• The Korean Journal of Applied Statistics
• /
• v.32 no.5
• /
• pp.671-681
• /
• 2019

Studies on predicting arrhythmia using machine learning have been actively conducted with increasing number of arrhythmia patients. Existing studies have predicted arrhythmia based on multivariate data of feature variables extracted from RR interval data at a specific time point. In this study, we consider that the pattern of the heart state changes with time can be important information for the arrhythmia prediction. Therefore, we investigate the usefulness of predicting the arrhythmia with multivariate time series data obtained by extracting and accumulating the multivariate vectors of the feature variables at various time points. When considering 1-nearest neighbor classification method and its ensemble for comparison, it is confirmed that the multivariate time series data based method can have better classification performance than the multivariate data based method if we select an appropriate time series distance function.

• Journal of the Korean Society for Precision Engineering
• /
• v.16 no.10
• /
• pp.141-151
• /
• 1999

The resistance Spot Welding is widely used in the field of assembling the plates. However we don't still have any satisfactory solution, which is non-destructive quality evaluation in real-time or on-line, against it. Moreover, even though the rate of welding under the condition of expulsion has been high until now, quality control of welding against expulsion hasn't still been established. In this paper, it was proposed on the quality assurance technique of resistance spot welding pieces using Neuro-Fuzzy algorithm. Four parameters from electrode separation signal in the case of non-expulsion, and dynamic resistance patterns in the case of expulsion are selected as fuzzy input parameters. The parameters consist of Fuzzy Inference System are determined through Neuro-Learning algorithm. And then, fuzzy Inference System is constructed. It was confirmed that the fuzzy inference values of strength have within ${\pm}$4% error specimen in comparison with real strength for the total strength range, and the specimen percent having within ${\pm}$1% error was 88.8%. According to KS(Korean Industrial Standard), tensile-shear strength limit for electric coated of zinc is 400kgf/mm2. Judging to the quality of welding is good or bad, according to this criterion and the results of inference, the probability of misjudgement that good quality is valuated into poor one was 0.43%, on contrary it was 2.59%. Finally, the proposed Neuro-Fuzzy Inference System can infer the tensile-shear strength of resistance spot welding pieces with high performance for all cases-non-expulsion and expulsion. And On-Line Welding Quality Inspection System will be realized sooner or later.

• The Journal of Korea Robotics Society
• /
• v.7 no.3
• /
• pp.171-181
• /
• 2012

Outdoor mobile robots are faced with various terrain types having different characteristics. To run safely and carry out the mission, mobile robot should recognize terrain types, physical and geometric characteristics and so on. It is essential to control appropriate motion for each terrain characteristics. One way to determine the terrain types is to use non-contact sensor data such as vision and laser sensor. Another way is to use contact sensor data such as slope of body, vibration and current of motor that are reaction data from the ground to the tire. In this paper, we presented experimental results on terrain classification using contact sensor data. We made a mobile robot for collecting contact sensor data and collected data from four terrains we chose for experimental terrains. Through analysis of the collecting data, we suggested a new method of terrain feature extraction considering physical characteristics and confirmed that the proposed method can classify the four terrains that we chose for experimental terrains. We can also be confirmed that terrain feature extraction method using Fast Fourier Transform (FFT) typically used in previous studies and the proposed method have similar classification performance through back propagation learning algorithm. However, both methods differ in the amount of data including terrain feature information. So we defined an index determined by the amount of terrain feature information and classification error rate. And the index can evaluate classification efficiency. We compared the results of each method through the index. The comparison showed that our method is more efficient than the existing method.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.16 no.4
• /
• pp.1-12
• /
• 2017

Traffic accidents are caused by a combination of human factors, vehicle factors, and environmental factors. In the case of traffic accidents where rental cars are involved, the possibility and the severity of traffic accidents are expected to be different from those of other traffic accidents due to the unfamiliar environment of the driver. In this study, we developed a model to forecast the severity of rental car accidents by using Naive Bayes classifier for Busan, Gangneung, and Jeju city. In addition, we compared the prediction accuracy performance of two models where one model uses the variables of which statistical significance were verified in a prior study and another model uses the entire available variables. As a result of the comparison, it is shown that the prediction accuracy is higher when using the variables with statistical significance.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.12 no.2
• /
• pp.325-330
• /
• 2017

Face recognition technology has been studied for decades and is being used in various areas such as security, entertainment, and mobile services. The main problem with face recognition technology is that the recognition rate is significantly reduced depending on the environmental factors such as brightness, illumination angle, and image rotation. Therefore, in this paper, we propose a robust face recognition against lighting variation using CNN which has been recently re-evaluated with the development of computer hardware and algorithms capable of processing a large amount of computation. For performance verification, PCA, LBP, and DCT algorithms were compared with the conventional face recognition algorithms. The recognition was improved by 9.82%, 11.6%, and 4.54%, respectively. Also, the recognition improvement of 5.24% was recorded in the comparison of the face recognition research result using the existing neural network, and the final recognition rate was 99.25%.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.1
• /
• pp.26-32
• /
• 2018

The protein secondary structures are important information for studying the evolution, structure and function of proteins. Recently, deep learning methods have been actively applied to predict the secondary structure of proteins using only protein sequence information. In these methods, widely used input features are protein profiles transformed from protein sequences. In this paper, to obtain an effective protein profiles, protein profiles were constructed using protein sequence search methods such as PSI-BLAST and HHblits. We adjust the similarity threshold for determining the homologous protein sequence used in constructing the protein profile and the number of iterations of the profile construction using the homologous sequence information. We used the protein profiles as inputs to convolutional neural networks and recurrent neural networks to predict the secondary structures. The protein profile that was created by adding evolutionary information only once was effective.

• Journal of Korea Game Society
• /
• v.18 no.5
• /
• pp.103-112
• /
• 2018

"Ito2", an early childhood educational coding game that allows students to learn sequential, loop, and conditional statement concepts through games is introduced. The developed game is a two-stage process of mock and practical classes for children in actual nursing cares, and coding education is conducted for actual children to determine its effectiveness. The degree of change is observed by observing trends in childhood cognitive development performance in all six areas, including parts and the overall, space, observation, shape and measurement, classification, comparison, and listing, as the coding training is conducted. In this paper, the improvement of cognitive development and spatial perceptual abilities were achieved by children playing games with infant functional coding with fun elements plus learning factors.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.66 no.7
• /
• pp.1131-1140
• /
• 2017

This study is concerned with a design methodology of optimized fuzzy clustering-based neural network classifier for classifying black plastic. Since the amount of waste plastic is increased every year, the technique for recycling waste plastic is getting more attention. The proposed classifier is on a basis of architecture of radial basis function neural network. The hidden layer of the proposed classifier is composed to FCM clustering instead of activation functions, while connection weights are formed as the linear functions and their coefficients are estimated by the local least squares estimator (LLSE)-based learning. Because the raw dataset collected from Raman spectroscopy include high-dimensional variables over about three thousands, principal component analysis(PCA) is applied for the dimensional reduction. In addition, artificial bee colony(ABC), which is one of the evolutionary algorithm, is used in order to identify the architecture and parameters of the proposed network. In experiment, the proposed classifier sorts the three kinds of plastics which is the most largely discharged in the real world. The effectiveness of the proposed classifier is proved through a comparison of performance between dataset obtained from chemical analysis and entire dataset extracted directly from Raman spectroscopy.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.60 no.4
• /
• pp.862-870
• /
• 2011

In this paper, we introduce a new topology of Radial Basis Function-based Polynomial Neural Networks (RPNN) that is based on a genetically optimized multi-layer perceptron with Radial Polynomial Neurons (RPNs). This study offers a comprehensive design methodology involving mechanisms of optimization algorithms, especially Fuzzy C-Means (FCM) clustering method and Particle Swarm Optimization (PSO) algorithms. In contrast to the typical architectures encountered in Polynomial Neural Networks (PNNs), our main objective is to develop a design strategy of RPNNs as follows : (a) The architecture of the proposed network consists of Radial Polynomial Neurons (RPNs). In here, the RPN is fully reflective of the structure encountered in numeric data which are granulated with the aid of Fuzzy C-Means (FCM) clustering method. The RPN dwells on the concepts of a collection of radial basis function and the function-based nonlinear (polynomial) processing. (b) The PSO-based design procedure being applied at each layer of RPNN leads to the selection of preferred nodes of the network (RPNs) whose local characteristics (such as the number of input variables, a collection of the specific subset of input variables, the order of the polynomial, and the number of clusters as well as a fuzzification coefficient in the FCM clustering) can be easily adjusted. The performance of the RPNN is quantified through the experimentation where we use a number of modeling benchmarks - NOx emission process data of gas turbine power plant and learning machine data(Automobile Miles Per Gallon Data) already experimented with in fuzzy or neurofuzzy modeling. A comparative analysis reveals that the proposed RPNN exhibits higher accuracy and superb predictive capability in comparison to some previous models available in the literature.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.1
• /
• pp.161-166
• /
• 2022

In this paper, we analyze the problems that occur when performing the big data analysis using R as a data analysis tool, and present the usefulness of the data analysis with SparkR which connects R and Spark to support distributed processing of big data effectively. First, we study the memory allocation problem of R which occurs when loading large amounts of data and performing operations, and the characteristics and programming environment of SparkR. And then, we perform the comparison analysis of the execution performance when linear regression analysis is performed in each environment. As a result of the analysis, it was shown that R can be used for data analysis through SparkR without additional language learning, and the code written in R can be effectively processed distributedly according to the increase in the number of nodes in the cluster.