Enhance Classification Accuracy Research Articles

CNN-LandCoverNet: An Effective Framework of Land Cover Classification Using Hybrid Metaheuristic-Aided Ensemble-Based Convolutional Neural Network

Land cover (LC) categorization is considered a necessary task of intelligent interpretation technology for remote sensing imagery that is intended to categorize every pixel to perform the predefined LC classification. Land Use and Land Cover (LULC) information has the ability to provide various insights in order to overcome environmental and socioeconomic impacts such as disaster risk, climate change, poverty, and food insecurity. Therefore, image categorization tasks are involved in conventional works, where the classical visual interpretation techniques completely depend upon professional knowledge as well as a professional’s classification experience, which is more susceptible to subjective awareness, inefficient, and time consuming. By overcoming this issue, the latest deep-structured approach is suggested to perform the LC image classification. Initially, the land images are gathered. Further, the collected images are employed for patch splitting, where the images are split into multiple patches. After splitting, the patches are fed to the Ensemble-based Convolutional Neural Network (ECNN), which is constructed with a Fully Convolutional Network (FCN), U-Net, DeepLabv3, and Mask Region-based Convolutional Neural Network (Mask R-CNN) for performing segmentation. Here, the hyperparameters are optimally tuned with the Hybrid Billiards-inspired Water Wave Algorithm (HB-WWA) by integrating the Billiards-inspired Optimization Algorithm (BOA) and Water Wave Algorithm (WWA). Finally, the classification is carried out with a fuzzy classifier. Thus, the performance is validated and measured through diverse metrics. Consequently, the developed work has demonstrated enhanced classification accuracy when tested on other existing algorithms.

Automatic music mood classification using multi-modal attention framework

Automatic music recommendation systems based on human emotions are becoming popular nowadays. Since audio and lyrics can provide a rich set of information regarding a song, a fusion model including both modalities can enhance classification accuracy and is attempted in this paper. The main objective of the paper is to address music mood classification using various attention mechanisms, namely, self-attention (SA), channel attention (CA), and hierarchical attention network (HAN), on a multi-modal music mood classification system. Experimental results show that multi-modal architectures with attention have achieved higher accuracy than multi-modal architectures without attention and uni-modal architectures. Motivated by the performance of attention mechanisms, a new network architecture, HAN-CA-SA based multi-modal classification system, is proposed, which reported an accuracy of 82.35%. ROC and Kappa are also computed to see the efficacy of the proposed model. The proposed model is also evaluated using the K-fold cross-validation technique. The performance of the proposed model is compared with that of XLNet and CNN-BERT systems. In addition, McNemar’s statistical hypothesis test is conducted to reaffirm the importance of the proposed approach.

Radar‐based human activity recognition using denoising techniques to enhance classification accuracy

AbstractRadar‐based human activity recognition is considered as a competitive solution for the elderly care health monitoring problem, compared to alternative techniques such as cameras and wearable devices. However, raw radar signals are often contaminated with noise, clutter, and other artifacts that significantly impact recognition performance, which highlights the importance of prepossessing techniques that enhance radar data quality and improve classification model accuracy. In this study, two different human activity classification models incorporated with pre‐processing techniques have been proposed. The authors introduce wavelet denoising methods into a cyclostationarity‐based classification model, resulting in a substantial improvement in classification accuracy. To address the limitations of conventional pre‐processing techniques, a deep neural network model called Double Phase Cascaded Denoising and Classification Network (DPDCNet) is proposed, which performs end‐to‐end signal‐level classification and achieves state‐of‐the‐art accuracy. The proposed models significantly reduce false detections and would enable robust activity monitoring for older individuals with radar signals, thereby bringing the system closer to a practical implementation for deployment.

Vehicle classification based on audio-visual feature fusion with low-quality images and noise

In Intelligent Transport Systems (ITS), vision is the primary mode of perception. However, vehicle images captured by low-cost traffic cameras under challenging weather conditions often suffer from poor resolution and insufficient detail representation. On the other hand, vehicle noise provides complementary auditory features that offer advantages such as environmental adaptability and a large recognition distance. To address these limitations and enhance the accuracy of low-quality traffic surveillance classification and identification, an effective audio-visual feature fusion method is crucial. This paper presents a research study that establishes an Urban Road Vehicle Audio-visual (URVAV) dataset specifically designed for low-quality images and noise recorded in complex weather conditions. For low-quality vehicle image classification, the paper proposes a simple Convolutional Neural Network (CNN)-based model called Low-quality Vehicle Images Net (LVINet). Additionally, to further enhance classification accuracy, a spatial channel attention-based audio-visual feature fusion method is introduced. This method converts one-dimensional acoustic features into a two-dimensional audio Mel-spectrogram, allowing for the fusion of auditory and visual features. By leveraging the high correlation between these features, the representation of vehicle characteristics is effectively enhanced. Experimental results demonstrate that LVINet achieves a classification accuracy of 93.62% with reduced parameter count compared to existing CNN models. Furthermore, the proposed audio-visual feature fusion method improves classification accuracy by 7.02% and 4.33% when compared to using single audio or visual features alone, respectively.

Efficiency in Orchid Species Classification: A Transfer Learning-Based Approach

Orchid is a type of plant that grows on land. It is highly valued for its beauty and is cherished by many because of its graceful flower shape, delicate fragrance, vibrant colors, and noble symbolism. Although there are various types of orchids, some of them look similar in appearance and color, making it challenging for people to distinguish them quickly and accurately. The existing methods for classifying orchid species face issues with accuracy due to the similarities between different species and the differences within the same species. This affects their practical use. To address these challenges, this paper introduces an efficient method for classifying orchid species using transfer learning. The main achievement of this study is the successful utilization of transfer learning to achieve accurate orchid species classification. This approach reduces the need for large datasets, minimizes overfitting, cuts down on training time and costs, and enhances classification accuracy. Specifically, the proposed approach involves four phases. First, we gathered a collection of 12 orchid image sets, totaling 12,227 images, through a combination of network sources and field photography. Next, we analyzed the distinctive features present in the collected orchid image sets. We identified certain connections between the acquired orchid datasets and other datasets. Finally, we employed transfer learning technology to create an efficient classification function for orchid species based on these relationships. As a result, our proposed method effectively addresses the challenges highlighted. Experimental results demonstrate that our classification algorithm, which utilizes transfer learning, achieves a classification accuracy rate of 96.16% compared to not using the transfer learning method. This substantial improvement in accuracy greatly enhances the efficiency of orchid classification.

89 Detecting Feigned Cognitive Impairment Using Pupillometry on the Warrington Recognition Memory Test for Words

Objective:Traditional methods of assessing performance validity have numerous weaknesses, among them, results can be consciously manipulated by examinees who wish to feign cognitive impairment. This study tested the ability of pupillary dilation patterns during a performance validity test (PVT) to enhance diagnostic accuracy in discriminating true from feigned impairment of traumatic brain injury (TBI). Pupillometry provides information about physiological and psychological processes related to cognitive load, familiarity, and deception and is outside of conscious control. Patrick, Rapport, Kanser, Hanks, and Bashem (2021) established proof of concept for the utility of pupillometry with PVTs applied to the Test of Memory Malingering (TOMM). This study replicated and extended this work by evaluating the incremental utility of pupillary-derived indices on the Warrington Recognition Memory Test for Words (RMT).Participants and Methods:Participants included 214 adults in three groups: adults with bona fide TBI (TBI; n = 51) healthy comparisons instructed to perform their best (HC; n = 72), and healthy adults instructed and incentivized to simulate cognitive impairment due to TBI (SIM; n = 91). Moreover, this study examined pupillary pattern differences among successful (i.e., failed < 1 PVT and performed impaired on cognitive tests) and unsuccessful (i.e., failed > 2 PVTs or did not score impaired on a cognitive test) SIM, including SIM who did and did not fail the RMT. The RMT was administered in the context of a comprehensive neuropsychological battery. Indices included two pure pupil dilation (PD) indices: a simple measure of baseline arousal (PD-Baseline) and a nuanced measure of dynamic engagement (PD-Range). A pupillo-behavioral index was also evaluated: Dilation-response inconsistency (DRI) captured the frequency with which examinees displayed a pupillary familiarity response to the correct answer but selected the unfamiliar stimulus (incorrect answer).Results:The results generally replicated Patrick et al. (2021), as all three indices were useful in discriminating between groups and provided incremental utility to traditional accuracy scores. PD-Baseline appeared sensitive to oculomotor dysfunction due to TBI (i.e., increasing accurate identification of that group); adults with TBI displayed significantly lower chronic arousal as compared to the two groups of healthy adults (SIM, HC). In fact, the TBI group showed significantly lower PD-Baseline than both unsuccessful simulators who were detected as feigners and successful simulators who passed PVTs but effectively feigned TBI on other tests. Dynamic engagement (PD-Range) yielded a hierarchical structure such that SIM were more dynamically engaged than TBI followed by HC. As predicted, simulators engaged in DRI significantly more frequently than other groups. Moreover, DRI added unique information to RMT accuracy in classifying unsuccessful simulators from all other groups. Each of these three pupillary indices showed large effect sizes, and logistic regressions indicated that each contributed unique variance in predicting group membership on one or more of the paired contrasts (i.e., SIM-TBI, SIM-HC, HC-TBI).Conclusions:Taken together, the findings support continued research on the application of pupillometry to performance validity assessment: Pupillometry provided unique information in enhancing classification accuracy beyond traditional PVT accuracy scores. Overall, the findings highlight the promise of biometric indices in multimethod assessments of performance validity.

Ensemble Learning Based Malicious Node Detection in SDN-Based VANETs

Background: The architecture of Software Defined Networking (SDN) integrated with Vehicular Ad-hoc Networks (VANETs) is considered a practical method for handling large-scale, dynamic, heterogeneous vehicular networks, since it offers flexibility, programmability, scalability, and a global understanding. However, the integration with VANETs introduces additional security vulnerabilities due to the deployment of a logically centralized control mechanism. These security attacks are classified as internal and external based on the nature of the attacker. The method adopted in this work facilitated the detection of internal position falsification attacks. Objective: This study aimed to investigate the performance of k-NN, SVM, Naïve Bayes, Logistic Regression, and Random Forest machine learning (ML) algorithms in detecting position falsification attacks using the Vehicular Reference Misbehavior (VeReMi) dataset. It also aimed to conduct a comparative analysis of two ensemble classification models, namely voting and stacking for final decision-making. These ensemble classification methods used the ML algorithms cooperatively to achieve improved classification. Methods: The simulations and evaluations were conducted using the Python programming language. VeReMi dataset was selected since it was an application-specific dataset for VANETs environment. Performance evaluation metrics, such as accuracy, precision, recall, F-measure, and prediction time were also used in the comparative studies. Results: This experimental study showed that Random Forest ML algorithm provided the best performance in detecting attacks among the ML algorithms. Voting and stacking were both used to enhance classification accuracy and reduce time required to identify an attack through predictions generated by k-NN, SVM, Naïve Bayes, Logistic Regression, and Random Forest classifiers. Conclusion: In terms of attack detection accuracy, both methods (voting and stacking) achieved the same level of accuracy as Random Forest. However, the detection of attack using stacking could be achieved in roughly less than half the time required by voting ensemble. Keywords: Machine learning methods, Majority voting ensemble, SDN-based VANETs, Security attacks, Stacking ensemble classifiers, VANETs,

An Ensemble Framework Approach to Crop Type Prediction Using Feature Selection and Multiclass Classification

Crop type classification plays a crucial role in modern agriculture, aiding in yield prediction, resource management, and land-use planning. This paper presents a comprehensive framework for crop type classification utilizing a combination of feature selection techniques, robust classification Algorithm, and a Support Vector Machine (SVM)-based multiclass classification approach. The proposed framework begins with a novel feature selection process that identifies the most relevant attributes from the Agricultural Data and Rainfall data. This feature selection step is essential for reducing data dimensionality, enhancing classification accuracy, and improving model interpretability. Following feature selection, a state-of-the-art multiclass classification strategy based on Support Vector Machines is employed. SVMs are known for their capability to handle high-dimensional data and have demonstrated superior performance in various classification tasks. In this framework, SVMs are adapted to handle multiclass crop type classification efficiently. The model is trained on the selected features and optimized using hyperparameter tuning techniques to ensure robust performance.

Review on Hybrid Swarm Algorithms for Feature Selection

Feature selection represents one of the critical processes in machine learning (ML). The fundamental aim of the problem of feature selection is to maintain performance accuracy while reducing the dimension of feature selection. Different approaches were created for classifying the datasets. In a range of optimization problems, swarming techniques produced better outcomes. At the same time, hybrid algorithms have gotten a lot of attention recently when it comes to solving optimization problems. As a result, this study provides a thorough assessment of the literature on feature selection problems using hybrid swarm algorithms that have been developed over time (2018-2021). Lastly, when compared with current feature selection procedures, the majority of hybrid algorithms enhance classification accuracy.

Salt Land classification based on pansharpening images using Random Forest algorithm

ABSTRACT The analysis and policymaking of national salt production require quality Salt Land maps with more detailed object information. This study successfully classified Salt Land into Active and Inactive based on pansharpening images using random forest algorithm. The results show: 1) the best pansharpening method is UNB PanSharp; 2) the texture variables have more significant contributions to enhance classification accuracy; 3) scheme 5 is the most efficient and recommended scheme in research, achieves an OA of 66.699% and a Kappa coefficient of 39.4%. This study can provide a good reference for developing Salt Land mapping and policies for practitioners or stakeholders.

Interpretable Multi-Channel Capsule Network for Human Motion Recognition

Recently, capsule networks have emerged as a novel neural network architecture for human motion recognition owing to their enhanced interpretability compared to traditional deep learning networks. However, the characteristic features of human motion are often distributed across distinct spatial dimensions and existing capsule networks struggle to independently extract and combine features across multiple spatial dimensions. In this paper, we propose a new multi-channel capsule network architecture that extracts feature capsules in different spatial dimensions, generates a multi-channel capsule chain with independent routing within each channel, and culminates in the aggregation of information from capsules in different channels to activate categories. The proposed structure endows the network with the capability to independently cluster interpretable features within different channels; aggregates features across channels during classification, thereby enhancing classification accuracy and robustness; and also presents the potential for mining interpretable primitives within individual channels. Experimental comparisons with several existing capsule network structures demonstrate the superior performance of the proposed architecture. Furthermore, in contrast to previous studies that vaguely discussed the interpretability of capsule networks, we include additional visual experiments that illustrate the interpretability of the proposed network structure in practical scenarios.

Optimized Convolutional Fusion for Multimodal Neuroimaging in Alzheimer's Disease Diagnosis: Enhancing Data Integration and Feature Extraction.

Multimodal neuroimaging has gained traction in Alzheimer's Disease (AD) diagnosis by integrating information from multiple imaging modalities to enhance classification accuracy. However, effectively handling heterogeneous data sources and overcoming the challenges posed by multiscale transform methods remains a significant hurdle. This article proposes a novel approach to address these challenges. To harness the power of diverse neuroimaging data, we employ a strategy that leverages optimized convolution techniques. These optimizations include varying kernel sizes and the incorporation of instance normalization, both of which play crucial roles in feature extraction from magnetic resonance imaging (MRI) and positron emission tomography (PET) images. Specifically, varying kernel sizes allow us to adapt the receptive field to different image characteristics, enhancing the model's ability to capture relevant information. Furthermore, we employ transposed convolution, which increases spatial resolution of feature maps, and it is optimized with varying kernel sizes and instance normalization. This heightened resolution facilitates the alignment and integration of data from disparate MRI and PET data. The use of larger kernels and strides in transposed convolution expands the receptive field, enabling the model to capture essential cross-modal relationships. Instance normalization, applied to each modality during the fusion process, mitigates potential biases stemming from differences in intensity, contrast, or scale between modalities. This enhancement contributes to improved model performance by reducing complexity and ensuring robust fusion. The performance of the proposed fusion method is assessed on three distinct neuroimaging datasets, which include: Alzheimer's Disease Neuroimaging Initiative (ADNI), consisting of 50 participants each at various stages of AD for both MRI and PET (Cognitive Normal, AD, and Early Mild Cognitive); Open Access Series of Imaging Studies (OASIS), consisting of 50 participants each at various stages of AD for both MRI and PET (Cognitive Normal, Mild Dementia, Very Mild Dementia); and whole-brain atlas neuroimaging (AANLIB) (consisting of 50 participants each at various stages of AD for both MRI and PET (Cognitive Normal, AD). To evaluate the quality of the fused images generated via our method, we employ a comprehensive set of evaluation metrics, including Structural Similarity Index Measurement (SSIM), which assesses the structural similarity between two images; Peak Signal-to-Noise Ratio (PSNR), which measures how closely the generated image resembles the ground truth; Entropy (E), which assesses the amount of information preserved or lost during fusion; the Feature Similarity Indexing Method (FSIM), which assesses the structural and feature similarities between two images; and Edge-Based Similarity (EBS), which measures the similarity of edges between the fused and ground truth images. The obtained fused image is further evaluated using a Mobile Vision Transformer. In the classification of AD vs. Cognitive Normal, the model achieved an accuracy of 99.00%, specificity of 99.00%, and sensitivity of 98.44% on the AANLIB dataset.

Exploring the ViDiDetect Tool for Automated Defect Detection in Manufacturing with Machine Vision

Automated monitoring of cutting tool wear is of paramount importance in the manufacturing industry, as it directly impacts production efficiency and product quality. Traditional manual inspection methods are time-consuming and prone to human error, necessitating the adoption of more advanced techniques. This study explores the application of ViDiDetect, a deep learning-based defect detection solution, in the context of machine vision for assessing cutting tool wear. By capturing high-resolution images of machining tools and analyzing wear patterns, machine vision systems offer a non-contact and non-destructive approach to tool wear assessment, enabling continuous monitoring without disrupting the machining process. In this research, a smart camera and an illuminator were utilized to capture images of a car suspension knuckle’s machined surface, with a focus on detecting burrs, chips, and tool wear. The study also employed a mask to narrow the region of interest and enhance classification accuracy. This investigation demonstrates the potential of machine vision and ViDiDetect in automating cutting tool wear assessment, ultimately enhancing manufacturing processes’ efficiency and product quality. The project is at the implementation stage in one of the automotive production plants located in southern Poland.

Disease classification using neighbourhood centroid opposition based multi-objective flamingo search algorithm based feature selection approach

In machine learning, a crucial task is feature selection in that the computational cost will be increased exponentially with increases in problem complexity. To reduce the dimensionality of medical datasets and reduce the computational cost, multi-objective optimization approaches are mainly utilized by researchers. Similarly, for improving the population diversity of the Flamingo Search Algorithm, the neighbourhood centroid opposition-based learning mutation is employed. In this paper, to improve the classification accuracy, enhance their exploration capability in the search space and reduce the computational cost while increasing the size of dataset, neighbourhood centroid opposition-based learning (NCOBL) is integrated into the multi-objective optimization based Flamingo Search Algorithm (MOFSA). The optimal selected datasets are classified by using the weighted K-Nearest Neighbour classifier. With the use of fifteen benchmark medical datasets, the efficacy of the suggested strategy is assessed in terms of recall, precision, accuracy, running time, F-measure, hamming loss, ranking loss, standard deviation, mean value error, and size of the selected features. Then the performance of the suggested feature selection technique is compared to that of the existing approaches. The suggested method produced a minimum mean value, standard deviation, mean hamming loss, and maximum accuracy of about 99%. The experimental findings demonstrate that the suggested method may enhance classification accuracy and also eliminate redundancy in huge datasets.

Enhancing Parkinson's disease severity assessment through voice-based wavelet scattering, optimized model selection, and weighted majority voting

Parkinson's disease (PD) is a neurodegenerative disorder characterized by motor and non-motor symptoms that significantly impact an individual's quality of life. Voice changes have shown promise as early indicators of PD, making voice analysis a valuable tool for early detection and intervention. This study aims to assess and detect the severity of PD through voice analysis using the mobile device voice recordings dataset. The dataset consisted of recordings from PD patients at different stages of the disease and healthy control subjects. A novel approach was employed, incorporating a voice activity detection algorithm for speech segmentation and the wavelet scattering transform for feature extraction. A Bayesian optimization technique is used to fine-tune the hyperparameters of seven commonly used classifiers and optimize the performance of machine learning classifiers for PD severity detection. AdaBoost and K-nearest neighbor consistently demonstrated superior performance across various evaluation metrics among the classifiers. Furthermore, a weighted majority voting (WMV) technique is implemented, leveraging the predictions of multiple models to achieve a near-perfect accuracy of 98.62%, improving classification accuracy. The results highlight the promising potential of voice analysis in PD diagnosis and monitoring. Integrating advanced signal processing techniques and machine learning models provides reliable and accessible tools for PD assessment, facilitating early intervention and improving patient outcomes. This study contributes to the field by demonstrating the effectiveness of the proposed methodology and the significant role of WMV in enhancing classification accuracy for PD severity detection.

Piecewise Linear Approximation-Driven Primal SVM Approach for Improved Iris Classification Efficiency

Classification, a crucial aspect of machine learning, revolves around the meticulous analysis of data. However, the complexity of diverse life forms on Earth poses a challenge in distinguishing species that share similar attributes. The iris flower, with its subspecies exemplifies this challenge. The aim of the paper is to develop a methodology that not only enhances classification accuracy but also effectively addresses computational efficiency, facilitating faster and more practical categorization of iris patterns. This novel approach named Piecewise Linear Approximation based SVM (PLA-SVM) is applied to flower species classification and is benchmarked against alternative machine learning techniques. Implementation is carried out utilizing MATLAB – GUROBI interface of and GUROBI Solver. The performance metrics such as accuracy, precision, F1 score and ROC – AUC Curve are used to compare proposed algorithm performance. This comprehensive analysis enables a comparative study of diverse algorithms, ultimately validating the proposed PLA-SVM technique using the Iris dataset. The numerical implementation results shows that the PLASVM outperforms the existing standard classifiers in terms of different performance matrices.

Improved feature selection using a hybrid side-blotched lizard algorithm and genetic algorithm approach

<span lang="EN-US">Feature selection entails choosing the significant features among a wide collection of original features that are essential for predicting test data using a classifier. Feature selection is commonly used in various applications, such as bioinformatics, data mining, and the analysis of written texts, where the dataset contains tens or hundreds of thousands of features, making it difficult to analyze such a large feature set. Removing irrelevant features improves the predictor performance, making it more accurate and cost-effective. In this research, a novel hybrid technique is presented for feature selection that aims to enhance classification accuracy. A hybrid binary version of side-blotched lizard algorithm (SBLA) with genetic algorithm (GA), namely SBLAGA, which combines the strengths of both algorithms is proposed. We use a sigmoid function to adapt the continuous variables values into a binary one, and evaluate our proposed algorithm on twenty-three standard benchmark datasets. Average classification accuracy, average number of selected features and average fitness value were the evaluation criteria. According to the experimental results, SBLAGA demonstrated superior performance compared to SBLA and GA with regards to these criteria. We further compare SBLAGA with four wrapper feature selection methods that are widely used in the literature, and find it to be more efficient.</span>

Monkeypox Detection Using Hyper-Parameter Tuned Based Transferable CNN Model

The reemergence of Monkeypox, a communicable illness resulting from the Monkeypox virus, has raised apprehensions about a potential swift global pandemic similar to the COVID-19 epidemic as COVID-19 infections diminish globally. The prompt emphasizes the criticality of prompt action within communities to mitigate the development of the phenomenon. The timely identification and accurate categorization of Monkeypox cutaneous manifestations are crucial for the successful implementation of containment strategies. This paper presents a novel methodology for detecting Monkeypox by utilizing a transferrable Convolutional Neural Network (CNN) model that has been optimized utilizing hyper-parameter tuning techniques. The proposed methodology initiates by improving the quality of the original Monkeypox images, with a specific emphasis on boosting edge details to increase visual clarity. Texture qualities are obtained through an energy layer, enhancing distinctive traits. Our methodology's cornerstone is utilizing the Hyper-parameter-based transferable Convolutional Neural Network (HPT-TCNN), specifically designed to enhance classification accuracy.
 In contrast to traditional methods, we enhance the architectural design by replacing the pooling layer with a configuration comprising three convolutional layers and one energy layer. The hyper-parameter tuning procedure is optimized by employing the Optimisation Algorithm known as MGS-ROA. In order to enhance the process of model training and validation, we have assembled the "Monkeypox Skin Lesion Dataset (MSLD)," which consists of a collection of images depicting human skin lesions produced by Monkeypox. The dataset in question is vital in evaluating and improving our methodology. In a comparison analysis conducted on other deep learning models, the suggested model has superior performance compared to other models, obtaining a notable accuracy, sensitivity, and specificity, all reaching a value of 93.60%. The outstanding performance shown in this study highlights the methodology's effectiveness in adequately classifying skin lesions associated with Monkeypox. This approach shows potential for physicians and healthcare workers since it facilitates early detection, a crucial factor in preventing the spread of Monkeypox.

A Fog-Based Privacy-Preserving Federated Learning System for Smart Healthcare Applications

During the COVID-19 pandemic, the urgency of effective testing strategies had never been more apparent. The fusion of Artificial Intelligence (AI) and Machine Learning (ML) models, particularly within medical imaging (e.g., chest X-rays), holds promise in smart healthcare systems. Deep Learning (DL), a subset of AI, has exhibited prowess in enhancing classification accuracy, a crucial aspect in expediting COVID-19 diagnosis. However, the journey to harness DL’s potential is rife with challenges: notably, the intricate landscape of medical data privacy. Striking a balance between utilizing patient data for insights while upholding privacy is formidable. Federated Learning (FL) emerges as a solution by enabling collaborative model training across decentralized data sources, thus bypassing data centralization and preserving data privacy. This study presents a tailored, collaborative FL architecture for COVID-19 screening via chest X-ray images. Designed to facilitate cooperation among medical institutions, the framework ensures patient data remain localized, eliminating the need for direct data sharing. Addressing imbalanced and non-identically distributed data, the architecture is a robust solution. Implementation entails localized and fog-computing-based FL models. Localized models utilize Convolutional Neural Networks (CNNs) on institution-specific datasets, while the FL model, refined iteratively, takes precedence in the final classification. Intriguingly, the global FL model, fortified by fog computing, emerges as the frontrunner in classification after weight refinement, surpassing local models. Validation within the COLAB platform gauges the model’s performance through metrics such as accuracy, precision, recall, and F1-score. Remarkably, the proposed model excels across these metrics, solidifying its efficacy. This research navigates the confluence of AI, FL, and medical imaging, unveiling insights that could reshape healthcare delivery. The study enriches scientific discourse by addressing data privacy in collaborative learning and carries potential implications for enhanced patient care.

A Novel Feature-Selection Algorithm in IoT Networks for Intrusion Detection.

The Internet of Things (IoT) and network-enabled smart devices are crucial to the digitally interconnected society of the present day. However, the increased reliance on IoT devices increases their susceptibility to malicious activities within network traffic, posing significant challenges to cybersecurity. As a result, both system administrators and end users are negatively affected by these malevolent behaviours. Intrusion-detection systems (IDSs) are commonly deployed as a cyber attack defence mechanism to mitigate such risks. IDS plays a crucial role in identifying and preventing cyber hazards within IoT networks. However, the development of an efficient and rapid IDS system for the detection of cyber attacks remains a challenging area of research. Moreover, IDS datasets contain multiple features, so the implementation of feature selection (FS) is required to design an effective and timely IDS. The FS procedure seeks to eliminate irrelevant and redundant features from large IDS datasets, thereby improving the intrusion-detection system's overall performance. In this paper, we propose a hybrid wrapper-based feature-selection algorithm that is based on the concepts of the Cellular Automata (CA) engine and Tabu Search (TS)-based aspiration criteria. We used a Random Forest (RF) ensemble learning classifier to evaluate the fitness of the selected features. The proposed algorithm, CAT-S, was tested on the TON_IoT dataset. The simulation results demonstrate that the proposed algorithm, CAT-S, enhances classification accuracy while simultaneously reducing the number of features and the false positive rate.