Phasukkit, Pattarapong
Loading...
Preferred name
Phasukkit, Pattarapong
Alternative Name
Phasukkit, P.
Main Affiliation
Email
pattarapong.ph@kmitl.ac.th
12 results
Now showing 1 - 10 of 12
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, Multi-Entropy Feature Extraction With LSTM Networks for Acoustic Emission-Based Railway Crack Localization(2026-01-01) - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Feasibility of Prediction Model for Internal Tumor Target Volume from 4-D Computed Tomography of Lung cancer(2021-01-01); - Some of the metrics are blocked by yourconsent settings
Item type:Publication, A Contactless Edge-AI Prototype for Simulated Apnea-like Respiratory Suppression and Motion Artifact Detection Using 60 GHz FMCW Radar(2026-07-01); 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 yourconsent settings
Item type:Publication, Frame-Level Accident Recognition via Detection Confidence Aggregation: A Cross-Domain Validation Framework for Thai Roadway Surveillance(2026-07-01); 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 yourconsent settings
Item type:Publication, Breast Cancer Detection using IR-UWB with Deep Learning(2021-01-01); This paper proposes breast cancer positioning detection using the IR-UWB system with deep learning, which is an interesting alternative method. When compared to ultrasound, x-ray mammogram, and CT-scan, there are several advantages to using IR-UWB, including low cost, less energy required, less long-term effect, portability, and providing much more breast cancer screening access for patients. Nowadays, the IR-UWB system has many techniques for processing IR-UWB signals, and one of the most interesting technique is using deep learning. In this study, we collected data from nine IR-UWB antennas. Then, the prepared data is fed through Deep Neural Networks to find the hidden patterns of signal and predict the cancer position which are 16 of breast cancer positions and one of undetected, also known as 17 classes. The model gave an average accuracy up to 95.60%. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Intelligent Battery Management System for Electric Vehicles: AI-Driven Voltage Cell Prediction Using GRU and K-Means Clustering(2025-01-01); 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 yourconsent settings
Item type:Publication, 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); 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 yourconsent settings
Item type:Publication, Hybrid Unsupervised–Supervised Learning Framework for Rainfall Prediction Using Satellite Signal Strength Attenuation(2026-01-01) - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Metamaterial Microwave Sensor for Glucose Level Measurement Based on Strip Line with Complementary Split Ring Resonator(2025-06-01); - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Deep Learning-Based Human Recognition Through the Wall using UWB radar(2021-01-01); Human activity detection in obscured or invisible area, for instance, human detection through the wall has become an interesting topic because it has potential for security, rescue, activity analysis application, etc. UWB radar, a detection system produces short radio frequency pulses and measures the reflected signals which UWB pulses have high spatial resolution and enable penetration in dielectric materials, was used to collect human activity through the wall signals at the frequency range of 3 GHz in this research. Subsequently, we applied signal data with the Deep Neural Network model to classify 5 classes of human activity including standing, walking, sitting, laying, and no-human gave the F1 score up to 96.94%.