KMITL

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

Browse

Search Results

Now showing 1 - 10 of 72

Some of the metrics are blocked by your
consent settings
Automated Resource Management System Based upon Container Orchestration Tools Comparison
(2023-01-01)
Purahong, B.
;
Sithiyopasakul, J.
;
Sithiyopasakul, P.
;
Lasakul, A.
;
Benjangkaprasert, C.
The goal of this article is to study and analyze the container orchestration technology Kubernetes, Docker Swarm, and Apache Mesos by performing performance evaluations and inspecting how many requests and responses the server can handle. Due to the fact that managing information system resources is a challenge in terms of performance, usability, reliability, and the cost of information resources. Some orchestration tools cannot automatically allocate resources depending on the scope of the information system resource management. This leads to allocating resources more than the needs of system requirements, resulting in excessive costs. Therefore, this article proposed testing the system by measuring its effectiveness using a structured process by examining measurement variables such as the number of requests per second, number of responses to requests, and resource extension period using all three-orchestration technology. From the testing and analysis of all three variables as mentioned, it is possible to know the efficiency of the Kubernetes technology in such a similar environment and compared it with other orchestration tools like Docker Swarm and Apache Mesos orchestrator. For Kubernetes, Docker Swarm, and Apache Mesos, the mean value of its handling average request per minute is 30,677.25/min, 33,688.67/min, and 29,682.6/min, respectively. Swarm performed better in aspects of handling requests per minute by 9.35% of the difference when compared to Kubernetes and by 12.64% when compared to Apache Mesos. However, there are several things which should be taken into consideration because each orchestration tool has its own strong and weak points. The testing experiment could display a piece of information on the dashboard for visualization and analytic purposes and there is an elaboration at the end of when to use which container orchestration tool to suit the business proposes the most.
Some of the metrics are blocked by your
consent settings
Comparison of logistic regression and artificial neural network model for apron allocation assignment
(2023-01-01)
Purahong, B.
;
Teerapanpong, S.
;
Satayarak, N.
;
Benjangkaprasert, C.
Management of the parking apron is one of the most essential airport ground service operations for flight operations to run smoothly. Effective airport ground service management will have a direct effect on the cost and duration of flights. Therefore, in this paper, we address the issue of using machine learning techniques, such as logistic regression analysis and artificial neural network (ANNs) models, for classified targets of stand locations assignment of an arriving flight. Also, this could assist ground controllers to assign apron allocation and improve the efficiency and predictability of airport operations which reduce the time required for airport ground processing to increase flight capacity. In order to evaluate the performance of the proposed method, simulation results reveal that ANN has the lowest error rate and the highest accuracy. Therefore, ANN is the effective classification technique for this data set.
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
An Application of an Adaptive Signal Processing Scheme for a QPSK Signal Demodulation
(2022-01-01)
Inban, P.
;
Punchalard, R.
;
Loedwassana, W.
;
Benjangkaprasert, C.
An adaptive digital signal processing scheme applied for a digital communication has been presented in the press. The model of an ANC is utilized to demodulate in a coherent detection scheme for a received QPSK signal. The coefficients of the system will be updated by the least mean square (LMS) algorithm that is controlled in the adaptation sequence according to the symbol duration of the received signal. Since such a manner is performed, the system is similar to integrate and dump (I&D) correlator in behavior. The analysis and simulation results have implied that the desired information signal can be recovered from the received signal by the proposed scheme with the same performance as the conventional optimum demodulation.
Some of the metrics are blocked by your
consent settings
An Improved RLS-based Interference Cancellation
(2022-01-01)
Inban, P.
;
Punchalard, R.
;
Benjangkaprasert, C.
An improved algorithm for mitigating the effect of power line interference in electrocardiogram (ECG) recording systems is presented. The proposed algorithm includes an interference detector (ID), an interference fundamental frequency estimator (IFFE), and an interference estimator (IE). The ID is used to evaluate the existence of the interference before recording. If it is present, the IFFE and IE are employed in the next steps. In the absence of interference, the observed signal is directly sent to the recorder and monitor. The presence of the ID can improve the performance of the system in terms of computational efficiency and system speed. The IFFE can track the variation of the interference frequency. Extensive computer simulations were run to demonstrate the performance of the proposed system.
Some of the metrics are blocked by your
consent settings
Sine-Squared Pulse Approximation for Matched Filter Design Using Generalized Bessel Polynomials and Particle Swarm Optimization
(2022-01-01)
Chutchavong, V.
;
Anuwongpinit, T.
;
Pumee, T.
;
Benjangkaprasert, C.
;
Janchitrapongvej, K.
This paper presents the study of mathematical characteristics of generalized Bessel polynomial that can be applied to approximate a sine-squared pulse for designing matched filters in communication systems. The proposed pulse can be designed by using the transfer function, in which the numerator is the five pairs of a transmissions zero pairs, and the generalized Bessel polynomial is used as the denominator. A parameters of generalized Bessel polynomials can be adjusted by particle swarm optimization to find the best parameter value. From the simulation results can be found that a parameter can be adjusted. A proposed pulse is close to the ideal response in mainlobe, and one sidelobe to four sidelobes with stability, which outperformed previous research.
Some of the metrics are blocked by your
consent settings
On the Study of Thai Music Emotion Recognition Based on Western Music Model
(2022-01-01)
Satayarak, N.
;
Benjangkaprasert, C.
The mood of the song could be identified by tracking the listener's emotion. The research in this area is growing significantly at the present. There are many research studies in western music, but a few in Thai music. Therefore, in this research, Thai songs were chosen because the Thai is a native language and Thai songs are quite popular in the region of research. This research is divided into 2 parts. First, Thai music was evaluated by the set of a system based on western music training settings. By using valence-arousal values, multiple linear regression, and k-nearest neighbors to represent the emotional annotations from the music. As a result, the highest f-measure of Thai music from multiple linear regression by ALL model was 41% and the f-measure of western music from multiple linear regression by No Tempo model was 51%, which was very different because ALL model in western music has lower efficiency than other models. Second, we measured the mood of 125 Thai popular songs and used valence-arousal (energy) values from Spotify API to investigate the results. In this research we used multiple linear regression (MLR) and support vector regression (SVR). Experimental results show that the multiple linear regression provides the highest accuracy of 61.29% with the precision of 65%, recall of 61%, and f-measure of 60% which is more than support vector regression.
Some of the metrics are blocked by your
consent settings
Direct-Lattice Adaptive Notch Filter for Frequency Estimation and Tracking
(2022-01-01)
Inban, P.
;
Punchalard, R.
;
Benjangkaprasert, C.
This paper presents a direct-lattice adaptive notch filter (DLANF) for frequency estimation and tracking. The proposed filter is the cascade of an all-pole direct form structure filter with an all-zero lattice predictor. The normalized gradient algorithm is used to adjust the filter parameter. This technique outperforms some conventional adaptive filters in terms of convergence time and provides a small mean square error (MSE). Computer simulations are conducted to show the superiority of the proposed filter.
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.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results