Author: Nahlah M.A.M.Najm

Abstract: Wireless sensor networks (WSN) have a vital role in the Internet of Things (IoT), which aids to generate seamless data that has a great influence over the lifetime of the network. In spite of the significant applications of the WSN, various challenges like load balancing, security, storage, and energy occurs. A prominent technique that has to be implemented in WSN is clustering of sensor nodes. The sensor nodes (SNs) were accumulated to generate clusters in a cluster-based WSN scenario. The SNs also contain limited battery power. Thus, energy effectiveness in WSNs becomes crucial. The load on the SN and its distance from the base station (BS) will be the important elements of energy consumption. Hence, load balancing in accordance with the communication distance becomes essential for WSNs. In this aspect, this article develops an Enhanced Bald Eagle Search Optimization for Energy-Aware Clustering (EBESO-EAC) technique for WSN. The proposed EBESO-EAC technique mostly focuses on load balancing process via clustering the nodes in WSN. To attain this, the presented EBESO-EAC technique chooses proper set of cluster heads (CH) using a fitness function with multiple sensor parameters. Moreover, the EBESO-EAC technique is based on the integration of the traditional BESO algorithm with the Levy function during swooping phase. The simulation result of the EBESO-EAC technique was tested under a series of simulations. An extensive set of experimental analyses reported the improved performance of the EBESO-EAC technique over other existing algorithms. DOI link:https://ieeexplore.ieee.org/document/10351198

Abstract: Remote sensing (both satellite and terrestrial) is deemed a suitable technique for collecting data on a large scale effectively and accurately that satisfies the demand for intelligent transportation systems (ITS). In recent times, the research works relevant to the use of remote sensing (RS) technologies towards their execution in transportation systems had raised immensely. Road network extraction will be one of the important projects for intelligent transportation systems, real-time updating road networks, and disaster emergency responses. Road extraction related to high-resolution remote sensing images (RSI) was becoming a hot research topic. At present, many studies are relevant to conventional machine learning methods that can be complex and computational due to impervious surfaces namely buildings and roads that are visible in the images. With this motivation, this study progresses a salp swarm optimization with Deep Transfer Learning based Road Extraction (SSODTL-RE) technique for ITS using high-resolution RSIs. The presented SSODTL-RE technique aims to extract the rod utilizing high-resolution RSIs. Further, to generate a collection of deep features from the RS images, the SSODTL-RE approach employs a capsule network (CapsNet). Moreover, the SSODTL-RE technique applies an adaptive neuro-fuzzy inference system (ANFIS) model for the integration of broken roads and improvises efficiency because of road connectivity. To improve the efficacy of the CapsNet model, the SSO is applied for the process of hyperparameter tuning. The stimulation analysis of the SSODTL-RE system was tested on two benchmark datasets. The experimental results stated the betterment of the SSODTL-RE technique over other DL approaches. DOI link:https://ieeexplore.ieee.org/document/10351451

Computational Linguistics emphasizes the real-time consequences of modeling the utility of human languages. Applied Computational Linguistics can be utilized for several purposes in today’s domain of scientific research and development, linguistic research, and business. Public utilizes health-based web forums to access health information easily. The government will operate medical web forums for providing medical data, managing needs and feelings of patients, and fostering information-sharing between patients. Gender classification is needed for automated identification of gender among people. This article presents a novel Deep Recurrent Neural Network for Computational Linguistics Driven Gender Classification (DRNNCL-GC) on Health Web Forums. The presented DRNNCL-GC technique is employed for the examination of health web forum data for gender recognition process. For attaining this, the DRNNCL-GC technique applies data preprocessing and feature engineering phases. Next, the DRNNCL-GC technique make use of DRNN model for gender classification process. Finally, Red Colobuses Monkey (RCM) algorithm is utilized for hyperparameter optimization process, which is stimulated by the characteristics of red monkeys in nature. The performance evaluation of the presented DRNNCL-GC technique is tested and the outcomes were measured under distinct aspects. A comprehensive comparison analysis highlighted the enhancements of the DRNNCL-GC technique over other recent approaches. DOI link:https://ieeexplore.ieee.org/document/10351478

Abstract Heterogeneity is considered the most essential benefit of the 5th Generation (5G) mobile system. Like a trait becomes eminent in advanced 5G traffic conditions that are enhanced Mobile Broadband (eMBB) in which coarse Quality of Service (QoS) profiles are fulfilled on the shared communication channels. Hence, Radio Resource Management (RRM) is a difficult issue which must be solved dependent upon the traffic condition. A wide attempt indulged in the literature endeavor to make a solution for the resource allocation (RA) issue from the downlink channel by optimizing the reach for some aspects of the QoS profile. This article develops an Atomic Orbital Search Enabled Delay Aware Resource Allocation Scheme (AOSE-DARAS) for 5G heterogeneous environments. The presented AOSE-DARAS technique is mainly based on AOA, which is stimulated by the law of quantum technicians. The presented delay aware RA issue undergoes formulation as a maximum utility optimization problem. The networked resources of the clustered heterogeneous network are pooled as well as virtualized to cloud service via Infrastructure Provider (InP) and afterward assigned to corresponding mobile virtual network operators (MVNO). A wide set of simulation analyses is implemented to signify the enhanced performance of the AOSE-DARAS technique. The resultant outcomes highlighted the promising allocation efficacy of the AOSE-DARAS model over other models. © 2023 IEEE. Author keywords 5G environment; Atomic orbital search; Delay; Metaheuristics; Resource allocation; Resource scheduling DOI link:https://ieeexplore.ieee.org/document/10351283

Abstract. Process scheduling is a vital usefulness of Operating system. The primary known process-scheduling algorithms are First Come First Serve (FCFS) algorithm, Round Robin (RR) algorithm, Priority scheduling algorithm and Shortest Job First (SJF) algorithm. Contrasted with its friends, Round Robin (RR) algorithm enjoys the benefit that it gives decent amount of CPU to the processes which are as of now in the prepared line. The viability of the RR algorithm significantly relies upon picked Time Quantum (TQ) esteem. This document proposes a fresh version of the Round Robin (RR) algorithm; depend on RR integration and priority scheduling algorithms. It maintains the benefit of the RR in debasing hunger and also internalizes the priority planning benefit. This algorithm called Hybrid Priority Based Round Robin with Dynamic Time Quantum Algorithm (HPBDRR) that calculates smart time frames for individual procedures and modifications after each execution. The submitted scheduling algorithm is created by taking into account the variable notion of TQ. An integrated system was designed in Python 3.8(HPBDRR-software) for the purpose of verifying the efficiency of the recommended algorithm and comparing it beside the traditional Round Robin and some of the methods presented by a number of researches. The exploratory outcomes show that the recommended algorithm works best in wording of depreciating the number of context switches (CS), average waiting time (AWT) and average turnaround time (ATAT). DOI link:https://pubs.aip.org/aip/acp/article-abstract/2787/1/050018/2902475/New-hybrid-priority-scheduling-algorithm-based-on?redirectedFrom=fulltext