KMITL

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

Browse

Search Results

Now showing 1 - 10 of 34

Some of the metrics are blocked by your
consent settings
Frame-Level Accident Recognition via Detection Confidence Aggregation: A Cross-Domain Validation Framework for Thai Roadway Surveillance
(2026-07-01)
Gabbualoy, Somprasonk
;
Phasukkit, Pattarapong
;
Houngkamhang, Nongluck
Real-time roadway surveillance now leans hard on automated detection. How a model trained in one geographic context actually behaves on another, though, is still underexplored for Southeast Asian deployments. We answer that question for Thai roadway closed-circuit television with a cross-domain validation framework. A YOLOv11n (Ultralytics v8.2.0; Ultralytics, Los Angeles, CA, USA) detector trained with focal loss feeds a confidence-aggregation step that turns per-detection scores into a per-frame accident score, and we put four aggregation operators head-to-head. Reliability comes from DeLong variance estimation paired with non-parametric bootstrap on 1245 Thai frames that carry 23 positive accident events. Under maximum-class aggregation the proposed configuration reaches a frame-level AUROC of 0.959 ± 0.020 across three random seeds. Under top-K aggregation it reaches 0.965 ± 0.018. Per-seed DeLong 95 percent intervals exclude chance performance throughout. We also evaluate three baseline configurations: YOLOv5su comes in at 0.738, YOLOv8n at 0.868, and a Chiang Mai-tuned YOLOv11n variant at 0.918. The architectural progression seen on standard benchmarks therefore carries cleanly into the cross-domain setting. The same Chiang Mai-tuned variant reached an in-domain mAP50 of 0.952 yet only 0.918 cross-region AUROC on a separate Thai region, which is a quiet but clear signal that geographic proximity within a country does not on its own remove distributional shift. Bounding-box localisation appears as a secondary diagnostic because the operational target here is frame-level alerting rather than pixel-precise annotation. Edge deployment optimisation falls outside the present scope. What the work leaves behind is a reproducible baseline and a statistical protocol that follow-up Southeast Asian roadway-safety research can build on.
Some of the metrics are blocked by your
consent settings
A Contactless Edge-AI Prototype for Simulated Apnea-like Respiratory Suppression and Motion Artifact Detection Using 60 GHz FMCW Radar
(2026-07-01)
Pairoch, Sathit
;
Phasukkit, Pattarapong
;
Houngkamhang, Nongluck
Sleep-related respiratory disturbances are difficult to monitor continuously outside specialized laboratories because conventional polysomnography is resource-intensive and intrusive. This study presents a contactless edge-AI engineering prototype for detecting controlled voluntary respiratory-motion suppression and motion artifacts using a 60 GHz frequency-modulated continuous-wave radar. The system integrates a 60 GHz radar front end, lightweight local preprocessing, an INT8 one-dimensional convolutional neural network deployed on the Analog Devices MAX78000 CNN accelerator (Analog Devices Thailand, Chon Buri, Thailand), and an event-driven Raspberry Pi Zero 2W gateway for alert transmission. Evaluation was performed using a controlled healthy-volunteer dataset consisting of normal breathing, voluntary breath-holding-induced respiratory suppression, and deliberate motion artifact. The final valid test set contained 270 technically valid 30 s windows balanced across the three classes. The INT8 model achieved an overall accuracy of 92.6% (95% confidence interval: 88.8–95.2%), with a macro-averaged precision, recall, and F1-score of 92.6%, 92.6%, and 92.5%, respectively. Active CNN inference on the MAX78000 consumed 0.152 ± 0.011 mJ and was completed in 5.20 ± 0.11 ms, corresponding to approximately 280-fold lower active inference energy than Python 3.14.6/TensorFlow Lite 2.21.0-based execution on the Raspberry Pi Zero 2W. These results demonstrate the feasibility of privacy-aware, low-power respiratory-pattern classification at the edge. However, the study should be interpreted strictly as an engineering proof-of-concept based on controlled voluntary breathing and movement tasks in healthy volunteers. It is not a clinically validated apnea or obstructive sleep apnea detection system and did not include polysomnography, oxygen saturation measurement, airflow sensing, sleep staging, or diagnosed patient cohorts.
Some of the metrics are blocked by your
consent settings
Multi-Entropy Feature Extraction With LSTM Networks for Acoustic Emission-Based Railway Crack Localization
(2026-01-01)
Laon, Popphon
;
Pourbunthidkul, Supavee
;
Rattan, Praphaporn
;
Sahavisit, Tanawit
;
Suwansin, Wara
Railway infrastructure security is contingent upon the prompt identification of structural anomalies within steel tracks. This research establishes a framework that merges acoustic emission (AE) sensing with advanced machine learning for prompt fracture identification and location. To improve the quality of Raw AE signals, they are first cleaned using Kalman filtering to tackle environmental disturbances and ambiguous readings. The characteristics that arise from entropy comprising approximate entropy, Shannon entropy, and dimensional entropy are derived to delineate the temporal patterns of fracture-induced emissions. Density-based spatial clustering of applications with noise (DBSCAN) is applied to remove outliers during preprocessing. Long short-term memory (LSTM) networks classify crack locations into three anatomical regions: rail head, web, and foot. Experimental validation with 3,000 labeled AE signals (1,000 per class) under laboratory conditions, the full pipeline that integrates Kalman filtering, entropy features, DBSCAN, and an LSTM classifier attains an accuracy of 98.83%. With an entropy-based variant, the accuracy drops to 96.67%, confirming the incremental value of temporal denoising and outlier rejection. While using mel-frequency cepstral coefficient (MFCC) baseline achieves 97.67% accuracy, a deep neural network (DNN) trained on Kalman-filtered, entropy-based, and DBSCAN-processed inputs reaches 96.33% accuracy, underscoring the advantages of temporal modeling for AE. A GRU using the same Kalman-filtered, entropy-based, and DBSCAN-processed inputs, achieves 97.67% accuracy, but trails the LSTM overall. When deployed on actual railway lines with a mobile inspection platform, the system maintained robust performance, correctly identifying 84.67% of cracks at 3 km/h and 80.67% at 5 km/h. The LSTM configuration consistently outperformed all alternative approaches, including the entropy-only variant, MFCC-based method, DNN classifier, and GRU model. This confirms the LSTM’s enhanced capability to capture the temporal dynamics of AE signals, establishing it as the most effective framework for AE-based crack localization in railway structural health monitoring.
Some of the metrics are blocked by your
consent settings
Hybrid Unsupervised–Supervised Learning Framework for Rainfall Prediction Using Satellite Signal Strength Attenuation
(2026-01-01)
Laon, Popphon
;
Sahavisit, Tanawit
;
Pourbunthidkul, Supavee
;
Puangragsa, Sarut
;
Wichittrakarn, Pattharin
Satellite communication systems experience significant signal degradation during rain events, a phenomenon that can be leveraged for meteorological applications. This study introduces a novel hybrid machine learning framework combining unsupervised clustering with cluster-specific supervised deep learning models to transform satellite signal attenuation into a predictive tool for rainfall prediction. Unlike conventional single-model approaches treating all atmospheric conditions uniformly, our methodology employs K-Means Clustering with the Elbow Method to identify four distinct atmospheric regimes based on Signal-to-Noise Ratio (SNR) patterns from a 12-m Ku-band satellite ground station at King Mongkut’s Institute of Technology Ladkrabang (KMITL), Bangkok, Thailand, combined with absolute pressure and hourly rainfall measurements. The dataset comprises 98,483 observations collected with 30-s temporal resolutions, providing comprehensive coverage of diverse tropical atmospheric conditions. The experimental platform integrates three subsystems: a receiver chain featuring a Low-Noise Block (LNB) converter and Software-Defined Radio (SDR) platform for real-time data acquisition; a control system with two-axis motorized pointing incorporating dual-encoder feedback; and a preprocessing workflow implementing data cleaning, K-Means Clustering (k = 4), Synthetic Minority Over-Sampling Technique (SMOTE) for balanced representation, and standardization. Specialized Long Short-Term Memory (LSTM) networks trained for each identified cluster enable capture of regime-specific temporal dynamics. Experimental validation demonstrates substantial performance improvements, with cluster-specific LSTM models achieving R2 values exceeding 0.92 across all atmospheric regimes. Comparative analysis confirms LSTM superiority over RNN and GRU. Classification performance evaluation reveals exceptional detection capabilities with Probability of Detection ranging from 0.75 to 0.99 and False Alarm Ratios below 0.23. This work presents a scalable approach to weather radar systems for tropical regions with limited ground-based infrastructure, particularly during rapid meteorological transitions characteristic of tropical climates.
Some of the metrics are blocked by your
consent settings
Reinforcement Learning-Driven Framework for High-Precision Target Tracking in Radio Astronomy
(2025-12-01)
Sahavisit, Tanawit
;
Laon, Popphon
;
Pourbunthidkul, Supavee
;
Wichittrakarn, Pattharin
;
Phasukkit, Pattarapong
Radio astronomy requires precise target localization and tracking to ensure accurate observations. Conventional regulation methodologies, encompassing PID controllers, frequently encounter difficulties due to orientation inaccuracies precipitated by mechanical limitations, environmental fluctuations, and electromagnetic interferences. To tackle these obstacles, this investigation presents a reinforcement learning (RL)-oriented framework for high-accuracy monitoring in radio telescopes. The suggested system amalgamates a localization control module, a receiver, and an RL tracking agent that functions in scanning and tracking stages. The agent optimizes its policy by maximizing the signal-to-noise ratio (SNR), a critical factor in astronomical measurements. The framework employs a reconditioned 12-m radio telescope at King Mongkut’s Institute of Technology Ladkrabang (KMITL), originally constructed as a satellite earth station antenna for telecommunications and was subsequently refurbished and adapted for radio astronomy research. It incorporates dual-axis servo regulation and high-definition encoders. Real-time SNR data and streaming are supported by a HamGeek ZedBoard with an AD9361 software-defined radio (SDR). The RL agent leverages the Proximal Policy Optimization (PPO) algorithm with a self-attention actor–critic model, while hyperparameters are tuned via Optuna. Experimental results indicate strong performance, successfully maintaining stable tracking of randomly moving, non-patterned targets for over 4 continuous hours without any external tracking assistance, while achieving an SNR improvement of up to 23.5% compared with programmed TLE-based tracking during live satellite experiments with Thaicom-4. The simplicity of the framework, combined with its adaptability and ability to learn directly from environmental feedback, highlights its suitability for next-generation astronomical techniques in radio telescope surveys, radio line observations, and time-domain astronomy. These findings underscore RL’s potential to enhance telescope tracking accuracy and scalability while reducing control system complexity for dynamic astronomical applications.
Some of the metrics are blocked by your
consent settings
An Enhanced Cascaded Deep Learning Framework for Multi-Cell Voltage Forecasting and State of Charge Estimation in Electric Vehicle Batteries Using LSTM Networks
(2025-06-01)
Pourbunthidkul, Supavee
;
Pahaisuk, Narawit
;
Laon, Popphon
;
Houngkamhang, Nongluck
;
Phasukkit, Pattarapong
Enhanced Battery Management Systems (BMS) are essential for improving operational efficacy and safety within Electric Vehicles (EVs), especially in tropical climates where traditional systems encounter considerable performance constraints. This research introduces a novel two-tiered deep learning framework that utilizes a two-stage Long Short-Term Memory (LSTM) framework for precise prediction of battery voltage and SoC. The first tier employs LSTM-1 forecasts individual cell voltages across a full-scale 120-cell Lithium Iron Phosphate (LFP) battery pack using multivariate time-series data, including voltage history, vehicle speed, current, temperature, and load metrics, derived from dynamometer testing. Experiments simulate real-world urban driving, with speeds from 6 km/h to 40 km/h and load variations of 0, 10, and 20%. The second tier uses LSTM-2 for SoC estimation, designed to handle temperature-dependent voltage fluctuations in high-temperature environments. This cascade design allows the system to capture complex temporal and inter-cell dependencies, making it especially effective under high-temperature and variable-load environments. Empirical validation demonstrates a 15% improvement in SoC estimation accuracy over traditional methods under real-world driving conditions. This study marks the first deep learning-based BMS optimization validated in tropical climates, setting a new benchmark for EV battery management in similar regions. The framework’s performance enhances EV reliability, supporting the growing electric mobility sector.
Some of the metrics are blocked by your
consent settings
Metamaterial Microwave Sensor for Glucose Level Measurement Based on Strip Line with Complementary Split Ring Resonator
(2025-06-01)
Rattan, Praphaporn
;
Houngkamhang, Nongluck
;
Orankitanun, Teerapong
;
Phasukkit, Pattarapong
This research focuses on investigating glucose meters utilizing metamaterial microwave sensors. The metamaterial microwave sensor is designed with a strip line loaded with a complementary split ring. The sensor is designed to conduct Ansys high-frequency structure simulator and uses conductor material coated on a hydrocarbon ceramic laminate (Roger RO4232) substrate, with a sweep frequency range of 1–6 GHz. The signal of the metamaterial microwave sensor depends on the change in glucose permittivity and conductivity when the glucose concentration changes. The research involves designing a simulation model to explore the impact of complementary split ring size on the sensor's response to changes in glucose permittivity. Additionally, experiments are conducted using the proposed sensor to measure glucose concentration in solution, aiming to analyze trends in sensor response to varying concentrations of glucose and evaluate its sensitivity to changes in glucose concentration. The experimental results indicate that the metamaterial microwave sensor is able to respond to variations in glucose level, a sensitivity of the proposed sensor is 0.0345 dB (mg dL−1)−1 in range of 0–110 mg dL−1 with R2 0.9628.
Some of the metrics are blocked by your
consent settings
Intelligent Battery Management System for Electric Vehicles: AI-Driven Voltage Cell Prediction Using GRU and K-Means Clustering
(2025-01-01)
Pahaisuk, Narawit
;
Pourbunthidkul, Supavee
;
Phasukkit, Pattarapong
;
Houngkamhang, Nongluck
The advancement of Electric Vehicles (EVs) requires intelligent Battery Management Systems (BMS) for accurate voltage prediction, ensuring battery reliability, longevity, and efficiency. Traditional BMS architectures rely on rule-based monitoring, which lacks predictive capabilities for early fault detection and proactive maintenance. This study presents an AI-driven BMS framework, integrating K-Means clustering and Gated Recurrent Unit (GRU) networks to enhance real-time voltage forecasting. Unlike conventional approaches that focus solely on clustering or deep learning, this research combines both methodologies to create a robust predictive system. K-Means clustering segments battery voltage data into operational groups, improving predictive accuracy by organizing similar voltage behaviors. GRU networks then capture sequential voltage dependencies, enabling precise voltage fluctuation predictions. Experimental validation was conducted using voltage data from 120 lithium-ion battery cells, recorded at 20 km/h under three load conditions (Load 0, Load 10, and Load 20) over a 5-minute duration. The findings demonstrate that K-Means clustering effectively categorizes battery voltage states, while GRU-based forecasting achieves high accuracy, reinforcing the practicality of AI-powered predictive maintenance. This study advances AI-driven BMS frameworks by demonstrating the integration of clustering and deep learning for voltage prediction, providing a foundation for real-time battery diagnostics and predictive analytics.
Some of the metrics are blocked by your
consent settings
Fabrication of Al/Au hybrid SERS substrate using laser engraving for rapid detection of melamine and its analogues by hand-held Raman spectrometer
(2024-05-01)
Wongwasuratthakul, Puwasit
;
Aumpalop, Weerada
;
Chakaja, Chaiwat
;
Satapornchai, Pemika
;
Eiamsamut, Ploypailin
Surface-enhanced Raman spectroscopy (SERS), combined with a handheld Raman spectrometer, was utilized for the rapid and highly sensitive detection of melamine and its analogues. The investigation focused on the hybrid micro-nano structures of SERS-active substrates, fabricated by laser engraving aluminum (Al) sheets and depositing gold (Au) nanoparticles using magnetron sputtering. The laser engraving frequency was varied to get optimum SERS substrate. The fabricated SERS substrates were tested with rhodamine 6G (R6G) to optimize the Raman signal and subsequently detect melamine and its analogues viz., cyanuric acid, ammeline, ammelide in milk samples. The results demonstrated that a laser frequency of 20 kHz was the optimal condition for fabricating a micro-nano Al template with a depth of 61.21 μm, providing the highest Raman signal for R6G. The limit of detection (LOD) for melamine in mild acid solution and milk samples were determined to be 1x10-5 M and 1x10-4 M, respectively. The laser-engraved Al sheet technique offers a cost-effective approach for SERS substrate fabrication. The integration of the Al/Au hybrid SERS substrate with a hand-held Raman spectrometer demonstrates significant potential for detecting melamine and its analogues in realistic environments.
Some of the metrics are blocked by your
consent settings
Label free detection of multiple trace antibiotics with SERS substrates and independent components analysis
(2023-07-05)
Limwichean, Saksorn
;
Leung, Wipawanee
;
Sataporncha, Pemika
;
Houngkamhang, Nongluck
;
Nimittrakoolchai, On Uma
Surface enhanced Raman spectroscopy (SERS) has been widely studied and recognized as a powerful label-free technique for trace chemical analysis. However, its drawback in simultaneously identifying several molecular species has greatly limited its real-world applications. In this work, we reported a combination between SERS and independent component analysis (ICA) to detect several trace antibiotics which are commonly used in aquacultures, including malachite green, furazolidone, furaltadone hydrochloride, nitrofurantoin, and nitrofurazone. The analysis results indicate that the ICA method is highly effective in decomposing the measured SERS spectra. The target antibiotics could be precisely identified when the number of components and the sign of each independent component loading were properly optimized. With SERS substrates, the optimized ICA can identify trace molecules in a mixture at a concentration of 10−6 M achieving the correlation values to the reference molecular spectra of 71–98%. Furthermore, measurement results obtained from a real-world sample demonstration could also be recognized as an important basis to suggest this method is promising for monitoring antibiotics in a real aquatic environment.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results