KMITL

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

Browse

Search Results

Now showing 1 - 10 of 53

Some of the metrics are blocked by your
consent settings
A Cascade of Encoder–Decoder with Atrous Convolution and Ensemble Deep Convolutional Neural Networks for Tuberculosis Detection
(2025-07-01)
Maneerat, Noppadol
;
Narkthewan, Athasart
;
Hamamoto, Kazuhiko
Tuberculosis (TB) is the most serious worldwide infectious disease and the leading cause of death among people with HIV. Early diagnosis and prompt treatment can cut off the rising number of TB deaths, and analysis of chest X-rays is a cost-effective method. We describe a deep learning-based cascade algorithm for detecting TB in chest X-rays. Firstly, the lung regions were segregated from other anatomical structures by an encoder–decoder with an atrous separable convolution network—DeepLabv3+ with an XceptionNet backbone, DLabv3+X, and then cropped by a bounding box. Using the cropped lung images, we trained several pre-trained Deep Convolutional Neural Networks (DCNNs) on the images with hyperparameters optimized by a Bayesian algorithm. Different combinations of trained DCNNs were compared, and the combination with the maximum accuracy was retained as the winning combination. The ensemble classifier was designed to predict the presence of TB by fusing DCNNs from the winning combination via weighted averaging. Our lung segmentation was evaluated on three publicly available datasets: it provided better Intercept over Union (IoU) values: 95.1% for Montgomery County (MC), 92.8% for Shenzhen (SZ), and 96.1% for JSRT datasets. For TB prediction, our ensemble classifier produced a better accuracy of 92.7% for the MC dataset and obtained a comparable accuracy of 95.5% for the SZ dataset. Finally, occlusion sensitivity and gradient-weighted class activation maps (Grad-CAM) were generated to indicate the most influential regions for the prediction of TB and to localize TB manifestations.
Some of the metrics are blocked by your
consent settings
Glioma Brain Tumor Classification Using Convolution Neural Network and Majority Voting
(2025-01-01)
Pilaoon, Pongsak
;
Hamamoto, Kazuhiko
;
Maneerat, Noppadol
Glioma brain tumors are malignant diseases for which early detection and instant treatment will increase the survival rate. Several studies have reported the efficiency of deep learning convolutional neural networks (CNN) in diagnosing brain tumors using magnetic resonance imaging (MRI). In this study, we investigated the potential of state-of-the-art classifiers to achieve the highest accuracy in the detection of brain tumors using MRI. For this purpose, we introduced a comparative study of eight state-of-the-art classifiers. The methodology comprised three different approaches: 1) an imbalanced dataset, 2) a balanced dataset using image augmentation, and 3) ensemble learning using the best of the top five models for majority hard and soft voting. The dataset comprised converted MRI data from the repository of molecular brain neoplasia data (REMBRANDT) and brain tumor segmentation 2021 (BraTS) databases. An increasing number of MRI images and datasets has prevented overfitting. Initially, a preprocessing stage morphological operation and contrast-limited adaptive histogram equalization (CLAHE) algorithms were used to remove skeletons and artifacts and optimize the image contrast for readiness classification. The stochastic gradient descent with the momentum algorithm option was used to train the network. The trained model was used to predict the testing dataset, and the results from each pretrained network were evaluated. The experimental results demonstrated that the prediction accuracy of the trained network was significantly improved using a balanced training dataset. The discriminative image region used to interpret the predicted result using the gradient-weighted class activation mapping (Grad-CAM) algorithm was proposed in the final stage for trustworthiness. The experimental results showed that the best approach was inceptionV3 with a balanced dataset. The accuracy, sensitivity, specificity, and area under the curve were 99.73%, 99.61%, 100%, and 1.00, respectively.
Some of the metrics are blocked by your
consent settings
Linear Interpolation Using Siemens S7-1200
(2025-01-01)
Maneerat, Noppadol
;
Wongworrada, Tharathorn
;
Cheypoca, Thepjit
;
Sepsirisuk, Kasemsuk
This research is a continuation of the research on circular interpolation use siemens s7-1200 [1] It presents the movement of 3 axes, $x y z$, as a method of moving in a curve that is controlled by programmable logic control (PLC). In the future research, PLC will be used to control linear movement straightly. The work will be in the original format, but change the equation used to move in a straight line instead.
Some of the metrics are blocked by your
consent settings
Apply PLC to Control 3-Axis Machines
(2025-01-01)
Cheypoca, Thepjit
;
Thaiyai, In
;
Maneerat, Noppadol
;
Narkthewan, Athasart
This report presents a method of using PLC (Programable Logic Control) to control the work instead of the 3-Axis machine position controller. PLC is popularly used in various types of control systems. It has a lot of control capabilities, is efficient, stable, durable, easy to use, and cheap. It is the use of commands to control the work of all 3 axes, 2 axes, and 1 axle. The commands used for moving in both straight lines and curves, and there are other devices that need to be controlled together with the machine that is being controlled.
Some of the metrics are blocked by your
consent settings
Development of a Health Index for Transformer Condition Assessment Using an Online Dashboard
(2025-01-01)
Sripatawasumadee, Kornchet
;
Maneerat, Noppadol
;
Dechothamsathit, Vorawut
;
Kingkham, Sukanya
;
Jeenmuang, Siwakorn
Power transformers are critical components in electrical power systems in the transmission and distribution of electricity. Keeping them in good working condition is necessary to prevent power outages and ensure system stability. Traditional maintenance strategies, such as time-based maintenance, may not always be the best way to avoid problems or use resources efficiently. To improve this, the concept of a Health Index (HI) has been introduced as a systematic method for transformer condition assessment. By integrating various diagnostic data - such as load data, oil analysis, maintenance record, and on-load tap changer (OLTC) parts - into a unified HI score, asset managers can make informed decisions regarding maintenance prioritization and replacement planning. Furthermore, this paper proposes the development of an online dashboard system that facilitates the input, storage, and visualization of transformer health data. This user-friendly platform enables engineers to monitor condition trends in real time and supports strategic maintenance scheduling. The integration of Health Index evaluation with an accessible digital interface enhances the efficiency, transparency, and reliability of transformer asset management practices.
Some of the metrics are blocked by your
consent settings
Glioma Brain Tumor Classification using Transfer Learning
(2024-01-01)
Pilaoon, Pongsak
;
Narkthewan, Athasart
;
Wadlom, Noppanat
;
Varakulsiripunth, Ruttikorn
;
Hamamoto, Kazuhiko
In this research the glioma brain tumor binary classification using transfer learning was introduced. The MRI image from 2 datasets comprised with REMBRANDT and BraTS2021 with increasing number of MRI images was proposed to prevent overfitting problem. MRI images were converted to JPEG format and heavily imbalanced with normal brain image is minority class. Morphological operation was used to remove skeletons and artifacts from brain region. We have introduced Contrast Limited Adaptive Histogram Equalization to preprocess and enhance contrast before classify using various CNNs. To handle imbalanced dataset problem, we proposed image augmentation to increase the number of images and obtain balanced dataset. The various CNNs transfer learning was implemented to classify glioma brain tumor. Finally, the best classifier is InceptionV3 with balanced dataset that obtained accuracy 99.19%, sensitivity 98.83%, and specificity 100% respectively, better than our past research work.
Some of the metrics are blocked by your
consent settings
Automatic Temperature Analysis of an Image Sensor using an Application in a Semiconductor Industry
(2024-01-01)
Wongsomboon, Chanathip
;
Maneerat, Noppadol
;
Thudthong, Jakkrit
;
Sukasem, Sutikamon
;
Yajima, Kuniaki
Manufacturing process improvement is a way to increase the efficiency of production in the process even further. This research is used to change the current work method where employees download oven temperature data of the image sensor in manual CSV file format to analyze and make reports in graph form. The window application is created the data to get the data from the PLC control machine to record temperature data from a CSV file and record it in the SQL database automatically. The web application is also developed to serve as a dashboard for data analysis. It is possible to reduce operating time by 91 percents and can reduce the cost of hiring employees.
Some of the metrics are blocked by your
consent settings
Manufacturing Process Improvement by Barcode Reader using Image Processing
(2024-01-01)
Sukasem, Sutikamon
;
Maneerat, Noppadol
;
Thudthong, Jakkrit
;
Wongsomboon, Chanathip
;
Yajima, Kuniaki
Manufacturing industries get perspective on the efficiency of their production process. This study focuses on improving the cycle time of the work process at the station related to barcode reading. This operation should be of minimal duration to result in shorter cycle times and resulting in increased production volumes while still maintaining quality and reducing production costs. Image processing methodology is applied to reading barcodes instead of using a barcode reader which creates clear image quality along with developing an application using Android Bridge (ABD) and ZXing libraries that can read 1D barcodes in many formats. More essentially, application development by multithreading programming can process barcode reading simultaneously at a time that meets the target cycle time. The result of this study proves that the process of reading barcodes by human work has taken 60 times per job cycle and the reading time was about 29 seconds, becoming reduced to 19.85 seconds, manpower can be reduced by 1 person and production cost as well. Moreover, this implementation eliminates human errors that are likely to occur from scanning barcodes in the wrong position. Therefore, this study has benefited the manufacturing industry achieve significantly increased productivity and efficiency.
Some of the metrics are blocked by your
consent settings
The Experiment of Dielectric Frequency Response of Serviced Aged Distribution Transformer
(2024-01-01)
Posrimahapoch, Purichaya
;
Maneerat, Noppadol
;
Daengdee, Danaiwat
;
Jeenmuang, Siwakorn
;
Pannil, Pittaya
Outdoor Distribution Transformers typically encounter random environments and affect moisture in any ingress ways, e.g., defective breathing, oil leakage, or human error during internal inspection, etc. Such moisture is a very important enemy of the insulation integrity of the transformer. It may cause the failure of the transformer eventually. Therefore, the condition of the transformer insulation needs to be monitored. Dielectric Frequency Response (DFR), also known as Frequency Domain Spectroscopy (FDS), and Polarization and Depolarization Current (PDC) are nondestructive tests providing efficient diagnostic for transformer insulation. The test results can be used to estimate moisture content and oil conductivity. In this paper, the dielectric investigation of a 315 kVA, 22 kV serviced aged distribution transformers, which have been retired for 6 months after being utilized for more than 20 years, was conducted. The experiment results of the DFR and the PDC tests including the investigated mineral oil characteristics (i.e., oil breakdown voltage, moisture content, and tan delta) are reported and analyzed. They should be useful to understand the condition of the transformers.
Some of the metrics are blocked by your
consent settings
The Effect of Insulating Oil Conditions in Transformer Bushing on Dielectric Response Analysis
(2024-01-01)
Srisub, Chanatip
;
Maneerat, Noppadol
;
Rojanasunan, Warisanan
;
Buranaaudsawakul, Techatat
;
Pannil, Pittaya
The bushing is one of the important parts of a transformer. Once the transformer is operated; each transformer part including its bushing starts the degradation mechanism. In some cases, the dielectric strength degradation of the bushing can lead to severe consequences. Thus, the study and diagnosis of the bushing conditions are important. This study aims to investigate the characteristics of the oil-impregnated pressboard bushing under various oil conditions by filling the new mineral oil with a controlled moisture content and letting it reach an equilibrium state to examine the dielectric response of such bushing. To determine the dielectric characteristics of the investigated bushing, A Frequency Domain Spectroscopy (FDS) device was utilized. In the experiment, the dissipation factor, capacitance, and current measurement of the bushing with different water content level were measured. The bushing test object was tested with the frequency range of 1 mHz -1 kHz. The effect of moisture clearly influenced the low-frequency ranges of the FDS. The result will be discussed in the paper.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results