University of QomJournal of Engineering Management and Soft Computing3116-015810120240921Combining Convolutional Neural Network (CNN) and Grad-CAM for Parkinson’s Disease Prediction and Visual Explanationترکیب شبکه عصبی کانولوشن (CNN) و Grad-CAM برای پیش بینی و تفسیر پذیری بصری بیماری پارکینسون113304810.22091/jemsc.2024.10828.1180ENReyhanehDehghanDepartment of Computer Engineering, Faculty of Engineering, Shahid Chamran University of Ahvaz, Ahvaz, Iran0009-0008-1372-4645MarjanNaderanDepartment of Computer Engineering, Faculty of Engineering, Shahid Chamran University of Ahvaz, Ahvaz, Iran0000-0002-3702-8977Seyed EnayatallahAlaviDepartment of Computer Engineering, Faculty of Engineering, Shahid Chamran University of Ahvaz, Ahvaz, IranJournal Article20240608Parkinson's disease is one of the types of neurological diseases that is caused by the destruction of brain cells that produce dopamine. Early detection of Parkinson's disease is an important factor in slowing the progression of the disease. In this study, a Convolutional Neural Network (CNN) namely ConvNet, is used to discriminate Parkinson's patients based on Single Photon Emission Computed Tomography (SPECT) images acquired from the PPMI database. Since the dataset is limited, after a pre-processing stage, two data augmentation techniques are used. Finally, the Grad-CAM technique is used to obtain visual interpretation from the predictions of the proposed CNN. To evaluate the proposed method, different measures such as accuracy, sensitivity (recall) and f1-score are used. Simulation results according to the measures shows that when the classic data augmentation method is used accuracy is increased to 98.50% and more efficient classification is performed.https://jemsc.qom.ac.ir/article_3048_7cf9cbcc4c7b5f32d1ac349f6c06be46.pdfUniversity of QomJournal of Engineering Management and Soft Computing3116-015810120240822Selection of green supplier by multi-moora combination method and two-stage clusteringانتخاب تامین کننده سبز با روش ترکیبی مولتی مورا و خوشه بندی دو مرحله ای1449309010.22091/jemsc.2024.10977.1181ENMahsaNiavandMaster of Industrial Engineering, Department of Industrial Engineering, Faculty of Industrial and Mechanical Engineering, Qazvin Branch, Islamic Azad University, Qazvin, Iran, Email: maadibi@aut.ac.irMohammad AminAdibiDepartment of Industrial Engineering, Faculty of Industrial and Mechanical Engineering, Qazvin Branch, Islamic Azad University, Qazvin, Iran, Email: mahsaniavand@yahoo.com0000-0002-7973-9814AdelPourghader ChobarDepartment of Industrial Engineering, Faculty of Industrial and Mechanical Engineering, Qazvin Branch, Islamic Azad University, Qazvin, Iran, Email: apourghader@qiau.ac.ir0000-0002-8377-5906Journal Article20240725Today, environmental management for companies with an emphasis on environmental protection has become one of the most important issues and global pressures require organizations to produce environmentally friendly products and services. This challenge has led to the creation of a new concept called green supply chain management in the field of business, which combines environmental thinking and supply chain. Also, the problems of green supplier selection methods have become a very important issue. a Hybrid supplier selection method, in the present study, is utilized to select the green supplier by combining the Tow-Step data clustering method and the MADM method which in this research is the MULTI MOORA method. A real-world case study is also presented at Etka Chain Stores which uses a questionnaire that measures the greenness of suppliers in 13 general criteria according to business context and criteria. The advantages of the proposed hybrid method are then discussed here to demonstrate its superiority.https://jemsc.qom.ac.ir/article_3090_a15ec0407a65e57d8619305786ff7906.pdfUniversity of QomJournal of Engineering Management and Soft Computing3116-015810120240822Enhancing Job Satisfaction Using an Adaptive Neuro-Fuzzy Inference System by Considering HSEE Factorsارائه رویکرد مبتنی بر سیستم استنتاج عصبی-فازی به منظور ارزیابی رضایت شغلی با درنظرگیری شاخصهای HSEE5066309110.22091/jemsc.2024.11008.1183ENMehrabTanhaeeanDepartment of Industrial Engineering, College of Engineering, University of Tehran, Tehran, Iran="0000"&"-000"&RANDBETWEEN(1,4)&"-"&RANDBETWEEN(2033,9479)&"-"&RANDBETWEEN(2013,9934)FatemehRaeisiDepartment of Industrial Engineering and Management, Shahrood University of Technology, Shahrood, IranHamidSaffariIndustrial Engineering Department, Iran University of Science and Technology, Tehran, IranJournal Article20240717Job satisfaction plays a crucial role in enhancing productivity and reveals intriguing insights that impact the operational effectiveness of organizations. Due to the importance of maintenance units, special attention should be paid to their employees. This study employs a machine learning approach to enhance the performance and job satisfaction of maintenance units through the focus on health, safety, environment, and ergonomics (HSEE). A standardized questionnaire is developed for on HSEE data. Within the neural-fuzzy inference network, inputs such as health and safety protocols, environmental data collection, and its reliability is assessed using Cronbach's alpha coefficient. Subsequently, various adaptive neuro fuzzy inference system (ANFIS) models are utilized to predict job satisfaction based factors, and ergonomics are considered, while job satisfaction serves as the output. Following the selection of the optimal model, individual efficiency levels are assessed and scrutinized based on the calculated error. The findings suggest that enhancing employee job satisfaction relies on prioritizing the enhancement of ergonomics and the work environment.https://jemsc.qom.ac.ir/article_3091_3d5eb6d063fc32902c3df2a34947f8b2.pdfUniversity of QomJournal of Engineering Management and Soft Computing3116-015810120240921Path Planning For A Mobile Robot Using The
Chessboard Method And Gray Wolf Optimization
Algorithm In Static And Dynamic Environmentsبرنامه ریزی مسیر رباتمتحرک باروششطرنجی باالگوریتم بهینه سازی گرگخاکستری درمحیط های ایستا وپویا6791304910.22091/jemsc.2024.11127.1189ENAliHatami ZadehMsc Student of Qom University of Technology, Faculty of Electrical and computer engineering. Email: ali.hatami72@yahoo.comJavadSharifiAssistant Professor of Qom University of Technology, Faculty of Electrical and computer engineering. Email: sharifi@qut.ac.irMeysamYadegarAssistant Professor of Qom University of Technology, Faculty of Electrical and Computer Engineering. Email: yadegar@qut.ac.ir0000-0003-0660-7017Journal Article20240806The Grey Wolf Optimization (GWO) algorithm, a computational optimization method inspired by the social behavior of wolves, has recently been effectively used to solve optimization and routing problems. This paper proposes a metaheuristic approach named Grey Wolf Optimization (GWO) inspired by grey wolves. Four types of grey wolves, namely alpha, beta, delta, and omega, are employed to simulate the leadership hierarchy. Additionally, three main stages of hunting—searching for prey, encircling prey, and attacking prey—are implemented. Overall, this paper examines how the combination of the chessboard method and the Grey Wolf Optimization algorithm can optimize the path planning of a mobile robot in both static and dynamic environments. The objective of this research is to shorten the path, minimize the final position to the target, avoid collisions, and prevent local minima. This paper investigates the Grey Wolf Optimization algorithm as an effective method for solving the routing problem. Simulation results demonstrate that using this algorithm leads to significant improvements in the robot's efficiency and enhanced path-planning performance in complex and dynamic environmentshttps://jemsc.qom.ac.ir/article_3049_8a6b08777d793f067521895429c17dda.pdfUniversity of QomJournal of Engineering Management and Soft Computing3116-015810120240921Designing a green supply chain pricing model with a multi-criteria decision-making approach and game theory (case study: home appliance industry)طراحی الگوی قیمت گذاری زنجیره تامین سبز با رویکرد تصمیم گیری چند معیاره و نظریه بازی(مورد مطالعه: صنعت لوازم خانگی)92122305010.22091/jemsc.2024.11144.1191ENSomayehSazegariPhD Candidate of Industrial Management, Department of Management, Dehaghan Branch, Islamic Azad University, Dehaghan, Iran. Email: Somayeh.sazegari@gmail.com0009-0000-6094-1679Sayyed MohammadrezaDavoodiAssociate professor. Department of Management ,Dehaghan Branch, Islamic Azad University, Dehaghan. Email: smrdavoodi@ut.ac.ir0000-0003-2347-7154AlirezaGoliAssistant Professor, Department of Industrial Engineering and Future Studies, Faculty of Engineering, University of Isfahan, Isfahan, Iran. Email: goli.a@eng.ui.ac.ir0000-0001-9535-9902Journal Article20240811pressure to continuously reduce the negative effects of pollutant emissions resulting from their supply chains. The aim of this research is to design a green supply chain pricing model using a multi-criteria decision-making approach and game theory (case study: the home appliance industry). In this study, after conducting a literature review and identifying key indicators for predicting green supply chain pricing, screening of the indicators was carried out in three stages using the fuzzy Delphi method. Out of 20 indicators, 13 were selected based on the opinions of 13 experts. According to the preference selection approach, Company D was identified as the leading company in the game theory due to its highest priority. Ultimately, based on game theory, scenarios among four members of the supply chain were evaluated, and the best and worst scenarios were identified. Additionally, to test the structural validity of the proposed model, information related to the green supply chain of nine selected home appliance companies was executed using MATLAB software. Finally, the analysis of this research based on game theory reveals the challenges currently faced by Company A. In recent years, Iran has encountered multiple challenges regarding sustainable growth. The results indicate that Company A can only achieve a better optimal status if its installed capacity is at least 20% larger than its current level. This will help Company A optimize production and reduce negative environmental impacts.https://jemsc.qom.ac.ir/article_3050_ab3e95d03b04a609118be4ef9b52b5f6.pdfUniversity of QomJournal of Engineering Management and Soft Computing3116-015810120240822Identifying barriers in the field of electronic payments based on blockchain technology: A multi-criteria decision-making approachشناسایی موانع حوزه پرداختهای الکترونیکی مبتنی بر فناوری بلاکچین با بهکارگیری روشهای تصمیمگیری چندمعیاره123142309210.22091/jemsc.2024.11160.1193ENAmir MohammadYektaei RudsariMaster Student in MBA, Department of Industrial Engineering, K.N.Toosi University of Technology, Tehran, Iran, Email: a.yektaeiroodsari@email.kntu.ac.irMajidMirzaei Ghazani.Associate Professor of Department of Industrial Engineering, K.N.Toosi University of technology, Tehran, Iran, Email: majidmirzaee@kntu.ac.ir0000-0002-7606-9464NaserSafaeiAssistant Professor of Department of Industrial Engineering, K.N.Toosi University of technology, Tehran, Iran, Email: nsafaie@kntu.ac.ir0000-0003-1889-2230Journal Article20240812With the growing trend of electronic payments, the use of blockchain technology has been introduced as one of the solutions for safe money transfer. Some of these obstacles include technical, technological, organizational, financial and security problems. To identify and prioritize these obstacles and solve them, multi-criteria decision-making methods can be useful.<br />In this research, in order to identify and rank the factors of obstacles related to electronic payments based on blockchain technology, the Delphi method has been used. This method includes reading previous articles and collecting the opinions of 35 specialists and experts in this field. To analyze the relationship between the factors and identify their causal relationships, the Dimtel method was used and finally, to prioritize the factors, the process of network analysis was used.<br />Out of 13 indicators, 11 indicators were evaluated in the final analysis. The privacy compliance index has the greatest impact on other indicators. On the other hand, indicators of non-commitment and the desire of senior managers to improve and make fundamental changes are also more influential than other indicators.https://jemsc.qom.ac.ir/article_3092_5e997558684802944499bb3feaeccd8f.pdfUniversity of QomJournal of Engineering Management and Soft Computing3116-015810120240822Application of linear programming model for optimizing the components of combined photovoltaic and battery systemکاربرد مدل برنامه ریزی خطی در بهینه سازی اجزای سیستم ترکیبی فتوولتائیک و باتری143154309310.22091/jemsc.2024.11166.1194ENLaleMohamadifarMaster student, Department of Industrial Engineering, Shahid Bahonar University of Kerman, Kerman Regional Electric Company. Email: mohamadifar_l@yahoo.comSeyed HamedMoosaviradAssociate Professor, Department of Industrial Engineering, Faculty of Engineering, Shahid Bahonar University of Kerman, Kerman. Email: s.h.moosavirad@uk.ac.ir="0000"&"-000"&RANDBETWEEN(1,4)&"-"&RANDBETWEEN(2033,9479)&"-"&RANDBETWEEN(2013,9934)MitraMirhosseiniAssistant Professor, Energy and Environment Research Institute, Shahid Bahonar University of Kerman, Kerman. Email m.mirhosseini@uk.ac.irJournal Article20240813In this article, a combined energy system independent of the national power grid, including solar panels and batteries, is used as a storage system to provide energy. Due to the high costs of the system components, optimization with linear programming aims to reduce costs systems and complete coverage of energy demand has been done and the model has been implemented for 2 cities of Kerman and Mashhad. The results showed that since the output power of the photovoltaic panel is dependent on the temperature and intensity of solar radiation, under the conditions of using the same components and demand Equally, the implementation of this system in Kerman is more cost-effective. The sensitivity analysis of the studied system has been carried out and its effect has been examined in the results.https://jemsc.qom.ac.ir/article_3093_2edc2c0be01b244f961fb204c059f192.pdfUniversity of QomJournal of Engineering Management and Soft Computing3116-015810120240921Non-linear multi-objective optimization model of production planning based on fuzzy logic and machine learningمدل بهینه سازی چند هدفه غیر خطی برنامه ریزی تولید بر اساس منطق فازی و یادگیری ماشین155189305110.22091/jemsc.2024.11186.1197ENZahraSaeidi MobarakehDepartment of Industrial Engineering, Central Tehran Branch, Islamic Azad University, Tehran, Iran. Email: z.saeedi2020@gmail.com0009-0007-0456-1592HosseinAmoozadkhaliliDepartment of Industrial Engineering, sari Branch, Islamic Azad University, sari, Iran. Email: Amoozad92@yahoo.com0000-0001-7222-2233Journal Article20240816This research introduces a nonlinear multi-objective optimization model that is designed to simultaneously optimize profit and customer satisfaction in production systems. The investigated problem includes optimization in complex and uncertain conditions of production, which is faced with resource and time limitations. The proposed model provides optimal solutions for managers by using non-linear objective functions and detailed analysis of operating conditions. This fuzzy logic is combined with machine learning algorithms such as neural networks and reinforcement learning to create an intelligent and flexible model that effectively adapts to sudden changes in dynamic environments. This model uses the combination of non-dominant fourth sorting genetic algorithms (NSGA-IV) and variable selection network (VSN) in a hybrid framework and provides an advanced and multi-faceted approach to solving complex multi-objective optimization problems. Pareto-optimal results obtained from this model indicate its efficient and optimal performance. The proposed model can be used as a practical and strategic source for managers and decision makers in optimizing production and improving customer satisfaction in uncertain and dynamic conditions.https://jemsc.qom.ac.ir/article_3051_8396cf4986ba31c33c78f28056b54de2.pdfUniversity of QomJournal of Engineering Management and Soft Computing3116-015810120240921Simulating the line balance to provide an improvement plan for optimal production and costing in petrochemical industriesشبیه سازی بالانس خط تولید برای ارائه طرح بهبود در مقدار تولیدات بهینه و هزینه یابی در صنایع پتروشیمی190212305210.22091/jemsc.2024.11189.1198ENAsgharHemmatiAssistance prof. Department of Industrial Engineering, Abhar Branch, Islamic Azad University, Abhar, Iran, Email: Hemati.asghar@iau.ir0000-0001-8074-2834FarshadKavehPhD student, Department of Industrial Engineering, Najafabad Branch, Islamic Azad University, Najafabad, Iran, Email: Farshadkaveh@gmail.com0000-0003-2276-0193MiladAbolghasemianPhD. Department of Industrial Engineering, Lahijan Branch, Islamic Azad University, Lahijan, Iran, Email: m.abolghasemian.bt@gmail.com0000-0002-1341-7855AdelPourghader ChobarPhD. Department of Industrial Engineering, Qazvin Branch, Islamic Azad University, Qazvin, Iran, Email: apourghader@qiau.ac.ir0000-0002-8377-5906Journal Article20240816This research examines the influential factors and theoretical principles of queuing in balancing production lines. The required information, including the number of active machines on the production line, the level of station idleness, and the waiting time for parts to receive services, has been quantitatively gathered through on-site observations and interviews with managers and supervisors. Process modeling has been developed using the ARENA simulation software version 13, which can identify the current status of tank and heavy product production in terms of queuing and line balance criteria, and its results are analyzed and described. The findings of this research indicate that the addition of a forklift increases costs from 65,902 monetary units to 80,577, equivalent to a 22% increase. However, this change results in a doubling of production compared to the current state; therefore, the extra expenditure due to increased production is satisfactory for the managers of this organization. The significance of this production increase aligns with enhanced productivity, especially considering the greater emphasis placed on production targets.https://jemsc.qom.ac.ir/article_3052_30d337b8e1c0d197988a2b799f5ccfc0.pdfUniversity of QomJournal of Engineering Management and Soft Computing3116-015810120240921Secure medical image transmission for healthcare applications using cooperative relaying based on physical layer securityارسال امن تصویر پزشکی با استفاده از رله مشارکتی و مبتنی بر امنیت لایه فیزیکی213237309410.22091/jemsc.2024.11195.1199ENAliKuhestaniAssistant Professor of Telecommunication Engineering at Qom University of Technology, Email: kuhestani@qut.ac.ir="0000"&"-000"&RANDBETWEEN(1,4)&"-"&RANDBETWEEN(2033,9479)&"-"&RANDBETWEEN(2013,9934)Mohammad AliSebtonabi2. Ph.D. Student of Telecommunication Engineering at Shahed University. Email: sma.sebtonabi1373@yahoo.comRoozbehRajabiAssistant Professor of Telecommunication Engineering at Qom University of Technology, Email: rajabi@qut.ac.ir="0000"&"-000"&RANDBETWEEN(1,4)&"-"&RANDBETWEEN(2033,9479)&"-"&RANDBETWEEN(2013,9934)MohammadrezaKeshavarziICT Research Institute, Iran Telecommunication Research Center (ITRC), Tehran, Iran, Email: mrkeshavarzi@itrc.ac.irJournal Article20240818In this article, a new idea and method to protect image against illegal users has been proposed. Considering that in medical images, most of the experts' emphasis is on the part of the image that shows the disease, in this article, the image is first divided into two parts namely, main and background parts, and then the transmitter estimats regarding the capacity of legal and non-legal channels. Here, the transmitter decides whether to send the main part or the background part, i.e., when the capacity of the legal channel is greater than the capacity of the eavesdropping channel, the main part of the image is sent, and when the capacity of the eavesdropping channel is greater than the legal channel, the background part is sent. In addition, in this article, due to the large distance between the transmitter and the receiver and the effect of the path loss, a relay is adopted to boost the signal. Simulation results are provided to highlight the effectiveness of our proposed cooperative relaying idea.https://jemsc.qom.ac.ir/article_3094_8ea7a5c885025955fb6c08d2b8af7839.pdfUniversity of QomJournal of Engineering Management and Soft Computing3116-015810120240822Prediction the Choice of Financing for Start-ups using Machine Learning Algorithms and Behavioral Biasesپیشبینی شیوه تأمین مالی استارتاپها با استفاده از الگوریتمهای یادگیری ماشین و درنظرگرفتن سوگیریهای رفتاری238261305310.22091/jemsc.2024.11203.1200ENNaimehNiaziDepartment of Industrial Engineering, Faculty of Engineering, University of Ferdowsi of Mashhad, Mashhad, Iran0009-0006-8874-3918HamidehRazaviDepartment of Industrial Engineering, Faculty of Engineering, University of Ferdowsi of Mashhad, Mashhad, Iran0000-0003-1837-7933Journal Article20240817The aim of this paper is to predict financing methods to support decision-making for startup founders and their investors. Initially, factors influencing the choice of financing methods, including structural, demographic, and behavioral factors, were identified. These factors were then assessed using a questionnaire consisting of 32 items, which was sent online to startup founders. Based on 70 responses received and using algorithms including binary matching, classification chains, label power set, K-nearest neighbors, extreme gradient boosting, cluster boosting algorithm and random forest, the financing methods chosen by startups were predicted. Comparison of the results from the algorithms shows that the boosting ensemble algorithm, with an F1 score of 89 and precison of 85%, predicts the selected financing methods on the test dataset better than other algorithms. Additionally, data analysis indicates that startups are more inclined towards personal funding methods, which aligns with the prevalence of loss aversion bias among entrepreneurs. Following loss aversion, overconfidence, anchoring, and illusion of control biases were the most frequent among entrepreneurs.https://jemsc.qom.ac.ir/article_3053_01c93a3763a4ff456dfc93cca7a93c11.pdfUniversity of QomJournal of Engineering Management and Soft Computing3116-015810120240822Locating Routing Problem (LRP) of distribution of priority support items to ground forces in war conditionsمسأله مسیریابی-مکان یابی توزیع اقلام پشتیبانی اولویت دار به نیروهای زمینی در شرایط جنگ262292309510.22091/jemsc.2024.11320.1206ENMiladAbolghasemianPh.D in industrial engineering, Department of Science and Technology Studies, AJA Command and Staff University, Tehran, Iran. Email: m.abolghasemian.bt@gmail.com0000-0002-1341-7855HamidBigdeliAssist. Prof. Department of Science and Technology Studies, AJA Command and Staff University, Tehran, Iran. Email: hamidbigdeli92@gmail.com="0000"&"-000"&RANDBETWEEN(1,4)&"-"&RANDBETWEEN(2033,9479)&"-"&RANDBETWEEN(2013,9934)NaderShamamiAssist. Prof. Department of Science and Technology Studies, AJA Command and Staff University, Tehran, Iran. Email: nader.shamami@gmail.comJournal Article20240916In this research, a mathematical modeling approach is presented to determine efficient locations for deploying support forces using Data Envelopment Analysis (DEA). Additionally, a mixed-integer linear programming model is proposed for routing prioritized support items. The proposed model allows for the adjustment of manageable inputs to improve outputs according to the principle of managerial accessibility, while also maintaining the current levels of unmanageable inputs if they cannot be reduced based on the principle of natural accessibility. Subsequently, routing for the distribution of these prioritized support items is provided using a mixed-integer linear programming model. The proposed model has been used to evaluate 25 potential locations prepared to provide ground support services to assist friendly forces in contested areas, with the aim of ending the conflict in favor of friendly forces. Sixteen viable support locations have been identified. Finally, routing for the distribution of support items to these 16 locations has been presented.https://jemsc.qom.ac.ir/article_3095_9fa6677b385e01056c9971adcd15ba00.pdf