KMITL

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

Browse

Search Results

Now showing 1 - 10 of 26

Some of the metrics are blocked by your
consent settings
Antibacterial characterization of ciprofloxacin-doped electrospun of low molecular weight polyethylene oxide (PEO) and sodium alginate (NaAlg) nanofibers
(2026-02-23)
Niyomchon, Phuphinee
;
Treebupachatsakul, Treesukon
;
Srirussamee, Kasama
Producing nanofibers using the electrospinning technique is a developed method that is widely used and of significant interest nowadays. This technique can be applied using various types of polymers. This research aimed to investigate the antibacterial PEO-NaAlg nanofiber fabrication. The fiber fabrication was examined under various viscosities of electrospinning solution. The electrospun nanofiber fabrication focuses on blending polyethylene oxide (PEO) with a molecular weight of 200-300 kDa, mixed with sodium alginate (NaAlg) of three different viscosities: 150 cP, 300 cP, and 730 cP to study how the viscosity of the solution affects the morphology of electrospun nanofibers. The PEO-NaAlg electrospun nanofiber was enhanced for water insolubility by crosslinking with calcium chloride (CaCl₂). The additional antibacterial property of the nanofiber by loading an antibacterial agent potentially against the growth of bacteria, was investigated. Antibacterial drug, ciprofloxacin at varying amounts of 0.05%w/v, 0.20%w/v, and up to 0.25%w/v was loaded to PEO-NaAlg solution and conducted electrospinning. The effectiveness of the antibacterial electrospun nanofiber was evaluated by testing its ability to inhibit the growth of Escherichia coli (E. coli) and Staphylococcus aureus (S. aureus). The inhibition area before and after crosslinking was observed. The results showed that the acquired nanofibber formation required 7%w/v of 200 kDa to 300 kDa of PEO, and blending 1%w/v NaAlg of 150 cP can certainly retain fiber morphology after crosslinking. Moreover, nanofibers loaded with ciprofloxacin effectively inhibit the growth of E. coli.
Some of the metrics are blocked by your
consent settings
Performance of deep learning models for the classification and object detection of different oral white lesions using photographic images
(2025-12-01)
Khovidhunkit, Siribang on Piboonniyom
;
Phosri, Kunchidsong
;
Thanathornwong, Bhornsawan
;
Rungraungrayabkul, Dulyapong
;
Poomrittigul, Suvit
Computer vision adjunctive technology for oral lesion diagnoses has been developed to detect and identify Oral Potentially Malignant Disorders (OPMDs) and non-OPMDs. The early detection of OPMDs can reduce the risk of oral cancer development, improving the survival rate of the patients. This study aims to evaluate the computer vision technique in the white oral lesion domain within the scope of photographic images. Deep learning techniques for the classification of Convolution Neural Networks (CNNs) and transformer neural networks, and one-stage models of YOLOv7 and YOLOv8 were utilized to classify and detect five classes of OPMDs and non-OPMDs oral white lesions including oral leukoplakia, oral lichen planus, pseudomembranous candidiasis, oral ulcers covered with pseudomembrane and other white benign oral lesions. From the evaluation results of classification, the IFormerBase model achieves overperformance compared to CNN models with accuracy, precision, and F1 score of more than 80% on the test set. The best model for object detection is YOLOv7 with 84.5% mean Average Precision (mAP) at Intersection over Union (IoU) threshold of 0.3 and 74.5% at IoU of 0.5 on the test set. Object detection results reveal promising automatic oral lesion identification, which can be further developed to enhance the lesion screening system.
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.
Some of the metrics are blocked by your
consent settings
Bilingual Audio Depression Identification Model by Machine Learning
(2025-01-01)
Poomrittigul, Suvit
;
Kiatrungrit, Komsan
;
Homsiang, Phanomkorn
;
Treebupachatsakul, Treesukon
The number of depression patients worldwide, particularly in Thailand, is increasing on an upward trend. Depression screening commonly relies on self-report questionnaires. However, these instruments provide subjective assessments. Recent advancements in machine learning technology offer potential improvements in diagnostic accuracy through more objective measures. This study aims to evaluate the effectiveness of machine learning models in classifying depression using a bilingual audio dataset comprising Thai and English languages. Such models have the potential to assist clinicians by providing objective preliminary screening for depression based on vocal analysis, enhancing diagnostic precision and clinical decision-making. Various machine learning models were implemented including KNN, MLP, Random Forest, Decision Tree, SGD, Logistic Regression, SVM, AdaBoost, and Gaussian Naïve Bayes using MFCC-converted audio datasets. The results indicate that machine learning models effectively classify and identify depression even in bilingual audio datasets compared to individual language models, with the highest accuracy reaching 0.95 from MLP and KNN when testing the trained model by a single Thai audio.
Some of the metrics are blocked by your
consent settings
Spatiotemporal variations of sand hydraulic conductivity by microbial application methods
(2024-01-01)
Kamchoom, Viroon
;
Khattiwong, Thiti
;
Treebupachatsakul, Treesukon
;
Keawsawasvong, Suraparb
;
Leung, Anthony Kwan
The spatiotemporal distributions of microbes in soil by different methods could affect the efficacy of the microbes to reduce the soil hydraulic conductivity. In this study, the specimens of bio-mediated sands were prepared using three different methods, i.e. injecting, mixing, and pouring a given microbial solution onto compacted sand specimens. The hydraulic conductivity was measured by constant-head tests, while any soil microstructural changes due to addition of the microbes were observed by scanning electron microscope (SEM) and mercury intrusion porosimetry (MIP) tests. The amount of dextran concentration produced by microbes in each type of specimen was quantified by a refractometer. Results show that dextran production increased exponentially after 5–7 d of microbial settling with the supply of culture medium. The injection and mixing methods resulted in a similar amount and uniform distribution of dextran in the specimens. The pouring method, however, produced a nonuniform distribution, with a higher concentration near the specimen surface. As the supply of culture medium discontinued, the dextran content near the surface produced by the pouring method decreased dramatically due to high competition for nutrients with foreign colonies. Average dextran concentration was negatively and correlated with hydraulic conductivity of bio-mediated soils exponentially, due to the clogging of large soil pores by dextran. The hydraulic conductivity of the injection and mixing cases did not change significantly when the supply of culture medium was absent.
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
Sensing Mechanisms of Rough Plasmonic Surfaces for Protein Binding of Surface Plasmon Resonance Detection
(2023-04-01)
Treebupachatsakul, Treesukon
;
Shinnakerdchoke, Siratchakrit
;
Pechprasarn, Suejit
Surface plasmon resonance (SPR) has been utilized in various optical applications, including biosensors. The SPR-based sensor is a gold standard for protein kinetic measurement due to its ultrasensitivity on the plasmonic metal surface. However, a slight change in the surface morphology, such as roughness or pattern, can significantly impact its performance. This study proposes a theoretical framework to explain sensing mechanisms and quantify sensing performance parameters of angular surface plasmon resonance detection for binding kinetic sensing at different levels of surface roughness. The theoretical investigation utilized two models, a protein layer coating on a rough plasmonic surface with and without sidewall coatings. The two models enable us to separate and quantify the enhancement factors due to the localized surface plasmon polaritons at sharp edges of the rough surfaces and the increased surface area for protein binding due to roughness. The Gaussian random surface technique was employed to create rough metal surfaces. Reflectance spectra and quantitative performance parameters were simulated and quantified using rigorous coupled-wave analysis and Monte Carlo simulation. These parameters include sensitivity, plasmonic dip position, intensity contrast, full width at half maximum, plasmonic angle, and figure of merit. Roughness can significantly impact the intensity measurement of binding kinetics, positively or negatively, depending on the roughness levels. Due to the increased scattering loss, a tradeoff between sensitivity and increased roughness leads to a widened plasmonic reflectance dip. Some roughness profiles can give a negative and enhanced sensitivity without broadening the SPR spectra. We also discuss how the improved sensitivity of rough surfaces is predominantly due to the localized surface wave, not the increased density of the binding domain.
Some of the metrics are blocked by your
consent settings
Preprocessing Technique for Oral Lesion Classification using U-NET Segmentation
(2023-01-01)
Dissorn, Pun
;
Treebupachatsakul, Treesukon
;
Phosri, Kunchidsong
;
Thanathornwong, Bhornsawan
;
Khovidhunkit, Siribang On Piboonniyom
This research aims to use deep learning techniques to segment oral lesions in medical images for use as a preprocessing step in a classification model. Due to the complexity of oral lesions with undefined margins and dynamic shapes, and the limited amount of data certified by dentists, this approach was found to be underfitting and unsatisfactory. To improve the accuracy of the model, a new approach was proposed to segment interferences such as teeth from the images. This allows the model to better focus on the oral lesions. To achieve this goal, we implemented U-net models with different additional Convolutional Neural Networks (CNN) backbones, including DenseNet 121, EfficientNet B3, VGG 19, ResNet 18, SE-ResNet 18, ResNeXt 50, Inception V3, Mobilenet V2 and SE-ResNeXt 50. A segmentation model was trained with five classes of oral lesions: leukoplakia, pseudomembranous candidiasis, lichen planus, ulcer, and other white lesions. The results showed that DenseUNet and EfficientUNet achieved the highest validation and Intersection over Union (IoU) scores of 98% and 92%, respectively. Our proposed approach effectively segmented the interferences from the images, demonstrating the success of these models in handling the approach. Subsequently, a CNN model of DenseNet 121 was employed for classification. The training accuracy achieved 99.1%, while the validation and test accuracies reached 86.1% and 75.5%, respectively.
Some of the metrics are blocked by your
consent settings
Fabrication of Water-insoluble Polyethylene Oxide and Sodium Alginate using Electrostatic Repulsive Forces: A Preliminary Study
(2023-01-01)
Niyomchon, Phuphinee
;
Srirussamee, Kasama
;
Treebupachatsakul, Treesukon
Polyethylene oxide (PEO) and sodium alginate (NaAlg) are widely used in biomedical applications due to their biocompatibility. The use of electrostatic repulsive forces could be employed to fabricate these polymers into various shapes, including fibers and particles. However, in some cases, their solubility in water could be a drawback. Therefore, this study aims to fabricate samples from PEO-NaAlg blends using electrostatic repulsive forces and stabilize their structure in water using calcium chloride (CaCl<inf>2</inf>) crosslinking method. The preliminary results have shown that the water solubility of the fabricated samples in this study was reduced by crosslinking, as analyzed by Fourier-transform spectroscopy (FTIR). Moreover, the images from scanning electron microscope (SEM) reveal that the fabricated samples were particle-like, and the increased NaAlg content could increase fiber density before crosslinking and particle aggregate formation after crosslinking. However, further studies are still required to optimize the parameters for fiber fabrication and also for future incorporation of bioactive molecules.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results