Sooraksa, Pitikhate

Preferred name

Sooraksa, Pitikhate

Alternative Name

Sooraksa, P.

Main Affiliation

School of Engineering

pitikhate.so@kmitl.ac.th

Now showing 1 - 10 of 98

Some of the metrics are blocked by your
consent settings
A practical position-based visual servo design and implementation for automated fault insertion test
(2014-01-01)
Banlue, Tassanai
;
Sooraksa, Pitikhate
;
Noppanakeepong, Suthichai
This paper presents the design and implementation of a practical visual servo. The visual servo has been designed for pose correction of an end-effector that is placed wrongly away from the test point on a printed circuit board (PCB). It is widely acknowledged that the error could be attributed to the connecting joints of robot arms, angular errors, geometric model, and/or camera projection model. In the automated fault insertion test (AFIT), the typical difficulty encountered by a robot is to servo and place the probe tip accurately on the targeted test point, i.e., the conductive pad on the PCB. Conventionally, touch and sense with a probe tip has been utilized. Upon detection of a failure, the visual servo is triggered and the robot literally looks through a camera and re-attempts with the use of visual information from the camera. Currently, no clearly defined specifications in carrying out feature extraction exist and thereby the test point detection as it is not cost-effective to designate part of PCB footprint as the test point separately from the main design to accommodate visual sensing. As a result, various kinds of test points have been implanted into PCB industrial design. This research work requires building of a custom knowledge base of the test point features to support image recognition. Furthermore, the operational factors in industrial manufacturing, e.g., head structure maintenance, the replacement of end-effectors and the changes of projection parameters caused by hardware adjustment, impact the accuracy of the probe placement. These factors cause the original geometric model to shift from the original configuration and thus errors. This research paper proposes the practical design of a closed-looped visual servo to address the issues of precision error, image feature extraction, and manufacturing factors. Besides, the paper details the findings from the design phase to the implementation phase. © 2014 Institute of Control, Robotics and Systems and The Korean Institute of Electrical Engineers and Springer-Verlag Berlin Heidelberg.
Some of the metrics are blocked by your
consent settings
A discovery of sequential attack patterns of malware in botnets
(2010-12-01)
Rosyid, Nur Rohman
;
Ohrui, Masayuki
;
Kikuchi, Hiroaki
;
Sooraksa, Pitikhate
;
Terada, Masato
More than 90 independent honeypots have observed malware traffic at the Japanese tier-1 backbone. Typical attacks were made by multiple servers, coordinating to send many kinds of malware. T his paper aims to discover some frequent new sequential attack patterns of malware. It is not easy to identify particular patterns logs of one year because the volume of dataset is too large to investigate one by one. To overcome the problem, this paper proposes data mining algorithm, the PrejixSpan method. We implement the PrejixSpan algorithm to analyze the malware footprints and show the experimental result. The result of analysis shows that the attacks are performed by multiple sequential attack patterns within a short amount of time. ©2010 IEEE.
Some of the metrics are blocked by your
consent settings
A geno-hydra control system: Design and tuning hybrid controller based on hydra control structure by using genetic algorithms
(2006-12-01)
Sanornoi, Nitiwat
;
Purahong, Boonchana
;
Sritheerawirojana, Uthai
;
Sooraksa, Pitikhate
This paper shows how to design the hybrid control system based on hydra control structure by introducing two design strategies which are as following: Double head and Line up. These two strategies use Genetic Algorithms to improve parameters in control system and they also situate the Challenge and Best-selection processes which are the methods to compare the efficiency of the system after they have been genetically calculated. In order to select an appropriate control system in each layer, the simulation's results in the end will show the test with Non-linear plant to show the efficiency of control system after it has been developed by designing and tuning process. © 2006 IEEE.
Some of the metrics are blocked by your
consent settings
Artificial intelligence based on fuzzy behavior for game programming
(2004-01-01)
Sanornoi, Nitiwat
;
Sooraksa, Pitikhate
This paper applies the behavior-based control for mobile robots to design the artificial-intelligent characteristics of game programming in order to reduce the complexity of the intelligence features of the enemies in a game. The artificial intelligence in this paper composes of fuzzy system for creation of the natural behavior. This fuzzy model employs Takagi-Sugeno's methodology for building program modules. The character described in the model herein is the enemy of 'Mage in the Demon Zone' game. Copyright 2004 ACM.
Some of the metrics are blocked by your
consent settings
Design of a cyber-physical system using STEM: Chicken egg incubator
(2019-07-01)
Tangsuknirundorn, Pirapat
;
Sooraksa, Pitikhate
In this paper, STEM approach to study, design and implement chicken egg incubator as a cyber-physical system is demonstrated. In science viewpoint (S), bringing a life to earth can provide magnificent feeling that inspires students to learn more about life sciences. In views of technology (T), the students learn how to design and use micro-controllers, sensors and other components. Specifically the students also develop programming skills in controlling optimal ventilation, temperature and relative humidity for incubators in order to hatch chicken eggs. In Engineering and Mathematically (EM), Kalman filter is adopted to estimate the states from a series of noisy measurements. According to our experiment, based on the survey questionnaire, the learning outcomes are satisfied.
Some of the metrics are blocked by your
consent settings
Hybrid fuzzy-conventional method to improve 360-degree performance appraisal
(2016-08-16)
Sooraksa, Nanta
;
Sooraksa, Pitikhate
A diagnostic tool used in human resource management for evaluation and prediction of employee performance is 360-degree performance appraisal. Recently, the effectiveness of the tool is suspicious about validity and reliability in case of unfair weighting and subjective data. This paper proposes a method to enhance the effectiveness of the tool by using a hybrid approach of fuzzy logic and conventional development. Contribution of the paper is highlight on assigning eigenvalues as natural weights obtained from the questionnaire development to be membership functions for the fuzzy model. The proposed method provided in this work helps improve survey and software for human resource management (HRM).
Some of the metrics are blocked by your
consent settings
Simple self-instructional modules based on chaotic oscillators: Few blocks generating many patterns
(2011-01-01)
Klomkarn, Kitdakorn
;
Sooraksa, Pitikhate
Chaotic circuits have been widely used in the teaching of nonlinear dynamics disciplines, where a common practice is pedagogically based on the circuit point of view. Chua's circuit is the most popular platform for the demonstration of its components with rich dynamical patterns. However, engineering students majoring in control systems are more familiar with feedback systems rather than physical electronics with nonlinear components. This may lead to some difficulty in understanding the nonlinear properties of Chua's circuit, at least on first sight. This paper provides an alternative approach to teaching and learning chaotic oscillators by using the inherent understanding of feedback systems with simple modules at the undergraduate level. Utilizing the idea of chaotification, which means to make a nonchaotic module chaotic, the modules consist of only four blocks yet can generate more than thirty types of chaotic patterns via their various combinations. Conceptually, the blocks can be assembled as various mixed-mode chaotic circuits. Functionally, the blocks are easy-to-use in a Simulink-like fashion. Structurally, they are a LEGO-like educational kit. With low-cost implementation employing a few op-amps for each block, the newly proposed modules are simple, self-instructional and suitable for teaching and training students in school laboratories and in experimental environments. © 2011 World Scientific Publishing Company.
Some of the metrics are blocked by your
consent settings
Development of salt-sensing system for jellyfish desalting process
(2020-01-01)
Rakmae, Samak
;
Sooraksa, Pitikhate
;
Pornchaloempong, Pimpen
In the seafood industry, a large amount of salt is added to preserve seafood products. During processing, it is necessary to desalt the products for the sake of customers' health. Unlike a large-scale factory, many small enterprises lack tools and methods for desalting and measuring the efficiency of the desalting process. We have developed a rapid prototype salt-sensing system that can measure the desalting efficiency. Dried salted jellyfish are used as testing materials to evaluate the system. The rapid prototype comprises a microcontroller, a wire, and a liquid crystal display. Using a simple mapping between electrical conductivity and actual data obtained from the measurement of samples, the sensing system is successfully calibrated. A method of desalting the salted jellyfish material is also proposed. This desalting method and the newly developed simple sensing system for the desalting process are expected to make a significant contribution to the seafood processing industry.
Some of the metrics are blocked by your
consent settings
Associate rule minimization using boolean algebra set function
(2014-01-01)
Deekumpa, Pornsak
;
Sooraksa, Pitikhate
Associated rule mining has become a common subject in data mining research field that is very popular used for marketing basket analysis. The discovery knowledge pattern mined can provide insight to the data holder as well as be invaluable in important task, such as decision making and strategic planning. This paper presents an associated rule mining technique that significantly helping for improvement of the decision making or planning. As a minimization mining strategy, we adopt the minimization using algebra set function and association rule mining methods. Our goal is to minimize the number of associated rule. This paper is of reviews preliminaries method presented a minimization algorithm and also tested with the well known data. The experimental results also show that our algorithm is an efficient method one. © 2014 IEEE.
Some of the metrics are blocked by your
consent settings
Credit scoring using least squares support vector machine based on data of Thai financial institutions
(2007-07-03)
Worrachartdatchai, Usanee
;
Sooraksa, Pitikhate
The quantitative method known as credit scoring has been developed for the credit assessment problem. Credit scoring is essentially an application of classification techniques, which classify credit customers into different risk groups. The Financial institutions are being more and more obliged to build credit scoring models assessing the risk of default of their clients. Support Vector Machine is a promising new technique that has recently emanated and become popular for data classification. Least Squares Support Vector Machines (LS-SVM) are re-formulations to the standard SVMs. The cost function is a regularized least squares function with equality constraints. The solution can be found efficiently by iterative method like the conjugate Gradient algorithm. Then in this paper, Least Squares Support Vector Machine is considered by approaching to the credit scoring with the data of Thai financial institutions. The optimum model will be able to divide the group of customers into four groups: very good, rather good, suspiciously bad and very bad with high accuracy.

Sooraksa, Pitikhate

Filters

Settings

Sort By

Results per page