In today’s dynamic financial environment, bank loan approval systems are crucial for determining credit accessibility and maintaining economic stability. Efficient and accurate mechanisms help financial institutions minimize risks, enhance customer satisfaction, and make informed lending decisions. Traditional evaluation methods, however, often struggle with complex applicant data, underscoring the need for advanced, data‐driven approaches. This study proposes an enhanced loan approval prediction framework that integrates SHAP‐guided feature selection and LIME‐based interpretability within a robust multiclassifier architecture. The methodology includes extensive data preprocessing, handling missing values, and encoding categorical variables, followed by SHAP to identify the most influential features. Using two Kaggle datasets, logistic regression achieved the highest performance, with 86.17% accuracy and 81% AUC on Dataset 1 and 99.06% accuracy on Dataset 2. LIME provided intuitive, visual explanations of model predictions, fostering transparency and trust. In addition, a user‐friendly, real‐time web application was developed for practical deployment. Overall, the study advances intelligent, interpretable, and efficient loan approval systems for modern banking.

The growing adoption of network technologies, particularly the Internet of Things (IoT), has led to the emergence of new and increasingly complex cyberattacks. To protect critical infrastructure from these evolving threats, it is essential to implement Intrusion Detection Systems (IDS) capable of accurately detecting a wide range of attacks while minimizing false alarms. While machine learning has been widely applied in IDS, most approaches rely on flat multi-class classification to distinguish between normal traffic and various attack types. However, cyberattacks often exhibit a hierarchical structure, where granular attack subtypes can be grouped under broader high-level categories—an aspect largely underexplored in IDS research. In this paper, we investigate the effectiveness of hierarchical classification in the context of IDS. We propose a three-level hierarchical classification model: the first level distinguishes between benign and attack traffic; the second level categorizes coarse-grained attack types; and the third level identifies specific, fine-grained attack subtypes. Our experimental evaluation, conducted using 10 different machine learning classifiers across 10 contemporary IDS datasets, reveals that hierarchical and flat classification approaches achieve comparable performance in terms of overall accuracy, precision, recall, and F1-score. However, flat classifiers are more likely to misclassify attack traffic as normal, whereas the hierarchical approach tends to misclassify one attack type as another. This distinction is critical, as failing to identify an attack altogether poses a greater risk to cybersecurity than incorrectly labeling its type. Thus, our findings highlight the value of hierarchical classification in enhancing the robustness of IDS, especially in environments where minimizing false negatives is paramount.

As Industry 5.0 emerges, the convergence of advanced technologies like the Internet of Things (IoT) and blockchain is vital in shaping the future of industrial automation. Industry 5.0 emphasizes the collaborative relationship between humans and machines, requiring robust, decentralized systems to ensure security, accountability, and trust in interconnected ecosystems. Currently, IoT data processing is cloud-centric, which introduces challenges like fragmented data silos, limiting the potential for seamless and secure real-time analytics. Blockchain technology offers a solution by providing a decentralized and transparent ledger that can enhance data integrity and security across IoT applications. This study investigates the integration of blockchain with the IoT in the context of Industry 5.0, highlighting the potential for improved data management, security, and human-machine collaboration. By conducting a comprehensive analysis of IoT application designs and blockchain platforms, we evaluate existing literature to uncover the challenges, benefits, and limitations of this integration. Our research contributes by proposing a framework for selecting optimal blockchain platforms for IoT applications in Industry 5.0, providing actionable recommendations for enhanced data trust and resilience. Future research directions are also outlined to address the evolving demands of this technological convergence, ensuring that IoT ecosystems are secure, scalable, and human-centered in the era of Industry 5.0.

In today’s digital age, our dependence on IoT (Internet of Things) and IIoT (Industrial IoT) systems has grown immensely, which facilitates sensitive activities such as banking transactions and personal, enterprise data, and legal document exchanges. Cyberattackers consistently exploit weak security measures and tools. The Network Intrusion Detection System (IDS) acts as a primary tool against such cyber threats. However, machine learning-based IDSs, when trained on specific attack patterns, often misclassify new emerging cyberattacks. Further, the limited availability of attack instances for training a supervised learner and the ever-evolving nature of cyber threats further complicate the matter. This emphasizes the need for an adaptable IDS framework capable of recognizing and learning from unfamiliar/unseen attacks over time. In this research, we propose a one-class classification-driven IDS system structured on two tiers. The first tier distinguishes between normal activities and attacks/threats, while the second tier determines if the detected attack is known or unknown. Within this second tier, we also embed a multi-classification mechanism coupled with a clustering algorithm. This model not only identifies unseen attacks but also uses them for retraining them by clustering unseen attacks. This enables our model to be future-proofed, capable of evolving with emerging threat patterns. Leveraging one-class classifiers (OCC) at the first level, our approach bypasses the need for attack samples, addressing data imbalance and zero-day attack concerns and OCC at the second level can effectively separate unknown attacks from the known attacks. Our methodology and evaluations indicate that the presented framework exhibits promising potential for real-world deployments.

Due to its nature of dynamic, mobility, and wireless data transfer, the Internet of Vehicles (IoV) is susceptible to a wide range of cyber threats, including spoofing, Distributed Denial of Service (DDoS) attacks, and malware. intrusion detection systems (IDS) play a vital role in protecting the IoV ecosystem by continuously monitoring network traffic to detect and respond to intrusions, malicious activities, and policy violations in real time. However, most existing research has focused on centralized, machine learning (ML)-based IDS solutions for IoV, often overlooking its inherently distributed architecture. Due to their high computational demands, these centralized systems often depend on Cloud resources to detect cyber threats, which can lead to increased response delays. On the other hand, Edge nodes typically lack the necessary resources to train and deploy complex ML and deep learning algorithms. To address this issue, this article proposes an effective hierarchical classification framework designed for IoV networks. Hierarchical classification enables classifiers to be trained and deployed across multiple levels. This allows Edge nodes to independently identify specific types of attacks. With this approach, Edge nodes can conduct targeted attack detection while utilizing Cloud nodes for more comprehensive threat analysis and coordination. Considering the resource limitations of Edge nodes, we employ the Boruta feature selection method to reduce data dimensionality and enhance processing efficiency. To evaluate our proposed framework, we utilize the latest IoV security dataset CIC-IoV2024 and CIC-DDoS2019 datasets, achieving promising results that demonstrate the feasibility and effectiveness of our models in securing IoV networks. This hierarchical framework might improve the scalability and responsiveness of intrusion detection in distributed IoV environments. By offloading lightweight detection tasks to Edge nodes and reserving deeper analysis for the Cloud, the model can reduce latency and network load, making real-time threat response more feasible. The proposed approach can offer a practical solution for deploying effective, resource-aware cybersecurity mechanisms in real-world vehicular networks, where traditional centralized systems fall short.

Nowadays, to accommodate the swift expansion of cloud computing, big data, and other emerging technologies, integrating data center networks and SDN (Software Defined Network) is suggested, which also improves the network management’s convenience and flexibility. As network devices in these data centers continue to increase at a high rate, efficient route management to handle these devices’ vast amounts of data has emerged as a significant concern. This work suggests a novel admission and routing scheme considering the importance or priorities of the network flows, path energy, and routing path load. Using the SDN paradigm in DCN (Data Center Network), we first develop a Mixed Integer Linear Programming (MILP) formulation by jointly considering flow priority, path energy, and path load. The MILP formulation can maximize the number of flows as well as minimize the energy consumption and load variance in the network, or it can make a trade-off among all three. However, due to the potentially long running time, later, we introduce two greedy methods, Priority Based Energy Minimization Algorithm (PEMA) and Priority Based Evenly Load Distribution Algorithm (PEDL), where PEMA aims to maximize the flow with less energy, and PEDL focuses on maximizing the flow with reduced load variation. Finally, the developed routing strategies are implemented, and the simulation results demonstrate the out-performance of our work compared to the existing works in terms of successful flow ratio, energy savings, and load balancing.

Abstract Financial institutions and businesses face an ongoing challenge from fraudulent transactions, prompting the need for effective detection methods. Detecting credit card fraud is crucial for identifying and preventing unauthorized transactions. While credit card fraud incidents are relatively rare, they can result in substantial financial losses, particularly due to the high monetary value associated with fraudulent transactions. Timely detection of fraud enables investigators to take swift actions to mitigate further losses. However, the investigation process is often time-consuming, limiting the number of alerts that can be thoroughly examined each day. Therefore, the primary objective of a fraud detection model is to provide accurate alerts while minimizing false alarms and missed fraud cases. In this paper, we introduce a state-of-the-art hybrid ensemble (ENS) dependable machine learning (ML) model that intelligently combines multiple algorithms with proper weighted optimization using grid search, including decision tree (DT), random forest (RF), K-nearest neighbor (KNN), and multilayer perceptron (MLP), to enhance fraud identification. To address the data imbalance issue, we employ the instant hardness threshold (IHT) technique in conjunction with logistic regression (LR), surpassing conventional approaches. Our experiments are conducted on a publicly available credit card dataset comprising 284,807 transactions. The proposed model achieves impressive accuracy rates of 99.66%, 99.73%, 98.56%, and 99.79%, and a perfect 100% for the DT, RF, KNN, MLP and ENS models, respectively. The hybrid ensemble model outperforms existing works, establishing a new benchmark for detecting fraudulent transactions in high-frequency scenarios. The results highlight the effectiveness and reliability of our approach, demonstrating superior performance metrics and showcasing its exceptional potential for real-world fraud detection applications.

Brain tumors significantly impact human health due to their complexity and the challenges in early detection and treatment. Accurate diagnosis is crucial for effective intervention, but existing methods often suffer from limitations in accuracy and efficiency. To address these challenges, this study presents a novel deep learning (DL) approach utilizing the EfficientNet family for enhanced brain tumor classification and detection. Leveraging a comprehensive dataset of 3064 T1‐weighted CE MRI images, our methodology incorporates advanced preprocessing and augmentation techniques to optimize model performance. The experiments demonstrate that EfficientNetB(07) achieved 99.14%, 98.76%, 99.07%, 99.69%, 99.07%, 98.76%, 98.76%, and 99.07% accuracy, respectively. The pinnacle of our research is the EfficientNetB3 model, which demonstrated exceptional performance with an accuracy rate of 99.69%. This performance surpasses many existing state‐of‐the‐art (SOTA) techniques, underscoring the efficacy of our approach. The precision of our high‐accuracy DL model promises to improve diagnostic reliability and speed in clinical settings, facilitating earlier and more effective treatment strategies. Our findings suggest significant potential for improving patient outcomes in brain tumor diagnosis.

Brain tumors are among the most fatal and devastating diseases, often resulting in significantly reduced life expectancy. An accurate diagnosis of brain tumors is crucial to devise treatment plans that can extend the lives of affected individuals. Manually identifying and analyzing large volumes of MRI data is both challenging and time-consuming. Consequently, there is a pressing need for a reliable deep learning (DL) model to accurately diagnose brain tumors. In this study, we propose a novel DL approach based on transfer learning to effectively classify brain tumors. Our novel method incorporates extensive pre-processing, transfer learning architecture reconstruction, and fine-tuning. We employ several transfer learning algorithms, including Xception, ResNet50V2, InceptionResNetV2, and DenseNet201. Our experiments used the Figshare MRI brain tumor dataset, comprising 3,064 images, and achieved accuracy scores of 99.40%, 99.68%, 99.36%, and 98.72% for Xception, ResNet50V2, InceptionResNetV2, and DenseNet201, respectively. Our findings reveal that ResNet50V2 achieves the highest accuracy rate of 99.68% on the Figshare MRI brain tumor dataset, outperforming existing models. Therefore, our proposed model’s ability to accurately classify brain tumors in a short timeframe can aid neurologists and clinicians in making prompt and precise diagnostic decisions for brain tumor patients.

Abstract Alzheimer's disease, often known as dementia, is a severe neurodegenerative disorder that causes irreversible memory loss by destroying brain cells. People die because there is no specific treatment for this disease. Alzheimer's is most common among seniors 65 years and older. However, the progress of this disease can be reduced if it can be diagnosed earlier. Recently, artificial intelligence has instilled hope in the diagnosis of Alzheimer's disease by performing sophisticated analyses on extensive patient datasets, enabling the identification of subtle patterns that may elude human experts. Researchers have investigated various deep learning and machine learning models to diagnose this disease at an early stage using image datasets. In this paper, a new Deep learning (DL) methodology is proposed, where MRI images are fed into the model after applying various pre‐processing techniques. The proposed Alzheimer's disease detection approach adopts transfer learning for multi‐class classification using brain MRIs. The MRI Images are classified into four categories: mild dementia (MD), moderate dementia (MOD), very mild dementia (VMD), and non‐dementia (ND). The model is implemented and extensive performance analysis is performed. The finding shows that the model obtains 97.31% accuracy. The model outperforms the state‐of‐the‐art models in terms of accuracy, precision, recall, and F‐score.

Electronic payment methods have become increasingly popular for business transactions, both online and in-person, across the globe. Anomalies like online fraud and default payments, which can result in substantial financial losses, have become more common as the usage of credit cards in online purchases has increased. To address this issue, researchers have explored various machine learning models and their ensemble techniques for detecting anomalies in credit card transaction data. However, detecting anomalies in this data can be challenging due to overlapping class samples and an imbalanced class distribution. Therefore, the detection rate of anomalies from minority class samples is relatively low, and general learning algorithms can be biased towards the majority class samples. In this paper, we propose a model called Credit Card Anomaly Detection (CCAD) that leverages the base learners paradigm and meta-learning ensemble techniques to improve the detection rate of credit card anomalies. We utilize four outlier detection algorithms as base learners and XGBoost algorithm as meta learner in the proposed stacked ensemble approach to detect anomaly in credit card transactions. We apply stratified sampling technique and k-fold cross-validation process to address the issues of data imbalance and overfitting. In addition, the discordance rate is calculated to enhance the accuracy of ensemble learning performances. The proposed model is trained and tested using two datasets: CCF (Credit Card Fraud) and CCDP (Credit Card Default Payment). Experimental results demonstrate that our approach outperforms existing approaches, particularly in detecting anomalies from the minority class instances of these datasets.

Conventional Internet of Things (IoT) ecosystems involve data streaming from sensors, through Fog devices to a centralized Cloud server. Issues that arise include privacy concerns due to third party management of Cloud servers, single points of failure, a bottleneck in data flows and difficulties in regularly updating firmware for millions of smart devices from a point of security and maintenance perspective. Blockchain technologies avoid trusted third parties and safeguard against a single point of failure and other issues. This has inspired researchers to investigate blockchain’s adoption into IoT ecosystem. In this paper, recent state-of-the-arts advances in blockchain for IoT, blockchain for Cloud IoT and blockchain for Fog IoT in the context of eHealth, smart cities, intelligent transport and other applications are analyzed. Obstacles, research gaps and potential solutions are also presented.

Abstract Anomaly detection has been an essential and dynamic research area in the data mining. A wide range of applications including different social medias have adopted different state-of-the-art methods to identify anomaly for ensuring user’s security and privacy. The social network refers to a forum used by different groups of people to express their thoughts, communicate with each other, and share the content needed. This social networks also facilitate abnormal activities, spread fake news, rumours, misinformation, unsolicited messages, and propaganda post malicious links. Therefore, detection of abnormalities is one of the important data analysis activities for the identification of normal or abnormal users on the social networks. In this paper, we have developed a hybrid anomaly detection method named DT-SVMNB that cascades several machine learning algorithms including decision tree (C5.0), Support Vector Machine (SVM) and Naïve Bayesian classifier (NBC) for classifying normal and abnormal users in social networks. We have extracted a list of unique features derived from users’ profile and contents. Using two kinds of dataset with the selected features, the proposed machine learning model called DT-SVMNB is trained. Our model classifies users as depressed one or suicidal one in the social network. We have conducted an experiment of our model using synthetic and real datasets from social network. The performance analysis demonstrates around 98% accuracy which proves the effectiveness and efficiency of our proposed system.

Blockchain technologies emerging for healthcare support secure health data sharing with greater interoperability among different heterogeneous systems. However, the collection and storage of data generated from Body Area Sensor Net-works(BASN) for migration to high processing power computing services requires an efficient BASN architecture. We present a decentralized BASN architecture that involves devices at three levels; 1) Body Area Sensor Network-medical sensors typically on or in patient's body transmitting data to a Smartphone, 2) Fog/Edge, and 3) Cloud. We propose that a Patient Agent(PA) replicated on the Smartphone, Fog and Cloud servers processes medical data and execute a task offloading algorithm by leveraging a Blockchain. Performance analysis is conducted to demonstrate the feasibility of the proposed Blockchain leveraged, distributed Patient Agent controlled BASN.

Blockchain emerging for healthcare provides a secure, decentralized and patient driven record management system. However, the storage of data generated from IoT devices in remote patient management applications requires a fast consensus mechanism. In this paper, we propose a lightweight consensus mechanism and a decentralized patient software agent to control a remote patient monitoring (RPM) system. The decentralized RPM architecture includes devices at three levels; 1) Body Area Sensor Network- medical sensors typically on or in patient's body transmitting data to a Smartphone, 2) Fog/Edge, and 3) Cloud. We propose that a Patient Agent(PA) software replicated on the Smartphone, Fog and Cloud servers processes medical data to ensure reliable, secure and private communication. Performance analysis has been conducted to demonstrate the feasibility of the proposed Blockchain leveraged, distributed Patient Agent controlled remote patient monitoring system.