Search published articles


Showing 65 results for Optimization
Markowitz Revisited: Addressing Ambiguity as an Important Parameter in Portfolio Optimization
Seyed Erfan Mohammadi, Emran Mohammadi, Ahmad Makui, Kamran Shahanaghi,
Volume 34, Issue 4 (12-2023)
Abstract
Since 1952, when the mean-variance model of Markowitz introduced as a basic framework for modern portfolio theory, some researchers have been trying to add new dimensions to this model. However, most of them have neglected the nature of decision making in such situations and have focused only on adding non-fundamental and thematic dimensions such as considering social responsibilities and green industries. Due to the nature of stock market, the decisions made in this sector are influenced by two different parameters: (1) analyzing past trends and (2) predicting future developments. The former is derived objectively based on historical data that is available to everyone while the latter is achieved subjectively based on inside-information that is only available to the investor. Naturally, due to differences in the origin of their creation the bridge between these two types of analysis in order to optimize the portfolio will be a phenomenon called "ambiguity". Hence, in this paper, we revisited Markowitz's model and proposed a modification that allow incorporating not only return and risk but also incorporate ambiguity into the investment decision making process. Finally, in order to demonstrate how the proposed model can be applied in practice, it is implemented in Tehran Stock Exchange (TSE) and the experimental results are examined. From the experimental results, we can extract that the proposed model is more comprehensive than Markowitz's model and has greater ability to cover the conditions of the stock market.

A Modified Harris Hawks Algorithm to Solving Optimization Problems
Rabie Mosaad Rabie, Hegazy Zaher, Naglaa Ragaa Saied, Heba Sayed,
Volume 35, Issue 1 (3-2024)
Abstract
Harris Hawks Optimization (HHO) algorithm, which is a new metaheuristic algorithm that has shown promising results in comparison to other optimization methods. The surprise pounce is a cooperative behavior and chasing style exhibited by Harris' Hawks in nature. To address the limitations of HHO, specifically its susceptibility to local optima and lack of population diversity, a modified version called Modified Harris Hawks Optimization (MHHO) is proposed for solving global optimization problems. A mutation-selection approach is utilized in the proposed Modified Harris Hawks Optimization (MHHO) algorithm. Through systematic experiments conducted on 23 benchmark functions, the results have demonstrated that the MHHO algorithm offers a more reliable solution compared to other established algorithms. The MHHO algorithm exhibits superior performance to the basic HHO, as evidenced by its superior average values and standard deviations. Additionally, it achieves the smallest average values among other algorithms while also improving the convergence speed. The experiments demonstrate competitive results compared to other meta-heuristic algorithms, which provide evidence that MHHO outperforms others in terms of optimization performance. 

Automobile Workshop Queue System Optimization Using Response Surface
Welly Sugianto, Reazul Haq Abdul Haq, Mohd Nasrull Bin Abdol Rahman,
Volume 35, Issue 1 (3-2024)
Abstract
The automobile workshop queue system has been optimized using various approaches, such as queuing theory, simulation, and probability. The utilization of response surface methodology (RSM) for optimizing automobile workshop queue systems is not yet established. The utilization of RSM with direct observation enables the detection of patterns of correlations between variables and responses, which are then represented through mathematical equations. The optimization process involves numerous factors that impact queue performance, which can be categorized into two parts. The number of servers, number of phases, number of workers, worker experience, and layout are classified in inner design. This study examines the relationship between two components of the outer design, specifically the arrival rate and the interarrival time. The responses analyzed are queue cost, service time, average customer waiting time, and number of customers. The findings indicate that queue costs are not reliable for establishing the optimum value due to the significant impact of the cost structure on the structure of the optimal location. This study discovered that the number of leaving customers is related to queue costs and is relevant in selecting the optimal point. This study also formulates mathematical equations for predicting the optimal point. This study emphasizes the necessity for further investigation to uncover alternative mathematical equations that can precisely predict the optimal conditions for various types of services.

A Robust Optimization Approach for a Discrete Time-Cost-Environment Trade-off Project Scheduling Problem Under Uncertainty
Ali Salmasnia, Elahe Heydarnezhad, Hadi Mokhtari,
Volume 35, Issue 2 (6-2024)
Abstract
Abstract. One of the important problems in managing construction projects is selecting the best alternative for activities' execution to minimize the project's total cost and time. However, uncertain factors often have negative effects on activity duration and cost. Therefore, it is crucial to develop robust approaches for construction project scheduling to minimize sensitivity to disruptive noise factors. Additionally, existing methods in the literature rarely focus on environmentally conscious construction management. Achieving these goals requires incorporating the project scheduling problem with multiple objectives. This study proposes a robust optimization approach to determine the optimal construction operations in a project scheduling problem, considering time, cost, and environmental impacts (TCE) as objectives. An analytical algorithm based on Benders decomposition is suggested to address the robust problem, taking into account the inherent uncertainty in activity time and cost. To evaluate the performance of the proposed solution approach, a computational study is conducted using real construction project data. The case study is based on the wall of the east coast of Amirabad port in Iran. The results obtained using the suggested solution approach are compared to those of the CPLEX solver, demonstrating the appropriate performance of the proposed approach in optimizing the time, cost, and environment trade-off problem.

Optimization of Hand Gesture Object Detection Using Fine-Tuning Techniques on an Integrated Service of Smart Robot
Faikul Umam, Hanifudin Sukri, Ach Dafid, Firman Maolana, Mycel Natalis Stopper Ndruru,
Volume 35, Issue 4 (12-2024)
Abstract
Robots are one of the testbeds that can be used as objects for the application of intelligent systems in the current era of Industry 4.0. With such systems, robots can interact with humans through perception (sensors) like cameras. Through this interaction, it is expected that robots can assist humans in providing reliable and efficient service improvements. In this research, the robot collects data from the camera, which is then processed using a Convolutional Neural Network (CNN). This approach is based on the adaptive nature of CNN in recognizing visuals captured by the camera. In its application, the robot used in this research is a humanoid model named Robolater, commonly known as the Integrated Service Robot. The fundamental reason for using a humanoid robot model is to enhance human-robot interaction, aiming to achieve better efficiency, reliability, and quality. The research begins with the implementation of hardware and software so that the robot can recognize human movements through the camera sensor. The robot is trained to recognize hand gestures using the Convolutional Neural Network method, where the deep learning algorithm, as a supervised type, can recognize movements through visual inputs. At this stage, the robot is trained with various weights, backbones, and detectors. The results of this study show that the F-T Last Half technique exhibits more stable performance compared to other techniques, especially with larger input scales (640×644). The model using this technique achieved a mAP of 91.6%, with a precision of 84.6%, and a recall of 80.6%.
 
Page 4 from 4