The integration of the Internet of Vehicles (IoV) with the Intelligent Transportation System (ITS) plays a significant role in ensuring safe and efficient traffic management. However, communication signals may encounter natural or artificial obstacles that result in uncovered road segments, where connectivity is lost. Even minor collisions in these unprotected areas can escalate into major incidents or traffic bottlenecks, especially when vehicles are traveling at high speeds on highways. Therefore, it is crucial to promptly inform the ITS of any adverse events occurring in these unnoticed areas. The importance of Store-Carry-Forward (SCF) techniques increases in such scenarios when uncovered patches exist and intervehicle distances exceed the communication range. Store-Carry-Forward (SCF) is a technique where vehicles temporarily store data and forward it when a connection is available. To address improved coverage and reduced latency using SCF, we propose a beacon-based Store-Carry-Forward Scheme to Deliver Emergency Messages via vehicle-to-vehicle (V2V) Communication for Highways (SCF-EMD). The proposed method aims to minimize congestion and delays in disseminating information about adverse events. It involves selecting high-mobility vehicles to travel across both covered and uncovered highway segments. The scheme integrates V2V and vehicle-to-infrastructure (V2I) communication to ensure rapid delivery of emergency alerts to ITS. SCF-EMD demonstrated significant improvements over existing schemes in Network Simulator (NS-3) , achieving over 10% , 16% and 5% gains in information coverage, end-to-end delay, and packet delivery ratio (PDR), respectively.

Pregnancy is an extraordinary journey marked by many bodily changes. One notable change is the rise in blood sugar levels, leading to a condition called gestational diabetes mellitus (GDM). It happens when the body struggles to produce or effectively use insulin during pregnancy. Several health risks of GDM highlight the critical need for accurate prediction and timely intervention. To address this, the study presents a predictive framework validated on a small real-world cohort dataset from a Brazilian public health setting. The core of this research is a composite predictive model that integrates a diverse ensemble of machine learning and deep learning algorithms. In order to enrich the training material, a function was created to generate new instances based on initial dataset records. The framework’s ability to combine the strengths of various models and leverage a meta-classifier for final predictions was rigorously tested across multiple datasets. The results demonstrate exceptional performance by achieving high AUC scores of 88.91

The rapid expansion of IoT, particularly wearable health monitoring devices, demands robust security to protect sensitive data against vulnerabilities and unauthorized access. However, ensuring security in resource-constrained medical IoT devices remains challenging due to limited processing power, memory, battery life, and security level. To address this, this work proposes Symmetric Wearable Encryption Algorithm for the Internet of Medical Things (SWEAT), a lightweight cryptographic scheme designed for secure data transfer in low-power wearable IoT devices. SWEAT introduces an efficient and optimized encryption mechanism with simplified key generation, random padding, and reduced encryption rounds, operating on a 128-bit block with a single-round design. The algorithm integrates seamlessly with fog nodes while ensuring data confidentiality and resistance against intruders. Experimental evaluation shows that SWEAT achieves competitive performance compared with the state-of-the-art Dynamic Light Weight Symmetric Encryption Algorithm (DLSEA) and Dynamic Lightweight Symmetric (DLS) algorithm, while significantly reducing computational cost and power consumption. These results highlight SWEAT as a secure, energy-efficient, and real-time solution for wearable healthcare monitoring applications.

High glucose levels during pregnancy cause Gestational Diabetes Mellitus (GDM). The risks include cesarean deliveries, long-term type 2 diabetes, fetal macrosomia, and infant respiratory distress syndrome. These risks highlight the need for accurate GDM prediction. This research proposes a novel fusion model for early GDM prediction. It uses conventional Machine Learning (ML) and advanced Deep Learning (DL) algorithms. Subsequently, it combines the strengths of both ML and DL algorithms using various ensemble techniques. It incorporates a meta-classifier that further reinforces its robust prediction performance. The dataset is split into training and testing sets in a 70/30 ratio. The initial steps involve exploratory analysis and data preprocessing techniques such as iterative imputation and feature engineering. Subsequently, oversampling is applied to the training set to address class imbalance which ensures the model learns effectively. The testing set remains imbalanced to maintain the credibility of the model’s performance evaluation. The fusion model achieves an accuracy of 98.21

Cognitive Radio Networks (CRNs) have become a prominent platform in recent years, particularly in the context of the Internet of Things (IoT) and Industry 5.0. CRNs include Primary Users (PUs) and Secondary Users (SUs). PUs are licensed users with priority over SUs for spectrum utilization. The growth rate of wireless devices is 40% annually. The available wireless spectrum is not quite enough to handle this immense growth rate. These facts makes channel assignment in CRNs as one of the highly explored research areas. In this study, we propose a cross-layer efficient routing protocol and channel selection algorithm for IoT named, an efficient Path setup and Fast Channel Switching (PFCS) for IoT-based Mobile Cognitive Radio Ad Hoc Networks (CRAHNs). PFCS evaluates multiple paths using various important network parameters and selects the path with minimal end-to-end channel switching and the highest score. Additionally, PFCS proposes a local channel recovery algorithm to handle PU activity through controlled broadcast. The recovery algorithm aims to resume ongoing communication with minimal control overhead. The proposed PFCS is compared with state-of-the-art, Software-Defined Routing Protocol (SDRP) and Optimal Channel Selection algorithm for CRahNs (OCSCRN) with varying numbers of PUs and SUs in Mobile Cognitive Radio Networks (MCRNs). Results demonstrate that PFCS outperforms SDRP and OCSCRN in terms of Delay, Packet Delivery Function (PDF), Routing overhead, and Network life.

The Internet of Things (IoT) represents a vast network of interconnected devices engaged in continuous data exchange, real-time information processing, and autonomous decision-making through the Internet. The pervasive presence of sensitive data on IoT devices highlights their indispensable role in our daily lives. The rapid evolution of Information and Communications Technology (ICT) has ushered in a new era of interconnected devices, reshaping the computing landscape. With the expanding IoT ecosystem, cyberspace has become increasingly susceptible to frequent cyber threats. While IoT devices have greatly simplified and automated daily tasks, these devices have simultaneously introduced significant security vulnerabilities. The existing inadequacies in safeguarding these smart devices have rendered IoT the most vulnerable entry point for potential breaches, posing a tempting target for malicious actors. In response to these critical challenges, our study introduces an innovative solution known as Swarm-based Inline Machine Learning (SIML). This approach leverages the coordinated data processing capabilities of a swarm to effectively address and counter emerging malware threats. SIML represents a divergence from conventional standalone threat detection systems, offering a promise of more robust, distributed, and end-to-end security solutions for IoT environments. This approach significantly reduces the risk of malicious exploitation of IoT devices for launching cyber-attacks. The effectiveness of our proposed method was validated through rigorous testing using the UNSW-NB15 dataset. The results are compelling, boasting an impressive accuracy rate of 93.7% and a precision rate of 95%, achieved through the application of the Gradient-Boosting Tree algorithm under the proposed framework. Our comparative analysis reveals that the Gradient Boosting algorithm outperforms traditional methods without compromising efficiency when deployed in an inline setting. Furthermore, the proposed method has been benchmarked against the BoT-Iot and Edge-IIoTset datasets, and outperformance is noted with a minor degradation at higher throughput. This innovative approach not only enhances security in IoT but also paves the way for a safer and more resilient digital future.

Fetal movements (FMs) are spontaneous actions performed by the fetus in the womb. Monitoring FMs is vital for assessing fetal health and detecting potential complications during pregnancy. Unmonitored fetal activity can indicate potential adverse effects such as fetal distress, restricted growth, or placental insufficiency. Regular monitoring helps detect issues early and ensures fetal health. FMs involve monitoring the frequency and force with which the baby kicks as well as the location of the kicks in the abdominal area. Monitoring of these parameters for a longer period gives details about fetal activity and its health. This article presents a novel fetus monitoring belt system designed to measure and analyze fetal kicks, its intensity, frequency, and the position where it occurred in abdomen. The system utilizes high accuracy thin-film pressure sensors strategically placed within a flexible and breathable belt to cover the entire abdominal area. The sensors operate by detecting changes in resistance caused by applied force due to fetus kicks and translate these changes into measurable electrical signals. The belt system integrates with a mobile application to offer real-time data visualization and analysis. Additionally, it tracks the temperature and position of the expecting mother using integrated sensors. This innovative system enables home-based monitoring and reduces the need for frequent visits to healthcare facilities and enhances maternal convenience. The belt's high sensitivity is capable of detecting forces ranging from 1.47 to 98.1 N. The belt is flexible and comfortable to wear. The fetus monitoring belt system can store and track data over time, which makes it a practical tool for continuous as well as remote monitoring. The fetus monitoring belt system offers convenience, accuracy, and comprehensive monitoring capabilities. The performance of the belt is evaluated by perceived fetus kicks and movements by volunteers and the comparison results proved significant accuracy of proposed belt system.

Protecting intellectual property (IP) in the digital age presents significant challenges due to rapid technological advancements and industrial growth. Traditional methods of registering and securing IP are becoming increasingly ineffective. To address these challenges, a more robust system is needed to control access, prevent unauthorized use, and safeguard digital rights. Despite efforts to transition from central registries to encrypted systems, vulnerabilities still exist that can compromise IP security. Therefore, a comprehensive solution must ensure legal use, prevent misuse, and enhance overall IP protection. This study introduces a robust framework designed to prioritize IP security and protection while addressing financial considerations. Our tiered Blockchain-based approach features logically segregated layers governed by smart contracts, which control access based on predefined agreements set by the IP owner. A common application interface (CAI) via smart contracts simplifies common operation with regard to an IP. The decentralized nature of Blockchain technology ensures unassailable trust, availability, and security. Additionally, we employ a flexible off-chain identity verification and storage mechanism for quick access and improved processing capabilities. Financial aspects tied to digital rights are managed through Blockchain's oracle services, ensuring seamless integration and management. Our integrated solution provides a reliable platform for IP protection, validated through thorough performance evaluations across diverse real-world scenarios. This framework demonstrates significant improvements in efficiency, security, and cost-effectiveness compared to traditional IP protection methods. By leveraging Blockchain's immutable ledger and decentralized network, we enhance the traceability and accountability of IP transactions, reinforcing legal compliance and reducing disputes. Ultimately, this approach ensures that IP is safeguarded, valued, and shared in a manner that benefits creators, consumers, and society as a whole. The rigorous analysis showed significant enhancements in process optimization, technology adoption, efficiency, and cost reduction compared to traditional IP rights protection practices.

The recent surge in Internet of Things (IoT) applications and smart devices has led to a substantial rise in the data generation. One of the major issues involved is to meet strict quality of service (QoS) requirements for computing these applications in terms of execution time, cost and in an energy-efficient manner. To extract useful information, fast processing and analysis of data is needed. Consequently, moving all the data to centralized cloud data centers would lead to high processing times, increased cost and energy consumption and more bandwidth usage; thus, processing of applications with strict latency requirements becomes challenging. The addition of fog layer between cloud and IoT devices has provided promising solutions to such issues. However, efficient employment of computing resources in the hybrid infrastructure of fog and cloud nodes is of great significance and demands an optimal scheduling strategy. Toward this direction, a novel Pareto-based algorithm in fog computing, namely energy-efficient time and cost (ETC) constraint scheduling algorithm, is introduced in this paper for scheduling workflow applications. ETC attempts to optimize monetary cost along with time and energy objectives. Improved multi-objective differential evolution (I-MODE) meta-heuristic is introduced and incorporated with deadline-aware stepwise frequency scaling approach that is based on our previously proposed energy makespan multi-objective optimization (EM-MOO) algorithm. Synthetic and real-world application workflows are used to conduct evaluation of the proposed work with existing well-known algorithms from the literature. The experimental results for synthetic workflows reveal that the proposed algorithm lessens energy utilization by 14–21

With the recent advancements in conversational artificial intelligence (AI), the practical applications of chatbots have risen significantly in diverse domains such as healthcare, education, e-government, customer support systems, social platforms, and entertainment. The chatbot converses with humans in natural language and responds to their queries with precise and relevant answers. The relevant literature presents several methods for intent classification and slot mapping for chatbot question answering. However, the existing chatbot architectures still suffer from few-shot learning problem (imbalance ratio of class labels over samples) and ineffective dialog management to retain the context and slots mapping. This study aims to introduce the architecture of chatbot by focusing few-shot learning problem and context management in dialog-based conversations. First, to mitigate the few-shot learning problem with chatbots, we propose a novel hybrid intent and slots transformers (HIST) model. The HIST chatbot architecture utilizes transformers and self-attention mechanisms along with bigated recurrent unit and combines conditional random field algorithms for intent classification and slot extraction. Second, to address dialog management, we introduce a hybrid interaction strategy for slots mapping and effective conversational context management. To validate the proposed model's effectiveness, comprehensive empirical analysis is carried out using three benchmark datasets including airline travel information system (ATIS), banking77, and conversational language interface for natural conversation 150 (CLINC150). The results show that HIST outperforms against the state-of-the-art existing methods with a clear margin and obtained an accuracy of 94.89% and 96.17% for intent classification and slots extraction, respectively. The empirical results confirm the effectiveness of the HIST chatbot for resolving the few-shot learning problem with effective dialog management in chatbot systems.

Strokes are a leading global cause of mortality, underscoring the need for early detection and prevention strategies. However, addressing hidden risk factors and achieving accurate prediction become particularly challenging in the presence of imbalanced and missing data. This study encompasses three imputation techniques to deal with missing data. To tackle data imbalance, it employs the synthetic minority oversampling technique (SMOTE). The study initiates with a baseline model and subsequently employs an extensive range of advanced models. This study thoroughly evaluates the performance of these models by employing k-fold cross-validation on various imbalanced and balanced datasets. The findings reveal that age, body mass index (BMI), average glucose level, heart disease, hypertension, and marital status are the most influential features in predicting strokes. Furthermore, a Dense Stacking Ensemble (DSE) model is built upon previous advanced models after fine-tuning, with the best-performing model as a meta-classifier. The DSE model demonstrated over 96% accuracy across diverse datasets, with an AUC score of 83.94% on imbalanced imputed dataset and 98.92% on balanced one. This research underscores the remarkable performance of the DSE model, compared to the previous research on the same dataset. It highlights the model's potential for early stroke detection to improve patient outcomes.

Internet of Vehicle (IoV) dominates the traditional concept of Vehicular Ad-hoc Network (VANET) to boost the capabilities of Intelligent Transportation System (ITS). Frequent deployment of high-speed vehicles with more enhanced features by vehicle manufacturers expands the variety of challenges for ITS. This technological enhancement enables vehicles to exchange information across other vehicles and existing communication infrastructures. When a vehicle detects any critical trouble, it transmits an emergency message (EM) to nearby vehicles and to the traffic control office as an alert message to take necessary actions. The main issue is congestion if each vehicle is authorized to broadcast warning messages constantly. This congestion may lead to delays in the transmission of critical emergency messages with the redundant receiving of the same EM at the traffic control office. In our proposed scheme, called Beacon-oriented Emergency Message Dissemination (BEMD), we proposed a novel technique to enhance coverage and distribution of EM with the least delay. We aim to implement beacon-oriented communication for traffics with high mobility and sparse density on highways. We furthermore fixated on the least dependence of density on EM dissemination. As compared to the latest existing schemes, BEMD shows enhanced simulated results of more than 13%, 26% and 4% in terms of information coverage, delay and packet distribution ratio (PDR) respectively.

Abstract The authors have requested that this preprint be removed from Research Square.

Electroencephalogram (EEG) signals, inherently non-stationary and non-linear, present significant challenges in their processing and interpretation. This paper presents a hybrid mode selection approach using two advanced decomposition methods: Empirical Mode Decomposition (EMD) and Variational Mode Decomposition (VMD), to analyze these signals, targeting their application in the classification of upper limb complex movements for enhanced prosthetic limb control and rehabilitation therapy assessment. Using optimized statistical features extracted from selected modes, Intrinsic mode functions (IMFs) via EMD and modes via VMD, we seek to better distinguish neural activities in pre-movement EEG signal. Our methodology involves the following two strategies: straightforward extraction of statistical features from modes yielded by EMD and VMD; a genetic algorithm (GA) feature selection technique to select the most optimal set from these statistical features. These derived features train machine learning (ML) classifiers to differentiate limb movements. The results, derived from proprietary dataset from Aalborg University, Denmark, comprising five distinct upper limb movements, demonstrate the effectiveness of our hybrid approach. The usage of EMD and VMD significantly enhanced the discriminatory power of the extracted features, leading to improved classification performance. Furthermore, our hybrid approach yielded classification accuracies of 93.1 % and 95.6% with EMD and VMD respectively when the K-NN classifier was deployed with a 10-fold cross-validation. K-NN classifier outperformed traditional ML classifiers in terms of computational time, highlighting its potential as lightweight yet robust algorithm for classification of complex movements. The primary goal is to present and validate a hybrid mode (IMFs/modes) selection approach through EMD and VMD to analyze EEG signals associated with upper limb complex movements.

The popularity of cloud and fog services has raised the number of users exponentially. Main advantage of Cloud/fog infrastructure and services are crucial specially for commercial users from diverse areas. The variety of service requests with different deadlines makes the task of a service broker challenging. The fog and cloud users always lookfor a suitable compromise between cost and quality of service in terms of response time therefore, the cost optimization is vital for the cloud/fog service providers to capture the market. In this paper an algorithm, Cost Optimization in the cloud/fog environment based on Task Deadline (COTD) is proposed that optimizes cost without compromising the response time. In this algorithm the task deadline is considered as a constraint and an appropriate data center for task processing is selected. The proposed algorithm is suitable for runtime decision making due to its low complexity. The proposed algorithm is evluated using a well-known simulation tool Cloud Analyst. Our comprehensive testbed simulations show that COTD outperforms the existing schemes, Service Proximity Based Routing and Performance-Optimized Routing. The proposed algorithm successfully minimizes the cost by 35% on average while maintaining the response time.

The concept of the internet of things (IoT) motivates us to connect bulk isolated heterogeneous devices to automate report generation without human interaction. Energy-efficient routing algorithms help to prolong the network lifetime of these energy-restricted smart devices that are connected by means of wireless sensor networks (WSNs). Current vendor-level advancements enable algorithm-level flexibility to design protocols to concurrently collect multiple application data while enforcing the reduction of energy expenditure to gain commercial success in the industrial stage. In this paper, we propose a hybrid clustering and routing algorithm with threshold-based data collection for heterogeneous wireless sensor networks. In our proposed model, homogeneous and heterogeneous nodes are deployed within specific regions. To reduce unnecessary data transmission, threshold-based conditions are presented to prevent unnecessary transmission when minor or no change is observed in the simulated and real-world applications. We further extend our proposed multi-hop model to achieve more network stability in dense and larger network areas. Our proposed model shows enhancement in terms of load balancing and end-to-end delay as compared to the other threshold-based energy-efficient routing protocols, such as the threshold-sensitive stable election protocol (TSEP), threshold distributed energy-efficient clustering (TDEEC), low-energy adaptive clustering hierarchy (LEACH), and energy-efficient sensor network (TEEN).

Abstract The task of a service broker in a cloud computing environment is vital and challenging. Several sophisticated techniques have been proposed to improve the overall performance and minimize the cost. Most of the approaches optimize either performance or the cost; however, the users of cloud and fog need the best compromise for both. In this paper, we propose a hybrid technique that is Cost Optimization in the cloud/fog environment based on Task Deadline (COTD) that focuses on both parameters simultaneously and maintains the Quality of Service. The proposed algorithm is based on the task deadline and selects the most appropriate data center for task processing. We have implemented and tested COTD on a well-known simulation tool Cloud Analyst. Our comprehensive testbed experiments and simulations show that COTD outperforms comparable with Service Proximity Based Routing and Performance-Optimized Routing, and successfully minimizes an average of 35% cost while maintaining the same response time.