KMITL

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

Browse

Search Results

Now showing 1 - 10 of 81

Some of the metrics are blocked by your
consent settings
Smart Cane for Assisting Visually Impaired People and the Blind
(2021-01-01)
Kramomthong, P.
;
Pintavirooj, C.
;
Paing, May Phu
The limited mobility of the visually impaired and blind makes daily activities such as avoiding obstacles, traveling, crossing the street, and dealing with an emergency difficult. Currently, there are active studies and developments about devices and technologies that increase deftness daily and travel independently. In this paper, we combine various functions into one device consisting of obstacle detection, navigation, and emergency calls to increase the safety and travel mobility of visually impaired people and the blind. The laboratory experiment results of whole functions were successful, and the device can alert the user with sound and vibration.
Some of the metrics are blocked by your
consent settings
Vascular Extraction by using matched filter on retinal image
(2020-02-24)
Kanjanasurat, I.
;
Purahong, B.
;
Pintavirooj, C.
;
Benjangkaprasert, C.
This paper presents a vascular extraction on the retinal image by using matched filter. It uses the approximation to calculate a matrix and convolved with retinal images. Also, the proposed method tested with two widely used databases, including DRIVE and STARE. The results of vascular extraction have an average accuracy of 0.944 in DRIVE and 0.936 in STARE. The sensitivity of DRIVE and STARE, which a parameter for detect vessel correctly was achieved 0.73 and 0.753, respectively. In addition, this algorithm has a high performance and fast algorithm.
Some of the metrics are blocked by your
consent settings
Approximation of the maximally flat filter by using Bézier curve with an exponential function
(2020-02-24)
Purahong, B.
;
Kanjanasurat, I.
;
Sithiyopasakul, P.
;
Chutchavong, V.
;
Pintavirooj, C.
This paper presents a design of filter by using Bézier curve with an exponential function. This paper used the advantage of The Bézier curve which had ability for approximation and an exponential function which had the adaptable parameters of the polynomial. It can adjust the characteristic of frequency response for the best performance. The simulation results of various setting show the frequency response, step response. The comparison of response between the Bernstein filter and Butterworth filter in order two show that the rise time of Bernstein filter better than Butterworth filter and Bézier curve filter has not overshoot. Furthermore, the stability Nyquist criterion has been used to guarantee the stability of the transfer function.
Some of the metrics are blocked by your
consent settings
Neurofeedback System
(2019-11-01)
Lochotinunt, Chanin
;
Suwanpathumlert, Nattasasi
;
Masawat, Nattachai
;
Airphaiboon, Surapan
;
Pintavirooj, C.
Nowadays, reading is one of the essential factors in learning. However, there are problems which make reading ineffective or time-wasting on comprehending the points read. The most efficient method to read is associated with our concentration. Practicing concentration allows us to control this factor. In this study, neurofeedback is applied in this situation together with the Neurosky Mindset measuring Electroencephalogram (EEG) to indicate the concentration level by the lamp which connects to the Arduino board informing the user about their state of concentration from the output. The output illustrates that the light will dim when the concentration level drops below the threshold. Making lamp's light brighter, you need to adjust your concentration level to be higher than a threshold. Moreover, the concentration level output will be demonstrated on the smartphone application.
Some of the metrics are blocked by your
consent settings
Intelligent glove for sign language communication
(2019-11-01)
Navaitthiporn, Nitipon
;
Rithcharung, Preeyarat
;
Hattapath, Phitnaree
;
Pintavirooj, C.
Communication is very important in daily life while many people in Thailand cannot communicate by talking. On the other hand, they can communicate only sign language. The sign language used in a specific group of people, but other people cannot understand. Therefore, we decided to do a project about glove for sign language communication. This research created a hand glove for deaf and mute people to provide better communication between disabling and normal people. We applied computer programming by used the flex sensor and GY-521 Module. The flex sensor has measured the bent of fingers and generated an analog output. GY-521 Module is use for measured the direction and movement of the hand. After got data from both sensors, it will send to Arduino IDE converted all the data to alphabet and text before converted to speech. Then we tested the accuracy of the glove, it has accuracy about 70-100% which depends on another factor. From this process, we got a hand glove for sign language communication. This glove will help deaf and mute people to communicate more efficiently.
Some of the metrics are blocked by your
consent settings
Force Sensor for Measuring Plantar Pressure
(2019-11-01)
Teechot, Thitirat
;
Maneerat, Areerat
;
Sansutnanont, Inarm
;
Ornketphon, Ornnattida
;
Treebupachatsakul, Treesukon
A foot is the importance organs that bear the weight of the entire body. Nowadays, the improper weight distribution of the sole causes damage to the body such as plantar fasciitis and the incidence of pressure injury in the sole, which lead to long-term effect. Shoes that are suitable to the person's feet condition including using shoe accessories in each person can help to relieve initial symptoms. However, the weight that presses to each part of the sole is different. Therefore, measured the pressed weight of each part of sole can be used to create the proper shoes accessories, which help balancing the force for individual foot condition. This research aims to improve the shoe accessory product by using the Fore sensor with the display report of graphical user interface color map for measuring the real-time pressure on moving plantar. The data from sensor was wirelessly sent to the computer, which then displayed the image results. From the result of measured pressured on planar indicated that our Force sensor padder can help patient correctly control the weight distribution of the body to make the muscles of legs and feet to function effectively.
Some of the metrics are blocked by your
consent settings
Image Processing for X-ray Calibration Phantom
(2019-01-10)
Wanluk, Nutthanan
;
Pintavirooj, C.
;
Treebupachatsakul, T.
Medical device calibration is the process of ensuring that there is accuracy before using. X-ray imaging device is one of the high-risk medical devices that must be calibrated. The calibration process required these values to be measured; center ray, focal object distance (FOD), resolution, and linearity of the imaging system. But the devices used to measure each of these are expensive. In this paper, a design of the x-ray calibration phantom that is affordable and yet effective is presented. An aluminum rectangular phantom consists of a center ray calibration unit, focal object distance (FOD) calibration unit and Linearity calibration unit. The x-ray image of all the phantom unit can be analyzed automatically by using the digital image processing.
Some of the metrics are blocked by your
consent settings
A comparative study of 3 deep learning models for Pap smear screening
(2019-01-10)
Promworn, Yuttachon
;
Pintavirooj, C.
;
Piyawattanametha, Wibool
This work presents a comparative study of automated screening procedure for Pap smear with deep learning technology. Three convolution neural network models (AlexNet, densenet161 and resnet101) were employed for detecting the presence of cervical precancerous or cancerous cells from Pap smear database. The study compares accuracy, sensitivity, specificity, and computation time for each deep learning model. The best model is the densenet161 due to its high sensitivity and accuracy which are key factors in an automated Pap smear screening procedure to offer the best early detection of cervical cancer to better treatment outcomes.
Some of the metrics are blocked by your
consent settings
Comparison of Sampling Methods for Imbalanced Data Classification in Random Forest
(2019-01-10)
Paing, May Phu
;
Pintavirooj, C.
;
Tungjitkusolmun, Supan
;
Choomchuay, Somsak
;
Hamamoto, Kazuhiko
Imbalanced data classification is a serious and challenging task for most of the medical image diagnosis applications. They usually produce a larger number of false samples compared to the actual ones. That is the number of samples for the class of interest (minority) is significantly fewer than other types of class (majority). The classification performed using such data is called imbalanced data classification. As a consequence, the learning model bias towards the majority class and fails the classification of the minority class. Data sampling and ensemble methods are common ways to compensate for this issue. Random forest (RF), an ensemble of multiple decision trees, is very famous in both of the classification and regression problems because of its robust and accurate predictions. However, it also suffers class bias in the imbalanced data classification problems. This paper proposes and compares different sampling methods to solve the imbalanced data classification in RF.
Some of the metrics are blocked by your
consent settings
Screening Computer Software for Peripheral Vestibular Dysfunction
(2019-01-10)
Wongwaraputh, Thanapol
;
Pintavirooj, C.
;
Mahasitthiwat, Visan
Vestibular system is balance system of human body. They provide Vestibulo-Ocular Reflex (VOR). Peripheral vestibular dysfunction is one the reasons causes vertigo. There is the diagnosis called Head Impulse Test (HIT). A doctor turns patient's head to left and right rapidly and observes an eye movement duration. In this paper, we develop computer software for both doctors, for supporting their diagnosis and patients, for screening themselves before going to see doctor. This project is creating a computer software using Python language with libraries. The software use OpenCV for image processing: Face detection and finding iris position in eye region and Dlib: Facial landmarks detection including the eye region. The Software requires the HIT video to detect patient's face and iris while face is turning left and right. The iris position is calculated compare to eye landmarks position and displayed by graph of left and right iris movement. The iris movement duration can be used to determine whether a patient has peripheral vestibular dysfunction. Patients can take the video and send to a doctor to diagnose. The software will be furthered developed on the mobile phone for patients to be used at home before going to see doctor.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results