Article
Engineering, Marine
Duc-Anh Pham, Seung-Hun Han
Summary: Efficient ship guidance and fuel savings can be achieved through the integration of neural networks and fuzzy logic control in an intelligent control system. This study presents a ship autopilot system using the Adaptive Neural Fuzzy Inference System (ANFIS) that outperforms the traditional PID controller in terms of stability and trajectory accuracy.
JOURNAL OF MARINE SCIENCE AND ENGINEERING
(2023)
Article
Computer Science, Interdisciplinary Applications
Ali Gholami Vijouyeh, Ali Kadkhodaie, Mohammad Hassanpour Sedghi, Hamed Gholami Vijouyeh
Summary: Determining the petrophysical properties of a reservoir, such as shear wave velocity, is crucial for exploration and production management. This study developed a robust committee machine model to estimate fast and slow shear wave velocities from petrophysical logs. Different algorithms, including artificial neural network, fuzzy logic, and neuro-fuzzy, were applied and their outputs were merged using optimization methods. The committee machine achieved superior performance over individual systems in estimating shear wave velocities.
COMPUTERS & GEOSCIENCES
(2022)
Article
Computer Science, Artificial Intelligence
Ismail Atacak, Kazim Kilic, Ibrahim Alper Dogru
Summary: In this study, a hybrid architecture is proposed for the detection of Android malware from the permission information of applications. The proposed method achieves high accuracy and F-scores in the detection of malicious applications.
PEERJ COMPUTER SCIENCE
(2022)
Article
Computer Science, Artificial Intelligence
Izaz Ullah Khan, Faisal Rafique
Summary: A novel fuzzy linear programming formulation for minimum-cost capacitated fuzzy network is proposed and implemented to minimize the operations cost of American Airlines. The research is helpful to identify the most profitable destinations and focuses on 12 origin/destination pairs.
Article
Engineering, Industrial
Hang Zhang, Wenhu Wang, Shusheng Zhang, Bo Huang, Yajun Zhang, Mingwei Wang, Jiachen Liang, Zhen Wang
Summary: This article presents a deep learning-based approach for estimating manufacturing costs, with a focus on the precision information of parts. The approach defines an attribute graph to represent the CAD model of a part and constructs a ConvGNN framework called Cost Estimation Network (CEN) that combines spectral-based and spatial-based convolutional layers. The trained CEN can accurately estimate manufacturing costs, and a modified Grad-CAM process is developed to explain the rationale behind cost decisions. Experimental studies using CNC machined rotary parts validate the feasibility and effectiveness of the approach.
JOURNAL OF MANUFACTURING SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Khalid Alsamadony, Ahmed Farid Ibrahim, Salaheldin Elkatatny, Abdulazeez Abdulraheem
Summary: The photoelectric factor (PEF) is an important tool for distinguishing different types of reservoir rocks, and models for estimating missing PEF logs are essential. In this study, various machine learning models were developed to predict PEF values using different well logs as inputs. A different approach based on automated machine learning was proposed, which selected a Gaussian process regression (GPR) model for accurate estimation of PEF values.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Construction & Building Technology
Abdulah M. M. Alsugair, Naif M. M. Alsanabani, Khalid S. S. Al-Gahtani
Summary: This study investigates the correlation between owner's cost estimation (OCE) accuracy and changes in the final contract cost (FCC). Through a case study, it is confirmed that the two variables are correlated. The study aims to develop a forecast model to predict FCC based on the initial OCE, which has not been previously studied. Utilizing data from 34 Saudi Arabian projects, linear regression models and an artificial neural network (ANN) model were developed. The results show that the ANN model outperforms the linear regression models in terms of accuracy.
Article
Computer Science, Hardware & Architecture
Divyendu Kumar Mishra, Aby Thomas, Jinsa Kuruvilla, P. Kalyanasundaram, K. Ramalingeswara Prasad, Anandakumar Haldorai
Summary: To achieve successful autonomous navigation, challenges related to perception, localization, planning, and control functions must be addressed. The introduction of a neuro-fuzzy system explores the benefits of both deliberate and reactive navigation control.
COMPUTERS & ELECTRICAL ENGINEERING
(2022)
Article
Automation & Control Systems
Behzad Nasrnia, Reza Falahat, Ali Kadkhodaie, Ali Gholami Vijouyeh
Summary: The estimation of reservoir parameters and elastic moduli relies on well-logging data and seismic velocity information. Due to the lack of shear velocity log and high acquisition costs, various approaches for shear velocity estimation have been developed. This study proposes a robust and cost-effective solution by combining intelligent methods with rock-physics models, which leads to improved estimations of shear velocity in carbonate reservoirs.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Green & Sustainable Science & Technology
Peng Yin, Jinzhou Chen, Hongwen He
Summary: In this paper, a nonlinear air supply system model integrated with the fuel cell stack voltage model is built. Conventional PID controls for the oxygen excess ratio are implemented, and fuzzy logic inference and neural network algorithm are integrated into the PID controller to tune the gain coefficients. Simulation results show that the fuzzy PID controller with seven subsets can improve the dynamic responses of the fuel cells in both constant and variable OER controls.
Article
Chemistry, Multidisciplinary
Hossein Saberi, Ehsan Esmaeilnezhad, Hyoung Jin Choi
Summary: This study developed a model using deep neural networks to predict the MR behavioral trend of magnetite-based MR fluids. Various networks were employed for analysis, showing exceptional performance in both training and testing data.
JOURNAL OF INDUSTRIAL AND ENGINEERING CHEMISTRY
(2021)
Article
Computer Science, Artificial Intelligence
Fahad H. Alshammari
Summary: Agile methodologies have become the accepted standard for software development due to their flexibility, but face challenges in estimating budget, complexity, and time. Therefore, there is a need for a simple computational solution that considers critical factors and is suitable for inexperienced practitioners.
Article
Green & Sustainable Science & Technology
Diego Marcochi de Melo, Joel Villavicencio Gastelu, Patricia T. L. Asano, Joel D. Melo
Summary: This paper presents a methodology based on fuzzy logic to characterize the spatiotemporal dynamics of photovoltaic system adopters in residential subareas, demonstrating the influence of early adopters on adjacent areas. The proposed methodology uses linguistic variables to model adherence levels and results in heat maps identifying subareas with higher adoption rates. The spatial distribution of photovoltaic adopters in a medium-sized city in Brazil shows heterogeneous patterns, with an increasing percentage of high adoption areas over the years.
Article
Polymer Science
Essam Shehab, Arshyn Meiirbekov, Akniyet Amantayeva, Aidar Suleimen, Serik Tokbolat, Shoaib Sarfraz, Md Hazrat Ali
Summary: This research paper presents the development of a fuzzy logic-based system to perform cost estimation of recycling processes of CFRP. The system considers factors such as characteristics of waste materials, diversity of recycling methods, and cost drivers, and it includes an interactive user-friendly interface. The system is capable of evaluating the cost structure of CFRP recycling techniques and providing heuristic rules for selecting cost-effective recycling methods.
Article
Physiology
Naoaki Sakamoto, Taiga Haraguchi, Koji Kobayashi, Yusuke Miyazaki, Takahisa Murata
Summary: The evaluation of scratching behavior is important in experimental animals. We established an automated scratching detection method using a convolutional recurrent neural network. Our model successfully predicted scratching bouts and duration in white mice and was further improved for black mice.
FRONTIERS IN PHYSIOLOGY
(2022)
Article
Computer Science, Software Engineering
S. Asadi, N. Mahdavi-Amiri, Zs Darvay, P. R. Rigo
Summary: In this study, a feasible interior-point algorithm is proposed to solve the horizontal linear complementarity problem defined on a Cartesian product of symmetric cones. The algorithm does not rely on a usual barrier function but utilizes the Nesterov-Todd scaling point to scale the full steps. The method generates search directions leading to the full-NT steps by algebraically transforming the centring equation of the system using the induced barrier of a positive-asymptotic kernel function. The global convergence and local quadratic rate of convergence of the proposed method are established.
OPTIMIZATION METHODS & SOFTWARE
(2022)
Article
Computer Science, Interdisciplinary Applications
Navid Gholamian, Iraj Mahdavi, Nezam Mahdavi-Amiri, Reza Tavakkoli-Moghaddam
Summary: This article discusses a complex supply chain model aimed at improving sustainability and reducing costs. It considers multiple objective functions and decision levels, proposing a fuzzy approach to address uncertainties.
COMPUTERS & INDUSTRIAL ENGINEERING
(2021)
Article
Computer Science, Software Engineering
Hani Ahmadzadeh, Nezam Mahdavi-Amiri
Summary: The algorithm proposed in this study utilizes inexact solutions of QPs to ensure global convergence, guaranteeing descent direction in feasible and infeasible iterations. Additionally, the introduction of a nonmonotone filter strategy enhances the robustness and efficiency of the algorithm.
OPTIMIZATION METHODS & SOFTWARE
(2022)
Article
Engineering, Biomedical
Nooshin Moradi, Nezam Mandavi-Amiri
Summary: This paper proposes a method for multi-class segmentation of dermoscopic images based on joint dictionary learning, achieving better results, especially for challenging skin lesions. The experimental results demonstrate the efficiency and effectiveness of the proposed method in producing reliable results for clinical applications, even using limited training data.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2021)
Article
Operations Research & Management Science
Saeed Khanchehzarrin, Maral Shahmizad, Iraj Mahdavi, Nezam Mahdavi-Amiri, Peiman Ghasemi
Summary: A new mixed-integer nonlinear programming model is proposed for the time-dependent vehicle routing problem, using a tabu search optimization algorithm to solve large problems and evaluating the effectiveness of the algorithm through modeling and calculations.
RAIRO-OPERATIONS RESEARCH
(2021)
Article
Robotics
Hamed Fazlollahtabar
Summary: Industry 4.0 integrated with robotic and digital fabrication technologies has attracted the attention of manufacturing researchers. This paper proposes an intelligent control system based on SCADA in the IoT platform for processing configuration and reconfiguration of an autonomous assembly system, and the implementation study confirms its effectiveness.
Article
Statistics & Probability
Ali Sadeghi, Mansour Saraj, Nezam Mahdavi Amiri
Summary: This paper utilizes interior-point methods for solving fractional programming problems with second order cone constraints, proposing a logarithmic barrier function to demonstrate self-concordance and presenting an algorithm for computing ε-solutions. A numerical example is provided to illustrate the approach.
PAKISTAN JOURNAL OF STATISTICS AND OPERATION RESEARCH
(2021)
Article
Engineering, Industrial
Samane Babaeimorad, Parviz Fattahi, Hamed Fazlollahtabar
Summary: The paper presents an integrated strategy for inventory control and preventive maintenance planning for a single-machine production system. By using a numerical algorithm to find the optimal policy, it reduces production system costs and effectively deals with customer loss.
JOURNAL OF QUALITY IN MAINTENANCE ENGINEERING
(2022)
Article
Economics
Saeed Khanchehzarrin, Mona Ghaebi Panah, Nezam Mahdavi-Amiri, Saber Shiripour
Summary: In recent years, the frequency and severity of natural disasters worldwide have increased, causing significant financial and human losses. Decision-makers are therefore seeking ways to provide relief and reduce these losses. This study proposes a multi-objective bi-level model for the disaster location-routing problem, which considers multiple suppliers and supply risk. The findings highlight the importance of public donations in providing low-risk, high-priority goods to improve relief efforts.
SOCIO-ECONOMIC PLANNING SCIENCES
(2022)
Article
Operations Research & Management Science
Ja'far Dehghanpour, Nezam Mahdavi-Amiri
Summary: This article proposes an approach to convert the orthogonal nonnegative matrix factorization problem into a non-convex constraint problem and applies a penalty function to handle the non-convex constraints. The method performs well in partitioning clustering problems.
ANNALS OF OPERATIONS RESEARCH
(2022)
Article
Computer Science, Theory & Methods
Elham Monifi, Nezam Mahdavi-Amiri
Summary: This study proposes a time-varying dual accelerated gradient method for minimizing the average of multiple strongly convex and smooth functions over a time-varying network. Experimental results demonstrate its high efficiency.
JOURNAL OF PARALLEL AND DISTRIBUTED COMPUTING
(2022)
Article
Green & Sustainable Science & Technology
Zahra Taherikhonakdar, Hamed Fazlollahtabar
Summary: These days software plays an important role in various aspects of our lives. With the increasing use of computers, mobile applications, and embedded systems, the energy consumption of software has become a growing concern. Green IT has emerged as a focus on optimizing software solutions to reduce energy consumption. Despite the importance of green software development, few developers pay attention to software energy consumption, and even fewer users care about the energy consumption of the software they use. This article aims to help software developers develop energy-efficient software and inform users about the energy consumption of the software they use in order to ultimately reduce the negative impact of software on the environment.
ENVIRONMENTAL PROGRESS & SUSTAINABLE ENERGY
(2023)
Article
Computer Science, Software Engineering
Hamed Fazlollahtabar
Summary: Supplier selection is a significant problem in supply chain management, involving concurrent decision-making on key performance indicators based on multi-dimensional data. Recent studies have examined the supplier selection problem in various applied cases, with a focus on a range of criteria. This problem becomes more pronounced in industries with high levels of investment, such as the renewable energy sector. This article presents a new method that encompasses all relevant indices for effective supplier selection. The proposed algorithm utilizes decision tree (DT) indices to group criteria and sub-criteria, and uses a machine learning (RML) approach to handle uncertain data through rough comparisons and weighing. The method also includes a transformation (T) step to obtain crisp values and a ranking (R) of suppliers. A case study on renewable energy supplier selection demonstrates the effectiveness of the proposed method, particularly in handling big data through machine learning techniques. The article also discusses the managerial implications of this method as decision support.
CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE
(2023)
Article
Business
Nasim Ganjavi, Hamed Fazlollahtabar
Summary: In today's competitive environment, quality management is crucial for companies to reach a larger market share and economic success. The integration of physical machinery systems with digital networking in Industry 4.0 provides extensive opportunities for quality-related issues. To encompass all dimensions effective on quality management, it is necessary to process a large amount of data within the context of Industry 4.0. Advanced production systems and quality management are complementary resources to enhance functionality and gain a higher competitive advantage.
IEEE TRANSACTIONS ON ENGINEERING MANAGEMENT
(2023)
Article
Operations Research & Management Science
Reza Ghanbari, Khatere Ghorbani-Moghadam, Nezam Mahdavi-Amiri
Summary: The study introduces a modified Kerre's method for comparing LR fuzzy numbers and applies it to solving fuzzy linear programming problems with LR coefficients. By presenting a TV-MOPSO algorithm for computing the Pareto front, the effectiveness of the proposed algorithm is demonstrated through illustrative examples with triangular fuzzy coefficients.