KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1

Browse

Search Results

Now showing 1 - 10 of 14

Some of the metrics are blocked by your
consent settings
Ant Colony Optimization for Solving Electric Vehicle Traveling Salesman Problems
(2026-01-01)
Janjarassuk, Udom
Electric Vehicles (EVs) have become very popular nowadays due to their affordability, lower operating cost and maintenance cost, and environmental benefits. In this paper, we study an electric vehicle variant of the traveling salesman problem (EV-TSP) by using a modified ant colony optimization (ACO) method. Unlike the traditional traveling salesman problem (TSP), the electric vehicle variant of the TSP is more complex due to the limited battery range and the requirement of recharging along the trip. To tackle these difficulties, our proposed algorithm incorporates the battery level constraint as a heuristic information for choosing the next visiting node. We use a sigmoid function to capture the probability of node selection in addition to the pheromone value and visibility of ant. The type of nodes is also considered during the node selection. When the remaining battery level of the vehicle is low, the charging station nodes will have higher probability of being selected compared to the customer nodes, and vice versa. The algorithm was implemented in C++ and tested by using a number of benchmark instances from TSPLIB. The problem instances were modified by adding vehicle range and charging stations with their associated locations. Computational results were reported to show the effectiveness of the algorithm.
Some of the metrics are blocked by your
consent settings
A Hybrid Greedy Algorithm for the Capacitated Vehicle Routing Problem
(2025-01-01)
Janjarassuk, Udom
The Vehicle Routing Problem (VRP) is one of the most common problems in logistics and supply chain. In this study, we propose a hybrid greedy algorithm for the capacitated vehicle routing problem (CVRP) which is a variant of the VRP with vehicle capacity constraint. The algorithm adapts the minimal spanning tree algorithm to decompose the CVRP into many smaller traveling salesman problems (TSPs), and solves each sub-problem by using the Nearest Neighbor (NN) greedy algorithm. The hybrid algorithm is tested by using instances from the CVRPLIB library. The algorithm provides relatively good performances with optimality gaps varying from 4-30% across all tested instances, and the computational time is less than 1 second in all cases.
Some of the metrics are blocked by your
consent settings
Hybrid Ant Colony Optimization Method for the Traveling Salesman Problem
(2024-01-01)
Janjarassuk, Udom
The traveling salesman problem (TSP) is a classic problem in computer science and operations research which involves finding the shortest possible route that visits a given set of cities. In this paper, we propose a hybrid algorithm for solving such problem. The algorithm combines the ant colony optimization (ACO) method with the 2-opt heuristic to improve the efficiency for solving the TSP. Instances from the TSPLIB were used to test the algorithm. The results showed that the hybrid ACO algorithm was more effective in solving the TSP as compared to the traditional ACO or the 2-opt heuristic methods.
Some of the metrics are blocked by your
consent settings
LPG Leakage Risk Predictions from an IoT-Based Detection System Using Machine Learning
(2023-01-01)
Lorthong, Saksiwa
;
Janjarassuk, Udom
;
Jayranaiwachira, Nuthvipa
LPG has the potential to ignite and explode if it spills since it is a flammable gas. Explosions and flames caused by LPG leaks can damage or kill people who are working in the hazardous area. The industrial sector currently lacks efficient warning systems to identify and anticipate leaks, necessitating efficient equipment to identify and monitor gas leaks. This work aims to investigate and identify a device designed to detect and keep track of LPG leaks by utilizing straightforward yet efficient IoT technologies. The experimental and carefully vetted data are applied to build an Artificial Neural Network (ANN) model for predicting the risk of gas leaks. Gas leaks in the workplace are monitored, alerted to, and controlled by using gas detection systems based on IoT technology. The dataset is then submitted to factor analysis for feature selection, which made use of the model's expertise from its examination of the information gathered from the detecting device in the Cloud system. Several measures were utilized to evaluate the model, including Accuracy, Precision, Recall, F1-Score and Area Under the Curve (AUC). The investigation led to clustering the Risk Ranking Number into three levels, which were then utilized in conjunction with the Risk Matrix to evaluate risk. The net processing time was 1.34 minutes, and the forecast accuracy was 96.05%. This study will assist in improving the model that establishes the alarm system's alert level.
Some of the metrics are blocked by your
consent settings
Two-stage stochastic program for supply chain network design under facility disruptions
(2021-03-01)
Kungwalsong, Kanokporn
;
Cheng, Chen Yang
;
Yuangyai, Chumpol
;
Janjarassuk, Udom
A supply chain disruption is an unanticipated event that disrupts the flow of materials in a supply chain. Any given supply chain disruption could have a significant negative impact on the entire supply chain. Supply chain network designs usually consider two stage of decision process in a business environment. The first stage deals with strategic levels, such as to determine facility locations and their capacity, while the second stage considers in a tactical level, such as production quantity, delivery routing. Each stage’s decision could affect the other stage’s result, and it could not be determined individual. However, supply chain network designs often fail to account for supply chain disruptions. In this paper, this paper proposed a two-stage stochastic programming model for a four-echelon global supply chain network design problem considering possible disruptions at facilities. A modified simulated annealing (SA) algorithm is developed to determine the strategic decision at the first stage. The comparison of traditional supply chain network decision framework shows that under disruption, the stochastic solutions outperform the traditional one. This study demonstrates the managerial viability of the proposed model in designing a supply chain network in which disruptive events are proactively accounted for.
Some of the metrics are blocked by your
consent settings
Locating an ambulance base by using social media: a case study in Bangkok
(2019-12-01)
Nilsang, Suriyaphong
;
Yuangyai, Chumpol
;
Cheng, Chen Yang
;
Janjarassuk, Udom
Response time reduction is a fundamental aspect of ambulance location management. To minimize patient mortality and disability, the response time of emergency medical services is critical. Therefore, real-time management is required to determine the location of an ambulance with a low response time or called or a dynamic allocation system. Dynamic allocation is moving the ambulance bases from low demand areas to high-demand areas that is useful in the operational level. However, the dynamic allocation model for real-time management requires re-allocation of ambulances, resulting in high costs and heavy workloads for the ambulance crews. This paper focuses on a covering model based on social media analysis. The model was used for developing an ambulance reallocation system. In addition to dynamic allocation, the proposed model considers real-time data from a social media application (Twitter) to minimize the response time and cost during emergencies and disasters. Twitter has been used in various ways to communicate during and manage emergencies. In this paper, we formulate the Maximal Covering Location Problem (MCLP), develop a solution procedure based on social media (Twitter application) and show the effect of the approach on the optimal solution by comparing it with the classical approach and also demonstrate our approach on Bangkok EMS.
Some of the metrics are blocked by your
consent settings
Product recommendation based on genetic algorithm
(2019-07-01)
Janjarassuk, Udom
;
Puengrusme, Sudatip
In this paper, we propose a product recommendation system based on genetic algorithm to find the best recommendation for a combination of products to the customers. The model evaluation relies on customer preferences and product requirements as well as feature ratings from the product experts. The system is tested by using a case study from recommendation of power unit selection for recording studio. Experimental results are provided.
Some of the metrics are blocked by your
consent settings
An interactive Analytic Hierarchy Process for product recommendation: A case study in studio recording
(2019-01-01)
Puengrusme, Sudatip
;
Janjarassuk, Udom
The Analytic Hierarchy Process (AHP) is a powerful tool for decision making. In this paper, we present an application of AHP used for product recommendation to assist customers in selecting power equipment for studio recording. The application is implemented in Microsoft Excel in an interactive manner where customers are asked to answer questions related to product requirements and customer preferences. The customer information is combined with the predefined judgments from the experts according to a given set of criteria for product selection. The score for each product is then calculated according to the AHP, and the top three products with the highest score are recommended for the customer. The proposed method is tested by the customers and the results are discussed.
Some of the metrics are blocked by your
consent settings
Classification of bearing fault location and severity using cascade ANNs with statistical and spectral features
(2019-01-01)
Kuendee, Punyisa
;
Janjarassuk, Udom
Advance in machine learning techniques for machine condition monitoring is now an active field of interest in modern industry for predicting the future health of machines. In this paper, Artificial Neural Networks (ANNs) technique is investigated by using the existing datasets of ball bearing fault to classify the fault location and severity. To enhance the accuracy, the utilization of statistical features and spectral features are used in pre-processing with the proposed method of cascade ANNs. Motor vibration data is collected by using accelerometers attached to the housing in the drive end and fan end. To diagnose the faults in the rolling bearing, the vibration data is pre-processing by using Fast Fourier Transform (FFT) and other statistical features such as standard deviation, skewness and kurtosis etc. Then the feature data is fed into cascade ANN_1 and ANN_2 to classify the fault location and severity. The objective of this research is to solve the problem of poor features such as slippage frequency component in FFT response and inappropriate statistical feature datasets to help increase in accuracy and efficiency. The results show that the proposed method gives more accuracy when the poor features are existed and guarantee the accuracy near to 100%.
Some of the metrics are blocked by your
consent settings
A comparison of Latin hypercube sampling techniques for a supply chain network design problem
(2018-08-14)
Kaewsuwan, Kantapit
;
Yuangyai, Chumpol
;
Janjarassuk, Udom
;
Rienkhemaniyom, Kanokporn
Currently, supply chain network design becomes more complex. In designing a supply chain network to withstand changing events, it is necessary to consider the uncertainties and risks that cause network disruptions from unexpected events. The current research related to the designing problem considers network disruptions using Monte Carlo Sampling (MCS) or Latin Hypercube Sampling (LHS) techniques. Both have a disadvantage that sample points or disruption locations are not scattered entirely sample space leading to high variation in objective function values. The purpose of this study is to apply a modified LHS or Improved Distributed Hypercube Sampling (IHS) techniques to reduce the variation. The results show that IHS techniques provide smaller standard deviation than that of the LHS technique. In addition, IHS can reduce not only the number of sample size but also and the computational time.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results