Explore the vast range of titles available.

The quick proliferation of pandemic diseases has been imposing many concerns on the international health infrastructure. To combat pandemic diseases in smart cities, Artificial Intelligence of Things (AIoT) technology, based on the integration of artificial intelligence (AI) with the Internet of Things (IoT), is commonly used to promote efficient control and diagnosis during the outbreak, thereby minimizing possible losses. However, the presence of multi-source institutional data remains one of the major challenges hindering the practical usage of AIoT solutions for pandemic disease diagnosis. This paper presents a novel framework that utilizes multi-site data fusion to boost the accurateness of pandemic disease diagnosis. In particular, we focus on a case study of COVID-19 lesion segmentation, a crucial task for understanding disease progression and optimizing treatment strategies. In this study, we propose a novel multi-decoder segmentation network for efficient segmentation of infections from cross-domain CT scans in smart cities. The multi-decoder segmentation network leverages data from heterogeneous domains and utilizes strong learning representations to accurately segment infections. Performance evaluation of the multi-decoder segmentation network was conducted on three publicly accessible datasets, demonstrating robust results with an average dice score of 89.9% and an average surface dice of 86.87%. To address scalability and latency issues associated with centralized cloud systems, fog computing (FC) emerges as a viable solution. FC brings resources closer to the operator, offering low latency and energy-efficient data management and processing. In this context, we propose a unique FC technique called PANDFOG to deploy the multi-decoder segmentation network on edge nodes for practical and clinical applications of automated COVID-19 pneumonia analysis. The results of this study highlight the efficacy of the multi-decoder segmentation network in accurately segmenting infections from cross-domain CT scans. Moreover, the proposed PANDFOG system demonstrates the practical deployment of the multi-decoder segmentation network on edge nodes, providing real-time access to COVID-19 segmentation findings for improved patient monitoring and clinical decision-making.

The rapid adoption of the Industrial Internet of Things (IIoT) model has exposed methods to inadequate security measures. False data injection attacks (FDIAs) pose a significant security threat in IIoT, as they aim to mislead industrial platforms by manipulating sensor readings. In IIoT, owing to the data attacker’s changeability, the FDIA is the most critical intrusion network. As aggressive devices permitted in the network perform their typical data-collecting tasks, identifying an FDIA becomes a nontrivial effort due to potential attacks. Conventional attack detection models have proven insufficient in addressing FDIAs, and most current countermeasures focus on the need to legalise data, primarily in the context of data clustering services. Presently, deep learning (DL) systems are employed for detecting FDIA in real-time and supply personalised protective measures to the threat. This paper presents an Intelligent Management of False Data Injection Attacks Using Feature Selection and Voting Classifier (IMFDIA-FSVC) technique in IIoT systems. The primary purpose of the IMFDIA-FSVC technique is to develop a model for detecting and mitigating FDIAs to ensure safe and trustworthy operations of IIoT systems. Initially, the data pre-processing stage involves two stages: missing value analysis and normalisation to standardise the input data for an effective study. For an effective feature selection, the IMFDIA-FSVC model utilises a statistical and information-theoretic selection (SITS) technique to select optimal features from the input data. Finally, the classification process is mainly deployed by three models: the temporal convolutional network (TCN), the deep belief network (DBN), and the autoencoder (AE). An ensemble classifier is then performed using the voting classifier. The comparison study of the IMFDIA-FSVC method showed a superior accuracy value of 99.15% compared to existing models on the IIoT and FDIA datasets.

One of the utmost frequently emerging neurodegenerative diseases, Parkinson’s disease (PD) must be comprehended through the forfeit of dopamine (DA)-generating nerve cells in the substantia nigra pars compacta (SN-PC). The etiology and pathogenesis underlying the emergence of PD is still obscure. However, expanding corroboration encourages the involvement of genetic and environmental factors in the etiology of PD. The destruction of numerous cellular components, namely oxidative stress, ubiquitin-proteasome system (UPS) dysfunction, autophagy-lysosome system dysfunction, neuroinflammation and programmed cell death, and mitochondrial dysfunction partake in the pathogenesis of PD. Present-day pharmacotherapy can alleviate the manifestations, but no therapy has been demonstrated to cease disease progression. Peroxisome proliferator-activated receptors (PPARs) are ligand-directed transcription factors pertaining to the class of nuclear hormone receptors (NHR), and are implicated in the modulation of mitochondrial operation, inflammation, wound healing, redox equilibrium, and metabolism of blood sugar and lipids. Numerous PPAR agonists have been recognized to safeguard nerve cells from oxidative destruction, inflammation, and programmed cell death in PD and other neurodegenerative diseases. Additionally, various investigations suggest that regular administration of PPAR-activating non-steroidal anti-inflammatory drugs (NSAIDs) (ibuprofen, indomethacin), and leukotriene receptor antagonists (montelukast) were related to the de-escalated evolution of neurodegenerative diseases. The present review elucidates the emerging evidence enlightening the neuroprotective outcomes of PPAR agonists in in vivo and in vitro models experiencing PD. Existing articles up to the present were procured through PubMed, MEDLINE, etc., utilizing specific keywords spotlighted in this review. Furthermore, the authors aim to provide insight into the neuroprotective actions of PPAR agonists by outlining the pharmacological mechanism. As a conclusion, PPAR agonists exhibit neuroprotection through modulating the expression of a group of genes implicated in cellular survival pathways, and may be a propitious target in the therapy of incapacitating neurodegenerative diseases like PD.

The automatic detection of student behaviors is essential for improving smart classroom technologies and offering data-driven insights regarding student engagement. Nevertheless, existing methods encounter considerable obstacles caused by class imbalance, restricted annotations, and the slight visual resemblances among behavior categories. To overcome these constraints, we present a meta-learning framework that combines Vision Transformers with Prototypical Networks, improved by supervised contrastive learning and hard negative mining. The process starts by preprocessing and cropping the input images, utilizing YAML annotations to focus on behavior-specific areas. Every input is converted into patch embeddings and handled by Transformer encoders, producing distinctive feature representations. Class prototypes are subsequently derived from the support set, and query samples are categorized through distance-based metrics within a few-shot learning framework based on episodes. Extensive experiments were carried out on the SCB-05 dataset under 5-way few-shot settings to confirm the effectiveness of the proposed framework. The findings show that combining Vision Transformers with contrastive learning greatly enhances feature distinctiveness, whereas hard negative mining additionally boosts generalization. Under the 5-way 10-shot evaluation protocol, our method attains a total accuracy of 91.3% and a mean Average Precision, exceeding the performance of both baseline ProtoNet and Transformer variants without hard negative mining. Further analyses, such as class-specific assessments, confusion matrices, and embedding visualizations, validate the strength and clarity of the suggested model. These results set a new standard for recognizing student behavior and emphasize the promise of meta-learning frameworks for practical uses in education.

Cardiovascular disease (CVD) is considered the number one killer disease in the world, underlining the importance of the application of more accurate diagnostic and therapeutic tools. Traditional screening procedures usually do not provide identification and guidance based on individual peculiarities that might result in less than beneficial results. This study seeks to create a hybrid computational framework that synergistically integrates a Support Vector Machine (SVM) classifier, a Particle Swarm Optimization (PSO) algorithm for hyperparameter tuning, and an AI-based interpretation module (SHapley Additive exPlanations, SHAP) to enable early diagnosis and risk assessment beyond various profiling of patients. A mathematical model was developed to provide the framework to deal with the diagnostic complexity of cardiovascular disease. Machine learning (ML) and AI techniques are then used to improve clinical decision-making. The proposed framework employs a variety of forms of patient data, namely electronic health records, medical images, and genomic data, to construct patient models. It utilizes advanced algorithms to enable accurate disease prognosis, identify high-risk individuals for early intervention, and facilitate personalized treatment strategies. This approach will help to eliminate the expense of ineffective therapies, shorten delays in care, and eventually improve patient outcomes and quality of life. Preliminary results on the MIMIC-III clinical database (v1.4) showed that the proposed framework performs better than previous methods by achieving higher accuracy 98.4%, precision 97.5%, recall 96.4%, F1 score 96.9%, and AUC-ROC 97.35%. Moreover, the sensitivity 96.4%, specificity 98.7%, and a low negative likelihood ratio (0.036) of the proposed framework demonstrate its ability and power in identifying high- and low-risk patients. The hybrid ML-AI framework provides an improved way for early detection of cardiovascular disease, which helps in personalizing treatments for patients. It also enables healthcare delivery through its combined predictive power to improve healthcare service.

Wireless Sensor Networks (WSNs) are one of the best technologies of the 21st century and have seen tremendous growth over the past decade. Much work has been put into its development in various aspects such as architectural attention, routing protocols, location exploration, time exploration, etc. This research aims to optimize routing protocols and address the challenges arising from conflicting objectives in WSN environments, such as balancing energy consumption, ensuring routing reliability, distributing network load, and selecting the shortest path. Many optimization techniques have shown success in achieving one or two objectives but struggle to achieve the right balance between multiple conflicting objectives. To address this gap, this paper proposes an innovative approach that integrates Particle Swarm Optimization (PSO) with a fuzzy multi-objective framework. The proposed method uses fuzzy logic to effectively control multiple competing objectives to represent its major development beyond existing methods that only deal with one or two objectives. The search efficiency is improved by particle swarm optimization (PSO) which overcomes the large computational requirements that serve as a major drawback of existing methods. The PSO algorithm is adapted for WSNs to optimize routing paths based on fuzzy multi-objective fitness. The fuzzy logic framework uses predefined membership functions and rule-based reasoning to adjust routing decisions. These adjustments influence PSO’s velocity updates, ensuring continuous adaptation under varying network conditions. The proposed multi-objective PSO-fuzzy model is evaluated using NS-3 simulation. The results show that the proposed model is capable of improving the network lifetime by 15.2%–22.4%, increasing the stabilization time by 18.7%–25.5%, and increasing the residual energy by 8.9%–16.2% compared to the state-of-the-art techniques. The proposed model also achieves a 15%–24% reduction in load variance, demonstrating balanced routing and extended network lifetime. Furthermore, analysis using p-values obtained from multiple performance measures (p-values < 0.05) showed that the proposed approach outperforms with a high level of confidence. The proposed multi-objective PSO-fuzzy model provides a robust and scalable solution to improve the performance of WSNs. It allows stable performance in networks with 100 to 300 nodes, under varying node densities, and across different base station placements. Computational complexity analysis has shown that the method fits well into large-scale WSNs and that the addition of fuzzy logic controls the power usage to make the system practical for real-world use.

Wireless sensor networks (WSNs) are essential in a wide range of applications, but the challenges of energy efficiency, load balancing, and optimal routing remain critical for ensuring long-term network reliability. In this study, we introduce a Modified Ant Colony Optimization Algorithm (MACOA) to address these challenges. The proposed MACOA lies in several key innovations to address the limitations of existing ACO-based and bio-inspired routing protocols. First, MACOA applies a multi-objective heuristic function to simultaneously optimize power consumption while ensuring reliability, bandwidth, and short path distances to achieve an efficient routing solution. Second, it introduces an adaptive pheromone decay mechanism that dynamically adjusts based on network conditions, such as node energy levels and link reliability, to prioritize energy-efficient paths. Third, MACOA incorporates a load-balancing factor that prevents the overloading of certain nodes, thus extending the network lifetime. Finally, it regulates the exploration–exploitation trade-off dynamically by promoting early-stage exploratory behavior and later-stage exploitative behavior during optimization. Together, these innovations enable MACOA to be an efficient routing protocol that outperforms current state-of-the-art algorithms. We compare the performance of the proposed MACOA with existing state-of-the-art techniques, such as Genetic Algorithms, Particle Swarm Optimization, Artificial Bee Colony, Deep Reinforcement Learning, and Energy Reliable ACO Routing Protocol (E-RARP) in terms of network lifetime, network stabilization time, energy efficiency, load balancing, and throughput. Extensive results demonstrate that the proposed method outperforms the compared techniques. They state the adaptability of the proposed MACOA to dynamic network conditions and its robustness to node failures, which make the proposed MACOA a promising solution for WSNs and qualify it as a potential solution to large-scale and power-limited WSNs.

Human activity recognition (HAR) is a fascinating and significant challenging task. Generally, the accuracy of HAR systems relies on the best features from the input frames. Mostly, the activity frames have the hostile noisy conditions that cannot be handled by most of the existing edge operators. In this paper, we have designed an adoptive feature extraction method based on edge detection for HAR systems. The proposed method calculates the direction of the edges under the presence of nonmaximum conquest. The benefits are in ease that depends upon the modest procedures, and the extension possibility is to determine other types of features. Normally, it is practical to extract extra low-level information in the form of features when determining the shapes and to get the appropriate information, the additional cultured shape detection procedure is utilized or discarded. Basically, this method enlarges the percentage of the product of the signal-to-noise ratio (SNR) and the highest isolation along with localization. During the processing of the frames, again some edges are demonstrated as a footstep function; the proposed approach might give better performance than other operators. The appropriate information is extracted to form feature vector, which further be fed to the classifier for activity recognition. We assess the performance of the proposed edge-based feature extraction method under the depth dataset having thirteen various kinds of actions in a comprehensive experimental setup.

Productivity and quality of food are crucial for populations around the world. However, food faces challenges due to the threats of fruit diseases, which lead to poor food quality. Therefore, early detection and classification of fruit diseases are important to help farmers detect and overcome these diseases, thereby improving food quality and productivity. One of the biggest challenges in the agriculture field is classifying and detecting fruit diseases using traditional manual visual grading. As a result, deep learning and computer vision models have emerged as new methods for visual grading, offering higher accuracy in classification and detection. This study proposes deep learning models for fruit disease detection and classification in the early stages. Five deep learning models are used: Convolutional Neural Network (CNN), DenseNet121, EfficientNetB3, Xception, and ResNet50. These models are applied to detect six types of fruit diseases, including orange, grape, mango, guava, apple, and banana plant diseases. Image preprocessing and data augmentation techniques were employed for image processing. The results show accuracies of 96.25%, 99.14%, 96.17%, 94.06%, 96.72%, and 99.33% for the CNN, EfficientNetB3, ResNet50, DenseNet121, ResNet50, and EfficientNetB3 models, respectively, for detecting orange, grape, mango, banana, guava, and apple plant diseases. We compared our models with other deep learning models, and the model that utilized image preprocessing and data augmentation techniques demonstrated higher accuracy and performance. We recommend the EfficientNetB3 model for fruit disease detection based on these results.

The development of green mines is essential for promoting sustainability in the mining sector due to the significant ecological impacts of resource extraction. This study proposes a novel hybrid multi-criteria decision-making (MCDM) framework that integrates Spherical Fuzzy Sets (SFSs) with SWOT analysis, the CRITIC method, and Grey Relational Analysis (GRA). The framework introduces several innovations: it applies SFS-based MCDM for the first time to green mine evaluation in Egypt, structures 37 sustainability-related criteria under SWOT dimensions, and employs SF-CRITIC for objective weighting without subjective comparisons. The model is applied to assess 20 gold mines, where the SF-GRA method is used to rank alternatives based on proximity to an ideal solution. The results show that GME20 consistently ranks highest, while GME5 ranks lowest. A sensitivity analysis is conducted by varying the Grey relational coefficient and simulating 37 weight scenarios, demonstrating stable rankings and strong model resilience. Comparative analysis against ten SFS-based MCDM methods confirms the consistency of results, with Spearman correlation coefficients exceeding 0.77. In addition to its methodological novelty, the framework supports interpretable decision outcomes by identifying key sustainability drivers such as renewable energy adoption and land reclamation. This contributes actionable insights for policymakers and stakeholders, enabling informed green investment and regulatory decisions. The study offers a transparent, reproducible, and scalable tool for sustainability evaluation in resource-intensive industries. The proposed model introduces a structured integration of SWOT-based criteria classification, objective weight computation via SF-CRITIC, and robust alternative ranking using SF-GRA. Furthermore, it contributes uniquely by applying the methodology to the underexplored context of green mine evaluation in Egypt. These distinctions articulate the methodological and application-based novelties of the proposed framework.