مرکز منطقه ای اطلاع رسانی علوم و فناوریJournal of Information Systems and Telecommunication (JIST) 2322-14371352202623Adaptive PID and Fuzzy Logic Control for Yaw Attitude in LEO Satellites Adaptive PID and Fuzzy Logic Control for Yaw Attitude in LEO Satellites 26627710.66224/jist.48337.13.52.266enStanley EAjagbaDepartment of Electronic and Computer Engineering, University of Nigeria, Nsukka, Enugu State, Nigeria Udora NNwawelu Department of Electronic and Computer Engineering, University of Nigeria, Nsukka, Enugu State, Nigeria Bonaventure OEkengwuDepartment of Electronic and Computer Engineering, University of Nigeria, Nsukka, Enugu State, Nigeria Nnaemeka CAsiegbuDepartment of Electronic and Computer Engineering, University of Nigeria, Nsukka, Enugu State, Nigeria Dumtochukwu OOyekaDepartment of Electronic and Computer Engineering, University of Nigeria, Nsukka, Enugu State, Nigeria Maryrose MOgbukaDepartment of Electronic and Computer Engineering, University of Nigeria, Nsukka, Enugu State, Nigeria 20241021The significance of an effective satellite attitude control system lies in its ability to ensure that data acquisition by a Low Earth Orbit (LEO) satellite is of good quality and reliable. In this paper, the design of an adaptive Proportional Integral Derivative (PID) controller and its modified form (PIDD), which includes an additional derivative component for a microsatellite y-axis attitude control system (ACS), is presented. Additionally, a Fuzzy Logic Controller (FLC) and its enhanced version, called Adjustable Gain Enhanced FLC (AGE-FLC), were designed. Models of the amplifier, actuator, and satellite structure were developed to derive the transfer function of the LEO satellite's yaw-axis attitude dynamics. Model Reference Adaptive Control (MRAC) based Proportional Integral Derivative (PID), referred to as MRAC-PID and its modified form, MRAC-PIDD, were designed. The models of the various control systems were developed in MATLAB and were used to simulate the designed control systems. The simulation results and analysis revealed that the MRAC-PID controller offered the most efficient performance in terms of fast response and transient time, with a rise time of 1.74 seconds and a settling time of 6.19 seconds. Also, the MRAC-PIDD and AGE-FLC exhibited no overshoot, indicating efficient performance in terms of stability and smoothness in torque control. All proposed control systems for the LEO satellite yaw-axis ACS met the performance criteria, except for the PID and FLC controllers, which yielded overshoots of 12% and 21.97%, respectively. Generally, it suffices to say that the introduction of the designed adaptive PID/PIDD controllers and the AGE-FLC enhanced the system performance.

http://jist.ir/en/Article/Download/48337

مرکز منطقه ای اطلاع رسانی علوم و فناوریJournal of Information Systems and Telecommunication (JIST) 2322-14371352202623Automatic Concept Extraction from Persian News Text Based On Deep LearningAutomatic Concept Extraction from Persian News Text Based On Deep Learning27828810.66224/jist.48902.13.52.278enZahraSadatHosseiniDepartment of Electrical and Computer Engineering, Malek-Ashtar University of Technology, Tehran, Iran0009-0004-4539-694X SayedGholamHassan TabatabaeiDepartment of Electrical and Computer, Engineering Malek-Ashtar University of Technology, Tehran, Iran,https://orcid.org/0000-0003-2869-748X20241218One of the most critical issues in natural-language understanding is extracting concepts from the text. The concept expresses essential information from the text. Concept Extraction to the process of extracting and generating keyphrases that may exist or not in the text. Automatic concept extraction from the Persian news text is a challenging problem due to the complexity of the Persian language. In this paper, we first review traditional and deep learning-based models in keyphrase extraction and generation. Then, an automated Persian news concept extraction algorithm is presented, which exploits encoder-decoder models. Specifically, our proposed models use the output vector of BERT-Base and ParsBERT language models as a word embedding. The evaluation results have shown that changing the word embedding layer has improved recall, precision, and F1 measures about 3.15%. Since encoder-decoder models get inputs consecutively, the training time increases. Also, if the sentence is long, they cannot store much information from the sentences. Therefore, for the first time, we have used mT5-Base with Transformer architecture, which receives and processes data parallelly. Recall, precision, and F1 measures used for the concept extraction results of the mT5-Base model are 55.66%, 55.47%, and 55.48%, respectively. The F1 score has increased by 19.8% compared to the previous models. Therefore, this model is effective for extracting the concept of Persian news texts.

http://jist.ir/en/Article/Download/48902

مرکز منطقه ای اطلاع رسانی علوم و فناوریJournal of Information Systems and Telecommunication (JIST) 2322-14371352202623A Comprehensive Framework for Enhancing Intrusion Detection Systems through Advanced Analytical TechniquesA Comprehensive Framework for Enhancing Intrusion Detection Systems through Advanced Analytical Techniques28929910.66224/jist.49054.13.52.289enChetanGuptaDepartment of Computer Science and Engineering, Jaypee University of Engineering and Technology, Guna, IndiaAmitKumarDepartment of Computer Science and Engineering, Jaypee University of Engineering and Technology, Guna, IndiaNeelesh KumarJainDepartment of Computer Science and Engineering, Jaypee University of Engineering and Technology, Guna, India202511Intrusion detection systems (IDS) are security technologies that monitor system activity, network traffic, and settings to detect potential threats. IDS provide proactive security management, detecting anomalies and ensuring continuous monitoring. It protects critical assets, such as sensitive data and intellectual property, from unauthorized access or data breaches, preventing downtime and disruption to business operations. In this paper we present a hybrid model based on Principal Component Analysis (PCA) and XGBoost algorithms. To show the effectiveness of the proposed system, various parameters are evaluated on the standard NSL-KDD dataset. First we trained the model using trained dataset and then evaluate the performance the model using testing dataset. In proposed work the we store the data into two-dimensional structure then we standardized and take a most significance features of the data then calculate the covariance matrix, after that calculate the eigenvalues and eigenvectors of the matrix and short in the descending order and using principal component identify the new features and remove the insignificant features. The proposed model outperforms and produces 97.76% accuracy and 94.51% precision; the recall rate is 93.44% and 93.97% F1-Score, which is much better than the previous proposed models. This hybrid approach is better to handle the categorical data and able to find the pattern well and the outcome of the model clearly shows the effectiveness of the proposed system.

http://jist.ir/en/Article/Download/49054

مرکز منطقه ای اطلاع رسانی علوم و فناوریJournal of Information Systems and Telecommunication (JIST) 2322-14371352202623Compilation of Avatar Development Roadmap in Iranian Banking with the Life Cycle Approach of System Development and Human-Computer InteractionCompilation of Avatar Development Roadmap in Iranian Banking with the Life Cycle Approach of System Development and Human-Computer Interaction30031510.66224/jist.49601.13.52.300enAmir BahadorMorovatDepartment of Industrial and System Studies, Eyvanekey University, Semnan, Iran FarhadNazari zadehDepartment of Industrial Engineering, Malek Ashtar University of Technology, Tehran, Iran0009-0001-2596-3335AhmadHaghiri DehbarezDepartment of Industrial and System Studies, Eyvanekey University, Semnan, Iran 0000-0001-6123-3754202533The spread and use of emerging technologies have led to a significant transformation in the banking industry and has created widespread changes in the relationship between customers and banks. These changes have led to avatars, previously seen in Hollywood movies, entering the banking sector and are now used as useful tools for providing services to bank customers. Considering the move of Iranian banks towards the adoption of emerging technologies and the willingness of these banks’ customers to use these technologies, this research outlines the roadmap of avatar technology in six stages of requirements gathering and analysis, system development, system implementation and coding, testing, deployment and system operation and maintenance, utilizing the expertise of 11 researchers from private and public banks as well as IT and information technology specialists in Iran. In addition, at each stage of the roadmap, the focus has been on customer satisfaction and improving the quality of avatars through human-computer interaction approaches. For this purpose, an estimated timeline of 37 to 49 weeks has been proposed for the roadmap, which describes the necessary actions for each stage, along with possible challenges and issues. What is certain is that the implementation and use of avatars in the Iranian banking industry requires short-term, medium-term, and long-term strategic planning to enable the use of this technology, according to the proposed strategic roadmap.

http://jist.ir/en/Article/Download/49601

مرکز منطقه ای اطلاع رسانی علوم و فناوریJournal of Information Systems and Telecommunication (JIST) 2322-14371352202623Optimally DBS Placement In 6G Communication Networks Using Improved Gray Wolf Optimization Algorithm to Enhance Network Energy EfficiencyOptimally DBS Placement In 6G Communication Networks Using Improved Gray Wolf Optimization Algorithm to Enhance Network Energy Efficiency31632510.66224/jist.50264.13.52.316enHusseinShakir Diwan Al-KhulaifawiDepartment of Electrical and Computer Engineering, University of Tabriz, Tabriz, Iran.https://orcid.org/0009-0003-4503-006XMahdiNangirDepartment of Electrical and Computer Engineering, University of Tabriz, Tabriz, Iran.https://orcid.org/0000-0002-1926-743X2025517The transition to sixth-generation (6G) networks demands highly energy-efficient solutions for large-scale IoT services. Drone Base Stations (DBSs) offer flexible coverage, but their three-dimensional placement must be optimized to reduce both transmission and hovering energy. This paper, model DBS deployment as a power-minimization problem and introduce an Improved Grey Wolf Optimization (IGWO) algorithm that integrates adaptive control parameters, exponential weighting of leader contributions (alpha/beta/delta), and a dynamic control structure that progressively favors elite solutions. This design improves search efficiency in high-dimensional, nonlinear spaces and reduces the risk of premature convergence. Extensive MATLAB simulations across multiple propagation environments demonstrate that IGWO achieves lower network power consumption and faster convergence compared to standard metaheuristics, while preserving coverage and connectivity. Specifically, the simulation results demonstrate that the proposed method achieves a remarkable superiority over other optimization algorithms, showing more than a 2% improvement compared to the best among them the standard GWO algorithm—thereby confirming its effectiveness and efficiency in low-power network scenarios.

http://jist.ir/en/Article/Download/50264

مرکز منطقه ای اطلاع رسانی علوم و فناوریJournal of Information Systems and Telecommunication (JIST) 2322-14371352202623Fabric Defect Identification based on KNN and PCA AlgorithmsFabric Defect Identification based on KNN and PCA Algorithms32633210.66224/jist.49914.13.52.326enZahraNouriDepartment of Communications Engineering, University of Sistan and Baluchestan, Zahedan, Iran FarahnazMohannaDepartment of Communications Engineering, University of Sistan and Baluchestan, Zahedan, Iran 0000000286896201MinaBolukiDepartment of Communications Engineering, University of Sistan and Baluchestan, Zahedan, Iran 2025412In this study, a K-Nearest Neighbor (KNN) classifier is employed for fabric defect identification. First, directional Grey-Level Co-occurrence Matrix (GLCM) of the fabric image is computed in , and directions. Six intensity-based features are then extracted from these directional GLCMs. In addition, the minimum, maximum, median, and mean grey levels of the fabric image are computed. These sixteen features are combined into a single feature vector representing the fabric image. Next, Principal Component Analysis (PCA) is applied to reduce the dimensionality of the feature vector. The reduced features are then classified using the KNN classifier, categorizing each fabric image as either defective or defect-free based on training data. To localize defects, patches containing defects are segmented from the original fabric image. Features of these defect patches are extracted, reduced via PCA, and classified using KNN. Finally, each defect class is identified, and defect locations are visualized using morphological operations. The proposed method is evaluated on the comprehensive TILDA dataset, which contains 3,200) fabric images (both defective and defect-free). Experimental results demonstrate a mean average accuracy of 95.65% for fabric defect identification across classes , , and .

http://jist.ir/en/Article/Download/49914

مرکز منطقه ای اطلاع رسانی علوم و فناوریJournal of Information Systems and Telecommunication (JIST) 2322-14371352202623Federated Learning for Privacy-Preserving Intrusion Detection: A Systematic Review, Taxonomy, Challenges and Future DirectionsFederated Learning for Privacy-Preserving Intrusion Detection: A Systematic Review, Taxonomy, Challenges and Future Directions33334510.66224/jist.45751.13.52.333enDattatray RaghunathKaleDepartment of Computer Science & Engineering, MIT Art Design and Technology University, Pune, India 0009-0008-8843-452XSwatiShirke-DeshmukhDepartment of Computer Science & Engineering, Pimpri Chinchwad University, Pune, Maharashtra, Indiahttps://orcid.org/0000-0001-6668-5610AmulkumarJadhavDepartment of Computer Science & Engineering, D Y Patil College of Engineering and Technology, Kolhapur, IndiaShrihari Khatawkar Department of Computer Science & Engineering, Annasaheb Dange College of Engineering and Technology, AshtaSunnyMohiteD Y Patil College of Engineering and Technology, Kolhapur, IndiaSarangPatilAmity School of Engineering and Technology, Amity University, Mumbai, Maharashtra, IndiaMadhavSalunkheAnnasaheb Dange College of Engineering and Technology AshtaRahulSonkambleDepartment of Computer Science & Engineering, Pimpri Chinchwad University, Pune, Maharashtra, Indiahttps://orcid.org/0000-0001-6075-9519202428This paper presents a systematic review of intrusion detection systems (IDS) that leverage federated learning (FL) to enhance privacy in distributed cybersecurity environments. A total of 78 peer-reviewed studies published between 2019 and 2024 were selected using PRISMA guidelines. We categorize FL-based IDS solutions based on architecture (centralized, decentralized, hierarchical), aggregation methods (e.g., FedAvg, DAFL), and privacy-preserving techniques (e.g., differential privacy, homomorphic encryption). The survey also examines solutions to key challenges such as communication overhead, data heterogeneity, and poisoning attacks. Furthermore, this study outlines unresolved issues and proposes future research directions, including adaptive federated optimization and cross-domain deployments. This review serves as a valuable resource for researchers and practitioners aiming to develop privacy-aware, scalable, and intelligent IDS using federated learning.

http://jist.ir/en/Article/Download/45751