promising tool for detecting seizures in epilepsy patients. The employed parallel path network benefits from memory function of Bi-LSTM and strong feature extraction capabilities of CNN. Moreover, eliminating the need for any domain transformation or additional preprocessing steps, model effectively reduces complexity and enhances efficiency, making it suitable for use by clinicians during the epilepsy diagnostic process.

Empowering modern E-commerce consumers: Optimized deep learning for product image classification in home shopping

Accurately classifying products in e-commerce is critical for enhancing user experience, but it remains challenging due to data quality issues and the dynamic nature of product categories. Customers are increasingly relying on visual information to make informed purchasing decisions, emphasizing the importance of accurate product classification using images. In this paper, an innovative approach called SSWSO_LeNet is proposed for product image classification in e-commerce. The method involves preprocessing the input images using Region of Interest (RoI) and Adaptive Wiener Filters to improve image quality and reduce unwanted distortions. Data augmentation techniques are then applied to increase the diversity of the dataset and the robustness of the model. To address this, we propose SSWSO_LeNet, integrating Squirrel Search Algorithm (SSA) and War Strategy Optimization (WSO) with LeNet. SSA mimics southern flying squirrels’ foraging behavior to find global optima efficiently, while WSO balances exploration and exploitation stages, enhancing classification accuracy. Experimental results show SSWSO_LeNet outperforms state-of-the-art models with an impressive accuracy of 0.976, sensitivity of 0.877, and specificity of 0.857. By leveraging SSA, WSO, and LeNet, SSWSO_LeNet not only improves classification accuracy but also reduces reliance on human editors, decreasing both cost and time in e-commerce product classification.

Efficient Feature Learning Model of Motor Imagery EEG Signals with L1-Norm and Weighted Fusion.

Brain-computer interface (BCI) for motor imagery is an advanced technology used in the field of medical rehabilitation. However, due to the poor accuracy of electroencephalogram feature classification, BCI systems often misrecognize user commands. Although many state-of-the-art feature selection methods aim to enhance classification accuracy, they usually overlook the interrelationships between individual features, indirectly impacting the accuracy of feature classification. To overcome this issue, we propose an adaptive feature learning model that employs a Riemannian geometric approach to generate a feature matrix from electroencephalogram signals, serving as the model's input. By integrating the enhanced adaptive L1 penalty and weighted fusion penalty into the sparse learning model, we select the most informative features from the matrix. Specifically, we measure the importance of features using mutual information and introduce an adaptive weight construction strategy to penalize regression coefficients corresponding to each variable adaptively. Moreover, the weighted fusion penalty balances weight differences among correlated variables, reducing the model's overreliance on specific variables and enhancing accuracy. The performance of the proposed method was validated on BCI Competition IV datasets IIa and IIb using the support vector machine. Experimental results demonstrate the effectiveness and superiority of the proposed model compared to the existing models.

Adaptive Threshold and Weighted Frequency Domain Histogram of Local Binary Patterns

Wire ropes are crucial load-bearing components in mining conveyance equipment, and machine vision is one of the methods used to assess the surface damage condition of wire ropes. In response to the light-sensitive nature of local binary patterns, which leads to issues such as differing feature values for similar textures and susceptibility to the influence of excessively large or small pixels within local windows, hindering the accurate reflection of window structure information and exacerbating the introduction of considerable feature noise, an investigation is conducted. To enhance the gradient structural information among pixels within local pixel window, an adaptive threshold binary pattern feature operator is proposed. This operator utilizes the mean and variance within the local window to balance the central pixel value, thereby enhancing the interconnection among neighboring pixels. To perform feature selection on block histograms, a block-weighted approach is employed. This approach utilizes the concept of block weighting and employs correlation coefficients to preprocess feature vectors, thereby enhancing classification accuracy. The algorithm experiments were conducted on a dataset of mine wire ropes. The results indicate that the improved local binary pattern significantly enhances the classification accuracy of the wire rope dataset, achieving an accuracy of 97.3%.

Leveraging Hyperspectral Images for Accurate Insect Classification with a Novel Two-Branch Self-Correlation Approach

Insect recognition, crucial for agriculture and ecology studies, benefits from advancements in RGB image-based deep learning, yet still confronts accuracy challenges. To address this gap, the HI30 dataset is introduced, comprising 2115 hyperspectral images across 30 insect categories, which offers richer information than RGB data for enhancing classification accuracy. To effectively harness this dataset, this study presents the Two-Branch Self-Correlation Network (TBSCN), a novel approach that combines spectrum correlation and random patch correlation branches to exploit both spectral and spatial information. The effectiveness of the HI30 and TBSCN is demonstrated through comprehensive testing. Notably, while ImageNet-pre-trained networks adapted to hyperspectral data achieved an 81.32% accuracy, models developed from scratch with the HI30 dataset saw a substantial 9% increase in performance. Furthermore, applying TBSCN to hyperspectral data raised the accuracy to 93.96%. Extensive testing confirms the superiority of hyperspectral data and validates TBSCN’s efficacy and robustness, significantly advancing insect classification and demonstrating these tools’ potential to enhance precision and reliability.

Optimizing Image Recognition Efficiency using Sparse Representation Learning and Transfer Learning for Resource-Constrained Environments

Image recognition in resource-constrained environments is crucial for mobile devices, IoT, and embedded systems. It reduces the need for internet connectivity and enhances privacy and security. Real-time processing and decision-making are critical for applications such as facial recognition, object detection, and augmented reality. This approach is efficient, making it accessible in remote areas or situations with limited internet access. Our study proposes a novel approach using a network architecture with four modules, emphasizing sparse representation learning and transfer learning to improve image recognition efficiency in resource-constrained environments. The Domain-Adaptive Feature Extractor () facilitates effective sparse representation learning by projecting data from diverse domains into a shared space. The Transferable Affine Decoder () captures affine relationships between domains to facilitate knowledge transfer, while the Cross-Domain Correspondence Network () enforces pixel-level correspondence to extract shared intrinsic representations. The Efficient Classifier Network () enhances classification accuracy using efficient CNNs. The baseline model achieved an accuracy of 0.89. Improved Model 1, leveraging transfer learning, attained 0.92 accuracy, while Improved Model 2 with the Cross-Domain Correspondence Network reached 0.91. The Final Model, amalgamating all methodologies, excelled with the highest accuracy of 0.94. This holistic approach optimizes resource usage and enables real-time processing, thus empowering a diverse array of applications in resource-limited environments.

Dynamic Adaptive Resource Allocation for Edge Computing in Big Data Analytics Using GBDT, DQN, and GA Algorithms

Edge computing in big data refers to processing and analysing data closer to its source, reducing latency and bandwidth usage. It leverages devices at the network edge to perform computations, making real-time analytics feasible. This distributed approach improves efficiency and enables faster decision-making, critical for applications like IoT, autonomous vehicles, and healthcare. The research proposes an innovative approach that harnesses three machine learning algorithms Gradient Boosting Decision Trees (GBDT), Deep Q-Network (DQN), and Genetic Algorithm (GA) to enable dynamic adaptive resource allocation within edge computing environments tailored for big data analytics. GBDT enhances classification accuracy by sequentially refining predictions through decision trees, accommodating heterogeneous data types and yielding high prediction accuracy crucial for dynamic edge environments. The GA evaluates resource allocation strategies represented as chromosomes within a population, selecting promising solutions as parents for the next generation and generating diverse offspring through crossover and mutation operations to discover optimal solutions. DQN facilitates intelligent resource allocation by iteratively refining Q-values based on experiences gathered during interactions with the environment, utilizing a neural network to determine optimal actions for a given state, thereby enhancing performance and efficiency in edge computing environments. This integrated approach ensures flexible resource allocation and fortified capabilities for big data analytics within edge computing environments. The research underscores GBDT as the most promising algorithm for resource allocation in edge computing environments, owing to its exceptional performance in resource utilization, scalability, and accuracy. This nuanced understanding of algorithmic behaviour in dynamic settings offers invaluable insights for optimizing resource allocation strategies, thereby enhancing the efficiency and effectiveness of edge computing systems in handling big data analytics tasks.

Fish Species Classification Using Deep Learning and Appearance-Based Feature Extraction

As aquatic ecosystems face increasing threats and challenges, the accurate and efficient classification of fish species has become a critical task for fisheries management, biodiversity conservation, and environmental monitoring. This research explores the application of deep learning techniques in conjunction with appearance-based feature extraction for the automated and precise identification of fish species from images. The study employs a comprehensive dataset of underwater fish images, encompassing various species, sizes, and environmental conditions. Convolutional Neural Networks (CNNs) are used for feature extraction and classification, allowing for the capture of intricate visual characteristics that distinguish different fish species. Moreover, appearance-based features, such as colour patterns, fin shapes, and other morphological attributes, are integrated into the model to enhance classification accuracy. Additionally, the study introduces Improved Sequential Forward Selection (ISFS) as a method to select relevant features for classification, further enhancing the efficiency and effectiveness of the model. The research evaluates the performance of the proposed methodology against existing classification methods, emphasizing the advantages of deep learning and appearance-based feature extraction in terms of classification accuracy, robustness, and efficiency. In addition, the study explores the potential for real-world applications in fisheries management, species monitoring, and ecological research. The findings of this research demonstrate that the combination of deep learning and appearance-based feature extraction provides a promising approach for fish species classification, offering a valuable tool for conservation efforts and ecological studies. This research contributes to the growing body of knowledge in the field of computer vision and biodiversity conservation and opens up new possibilities for automated fish species identification in aquatic environments.

Advancements in Agricultural Automation: SVM Classifier with Hu Moments for Vegetable Identification

This study investigates the application of Support Vector Machine (SVM) classifiers in conjunction with Hu Moments for the purpose of classifying segmented images of vegetables, specifically Broccoli, Cabbage, and Cauliflower. Utilizing a dataset comprising segmented vegetable images, this research employs the Canny method for image segmentation and Hu Moments for feature extraction to prepare the data for classification. Through the implementation of a 5-fold cross-validation technique, the performance of the SVM classifier was thoroughly evaluated, revealing moderate accuracy, precision, recall, and F1-scores across all folds. The findings highlight the classifier's potential in distinguishing between different vegetable types, albeit with identified areas for improvement. This research contributes to the growing field of agricultural automation by demonstrating the feasibility of using SVM classifiers and image processing techniques for the task of vegetable identification. The moderate performance metrics emphasize the need for further optimization in feature extraction and classifier tuning to enhance classification accuracy. Future recommendations include exploring alternative machine learning algorithms, advanced feature extraction methods, and expanding the dataset to improve the classifier's robustness and applicability in agricultural settings. This study lays a foundation for future advancements in automated vegetable sorting and quality control, offering insights that could lead to more efficient agricultural practices.

Music Genre Classification Using K-Nearest Neighbor and Mel-Frequency Cepstral Coefficients

Music genre classification plays a pivotal role in organizing and accessing vast music collections, enhancing user experiences, and enabling efficient music recommendation systems. This study focuses on employing the K-Nearest Neighbors (KNN) algorithm in conjunction with Mel-Frequency Cepstral Coefficients (MFCCs) for accurate music genre classification. MFCCs extract essential spectral features from audio signals, which serve as robust representations of music characteristics. The proposed approach achieves a commendable classification accuracy of 80%, showcasing the effectiveness of KNN-MFCC fusion. Nevertheless, the challenge of overlapping genres, particularly rock and country, demands special attention due to their shared acoustic attributes. The inherent similarities between these genres often lead to misclassification, hampering accuracy. To address this issue, an enhanced feature engineering strategy is devised, leveraging deeper insights into the subtle nuances that differentiate rock and country music. Additionally, a refined KNN distance metric and neighbor selection mechanism are introduced to further refine classification decisions. Experimental results underscore the effectiveness of the refined approach in mitigating genre overlap issues, significantly enhancing classification accuracy for rock and country genres. This study contributes to the advancement of music genre classification techniques, offering an innovative solution for handling overlapping genres and demonstrating the potential of KNN-MFCC synergy in achieving accurate and refined genre classification.

Prediction Consistency Regularization for Learning with Noise Labels Based on Contrastive Clustering.

In the classification task, label noise has a significant impact on models' performance, primarily manifested in the disruption of prediction consistency, thereby reducing the classification accuracy. This work introduces a novel prediction consistency regularization that mitigates the impact of label noise on neural networks by imposing constraints on the prediction consistency of similar samples. However, determining which samples should be similar is a primary challenge. We formalize the similar sample identification as a clustering problem and employ twin contrastive clustering (TCC) to address this issue. To ensure similarity between samples within each cluster, we enhance TCC by adjusting clustering prior to distribution using label information. Based on the adjusted TCC's clustering results, we first construct the prototype for each cluster and then formulate a prototype-based regularization term to enhance prediction consistency for the prototype within each cluster and counteract the adverse effects of label noise. We conducted comprehensive experiments using benchmark datasets to evaluate the effectiveness of our method under various scenarios with different noise rates. The results explicitly demonstrate the enhancement in classification accuracy. Subsequent analytical experiments confirm that the proposed regularization term effectively mitigates noise and that the adjusted TCC enhances the quality of similar sample recognition.

Thermal radiation of tongue surface as a human computer interaction diagnostics technique based on image classification with software interface

Backgroundand Purpose: Thermal radiation plays a pivotal role in addressing recognition limitations encountered by traditional Chinese medicine's tongue diagnosis. Modern thermal radiation diagnostic instruments offer enhanced objectivity, and in this study, we strive to further improve the diagnostic process through the integration of Human-Computer Interaction (HCI) principles. Our objective is to introduce the thermal radiation DenseNet ensemble model, synergizing the strengths of Convolutional Neural Networks (CNNs) and HCI principles to advance tongue image recognition in healthcare. This approach aims to enhance classification accuracy, even when faced with limited training data. MethodologyTransfer learning, utilizing fine-tuned CNNs and DenseNet, is employed for precise classification, with a specific focus on distinguishing tooth-marked tongues. A portable hand-held thermal radiation diagnostic instrument, seamlessly integrated with HCI, is developed for both clinical use and research. Experimental resultsMeticulously curated datasets, formed through the annotation of thermal radiation images, confirm the superior performance of the DenseNet architecture in tooth mark and tongue feature recognition. The proposed tooth mark tongue recognition model exhibits a significant accuracy improvement of approximately 25% compared to similar tasks in existing studies. Additionally, an AI health detector tailored for Traditional Chinese Medicine (TCM) thermal radiation image recognition is introduced, showcasing the seamless integration of HCI principles into healthcare applications. This innovative tool not only assesses users' health but also provides personalized health recommendations, illustrating the transformative potential of combining technology and healthcare. Discussion and conclusionIn addressing the limitations of traditional tongue diagnosis, thermal radiation emerges as a key factor enhancing objectivity and accuracy. The thermal radiation DenseNet ensemble model, along with HCI integration through the portable hand-held device, proves effective for improved TCM thermal radiation image identification in healthcare. The fusion of technology and HCI principles underscores the potential to elevate health assessments and offer valuable guidance to users.

Explainable Deep Learning: A Visual Analytics Approach with Transition Matrices

The non-transparency of artificial intelligence (AI) systems, particularly in deep learning (DL), poses significant challenges to their comprehensibility and trustworthiness. This study aims to enhance the explainability of DL models through visual analytics (VA) and human-in-the-loop (HITL) principles, making these systems more transparent and understandable to end users. In this work, we propose a novel approach that utilizes a transition matrix to interpret results from DL models through more comprehensible machine learning (ML) models. The methodology involves constructing a transition matrix between the feature spaces of DL and ML models as formal and mental models, respectively, improving the explainability for classification tasks. We validated our approach with computational experiments on the MNIST, FNC-1, and Iris datasets using a qualitative and quantitative comparison criterion, that is, how different the results obtained by our approach are from the ground truth of the training and testing samples. The proposed approach significantly enhanced model clarity and understanding in the MNIST dataset, with SSIM and PSNR values of 0.697 and 17.94, respectively, showcasing high-fidelity reconstructions. Moreover, achieving an F1m score of 77.76% and a weighted accuracy of 89.38%, our approach proved its effectiveness in stance detection with the FNC-1 dataset, complemented by its ability to explain key textual nuances. For the Iris dataset, the separating hyperplane constructed based on the proposed approach allowed for enhancing classification accuracy. Overall, using VA, HITL principles, and a transition matrix, our approach significantly improves the explainability of DL models without compromising their performance, marking a step forward in developing more transparent and trustworthy AI systems.

Enhancing temporal action localization in an end-to-end network through estimation error incorporation

Temporal action localization presents a significant challenge in computer vision, as the development of an efficient method for this task remains elusive. The objective is to identify human activities within untrimmed videos, determining when and which actions occur in each video. While using trimmed videos could potentially resolve the localization problem and enhance classification accuracy, it is impractical for real-world applications as the trimming process itself requires human intervention. This highlights the importance of temporal localization. Due to the availability of several successful approaches for action recognition in trimmed video, conventional multi-stage methods for untrimmed video, commonly employ a network to generate activity proposals, followed by a separate network for classification. These disjoint networks are optimized individually and thus usually vary from the global optimum, leading to less precise candidate action proposals. To address this challenge, we propose a novel end-to-end neural network that utilizes error estimation for precise action localization and recognition in untrimmed videos. The proposed method performs the localization and classification of action instances simultaneously, thereby optimizing the corresponding networks concurrently. To increase the precision of the action proposal boundaries, the Regression module is innovatively utilized as part of the proposed end-to-end network, along with the Evaluation and Classification modules. This module estimates the potential error in proposal time boundaries and enhances the result accuracy. We have conducted experiments on THUMOS 14 and ActivityNet-1.3, which are considered the most challenging datasets for temporal action localization. The novel, yet fairly simple, proposed network achieves remarkable performance improvement compared to the other state-of-the-art methods. This improvement, which is more pronounced in the cases of high temporal intersection with ground truth, is accomplished without requiring extra data or complicated architecture. By incorporating error estimation, we achieved improvement in mean Average Precision (mAP). The proposed approach particularly shines for the localization of challenging activities in the complex and diverse dataset ActivityNet-1.3. For instance, for the “drinking coffee” activity, the mean Average Precision (mAP) was enhanced fivefold compared to the best-reported results.

Enhancing Lung Nodule Classification: A Novel CViEBi-CBGWO Approach with Integrated Image Preprocessing.

Cancer detection and accurate classification pose significant challenges for medical professionals, as it is described as a lethal illness. Diagnosing the malignant lung nodules in its initial stage significantly enhances the recovery and survival rates. Therefore, a novel model named convolutional vision Elman bidirectional-based crossover boosted grey wolf optimization (CViEBi-CBGWO) has been proposed to enhance classification accuracy. CT images selected for further preprocessing are obtained from the LUNA16 dataset and LIDC-IDRI dataset. The data undergoes preprocessing phases involving normalization, data augmentation, and filtering to improve the generalization ability as well as image quality. The local features within the preprocessed images are extracted by implementing the convolutional neural network (CNN). For extracting the global features within the preprocessed images, the vision transformer (ViT) model consists of five encoder blocks. The attained local and global features are combined to generate the feature map. The Elman bidirectional long short-term memory (EBiLSTM) model is applied to categorize the generated feature map as benign and malignant. The crossover operation is integrated with the grey wolf optimization (GWO) algorithm, and the combined form of CBGWO fine-tunes the parameters of the CViEBi model, eliminating the problem of local optima. Experimental validation is conducted using various evaluation measures to assess effectiveness. Comparative analysis demonstrates a superior classification accuracy of 98.72% in the proposed method compared to existing methods.

A novel stochastic resonance based deep residual network for fault diagnosis of rolling bearing system

Rolling bearings constitute one of the most vital components in mechanical equipment, monitoring and diagnosing the condition of rolling bearings is essential to ensure safe operation. In actual production, the collected fault signals typically contain noise and cannot be accurately identified. In the paper, stochastic resonance (SR) is introduced into a spiking neural network (SNN) as a feature enhancement method for fault signals with varying noise intensities, combining deep learning with SR to enhance classification accuracy. The output signal-to-noise ratio(SNR) can be enhanced with the SR effect when the noise-affected fault signal input into neurons. Validation of the method is carried out through experiments on the CWRU dataset, achieving classification accuracy of 99.9%. In high-noise environments, with SNR equal to −8 dB, SRDNs achieve over 92% accuracy, exhibiting better robustness and adaptability.