Search Results

Now showing 1 - 6 of 6

Some of the metrics are blocked by your
consent settings
Comparison of logistic regression and random forest algorithms for airport's runway assignment
(2023-01-01)
Kanjanasurat, I.
;
Jungsuwadee, W.
;
Lasakul, A.
;
Benjangkaprasert, C.
Various automation systems are currently developed using machine learning techniques. It is used to predict and decide on numerous complex tasks in order to reduce the likelihood of human error. Logistic regression is one of the most widely employed machine learning (ML) algorithm. In this study, the accuracy of logistic regression was compared to that of random forest for the assignment of Suvarnabhumi Airport runways to arriving aircraft. The accuracy of the logistic regression model was determined to be 82%, while the accuracy of the random forest model was 77%. Logistic regression was found to be more precise for predicting the appropriate runway to assign to arriving aircraft.
Some of the metrics are blocked by your
consent settings
Classification of Overlapping Eggs Based on Image Processing
(2022-01-01)
Purahong, B.
;
Krungseanmuang, W.
;
Chaowalittawin, V.
;
Pumee, T.
;
Kanjanasurat, I.
This paper presents a method for classifying the overlapped eggs and counting the number of eggs on the conveyor belt using image processing techniques. The image was acquired by a webcam camera that connected to the computer and then rescaled. The image was then converted to grayscale and noise was reduced using a Gaussian blur filter. Otsu's Binarization is used to convert the image to binary. The binary image is then subjected to morphological operations. Following that, using the Watershed Algorithm, separate the egg's overlapped area. Finally, the prepared image is ready to be counted using the contour matrix method. This method independently classifies each egg segmentation and can count up to 18 eggs per frame with a processing time of less than 1 second.
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
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
The comparison of Faster R-CNN and Atrous Faster R-CNN in different distance and light condition
(2020-02-24)
Srijakkot, K.
;
Kanjanasurat, I.
;
Wiriyakrieng, N.
;
Benjangkaprasert, C.
This paper presents the comparison of Faster R-CNN and Atrous Faster R-CNN, which detection model, in the different distance and light condition. Also, the dataset for model training is COCO, and the classification model is residual network. The parameter for decision the performance of the model is Mean Average Precision (mAP). The results from an object resolution at 1024x768 of Faster R-CNN at 3 meters in the evening achieved mAP 1.000. Besides, the mAP at 5 meters and 8 meters were 0.798 and 0.760, respectively. The same resolution as previous, the results of Atrous Faster R-CNN at 3 meters in the evening presented mAP 1.000. Also, the mAP at 5 meters and 8 meters were 1.000 and 0.960, respectively. In addition, Atrous Faster R-CNN had better accuracy than Faster R-CNN with appropriate range and brightness from the period of the day for real-life usage.
Some of the metrics are blocked by your
consent settings
Bernstein polynomial and rational Bézier curve for blood pressure simulation
(2017-02-08)
Kanjanasurat, I.
;
Chutchavong, V.
;
Pirajnanchai, V.
;
Janchitrapongvej, K.
This paper presents blood pressure waveform simulation using the Bernstein polynomial model, Bézier-Bernstein model, and Rational Bézier-Bernstein model. All mathematical models can generate the blood pressure waveform which is similar to the normal blood pressure waveform. Moreover, all mathematical models can simulate a normal blood pressure waveform as well. As the results, the Rational Bezier-Bernstein model is a simple form, low order, easy to implement in the microcontroller.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results