Transactions on Machine Intelligence 2821-1693 8 4 2025 12 01 Gazebo Simulation and ROS Implementation to Examine G-mapping SLAM Algorithm to Navigate Turtlebot-3 Robot 171 180 244865 10.22034/tmi.2025.244865 EN M.R. Sayyed Noorani Department of Mechatronics Engineering, University of Tabriz, Tabriz, Iran 0000-0002-7487-8233 F. Aghdam Shahryar Department of Mechatronics Engineering, University of Tabriz, Tabriz, Iran Journal Article 2025 06 24 This study addresses to Gazebo-based simulations and real-world implementations of G-mapping SLAM (Simultaneous Localization and Mapping) algorithm by exploiting the ROS (Robotic Operating System) framework to navigate Turtlebot3 robot. Specifically, we utilize the SLAM_Gmapping package, a well-established algorithm included in the Turtlebot3 package developed for ROS, which employs a LIDAR sensor for environmental mapping. We evaluate the performance of the SLAM_Gmapping algorithm in the both of simulated and real-world environments. Two strategies of manual and automatic (DWA) guidance in the present of static as well as dynamic obstacles are compared. Results indicate that in the simulated environment, manual navigation of the robot in the presence of static obstacles leads to more accurate and faster mapping. In contrast, in the real-world, automatic guidance yields better performance, albeit over a longer duration. Parametric examination of G-mapping SLAM algorithm in different environmental conditions demonstrates its adaptability and capabilities to navigate the Turtlebot3 in indoor spaces.

Transactions on Machine Intelligence 2821-1693 8 4 2025 12 01 Melanoma Skin Cancer Detection Using Deep Learning and the Ant Colony Optimization Algorithm 181 190 244866 10.22034/tmi.2025.244866 EN A. Aliabadian Assistant Professor, Department of Electrical and Biomedical Engineering, Shomal University 0000-0002-8646-7968 Journal Article Skin cancer is among the most common and potentially fatal forms of cancer worldwide, making early and accurate diagnosis essential for effective treatment and improved patient outcomes. Conventional diagnostic procedures, such as histopathological examination and biopsy, are often time-consuming and require significant clinical expertise. Recent advances in artificial intelligence and deep learning have enabled the development of automated diagnostic systems that can support clinicians in the early detection of skin lesions. In this study, a deep Convolutional Neural Network (CNN) is proposed for the classification of skin cancer images. To enhance the performance of the network, the Ant Colony Optimization (ACO) algorithm is employed to optimize the model parameters and reduce classification error. The proposed hybrid CNN–ACO framework is evaluated using a benchmark skin lesion dataset and compared with conventional deep learning approaches. Experimental results demonstrate that the optimization process improves classification performance and model convergence. The proposed method achieves an overall classification accuracy of 96%, outperforming baseline architectures and highlighting the effectiveness of integrating metaheuristic optimization techniques with deep learning models for automated skin cancer diagnosis. The findings suggest that the proposed framework can serve as a reliable decision-support tool for early skin cancer detection in clinical applications.