Ploysuwan, Tuchsanai

Preferred name

Main Affiliation

School of Information Technology

tuchsanai.pl@kmitl.ac.th

Now showing 1 - 8 of 8

Some of the metrics are blocked by your
consent settings
Reducing the Counting Time of Colonies Using Image Processing Techniques
(2024-01-01)
Siangchin, Apichai
;
Ploysuwan, Tuchsanai
Microbial colony counting is a crucial process in microbiology laboratories and medical research, yet it is often time-consuming and labor-intensive, particularly in large-scale settings or when dealing with numerous samples. Incorporating image processing techniques can significantly reduce the time and error associated with manual colony counting. In this study, we developed and evaluated a deep learning model for automated E. coli colony counting using the YOLO (You Only Look Once) framework. The model achieved an mAP50 of 90.3%, demonstrating its high accuracy and potential for real-world application in laboratories of various sizes. This research not only streamlines the colony counting process but also allows laboratory personnel to allocate their time to other essential tasks.
Some of the metrics are blocked by your
consent settings
Dynamic System Linearization via Deep Relative Displacement Prediction for Robust IMU-WiFi Indoor Trajectory Estimation
(2025-01-01)
Chapha, Naphat
;
Ploysuwan, Tuchsanai
Standalone WiFi fingerprinting and Inertial Measurement Unit (IMU) sensors are unreliable for indoor positioning due to signal instability and cumulative drift error, respectively. We present a novel sensor fusion framework that overcomes these challenges by enhancing WiFi fingerprint quality while simplifying the fusion process. Our approach filters and ranks WiFi signals to create a stable input for a Long Short-Term Memory (LSTM), while a Convolutional Neural Network (CNN) is uniquely trained to predict relative displacement from IMU data. This latter step linearizes the system dynamics, enabling the use of a simple Linear Kalman Filter and avoiding the complexity of traditional non-linear filters. Combining these innovations, the integrated framework achieves a mean position error of 4.30 m, a 32.3% improvement over the best standalone model. This work demonstrates that our approach to WiFi selection and system linearization provides a robust and highly accurate solution for real-time indoor positioning.
Some of the metrics are blocked by your
consent settings
Zero-Shot Eggshell Crack Detection Using Grounding DINO and FFT-Based Outer-to-Inner Ring Energy Ratio
(2025-01-01)
Soontornnapar, Tomorn
;
Ploysuwan, Tuchsanai
This study presents a novel approach to eggshell crack detection by integrating zero-shot learning with advanced image analysis techniques. The proposed method utilizes a hybrid dataset composed of a custom hen egg collection-50 tray images containing 30 eggs each arranged in a 6 × 5 grid-and the Botta et al. duck egg dataset, comprising approximately 1,000 images of cracked and intact eggs. Using YOLOv8s and the Fast Segment Anything Model (FastSAM), we generate bounding boxes, annotate segmentation masks, and crop background-free images, resulting in a curated set of 1,500 hen egg images alongside the processed duck egg samples. To localize crack regions accurately, we employ Grounding DINO with fine-grained prompting. To distinguish cracks from dirt and subtle surface irregularities, we introduce a novel frequency-domain feature: the FFT-based Outer-to-Inner (O/I) Ring Energy Ratio, which enhances the visibility of fine anomalies. Our zero-shot detection model achieves an average accuracy of 92.54% across 10-fold cross-validation on both datasets-without retraining-demonstrating strong generalization and eliminating the reliance on labeled training data.We benchmark our approach against supervised models (CNN, SVM, XGBoost, k-NN) and popular zero-shot and anomaly detection frameworks (CLIP, CLIPSeg, Florence-2, and SAA). For real-world validation, we implement our system on an egg-belt conveyor using a low-cost CCD microscope camera capturing 60 FPS video. The model processes one hen egg in tray images at 7.79 FPS in simulation and 0.44 FPS in real-time video testing, enabling inspection of approximately 1,794 eggs per hour per camera. The system's scalability with multiple cameras enables adaptation to industrial egg-sorting speeds. The results demonstrate significant advancements in crack detection accuracy and throughput, highlighting the potential of combining frequency-based image analysis with zero-shot prompting for scalable, real-time quality control in the poultry industry. The full implementation and associated dataset are publicly available at (https://github.com/tomorn112/ZC-DINO-ER/).
Some of the metrics are blocked by your
consent settings
A novel approach to enhanced fall detection using STFT and magnitude features with CNN autoencoder
(2025-02-01)
Soontornnapar, Tomorn
;
Ploysuwan, Tuchsanai
The ability to accurately detect and classify falls is critical for ensuring timely medical intervention, especially for the elderly, who face a significantly higher risk of severe injuries, loss of independence, or fatal outcomes from falls. This paper introduces a novel fall detection approach that addresses these urgent needs by using short-time Fourier transform (STFT) images and the magnitude of quaternion (MQ) signals, fused into STFT-MQ images. The proposed method leverages STFT’s time–frequency representation to capture rapid changes and dynamic characteristics in human motion data from wearable sensors, enhancing its ability to distinguish between fall and non-fall incidents. Utilizing a convolutional neural network autoencoder (CNN-AE), an unsupervised learning model, this approach analyzes transformed data without extensive labeled datasets, offering a scalable solution in diverse settings. Tested on the HIFD dataset with heart rate and IMU sensor data, the STFT-MQ-AE method achieves remarkable sensitivity of 98.08%, specificity of 98.78%, and an overall accuracy of 98.57%, setting a new benchmark in fall detection accuracy. Furthermore, the model’s reliance on an N-way K-shot learning approach enables it to manage unforeseen fall cases effectively without retraining, enhancing adaptability and real-world utility. The model achieves the highest Youden’s index (YI) of 96.85%, underlining balanced performance between fall and non-fall classification. Consistent performance across varied training scenarios yields an average accuracy of 96.10%, making this approach highly reliable. This advancement in fall detection technology offers a practical, effective solution to reduce fall-related injuries and enable timely assistance, thereby promoting safer, more independent living for at-risk populations.
Some of the metrics are blocked by your
consent settings
Code Smell Classification Using Graph Convolutional Network with Imbalanced Data and Model Integration
(2025-01-01)
Suphawimon, Phawinee
;
Ploysuwan, Tuchsanai
Code smell represents critical design anomalies that significantly impact software maintainability and quality. This paper presents a comprehensive framework using Graph Convolutional Networks (GCNs) integrated with traditional machine learning techniques. We systematically evaluated graph construction approaches, model integration methodologies, and data balancing strategies using nine real-world Python repositories labeled with PyExamine. Our methodology combines BERT embeddings with graph structural representations, implementing layer integration (Method I) and feature concatenation (Method II). Results show per-line graph construction outperforms global approaches, with SMOTE achieving 96.14% accuracy compared to 86.70% for imbalanced data. Including non-smelly code improves performance from 71% to 95%, demonstrating the importance of negative examples. Our ablation study shows explicit feature engineering achieves only 67% accuracy compared to 95% for end-to-end learning. The integrated GCN with Transformer using Method II achieved 95% accuracy and 89% F1-score, nearly matching CodeT5 (97% accuracy, 85% F1-score) while providing better interpretability.
Some of the metrics are blocked by your
consent settings
Fall Detection Approach Using Variational Autoencoders with Self-Attention Features
(2023-01-01)
Soontornnapar, Tomorn
;
Ploysuwan, Tuchsanai
In this paper, we propose an alternative method for fall detection using variational autoencoders (VAEs) with an attention mechanism on an existing dataset. The dataset consists of 6 different fall cases from 21 people. For effective fall detection, we introduce the use of the magnitude of the acceleration vector (MAV) of wearable gyroscope data and apply fast-Fourier transform (FFT) to create new features. These FFT features are then passed through attention modules with self-combination to form attention features. Our experimental results show that the VAE with self-attention features achieved an average accuracy of 90.7% and an F1 score of 93.8% in fall detection, demonstrating the effectiveness of the proposed method in utilizing gyroscope sensors for fall detection in the context of threshold criteria.
Some of the metrics are blocked by your
consent settings
Zero-/Few-Shot Anomaly Classification for Transistor Using Multimodal CLIP Retrieval Augmented
(2024-01-01)
Praneenatthavee, Natdhanai
;
Ploysuwan, Tuchsanai
Detecting anomalies in transistors is a challenging task due to the intricate features distinguishing normal from abnormal components. This paper introduces a zero-shot and few-shot anomaly classification framework for transistors using a retrieval-augmented multimodal approach. We focus on two critical parts of the transistor: the Component BOX and the Metal Legs. Utilizing Florence2 for prompt-based bounding box generation and Segment Anything Model2 (SAM2) for segmentation, we create precise masks for each part. Embeddings generated through Contrastive Language-Image Pre-training (CLIP) are employed to classify each component effectively. For the few-shot learning scenario, we implement Retrieval-Augmented Generation (RAG) to simulate learning from both images and textual data, enhancing the anomaly classification performance. Our zero-shot model achieved an fl score of 70.5, while the few-shot model attained an improved fl score of 77.0, demonstrating the efficacy of our approach in transistor anomaly detection.
Some of the metrics are blocked by your
consent settings
Revolutionizing Egg Quality Control: Advanced Prompt-based Models for Automated Detection of Broken Eggs Without the Need for Training
(2025-02-01)
Soontornnapar, Tomorn
;
Praneenatthavee, Natdhanai
;
Ploysuwan, Tuchsanai
This paper proposes an end-to-end pipeline to detect broken eggs in a holder without extensive training, employing a two-step image segmentation and processing approach using saliency scores, all without relying on a large amount of labeled data. The process begins by inputting an egg image with text prompts into Grounding DINO, which returns an egg bounding box. This is followed by the segment anything model (SAM), which extracts the egg’s segmented region. The segmented region is then divided into two crucial components for detection: a binary mask image and a background-removed egg image. The innovation in our method lies in using the saliency score of the estimated anomaly region by employing image processing techniques to effectively distinguish between intact and broken eggs. To validate our approach, we compare it to well-known models such as SVM, XGBoost, and YOLOv8, and we also conduct zero-shot experiments with CLIPSeg, Florence-2, and SAA. In our experimental setup, we utilize 50 egg holder images, each containing both intact and broken eggs. We carefully cropped and processed 30 eggs (arranged in a 6×5 grid) from each holder, resulting in a comprehensive testing dataset totaling 1,500 images. Our results demonstrate the robustness of our method, achieving an impressive 99.56% accuracy in detecting both intact and broken eggs. This breakthrough promises significant advancements in the field of broken egg detection, with broad applications across diverse industries, including food safety, quality control, and automated packaging systems.

Ploysuwan, Tuchsanai

Filters

Settings

Sort By

Results per page