Transactions on Machine Intelligence2821-16933220200601Design and Implementation of a Discrete-Time Unscented Kalman Filter (DTUKF) Based on Genetic Algorithm to Enhance the Performance of Nonlinear Navigation Systems648020618610.47176/TMI.2020.64ENA.Talebi Sheikh SarmastControl Department, Faculty of Electrical Engineering, Shahid Beheshti University, Tehran, IranN.SamadianElectronics Department, Faculty of Electrical Engineering, Semnan University, Semnan, IranH.ZeinaliControl Department, Faculty of Electrical Engineering, Shahid Beheshti University, Tehran, IranS. M.Mousavi MirkalaeiProfessor, Electronics Department, Faculty of Electrical Engineering, Iran University of Science and Technology, Tehran, IranJournal Article20200210Nonlinear inertial navigation systems are considered among the most important navigation systems, featuring advantages such as independence from external communication, real-time speed and position calculation, and suitable bandwidth, making them very popular in vehicle navigation. These systems consist of an inertial measurement unit comprising three orthogonal accelerometers and three gyroscopes used to determine the position, speed, and direction of vehicle movement, calculating the vehicle''s position with minimal error over short distances. However, over time, due to errors in the gyroscopes and accelerometers and consecutive integrations of their outputs, the estimated position error increases. To achieve higher accuracy, especially in long-term navigation, a global positioning system (GPS) is used for its complementary properties with the inertial navigation system (INS). This paper discusses and analyzes the application of two Kalman filters linear Kalman filter and unscented Kalman filter on nonlinear navigation systems. A discrete-time unscented Kalman filter (DTUKF) is utilized to estimate the position, speed, and state of a nonlinear system, which in this case is an integrated navigation system. By accurately selecting a set of sigma points from a Gaussian distribution and propagating these points through the nonlinear function, estimation is performed with significantly higher accuracy. The unscented transformation allows for the selection of the distribution of these points and control of higher-order error using design parameters. Comparing this filter with the linear Kalman filter reveals the superior performance of the unscented Kalman filter due to not linearizing the nonlinear system, thereby reducing system error. Notably, this paper is the first to use a genetic algorithm to optimize the Q and R noise matrices to achieve minimal variance and optimal mean convergence to reference values.https://www.tmachineintelligence.ir/article_206186_1aa7d6a7eee11d62406673b1eb20c6eb.pdfTransactions on Machine Intelligence2821-16933220200601Automatic Car Parking Based on Petri Net, PFA Algorithm, and Fuzzy System818920619010.47176/TMI.2020.81ENA. M.HatamiDepartment of Electrical Engineering, Technical and Vocational University, Tehran, IranA.ZamaniDepartment of Electrical Engineering, Technical and Vocational University, Tehran, IranJournal Article20200412This paper presents the design and implementation of a hybrid intelligent system aimed at optimizing vehicle parking through efficient path planning. With the increasing demand for intelligent transportation systems, optimizing parking spaces and vehicle movement within parking areas has become a crucial research focus. The proposed system integrates multiple computational techniques to enhance the accuracy and efficiency of automatic parking.<em> </em>The Path Finding Algorithm (PFA) is employed to identify potential parking locations based on predefined constraints and real-time data. Unlike conventional approaches that rely on static flowcharts for parking path planning, this study utilizes Petri nets, which offer a more dynamic and structured framework for modeling alternative parking paths, particularly in global coordinate systems. This method enables adaptive and flexible decision-making in response to varying parking scenarios.<em> </em>To ensure precise maneuverability along the optimized path, a fuzzy logic control system is implemented, allowing the vehicle to adapt its movements in real time based on environmental factors and space constraints. The effectiveness of the proposed system is validated through numerical simulations and experimental studies, demonstrating its capability to improve both parking efficiency and vehicle positioning accuracy. Results indicate that the hybrid integration of PFA, Petri nets, and fuzzy logic significantly enhances the automation and optimization of the vehicle parking process, offering a robust, adaptive, and intelligent parking solution for modern transportation systems.https://www.tmachineintelligence.ir/article_206190_ced605078ae5345616e7e7ac5a23e48e.pdfTransactions on Machine Intelligence2821-16933220200601Comparative Analysis of Waveform Design in Fifth-Generation (5G) Wireless Communication Systems909920619410.47176/TMI.2020.90ENM. H.Mohammadian SarcheshmehElectrical Engineering-Telecommunications Systems, Alborz Campus, University of Tehran, Tehran, IranA.Azam AbbasfarTelecommunications Group, Faculty of Electrical and Computer Engineering, University of Tehran, Tehran, IranJournal Article20200210This paper aims to provide a comprehensive overview of studies on 5G waveforms, reviewing the main candidates and performing a comparative analysis of the proposed suitable waveforms. The research scenario is presented as follows: initially, a brief description of waveform definition and the use cases and design requirements of 5G waveforms are discussed. Subsequently, the main characteristics of CP-OFDM, currently used in fourth-generation (4G LTE) wireless communication systems, are presented. The foundation of 5G waveform discussions is CP-OFDM, as the performance of a new waveform is typically compared to it. Additionally, the fundamental features of the main waveform candidates, along with their respective advantages and disadvantages, are examined and analyzed. In conclusion, based on the research objectives, the key and essential features of the waveforms are briefly reviewed and compared.https://www.tmachineintelligence.ir/article_206194_b430704024954296a191182c589d7097.pdfTransactions on Machine Intelligence2821-16933220200601Design and Development of a Pressure Monitoring System to Prevent Bedsores in Immobile Patients10111020892910.47176/TMI.2020.101ENA.MemariFaculty of Medical Sciences and Technologies, Science and Research Branch, Islamic Azad UniversityA.Tavakoli GolpayeganiStandard Research Institute, Research Center for Technology and Engineering, Biomedical Engineering GroupM. S.HosseinzadehFaculty of Medical Sciences and Technologies, Science and Research Branch, Islamic Azad UniversityJournal Article20200419Pressure ulcers, commonly known as bedsores, are localized injuries to the skin and underlying tissue caused by prolonged pressure, which restricts or entirely halts blood circulation. These ulcers typically develop in bony prominences such as the sacrum, heels, elbows, and hips due to the limited cushioning provided by subcutaneous fat in these areas. Immobile patients, particularly the elderly and individuals with chronic illnesses, are at a heightened risk of developing pressure ulcers, necessitating continuous monitoring and effective preventive measures. Traditional prevention methods involve regular patient repositioning, but manual monitoring is often inconsistent and labor-intensive. In response to this challenge, this paper presents the design and implementation of a smart mattress system capable of detecting and predicting the onset of pressure ulcers. The system utilizes an array of pressure sensors embedded beneath the mattress surface to continuously measure and analyze the distribution of pressure exerted on different body regions. By leveraging real-time data processing, the system can identify prolonged pressure points and issue timely alerts to caregivers or nursing staff, prompting necessary repositioning interventions. The proposed smart mattress aims to enhance patient care by automating pressure ulcer prevention, reducing the burden on healthcare personnel, and improving overall patient outcomes. The study explores the technical aspects of sensor integration, data analysis algorithms, and alert mechanisms to ensure the system's reliability and effectiveness in clinical settings.https://www.tmachineintelligence.ir/article_208929_1c055a7b6f884ebb6d0366927e0ddbb5.pdfTransactions on Machine Intelligence2821-16933220200601Introduction of an Optimal Portfolio Recommendation System Using Quantum Potential11112020893010.47176/TMI.2020.111ENA.Nasiri GheydariDepartment of Computer Engineering, Faculty of Electrical and Computer Engineering, Islamic Azad University, Zanjan, IranM.AfzaliDepartment of Information Technology Engineering, Faculty of Electrical and Computer Engineering, Islamic Azad University, Zanjan, Iran,0000-0003-3233-8084Journal Article20200318In today's world, with the evolution of science and technology and the increasing complexity of human life, the vast and growing volume of information in various fields has made the decision-making process to achieve the desired goal very challenging. To address this challenge, recommender systems have emerged, striving to suggest the desired and useful option from among the possible choices based on the applicant's interests, needs, and past analyses. A recommender system is a system that, based on the analysis of existing data from variables and applicants, recommends and introduces the most appropriate findings to the applicants. In this paper, using data related to the multi-year performance of several stock companies, we aim to introduce a recommender system that can recommend a suitable portfolio to investors. By a suitable portfolio, we mean one that offers the highest profit with the least risk to the investor. The basis of this work is using a method developed as an interdisciplinary activity by economists and physicists applying the laws governing complex systems, known as quantum potential. Here, we present a model using the quantum potential method, where the input is data related to company performance and stock market data, and the output is an optimal portfolio comprising suitable weights of each company's stocks.https://www.tmachineintelligence.ir/article_208930_bc632a719c0d2bdd5d5cd862fb5bbf50.pdfTransactions on Machine Intelligence2821-16933220200601Intrusion Detection in Cloud Computing Virtualization Using Radial Basis Function Neural Network Optimized by Grasshopper Optimization Algorithm12113520893310.47176/TMI.2020.121ENS.MirabiDepartment of Information Technology Engineering, Faculty of Engineering, Science and Research Branch, Islamic Azad University, Tehran, IranS.AlizadehDepartment of Computer Engineering, South Tehran Branch, Islamic Azad University, Tehran, IranJournal Article20200307Cloud computing plays a crucial role in handling massive computations, providing a very simple computational model for users that meets their requests and needs at minimal cost. One of the major challenges in using cloud computing infrastructure is data security and preventing various possible intrusions. Intrusion detection systems (IDS) are one of the main components of cloud computing environment monitoring systems. This paper presents a hybrid learning system for use in intrusion detection systems in virtualization within cloud computing. After data collection and preparation, a Radial Basis Function Neural Network (RBFNN) trained with the Grasshopper Optimization Algorithm (GOA) is used as the proposed method for intrusion detection in cloud computing virtualization. GOA is employed to determine the centers, spread parameters, and weights of neurons in the RBFNN. The results are compared with the k-Nearest Neighbor (k-NN) classifier based on various error types and standard performance criteria. Simulation results indicate a 96.3% accuracy for the proposed method and show superior performance.https://www.tmachineintelligence.ir/article_208933_9cd916abd6e07a42bec47a6d0466c819.pdf