KMITL

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

Browse

Search Results

Now showing 1 - 10 of 7986

Some of the metrics are blocked by your
consent settings
A Comparative Study of Deep Reinforcement Learning Agents for Gold Trading with Technical Indicators and LLM-Filtered News Sentiment
(2026-06-16)
Thanasarn, Thanapong
;
Anuntachai, Anuntapat
;
Netisopakul, Ponrudee
Integrating macroeconomic news into deep reinforcement learning (DRL) for daily gold (XAU/USD) trading remains challenging. This study implements a natural language processing pipeline using majority voting from three large language models (Llama-3.1-8B-Instruct, Qwen3-8B, and Gemma-3-12B-it) to filter articles from The New York Times from 2010 to 2024, yielding 592 relevant articles that are subsequently assigned sentiment scores using FinBERT. We evaluate A2C, PPO, and SAC agents in a FinRL and Stable-Baselines3 framework using a four-fold walk-forward expanding-window protocol and Optuna hyperparameter tuning. The models are compared under two feature settings: (1) six technical indicators only and (2) technical indicators combined with sentiment features. Results show that incorporating LLM-filtered sentiment can modestly improve trading performance for some agents. PPO with sentiment achieves the best average cumulative return (10.05%) and Sharpe ratio (0.74), compared with its indicator-only version (9.80%, 0.72), and slightly outperforms the Buy-and-Hold (B&H) baseline (9.58%, 0.71). A2C also improves with sentiment (9.50% to 9.90%), while SAC shows no improvement in this setting. These findings suggest that LLM-filtered sentiment provides a modest benefit for some DRL agents in daily gold trading in our experiments.
Some of the metrics are blocked by your
consent settings
YOLO Based IoT Tracking for Academic Labs on Raspberry Pi
(2026-06-16)
Jiamrachada, Tamakorn
;
Nonsiri, Sarayut
;
Kamin, Pichitchai
;
Nanthajirapong, Nathaphon
Academic IoT laboratories often rely on shared equipment, making efficient borrow-return management essential. Conventional management methods depend on manual recording, which can cause verification delays, data entry errors, and increased staff workload. This study proposes a YOLO based IoT equipment tracking system that uses a camera to detect and count devices inside student equipment boxes for borrow-return recording and inventory monitoring. The system runs on a Raspberry Pi 5 for real-time edge-based processing, while detection results are stored in a database and displayed through a web-based dashboard. Experimental results show that the YOLO12n model achieved an F1-score of 0.996 with a real-time inference speed of 12.01 FPS, demonstrating the system's effectiveness in reducing human error and improving laboratory inventory management efficiency.
Some of the metrics are blocked by your
consent settings
Personalized Health Insurance Recommendation with Retrieval-Augmented Generation: A Study of Lexical, Dense, and Hybrid Retrieval
(2026-06-16)
Rujireksareekul, Phakon
;
Anuntachai, Anuntapat
;
Netisopakul, Ponrudee
Health insurance information in Thailand is available on many company websites and is presented in different formats, making it difficult for users to compare coverage, conditions, and benefits. In this study, we propose a personalized health insurance recommendation system using Retrieval-Augmented Generation (RAG). The system retrieves information using three methods: BM25, dense retrieval, and hybrid retrieval with Reciprocal Rank Fusion. The language model analyzes the retrieved insurance plans and recommends suitable options based on the user query. Experimental results show that dense retrieval provides the best overall performance, while hybrid retrieval performs better than lexical search. The proposed RAG system also maintains practical response latency, making it suitable for interactive applications.
Some of the metrics are blocked by your
consent settings
Machine Learning Models for Multi-Horizon Classification of Bitcoin Future Price Movements
(2026-06-16)
Boonpai, Sirawat
;
Netisopakul, Ponrudee
;
Anuntachai, Anuntapat
This study presents a comprehensive framework for multi-horizon classification of Bitcoin futures price movements using machine learning. Five models of Logistic Regression, Random Forest, XGBoost, LightGBM, and CatBoost were systematically evaluated across three timeframes (4h, 12h, 1d) and four classification schemes: binary (up/down) and multi-class (up/down/stable) with thresholds of 0.5%, 1.0%, and 1.5%, totaling 60 distinct experimental configurations. Rather than pursuing a strong predictive performance, this study prioritizes a rigorous comparative analysis across multiple dimensions to identify which combinations of model, timeframe, and classification scheme are most effective for Bitcoin futures. The results demonstrate that binary classification achieves the best predictive performance, with shorter timeframes yielding significantly better results, confirming the effectiveness of technical indicators in capturing the rapid price dynamics of Bitcoin futures. Notably, CatBoost achieved the highest F1-score for binary classification, while Random Forest proved the most robust model across diverse configurations. Feature importance analysis revealed that momentum-based indicators are the dominant predictors of price direction, while volatility features play a critical role in distinguishing sideways movements from directional ones in multi-class settings. Furthermore, the study demonstrates that narrower classification thresholds (0.5%) introduce noisier class boundaries and degrade performance, whereas wider thresholds (1.0%-1.5%) yield more stable results. These findings provide actionable guidelines for algorithmic trading in Bitcoin futures and establish a reproducible benchmark for future research.
Some of the metrics are blocked by your
consent settings
A Persona-based Automated Evaluation Framework for Intelligent AI Teaching Assistants
(2026-06-16)
Limcharoen, Chananyu
;
Sripinta, Keetaphat
;
Pasupa, Kitsuchart
To address global teacher shortages and the need for personalized learning, we develop an intelligent teaching assistant leveraging multimodal large language models, agentic retrieval-augmented generation, and function calling. Unlike standard models, our system provides verifiable pedagogical guidance by reasoning across heterogeneous resources, including lecture slides and instructional videos. To overcome the scarcity of real-world datasets and high human evaluation costs, we propose a scalable, human-annotation-free framework utilizing simulated learner agents grounded in the Big Five personality theory. This allows for systematic assessment across 18 distinct student personas. We introduce a novel process-level metric, the dialogue recovery rate, and a dynamic adaptive policy to mitigate conversational deadlocks. Experimental results across 1,800 simulated dialogues using the Qwen3 family (8B, 14B, 32B) and its Thai-variant (Typhoon 2.5) reveal that Qwen3-14B attains the highest robustness and aggregate tutor-performance score within the proposed framework (72.6%). Analysis demonstrates significant correlations between learner traits and performance: Conscientiousness positively correlates with success (r = 0.49), while Extraversion is negatively associated with structural adherence (r = -0.54). This work establishes a reproducible benchmarking protocol for persona-aware, adaptive intelligent tutoring systems.
Some of the metrics are blocked by your
consent settings
Stock Price Prediction from Multi Data Sources Using LSTM, FinBERT and BERTweet
(2026-06-16)
Auensupa, Suchart
;
Netisopakul, Ponrudee
;
Chotipant, Supannada
This research presents a stock price forecasting approach for technology sector companies Apple, Amazon and Tesla. The study begins by comparing a statistical model (ARIMA) with a deep learning model (LSTM) to identify the best-performing model, which is then used as the baseline for stock price forecasting. The approach integrates data from multiple sources, including numerical time series data and textual data. Numerical inputs consist of open, high, and low prices, which are used to forecast the closing price. Technical indicator features are subsequently added to enhance the model's predictive capability. Finally, textual data from economic news and Twitter social media reflecting market sentiment are incorporated. News sentiment is analyzed using the FinBERT model, while sentiment from social media data is evaluated using the BERTweet model. The resulting sentiment features are then combined with the numerical data and all inputs are processed using the LSTM model. Experimental results show that incorporating technical indicator features improves forecasting accuracy by an average of 17%. Furthermore, integrating textual data from news improves accuracy by an additional 6%, resulting in an overall performance improvement of up to 23%. These findings demonstrate the value of integrating multi-source data and highlight the important role of textual information in enhancing stock price forecasting performance.
Some of the metrics are blocked by your
consent settings
Virtue-Based Thai Folktale Recommendation with Ensemble LLMs
(2026-06-16)
Daeng-Am, Wassana
;
Anuntachai, Anuntapat
;
Netisopakul, Ponrudee
Moral learning plays an important role in early childhood education, yet teachers often spend considerable time identifying moral lessons in stories and deciding which virtues they represent. This study investigates whether a multi-model ensemble strategy can produce more teacher-aligned moral extractions from Thai folktales than a single-LLM baseline. We propose an LLM-based ensemble framework that extracts concise moral statements and classifies them into eight core virtues promoted by the Thai Ministry of Education: diligence, frugality, honesty, discipline, politeness, cleanliness, unity, and kindness. The framework combines outputs from Google Gemini 2.0 Flash, OpenAI GPT-4o-mini, and Anthropic Claude 3.5 Sonnet through a semantic consensus mechanism using BGE-M3 embeddings and majority voting. The system is evaluated on a corpus of 200 Thai folktales annotated by three experienced early childhood educators using multi-label metrics including Hamming Loss, Jaccard Similarity, and Exact Match. The results show that the ensemble approach achieves a Hamming Loss of 0.208, Jaccard Similarity of 0.564, and Exact Match of 0.175, consistently outperforming all single-model baselines. These findings suggest that consensus-driven ensemble inference provides a more robust and teacher-aligned foundation for automated moral education tools in Thai NLP.
Some of the metrics are blocked by your
consent settings
Phytochemical analysis of Melaleuca cajuputi Powell leaves for the development of herbal tea
(2026-06-01)
Montri, N.
;
Chalornsiri, S.
;
Pato, N.
;
Kueasakun, N.
;
Deewatthanawong, R.
The plant Melaleuca cajuputi Powell, commonly known as cajuput, is found in coastal swamp forests in Thailand. Traditional knowledge suggests using cajuput tea, derived from its leaves, for treating peptic ulcers. The research was conducted to evaluate the chemical composition of the dried leaves from different stages of leaf age and drying methods. The young, immature, and mature leaves were picked from the tree. Leaves were cleaned and dried in a hot air oven at 40, 45, and 50°C. The tea extracts were then analyzed for acid concentration and phenolic content. The study revealed that drying young leaves using varying acid concentrations significantly affected leaf age; however, the drying methods did not exhibit a notable effect. The highest levels of citric acid, malic acid, and tartaric acid were observed in young leaves. Hot air oven at 40°C resulted in the highest total phenolic content at 137.55mg GAE g<sup>-1</sup> DW.
Some of the metrics are blocked by your
consent settings
Implementing short-term anoxic conditions as a straightforward and effective postharvest technique to preserve the quality of ‘Sucrier’ bananas
(2026-06-01)
Techavuthiporn, C.
;
Sittiprasert, W.
;
Phakawan, J.
;
Supapvanich, S.
The aim of this study was to examine the impact of an oxygen limitation, so-called anoxic conditions, on the ripening process and the physicochemical characteristics of ‘Sucrier’ bananas during storage. A preliminary experiment was conducted to determine the optimal duration of anoxia treatment, ranging from 0 to 20 h. The experiment determined that subjecting the fruit to anoxic conditions for 16 h resulted in the most successful treatment for delaying the development of fruit skin color at room temperature for a period of 8 days. Furthermore, the reduction in moisture content of the peel and the increase in weight loss, pulp-to-peel ratio, and moisture content of the pulp exhibited a notable disparity compared to the other treatments. Therefore, the duration of 16 h of anoxic conditions was chosen to further examine the responses of fruit after storage for 18 d at 15°C, in comparison to the control fruit, which had no exposure to anoxic conditions. Bananas treated with anoxia exhibited a decrease in the developed peel color, as indicated by decreased Δa* and ΔH values. The treatment also demonstrated greater fruit firmness in comparison to the untreated fruit. In addition, the peel of treated bananas exhibited a greater relative value of firmness, whereas the relative values of electrolyte leakage, malondialdehyde, and H2O2 were lower. This is likely caused by the application of anoxia treatment, which might stimulate the activity of DPPH scavenging.
Some of the metrics are blocked by your
consent settings
Efficacy of preharvest salicylic acid treatment on postharvest quality enhancement of Marian plums (Bouea oppositifolia (Roxb.) Meisn.)
(2026-06-01)
Supapvanich, S.
;
Da, L.
;
Phakawan, J.
;
Techavuthiporn, C.
Marian plum (Bouea oppositifolia (Roxb.) Meisn.) is a tropical fruit tree that holds significant commercial importance in Southeast Asia. Softening and disease incidence are the main problems limiting the postharvest quality of the fruits. The purpose of this study was to determine the efficacy of preharvest salicylic acid (SA) spray on fruit quality maintenance during storage at room temperature (25±1°C). The fruits were preharvest sprayed with SA at concentrations of 0 (water), 1, 2, and 3 mM prior to harvest for 3 days. The finding showed that 3 mM SA evidently delayed the progression of fruit coloration from the time of harvest to the end of storage (day 8) in comparison to the control treatment. During storage, disease incidence in the 3 mM SA-treated fruits was not found in comparison to other treatments. All SA treatments reduced the magnitude of the weight loss increase. The 3 mM SA treatment delayed fruit softening, lipid membrane degradation, and an increase in total soluble solids, while maintaining a high level of total acidity. In addition, the application of 3 mM SA significantly increased the ferric reducing antioxidant potential, and all SA treatments effectively maintained free radical scavenging activity compared to the control treatment. In conclusion, preharvest SA spray at 3 mM prior to harvest is an effective approach to maintaining the postharvest quality of marian plums during storage.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results