بحوث سكوبس — رامي قيس مالك

From a future perspective and with the current advancements in technology, deep reinforcement learning (DRL) is set to play an important role in several areas like transportation, automation, finance, medical and in many more fields with less human interaction. With the popularity of its fast-learning algorithms there is an exponential increase in the opportunities for handling dynamic environments without any explicit programming. Additionally, DRL sophisticatedly handles real-world complex problems in different environments. It has grasped great attention in the areas of natural language processing (NLP), speech recognition, computer vision and image classification which has led to a drastic increase in solving complex problems like planning, decision-making and perception. This survey provides a comprehensive analysis of DRL and different types of neural network, DRL architectures, and their real-world applications. Recent and upcoming trends in the field of artificial intelligence (AI) and its categories have been emphasized and potential challenges have been discussed. © 2022 The Authors. IET Communications published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and Technology.

The increasing complexity of 5G network slicing presents substantial challenges for accurate and real-time classification, which is essential for effective resource allocation and service differentiation. Standard machine learning classifiers such as Logistic Regression (LR), K-Nearest Neighbours (KNN), and Support Vector Machine (SVM) are commonly employed in this domain; however, they often fall short in capturing the harmonious and non-linear relationships between features, leading to reduced classification performance. To address these limitations, this study proposes a novel classification framework based on the Taneja Distance-Based Classifier (TDC). Unlike conventional models, TDC leverages a divergence-based distance metric to better capture subtle distributional differences between feature vectors, thus enhancing its discriminative capability. To further optimize performance and reduce feature redundancy, Particle Swarm Optimization (PSO) is incorporated as a feature selection strategy. Experimental evaluations reveal that the proposed TDC-PSO framework achieves a high classification accuracy of 98.9% on the 5G Network Slicing Dataset with a low execution time of just 1.7 milliseconds. These results clearly demonstrate the effectiveness of the proposed TDC-PSO approach in addressing both the accuracy and efficiency limitations of traditional classifiers. The framework offers a scalable and real-time solution for intelligent classification tasks in 5G and future communication networks, making it a strong candidate for deployment in practical, latency-sensitive environments. © This article is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. License details: https://creativecommons.org/licenses/by-sa/4.0/

Steel guardrails on expressways are a vital piece of traffic safety infrastructure. Unexpected events, such as accidents, might cause a freight vehicle travelling on the road to lose control. Because it may prevent the freight vehicle from speeding off the road, a steel guardrail can help keep the driver safe. As a result, the steel guardrail’s guiding ability, anti-collision performance and safety behaviour are crucial indices to measure expressway steel safety in collision accidents between freight vehicles and the steel guardrails. In this study, finite element (FE) simulation is carried out on the collision between freight cars and an expressway three-wave steel guardrail. A two-wave beam steel guardrail has been compared to the simulation results. The dynamic simulation results were predicted using the LS-Dyna FE simulator at a speed of 90 km/h and impact angles of 10°, 15°, 20°, 25°, and 30°. To estimate the steel guardrail’s protective function in real-time experimental approaches, freight vehicles clash with steel guardrails on expressways, resulting in the steel guardrail collapsing and the freight car rushing off the road. To accurately anticipate the safety of highway steel guardrails, FE modelling is the best option. The expressway three-wave steel guardrail absorbs more than 60% of the freight car’s principal translational momentum in a collision, reducing collision force transmitted to passengers and highway accident severity. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2023.

The vulnerabilities of the Internet of Things (IoTs) in general and the Internet of Mobile Things (IoMTs) in particular motivate researchers to equip them with security systems against intruders and attacks. The integration of anomaly detection with intrusion detection for IoMTs has not been addressed adequately. This paper tackles this issue through building a Kalman filter and Cauchy clustering algorithm for anomaly detection and using them for authentication nodes within IoMTs using the Extreme Learning Machine classifier. The algorithm of this proposed work is composed of various components; first, the Kalman filter-based model for estimating the trajectory of pedestrians within an indoor environment based on fusing WiFi with IMU data. Second, trustworthiness assessment for detecting anomaly behaviour in IoMT based on the estimated trajectory using the Kalman filter. Third, the trust IDS model for IoMT systems by integrating anomaly detection with online learning for attacks identification using an online sequential extreme learning machine. The algorithm has been implemented and evaluated using TamperU dataset for WiFi fingerprinting and KDD99 for intrusion detection. Furthermore, a comparison with benchmarks (the algorithms which used in other studies) for intrusion and anomaly detection proves the superiority of this proposed approach in terms of all the considered classification metrics. © 2022 The Authors. IET Communications published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and Technology.

Though the exponential growth of data-intensive applications has raised significant questions about the efficiency of task scheduling and the energy consumed, cloud computing has become the prevailing model for delivering computational resources on demand. Cloud computing is cloud computing. This study is being done to create a one-of-a-kind multiobjective genetic Algorithm (MOGA) meant to optimize the scheduling of tasks in cloud computing systems to reach the maximum feasible degree of energy efficiency. Unlike traditional methods focusing on one aim, the proposed technique addresses several conflicting ones concurrently. Among these objectives are optimizing resource use, decreasing energy use, and shortening the time needed to finish a task. Selection, crossover, and Mutation are the three ideas of genetic evolution that the algorithm uses iteratively to create the best task-resource mappings. These concepts are used to make the best maps. A dynamic workload's features are also considered in an adaptive fitness function to balance the trade-offs between energy use and performance measurements. Including non-dominated sorting and crowding distance algorithms ensures the presence of a Pareto front, both varied and uniformly dispersed. Given that cloud workload could differ, this allows for flexible decision-making. Experimental tests conducted on benchmark cloud simulation settings like CloudSim show the suggested MOGA performs far better than conventional heuristics and single-objective genetic algorithms. This holds for the energy saved and the time needed to do a task. The results show that by using its application, the algorithm may sustainably manage cloud infrastructure by lowering operational costs and carbon footprints. The algorithm's reduction of both these measures shows this. Next-generation cloud ecosystems that are aware of energy use will benefit from this research regarding resource allocation. A scalable, intelligent scheduling method consistent with green computing ideas makes these ideas viable. © 2025 IEEE.

LSTM-Based Anomaly Detection is a powerful technique for identifying irregular patterns in real-time financial transaction logs and network data. It leverages deep learning's ability to model sequential dependencies and detect hidden anomalies in dynamic transaction environments. Existing rule-based and statistical anomaly detection methods often fail to capture temporal patterns, leading to high false positives and delayed detection of complex fraudulent activities. To overcome these limitations, propose a Long Short-Term Memory Autoencoder for Anomaly Detection (LSTM-AAD) framework that learns normal transaction behavior and identifies deviations through reconstruction errors. The framework uses LSTM layers to encode and decode transaction sequences, effectively capturing long-range dependencies and temporal behaviors. The proposed method continuously analyzes live transaction logs, comparing actual behavior against reconstructed patterns to flag potential real-time anomalies. Results from extensive experiments on synthetic and real-world datasets demonstrate that LSTM-AAD significantly improves anomaly detection accuracy by 97.5%, reduces false alarms by 96.75%, precision 95.4% and adapts well to evolving fraud patterns with 98.2%. This makes it a promising approach for enhancing security in online banking and financial networks. © 2025 IEEE.

The integration of AI could solve the long-standing network challenges for optimising a robust, scalable, and power-efficient Internet of Medical Things (IoMT) network. AI using the Deep Reinforcement Learning (DRL) approach has already been applied to optimise the data processing, energy efficiency, mobility management, network congestion, and data transmission reliability in IoMT. However, the power utilisation efficiency of IoMT networks is highly dependent on adaptive data rate control and transmission power levels. We have proposed a DRL-based framework that periodically adapts the transmission rates as well as power levels of IoMT networks, aiming to optimise the data packet transmission schedule by the utilisation of smart packets that consume less power while maintaining the same reliability and speed. The framework is enabled by a central gateway connected to a cloud server, where the learning agent (DRL) is trained from offline real-time data of the network to determine the optimised transmission schedules. As shown in the simulation results, the proposed DRL framework can enhance the network performance compared with the traditional methods. It indicates that the DRL approach for these 2000 iterations has improved 27% of power consumption compared with the traditional system, whereas the average packet delivery rate and throughput are quite steady at 80 packets per second and 70 packets per second, respectively. It illustrates some extent of robustness in the network’s energy efficiency and reliability when it is controlled by using the proposed DRL method. Furthermore, DRL-fund methods improve power control and network performance remarkably, enabling reliable and low-energy IoMT systems for healthcare in-body monitors. © 2025 The authors. This article is published by IIETA and is licensed under the CC BY 4.0 license (http://creativecommons.org/licenses/by/4.0/).

In the published article [1], the authors raised concerns about an error related to the affiliation “Shenzhen Institute of Advanced Technology (SIAT), University of Chinese Academy of Sciences, Shenzhen 518055, China” for Ijaz Ahmad due to improper authorization. In addition, the updated affiliation should include: “Institute of Computer Sciences and Information Technology (ICS/IT), The University of Agriculture, Peshawar 25130, Pakistan”, where the project was conducted. The authors state that the scientific conclusions are unaffected. This correction was approved by the Academic Editor. The original publication has also been updated. © 2025 by the authors.

In recent years, the secure processing of financial data in cloud environments has become critical due to recent concerns regarding data confidentiality and unauthorized access. Homomorphic Encryption (HE) allows clients to perform computations on data that maintain confidentiality, while the data remains encrypted through the computations. However, existing HE methods often have high computational and latency/output overhead preventing the use of HE in real-world financial applications. The focus of this research study is to propose an Encrypted Credit Scoring System that utilizes Fully Homomorphic Encryption (FHE), and Parallel Processing Optimization to address these issues. The Encrypted Credit Scoring system will allow clients to process encrypted financial data in the cloud securely and efficiently without compromising data confidentiality or privacy. The Encrypted Credit Scoring system would contain a mechanism for cloud servers to perform computing on scoring algorithms directly on encrypted inputs enabling cloud computations on encrypted financial data required for secure credit risk assessments. The proposed method would help with regulatory compliance and confidentiality or anonymization while utilizing cloud processing capabilities and leveraging scalability. The final results from experiments on processing speed and accuracy show all factors improved and the quantitative analysis of the processing delays with the working secure and usable FHE over legacy implementations shows a drastic reduction in computational delays helping to reduce latency and output delays while achieving operational needs and practicality to foster implementations of size leveraging FHE capabilities on secure financial sensitive data. © 2025 IEEE.

Electronic payment systems must assess cyber risk in order to protect the integrity of the transaction and limit fraud. Fuzzy Logic and Decision Trees offer intelligent adaptive approaches to analyze the complex and uncertain cybersecurity data that poses risks, within payment systems. Unlike classic rule-based or binary classification techniques that can be mired by imprecise classifications and produce heights amounts of false positives or threat miss, Fuzzy Logic and Decision Trees have higher potential to recognize or disregard threats within a broader state of uncertainty. The inherent limitations of these techniques will often hinder the real-time assessment of transaction risks in rapidly changing environments. This paper, introduce a Fuzzy Decision Tree (FDT) Framework that connects the understandability of decision trees with the more flexible and adaptable approach associated with fuzzy logic. The FDT framework dynamically classifies transactions as safe, suspicious, or high-risk, enabling timely and intelligent decision-making. The proposed method facilitates real-time fraud detection, reduces false alerts, and enhances operational efficiency in cybersecurity monitoring of payments. Findings demonstrate that the FDT approach improves the accuracy and explainability of cyber risk assessment models, making it suitable for both automated systems and human analysts in fintech environments. FDT model outperforms others, showing higher classification accuracy (up to 95%). © 2025 IEEE.

The rise of mobile wallet financial applications has necessitated the integration of robust yet lightweight security mechanisms. This paper focuses on combining Lightweight Cryptographic Techniques and Multi-Factor Authentication (MFA) to enhance security and efficiency in mobile financial transactions. Current mobile wallet systems often rely on computationally intensive traditional cryptographic algorithms, leading to performance bottlenecks on resource-constrained mobile devices. The lack of dynamic authentication mechanisms also increases the risk of unauthorized access and financial fraud. To address these challenges, proposes a novel framework: SETA-ECC-TOTP (Secure and Efficient Transaction Authorization using Elliptic Curve Cryptography and Time-Based One-Time Password). This framework leverages the lightweight and strong security properties of Elliptic Curve Cryptography (ECC) for encryption and digital signatures, combined with TOTP. This dynamic, time-based MFA mechanism generates ephemeral authentication codes. The proposed method operates by securely encrypting transaction data using ECC, while TOTP ensures that only authorized users can complete transactions within a short time window, adding a second layer of security without compromising performance. The framework is designed to be lightweight, making it ideal for mobile environments with limited computational resources. Experimental results and security analysis demonstrate that SETA-ECC-TOTP significantly enhances security while maintaining low latency and computational overhead. The integration of ECC and TOTP effectively mitigates threats such as replay attacks, brute-force attempts, and unauthorized access, making the framework a viable solution for securing mobile wallet applications. © 2025 IEEE.

The multifaceted, decentralized, and anonymous nature of blockchain systems means that each cryptocurrency transaction is a potential threat to financial security arising from money laundering. Graph neural networks (GNNs) are a promising method for uncovering hidden illicit patterns due to their design for complex relational data. However, existing GNN-based methods for detection in cryptocurrency transactions and interactions have limited themselves to the relationships contaminants and skeletons do overlap with; they have not accounted for the heterogeneity of relationships, such as the number of different entities like users, wallets, and exchanges that could be considered a party to any one single transaction. This shortcoming limits existing methods ability to generalize detection beyond some finite threshold of actions within these complexities, thereby failing to draw upon the homeland knowledge and patterns needed to address evolving laundering by considering anomalies as departure from typical. To address these issues, this study develops a Heterogeneous Graph Neural Network (HGNN) based framework that was devised to model the multi-typed entities and interactions that exist within cryptocurrency transaction networks. Moreover, the HGNN was applied to actual blockchain dataset samples in order to detect anomalous patterns. The proposed methodology of HGNN improves accuracy by 98.32%, precision by 97.6%, robustness by 96.4%, and F1 score by 99.1%. © 2025 IEEE.

In this work, the vacuum evaporation method was used to prepare perovskite thin films that were deposited on glass substrates in varying thicknesses. Some properties of perovskite film were studied, such as structural and optical properties. XRD analysis gave that perovskite has tetragonal structural. The morphology of perovskite shows by SEM best uniform structure and have fairly small grain sites. Optical properties of perovskite films have been studied, such as transmittance, absorption coefficient, energy gap, and extinction coefficient. The transmittance was in the range of 300 to 1100 nm. The optical energy gap of the allowed direct electron transition was found to be (2.65-2.5 eV) for perovskite. The Urbach tail energy was studied and found to be equal to (1.8 eV) for perovskite. In the 1.5-4 eV range, the reflectivity of perovskite is shown as a function of photon energy. The result gives the band gap of perovskite equal to 1.65 eV. The Fourier transform infrared spectroscopy (FTIR) investigation confirmed the formation of perovskite films. For perovskite, Raman spectra demonstrated modes considered characteristic modes in the perovskite crystal structure. © Published under licence by IOP Publishing Ltd.

Mesenchymal stem cell (MSC) transfusion has shown promising results in treating COVID-19 cases despite the limited availability of these MSCs. The task of prioritizing COVID-19 patients for MSC transfusion based on multiple criteria is considered a multi-Attribute decision-Analysis (MADA) problem. Although literature reviews have assessed the prioritization of COVID-19 patients for MSCs, issues arising from imprecise, unclear and ambiguous information remain unresolved. Compared with the existing MADA methods, the robustness of the fuzzy decision by opinion score method (FDOSM) and fuzzy-weighted zero inconsistency (FWZIC) is proven. This study adopts and integrates FDOSM and FWZIC in a homogeneous Fermatean fuzzy environment for criterion weighting followed by the prioritization of the most eligible COVID-19 patients for MSC transfusion. The research methodology had two phases. The decision matrices of three COVID-19 emergency levels (moderate, severe, and critical) were adopted based on an augmented dataset of 60 patients and discussed in the first phase. The second phase was divided into two subsections. The first section developed Fermatean FWZIC (F-FWZIC) to weigh criteria across each emergency level of COVID-19 patients. These weights were fed to the second section on adopting Fermatean FDOSM (F-FDOSM) for the purpose of prioritizing COVID-19 patients who are the most eligible to receive MSCs. Three methods were used in evaluating the proposed works, and the results included systematic ranking, sensitivity analysis, and benchmarking checklist. © 2024 World Scientific Publishing Company.

Environmentally friendly and intelligent transportation options have been developed to tackle pollution and fuel shortages during the past several years. Numerous standards organizations and transportation authorities have provided a range of alternative energy sources intending to create a more environmentally friendly and sustainable atmosphere. However, some obstacles remain to clear before the goal may be fulfilled in green transportation. The research examines and identifies transportation pollution and greenhouse gas emissions. An electric vehicle-centric approach to green mobility is taken, emphasizing electric vehicle architecture and current solutions initiatives, and essential for effectively done. Regarding an Electric Vehicle Charging Station (EVCS), location is key; according to the study, EVSC location selection may be improved using an Internet of Things (IoT) with a cloud computing (IoT-CC) approach. Carbon-producing vehicles such as trains and buses are being phased out globally for more eco-friendly transportation. Electrified vehicles are a significant step toward a more environmentally friendly mode of transportation. However, electric vehicles are becoming more common, and the infrastructure for charging must be expanded and seamless. Solar panels may be used to electric power vehicles and generate their energy by certain entities. There are plans to develop EVSC-IoT service architecture to minimize carbon dioxide emissions and fuel consumption in a smart transportation system. It gathers data from telematics, digital systems, and roadside camera to assist fuel consumption. Electric vehicle drivers may use electronic wallets to pay for their charging costs. The suggested EVSC-IoT model enhances the charging demand, charging time, time distribution, and traveling velocity compared to other existing methods. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2023.

Numerous nations have prioritised the inclusion of citizens with disabilities, such as hearing loss, in all aspects of social life. Sign language is used by this population, yet they still have trouble communicating with others. Many sign language apps are being created to help bridge the communication gap as a result of technology advances enabled by the widespread use of smartphones. These apps are widely used because they are accessible and inexpensive. The services and capabilities they offer and the quality of their content, however, differ greatly. Evaluation of the quality of the content provided by these applications is necessary if they are to have any kind of real effect. A thorough evaluation like this will inspire developers to work hard on new apps, which will lead to improved software development and experience overall. This research used a systematic literature review (SLR) method, which is recognised in gaining a broad understanding of the study whilst offering additional information for future investigations. SLR was adopted in this research for smartphone-based sign language apps to understand the area and main discussion aspects utilised in the assessment. These studies were reviewed on the basis of related work analysis, main issues, discussions and methodological aspects. Results revealed that the evaluation of sign language mobile apps is scarce. Thus, we proposed a future direction for the quality assessment of these apps. The findings will benefit normal-hearing and hearing-impaired users and open up a new area where researchers and developers could work together on sign language mobile apps. The results will help hearing and non-hearing users and will pave the way for future collaboration between academicians and app developers in the field of sign language technology. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2023.

The authors regret that they have missed to add the second affiliation of the author A.S. Albahri. The additional affiliation of A.S. Albahri should be included as follows: Technical College, Imam Ja'afar Al-Sadiq University, Baghdad, Iraq. The authors would like to apologise for any inconvenience caused. © 2023 Elsevier Ltd

The growth of the fish is influenced by a variety of scientific factors. So, profit can be easily achieved by using some clever techniques, for example, maintaining the correct pH level along with the dissolved oxygen (DO) level and temperature, as well as turbidity for good growth of fish. Fully grown fish are generally sold at a good price because price of fish in the market is governed by weight as well as size of nurtured fish. Artificial intelligence (AI)-based systems may be created to regulate key water quality factors including salinity, dissolved oxygen, pH, and temperature. The software programme operates on an application server and is connected to multiparameter water quality meters in this system. This study examines smart fish farming methods that show how complicated science and technology may be simplified for use in seafood production. This research focuses on the use of artificial intelligence in fish culture in this setting. The technical specifics of DL approaches used in smart fish farming which includes data and algorithms as well as performance was also examined. In a nutshell, our goal is to provide academics and practitioners with a better understanding of the current state of the art in DL implementation in aquaculture, which will help them deploy smart fish farming applications as well their benefits. © 2023 Gaganpreet Kaur et al.

The technology deployment in smart e-tourism brings high potential in terms of customer data, events, reservations, and others. It acts as an effective and personalized guide to aid travelers. There is an increasing variety of smart e-tourism apps with multiple categories and criteria, but in terms of decision making, this presents a multicriteria complex problem to determine the best app from a group of available options with high criteria subjectivity. Literature reviews have evaluated and modeled the existing smart e-tourism apps alternatives, but informational uncertainty remains. The fuzzy sets and Multi-Attribute Decision Analysis (MADA) were used to handle the subjectivity issue. However, this process includes levels of uncertainty, which affects the decisions made and still an open issues. Spherical fuzzy rough sets (SFRSs) environment are useful in this situation for resolving fuzziness and ambiguity. This paper proposed a decision modeling approach for smart E-Tourism data management applications based on SFRSs environment. For methodology: firstly, a decision matrix is adopted for 5 different categories of Smart E-tourism's system applications on the basis of the integrated 12 evaluation criteria. Secondly, a new formulation and development formulating a new extension of FWZIC, called a Spherical Fuzzy Rough-Weighted Zero-Inconsistency (SFR-WZIC), for weighting the smart key concept attributes involved in modeling smart e-tourism, whereas a new formulation and development for a new extension of FDOSM, called a Spherical Fuzzy Rough Decision by Opinion Score Method (SFR-DOSM), for modeling the applications of smart e-tourism per each e-tourism category; then, the new developments are integrated. The proposed methods were evaluated using systematic ranking and sensitivity analysis. © 2023 Elsevier B.V.

Intrusion detection systems (IDSs) employ sophisticated security techniques to detect malicious activities on hosts and/or networks. IDSs have been utilized to ensure the security of computer and network systems. However, numerous evaluation and selection issues related to several cybersecurity aspects of IDSs were solved using a decision support approach. The approach most often utilized for decision support in this regard is multi-Attribute decision-making (MADM). MADM can aid in selecting the most optimal solution from a huge pool of available alternatives when the appropriate evaluation attributes are provided. The openness of the MADM methods in solving numerous cybersecurity issues makes it largely efficient for IDS applications. We must first understand the available solutions and gaps in this area of research to provide an insightful analysis of the combination of MADM techniques with IDS and support researchers. Therefore, this study conducts a systematic review to organize the research landscape into a consistent taxonomy. A total of 28 articles were considered for this taxonomy and were classified into three main categories: data analysis and detection (n=4), response selection (n=7) and IDS evaluation (n=17). Each category was thoroughly analyzed in terms of a variety of aspects, including the issues and challenges confronted, as well as the contributions of each study. Furthermore, the datasets, evaluation attributes, MADM methods, evaluation and validation and bibliography analysis used by the selected articles are discussed. In this study, we highlighted the existing perspective and opportunities for MADM in the IDS literature through a systematic review, providing researchers with a valuable reference. © 2023 World Scientific Publishing Company.

A First-principles study based on density functional theory was accomplished to examine the different properties of ABVO4 (A = Pb/Cd, B[dbnd]La/Lu) materials such as structural, optical, and electronic properties. The band gap of Pb/Cd-doped LuVO4 is found to be remarkably and significantly decreased from 2.921 to 1.71eV as compared to a decrement of 3.455 to 2.650eV in Pb/Cd-doped LaVO4. Under the DFT study, Pb (Lead) and Cd (Cadmium) are appropriate materials for band gap decrement of LuVO4 and LaVO4. The nature of the band gap was found indirect moreover band gap indicated that materials are prominent semiconductors. Pb/Cd is doped at the vanadium (V) sites, which are more advantageous than the La/Lu sites. By capturing Pb/Cd at the V sites in LuVO4/LaVO4, additional gamma points were incorporated into the electronic band gap energy (Eg). A significant decrement is found in the band gap as well as optical conductivity. After the substitution of different impurities of Pb/Cd the energy absorption peaks are increased. It is also examined that after doping of Pb/Cd optical conductivity shifted toward larger energy because of the band gap. Both Pb/Cd-doped LuVO4 and Pb/Cd-doped LaVO4 compounds have high optical conductivity, refractive index, and energy absorption moreover Pb/Cd-doped LuVO4 is a more appropriate material as compared to Pb/Cd-doped LaVO4 for electronic device applications. © 2022 Elsevier B.V.

This study presents a review of literature on the usage of artificial neural networks (ANNs) architecture contribution method and structural equation modeling (SEM), and proposes a new selection process in the context of algorithm -based SEM-ANNs schemes. This study enriches academic literature by providing a review of all the main aspects of customization in ANNs and contribution methods in combination with SEM. Academic databases are examined for exhibition findings, yielding 253 papers published between 2016 and 2022. The retrieved papers are categorized according to inclusion criteria, and the final set of 73 articles are discussed based on two directions, namely, ‘Sector-based’ and ‘Algorithm-based’ as a new representation of taxonomy research. A state-of-the-art bibliographic analysis is presented. This review also identifies modern challenges and open issues in terms of multiple evaluation criteria, importance criteria, and data variations related to the selection of customizations in ANNs and contribution methods combined with SEM in different industrial cases. Several issues fall under multicriteria decision making for handling complexity problems in different ANNs and contribution methods. Thus, this study also presents a research proposal and recommends a solution based on a three-phase methodology for handling the selection and overcoming the identified issues, subsequently completing a strategic guideline solution. © 2023 Elsevier Ltd

Many data resources and network availability are needed for smart city applications to execute at their highest efficiency level. Demand for these objects is driving up data traffic, which in turn is placing strain on the network. The 5G-enabled Internet of Things applications address these difficulties in smart city applications. This article proposes an Information-centric Networking System using Multiaccess Edge Computing (ICNMEC) to reduce computation offloading and optimize data traffic. This system's 5G network slicing approaches combine edge computing and software characterization. Internet of Things applications have been used to store and analyze the information gathered. In addition, an algorithm known as OMNM (Optimized Memory Network Management) is created to control network traffic better and better use of storage. With minimal delays, network traffic, and storage ratio, the system's modelling tests demonstrate that it is very efficient. This method can progressively enhance the pace at which one can access and use the system. The performance assessment shows that the proposed method can improve the efficiency ratio of 95.141%, storage utilization ratio of 60.1% and access rate by 0.9, reducing network traffic and delay by 0.6. © 2023

Remote sensing image (RSI) classifier roles a vital play in earth observation technology utilizing Remote sensing (RS) data are extremely exploited from both military and civil fields. More recently, as novel DL approaches develop, techniques for RSI classifiers with DL have attained important breakthroughs, providing a new opportunity for the research and development of RSI classifiers. This study introduces an Improved Slime Mould Optimization with a graph convolutional network for the hyperspectral remote sensing image classification (ISMOGCN-HRSC) model. The ISMOGCN-HRSC model majorly concentrates on identifying and classifying distinct kinds of RSIs. In the presented ISMOGCN-HRSC model, the synergic deep learning (SDL) model is exploited to produce feature vectors. The GCN model is utilized for image classification purposes to identify the proper class labels of the RSIs. The ISMO algorithm is used to enhance the classification efficiency of the GCN method, which is derived by integrating chaotic concepts into the SMO algorithm. The experimental assessment of the ISMOGCN-HRSC method is tested using a benchmark dataset. © 2023 CRL Publishing. All rights reserved.

Cyber-physical system (CPS) is a concept that integrates every computer-driven system interacting closely with its physical environment. Internet-of-things (IoT) is a union of devices and technologies that provide universal interconnection mechanisms between the physical and digital worlds. Since the complexity level of the CPS increases, an adversary attack becomes possible in several ways. Assuring security is a vital aspect of the CPS environment. Due to the massive surge in the data size, the design of anomaly detection techniques becomes a challenging issue, and domain-specific knowledge can be applied to resolve it. This article develops an Aquila Optimizer with Parameter Tuned Machine Learning Based Anomaly Detection (AOPTML-AD) technique in the CPS environment. The presented AOPTML-AD model intends to recognize and detect abnormal behaviour in the CPS environment. The presented AOPTML-AD framework initially pre-processes the network data by converting them into a compatible format. Besides, the improved Aquila optimization algorithm-based feature selection (IAOA-FS) algorithm is designed to choose an optimal feature subset. Along with that, the chimp optimization algorithm (ChOA) with an adaptive neuro-fuzzy inference system (ANFIS) model can be employed to recognise anomalies in the CPS environment. The ChOA is applied for optimal adjusting of the membership function (MF) indulged in the ANFIS method. The performance validation of the AOPTML-AD algorithm is carried out using the benchmark dataset. The extensive comparative study reported the better performance of the AOPTML-AD technique compared to recent models, with an accuracy of 99.37%. © 2023 CRL Publishing. All rights reserved.

This paper aims to investigate the main factors that have an impact on the adoption of cloud-based enterprise resource planning (ERP) among small and medium-sized enterprises (SMEs) in the Republic of Iraq using TOE, DOI, and HOT-fit as a theoretical framework. Data was collected from 136 decision maker senior executives, and IT managers in SMEs in the Republic of Iraq. A web-based survey questionnaire was used for data collection processes. The research model and the derived hypotheses were tested using SPSS and SmartPLS. The findings indicate several specific factors have a significant effect on the adoption of cloud-based ERP. This conclusion can be utilized in enhancing the strategies for approaching cloud-based ERP by pinpointing the reasons why some SMEs choose to adopt this technology and success during the adoption phase, while others still do not go forward with the adoption. This study provides an overview and empirically shows the main determinants logistical factors that might face SMEs in the Republic of Iraq. The findings also help SMEs consider their information technologies investments when they think to adopt cloud-based ERP © 2023, International Journal of Advanced Computer Science and Applications.All Rights Reserved.

The higher education industry in Iraq had various challenges during the covid-19 outbreak, and this study looked at how remote learning and other relevant technology helped. During the new standard period, a platform with other internet providers helped to keep this sector afloat. The Corona crisis (COVID-19) had a huge impact on Iraqi education, which was revolutionized through the use of e-learning to lessen the danger of pupils contracting COVID-19. learning and its related technology platform, and other online outcomes enabled Iraq's critical higher education businessto survive the covid-19 crisis while also providing insight into the sector's difficulties in the new normal age. © 2023 CAD Solutions, LLC.

Identifying the gender, race, age, and stature of the target during the forensic inquiry is a critical stage in various events such as accidents, bombings, terrorism, wars, and disasters. In this paper, an application has been developed that uses hand X-rays to identify and determine gender for medical applications such as special cases where diagnosing the gender is difficult, like accidents in which the hand is amputated and unknown, severe burns, and in old skeletal structures using deep learning models. For comparative purposes, GoogLeNet and ResNet-18 were employed. Gender determination using hand X-rays yielded positive results. The accuracy of gender detection in the model GoogLeNet (validation, training, test, and total) is (76.67%, 96.68%, 53.33%, and 89.5%) respectively, while the accuracy of gender detection in the model ResNet-18 (validation, training, test, and total) are (80%, 99.29%, 87.5%, 94.63%) respectively. The ResNet-18 model was adopted as the best model for gender detection and determination because high results were obtained. Simulation results showed acceptable results with high accuracy in diagnosis, where the highest gender determination rate was obtained through hand X-ray analysis at 94.63%. © 2023 IEEE.

Lately, the Internet of Things (IoT) application requires millions of structured and unstructured data since it has numerous problems, such as data organization, production, and capturing. To address these shortcomings, big data analytics is the most superior technology that has to be adapted. Even though big data and IoT could make human life more convenient, those benefits come at the expense of security. To manage these kinds of threats, the intrusion detection system has been extensively applied to identify malicious network traffic, particularly once the preventive technique fails at the level of endpoint IoT devices. As cyberattacks targeting IoT have gradually become stealthy and more sophisticated, intrusion detection systems (IDS) must continually emerge to manage evolving security threats. This study devises Big Data Analytics with the Internet of Things Assisted Intrusion Detection using Modified Buffalo Optimization Algorithm with Deep Learning (IDMBOA-DL) algorithm. In the presented IDMBOA-DL model, the Hadoop MapReduce tool is exploited for managing big data. The MBOA algorithm is applied to derive an optimal subset of features from picking an optimum set of feature subsets. Finally, the sine cosine algorithm (SCA) with convolutional autoencoder (CAE) mechanism is utilized to recognize and classify the intrusions in the IoT network. A wide range of simulations was conducted to demonstrate the enhanced results of the IDMBOA-DL algorithm. The comparison outcomes emphasized the better performance of the IDMBOA-DL model over other approaches. © 2023 CRL Publishing. All rights reserved.

Due to the developments and increasing the manufacturing processes, the number of vehicles increased, especially smart ones, and for the purpose of reducing accidents and the dangers resulting from vehicle collisions with each other or with pedestrians. It has become necessary to create a system of communication between the vehicles themselves and the external environment through the Internet, hence the need for the Internet of vehicles (IoV), which is part of the Internet of' Things (IoT). By connecting (VANETs) with the Internet of Things, we can expand the possibilities of (IoT). Internet of vehicles (IoV) communicates between vehicles and public network and involves communication between vehicles and human, sensors and vehicles. (IoV) architecture involves four significant layers. This paper introduced also the most effective challenges and issues of (IoV) system and it's applications. © 2023 Author(s).

The authors regret the inadvertent omission of second affiliation of author A.S. Albahri. Affiliation is presented as below: Department of Computer Technology Engineering, College of Information Technology, Imam Ja'afar Al-Sadiq University, Baghdad, Iraq. The authors would like to apologise for any inconvenience caused. © 2023 Elsevier B.V.

Wireless Sensor Networks (WSN) have revolutionized the processes involved in industrial communication. However, the most important challenge faced by WSN sensors is the presence of limited energy. Multiple research inves-tigations have been conducted so far on how to prolong the energy in WSN. This phenomenon is a result of inability of the network to have battery powered-sensor terminal. Energy-efficient routing on packet flow is a parallel phenomenon to delay nature, whereas the primary energy gets wasted as a result of WSN holes. Energy holes are present in the vicinity of sink and it is an important efficient-routing protocol for WSNs. In order to solve the issues discussed above, an energy-efficient routing protocol is proposed in this study named as Adaptive Route Decision Sink Relocation Protocol using Cluster Head Chain Cycling approach (ARDSR-CHC2H). The proposed method aims at improved communication at sink-inviting routes. At this point, Cluster Head Node (CHN) is selected, since it consumes low energy and permits one node to communicate with others in two groups. The main purpose of the proposed model is to reduce energy con-sumption and define new interchange technology. A comparison of simulation results demonstrates that the proposed algorithm achieved low cluster creation time, better network error and high Packet Delivery Rate with less network failure. © 2023, Tech Science Press. All rights reserved.

ZnO is an important II-IV n-type direct bandgap semiconductor material that has exhibited wide consideration due to its applications in optoelectronic devices. In the present investigation, untreated and plasma-treated ZnO NPs were fabricated by a sol-gel route and analyzed with XRD, Raman, UV-Vis spectra, and I-V characteristic techniques. To be used in electronic applications, the ZnO nanoparticles were subjected to a plasma treatment process to tune their optical, vibrational mode, structural and electrical properties. XRD confirmed the pure Wurtzite tetragonal phase crystalline nature of produced samples. The average crystalline size, lattice constant, unit cell volume, and porosity were found in the range of 3.81-4.68 nm, a = 3.217-3.323 Å and c = 2.032-2.178 Å, 5.662-11.274 Å3 and 7.09-5.03%, respectively. The Raman spectra revealed that the intensity of Raman bands was increased due to the increase in the vibrational amplitude and increase in force constants with the enhancement in grain size, these spectra results are in good agreement with XRD and reveal the purity of samples. The bandgap found reduced from 3.56 eV to 3.39 eV by plasma treatment. The electrical studies revealed that plasma treatment improves the electrical properties of ZnO NPs without producing any structural distortions. I-V characteristic curves confirmed that the conductivity was increased from 8.3 X 10-6 to 5.5 X 10-4 ω cm-1 on plasma treatment which caused an increase in leakage current. The improved structural, vibrational mode, optical and electrical properties of prepared ZnO NPs make them a suitable candidate for application in electronic devices. © 2022 The Author(s).

Maximum power point tracking (MPPT) algorithms are a practical solution to ensure the continuous operation of the photovoltaic systems, maximize the output of the PV system and overcome nonlinear characteristics under all circumstances. Different MPPT strategies were used to achieve the maximum output power of the photovoltaic system. There are conventional MPPT algorithms. Also, there are soft computing techniques to attract the maximum PowerPoint. In this paper, the MPPT approaches for solar systems are reviewed and compared in-depth with six different requirements, the comparison shows that the Incremental Conductance has an advantage over the conventional methods. Soft computing methods give high efficiency, but the effectiveness of soft computing techniques needs users for a good background on how it works, it's more complex than conventional MPPT methods, the essential variations among these approaches are digital versus analogy applications, design simplicity, sensor requirements, convergence time, effectiveness range, and hardware pricing. As a consequence, choosing the right algorithm is crucial for users since it impacts the electrical efficiency of the photovoltaic (PV) module and lowers expenses by lowering the number of solar panels required to produce the necessary electricity. © 2022 IEEE.

In this paper, a coplanar waveguide (CPW)-fed patch antenna is fabricated on a layer of metasurface to increase gain. The antenna is fabrication on Roger substrate with a thickness of 0.25 mm, with the overall dimension of the proposed design being 45 × 30 × 0.25 mm3. The size of the patch antenna is 24 × 14 × 0.25 mm3, and the AMC unit cell is 22 × 22 × 0.25 mm3. This metasurface is designed based on the split-ring resonator unit cells forming an array of the artificial magnetic conductor (AMC). Meanwhile, the antenna operation on 3.5 GHz is enabled by etching a split-ring resonator slot on the ground plane with a small gap to enhance antenna gain and improve impedance bandwidth when integrated with a metasurface. This simulation planer monopole antenna is applied for 5G application. The experimenter test is applied for the antenna performance in terms of return loss, gain, and radiation patterns. The operating frequency range with and without MTM is from 3.41 to 3.68 GHz (270 MHz) and 3.37 to 3.55 GHz (180 MHz), respectively, with gain improvements of about 2.7 dB (without MTM) to 6.0 dB (with MTM) at 3.5 GHz. The maximum improvement of the gain is about 42% when integrated with the AMC. The AMC has solved several issues to overcome the typical limitation in conventional antenna design. A circuit model is also proposed to simplify the estimation of the performance of this antenna at the desired frequency band. The proposed design is simulated by CST microwave studio. Finally, the antenna is fabricated and measured. Result comparison between simulations and measurements indicates a good agreement between them. © 2022 Ali Abdulateef Abdulbari et al.

The aim of this article is to review and analyse previous academic articles associated with car behaviour analysis for the period of 2010 to June 10, 2021 and understand the benefits of using data collection devices. Articles related to car driver behaviour and sensor utilisation are systematically searched. Three major databases – ScienceDirect, IEEE Xplore and Web of Science – were searched. A set of inclusion and exclusion criteria were developed for the search protocol. All articles were coherently classified via taxonomy. Also. The motives that have led researchers to continue their investigations are explored. The challenges and issues of driver behaviour analysis are illustrated with respect to power consumption, data analysis, detection, cost, security and privacy, sensor usage and individual challenges. The research direction of this review points towards different aspects based on the critical analysis of the different scenarios of driver behaviour studies in real time situations. Here, the critical behaviour analysis of intelligent transportation system development is addressed. The gaps in the reviewed articles include the following: sensors used during experiments, the effect of thresholds on labelling processes or data balancing and classification accuracy, the thresholds in identifying driving styles in the car-following model, insufficient experiment size (large scale or small scale) and limitations in data pre-processing. An implementation map depicting the steps of the case study is provided to give insights into the procedures and the problems they address. This review is expected to offer valid and clear points, contributing to the enhancement of driver behaviour research. © 2022 Elsevier Ltd

Indoor air quality (IAQ) refers to the conditions found within buildings that can impact respiratory health. Good IAQ conditions for hospital facilities are essential, especially for patients and medical staff. Recently, several concerns have been outlined and require an urgent solution in identifying IAQ pollutants and related thresholds and ways to provide a knowledge-based method for labelling pollution levels. To this end, a systematic review should be conducted first to construct new taxonomy research on internet of things-based IAQ sensory technology in hospital facilities to identify a research gap. Thus, the present study aims to develop an IAQ methodology that includes the recommended nine pollutants for hospitals and facilities: Carbon monoxide, Carbon dioxide, Nitrogen Dioxide, Ozone, Formaldehyde, Volatile organic compound, particulate matter (PM) and air humidity and temperature. The developed methodology utilised actual and simulated IAQ pollutant datasets to predict the pollution levels within hospital facilities in three distinct phases. In the first phase, two IAQ datasets (real and large-scale simulated datasets) are identified. The second phase includes the following: First is utilising the Interval type 2 trapezoidal-fuzzy weighted with zero inconsistency (IT2TR-FWZIC) method from the Multi-Criteria Decision Making theory for providing the required weights to the nine pollutants. Second is developing a new method, the Unified Process for Labelling Pollutants Dataset (UPLPD), consisting of six processes based on the IT2TR-FWZIC method. The UPLPD can classify the pollution levels into four levels and assign the required labels within the two datasets. Third is applying the labelled datasets to the developed machine learning model using eight algorithms. The third phase includes the model evaluation using five metrics in terms of accuracy, Area under the Curve, F1-score, precision and recall. For the actual dataset, the best three algorithms' results are Support Vector Machine, Logistic Regression and Decision Tree (DT), which achieved the highest accuracy of 99.813, 99.259 and 98.182%, respectively, with performance metrics. The simulated dataset, the Random Forest, DT and AdaBoost achieved the highest accuracy of 90.094, 88.964 and 87.735%, respectively, with performance metrics. The results satisfied the challenges and overcame the issues, and experimental results confirmed the efficacy of the predictive model. © 2022, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.

The Internet of Railways (IoR) network is made up of a variety of sensors, actuators, network layers, and communication systems that work together to build a railway system. The IoR’s success depends on effective communication. A network of railways uses a variety of protocols to share and transmit information amongst each other. Because of the widespread usage of wireless technology on trains, the entire system is susceptible to hacks. These hacks could lead to harmful behavior on the Internet of Railways if they spread sensitive data to an infected network or a fake user. For the previous few years, spotting IoR attacks has been incredibly challenging. To detect malicious intrusions, models based on machine learning and deep learning must still contend with the problem of selecting features. k-means clustering has been used for feature scoring and ranking because of this. To categorize attacks in two datasets, the Internet of Railways and the University of New South Wales, we employed a new neural network model, the extended neural network (ENN). Accuracy and precision were among the model’s strengths. According to our proposed ENN model, the feature-scoring technique performed well. The most accurate models in dataset 1 (UNSW-NB15) were based on deep neural networks (DNNs) (92.2%), long short-term memory LSTM (90.9%), and ENN (99.7%). To categorize attacks, the second dataset (IOR dataset) yielded the highest accuracy (99.3%) for ENN, followed by CNN (87%), LSTM (89%), and DNN (82.3%). © 2022 by the authors.

The autonomous landing of an unmanned aerial vehicle (UAV) on a moving platform is an essential functionality in various UAV-based applications. It can be added to a teleoperation UAV system or part of an autonomous UAV control system. Various robust and predictive control systems based on the traditional control theory are used for operating a UAV. Recently, some attempts were made to land a UAV on a moving target using reinforcement learning (RL). Vision is used as a typical way of sensing and detecting the moving target. Mainly, the related works have deployed a deep-neural network (DNN) for RL, which takes the image as input and provides the optimal navigation action as output. However, the delay of the multi-layer topology of the deep neural network affects the real-time aspect of such control. This paper proposes an adaptive multi-level quantization-based reinforcement learning (AMLQ) model. The AMLQ model quantizes the continuous actions and states to directly incorporate simple Q-learning to resolve the delay issue. This solution makes the training faster and enables simple knowledge representation without needing the DNN. For evaluation, the AMLQ model was compared with state-of-art approaches and was found to be superior in terms of root mean square error (RMSE), which was 8.7052 compared with the proportional–integral–derivative (PID) controller, which achieved an RMSE of 10.0592. © 2022 by the authors.

In the current research, the resist action of silver-doped polystyrene/polyethylene terephthalate (PET) solar thin film towards laser irradiation was observed. Moreover, silver-doped polystyrene nanoparticles were synthesized via a chemical technique while the PET film was purchased from the commercial market. Nd:YAG pulsed laser has been used to irradiate the samples at 2 minutes, 4 minutes, and 6 minutes respectively. The XRD (X-ray diffraction) pattern shows that silver-doped polystyrene peak at around angle θ = 26° tends to decrease after the bombardment of Nd:YAG pulsed laser. This indicates that the crystallinity of PET film decreased after laser irradiation. The Raman spectra have revealed the zwitter characteristics of silver-doped polystyrene are shifting of bands at 1380 cm−1 and 1560 cm−1 upon laser irradiation. For PET film, the Raman spectra showed that the exposed regions tend to change to cross-linking/chain-scissoring at 2 minutes and 4 minutes of irradiation. The surface roughness first increases and decreases upon irradiation. These results indicate that silver-doped polystyrene/polyethylene terephthalate (PET) thin film is appropriate for solar cell applications. © 2022 The Royal Society of Chemistry.

Despite the wide range of research on pedestrian safety, previous studies have failed to analyse the real-time data of pedestrian walking misbehaviour on the basis of either pedestrian behaviour distraction or movements during specific activities to realise pedestrian safety for positive (normal) or aggressive pedestrians. Practically, pedestrian walking behaviour should be recognised, and aggressive pedestrians should be differentiated from normal pedestrians. This type of pedestrian behaviour recognition can be converted into a classification problem, which is the main challenge for pedestrian safety systems. In addressing the classification challenge, three issues should be considered: identification of factors, collection of data and exchange of data in the contexts of wireless communication and network failure. Thus, this work proposes a novel approach to pedestrian walking behaviour classification in the aforementioned contexts. Three useful phases are proposed for the methodology of this study. In the first phase involving factor identification, several factors of the irregular walking behaviour of mobile phone users are established by constructing a questionnaire that can determine users’ options (attitudes/opinions) about mobile usage whilst walking on the street. In the second phase involving data collection, four different testing scenarios are developed to acquire the real-time data of pedestrian walking behaviour by using gyroscope sensors. In the third phase involving data exchange, the proposed approach is presented on the basis of two modules. The first module for pedestrian behaviour classification uses random forest and decision tree classifiers part of machine learning techniques via wireless communication when a server becomes available. The developed module is then trained and evaluated using five category sets to obtain the best classification of pedestrian walking behaviour. The second module is based on four standard vectors for classifying pedestrian walking behaviour when a server is unavailable. Fault-tolerant pedestrian walking behaviour is identified and is initiated when failures occur in a network. Two sets of real-time data are presented in this work. The first dataset is related to the questionnaire data from 262 sampled respondents, and the second dataset comprises data on 263 sampled participants with pedestrian walking signals. Experimental results confirm the efficacy of the proposed approach relative to previous ones. © 2021, The Author(s).

Electrocardiography (ECG) is a technique for observing and recording the electrical activity of the human heart. The usage of an ECG signal is common among clinical professionals in the collection of time data for the examination of any rhythmic conditions associated with a subject. The investigation was carried out in order to computerize the assignment by exhibiting the issue using encoder-decoder techniques, creating the information that was simply typical of it, and utilising misfortune appropriation to anticipate standard or anomalous information. On a broad variety of applications such as voice recognition and prediction, the long short-term memory (LSTM) fully connected layer (FCL) and the two convolutional neural networks (CNNs) have shown superior performance over deep learning networks (DLNs). DNNs are suitable for making high points for a more divisible region and CNNs are suitable for reducing recurrence types, LSTMs are appropriate for temporary displays, in the same way as CNNs are appropriate for reducing recurrence types. The CNN, LSTM, and DNN algorithms are acceptable for viewing. The complementarity of DNNs, CNNs, and LSTMs was investigated in this research by bringing them all together under the single architectural company. The researchers got the ECG data from the MIT-BIH arrhythmia database as a result of the investigation. Our results demonstrate that the approach proposed may expressively describe ECG series and identify abnormalities via scores that outperform existing supervised and unsupervised methods in both the short term and long term. The LSTM network and FCL additionally demonstrated that the unbalanced datasets associated with the ECG beat detection problem could be consistently resolved and that they were not susceptible to the accuracy of ECG signals. It is recommended that cardiologists employ the unique technique to aid them in performing reliable and impartial interpretation of ECG data in telemedicine settings. © 2022 Dhanagopal Ramachandran et al.

The main aim of this study was to address the problem of congestion in TCP nonlinear systems in the presence of mismatched exogenous disturbances. To achieve this problem, two methods are proposed: the first is active queuing management, based on two proposed controllers, an NLPID and STC-SM, while the second is the application of active queuing management-based anti-disturbance techniques such as active disturbance rejection control (ADRC) and the nonlinear disturbance observer (NLDO). The proposed ADRC consists of a new NLPID and a new super-twisting sliding mode controller (STC-SM), which functions as a novel NLSEF, and a proposed NLESO estimates the applied disturbance and cancels it in a responsive manner. A new tracking differentiator with a novel function is also used to generate a smooth and accurate reference signal and derivative. The NLDO is proposed to estimate the disturbance and combine this with the control signal of the designed nonlinear controller as a way to compensate for the disturbance. The simulation results for the proposed scheme (ADRC) as applied to a nonlinear model of the TCP network are thus found to provide smoother and more accurate tracking of the desired value, with high robustness against applied disturbance, as compared to the other schemes introduced in this study. The proposed scheme also shows a noticeable improvement in terms of the utilized performance indices and the OPI. © 2022 Anwer S. Aljuboury et al.

Cloud-based enterprise resource planning (ERP) and cloud computing are critical requirements for all SMEs since they can be used to facilitate the SMEs’ growth by creating competitive and personalized innovations considering their required business scope. To date, the growth of cloud technologies has led to the development of new systems and applications in many fields and areas including businesses. Our previous study proposed an adoption model to investigate the main determinants and logistical factors that influence decision-makers of SMEs to adopt cloud-based ERP systems. The aim of this research is to enhance the previous work by evaluating and validating the new model in real life to determine whether it has achieved what it was developed for and determine the reliability of the research results. The methodology and results of the evaluation and validation process of the proposed model are presented in this research. Considering there is little documentation in the literature specifically relevant to how proposed models have been evaluated and validated, hence providing this insight will assist both the academic researchers and decision-makers. The evaluation and validation methodology and the model itself contribute toward a better understanding of adoption processes. Furthermore, the evaluation and validation procedure in future work can be used to measure, enhance and determine whether the proposed models can be used in real life. © 2022, International Journal of Interactive Mobile Technologies. All Rights Reserved.

Security issues and Internet of Things (IoT) risks in several areas are growing steadily with the increased usage of IoT. The systems have developed weaknesses in computer and memory constraints in most IoT operating systems. IoT devices typically cannot operate complicated defense measures because of their poor processing capabilities. A shortage of IoT ecosystems is the most critical impediment to developing a secured IoT device. In addition, security issues create several problems, such as data access control, attacks, vulnerabilities, and privacy protection issues. These security issues lead to affect the originality of the data that cause to affects the data analysis. This research proposes an AI-based security method for the IoT environment (AI-SM-IoT) system to overcome security problems in IoT. This design was based on the edge of the network of AI-enabled security components for IoT emergency preparedness. The modules presented detect, identify and continue to identify the phase of an assault life span based on the concept of the cyberspace killing chain. It outlines each long-term security in the proposed framework and proves its effectiveness in practical applications across diverse threats. In addition, each risk in the borders layer is dealt with by integrating artificial intelligence (AI) safety modules into a separate layer of AI-SM-IoT delivered by services. It contrasted the system framework with the previous designs. It described the architectural freedom from the base areas of the project and its relatively low latency, which provides safety as a service rather than an embedded network edge on the internet of-things design. It assessed the proposed design based on the administration score of the IoT platform, throughput, security, and working time © 2022, Authors. This is an open access article under the Creative Commons CC BY license

This paper presents a method for online image restoration and enhancement via learning SVM model. The proposed method first obtains the images with the camera's laptop, then, process this image with learning approach via machine learning model (i.e. SVM model), where each image is divided into front-lit and back-lit segments. After that, the front-lit segment is expanded with the exposure of each pixel. Finally, both segments are merged together to produce the final restored image. Experiments and comparisons are performed on the proposed method, and shows that it outperformed standard restoration method. © 2022 IEEE.

Driver behavior is a determining factor in more than 90% of road accidents. Previous research regarding the relationship between speeding behavior and crashes suggests that drivers who engage in frequent and extreme speeding behavior are overinvolved in crashes. Consequently, there is a significant benefit in identifying drivers who engage in unsafe driving practices to enhance road safety. The proposed method uses continuously logged driving data to collect vehicle operation information, including vehicle speed, engine revolutions per minute (RPM), throttle position, and calculated engine load via the on-board diagnostics (OBD) interface. Then the proposed method makes use of severity stratification of acceleration to create a driving behavior classification model to determine whether the current driving behavior belongs to safe driving or not. The safe driving behavior is characterized by an acceleration value that ranges from about ±2 m/s2 . The risk of collision starts from ±4 m/s2, which represents in this study the aggressive drivers. By measuring the in-vehicle accelerations, it is possible to categorize the driving behavior into four main classes based on real-time experiments: safe drivers, normal, aggressive, and dangerous drivers. Subsequently, the driver’s characteristics derived from the driver model are embedded into the advanced driver assistance systems. When the vehicle is in a risk situation, the system based on nRF24L01 + power amplifier/low noise amplifier PA/LNA, global positioning system GPS, and OBD-II passes a signal to the driver using a dedicated liquid-crystal display LCD and light signal. Experimental results show the correctness of the proposed driving behavior analysis method can achieve an average of 90% accuracy rate in various driving scenarios. © 2021 by the authors. Licensee MDPI, Basel, Switzerland.

Driver behavior is a concerning issue in the area of intelligent transportation system (ITS). Driver behavior is a significant key player in a wide range of unpleasant events during the ride, such as accidents or crashes, traffic congestion, harsh braking, and acceleration/deceleration. Influencing factors of driver behavior have been explored in several studies. It is imperative to investigate these factors in order to provide a comprehensive analysis and to categorize them on the basis of a coherent taxonomy. With that, this study conducted a systematic review on prior studies that focused on bus driver behavior, particularly in the ITS. This study also established a taxonomy on the topic of driver behavior in multiple areas of ITS and their classifications. Different databases, namely ScienceDirect, Web of Science, and IEEE Explore, were utilized to obtain relevant articles from 2008 to 2021 (15 April). Several filtering and scanning stages were performed according to the exclusion/inclusion criteria on all 2,803 articles obtained; however, only 87 articles met the criteria. The final set of articles were categorized into a taxonomy. The first part of the taxonomy focuses on five main factors that influence driver behavior: environmental, demographic, habit, vehicle, and on-road routine factors. The second part of the taxonomy discusses the mapping of data collection methods on the basis of four categories: real-time data collection, survey, simulation, and benchmark. Discussion and analysis were provided to highlight the critical literature gaps on bus driver behavior in the ITS, involving the use of real-time data collection, which is imperative for acquiring highly accurate and sophisticated data. This multi-field systematic review has exposed new research opportunities, motivations, challenges, limitations, and recommendations and highlighted the need for the synergistic integration of interdisciplinary works. Overall, this study presented pathways solution in future direction on the basis of three sequenced phases, namely design, labeling and validation, and machine learning. This study can serve as a guide for future researchers, as it addressed the ambiguities in the ITS-driver behavior domain and provided valuable information on these ITS-driver behavior trends. © 2013 IEEE.

Cervical cancer is a prevalent and deadly cancer that affects women all over the world. It affects about 0.5 million women anually and results in over 0.3 million fatalities. Diagnosis of this cancer was previously done manually, which could result in false positives or negatives. The researchers are still contemplating how to detect cervical cancer automatically and how to evaluate Pap smear images. Hence, this paper has reviewed several detection methods from the previous researches that has been done before. This paper reviews pre-processing, detection method framework for nucleus detection, and analysis performance of the method selected. There are four methods based on a reviewed technique from previous studies that have been running through the experimental procedure using Matlab, and the dataset used is established Herlev Dataset. The results show that the highest performance assessment metric values obtain from Method 1: Thresholding and Trace region boundaries in a binary image with the values of precision 1.0, sensitivity 98.77%, specificity 98.76%, accuracy 98.77% and PSNR 25.74% for a single type of cell. Meanwhile, the average values of precision were 0.99, sensitivity 90.71%, specificity 96.55%, accuracy 92.91% and PSNR 16.22%. The experimental results are then compared to the existing methods from previous studies. They show that the improvement method is able to detect the nucleus of the cell with higher performance assessment values. On the other hand, the majority of current approaches can be used with either a single or a large number of cervical cancer smear images. This study might persuade other researchers to recognize the value of some of the existing detection techniques and offer a strong approach for developing and implementing new solutions. © 2021, Tech Science Press. All rights reserved.

Pedestrian safety is a serious problem in transportation systems because pedestrian and vehicle crashes often result in fatalities amongst vulnerable road users. A vehicle-to-pedestrian (V2P) communication system allows data exchange between pedestrians and vehicles to prevent or minimise potential dangers of accidents from happening. This work aimed to analyse and review the previous work associated with information exchange in the V2P communication system and classify the existing technology utilized for this purpose. Motivation, accessible problems confronting researchers, and suggestions posed to researchers to develop this critical area of study have been among the reasons considered to enhance awareness of the field's numerous qualitative facets in reported investigations and properties. All of the papers have been divided into four categories: growth, analysis, and survey, FRAMEWORK, and data exchange in the V2P communication system. V2P communication is an area that necessitates automated solutions, instruments, and techniques that allow pedestrian detection and prediction. Pedestrian identification and data sharing on V2P have been the subject of several experiments in order to support pedestrian protection techniques. The reasons, open barriers that hinder the technology's usefulness, and authors' suggestions have been used to identify the essential characteristics of this evolving sector. This study is intended to provide researchers with new resources and enable them to focus on the holes that have been found. © 2021. All rights reserved.

Road traffic accident management is very complex and sensitive issue. Recently, more attention has delivered to research in Vehicle-to-Pedestrian (V2P) communication systems, which function for different purposes such as safety or convenience and cater to different Vulnerable Road User (VRU) groups. This paper gives a brief overview for vehicle-to-pedestrian system with focusing on different communication technologies that V2P system employ it and the different mechanisms to interact with the users. The varying characteristics of different communication architecture and applications needs to be considered in an effective V2P system. Therefore, in the field of intelligent transportation research, there is the task of improving the road user safety such as, pedestrian through the development of technological tools, which can apply to reduce the number of accidents. © 2020 IEEE.

The field of vehicular communication technology is rapidly developing. vehicular communication technologies provide great social benefits such as reduced road accident and increased road efficiency. To improve traffic safety and provide drivers with the best end-to-end transportation experience, vehicles need to be more automated which is the most important goals of modern vehicular communication technologies. Utilizing Vehicle-to- Infrastructure communication (V2I) may be a keystone to enhance and promote the various vehicular communications applications. By the exchange of information between vehicles and road infrastructures, drivers will have more ability to predict and avoid various road hazard and thus make driving experience much safer. In this paper, we will focus on the study of the main requirement and component in V2I systems and present a review of the major V2I benefits related to safety and mobility applications. © 2020 IEEE.

Data exchange in Vehicle-to-vehicle (V2V) communications systems is a field that requires automated solutions, tools and methods and the capability to facilitate early detection and even a prediction. Many studies have focused on V2V system and its classification to improve road safety, reduce traffic congestion and help streamline the vehicle flow on the road. This study aims to review and analyse literature related to data exchange in V2V communications systems. The factors considered to improve the understanding of the field's various contextual aspects were derived from published studies. We systematically searched all articles about the classification and detection of data exchange in vehicles, as well as their evaluation. Three main databases, namely, ScienceDirect, Web of Science and IEEE Xplore from 2008 to 2018, were used. These indices were considered sufficiently extensive to encompass our literature. On the basis of our inclusion and exclusion criteria, 140 articles were selected. Most articles (53/140) are studies conducted in a V2V communication system; a number of papers (51/140) covered the actual attempts to develop V2V communications; and few papers (18/140) comprised framework proposals and architectures. The last portion (18/140) of articles presented review and survey articles. V2V collision avoidance system, which is a field requiring automated solutions, tools and methods, entails the capability to facilitate early detection. Several studies have been performed on the automatic detection of V2V and their subtypes to promote accurate detection. The basic characteristics of this emerging field are identified from the aspects of motivations, open challenges that impede the technology's utility, authors' recommendations and substantial analysis of the previous studies are discussed based on seven aspect (devices, number of scenario, test location, types of sensors, number of vehicle, evaluation techniques used and types of software). A propose research methodology as new direction is provided to solve the gaps identified in the analysis. This methodology consists of four phases; investigation, develop a hardware system, study and analysis, and evaluation phases. However, research areas on V2V communication with the scope of data exchange are varied. This systematic review is expected to open opportunities for researchers and encourage them to work on the identified gaps. © 2013 IEEE.

The vehicle-to-infrastructure (V2I) communication system allows the exchange of information between vehicles and road infrastructures. It aims to avoid or reduce vehicular accidents, increase mobility, and provide other road safety benefits. This paper aimed to review and analyze the literature on data exchanges in the V2I communication system. The factors considered to improve the understanding of various contextual aspects and the characteristics of the field were motivations, open challenges, and recommendations from other researchers. We systematically searched all articles on data exchanges in the V2I communication system from the three main databases, namely ScienceDirect, Web of Science, and IEEE Xplore, from 2008 to 2018. These indices were sufficiently extensive to encompass our field of literature. A total of 70 articles were selected based on our inclusion and exclusion criteria. Most studies (42/70) covered a developed V2I communication system, while numerous articles (22/70) focused on general research on the V2I communication system. The smallest portion of articles (6/70) comprised reviews and surveys. The V2I system plays a key role in vehicular ad hoc networks but is less implemented than vehicle-to-vehicle communication owing to its deployment costs and maintenance requirements. However, numerous studies have been conducted on the V2I communication system to promote its utility. Research areas on V2I communication classification vary but are all equally vital. We expect this systematic review to help emphasize current research opportunities and thus extend and create additional research fields. © 2013 IEEE.