KMITL

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

Browse

Search Results

Now showing 1 - 7 of 7

Some of the metrics are blocked by your
consent settings
Bacterial Colony Counting and Classification System Based on Deep Learning Model
(2026-02-01)
Pintavirooj, Chuchart
;
Bunkum, Manao
;
Vongmanee, Naphatsawan
;
Nampeng, Jindapa
;
Visitsattapongse, Sarinporn
Microbiological analysis is crucial for identifying species, assessing infections, and diagnosing infectious diseases, thereby supporting both research studies and medical diagnosis. In response to these needs, accurate and efficient identification of bacterial colonies is essential. Conventionally, this process is performed through manual counting and visual inspection of colonies on agar plates. However, this approach is prone to several limitations arising from human error and external factors such as lighting conditions, surface reflections, and image resolution. To overcome these limitations, an automated bacterial colony counting and classification system was developed by integrating a custom-designed imaging device with advanced deep learning models. The imaging device incorporates controlled illumination, matte-coated surfaces, and a high-resolution camera to minimize reflections and external noise, thereby ensuring consistent and reliable image acquisition. Image-processing algorithms implemented in MATLAB were employed to detect bacterial colonies, remove background artifacts, and generate cropped colony images for subsequent classification. A dataset comprising nine bacterial species was compiled and systematically evaluated using five deep learning architectures: ResNet-18, ResNet-50, Inception V3, GoogLeNet, and the state-of-the-art EfficientNet-B0. Experimental results demonstrated high colony-counting accuracy, with a mean accuracy of 90.79% ± 5.25% compared to manual counting. The coefficient of determination (R<sup>2</sup> = 0.9083) indicated a strong correlation between automated and manual counting results. For colony classification, EfficientNet-B0 achieved the best performance, with an accuracy of 99.78% and a macro-F1 score of 0.99, demonstrating strong capability in distinguishing morphologically distinct colonies such as Serratia marcescens. Compared with previous studies, this research provides a time-efficient and scalable solution that balances high accuracy with computational efficiency. Overall, the findings highlight the potential of combining optimized imaging systems with modern lightweight deep learning models to advance microbiological diagnostics and improve routine laboratory workflows.
Some of the metrics are blocked by your
consent settings
A Deep Learning Model for Bacterial Classification Using Big Transfer (BiT)
(2024-01-01)
Visitsattaponge, Sarinporn
;
Bunkum, Manao
;
Pintavirooj, Chuchart
;
Paing, May Phu
Identification and classification of bacterial genera and species are very important for medical prevention, diagnosis, and treatment. However, due to microbial diversity and high variability in appearance, the manual classification of bacteria is a challenging and time-consuming task. This paper aims to facilitate such a troublesome task using deep learning techniques. Through the utilization of a deep learning model, specifically a Big Transfer (BiT) combined with graph Laplacian-based data cleaning and weight initialization based-rectified linear unit (WIB-Relu) activation, we have developed an accurate bacteria classification model. We have tested our proposed method on a public dataset of microscopic bacteria images, called the Digital Images of Bacteria Species (DIBaS), and achieved promising results with an accuracy of 99.11%, precision of 99.31%, recall of 99.09%, and F1 score of 99.06%, respectively. Moreover, the proposed bacteria classification performed well regardless of the size of the training data. We investigated its generalizability not only on the original dataset but also on the few shots (5-shots, 2-shots, and 1-shot) and augmented datasets.
Some of the metrics are blocked by your
consent settings
Automated Bacterial Colony Counting on Agar Plate
(2023-01-01)
Bunkum, Manao
;
Visitsattapongse, Sarinporn
In several fields, such as microbiology research, medical diagnostics, and food safety evaluation, bacterial colony counting is extremely important. However, the method of manual counting is time-consuming, labor-intensive, and prone to human error. This research approached these problems by using MATLAB's image processing feature to automatically count the number of bacterial colonies on agar plates. This technique effectively detects bacterial colonies from photos of agar plates by using image analysis algorithms. The images of agar plates were captured while controlling the lighting and adjusting the size to achieve the highest possible image quality. This study encompassed 10 bacterial species, achieving an accuracy of approximately 80%. This level of precision underscores the reliability and effectiveness of our automated system.
Some of the metrics are blocked by your
consent settings
Prototype of Wearable Device for Blood Pressure using Pulse Transit Time
(2021-01-01)
Bunkum, Manao
;
Wanluk, Nutthanan
;
Visitsattapongse, Sarinporn
At present, there is a continuous increase in the number of patients suffering from hypertension in Thailand. and resulted in higher mortality rates as well. with an increasing trend every year Some people with high blood pressure need medication and regular monitoring of their blood pressure to prevent further complications. Most of these are pressure gauges that require a cuff that is wrapped around a patient's upper arm, wrist, or thigh. which is not convenient to carry for patients who need to measure blood pressure regularly This research proposes a prototype of a wearable device for measuring blood pressure using Pulse Transit Time (PTT) by measuring the pulse between the wrist and the index finger of the other hand. and take the pulse movement time to calculate the blood pressure Based on the results of testing prototypes of wearable devices for measuring pressure compared to commercially available pressure gauges. Of the five participants, the prototype of a wearable device for measuring pressure was approximately 94% accurate compared to commercially available pressure gauges. The prototype device can measure blood pressure in real time and is always portable.
Some of the metrics are blocked by your
consent settings
Tele-Operation of Robotic Arm
(2019-11-01)
Bunkum, Manao
;
Vachirasakulchai, Phakjira
;
Nampeng, Jindapa
;
Tommajaree, Ramita
;
Visitsattapongse, Sarinporn
This research is for facilitate the healthcare worker to approach patient that located in distant areas via internet. Also, patient need not to get to the city to see a doctor. Hence, this research will reduce time and cost of traveling. This research is to create tele-control robot arm, use in the operating room, which is controlled by joystick from anywhere. It is separated into 2 parts that is hardware part to design and print 3D robot arm and joystick and software part, which is code to control robot arm also send controlling data via internet. Furthermore, this project will send real-time video from robot arm to controller side. The data is sent between robot arm and joystick by nodeMCU or in this project use two ESP32, one will receive data from joystick and send the data to another for control robot arm. In the section of sending real-time video, this project use Raspberry pi as a device for sending.
Some of the metrics are blocked by your
consent settings
Prototype Modeling of Bed for Bedridden Patients
(2019-01-10)
Bunkum, Manao
;
Reanaree, Parkbhum
;
Wanluk, Nutthanan
;
Visitsattapongse, Sarinporn
One of the most common health risks for bedridden patient is a pressure sore or decubitus ulcers. Pressure sore developed in people who are not able to move or lying in the same position for a long period of time. To solve this problem, a caregiver must change the patient's position every two hours if possible. In addition, the caregiver already has many kinds of care work to assist the patient such as changing clothes, administering medicine, daily health checking etc. This paper presented a design model of the bed used for bedridden patients, including paralysis, individuals with impaired mobility, and the elderly. The bed consists of an automatic bed lift control system and a patient monitoring system. The bed can change the patient's position in left or right tilt by lifting the left or right side of the bed up automatically. The system came with a graphic user interface to communicate with the caregiver or physician. The patient monitoring system including, the heart rate monitor, the body temperature monitor and the blood pressure monitor which are then sent to a home or hospital server. All data can then be remotely monitored by caretaker or physician. The proposed of the bed is designed to better assist the daily life of bedridden patients and caregivers.
Some of the metrics are blocked by your
consent settings
Indirect Measure Voltage and Exposure Time Device for Medical X-ray
(2019-01-10)
Bunkum, Manao
;
Pintavirooj, C.
;
Visitsattapongse, Sarinporn
X-ray machine is used to create an image of diagnosing or treatment by using X-ray beam. X-ray beams are harmful to the body's cells when the radiation dose is high enough. Therefore, the X-ray machine must always be calibrated or test to ensure that the X-ray machine is accurate to keep users safe. In this research presents the design and construction of x-ray testing device. It will focus on measuring the two main parameters of the x-ray machine. Measurement of exposure time (x-ray emission time) and measurements of peak kilovoltage from the x-ray tube. This device has 2 parts, hardware and software. The hardware is the circuit consist of intensifying screen for a radiation receiver and converted energy from x-ray into light energy. The wavelength of the light emitted is in the range of 500-600 nm, then use a circuit of photodiode. It is a semiconductor device that converts light into an electric current. The electric current is a full-wave rectification waveform corresponding to the 100 Hz high voltage supply of the x-ray tube. Take the signal from the electric current to filter circuit for reducing noise. And then take the signal to the microcontroller (Arduino). Arduino is used for taking the signal to process in Visual Studio program to measure exposure time and peak kilovoltage of x-ray, which can be measured and processed immediately. The waveform is digitized, and peak detected with Arduino. The number of peaks is then converted to exposure time, i.e. one peak corresponds to 10 milliseconds. The result, exposure time and peak kilovoltage of x-ray, will show on window form application in Visual Studio program.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results