KMITL

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

Browse

Search Results

Now showing 1 - 10 of 12

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
Modeling the green extraction of bioactive compounds from Pilangkasa fruit (Ardisia elliptica Thunb) through empirical and machine learning approaches
(2026-01-01)
Vinh, B. T.
;
Loan, L. T.K.
;
Mansamut, C.
;
Tai, N. V.
Pilangkasa Fruit (Ardisia elliptica Thunb) contains the rich bioactive compounds, which still limited the study to utilization. This study aimed to investigate the effect of green extraction technique – ultrasoud-assisted extraction on the antioxidants recovery efficient and establish the kinetic extraction under different conditions. Five level of sonication amplitute (0, 25, 50, 75, 100%) were used for extraction at a time range from 0 to 90 minutes. The extraction yield (%), total phenolic compound (mg gallic acid equivalent per g, mgGAE/100 g), total anthocyanin content (mg/100 g) were determined. The experimental data was fitted with five empirical models to find the best fit model. The power of sonication greatly influenced the efficiency for recovering the phytochemical compounds in Pilangkasa fruit (Ardisia elliptica Thunb). The fast rate of extraction was found at the initial stage (after 30 min of extraction), then reached the equilibrium stage or slightly declined. Among the five empirical models, first-order model showed the best fit between the actual and predicted data. While, ANN model presented the fast and accurate prediction the extraction process. Based on the extraction rate constant from the first-order model, the level of around 50-75% of amplitute was considered as the appropriate condition for extraction polyphenol from Pilangkasa fruit with high yield of extraction, total polyphenol content, total anthocyanin content. These conditions could be further optimized and upscaled for used in food industry.
Some of the metrics are blocked by your
consent settings
Modelling the Effect of Types and Concentrations of Sugar on Hardness and Overall Acceptability of Freeze-Dried “Sáp” Coconut Meat: An Artificial Intelligent Approach
(2025-01-01)
Loan, Le Thi Kim
;
Chi, Huynh Thi Kim
;
Mansamut, Chaiyut
;
Van Tai, Ngo
Coconut is one of the common plants in Southeast Asia countries, which could further develop into various products. This study is aimed to study the effect of soaking conditions (types and concentrations of sugar) on the hardness and acceptance score of freeze-dried meat of “Sáp” coconut variety in Vietnam. Artificial neural network (ANN) model was used for predicting and modelling. A total of 540 datasets with two input variables and two output responses were divided into 70% of the training dataset, 15% of the validation dataset, and 15% of the testing dataset. ANN model was successfully forecasted the impact of soaking conditions on physical hardness and eating quality of product. The high agreement between actual and ANN’s predicted values was found with high coefficient determination (R2 > 0.9). Moreover, the correlation between the hardness and acceptability of product also provided. This information could be supported for further study to optimize the process of producing high-quality and sensory freeze-dried coconut meat.
Some of the metrics are blocked by your
consent settings
A Kinetic Study on Starch Digestibility and Polyphenol Release of Different Physically Modified Riceberry Flours During In Vitro Stimulated Gastrointestinal Digestion
(2025-01-01)
Van Ngo, Tai
;
Naphatrapi, Luangsakul
Riceberry rice has a dark purple color; and a high content of antioxidants, which could affect the digestion behaviors and its application. This study is aimed to analyze the starch digestion rate and predict the bio-accessibility of polyphenols in various modified Riceberry flours during the in vitro digestive process. It also discussed the relationship between the rate of digestion and polyphenol release, which provided basic information about the digestion behavior of Riceberry flour. Seven rice flour samples were used for this study, which included six physically treated flours: annealed flour (AF), heat moisture-treated flour (HMT), pregelatinized flour (Pregel), ultra-sonicated flour (US), wet microwave-treated flour (Wet), dry microwave treated flour (Dry), and untreated (control sample). The obtained results showed that, compared with the control sample, the digestion rate of the Pregel sample was higher, while the others had lower values. However, the Pregel sample showed the second highest rank of bio-accessible polyphenol during digestion after the US sample. While the HMT sample presented the lowest rate of starch digestion and release of bioactive compounds. This investigation also used an artificial neural network (ANN) to forecast the starch digestion and polyphenol bio-accessibility of rice flours. During digestion, the ANN model demonstrated a high capacity to predict the polyphenol bio-accessibility and starch hydrolysis percentage. There was a goodness of fit between the ANN-predicted and the actual values (R2 >0.95). The importance of the bioavailability and bio-accessibility analysis indicates the functional potential that flour can have, which could be predicted effectively by applying modern techniques such as the ANN model. Moreover, it was also concluded that the digestive tract readily absorbs released polyphenol compounds in rice flour, which also influences the rate of starch hydrolysis. However, the impact could vary depending on the flour’s starch fraction content and the polyphenol activity, which is a topic for future investigation. The high antioxidant content and low digestion rate of flour could be highly promising functional materials for application in the food industry..
Some of the metrics are blocked by your
consent settings
Modeling of dehydration, polyphenol thermal degradation, and rehydration of instant germinated VD20 rice: Mathematical and artificial intelligence model
(2025-01-01)
Loan, L. T.K.
;
Tat, T. Q.
;
Minh, P. D.T.
;
Thao, V. T.T.
;
Hoang, P. T.M.
VD20 rice, a local rice variety in Vietnam, is currently undergoing restoration and provides limited information about product development. In order to produce the instant germinated VD20 rice, the study on kinetics of dehydration, polyphenol thermal degradation, and rehydration of the instant product was carried out. Different temperatures were applied in this study, including 50°C, 55°C, 60°C, and 65°C. Various models were developed to describe these changes. The Page model provided the best fit for the sample's dehydration properties, with the moisture diffusivity (D<inf>eff</inf>) ranging from 7 x 10-12 to 1.19 x 10-11 m2/s and an activation energy of 31.70 kJ/mol. A zero-order model described the change in polyphenol during the drying process. The half-life values ranged from 3.737 h to 5.723 h. Also, the ANN model was used. This is an intelligent model made of an artificial neural network. It worked better and faster than earlier models like the Page model for dehydration behavior and the zero-order model for degradation property. The rehydration ratio of instant germinated rice also fitted well with the exponential model. These developed insights could facilitate further optimization and production on a larger scale, thereby enabling farmers to produce more products from this rice.
Some of the metrics are blocked by your
consent settings
Evaluation of the Power Demand for Economic Load Dispatch Problem Using Adaptive Neuro-Fuzzy Inference System and Artificial Neural Network
(2024-01-01)
Jiriwibhakorn, Somchat
;
Wongwut, Kamolwan
The evaluation of power demand is fundamental in the Economic Load Dispatch problem, ensuring that the generated power meets the needs of consumers reliably and efficiently in planning system operations. This paper presented two approaches using an Adaptive Neuro-Fuzzy Inference System (ANFIS) and an Artificial Neural Network (ANN) to evaluate the power demand. The modified IEEE 57-Bus system is considered the thermal units that incorporate renewables. The ANFIS and ANN are implemented using MATLAB online version R2023b. The results show that the ANN and ANFIS techniques are suitable for evaluating power demand. A comparison of both methods indicates that ANFIS is relatively superior to the ANNs techniques, considering the coefficient of determination of the ANNs and ANFIS were equal. The accuracy of its results in terms of prediction RMSE for the ANN and ANFIS of 10.147e-05 and 5.2177e-05 for the training and 14.639e-05 and 5.2177e-05 for the testing, respectively. Finally, the prediction accuracy of the ANFIS can be observed to be higher than that of the ANN, but the ANFIS takes longer to process. ANFIS is the method that can be appropriately applied to evaluate the power demand in this research. However, it could not guarantee for other research topics that ANFIS would be better than ANN for the RMSE. It depends on input and output data complexity and the training function type.
Some of the metrics are blocked by your
consent settings
Modeling Textural Properties of Cooked Germinated Brown Rice Using the near-Infrared Spectra of Whole Grain
(2023-12-01)
Kaewsorn, Kannapot
;
Phanomsophon, Thitima
;
Maichoon, Pisut
;
Pokhrel, Dharma Raj
;
Pornchaloempong, Pimpen
If a non-destructive and rapid technique to determine the textural properties of cooked germinated brown rice (GBR) was developed, it would hold immense potential for the enhancement of the quality control process in large-scale commercial rice production. We combined the Fourier transform near-infrared (NIR) spectral data of uncooked whole grain GBR with partial least squares (PLS) regression and an artificial neural network (ANN) for an evaluation of the textural properties of cooked germinated brown rice (GBR); in addition, data separation and spectral pretreatment methods were investigated. The ANN was outperformed in the evaluation of hardness by a back extrusion test of cooked GBR using the smoothing combined with the standard normal variate pretreated NIR spectra of 188 whole grain samples in the range of 4000–12,500 cm−1. The calibration sample set was separated from the prediction set by the Kennard–Stone method. The best ANN model for hardness, toughness, and adhesiveness provided R2, r2, RMSEC, RMSEP, Bias, and RPD values of 1.00, 0.94, 0.10 N, 0.77 N, 0.02 N, and 4.3; 1.00, 0.92, 1.40 Nmm, 9.98 Nmm, 1.6 Nmm, and 3.5; and 0.97, 0.91, 1.35 Nmm, 2.63 Nmm, −0.08 Nmm, and 3.4, respectively. The PLS regression of the 64-sample KDML GBR group and the 64-sample GBR group of various varieties provided the optimized models for the hardness of the former and the toughness of the latter. The hardness model was developed by using 5446.3–7506 and 4242.9–4605.4 cm−1, which included the amylose vibration band at 6834.0 cm−1, while the toughness model was from 6094.3 to 9403.8 cm−1 and included the 6834.0 and 8316.0 cm−1 vibration bands of amylose, which influenced the texture of the cooked rice. The PLS regression models for hardness and toughness had the r2 values of 0.85 and 0.82 and the RPDs of 2.9 and 2.4, respectively. The ANN model for the hardness, toughness, and adhesiveness of cooked GBR could be implemented for practical use in GBR production factories for product formulation and quality assurance and for further updating using more samples and several brands to obtain the robust models.
Some of the metrics are blocked by your
consent settings
Gold-Price Forecasting Method Using Long Short-Term Memory and the Association Rule
(2023-01-01)
Boongasame, Laor
;
Viriyaphol, Piboonlit
;
Tassanavipas, Kriangkrai
;
Temdee, Punnarumol
Since gold prices influence international economic and monetary systems, numerous studies have been conducted to forecast gold prices. Nonetheless, studies employing the linear relationship method usually fail to explain the change in the pattern of the gold price. This study introduces a new paradigm that incorporates association rules and long short-term memory (LSTM) as a nonlinear-based method. For simulation, the proposed method was analyzed with data from Yahoo Finance from January 2010 to December 2020. The association rule was used to choose features relevant to the gold spot (GS) in the US Dollar Index (DXY). The LSTM forecast the gold price with a range of hyperparameter settings. The simulation results showed that the proposed method—the LSTM with GS and DXY, or LSTM-GS-DXY—resulted in low mean absolute percentage error (MAPE) metrics. In addition, the proposed LSTM-GS-DXY system outperformed the simple moving average (SMA), weight moving average (WMA), exponential moving average (EMA), and auto-regressive integrated moving average (ARIMA).
Some of the metrics are blocked by your
consent settings
A Guided Tutorial on Modelling Human Event-Related Potentials with Recurrent Neural Networks
(2022-12-01)
O’Reilly, Jamie A.
;
Wehrman, Jordan
;
Sowman, Paul F.
In cognitive neuroscience research, computational models of event-related potentials (ERP) can provide a means of developing explanatory hypotheses for the observed waveforms. However, researchers trained in cognitive neurosciences may face technical challenges in implementing these models. This paper provides a tutorial on developing recurrent neural network (RNN) models of ERP waveforms in order to facilitate broader use of computational models in ERP research. To exemplify the RNN model usage, the P3 component evoked by target and non-target visual events, measured at channel Pz, is examined. Input representations of experimental events and corresponding ERP labels are used to optimize the RNN in a supervised learning paradigm. Linking one input representation with multiple ERP waveform labels, then optimizing the RNN to minimize mean-squared-error loss, causes the RNN output to approximate the grand-average ERP waveform. Behavior of the RNN can then be evaluated as a model of the computational principles underlying ERP generation. Aside from fitting such a model, the current tutorial will also demonstrate how to classify hidden units of the RNN by their temporal responses and characterize them using principal component analysis. Statistical hypothesis testing can also be applied to these data. This paper focuses on presenting the modelling approach and subsequent analysis of model outputs in a how-to format, using publicly available data and shared code. While relatively less emphasis is placed on specific interpretations of P3 response generation, the results initiate some interesting discussion points.
Some of the metrics are blocked by your
consent settings
Data-driven approach to solve vertical drain under time-dependent loading
(2021-06-01)
Nghia-Nguyen, Trong
;
Kikumoto, Mamoru
;
Khatir, Samir
;
Chaiyaput, Salisa
;
Nguyen-Xuan, H.
Currently, the vertical drain consolidation problem is solved by numerous analytical solutions, such as time-dependent solutions and linear or parabolic radial drainage in the smear zone, and no artificial intelligence (AI) approach has been applied. Thus, in this study, a new hybrid model based on deep neural networks (DNNs), particle swarm optimization (PSO), and genetic algorithms (GAs) is proposed to solve this problem. The DNN can effectively simulate any sophisticated equation, and the PSO and GA can optimize the selected DNN and improve the performance of the prediction model. In the present study, analytical solutions to vertical drains in the literature are incorporated into the DNN—PSO and DNN—GA prediction models with three different radial drainage patterns in the smear zone under time-dependent loading. The verification performed with analytical solutions and measurements from three full-scale embankment tests revealed promising applications of the proposed approach.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results