Transactions on Machine Intelligence2821-16936320231001A Bayesian Model and Bayesian Classification on the Data Obtained from Children's Educational Activity in the IoT Environment12613618142810.47176/TMI.2023.126ENM.MoradiInformation Technology and Computer Engineering, University of Qom, Qom, Iran0000-0002-3124-3289Journal Article20220417Over the past decade, there has been a significant increase in interest and research concerning the integration of technology within educational environments. A notable outcome of incorporating such technology in early childhood education is the enhancement of children's motivation, self-confidence, and collaborative abilities. The importance of early childhood education can be examined from two perspectives: the adaptability of young minds in contemporary times and the lasting impact of education during this formative period. To assess the effectiveness of technology in education, a study utilized Bayesian modeling to analyze data collected through Internet of Things (IoT) technologies. Specifically, a classifier was developed to predict future educational outcomes for children based on their previous performance. The test data confirmed the model's high accuracy, underscoring the positive potential of technology in shaping the educational experiences of young learners. This approach aligns with broader research trends that employ Bayesian networks to predict student performance and learning behaviors. For instance, studies have demonstrated the application of Bayesian models in forecasting student outcomes and identifying at-risk students, thereby facilitating timely interventions and personalized learning strategies . Such methodologies highlight the transformative role of technology and advanced analytics in modern education, particularly in enhancing early childhood learning experiences.https://www.tmachineintelligence.ir/article_181428_13e849f87865123639269aaaae624474.pdfTransactions on Machine Intelligence2821-16936320231001A Security Method for Intrusion Detection in Mobile Ad Hoc Networks Based on DSR Protocol13714518143210.47176/TMI.2023.137ENS.PanahiDepartment of Computer Engineering, Islamic Azad University,Ardabil , IranS.Jahanbakhsh GudakahrizDepartment of Computer Engineering, Islamic Azad University,Germi branch , Germi0000-0001-9397-723XJournal Article20230525A mobile ad hoc network consists of mobile nodes communicating with each other without centralized control or infrastructure. The inherent wireless nature of these networks introduces significant security challenges. However, recognizing that routing plays a pivotal role in most mobile ad hoc network operations, enhancing the security of routes can contribute to overall network performance. This paper introduces a novel technique aimed at improving intrusion detection in mobile ad hoc networks by identifying and detecting black hole nodes. The proposed solution involves the introduction of the S-DSR protocol, a variant of the DSR protocol. The primary objective is to enhance intrusion detection by identifying black hole nodes during the route detection phase and subsequently excluding routes containing them. This ensures secure data transmission and reception within the network. The protocol, named S-DSR, is designed to address these security concerns. The results obtained from simulations conducted in the NS-2 environment indicate that the S-DSR protocol outperforms the traditional DSR protocol in terms of network performance.https://www.tmachineintelligence.ir/article_181432_36487670b36a7e42c844148a33858ffc.pdfTransactions on Machine Intelligence2821-16936320231001Investigating the relations proposed for the dynamic impact factor in the railway (in terms of velocity parameter of the railway vehicle)14615917138710.47176/TMI.2023.146ENM. H.SayyadiDepartment of Railway Engineering and Transportation Planning, Faculty of Civil and Transportation Engineering, Isfahan University, Isfahan, IranA. M.FereidoonfarDepartment of Mechanical Engineering, Faculty of Technical and Engineering, Isfahan University, Isfahan, IranJournal Article20230507Railway systems are subject to complex vertical dynamic forces, which arise due to the movement of trains and the presence of structural irregularities or defects within both the track infrastructure and rolling stock. Accurately evaluating these dynamic forces is crucial for ensuring the safety and longevity of railway components, yet the process is often time-consuming and computationally demanding when dynamic effects are fully considered. As a practical alternative in design applications, these forces are typically approximated as quasi-static. In this approach, the static load defined as the total weight of a vehicle divided by the number of wheels is adjusted by a dynamic impact factor to account for additional loads generated during motion. Various researchers and transportation authorities have proposed different formulas for calculating this impact factor, many of which incorporate the influence of train speed. Among the most commonly referenced models, Talbot's equation recommends conservative dynamic amplification at speeds exceeding 44 km/h, indicating a precautionary design strategy. Conversely, the formulation introduced by Mir Mohammad Sadeghi predicts the lowest dynamic load increases at speeds above 84 km/h, suggesting potential for more optimized design parameters. This comparative analysis underscores the importance of selecting an appropriate dynamic impact factor based on vehicle speed and operational conditions.https://www.tmachineintelligence.ir/article_171387_ce78f69fc27cd85529d8b5901ffd4d7d.pdfTransactions on Machine Intelligence2821-16936320231001Numerical analysis of the effect of rotor slot opening on induction motor performance using finite element method16016518143910.47176/TMI.2023.160ENA.BehniafarDepartment of electrical and computer engineering
Gonbad Kavous University
Gonbad kavous, Iran0000-0002-5382-7410Journal Article20230404This study assesses the impact of alterations in rotor slot width on the performance of a squirrel cage induction motor. Despite the widespread use of induction motors in various industries due to their simple structure, designing them accurately remains a challenge. Many design algorithms rely on analytical equations, which often fall short in providing precise results for factors like leakage fluxes and the effects of magnetic saturation. To address this limitation, finite element methods have been employed for improved accuracy, but their drawback lies in their time-consuming nature, making them impractical for use in design algorithms with optimization components. Consequently, there is a need to establish practical experimental guidelines that designers can incorporate into analytical design algorithms for obtaining satisfactory results swiftly. This paper specifically evaluates motor performance by varying the width of the rotor slot opening from fully closed to fully open, presenting valuable results to enhance design algorithms.https://www.tmachineintelligence.ir/article_181439_fd8cf493db5a9c2e3c03e76d722518f7.pdfTransactions on Machine Intelligence2821-16936320231001Analysis of the Process of Forming Stainless Steel Sheets using the Forming Limit Diagram.16617418141810.47176/TMI.2023.166ENF.TurkiMechanical Engineering, K. N. Toosi University of Technology, Tehran, IranH.Seyed SalehiMechanical Engineering, K. N. Toosi University of Technology, Tehran, IranA. JalaliAghcheiMechanical Engineering, K. N. Toosi University of Technology, Tehran, Iran0000-0003-2735-6763J.Bakhtiari DoostMechanical Engineering, K. N. Toosi University of Technology, Tehran, IranJournal Article20230505Formability in sheet metal forming refers to the material's ability to undergo plastic deformation without incurring defects during the manufacturing process. This typically involves shaping the metal sheet by applying force through a punch and die system, resulting in a three-dimensional deformation of the material. A key tool for evaluating formability is the Forming Limit Diagram (FLD), which graphically represents the forming limit curves. These curves illustrate combinations of major and minor strains at which localized necking also known as local throat initiation begins, thus indicating the material’s plastic deformation threshold under various loading conditions. In this study, the tensile behavior of a sheet metal component was analyzed under different strain rates to assess its formability. The forming limit curve was derived through three distinct approaches: experimental testing, theoretical modeling, and finite element analysis. To support these methods, the material’s work-hardening behavior was characterized using Swift’s law, with its parameters determined from experimental data. The comparison of the results obtained from all three methodologies revealed a high degree of consistency, confirming the validity and reliability of the theoretical and simulation models in predicting the material’s formability. These findings offer valuable guidance for improving sheet metal forming processes and minimizing failure during production.https://www.tmachineintelligence.ir/article_181418_95e70fa61dd4d5f9c8dd8aafb70342eb.pdfTransactions on Machine Intelligence2821-16936320231001Using Reinforcement Learning to Find the Shortest Path between two Locations on the Public Roadways17518118144410.47176/TMI.2023.175ENH. R.NajiDepartment of Computer Engineering and Information Technology Graduate University of Advance Technology Kerman, Iran0000-0001-8422-2433F.AmirteimouryDepartment of Computer Engineering and Information Technology Islamic Azad University of Kerman, Kerman, IranJournal Article20230403With the rapid increase in urban populations, the proliferation of private vehicles, and the worsening state of air quality, conventional urban transportation planning methods are struggling to meet modern demands. These traditional systems often lack the adaptability and intelligence required to respond effectively to dynamic and complex traffic patterns. In response to these challenges, this study proposes a reinforcement learning (RL)-based approach designed to enhance urban transportation efficiency and sustainability. The core objective of the proposed model is to determine optimal routes between origin and destination points by dynamically avoiding congested areas. Unlike static routing algorithms, the RL model continuously learns and adapts to traffic conditions, enabling the selection of routes that minimize travel time and reduce vehicle idling. As a result, the approach significantly contributes to lowering fossil fuel consumption and energy use, while simultaneously addressing the broader environmental concern of urban air pollution. The integration of artificial intelligence in transportation systems through RL not only enhances service quality and traffic flow but also supports the development of smarter, greener cities. This study underscores the transformative potential of RL in revolutionizing traffic management systems and presents a viable framework for future intelligent transportation networks.https://www.tmachineintelligence.ir/article_181444_3c923252d3cdecbe02037251dbe8f996.pdf