Phasukkit, Pattarapong

Preferred name

Alternative Name

Phasukkit, P.

Main Affiliation

School of Engineering

pattarapong.ph@kmitl.ac.th

Now showing 1 - 10 of 96

Some of the metrics are blocked by your
consent settings
Basic investigation of breast cancer detection in early stage using microwave radiation: Finite element analysis approach
(2011-12-01)
Sanpanich, A.
;
Phasukkit, P.
;
Tungjitkusolmun, S.
;
Pintavirooj, C.
;
Wongtrairat, W.
One of the main problem which threatening health in middle-aged women around the world is breast cancer. Not only a physical painfulness but also including her own family and victim relatives who suffering from this unavoidable pity fate. To detect those cancerous tumors as in an earlier stage as possible seem to be the best way to handle with this hazard. Besides from x-rays mammography and a conventional diagnostic ultrasound, microwave radiation tomography technique is a promising method to investigate any abnormality forming in her mammalian gland. In this paper, we propose a simulation of microwave radiation using a finite element method (FEM) of our modified imaging setup system for female breast cancer diagnosis. By using FEM, we propose a preliminary study of microwave breast cancer detection from a patch antenna propagation in 3D tissue space approaching. In term of wave penetration, voluminous 3D distribution geometry of electrical field in nonhomogenous simple breast phantom model was presented. These simulations not only show a promising result but also encourage us to develop a real imaging setup system in the near future. © 2011 IEEE.
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
Analysis of heat sink effect in hepatic cancer treatment near arterial for microwave ablation by using finite element method
(2012-12-01)
Yhamyindee, P.
;
Phasukkit, P.
;
Tungjitkusolmon, S.
;
Sanpanich, A.
This paper presents an analysis of heat sink effect in hepatic cancer treatment near arterial vessel for microwave ablation by using finite element method. We analyze the temperature distribution, Specific Absorbtion Rate (SAR) and coagulation area in two models. The first is hepatic tissue without artery and the second is hepatic tissue with artery. In the second model, we specify distance between antenna and artery at 10 mm. The initial condition is set as power at 50 watts, temperature at 37°C and blood perfusion rate is varied at 6.4 × 10-10, 6.4 × 10-3 and 6.4 × 104 l/s. The simulation results by using three-dimensional finite element analysis show that the temperature distribution in case of hepatic tissue with no artery is larger than the case with artery. We also found that blood perfusion rate affects to the temperature distribution in hepatic tissue. Higher blood perfusion rate, higher heat sink effect occur. ©2012 IEEE.
Some of the metrics are blocked by your
consent settings
Recurrent neural network based underground object detection using a-scan ground penetrating radar
(2021-05-19)
Choochim, Poomsak
;
Kasjarun, Panut
;
Phasukkit, Pattarapong
Ground penetrating radar is a highly effective tool to find objects buried underground. But there are still some limitations that prevent it from being applied to a wider variety of applications. The complexity of processing and the opportunity to collect the signal. This work is applied GPR with AI to reduce the processing steps and displayed your object's features immediately. Based on the time series model in Bidirectional Neural Network as RNN in bidirectional format. Because it possible to predict the position and shape of the object simultaneously. The object was buried under a sandbox with a depth of 10 - 50 centimeters and used two antennas to receive and transmit the signal as a GPR machine in this experiment. Found that the accuracy is at 92.8 % and also measured by F1-score in each target positions as well, when using the results of this work to add features and extend it to work with multiple functions, it will be possible to use the GPR used with Neural Network model can be used in the actual situation.
Some of the metrics are blocked by your
consent settings
Image Enhancement by using Triple Filter and Histogram Equalization for Organ Segmentation
(2019-11-01)
Thitivirut, Mongkol
;
Leekitviwat, Jirayuts
;
Pathomsathit, Carat
;
Phasukkit, Pattarapong
Convolution filters are used for blurring and sharpening to modifying image when combined with the Histogram equalization for enhancing medical image by adjusting the contrast of the image. Then, the image will be optimized. So, use morphological for segmentation. This research has been designed the filtering in a part of the convolution filter by using the triple filter to adjust the threshold of morphological and normalization value. The results of this experiment are presented that the accuracy of segmentation is increasing and detecting the multiple organs. Nevertheless, we also found that each algorithm can be used for each organ.
Some of the metrics are blocked by your
consent settings
Temperature Distribution of Microwave Balloon Treatment Benign Prostatic Hyperplasia using Finite Element Model
(2019-11-01)
Jandang, Sinchai
;
Tungjitkusolmun, Supan
;
Phasukkit, Pattarapong
In this paper, the 3D model of Microwave balloon antenna for treatment urethral stricture from Benign Prostatic Hyperplasia (BPH) was presented. The 3D modeling heating pattern's ability of thin slot antenna of microwave balloon in the research was also demonstrated. As the results showed that the distribution of temperature and surrounding temperature of modeling of open microwave system. Microwave system at 2.45 GHz. Power Operation are 40, 60 and 80 W. Time operation are 5-600s. A design microwave balloon antenna has protection of critical tissue structure.
Some of the metrics are blocked by your
consent settings
Real-time monitoring glucose by used microwave antenna apply to biosensor
(2011-12-01)
Wiwatwithaya, Sujitra
;
Phasukkit, Pattarapong
;
Tungjitkusolmun, Supan
;
Wongtrairat, Wannaree
In this paper we investigate the electromagnetic field interaction with a glucose aqueous solution using a microwave antenna (U-shape) to evaluate the glucose concentration and vary temperature. The glucose concentration vary from 10-40 mg/ml compare with DI(de-ionized) water, the operating frequency of about 1-2.5GHz. The change of the glucose concentration is directly related to the change of the reflection coefficient due to electromagnetic interaction between the dielectric wave and the glucose aqueous solution. A glucose biosensor using microwave antenna (U-shape) provides a unique approach for glucose monitoring. The antenna is designed have various formed and test by comsol program. The principles of Comsol is finite element for dispersion of electromagnetic waves from a real experiment to measure the concentration of glucose solution. © 2011 IEEE.
Some of the metrics are blocked by your
consent settings
An Infant Cry Recognition based on Convolutional Neural Network Method
(2019-11-01)
Teeravajanadet, K.
;
Siwilai, N.
;
Thanaselanggul, K.
;
Ponsiricharoenphan, N.
;
Tungjitkusolmun, S.
In this paper, an investigation of crying signal spectra is used to classify categories of infant cries. Three different types of crying considered in this work are hungry, sleepy and burping need. These cries are preprocessed and converted for calculation of Mel-Frequency Cepstral Coefficients (MFCC) before being classified by Convolutional Neural Network (CNN). Experimental results show that CNN based deep learning achieves high performance of 84%.
Some of the metrics are blocked by your
consent settings
Crack Localization Detection in Monolithic Zirconia Dental Crowns via 1D-Convolutional Neural Networks Algorithm-Based Acoustic Emission Analysis
(2024-01-01)
Tuntiwong, Kuson
;
Wangman, Rangsinee
;
Sritart, Hiranya
;
Kanchanatawewat, Kanchana
;
Tungjitkusolmun, Supan
The feasibility of utilizing the acoustic emission (AE) technique for the detection and classification of cracks within monolithic dental crown is assessed in this study, owing to its non-destructive nature which enables passive monitoring of structures. The AE signals captured are subjected to analysis to extract pertinent information regarding the source and location of the cracks. A novel approach is proposed, employing deep learning 1D convolutional neural networks (1D-CNNs) for the recognition and classification of the recorded cracked signals. The AE signals, obtained through a handmade AE data acquisition unit, are converted into .csv format and subjected to denoising using Bayesian methods to eliminate background noise. The signals are collected through the breakage of pencil lead (Vallen systeme) Hsu-Nielsen-Source 0.5 (ASTM E976) applied to each surface of the dental crown. Subsequently, the data signals are divided into training and testing groups following an 85 / 15 split. The performance of the deep learning 1D-CNNs is evaluated based on Precision, Recall and total accuracy metrics. The applicated of automated deep learning in this study demonstrated significantly high overall accuracy (98.67%). The integration of handmade data acquisition with 1D-CNN crack detection proves to be an effective method for early screening. The novel method harnesses acoustic emission signals in 1D-CNNs, thereby enhancing the accuracy of clinical dental restorative crack identification and determining the onset time.
Some of the metrics are blocked by your
consent settings
Cross-Sensor and Cross-Population Generalization of Deep Learning Models for Digital Mammography: A Controlled Four-Country Benchmark of Five Backbone Architectures with Statistical Significance Testing
(2026-06-01)
Gabbualoy, Somprasonk
;
Phasukkit, Pattarapong
;
Tungjitkusolmun, Supan
Background/Objectives: Deep learning models for digital mammography sensor data are increasingly deployed across hospitals using different X-ray detector technologies and patient populations. Whether models trained on one sensor platform and population maintain accuracy when transferred to another has not been tested for the latest generation of mammography-specific foundation models under one controlled protocol. Methods: We fine-tuned five backbone architectures (ResNet-50, DINOv2-B14, Rad-DINO, Mammo-CLIP B5, and Mammo-FM) on CBIS-DDSM (film-digitized, USA, n = 714 validation) with three seeds, ablated a density-aware focal loss across three auxiliary weights, and evaluated transfer to three external sensor cohorts: CMMD (full-field digital, China, n = 1032), DMID (mixed digital, India, n = 509), and MIAS (film-digitized, UK, n = 322). Significance used paired DeLong z-tests with Benjamini–Hochberg FDR correction; temperature scaling tested post hoc recalibration at all transfer targets. Results: Within this single-source three-seed evaluation, ResNet-50 outperformed all four foundation models on CBIS-DDSM (AUC 0.867 vs. 0.847, 0.846, 0.813, and 0.703; all gaps p_adj < 0.05). The density-aware focal loss degraded both AUC and calibration at every weight tested. At transfer, every model lost 0.165 to 0.320 AUC points relative to in-distribution performance, with sensitivity at 95% specificity collapsing from 0.31 to 0.47 in-distribution to 0.11 to 0.22 across the three external targets. A per-seed Stouffer meta-analysis confirms that Mammo-CLIP B5 and Mammo-FM significantly outperformed ResNet-50 on DMID and Mammo-CLIP on CMMD, after BH-FDR; MIAS comparisons remained directional only. In the extremely dense subgroup (BI-RADS D4), Mammo-FM reached AUC 0.870 versus ResNet-50 at 0.842, a directional observation whose 95% CIs overlap heavily at the n = 140 sample size and which we do not interpret as a statistically supported advantage. Conclusions: In this single training-source, three-seed protocol, mammography-specific pretraining did not deliver the in-distribution AUC premium reported in the originating papers, and no architecture reached a level at which transfer deployment without local validation would be defensible. We frame these as observations specific to the present protocol rather than as broader conclusions about foundation models for mammography classification. The findings argue for sensor-stratified and population-stratified external validation and for local recalibration as practical prerequisites before clinical use. Code and weights are released under MIT license.

Phasukkit, Pattarapong

Filters

Settings

Sort By

Results per page