KMITL

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

Browse

Search Results

Now showing 1 - 10 of 17

Some of the metrics are blocked by your
consent settings
Short-term gains, long-term losses: exploring food waste practices of chefs in professional kitchens of casual dining restaurants through the lens of time discounting and habit formation
(2026-09-01)
Sinchai, Ananta
;
Koiwanit, Jarotwan
;
Chatmarathong, Awirut
;
Filimonau, Viachaslau
Food waste in professional kitchens is a significant challenge, but the cognitive and behavioural drivers of chefs' food waste practices remain under-explored. Drawing on the concept of time discounting and habit theory, this study investigates how chefs navigate immediate operational priorities of busy kitchens and how routinised food waste behaviour is formed and maintained. Semi-structured interviews with chefs in Thailand (n = 20) identify a pattern of short-term incentives i.e., speed, aesthetics, and perceived guest satisfaction, reinforcing food waste habits among chefs. Findings reveal that conventional, temporally distant interventions designed to encourage resourceful behaviour, such as monthly food cost reports, fail to disrupt habitual, present-biased wasteful behaviour. Theoretically, the study offers a novel conceptual framework for understanding food waste generation by chefs as a habit loop reinforced by time-discounted decision-making. Practically, it advocates for ‘present-focussed’ interventions, such as real-time feedback on leftover repurposing, to facilitate food waste reduction in professional kitchens.
Some of the metrics are blocked by your
consent settings
Low–cost IoT–enabled organic pH control system for smart aquaponic production in urban agriculture
(2026-02-15)
Sinchai, Ananta
;
Ardkaew, Chitsanucha
;
Jaiyen, Tontrakan
This study presents a smart aquaponic system integrating low–cost IoT monitoring, automated organic pH control using food–grade orange juice, and computer vision–based plant growth assessment to enhance sustainable urban lettuce production. Two experimental rounds compared uncontrolled pH conditions with active regulation across 15 plants per group, with sample size adequacy confirmed through power analysis for large observed effects. The system maintained optimal pH (5.8–7.0) through automated feedback control of orange juice within a defined range, producing 13–30 % higher growth rates, supported by t-tests, effect sizes, confidence intervals, and regression analysis. Performance and cost efficiency were assessed against established control strategies, showing competitive outcomes under resource–limited conditions. Economic evaluation indicated a payback period of 9–59 months depending on local market factors. Overall, results demonstrate the feasibility of combining natural pH buffers with IoT feedback to reduce chemical inputs, sustain growth improvements, and enable scalable adoption in small– to medium–scale aquaponics.
Some of the metrics are blocked by your
consent settings
Sustainable urban waste collection using a hybrid heuristic–genetic approach: a Bangkok case study
(2026-01-01)
Hamontree, Chaowalit
;
Koiwanit, Jarotwan
;
Sinchai, Ananta
Urban waste collection is a critical component of sustainable city development, directly influencing emissions reduction, resource efficiency, and public health. This study develops a hybrid optimization framework combining a Nearest Neighbor Heuristic with a Genetic Algorithm (GA) to optimize municipal waste collection routes in Bangkok, addressing the Vehicle Routing Problem (VRP) under real-world constraints such as vehicle capacity, time windows, and traffic conditions. The optimized algorithm reduced weekly travel distance by 8.51% and increased average vehicle utilization by 7.78%, translating into projected five-year economic benefits of over 4.7 million Baht and annual GHG emission reduction equivalent to planting approximately 1,750 trees. These findings demonstrate how algorithmic optimization can advance SDG 11 (sustainable cities and communities) and SDG 12 (responsible consumption and production) by aligning technical innovation with environmental and social outcomes. Beyond Bangkok, the framework is scalable to other rapidly urbanizing contexts, offering policymakers a data-driven pathway toward inclusive, low-carbon, and effective waste management systems.
Some of the metrics are blocked by your
consent settings
Correction: Sustainable urban waste collection using a hybrid heuristic–genetic approach: a Bangkok case study (Frontiers in Sustainability, (2026), 6, (1716538), 10.3389/frsus.2025.1716538)
(2026-01-01)
Hamontree, Chaowalit
;
Koiwanit, Jarotwan
;
Sinchai, Ananta
Waste Management An incorrect number was provided for School of Engineering, King Mongkut's Institute of Technology Ladkrabang. The correct number is 2565-02-01-074. The original version of this article has been updated.
Some of the metrics are blocked by your
consent settings
Time Series Forecasting Using Transfer Learning with an Attention-Revamped Transformer: A Case Study of Financial Instruments
(2025-12-01)
Feng, Ling
;
Sinchai, Ananta
Accurate financial time series forecasting is essential for informed investment and risk management decisions. Traditional methods, including statistical techniques such as SMA, ARIMA, VAR, and LASSO, and deep learning models like LSTM and Transformer, often fall short of capturing the complex seasonal and cyclical dynamics inherent in financial data. To overcome the noted shortcomings, this study introduces a transfer learning approach utilizing an enhanced Transformer model with correlation-based attention mechanisms. This proposed model significantly improves its capacity to capture long-term dependencies and perform robust cross-market predictions. Initially trained on the Dow Jones Index, it demonstrates superior transferability to diverse asset classes, including stock indices, commodities, and cryptocurrencies. Experimental evaluations across multiple metrics, including MSE, MAE, MHD, and R<sup>2</sup>, reveal that the proposed model consistently outperforms benchmarks. Notably, it achieves outstanding predictive accuracy in BTC (MSE: 0.0352) and SET (MSE: 0.1701), establishing a strong foundation for advanced transfer learning applications in financial forecasting across varied markets.
Some of the metrics are blocked by your
consent settings
Simplified Derivative-Based Carrierless PPM Using VCO and Monostable Multivibrator
(2025-06-01)
Koseeyaporn, Jeerasuda
;
Wardkein, Paramote
;
Sinchai, Ananta
;
Kaew-in, Chanapat
;
Tuwanut, Panwit
This study proposes a derivative-based, carrierless pulse position modulation (PPM) scheme utilizing a voltage-controlled oscillator (VCO) and a monostable multivibrator. In contrast to conventional PPM systems that rely on reference carriers or complex demodulation methods, the proposed architecture simplifies signal generation by directly modulating the time derivative of the message signal. The modulated signal, when processed through standard analog demodulators, inherently yields the derivative of the original message. This behavior is first established through theoretical derivations and then confirmed by simulations and circuit-level experiments. The proposed method includes a differentiator feeding into a VCO, followed by a monostable multivibrator to generate a carrierless PPM waveform. Experimental validation confirms that, under all tested demodulation approaches—integrator-based, PLL-based, and quasi-FM—the recovered output aligns with the differentiated message signal. The integration of this output to retrieve the original message was not performed to maintain focus on verifying the modulation principle. Additionally, the study aimed to ensure the consistency of derivative recovery. Signal-to-noise ratio (SNR) expressions for each demodulator type are presented and discussed in the context of their relevance to the proposed system. Limitations and directions for further study are also identified.
Some of the metrics are blocked by your
consent settings
Deep context-attentive transformer transfer learning for ﬁnancial forecasting
(2025-01-01)
Feng, Ling
;
Sinchai, Ananta
This study presents 2CAT (CNN-Correlation-based Attention Transformer), a deep learning model for financial time-series forecasting. The model integrates signal decomposition, convolutional layers, and correlation-based attention mechanisms to capture temporal patterns. A transfer learning framework is incorporated to enhance generalization across markets through pretraining, encoder freezing, and fine-tuning. Evaluation on six stock indices—Dow Jones Industrial Average (DJIA), Nikkei 225 (N225), Hang Seng Index (HSI), Shanghai Stock Exchange (SSE), Bombay Stock Exchange (BSE), and the Stock Exchange of Thailand (SET)—demonstrates strong predictive accuracy. On DJIA, 2CAT records an MSE of 0.0655, MAE of 0.2023, and R2 of 0.9169, outperforming Deep-Transformer, which yields an MSE of 0.1360 and R2 of 0.8274. The SET index, which posed challenges for previous models, demonstrates notable improvement with 2CAT, achieving an R2 of 0.9094. Wilcoxon signed-rank test confirms statistically significant gains in non-transfer learning scenarios at the 0.05 level. Transfer learning experiments reveal statistically significant improvements, reinforcing the feasibility of cross-market knowledge transfer. An ablation study highlights the impact of architectural refinements and rotary positional encoding, while prediction horizon analysis confirms stable forecasting performance. These results establish 2CAT as a robust financial forecasting framework adaptable to diverse market conditions.
Some of the metrics are blocked by your
consent settings
Development of a Low-Cost Automated Injection Molding Device for Sustainable Plastic Recycling and Circular Economy Applications
(2024-12-01)
Sinchai, Ananta
;
Boonyang, Kunthorn
;
Simmala, Thanakorn
In response to the critical demand for innovative solutions to tackle plastic pollution, this research presents a low-cost, fully automated plastic injection molding system designed to convert waste into sustainable products. Constructed entirely from repurposed materials, the apparatus focuses on processing high-density polyethylene (HDPE) efficiently without hydraulic components, thereby enhancing eco-friendliness and accessibility. Performance evaluations identified an optimal molding temperature of 200 °C, yielding consistent products with a minimal weight deviation of 4.17%. The key operational parameters included a motor speed of 525 RPM, a gear ratio of 1:30, and an inverter frequency of 105 Hz. Further tests showed that processing temperatures of 210 °C and 220 °C, with injection times of 15 to 35 s, yielded optimal surface finish and complete filling. The surface finish, assessed through image intensity variation, had a low coefficient of variation (≤5%), while computer vision evaluation confirmed the full filling of all specimens in this range. A laser-based overflow detection system has minimized material waste, proving effective in small-scale, community recycling. This study underscores the potential of low-cost automated systems to advance the practices of circular economies and enhance localized plastic waste management. Future research will focus on automation, temperature precision, material adaptability, and emissions management.
Some of the metrics are blocked by your
consent settings
Transfer learning model for cash-instrument prediction adopting a Transformer derivative
(2024-03-01)
Feng, Ling
;
Sinchai, Ananta
Investors aiming for high market returns must accurately predict the prices of various cash instruments. However, making accurate predictions is challenging due to the complex cyclic and trending characteristic of markets, characterized by high volatility and unpredictable fluctuations. Furthermore, many studies overlook how interactions between different markets affect price movements. To address these problems, this research introduces a deep transfer-learning approach derived from the Transformer model, named the rotary-positional encoding autocorrelation Transformer (RAT). Unlike traditional methods, the RAT employs autocorrelation instead of self-attention to more effectively capture periodic features, while rotary-positional encoding preserves both the absolute and relative positioning within sequences to enhance trend understanding. Through transfer learning, the RAT model extracts deep features from a source domain and applies them to a target domain, demonstrating superior performance over LSTM, CNN-LSTM, gated recurrent units (GRUs), and Transformer models in multi-day predictions across 12 cash-instrument datasets. It achieved a substantial increase in accuracy, with a 35.83% reduction in mean squared error (MSE), a 23.95% reduction in mean absolute error (MAE), and a 32.63% increase in the coefficient of determination (R2). This study validates the RAT model's effectiveness in predicting financial instrument prices.
Some of the metrics are blocked by your
consent settings
Enhanced Fire Detection Using Deep Learning and Heat Signatures
(2024-01-01)
Sinchai, Ananta
;
Pumanee, Ploychattra
;
Lomwong, Rattaphum
This study presents an innovative fire alarm system that integrates deep learning with thermal camera technology to tackle the urgent problem of slow fire detection, which often leads to considerable harm to individuals and extensive property damage. The system excels in identifying heat signatures prior to the full development of a fire, enabling timely notifications and thus mitigating potential damages and risks associated with fire incidents. Compared to traditional smoke detectors, this system operates at a considerably faster pace and offers a more flexible installation process by leveraging thermal cameras, which eliminates the need for ceiling-mounted detectors. Experimental evaluations demonstrate the efficacy of the proposed system, achieving up to 97% accuracy in fire detection. Simulations of various fire scenarios, ranging from initial heat detection to severe fire conditions, were used to train the system using a deep learning platform and a model of you only look once version 4 tiny (YOLOv4-Tiny). The results underscore the system's capability to detect early heat buildup swiftly, facilitating prompt alerts and enhancing overall fire safety.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results