Jearanaitanakij, Kietikul

Preferred name

Main Affiliation

School of Engineering

kietikul.je@kmitl.ac.th

Now showing 1 - 10 of 11

Some of the metrics are blocked by your
consent settings
Improving the running time of the nearest neighbor algorithm
(2013-12-01)
Chompupatipong, Nattakon
;
Jearanaitanakij, Kietikul
Nearest neighbor algorithm is a well-known method, in pattern recognition, for classifying objects based on the nearest examples in the feature space. However, it's major drawback is the sequential search operation which calculates the distance between the probing object and the entire set of the training instances. In this paper, we propose a novel method to accelerate the searching operation in the nearest neighbor algorithm. Our method consists of two main steps; creating the reference table and searching the nearest neighbor. Reference table of the training instances is created once in the initial phase and referred periodically by the searching step. Surprisingly, this reference table can drastically reduce the searching time of the nearest neighbor algorithm on any feature space. The experimental results on five real-world datasets from the VCI repository show a remarkable improvement on the searching time while the accuracy is still preserved. © 2013 IEEE.
Some of the metrics are blocked by your
consent settings
Predicting Short Trend of Stocks by Using Convolutional Neural Network and Candlestick Patterns
(2019-10-01)
Jearanaitanakij, Kietikul
;
Passaya, Bundit
Candlestick chart pattern is a technical tool that encapsulates the price of the asset for multiple time frames into a single price bar. The expertized trader can predict the price trend of the asset by looking at the pattern of some adjacent candlesticks. This paper proposes the architecture for predicting the short trend of the stocks by using the convolutional neural network and the candlestick patterns. The experiments are conducted with a set of candlestick pattern images collected from various stocks in the stock exchange of Thailand (SET). Each image captures six to twelve adjacent candlesticks. The experimental results indicate that the proposed method can correctly predict the short trend for most stocks with acceptable accuracy. In addition, the proposed architecture achieves better accuracy and training time than that of the well-known architecture, ResNet-18.
Some of the metrics are blocked by your
consent settings
Improving Particle Swarm Optimization by using incremental attribute learning and centroid of particle's best positions
(2017-11-03)
Srimakham, Sornnarong
;
Jearanaitanakij, Kietikul
Particle Swarm Optimization (PSO) is a powerful algorithm that can search a solution for a function which contains a large number of peaks and valleys. However, PSO might encounter a difficulty when the function gets more complex or the number of attributes (dimensions) grows larger. This paper proposes a modification of PSO by using the incremental attribute strategy along with the centroid of particle's best positions to avoid the local minima which can easily occur in a multimodal problem. The experimental results from four standard benchmarks show that the proposed method can improve PSO in terms of optimality and stability when compared with the conventional PSO and another incremental attribute-based PSO.
Some of the metrics are blocked by your
consent settings
Improving ID3 algorithm by ignoring minor instances
(2018-07-02)
Kaewrod, Nicha
;
Jearanaitanakij, Kietikul
Among various classification algorithms, ID3 is one of the most widely used and well-known tools that generates an efficient decision tree. Nevertheless, ID3 is too rigorous in generating the decision rules. As a result, the final decision tree may carry too many decision rules. Some of these decision rules may have very low number of instances which do not make significant change to the classification accuracy. The aim of this paper is to propose an approach to relax the rigorousness of the conventional ID3 algorithm by ignoring minor instances so that the resulting decision tree will have the lower number of depths yet produce promising accuracy. The proposed algorithm is examined on six datasets from UCI repository and Weka. The experimental results indicate that the proposed algorithm not only significantly reduces the maximum number of depths of the decision tree, but also retains the classification accuracy in the satisfying level. Moreover, the training time, the classification time, and the number of decision rules of the proposed algorithm are lower than those of the conventional ID3.
Some of the metrics are blocked by your
consent settings
Street Surface Quality Assessment and Visualization using Gyro Sensor
(2018-08-21)
Chawuthai, Rathachai
;
Jearanaitanakij, Kietikul
Street maintenance is one of important tasks for transportation safety. An inclusive report is required for demonstrating the quality of street surface in order to have a precise plan for repairing any defects on street at the right locations. Most observations from any government agencies are usually done by human, however reports about street surface are not well-appointed enough due to the limitation of human cognition and documentation. This paper addresses the according issue by using computation process that uses the power of the Internet of Things (IoT) to analyze the movement of gyro data with locations and time along driving routes, and then generates a visualization report to point out any broken street surface. It has been found that the analysis of gyro data using linear regression could enable street surface quality assessment and visualization for improving road safety.
Some of the metrics are blocked by your
consent settings
Hybrid algorithm for training feed-forward neural networks using PSO-information gain with back propagation algorithm
(2012-10-02)
Sanguanchue, Tanyawat
;
Jearanaitanakij, Kietikul
This paper proposes a hybrid algorithm for training a feed-forward neural network by combining both Particle Swarm Optimization (PSO) and Information Gain with Backpropagation (BP) algorithm. A conventional neural network training algorithm, i.e. BP, has several drawbacks in its slow convergence and local optima. Although PSO can be applied to search for the near optimal set of weights in the neural network, it may still stuck in the local optima because its fitness function depends merely on the error of the network. By combining the information gain of attributes in the dataset with the fitness function of PSO to train weights in the neural network, we find out that the resulting network has a significant improvement on its recognition rate. The comparisons among other training algorithm on two real-world datasets are provided and discussed. © 2012 IEEE.
Some of the metrics are blocked by your
consent settings
An early exploratory method to avoid local minima in Ant Colony System
(2015-08-17)
Satukitchai, Thanet
;
Jearanaitanakij, Kietikul
Ant colony optimization (ACO) is a famous technique for solving the traveling salesman problem (TSP). However, one of its disadvantages is that it can be easily trapped into local optima. Although there is an attempt by Ant Colony System (ACS) to improve the local optima by introducing local pheromone updating rule, the chance of being trapped into local optima still persists. This paper presents an extension of ACS algorithm by modifying the construction solution phase of the algorithm, the phase that ants move and build their tours, for reducing the duplication of tours produced by ants. This modification forces ants to select unique path which has never visited by other ants in the current iteration. As a result, the modified ACS can explore more search space than the conventional ACS. The experimental results on five standard data sets from TSPLIB show improvements on both the quality and the number of optimal solutions founded.
Some of the metrics are blocked by your
consent settings
Reducing the depth of ID3 algorithm by combining values from neighboring important attributes
(2018-07-02)
Kraidech, Suratchanan
;
Jearanaitanakij, Kietikul
The ID3 algorithm is one of the most popular decision tree algorithms which is mainly used in the classification task. There are many pieces of research about improving the ID3 algorithm by using various strategies. We improved the ID3 algorithm by addressing the equally important attributes problem in our previous work. In this paper, we extend our previous algorithm by changing the attribute selection to allow the neighboring second-place important attributes to be combined with the most important attributes. The proposed algorithm is tested on four standard benchmarks from the UCI repository. The experimental results indicate the significant reduction in the maximum depth and the classification depth of the decision tree. In addition, the testing time is also reduced while the classification accuracy is satisfying stable.
Some of the metrics are blocked by your
consent settings
The Improved Training Algorithm of Deep Learning with Self-Adaptive Learning Rate
(2018-12-24)
Ongart, Sutit
;
Jearanaitanakij, Kietikul
;
Sangthong, Jirapat
This paper proposed the improvement of convergence performance for deep learning. For traditional algorithm, the learning rate is depended on experience and experiment. In this work, the learning rate can be adaptived based on Taylor's formula. This formula has the relationship between the root mean square errors changed, connection template, weights and biases changes are obtained. The proposed self-Adaptive learning rate is depended on neural network structure, root mean square error and error curve surface gradient. From the results, this proposed system has iteration times less than the traditional algorithm with constant learning rate.
Some of the metrics are blocked by your
consent settings
Improving ID3 Algorithm by Combining Values from Equally Important Attributes
(2018-08-21)
Kraidech, Suratchanan
;
Jearanaitanakij, Kietikul
ID3 is a well-known algorithm which is used in the classification task of the decision tree learning. Although a lot of research provides improvements on the traditional ID3 algorithm with various strategies, no attempt was made on ID3 to address the problem when there are more than one attribute that can be placed at a particular node, i.e. those attributes are equally important. This paper proposes a new variation of ID3 to combine equally important attributes into a single node of the decision tree classification. The Connect-4 dataset from UCI is used in our experiment since the dataset contains many attributes and instances which can easily encounter the equally important attribute problem. The experimental results show that our proposed method significantly reduces the average depth of the decision tree generated by ID3 algorithm while the average accuracy rate is still preserved.

Jearanaitanakij, Kietikul

Filters

Settings

Sort By

Results per page