KMITL

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

Browse

Search Results

Now showing 1 - 6 of 6

Some of the metrics are blocked by your
consent settings
Artificial Neural Network (ANN)-Based Analysis and Optimal Control of Smoking Dynamics with Global Sensitivity Assessment
(2026-06-01)
Omrane, Ines Ben
;
Ullah, Naeem
;
Alhamzi, Ghaliah
;
Jeelani, Mohammadi Begum
The main objective of this study is to investigate smoking dynamics, identify the most influential factors governing smoking behavior, and develop effective intervention strategies through the integration of fractional-order modeling, sensitivity analysis, optimal control theory, and artificial neural networks (ANNs). A nonlinear fractional-order compartmental model is formulated by dividing the population into potential smokers, light smokers, heavy smokers, and quit smokers. The smoking reproduction number is derived to characterize the transmission and persistence of smoking behavior within the population. To determine the impact of model parameters on smoking dynamics, both normalized forward sensitivity analysis and global sensitivity analysis based on Latin Hypercube Sampling (LHS) with Partial Rank Correlation Coefficient (PRCC) are performed. The obtained results identify the most sensitive transmission and progression parameters and demonstrate their important role in shaping smoking prevalence within the community. Furthermore, the classical integer-order model is compared with the fractional-order formulation, where the fractional model provides a more realistic description due to its ability to incorporate memory and hereditary effects associated with smoking behavior. An optimal control framework involving awareness and treatment strategies is further introduced to investigate effective smoking reduction policies. The numerical results demonstrate that awareness campaigns reduce smoking initiation, while treatment interventions increase smoking cessation, and the combined implementation of both strategies produces the most significant reduction in smoking prevalence. The consistency between the sensitivity analysis and optimal control results further supports the reliability of the proposed framework. Numerical simulations are carried out to analyze the qualitative and quantitative behavior of the system under different epidemiological scenarios. In addition, an ANN-based computational framework is employed as an efficient numerical tool to accurately approximate the complex dynamics of the proposed fractional-order smoking model with very low prediction error. Overall, the present study provides a comprehensive mathematical and computational framework for understanding, analyzing, and controlling smoking behavior within a population.
Some of the metrics are blocked by your
consent settings
Advancing Masonry Engineering: Effective Prediction of Prism Strength via Machine Learning Techniques
(2026-04-01)
Saingam, Panumas
;
Chatveera, Burachat
;
Nawaz, Adnan
;
Ali, Muhammad Hassan
;
Choudhary, Sandeerah
Masonry buildings have shaped construction history since about 6500 BCE. They offer durability, strength, and cost effectiveness, especially in developing countries. Yet assessing compressive strength during construction remains challenging due to the constituent materials soil, cement, and stone, complicating standardization worldwide. In the present study, an innovative model based on a machine learning algorithm is put forth to predict the compressive strengths of prisms. Some important factors considered as input to the algorithm based on traditional methods are the brick and mortar strengths, prism geometry, mortar bed thickness, and empirically derived height-to-thickness (t) (h/t) ratios. Three different ANN algorithms are coded and trained on the input data, and they are based on the Levenberg–Marquardt algorithm, the resilient backpropagation algorithm, and the conjugate gradient algorithm. The optimal ANN model trained using the conjugate gradient Polak–Ribière algorithm (traincgp) achieves superior performance, with R<sup>2</sup> = 0.9881, R<sup>2</sup> = 0.9927, RMSE = 0.9914 MPa, MAE = 0.6039 MPa, MAPE = 20.9141%, VAF = 0.9881, and WI = 0.9970. Sensitivity analysis shows the height-to-thickness (h/t) ratio is the dominant influence on compressive strength, consistent with structural mechanics. The primary contributions are the systematically curated, richly parameterized dataset and its use to produce robust, physically interpretable predictions with established ANN methods.
Some of the metrics are blocked by your
consent settings
An Optimization Model for the Maximized Profit of Housing Development Project: A Case Study of Bangkok and Perimeter, Thailand
(2023-05-01)
Kakaew, Siripob
;
U-tapao, Chalida
The objective of this research was to assess the profitability of the housing development project located in Bangkok, and the perimeter areas are Nonthaburi, Samut Prakan, and Pathum Thani, which are the result of good construction management. Moreover, the researchers’ previous data were used to predict the profit for construction planning, using stepwise multiple regression analysis. Then, we found the profit equation of the housing development project and applied it to the optimization model to clarify the model by the case study. The case study has 427 units, dividing the house into three types, with an optimization performed using the GAMS tool. In the same way, according to this optimization, it can be divided into two scenarios: scenario one found the maximized profit of the project to be 1053.91 MB, and scenario two was the result of making a sensitive analysis of scenario one and found the maximized profit of the project to be 1054.18 MB, which is the best scenario for the maximized profit of the project, and so it is the best choice for construction planning. The research contribution in this model can be applied to other projects that are suitable for large or densely populated cities, such as Beijing, New Delhi, and others. In the Conclusion section, we offer recommendations and detail future work that the researchers have discussed and described for the benefit of future research in housing development projects.
Some of the metrics are blocked by your
consent settings
Sensitivity analysis of cassava mosaic disease with saturation incidence rate model
(2023-01-01)
Sangsawang, Sireepatch
;
Humphries, Usa Wannasingha
;
Khan, Amir
;
Pongsumpun, Puntani
Cassava mosaic disease (CMD) is caused by a virus transmitted by the whitefly. This disease can destroy cassava at any stage of its growth and it resulted in lower cassava yields. In this paper, we developed a mathematical model for the epidemic of cassava mosaic disease with a deterministic model which has saturation incidence rates. This model aims to explain the effect of vectors on cassava disease outbreaks. First, this model was analyzed using standard dynamic methods to determine the behavior of the solution. We found the existence and condition of disease-free and endemic steady state. The basic reproductive number (R<inf>0</inf>) is obtained by using the next-generation method which R<inf>0</inf> helps assess the ability to spread infectious diseases. Second, the stability of the steady state was analyzed, then we obtain the condition of existence of local stability and global stability at each steady state of this model. Third, analysis of the sensitivity indices in the threshold number to determine the effect of the various parameters. Finally, the results of the theoretical model were validated by numerical simulations. It is represented by various graphs converging at a steady state and stable.
Some of the metrics are blocked by your
consent settings
An Integrated Factor Analysis-Technique for Order Preference by Similarity to Ideal Solution for Location Decision in ASEAN Region: A Case Study of Thai Fabric Manufacturing Plant
(2023-01-01)
Atthirawong, Walailak
;
Panprung, Wariya
;
Wanitjirattikal, Puntipa
In this paper, we propose an integrated model for selecting a suitable location for fabric manufacturing plants in the ASEAN region. In the first phase, Cambodia, Vietnam and Indonesia were determined as candidate locations for evaluation from the screening process. In this regard, key criteria influencing location decisions were derived using factor analysis of responses extracted from questionnaires. In the second phase, criterion weights were calculated using the rank of centroid (ROC) method. Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) was then used to prioritize three location alternatives, and sensitivity analysis was also employed to verify the stability of the method. Based on TOPSIS method, Vietnam was the preferred location, followed by Indonesia while Cambodia was not recommended. Sensitivity analysis also showed that the proposed model was valid. The findings from this study provided references for enterprises engaged in international location decision making. The results can help them better understand the decision-making process and identify key criteria that can influence location decisions internationally.
Some of the metrics are blocked by your
consent settings
A stochastic multimodal reliable network design problem under adverse weather conditions
(2015-01-01)
Uchida, Kenetsu
;
Sumalee, Agachai
;
Ho, H. W.
This paper formulates a network design problem (NDP) for finding the optimal public transport service frequencies and link capacity expansions in a multimodal network with consideration of impacts from adverse weather conditions. The proposed NDP aims to minimize the sum of expected total travel time, operational cost of transit services, and construction cost of link capacity expansions under an acceptable level of variance of total travel time. Auto, transit, bus, and walking modes are considered in the multimodal network model for finding the equilibrium flows and travel times. In the proposed network model, demands are assumed to follow Poisson distribution, and weather-dependent link travel time functions are adopted. A probit-based stochastic user equilibrium, which is based on the perceived expected travel disutility, is used to determine the multimodal route of the travelers. This model also considers the strategic behavior of the public transport travelers in choosing their routes, that is, common-line network. Based on the stochastic multimodal model, the mean and variance of total travel time are analytical estimated for setting up the NDP. A sensitivity-based solution algorithm is proposed for solving the NDP, and two numerical examples are adopted to demonstrate the characteristics of the proposed model.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results