Search

IoT is a groundbreaking technology that enables wireless interoperability between devices without human intervention. It has become an integral part of human life and has made significant advancements in the automotive industry. The combination of vehicular networks and IoT has opened up new possibilities but has also led to challenges such as degraded QoS (Quality of Service), network congestion, packet loss, transmission delay, intrusions, etc. These problems are also apparent in vehicular health monitoring systems. To overcome such challenges, it is necessary to develop an intricate framework that can address them all. TCP/IP is a five-layer-based standardized communication protocol that facilitates communication between devices over the internet. Unique network protocols and functions are authorized to each of the five layers. In this paper, a comprehensive survey is done on all the recent studies on the five communication layer protocols, their functionalities, and practical challenges associated with each of them for an intra-vehicular health monitoring system (IVHMS). Analyzing them, a novel taxonomy is also proposed with visual representation. In the end, this paper proposes a cross-layer-based framework to address communication-related complexities. This cross-layer model aims to integrate all the dynamic capabilities of the five protocol layers (Application, Transport, Network, Data Link & Physical) and resolve issues within each layer by implementing functionalities of other layer protocols. Future research scopes and possibilities of the proposed system are also discussed.

With the increasing prevalence of multi-user, multi-service, and heterogeneous multi-device environments, there is a need to address the imperative for efficient resource allocation in contemporary wireless networks, such as those involving unmanned aerial vehicles (UAVs) or drones. In this regard, this work addresses the challenges within a five-dimensional heterogeneous wireless network model, focusing on diverse services such as Big Data Analytics, Video Rendering, and Computer-Aided Design, and the allocation of resources among heterogeneous devices, including UAVs, tethered balloons, and multi-rotors. The resource allocation is facilitated through multiple interfaces like LTE, Wifi, LoRa, and Sigfox, catering to the diverse needs of users operating in aerial Networks. Additionally, this work introduces a novel Intelligent Relaxation using the Penalty Function (IRPF) approach for resource allocation, treating it as an integer programming problem to balance user needs while ensuring affordability. A comparative analysis is conducted between the proposed approach and the traditional branch-and-bound algorithm. In scenarios requiring resource allocation for numerous services based on user demand and device capabilities, the proposed work presents a penalty-based integrality gap solution adept at managing fractional values. The resulting optimization framework is meticulously designed to minimize activation and operating costs while optimizing utility. Additionally, the computing efficiency of the proposed approach is demonstrated by extensive simulations that prove its superiority over the traditional algorithm. Consequently, this research emphasizes the essential role of the proposed model in navigating the intricate challenges of resource allocation in modern drone-centric wireless networks.

Nowadays, emails are used across almost every field, spanning from business to education. Broadly, emails can be categorized as either ham or spam. Email spam, also known as junk emails or unwanted emails, can harm users by wasting time and computing resources, along with stealing valuable information. The volume of spam emails is rising rapidly day by day. Detecting and filtering spam presents significant and complex challenges for email systems. Traditional identification techniques like blocklists, real-time blackhole listing, and content-based methods have limitations. These limitations have led to the advancement of more sophisticated machine learning (ML) and deep learning (DL) methods for enhanced spam detection accuracy. In recent years, considerable attention has focused on the potential of ML and DL methods to improve email spam detection. A comprehensive literature review is therefore imperative for developing an updated, evidence-based understanding of contemporary research on employing these methods against this persistent problem. The review aims to systematically identify various ML and DL methods applied for spam detection, evaluate their effectiveness, and highlight promising future research directions considering gaps. By combining and analyzing findings across studies, it will obtain the strengths and weaknesses of existing methods. This review seeks to advance knowledge on reliable and efficient integration of state-of-the-art ML and DL into identifying email spam.

Vehicle control in autonomous traffic flow is often handled using the best decision-making reinforcement learning methods. However, unexpected critical situations make the collisions more severe and, consequently, the chain collisions. In this work, we first review the leading causes of chain collisions and their subsequent chain events, which might provide an indication of how to prevent and mitigate the crash severity of chain collisions. Then, we consider the problem of chain collision avoidance as a Markov Decision Process problem in order to propose a reinforcement learning-based decision-making strategy and analyse the safety efficiency of existing methods in driving security. To address this, A reward function is being developed to deal with the challenge of multiple vehicle collision avoidance. A perception network structure based on formation and on actor-critic methodologies is employed to enhance the decision-making process. Finally, in the safety efficiency analysis phase, we investigated the safety efficiency performance of the agent vehicle in both single-agent and multi-agent autonomous driving environments. Three state-of-the-art contemporary actor-critic algorithms are used to create an extensive simulation in Unity3D. Moreover, to demonstrate the accuracy of the safety efficiency analysis, multiple training runs of the neural networks in respect of training performance, speed of training, success rate, and stability of rewards with a trade-off between exploitation and exploration during training are presented. Two aspects (single-agent and multi-agent) have assessed the efficiency of algorithms. Every aspect has been analyzed regarding the traffic flows: (1) the controlling efficiency of unexpected traffic situations by the sudden slowdown, (2) abrupt lane change, and (3) smoothly reaching the destination. All the findings of the analysis are intended to shed insight on the benefits of a greater, more reliable autonomous traffic set-up for academics and policymakers, and also to pave the way for the actual carry-out of a driver-less traffic world.

The prediction of protein-protein interactions (PPIs) is essential to understand the cellular processes from a medical perspective. Among the various machine learning techniques, kernel-based Support Vector Machine (SVM) has been commonly employed to discriminate between interacting and non-interacting protein pairs. The main drawback of employing the kernel-based SVM to datasets with many features, such as the primary sequence-based protein-protein dataset, is the significant increase in computational time of training stage. This increase in computational time is mainly due to the presence of the kernel in solving the quadratic optimisation problem (QOP) involved in nonlinear SVM. In order to fix this issue, we propose a novel and efficient computational algorithm by approximating the kernel-based SVM using a low-rank truncated Mercer series as well as desired. As a result, the QOP for the approximated kernel-based SVM will be very tractable in the sense that there is a significant reduction in computational time of training and validating stages. We illustrate the novelty of the proposed method by predicting the PPIs of “S. Cerevisiae” where the protein features extracted using the multiscale local descriptor (MLD), and then we compare the predictive performance of the proposed low-rank approximation with the existing methods. Finally, the new method results in significant reduction in computational time for predicting PPIs with almost as accuracy as kernel-based SVM.

This study presents the operation and assessment of a solar-wind-biomass-hydro-electrolyser hybrid microgrid for different types of load variations by using a proprietary derivative-free algorithm (Model Predictive Deterministic Algorithm) and voltage IQ droop controller. The proposed hybrid microgrid integrates various renewable energy sources and an electrolyser to generate hydrogen and produce electricity. The objective is to optimize the microgrid’s performance and provide reliable power supply to meet varying load demands. The proprietary derivative-free algorithm is used to determine the optimal dispatch of power from each energy source to meet the load demand while minimizing the overall cost of energy. Additionally, a voltage IQ droop and voltage Q droop controller are employed to regulate the voltage, frequency and active power of the microgrid and maintain its stability during load variations. The proposed hybrid microgrid is assessed under different load scenarios for both grid tied and isolated modes. The results demonstrate that the proposed hybrid microgrid with the derivative-free algorithm and voltage droop controllers can effectively operate and provide reliable power supply under different load variations while maintaining the power system stability of the microgrid. Further, the mutual performances of the controller are compared to find the best controller for the specific microgrid. The findings of this study can contribute to the development of efficient and reliable hybrid microgrid systems for sustainable energy production and distribution.