Search Results

Now showing 1 - 4 of 4

Some of the metrics are blocked by your
consent settings
Real Time Diagnosis of Neonatal Jaundice using Machine Learning
(2025-01-01)
Akarapanuvitaya, Napat
;
Pintavirooj, Chuchart
Neonatal jaundice, a condition commonly found among newborns, usually requires invasive and timely methods for diagnosis to prevent further complications. This research presents a real-time diagnostic system for neonatal jaundice using machine learning and image processing techniques. The system utilizes a dataset of neonatal images, which undergo preprocessing to extract relevant features. Features, including color values from different color spaces, are analyzed using multiple machine learning models, such as XGBoost, CatBoost, Support Vector Machines (SVM), Random Forest (RF), and LightGBM. These models are trained and evaluated for their predictive performance. A user-friendly graphical user interface is developed to enable real-time diagnosis, implemented on a Raspberry Pi device equipped with a webcam to acquire real-time image capture and apply image processing. The system demonstrates the potential for accessible and reliable neonatal care solutions.
Some of the metrics are blocked by your
consent settings
Embedded foot plantar classification system using Raspberry Pi
(2018-05-30)
Niemhom, Anyamanee
;
Keatsamarn, Tanapon
;
Pintavirooj, Chuchart
Foot plantar classification is crucial to prevent dangers to patient's health that originated from an abnormal type of foot. When patients comprehend their type of foot, they will be able to form personal insole to prevent a hazard. On the contrary, some patients who ignore their risk will possibly have the problem. We design the system to classify type of foot by measuring foot pressure and foot curvature. For the software, we use webcams to capture the foot images that will be further processed by Raspberry Pi with OpenCV and color coding which correspond to foot pressure. For the hardware system, we use the component which is inexpensive and easily available. The hardware structure is composed of steel as a base where the transparent acrylic plate and glossy white paper is placed on. The black polypropylene sheet covering on the uppermost is used to block light from outside. Aligned on the side of the transparent acrylic plate LED strip is used for light source for the system. Underneath the steel base there are four webcams which is used to record feet images (two webcams for each foot). The images are sent to Raspberry Pi for image processing and displaying. The system is able to classify three types of the foot for patients including normal foot, high arch foot, and flat foot.
Some of the metrics are blocked by your
consent settings
Foot plantar pressure measurement system using optical sensor
(2017-02-21)
Keatsamarn, Tanapon
;
Pintavirooj, Chuchart
Foot pressure measurement is necessary for classifying disorders of the foot and designing insole for individual person. This present work uses optical sensor (webcam) to capture the foot-pressure image. Image processing on Raspberry Pi with OpenCV library is applied to process image and color coding corresponding to foot pressure. The hardware system uses the transparent acrylic plate and uses the steel as a base of the acrylic plate. The glossy white paper is placed on the top of the transparent acrylic plate covering with polypropylene sheet on the system to block light from outside. Light in the system is released from LED strip entering from a side of the acrylic plate. The scattered light occurred in acrylic plate from the foot pressing were recorded by the webcams. The four webcams placed below facing upward for collecting images (2 cameras for each foot) and sending to Raspberry Pi. Raspberry Pi will perform image process including image enhancement and image stitching and image displaying. The result can be used to classifying foot type and find methods to prevent the occurrence of for disorders.
Some of the metrics are blocked by your
consent settings
Detection of disk drug orientation for disk diffusion susceptibility testing
(2011-12-01)
Okowat, Thitikarn
;
Taertulakarn, Somchat
;
Samosornsuk, Seksun
;
Pintavirooj, Chuchart
At the present, the microbiological infection is one of the most significant issues in the global. The medical laboratory diagnosis, microbiology, is the most popular way to identify a type of microbiology which is infected-source. Moreover, there are a few microbial prognoses to support a medical treatment. It is effectively controlled by antibiotic management such as Disk diffusion antimicrobial susceptibility testing, Kirby Bauer AST. This technique is well-known in all microbiological laboratories. This study was the development of interpreting system for antimicrobial susceptibility testing by the disc diffusion technique with automatically measures and interprets inhibition zone diameter. The operated system has comprised electronic part; optical devices, video capture part, and software which manages and analyses all processes. The technology of this system was uncomplicated, effective cost and potential automated test. The disk detected-process and measured process; pre-process, were operated via image processing steps such as image smoothening, edge detection, template matching. The output of this part was sent to the next sections, data correction, interpretation and report, respectively. © 2011 IEEE.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results