Transactions on Machine Intelligence2821-16936220230601Evaluating Electricity Bill Savings of Self-Consumption Pv in Italian Residential Sector536518141010.47176/TMI.2023.53ENS.KHorramiElectrical Engineering, Sapienza University, Rome, Italy0009-0002-4386-3415L.MartiranoDepartment of Astronautical, Electrical and Energy Engineering, Sapienza University, Rome, ItalyJ.Manuel Roldan FernandezDepartment Electric Engineering, University Sevilla, Spain0000-0002-3811-1078Journal Article20230210The installation of PV systems in residential buildings has significantly increased in the last decade, thanks to national programs such as Feed-in Tariffs and Net Metering. To maximize their earnings from these systems, some users must boost their self-consumption. Various components have been successfully tested, but there are still several challenges to overcome before these technologies can become fully viable. An initial purchase of a photovoltaic system requires a significant investment. This article outlines the cost of installing and wiring solar panels, inverters and related equipment. Additionally, conventional academic sections are included, and the language remains formal with no biased or emotional language. Lastly, correct spelling, grammar, and punctuation are employed. The article aims to provide an economic assessment of potential electricity bill savings via self-consumption in the residential sector of Rome, limiting the solar panel capacity between 1 kWp to 4.5 kWp. Technical terms are explained upon first use, ensuring the logical flow of information throughout. To fulfill this objective, we compare the situation of a typical Italian household, which solely relied on purchased power from the grid, with a hypothetical circumstance in which the residence participated in a scheme to construct a photovoltaic self-generation system that can meet some or all of its energy requirements. In Rome, employing "PV 1 kWp", we obtained a commendable result (IRR = 26%) and the greatest NPV (€4438.046).https://www.tmachineintelligence.ir/article_181410_78d705691857b9f9f4c20ebe20e40d7d.pdfTransactions on Machine Intelligence2821-16936220230601Investigation and Analysis of Gene Expression Using the Fusion Method of Feature Selection and Dynamic Neural Network Classification667518141110.47176/TMI.2023.66ENF.TurkiMechanical Engineering, K. N. Toosi University of Technology, Tehran, IranA.KhademMechanical Engineering, K. N. Toosi University of Technology, Tehran, IranA.H. JalaliAghcheiMechanical Engineering, K. N. Toosi University of Technology, Tehran, Iran0000-0003-2735-6763Journal Article20230310The analysis of high-volume microarray data faces challenges such as limited sample size, computational complexity, and the risk of inappropriate gene selection. The scarcity of samples hampers computational analysis and classification complexity, while reducing the classification's ability to generalize and predict new samples. Moreover, datasets with a high gene-to-sample ratio raise concerns about the selection of relevant genes for accurate predictive models. Interpreting disease-causing genes becomes intricate as only a subset of genes offers a precise biological insight into the disease. To address these issues, a focus on a smaller set of gene expression data is crucial for a more effective understanding of informative genes. Hence, the primary objective in microarray data analysis is to significantly reduce the number of genes through discriminative gene selection, enhancing the precision of information contained in the data. This article conducts gene expression classification on various cancer types, including colon cancer, breast cancer, leukemia, prostate tumors, and DLBCL. Each cancer type is independently evaluated in the feature selection cycle and classified using varying numbers of features. This approach aims to overcome challenges in microarray data analysis and improve the accuracy and interpretability of gene expression classification.https://www.tmachineintelligence.ir/article_181411_8d62af7aea1cf8f66ca6d05f2527c17b.pdfTransactions on Machine Intelligence2821-16936220230601Analytical Response of Nonlinear Buckling of Composite Plates Reinforced with Graphene Nanosheets768818141210.47176/TMI.2023.76END.ShokriDepartment of Mechanics, Technical and Engineering Faculty, Imam Khomeini International University, Qazvin, Iran (Master's student)M. R.EbrahimianDepartment of Mechanics, Technical and Engineering Faculty, Kar Higher Education Institute, Qazvin, Iran (Assistant Professor)B.TabibianDepartment of Mechanics, Technical and Engineering Faculty, Imam Khomeini International University, Qazvin, Iran (Master's student)M. R.AllahverdlouDepartment of Mechanics, Technical and Engineering Faculty, Imam Khomeini International University, Qazvin, Iran (Master's student).M. S.AtlasbafDepartment of Mechanics, Technical and Engineering Faculty, Imam Khomeini International University, Qazvin, Iran (Master's student).Journal Article20230316This paper presents a detailed analytical investigation into the nonlinear buckling behavior of a composite rectangular plate reinforced with graphene nanosheets (GNSs). The analysis is grounded in the third-order shear deformation theory (TSDT), which accurately captures transverse shear effects in thick plates. The governing equations are systematically derived using Hamilton’s principle and result in a system of five coupled nonlinear partial differential equations. These equations are analytically solved using Navier’s method, assuming simply supported boundary conditions along all four edges of the plate. The study explores the influence of key parameters including graphene distribution patterns, nanosheet geometry (thickness and width), the plate's thickness-to-length ratio, and the effects of geometric nonlinearity on the critical buckling load. To validate the analytical model, numerical results are compared with findings reported in the literature, demonstrating excellent agreement. The results highlight the significant reinforcement potential of GNSs in enhancing structural stability. Specifically, the inclusion of a small graphene content only 0.5% by mass can lead to a dramatic increase in the buckling load, nearly tripling it. These findings underscore the effectiveness of GNSs as nanofillers for improving the mechanical performance of composite structures under compressive loads, making them promising candidates for advanced engineering applications.https://www.tmachineintelligence.ir/article_181412_bfeb001eb5a0b3162d945f1b9cdcb912.pdfTransactions on Machine Intelligence2821-16936220230601An Improved Multiport Power Converter for Grid-tied PV-EV Charging Systems8910318141310.47176/TMI.2023.89ENA.ShalbafDepartment of Electrical Engineering, Shahid Chamran University, Ahvaz, Iran0000-0003-3979-5333Journal Article20230306Renewable energy is in high demand for residential use, and solar energy is a favored source due to its popularity. One of the benefits of incorporating solar energy into EV charging systems is the reduction of GHG emissions while also lessening the load on the electrical grid, thus aiding in grid stabilization during peak hours. Integrated power converter topologies between photovoltaic (PV) panels, grid, and EV provide improved efficiency and reduced size, weight, and cost compared to non-integrated structures. Nevertheless, conventional integrated topologies mainly rely on traditional sub-converters which experience high voltage stresses on the semiconductor devices and low voltage gains. The paper presents a novel Multiport Power Converter, which is integrated into grid-tied PV-EV charging systems. This Converter is capable of offering lowered voltage stress on the bidirectional EV-side converter, thus improving the system's efficiency. Additionally, it can achieve a higher voltage gain for the PV-side converter operations. The converter can function in various modes- grid to EV, EV to grid, PV/EV to grid, PV to EV, and PV to grid. To validate the proposed converter, a MATLAB-based simulation programme is utilised to verify the theoretical analysis and performance of the proposed converter.https://www.tmachineintelligence.ir/article_181413_3bee85ac5d60c54d2a92f67e0814422f.pdfTransactions on Machine Intelligence2821-16936220230601Diabetes Diagnosis from Big Data using Fuzzy-Neural Chaotic Tree10411318141710.47176/TMI.2023.104ENB.SalehDepartment of Information Technology, Sabzevar Branch, Islamic Azad University, Sabzevar, Iran0000-0002-3318-397XH.HasanpourDepartment of Computer Engineering,
Sabzevar Branch, Islamic Azad University
Sabzevar, IranJournal Article20230210Today, diabetes is a recognized global health concern. Global statistics show an increasing prevalence of the disease, posing a challenging issue for modern medicine. In response, computer science has proposed various methods to diagnose and predict diabetes. Nonetheless, researchers continue to work on resolving outstanding issues and errors. Data mining is used as a technical method for identifying and extracting new knowledge from data. This study introduces a novel approach for categorizing diabetic data that consists of three stages. Firstly, pre-processing is conducted, where data normalization procedures are applied. Subsequently, attribute extraction and selection are carried out. Finally, data mining principles are utilized for classification. The classification results obtained can be utilized to predict diabetes in various individuals. Evaluation of the results involves adherence to certain standards such as sensitivity, specificity, and accuracy. Our recommended approach, which combines chaotic fuzzy-neural with K-means tree, proves more effective than previous techniques, as confirmed by the results.https://www.tmachineintelligence.ir/article_181417_6c3eeaf1056cfd8e123b4786438e086e.pdfTransactions on Machine Intelligence2821-16936220230601Cardiovascular Disease Diagnosis Using the Combination of Principal Component Analysis Algorithm and Regression Tree11412518160810.47176/TMI.2023.114ENH. R.AvinyPh.D. student, Department of Computer Engineering, Faculty of Technology and Engineering, Yasouj branch, Islamic Azad University, Yasouj, Iran0009-0000-4872-3185M.GhasemiMasters student, Department of Computer Engineering, Faculty of Technology and Engineering, Yasouj branch, Islamic Azad University, Yasouj, IranM.FazlazadMasters, Department of Computer Engineering, Faculty of Technology and Engineering, Yasouj branch, Islamic Azad University, Yasouj, IranJournal Article20230410Cardiovascular disease stands as a prominent global cause of mortality, emphasizing the pivotal need for effective diagnostic and treatment strategies. Recognizing the significance of early detection, this study centers on employing the regression tree algorithm as a primary method. To gauge the precision of cardiovascular disease diagnosis, we scrutinized a dataset encompassing 270 patient samples and 14 distinct characteristics. The implementation approach involved a dual deployment of the Principal Component Analysis (PCA) algorithm and the regression tree algorithm. Employing PCA, we streamlined the feature set from 14 to 8, followed by the application of the regression tree algorithm to enhance detection accuracy. The decision tree classification method adopted encompasses critical facets such as feature selection, tree generation, and pruning. Implementation of these procedures was facilitated through the Weka tool, a data mining software. The collaborative utilization of PCA and the regression tree algorithm culminated in a noteworthy improvement, yielding a diagnostic accuracy increase of 81.48% in detecting cardiovascular disease.https://www.tmachineintelligence.ir/article_181608_3e313ab53d596a4594577f5100b4cef4.pdf