Treebupachatsakul, Treesukon

Preferred name

Alternative Name

Treebupachatsakul, T.

Main Affiliation

School of Engineering

treesukon.tr@kmitl.ac.th

Now showing 1 - 10 of 26

Some of the metrics are blocked by your
consent settings
The Comparison of Deep Learning Model Efficiency for Classification of Oral White Lesions
(2022-01-01)
Phosri, Kunchidsong
;
Treebupachatsakul, Treesukon
;
Chomkwah, Wanwalee
;
Tanpatanan, Tananan
;
Thanathornwong, Bhornsawan
Oral cancer is one of the top health problems globally. Some white lesions of the oral cavity can develop into oral cancer if not screened and treated immediately. Modern screening technologies are popular for applying deep learning knowledge to screen and classify images. In this study, we used deep convolution neural network (CNN) to classify oral white lesions, ulcers, and normal anatomy using transfer learning, which can reduce training time. Ten pre-trained model of transfer learning including DenseNet121, DenseNet169, DenseNet201, Xception, ResNet50, InceptionResNetV2, InceptionV3, VGG16, VGG19, and EfficientNetB7 are implemented and evaluated. The evaluation of accuracy, precision, F1score, recall, sensitivity, confusion matrix, and AUC-ROC curve are discussed. The trained models of DenseNet169, DenseNet201, and Xception showed the highest testing accuracy of more than 90% and recall of 0.8833. In addition to the precision, F1score, and specificity, the DenseNet169 outperforms at 0.9034, 0.884, and 0.9417, respectively.
Some of the metrics are blocked by your
consent settings
Pressure Swing Absorption Oxygen Concentrator equipped with Remote Monitoring Pulse Oximeter
(2021-01-01)
Ongtrakul, Salila
;
Thitiratannapong, Anyarin
;
Pintavirooj, Chuchart
;
Treebupachatsakul, Treesukon
The new COVID-19 disease was first identified in China at the end of 2019 and has spread rapidly all over the world. It has been projected that, by March 2021, the number of infections could reach 300 million cases and over two million deaths. One of the main implications for COVID-19 patients is pneumonia where the lung is infected, hence patients suffering from insufficient oxygen in the blood. As the number of COVID-19 cases have significantly increased, the demand for oxygen generators have also skyrocketed. This research concerns the design and construction of emergency low-cost oxygen concentrators used for mild COVID-19 symptoms, of which are forced to be treated at home. Our absorption-based oxygen concentrator uses zeolite packed in a sieve canister. An Oil-free compressor is then used to pump air in. Zeolite will absorb nitrogen from the air leaving oxygen free to travel towards the outlet. To evaluate the treatment, we have equipped the system with a pulse oximeter to measure the percent saturation oxygen, pulse rate and temperature. To prevent COVID-19 infections between patients and caretakers, we have designed an android application to remotely control the oxygen concentrator. Experiment has shown that our emergency low-cost oxygen concentrator can supply oxygen with an 85% purity rate.
Some of the metrics are blocked by your
consent settings
Classification model for predicting inflammation of the urinary bladder and acute nephritis of the renal pelvis
(2022-01-01)
Lochotinunt, Chanin
;
Pechprasarn, Suejit
;
Treebupachatsakul, Treesukon
Urinary tract diseases can occur in many organs of the urinary system, such as kidneys, urinary bladder, renal pelvis, ureters, and urethra. The most common disease in the urinary system is bladder inflammation, cystitis, and acute nephritis. In this research, the classification artificial intelligent model is applied to predict 2 symptoms of inflammation of the urinary bladder and acute nephritis of the renal pelvis from 6 parameters, including body temperature of patient, nausea, lumbar pain, urinary pushing, micturition pains, and burning of the urethra. Here, the principal components analysis or PCA are also applied to identify the critical parameters employed to train the machine learning model. Here, we propose to compare several machine learning classification models and show the proper model accurately diagnosing these two symptoms.
Some of the metrics are blocked by your
consent settings
Deep Learning to Classify Bacterial Species in the same Genus
(2024-01-01)
Sheela, Sherin
;
Piang, May Phu
;
Sakorntanant, Sakda
;
Poomrittigul, Suvit
;
Treebupachatsakul, Treesukon
Bacterial strains in the same genus share highly similar morphology, gram-staining characteristics, colony sizes, and spatial arrangements. Therefore, identifying them by deep learning can be quite challenging. This study aimed to assess the classification of 7 species of bacteria from 2 genera of Bacillus and Vibrio by using 8 Convolutional Neural Network (CNN) models. We implemented Python programming along with Keras API within the Jupyter Notebook. The models were constructed and evaluated under unbalanced and balanced datasets by augmentation (rotation, flip, etc.). Transfer learning with fine-tuning, and pre-processing of mixup and label smoothing were also applied to reduce overfitting and enhance generalization. Based on the experimental results on private dataset, the results of InceptionResNetV2 emerged as the top-performing model with a notable accuracy of 82.8%, 88.6% precision, 78.4% recall, and 78.0% F1-score when label smoothing was applied at 0.5 on balanced dataset.
Some of the metrics are blocked by your
consent settings
Multi-parameter vital sign telemedicine system using web socket for covid-19 pandemics
(2021-03-01)
Pintavirooj, Chuchart
;
Keatsamarn, Tanapon
;
Treebupachatsakul, Treesukon
Telemedicine has become an increasingly important part of the modern healthcare infras-tructure, especially in the present situation with the COVID-19 pandemics. Many cloud platforms have been used intensively for Telemedicine. The most popular ones include PubNub, Amazon Web Service, Google Cloud Platform and Microsoft Azure. One of the crucial challenges of telemedicine is the real-time application monitoring for the vital sign. The commercial platform is, by far, not suitable for real-time applications. The alternative is to design a web-based application exploiting Web Socket. This research paper concerns the real-time six-parameter vital-sign monitoring using a web-based application. The six vital-sign parameters are electrocardiogram, temperature, plethysmogram, percent saturation oxygen, blood pressure and heart rate. The six vital-sign parameters were encoded in a web server site and sent to a client site upon logging on. The encoded parameters were then decoded into six vital sign signals. Our proposed multi-parameter vital-sign telemedicine system using Web Socket has successfully remotely monitored the six-parameter vital signs on 4G mobile network with a latency of less than 5 milliseconds.
Some of the metrics are blocked by your
consent settings
Permeability and setting time of bio-mediated soil under various medium concentrations
(2021-04-01)
Treebupachatsakul, Treesukon
;
Kamchoom, Viroon
The bio-clogging using bacteria can be an eco-friendly and sustainable alternative to conventional grouting methods for seepage control. However, it remains unclear to date how the dilute concentration of bacterium and medium during field installation can affect the setting time of bacterium and its correlation with permeability reduction. In this study, the setting time of bacterium and its effectiveness in permeability reduction were addressed through experimental and theoretical investigations. A series of sand column was cultivated using different concentrations of Leuconostoc mesenteroides and culture medium. The distribution and composition of the bacterial product (i.e. dextran) were observed by refractometer, scanning electron microscope (SEM), and energy dispersive X-ray spectroscopy (EDS). Soil permeability was recorded using a constant head test. The results revealed that bacterium was effective to produce dextran at the setting time of about 5 d after installation. This dextran can reduce the permeability of bio-mediated soil by two orders of magnitude, even without culture medium supply. In general, the dextran production decreased proportionally with increase of bacterium and medium concentration. However, at 50% bacterium and medium concentration by weight, it still has a significant influence on permeability reduction with similar setting time, compared to 100% concentration.
Some of the metrics are blocked by your
consent settings
Microfluidic channel from gelatin using laser printer
(2020-10-29)
Lochotinunt, Chanin
;
Teechot, Thitirat
;
Pechprasarn, Suejit
;
Treebupachatsakul, Treesukon
Microfluidic channel is a tool for manipulating and controlling fluids under small precise volumes and spaces. Nowadays, microfluidic fabrication has used varieties of materials such as silicon, glass, polymer, and ceramic. These materials generate waste and pollution in our environment. Moreover, the process of making microfluidic is sophisticated. Therefore, using the green-material, Gelatin is an attractive alternative to fabricate microfluidic because it is abundant, cheap, environmentally friendly, and reusable. Here, the Gelatin is employed for fabricating microfluidic by which the channel features were prepared using a laser printer. The fabrication procedure consists of the following steps (1) design the microfluidic channel features and print them on a transparency plastic sheet using a laser printer. (2) Pour aqueous gelatin solution on this printed template plastic sheet and (3) make the liquid gelatin setting by cooling it down in a refrigerator or leave it at room temperature. These steps allowed us to fabricate the smallest channel of 1.78mm (width) x 0.19mm (height) from 3pt line with 30 times layer printed, which was applicable to flow the liquid through the microfluidic.
Some of the metrics are blocked by your
consent settings
Generalized figure of merit for plasmonic dip measurement-based surface plasmon resonance sensors
(2022-04-01)
Treebupachatsakul, Treesukon
;
Boosamalee, Apivitch
;
Chaithatwanitch, Kamejira
;
Pechprasarn, Suejit
We propose a theoretical framework to analyze quantitative sensing performance parameters, including sensitivity, full width at half maximum, plasmonic dip position, and figure of merits for different surface plasmon operating conditions for a Kretschmann configuration. Several definitions and expressions of the figure of merit have been reported in the literature. Moreover, the optimal operating conditions for each figure of merit are, in fact, different. In addition, there is still no direct figure of merit comparison between different expressions and definitions to identify which definition provides a more accurate performance prediction. Here shot-noise model and Monte Carlo simulation mimicking the noise behavior in SPR experiments have been applied to quantify standard deviation in the SPR plasmonic dip measurements to evaluate the performance responses of the figure of merits. Here, we propose and formulate a generalized figure of merit definition providing a good performance estimation to the detection limit. The measurement parameters employed in the figure of merit formulation are identified by principal component analysis and machine learning. We also show that the proposed figure of merit can provide a good estimation for the surface plasmon resonance performance of plasmonic materials, including gold and aluminum, with no need for a resource-demanding computation.
Some of the metrics are blocked by your
consent settings
The Study of Image Quality Effect on Model Performance for Bacteria Classification
(2025-01-31)
Treebupachatsakul, Treesukon
;
Chomkwah, Wanwalee
;
Tanpatanan, Tananan
;
Poomrittigul, Suvit
One of the key requirements for supervised learning in deep learning model construction is the dataset for training and validation. For gathering the dataset, obtaining various image qualities from different resources is unavoidable, and this has been considered to affect the supervised model performance. This research proposes to demonstrate the effect of image quality involving high and standard datasets obtained from 2 different resources on the performance of models. The various cell characteristics with gram-positive and gram-negative bacteria datasets were challenged for trial. These different datasets were matched and contributed to 5 cases; case 1: train and test with high-quality images, case 2: train with high-quality images and test with standard quality images, case 3: train and test with images of standard quality, case 4: train with standard-quality images and test with high-quality images, and case 5: train and test with combining these two image qualities. Pre-trained CNN models were implemented to prove the purpose with and without stratified K-fold cross-validation. The results of retrained models showed that the high-performance models require high-quality datasets obtained from the same resource as the testing set, which yield more than 90% of all performance evaluation metrics when tested on challenging unseen datasets. This study provides valuable insights for building high-performance models that can be applied to automate microbiology diagnostics, impacting public health and clinical practice.
Some of the metrics are blocked by your
consent settings
Real-Time White Blood Cell Classification with YOLO
(2025-01-01)
Eamkong, Anoma
;
Pintavirooj, Chuchart
;
Treebupachatsakul, Treesukon
White blood cell (WBC) classification plays a crucial role in diagnosing various hematological conditions, including infections, immune disorders, and leukemia. This study presents an automated approach for WBC detection and classification using the YOLOv5 deep learning model. The system integrates a 1.3MP microscope camera with a stepper motor-driven platform for real-time imaging and classification. The dataset consists of five WBC types: basophils, eosinophils, lymphocytes, monocytes, and neutrophils, with image enhancement and data augmentation applied to improve model performance. The trained YOLOv5 model achieved a classification accuracy of 92.61% and a validation accuracy of 95.86%, demonstrating high precision and recall in WBC identification. The results indicate that this system can effectively automate WBC analysis, reducing manual effort and improving diagnostic accuracy. This approach has potential applications in clinical hematology, offering a rapid and reliable method for WBC classification.

Treebupachatsakul, Treesukon

Filters

Settings

Sort By

Results per page