Papers by International Journal of Enterprise Modelling
Article Info This research aims to address the issue of exponential rule generation in fuzzy rule... more Article Info This research aims to address the issue of exponential rule generation in fuzzy rule-based classification systems by developing a hybrid grid partition and rough set method. Fuzzy rule-based classification systems have the potential to construct linguistically understandable models, but a major constraint is the significant increase in the number of rules with a high number of attributes, which can diminish interpretation and classification accuracy. In this study, the grid partition method is utilized to generate fuzzy rules with adaptively adjusted grid structures, thus avoiding exponential rule proliferation. The research encompasses the use of the Iris Flower dataset, rule formation while considering variable precision, and classification accuracy testing. The research findings indicate that the hybrid grid partition and rough set method produces more efficient and accurate fuzzy rules, with a classification accuracy rate of 83.33%. This method also successfully reduces the number of generated rules, making it a promising solution to tackle the issue of exponential rule increase in fuzzy rule-based classification systems.
Article Info This research addresses the Vehicle Routing Problem (VRP) with uncertain data and pr... more Article Info This research addresses the Vehicle Routing Problem (VRP) with uncertain data and proposes a novel approach using quantum computing techniques. The problem involves optimizing vehicle routes considering uncertain customer demands, time windows, and vehicle capacities. We formulate the problem mathematically and develop an algorithmic framework to tackle it. The approach incorporates multiple scenarios based on the uncertainty distribution and selects the one with the minimum cost to optimize the vehicle routes. Through a numerical example, we demonstrate the effectiveness of the proposed approach in generating optimal routes that minimize the total distance traveled by the vehicles. The results highlight the solution quality, adaptability to uncertainty, and potential benefits in terms of cost reduction and resource utilization. While the computational efficiency of quantum computing approaches is a consideration, this research provides a promising direction for addressing uncertain optimization problems in logistics and transportation. Future research should focus on scalability and refinement of the algorithm to further enhance its applicability in real-world scenarios.
Article Info Rule generation in complex data analysis tasks poses challenges in terms of accuracy... more Article Info Rule generation in complex data analysis tasks poses challenges in terms of accuracy and interpretability. This research proposes a novel approach called Quantum-Inspired Fuzzy Genetic Programming (QIFGP) that integrates concepts from fuzzy logic, genetic programming, and quantum-inspired computing to address these challenges. The QIFGP model enhances the exploration of the solution space, increases the diversity of generated rules, and improves the accuracy and interpretability of the generated rules. The model is applied to a credit risk assessment problem, and the results are compared with traditional fuzzy logic-based approaches and genetic programming without quantum-inspired features. The experimental results demonstrate that the QIFGP model outperforms the baseline methods in terms of accuracy, achieving an accuracy of 87.5%. The generated rules exhibit a high level of interpretability, providing linguistic labels that capture meaningful relationships between the input features and risk classes. The incorporation of quantum-inspired features enables efficient exploration of the solution space while maintaining computational efficiency. The generalizability and robustness of the QIFGP model are demonstrated through consistent performance across multiple experiments and datasets. The QIFGP model offers a promising approach for enhanced rule generation in complex data analysis tasks, with potential applications in various domains where accurate and interpretable rule generation is crucial.
Article Info This research investigates the potential of quantum computing in production planning... more Article Info This research investigates the potential of quantum computing in production planning and addresses the limitations of conventional computing approaches. Traditional methods have been partially effective, but they struggle to solve complex optimization problems, accurately predict demand, and manage supply chains efficiently. The unique computational capabilities of quantum computing offer promising solutions to surmount these obstacles and revolutionize production planning processes. This study seeks to bridge the gap between quantum computing and production planning by analyzing the benefits, limitations, and challenges of its applicability in this field. It proposes customized algorithms and methodologies for leveraging quantum computation to enhance production planning efficiency, cost reduction, and decision-making processes. The research demonstrates the potential of quantum algorithms to minimize total production costs while appeasing demand and resource constraints through a numerical example and mathematical formulation. The results emphasize the advantages of quantum computing in terms of cost reduction, enhanced efficiency, and scalability. Comparisons with conventional methods illuminate the benefits and drawbacks of quantum computing in production planning. This research contributes to the development of novel strategies to improve production planning efficiency, lower costs, and enhance decision-making processes, allowing organizations to leverage quantum computing for optimized production operations.
Quantum computing is used to address supply chain optimization complexity and efficiency. Multipl... more Quantum computing is used to address supply chain optimization complexity and efficiency. Multiple locations, time periods, transportation expenses, facility opening costs, production capacity, and demand fulfillment requirements complicate supply chains. Supply chain optimization's complexity and huge solution areas challenge traditional optimization methods. Quantum algorithms can efficiently explore bigger solution areas in quantum computing. Starting with problem identification, this research reviews quantum computing and supply chain optimization literature. The supply chain optimization problem is modeled mathematically to incorporate transportation, facility opening, production, and cost. Binary choice factors and constraints ensure demand fulfillment, facility capacity limitations, and flow balance. The mathematical theory is applied numerically. The example addresses three locations, two time periods, transportation costs, demand amounts, production capacity, and facility opening costs. A proper optimization solver optimizes the decision variables to reduce total cost while meeting demand and making efficient supply chain decisions. The supply chain optimization model reduces costs and informs transportation, facility opening, and production decisions. The numerical example shows how quantum computing may optimize supply chain topologies and reduce costs. The study explains the findings, highlights gaps in the literature, and stresses the need for more research to bridge theory and practice. This study advances supply chain optimization with quantum computing. It shows how quantum computing might improve supply chain network decision-making, efficiency, and cost.
Article Info The research explores the application of quantum computing to manufacturing and supp... more Article Info The research explores the application of quantum computing to manufacturing and supply chain optimization in an effort to increase productivity, reduce costs, and improve product quality. Quantum algorithms, specifically the Quantum Approximate Optimization Algorithm (QAOA), are developed and evaluated to solve complex optimization problems in these domains. Quantum computing approaches are contrasted with traditional optimization techniques to demonstrate the potential advantages of quantum algorithms in terms of solution quality and working time efficiency. Practical implementation considerations of data availability, algorithm scalability, and system integration are also discussed. This research shows that quantum algorithms can effectively optimize production scheduling, resource allocation, and supply chain management, resulting in shorter production schedules and improved operational performance. This research recognizes the limitations of current quantum hardware, the complexity of the problem domain, and the difficulty of implementation. Despite these limitations, this research lays the foundation for further investigation and innovation in quantum computing for manufacturing and supply chain optimization, highlighting the potential for long-term transformative effects on industrial operations.
Article Info Efficient scheduling and routing of heterogeneous instant delivery orders pose signi... more Article Info Efficient scheduling and routing of heterogeneous instant delivery orders pose significant challenges in achieving timely and costeffective delivery operations. In this research, we propose a multiobjective optimization approach with real-time adaptability to address these challenges. We formulate a mathematical model that considers factors such as distance, importance of orders, capacity constraints, time windows, and cost per unit distance or time. The model aims to minimize the overall cost while optimizing the assignment of delivery orders to delivery agents and determining the corresponding routes. We present a numerical example to illustrate the application of the model and discuss the results obtained. The findings highlight the effectiveness of the proposed approach in achieving efficient scheduling and routing, leading to improved resource utilization, cost reduction, and enhanced customer satisfaction. This research contributes to the field of instant delivery services by providing a systematic framework that can be employed to optimize operations in real-world delivery scenarios.
Article Info This research aims to integrate machine learning and real-time optimization for hete... more Article Info This research aims to integrate machine learning and real-time optimization for heterogeneous instant delivery order scheduling and routing. The objective is to minimize the total delivery time while considering factors such as demand, time windows, predicted demand, and vehicle capacity constraints. By leveraging machine learning algorithms and real-time data, the proposed approach provides adaptive decision-making capabilities, allowing for dynamic adjustments in response to changing conditions. A mathematical formulation is developed to model the problem, and an algorithm is proposed to solve it. A numerical example is presented to demonstrate the effectiveness of the approach. The results highlight the optimal assignment of orders to vehicles at different time periods, leading to efficient delivery routes and minimized delivery time. The integration of machine learning and real-time optimization offers promising opportunities for enhancing the efficiency and responsiveness of delivery operations. This research contributes to advancing the field of instant delivery order scheduling and routing and paves the way for further developments in real-time logistics optimization.
Article Info Intelligent routing and scheduling strategies play a crucial role in optimizing effi... more Article Info Intelligent routing and scheduling strategies play a crucial role in optimizing efficiency, customer satisfaction, and sustainability in heterogeneous instant delivery services. This research focuses on developing a mathematical formulation and algorithm to address these challenges. The proposed model considers various factors, including delivery orders, vehicle capacities, time windows, and environmental impact, to minimize cost, delivery time, and emissions. The research also explores the integration of multiobjective optimization techniques to strike a balance between conflicting objectives. A numerical example is presented to illustrate the application of the mathematical formulation, showcasing the benefits of the proposed strategies in terms of efficient vehicle assignment, timely deliveries, and reduced environmental footprint. The findings highlight the potential for improving instant delivery services through intelligent routing and scheduling strategies, leading to enhanced operational efficiency, customer satisfaction, and sustainability. Further research is recommended to validate the proposed strategies in real-world scenarios and explore additional factors that may impact the routing and scheduling process in heterogeneous instant delivery services.
Article Info Data-driven decision making is vital in credit risk assessment and other areas. Comp... more Article Info Data-driven decision making is vital in credit risk assessment and other areas. Complex datasets are hard to rule. We use adaptive fuzzy network partitioning, rough set theory, and rule generation to improve data-driven credit risk assessment. An adaptive fuzzy network partitioning algorithm is used to cluster the dataset. Each cluster instance receives fuzzy membership degrees. Next, rough set-based attribute reduction identifies credit risk assessment attributes inside each cluster. Finally, attributes are used to build accurate and understandable credit risk assessment criteria. A loan application dataset is used to test the suggested method. The results show successful loan application clustering and the creation of credit risk criteria for each cluster. Accurate predictions and interpretable rules improve credit risk assessment comprehension and decisionmaking. By merging adaptive fuzzy network partitioning, rough set theory, and rule generation, the hybrid methodology overcomes classic technique constraints. These methods create a comprehensive framework for credit risk assessment criteria that improves accuracy and interpretability. Financial institutions and credit providers may benefit from the approach. The proposed approach can be tested in multiple domains and extended to handle increasingly complicated datasets. Evaluating the methodology on real-world datasets and comparing it to existing methods can also reveal its practicality and efficacy. This research generates accurate and interpretable rules for data-driven credit risk assessment using a hybrid method. Adaptive fuzzy network partitioning, rough set theory, and rule generation can improve decision-making across domains.
Article Info This research proposes a hybrid approach for adaptive fuzzy grid partitioning and ru... more Article Info This research proposes a hybrid approach for adaptive fuzzy grid partitioning and rule generation using rough set theory to address the problem of customer segmentation based on purchasing behavior. The objective is to minimize the fuzziness of the partitioning while maximizing the accuracy and interpretability of the generated rules. The research utilizes a dataset consisting of customer transactions, including demographics, purchase details, and satisfaction ratings. The fuzzy grid partitioning process divides the customer space into grid cells, representing different segments. Fuzzy membership values are assigned to data points based on their association with each grid cell. Rough set theory is employed for attribute reduction, identifying the most relevant attributes for customer segmentation. Rule induction algorithms generate rules that capture the patterns and dependencies among customer attributes and their association with specific grid cells. The hybrid approach combines the advantages of adaptive fuzzy grid partitioning and rough set-based rule generation. The optimization process adjusts fuzzy membership values and refines the generated rules to improve accuracy and interpretability. A numerical example and a case study in the retail industry are presented to demonstrate the effectiveness of the proposed approach. Results show successful customer segmentation and generation of actionable rules for marketing strategies. The research contributes to the field of customer segmentation by providing a comprehensive methodology that integrates adaptive fuzzy grid partitioning and rule generation using rough set theory. The hybrid approach offers valuable insights into customer behavior, enabling targeted marketing campaigns, personalized recommendations, and enhanced customer satisfaction.
Article Info Unpredictable timing and demand changes can greatly impair supply chain performance ... more Article Info Unpredictable timing and demand changes can greatly impair supply chain performance and resilience. Optimizing robust routing and production planning in stochastic supply chains improves efficiency and adaptability. Addressing timing and demand uncertainty improves resilience and efficiency. Supply chain management research emphasizes stochastic factors and resilient optimization. This research introduces a mathematical model that accounts for stochastic demand, transportation costs, holding costs, production capabilities, and lead times. The formulation minimizes cost while meeting uncertain demand and capacity constraints. Numerical examples demonstrate the model's use. Due to restrictions, the numerical example results are not supplied, but expected outputs include optimal routing and production plans, total cost minimization, sensitivity analysis, and insights into uncertainty. Comparisons with baseline situations can show how the proposed strategy improves resilience and efficiency. Supply chains may become more resilient, flexible, and efficient by optimizing routing and production planning in uncertainty. This research introduces stochastic components and resilient optimization methods to supply chain management. To improve the proposed approach in real-world supply chains, further research can examine improved algorithms, real-time data integration, and practical implementation strategies.
Article Info This research addresses the challenge of robust routing optimization in the context ... more Article Info This research addresses the challenge of robust routing optimization in the context of the Vehicle Routing Problem (VRP) with stochastic demands and time windows. The objective is to develop an effective logistics planning approach that considers demand uncertainty and time constraints in order to minimize costs and improve operational efficiency. A mathematical formulation is presented to model the problem, considering a robustness parameter to account for uncertainty in demand scenarios. The formulation incorporates binary decision variables to determine the routing plan and meet customer demands within specified time windows. A numerical example is provided to illustrate the application of the model, highlighting the impact of uncertainty and time window compliance on the routing plan and total expected cost. The results demonstrate the potential benefits of employing robust routing optimization, providing insights for logistics planners and decision-makers in designing more resilient and cost-effective routing strategies. Further research can explore advanced algorithms and real-world case studies to validate and enhance the proposed approach in practical logistics scenarios.
Article Info This research focuses ons addresses vehicle routing uncertainty in time windows and ... more Article Info This research focuses ons addresses vehicle routing uncertainty in time windows and stochastic needs. The project intends to increase vehicle routing efficiency, adaptability, and robustness by developing optimization approaches. Traffic congestion, unanticipated events, and changing client expectations can greatly impact truck routing solutions. Traditional methods presume fixed time frames and deterministic needs, resulting in suboptimal or infeasible paths. This paper presents a mathematical model that includes time window uncertainty and stochastic needs into the vehicle routing issue to address these restrictions. The formulation incorporates arrival times, delivery amounts, and route decisions to minimize transportation costs and ensure timely deliveries and resource efficiency. Advanced algorithms and solvers tackle the optimization challenge. Integer programming, flow conservation constraints, and temporal window constraints are used to identify optimal or near-optimal solutions to uncertainty and dynamic changes. Numerical examples and case studies demonstrate the approach's efficacy. Numerical examples demonstrate the mathematical formulation, while the case study shows the practical consequences and benefits for a dynamic delivery service organization. The research shows that the proposed approach can handle temporal window uncertainties and stochastic demands. These innovations can optimize vehicle routing, reduce transportation costs, boost customer happiness, and increase resource utilization. Addressing time window uncertainty and stochastic demands advances vehicle routing. The proposed approach helps logistics and transportation industries overcome dynamic and uncertain operating environments, boosting operational efficiency and competitiveness.
Article Info This research addresses time windows and stochastic demands in vehicle routing using... more Article Info This research addresses time windows and stochastic demands in vehicle routing using algorithmic improvements and robust solutions. Optimizing delivery operations requires managing routes and schedules while considering demand uncertainty and severe time frame limits. The research starts with a mathematical formulation that includes consumer locations, stochastic demands, time windows, and costs. Algorithms are added to handle uncertain requests and severe time window restrictions. Demand forecasting, route optimization, and uncertainty-based decision-making are used in the suggested strategy. The proposed routing method models stochastic requests using historical demand data and probability distributions. To create effective delivery plans, it analyzes client visit sequencing, vehicle capabilities, and time window limits. Numerical examples and case studies validate the proposed approach. Numerical examples show how the mathematical theory and algorithm address vehicle routing issues with time windows and stochastic demands. Case studies demonstrate how algorithmic advances and robust solutions benefit logistics firms in real-world circumstances. The proposed approach improves efficiency, cost savings, and customer satisfaction. Optimized routes and timetables help handle uncertain demand patterns, resource use, and time slots. Discussing the solutions' scalability and adaptability sheds light on their application and future research. This research provides algorithmic breakthroughs and robust solutions for vehicle routing time windows and stochastic needs. Logistics companies can increase operational efficiency and customer service with the findings. The proposed method optimizes delivery operations under uncertainty and time restrictions, helping logistics organizations compete in a changing business environment.
Article Info This research develops a machine learning-based multi-objective optimization techniq... more Article Info This research develops a machine learning-based multi-objective optimization technique for dynamic scheduling and routing heterogeneous instant delivery orders. Instant delivery service providers confront issues improving their operations due to order characteristics, time windows, vehicle capabilities, and real-time adaption. Scheduling, routing, and optimization literature for immediate delivery services is reviewed to start the investigation. Based on gaps, a new mathematical formulation is proposed to model the problem. Machine learning allows adaptive and dynamic decision-making. The formulation is used to address the optimization problem utilizing a method. Machine learning algorithms use past data to anticipate, optimize, and schedule routes. Real-time adaption solutions address changing order characteristics and operating situations. Numerical examples and case studies evaluate the proposed approach. The optimization approach solves difficult scheduling and routing problems in these cases. The research improves operational efficiency, cost savings, and order satisfaction. This research introduces a machine learningbased multi-objective optimization framework for rapid delivery order scheduling and routing. The findings help immediate delivery service providers streamline operations, boost customer happiness, and maximize resource use. To create more comprehensive optimization models, future research can integrate traffic circumstances, environmental implications, and customer preferences.
Article Info This study suggests combining Goal Programming, Multiple Criteria Decision Making (M... more Article Info This study suggests combining Goal Programming, Multiple Criteria Decision Making (MCDM), and Dynamic Decision-Making to solve production planning difficulties. Production planning entails balancing conflicting goals and dynamic circumstances when allocating resources, scheduling production, and managing inventory. The hybrid approach provides decision-makers with a comprehensive and adaptive framework that balances conflicting objectives, analyzes options using numerous criteria, and accounts for the dynamic production environment. Goal Programming helps solve the production planning challenge. MCDM methods like AHP or TOPSIS analyze and rank various production plans based on multiple factors. Dynamic Decision-Making methods like stochastic programming or simulation optimization accommodate for demand, supply, and other uncertainties in the production environment. A numerical example shows how the hybrid approach develops an optimal production plan by minimizing deviations from desired targets. Decision-makers can evaluate objective priorities and their effects on the solution by altering objective weights in sensitivity analysis. The hybrid approach can handle conflicting objectives, evaluate options using numerous criteria, and adapt to a dynamic production environment, according to studies. The suggested approach provides decision-makers with a comprehensive framework for efficient and successful production planning, adding to current information. Applying the hybrid method to real-world case studies, addressing supply chain dynamics and sustainability, and using AI and machine learning to improve decision-making are future research objectives. Production planning using Goal Programming, MCDM, and Dynamic Decision-Making seems promising. It helps manufacturers optimize resource allocation, customer happiness, and operational efficiency.
Article Info Optimization of production planning efficiency and sustainability is crucial for org... more Article Info Optimization of production planning efficiency and sustainability is crucial for organizations aiming to achieve operational excellence while minimizing their environmental footprint. This research proposes a novel approach that combines Goal Programming and Multiple Criteria Decision Making (MCDM) techniques to address the multi-objective nature of production planning. The study develops a mathematical formulation that considers objectives such as production efficiency, cost minimization, environmental impact reduction, and adherence to sustainability targets. A decision support system is designed to assist decision-makers in evaluating trade-offs and identifying the most suitable compromise solution. The research employs a numerical example to demonstrate the effectiveness of the proposed approach, showcasing how production quantities and sustainability practices can be optimized. The results highlight the ability of the approach to strike a balance between efficiency and sustainability, providing decision-makers with a comprehensive framework to make informed decisions aligned with sustainability goals. This research contributes to the existing literature by offering a practical methodology that enhances production planning processes, leading to more sustainable and efficient operations.
Article Info Next-generation air routing aims to revolutionize flight planning by integrating art... more Article Info Next-generation air routing aims to revolutionize flight planning by integrating artificial intelligence (AI), multi-objective optimization, and collaborative decision making to improve efficiency and sustainability. This research investigates the application of these techniques to optimize flight routes, minimize fuel consumption, reduce flight time, and enhance overall operational efficiency. The research develops a mathematical formulation model based on binary decision variables for aircraft routing, considering constraints such as airspace capacity, departure time, time windows, and route connectivity. The formulated model is solved using optimization algorithms to obtain optimized routing decisions. The results demonstrate the potential benefits of next-generation air routing, including reduced fuel consumption, improved flight time, efficient airspace capacity utilization, and logical route connectivity. The research contributes to the ongoing efforts in the aviation industry to address challenges related to efficiency, sustainability, and capacity management in flight planning. The findings provide insights for industry practitioners and policymakers to develop advanced systems and decision support tools for more efficient and sustainable flight operations.
Article Info The Vehicle Routing Problem (VRP) involves finding optimal routes for a fleet of veh... more Article Info The Vehicle Routing Problem (VRP) involves finding optimal routes for a fleet of vehicles to serve a set of clients while minimizing costs or optimizing efficiency. Scalability and uncertainty handling are issues with traditional VRP solutions. This study integrates Deep Reinforcement Learning (RL) with Graph Neural Networks (GNNs) to improve VRP solutions. Deep RL algorithms let agents learn optimal decision-making rules by interacting with the environment, whereas GNNs capture the VRP's graph representation's spatial and structural relationships. This research uses deep RL and GNNs to improve VRP solutions. The project intends to create an agent that can reason about customer, vehicle, and depot interactions and make educated routing decisions depending on the problem state by integrating deep RL agents with GNN models. Formulating the problem, preprocessing the data, constructing state and action representations, defining reward functions, training the deep RL agent and GNN models, and assessing the proposed strategy using benchmark VRP datasets. The merged deep RL-GNN technique improves VRP solutions. Optimized routing reduces travel expenses, improves resource use, and boosts efficiency. This research shows how deep RL and GNNs can overcome the limits of classic optimization methods for vehicle routing optimization. The findings emphasize the need of integrating advanced machine learning techniques into the VRP domain, enabling more effective and scalable real-world vehicle routing systems.
Uploads
Papers by International Journal of Enterprise Modelling