A5056011854- Forecasting Techniques and Applications
- Stock Market Forecasting Methods
- Vehicle Routing Optimization Methods
- Urban and Freight Transport Logistics
- Big Data and Business Intelligence
- Food Supply Chain Traceability
- Scheduling and Timetabling Solutions
- Network Traffic and Congestion Control
- Real-Time Systems Scheduling
- Energy Load and Power Forecasting
- Management and Optimization Techniques
- Advanced Manufacturing and Logistics Optimization
- Smart Parking Systems Research
- Transportation Planning and Optimization
- Data Stream Mining Techniques
- Spectroscopy and Chemometric Analyses
- Traffic Prediction and Management Techniques
- Market Dynamics and Volatility
- Scheduling and Optimization Algorithms
- Simulation Techniques and Applications
- Optimization and Packing Problems
- Software Testing and Debugging Techniques
- Time Series Analysis and Forecasting
- Telecommunications and Broadcasting Technologies
- Model-Driven Software Engineering Techniques
Burapha University
2023-2025
Laboratoire d'Automatique, de Mécanique et d'Informatique Industrielles et Humaines
2004-2021
Université Polytechnique Hauts-de-France
2020
Centre National de la Recherche Scientifique
2020
Supply chains are complex, stochastic systems. Nowadays, logistics managers face two main problems: increasingly diverse and variable customer demand that is difficult to predict. Classical forecasting methods implemented in many business units have limitations with the fluctuating complexity of fully connected supply chains. Machine Learning been proposed improve prediction. In this paper, a Long Short-Term Memory (LSTM) for physical internet chain network. A hybrid genetic algorithm...
The National Broadcasting and Telecommunications Commission (NBTC) Thailand has implemented a policy to evaluate the quality of Fixed Broadband (FBB) internet in response numerous customer complaints across country. One proposed solutions for assessing FBB involves installing end devices test speeds with various service providers experimental area. However, due presence many within area, planning vehicle routes this mission is challenging, particularly given resource limitations. This paper...
This paper proposes an appropriate model to forecast the trend of white sugar consumption rate in Thailand due fluctuation nowadays. will focus on two main forecasting types, which are regression models and neural network models. Moreover, performance is evaluated by using Root Mean Square Error (RMSE) Theil'U statistic value. After processing experiments, results demonstrate that Long Short-Term Memory (LSTM) recurrent provides best for forecasting, with condition combination between...
Purpose This paper proposes an approach to solve the vehicle routing problem with simultaneous pickup and delivery (VRPSPD) in context of Physical Internet (PI) supply chain. The main objective is minimize total distribution costs (transportation cost holding cost) retailers from PI hubs. Design/methodology/approach Mixed integer programming (MIP) proposed smaller instances. A random local search (RLS) algorithm a simulated annealing (SA) metaheuristic are larger instances problem. Findings...
This paper proposes a hybrid partition clustering, which is the combination of three techniques: partitional proportional allocation, and center-of-gravity. The objective this clustering to identify applicable position established cloud servers support testing high-speed internet platform. These will be installed in Eastern region Thailand. Moreover, developed using RStudio R packages. latitude-longitude number populations from each district that has service providers are considered as main...
This paper proposes Dynamic Multiple Depots Vehicle Routing (DMDVR) to explore the feasible solution of routing transportation between PI-hubs and retailers in same cluster. The this research is constructed by daily forecasting demand a commodity crop, Pineapple, from Thailand’s northern region. Each route composed starting hub, number retailers, an ending hub. authors propose Mixed Integer Linear Programming (MILP) construct routes considering inventory truck capacity constraints. Besides,...
The performance metrics play a crucial role in evaluating Service Level Agreement (SLA) between Internet Providers (ISPs) and their customers. This paper introduces indicators designed for monitoring network's over both short extended periods. In the term, encompass ping, jitter, download speed, upload speed. Meanwhile, long suggested include average percentage, continued network functionality, reliability. These can serve as criteria establishing new SLA while considering all stakeholders involved.
Abstract Forecasting is a crucial part of supply chain management. Accurate forecasts have strong influence on performance. Many forecasting methods been developed and adapted in various domains industries. However, none are perfect all contexts due to the data's characteristics methods' strength. Hence, we propose new ARIMAX‐LSTM hybrid model that integrates ARIMAX LSTM models improve ability capture different combinations linear nonlinear patterns time series. Our proposed validated case...