Transactions on Machine Intelligence2821-16938120250301Genetic Algorithm Optimization with Deterministic Circular Crossover Operator for Unit Commitment Problem (UCP)11621399910.47176/TMI.2025.1ENM.Esmail BeagAssistant Professor, Department of Electrical Engineering, Faculty of Engineering, Islamic Azad University, Bushehr Branch, Bushehr, IranS.NajibiDepartment of Electrical Engineering, Faculty of Engineering, Islamic Azad University, Bushehr Branch, Bushehr, Iran0000-0002-3247-3473Journal Article20241203One of the major drawbacks of the conventional genetic algorithm (GA) is premature convergence, which typically occurs because the selection operator relies heavily on the genetic information of the best individuals in the population. When the chromosomes of individuals are directly accessible, their genetic structure becomes easily exploitable during selection, increasing the likelihood of converging to suboptimal solutions. Moreover, in linear chromosome representations, the crossover process is highly dependent on the encoding scheme and the positional arrangement of genes, resulting in a very low probability of structural variation through mutation particularly toward the end of the chromosome. In this study, the unit commitment problem is addressed using a GA enhanced with a deterministic selection operator, in which all individuals in the population are treated as parents. Additionally, a circular crossover (CR) operator is employed, converting the chromosome into a ring-shaped structure. This approach increases the diversity of potential recombination’s and reduces the risk of early stagnation. The experimental results demonstrate that incorporating these operators leads to superior convergence behavior and enables the GA to achieve more optimal solutions compared with conventional genetic operators.https://www.tmachineintelligence.ir/article_213999_f22831a9d3173e63b167eb14d4b60939.pdfTransactions on Machine Intelligence2821-16938120250301Phase Transition of the Two-Dimensional Ising Model in a Homogeneous Magnetic Field Using the Metropolis Monte Carlo Algorithm and Separation of Different Phases via CNN172521419810.47176/TMI.2025.17ENR.Rastgar PoorSchool of Engineering Sciences, College of Engineering, University of Tehran, Tehran, IranN.MajdAssistant Professor, Department of engineering science, college of engineering, university of Tehran, Tehran, Iran0000-0002-5652-7405Journal Article20241203Quantum spin networks represent configurations of spins arranged on a topological lattice, where the spin interactions are governed by the system's Hamiltonian. These networks are critical for understanding magnetic materials, as the arrangement of spins and the type of interaction between neighboring spins determine the macroscopic behavior of the system. The behavior of these systems is further influenced by the presence of external magnetic fields. In this paper, we first investigate the various phases of the two-dimensional Ising lattice with periodic boundary conditions under the influence of a uniform external magnetic field. The exploration of these phases is performed using the Metropolis Monte Carlo (MP-MN) algorithm, a well-established statistical method for simulating spin systems. Subsequently, we explore the potential of deep learning, specifically convolutional neural networks (CNN), in identifying and predicting these phases of spin lattices. The CNN's ability to classify different phases of the two-dimensional Ising model in the presence of a homogeneous magnetic field at a constant temperature is examined. The study aims to demonstrate how machine learning models, particularly CNNs, can effectively detect phase transitions and predict the system's behavior, which traditionally requires extensive computational methods. Finally, the performance of the CNN algorithm is evaluated by assessing its accuracy in predicting different phases of the Ising model.https://www.tmachineintelligence.ir/article_214198_73b8a31aed7035b0267911340ed25a89.pdfTransactions on Machine Intelligence2821-16938120250301Design and Development of a Knee Rehabilitation Robot to Improve Range of Motion and Strength in Injured Athletes263722418710.47176/TMI.2025.26ENS.Javanshiri VaziriMSc, Mechatronics Engineering, University of Tehran, International Campus – Kish Island, IranN.Mohammad HashemiPhD Candidate, Mechanical Engineering, Faculty of Engineering, University of Tehran, Tehran, IranK.Ghaemi OsgouieAssistant Professor, Mechanical Engineering, Faculty of Engineering, University of Tehran, Tehran, IranJournal Article20241226The knee joint, being the largest and most complex synovial joint in the body, plays a crucial role in weight-bearing and bodily movements. Due to its wide range of motion, the knee joint is highly vulnerable to injury, and damage to it can lead to movement limitations, significant disability, and a reduction in the quality of life. The use of robotics in rehabilitation has attracted significant attention in knee rehabilitation exercises, offering extensive capabilities for functional adaptation of knee movements in injured athletes. This study focuses on the knee joint's musculoskeletal structure and dynamics, using mathematical modeling and simulation to analyze its behavior. The goal of this research is to identify the forces, torques, and reaction forces in the tibiofemoral joint (the connection between the shinbone and femur) to design and develop a rehabilitation device that reduces knee injuries and is suitable for athletes of different weights and heights. In designing this sports device, emphasis is placed on reducing the negative effects of variable forces on the knee muscles, particularly at angles where the forces reach their maximum. The ultimate goal is to reduce the risk of injury in this area. Furthermore, the device should be designed to be adjustable for athletes of different body sizes, which can be achieved by applying standard settings based on the actual forces exerted on the knee. Lastly, a genetic algorithm is used to optimize the lengths of the links and their placement in the mechanism.https://www.tmachineintelligence.ir/article_224187_51fb1e82f5dabef01f70998c1b1dd9d1.pdfTransactions on Machine Intelligence2821-16938120250301Medical Image Processing of Patients for Skin Cancer Diagnosis Using Artificial Intelligence384622418810.47176/TMI.2025.38ENS.GorgbandiDepartment of Computer Science, Faculty of Engineering, Falaq Unit, Islamic Azad University, Arak, IranS.NazariAssistant Professor, Department of Computer Science, Islamic Azad University, Arak, Iran0009-0008-4203-4352Journal Article20250102Skin cancer represents a serious and growing global public health challenge, with incidence rates increasing steadily across diverse populations. Early diagnosis and timely intervention play a vital role in reducing mortality and improving treatment outcomes. Traditionally, accurate diagnosis has relied on the expertise of trained dermatologists, posing accessibility challenges in resource-limited settings. In recent years, artificial intelligence (AI) technologies particularly deep learning and advanced image processing techniques have emerged as promising tools for assisting in medical image analysis and automated disease detection. This study presents a computer-aided diagnosis (CAD) system based on deep convolutional neural networks (CNNs) designed for the early detection of skin cancer through dermoscopic image analysis. The CNN model was trained and tested on a curated dataset, and achieved a prediction accuracy of 90.5%. The system demonstrates strong potential for identifying malignant skin lesions with high precision, contributing to the rapid, non-invasive, and cost-effective assessment of skin abnormalities. The use of deep learning in this context not only improves diagnostic speed but also offers a scalable solution for screening large populations. These findings underscore the transformative role of AI in dermatological diagnostics and highlight the capability of CNN-based systems to complement clinical expertise. Future work will focus on enhancing model robustness, incorporating multi-modal data, and validating performance through real-world clinical trials.https://www.tmachineintelligence.ir/article_224188_fd800b92278b59ccdfed82378ea02f8c.pdfTransactions on Machine Intelligence2821-16938120250301Fault Detection and Location in Distribution Networks Using the Traveling Wave Theory Based on Hilbert-Huang Transform475622418910.47176/TMI.2025.47ENS.DarbaniDepartment of Electrical Engineering - Power, Faculty of Engineering, Urmia Branch, Islamic Azad University, Urmia, IranJ.GhanbariDepartment of Electrical Engineering - Power, Faculty of Engineering, Urmia Branch, Islamic Azad University, Urmia, IranM.BeiraghiAssistant Professor, Department of Electrical Engineering, Urmia Branch, Islamic Azad University, Urmia, Iran0000-0003-3332-1719Journal Article20250106Identifying and locating various faults in distribution networks can significantly reduce maintenance costs in these systems. For this reason, intelligent methods for fault detection and location with high accuracy and speed have recently gained attention from system operators and planners in power systems. This paper proposes an intelligent fault detection and location model based on the concept of traveling waves (TW), where the input signal is generated using the Hilbert-Huang Transform (HHT). In the proposed method, the voltage at all network terminals is measured and converted into the phasor domain in the complex space. The obtained phasor components are processed using the Hilbert-Huang Transform (HHT), and the intrinsic mode functions (IMFs) are extracted. The instantaneous magnitude of the first IMF associated with each voltage signal determines the branch where the fault has occurred, and this component is also used for fault detection and determining the fault occurrence time. Subsequently, by identifying the branch and comparing the time-domain components of the traveling wave signals from both the initial and terminal terminals of the branch, the precise fault location on the branch is determined using the concept of traveling waves. Simulation results show that the fault location estimation accuracy under various scenarios is over 98%.https://www.tmachineintelligence.ir/article_224189_a724b6b78e909e776d2e1953ab65466c.pdfTransactions on Machine Intelligence2821-16938120250301Improving Medical Image Segmentation Using a Hybrid ResUNet-Transformer Architecture for Liver Tumor Detection576822419010.47176/TMI.2025.57ENN.ShakeriDepartment of Biomedical Engineering, South Tehran Branch, Islamic Azad University, Tehran, IranO.Rahmani SeryasatAssistant Professor, Department of Electrical Engineering, Shams Higher Education Institute, Gorgan, Iran0000-0002-9289-6128Journal Article20250122In this research, a new method for segmentation of medical images is presented using a combination of ResUNet architecture and transformer layers. The main objective of this study is to improve the accuracy and efficiency of segmentation models in identifying liver tumors from medical images. In this method, the ResUNet50 architecture is used as the encoder for extracting deep features from images, and transformer layers have been added to the model to enhance the model's ability to understand spatial and channel relationships between features. Then, a decoder section with U-Net structure has been designed to reconstruct the predicted maps. To evaluate the proposed method, a dataset of medical images related to liver tumors was used. The experimental results show that the proposed method performs better compared to baseline models according to metrics such as accuracy, Jaccard coefficient (IoU), and Dice coefficient, and has achieved an average accuracy of 92.5%, Jaccard coefficient of 75.4%, and Dice coefficient of 83.1%. These results indicate that the combination of ResUNet and transformer architecture can provide an effective and powerful tool for segmentation of medical images and more accurate identification of liver tumors. In the future, using more diverse data and applying further optimization techniques can improve the efficiency of this model.https://www.tmachineintelligence.ir/article_224190_e447ca5bf8514a4ccead026b5a5ea69a.pdf