• IEMEK Journal of Embedded Systems and Applications
• /
• v.13 no.4
• /
• pp.215-223
• /
• 2018

Recently, as interest of wearable devices has increased, commercially available smart wristbands and applications have been used as a tool for personal healthy management. However most previous studies have focused on evaluating the accuracy and reliability of the technical problems of wearable devices, especially step counts, walking distance, and energy consumption measured from the smart wristbands. In this study, we propose a physical activity evaluation model using classification rules, induced from the associative classification mining approach. These rules associated with five physical activities were generated by considering activities and walking times in target heart rate zones such as 'Out-of Zone', 'Fat Burn Zone', 'Cardio Zone', and 'Peak Zone'. In the experiment, we evaluated the prediction power of classification rules and verified its effectiveness by comparing classification accuracies between the proposed model and support vector machine.

• Journal of the Korean Data and Information Science Society
• /
• v.27 no.1
• /
• pp.255-264
• /
• 2016

Classification is a predictive modeling for a categorical target variable. Various classification ensemble methods, which predict with better accuracy by combining multiple classifiers, became a powerful machine learning and data mining paradigm. Well-known methodologies of classification ensemble are boosting, bagging and random forest. In this article, we assume that decision trees are used as classifiers in the ensemble. Further, we hypothesized that tree size affects classification accuracy. To study how the tree size in uences accuracy, we performed experiments using twenty-eight data sets. Then we compare the performances of ensemble algorithms; bagging, double-bagging, boosting and random forest, with different tree sizes in the experiment.

• Journal of Korean Institute of Industrial Engineers
• /
• v.41 no.5
• /
• pp.439-446
• /
• 2015

Recently, the importance of one-class classification problem is more increasing. However, most of existing algorithms have the limitation on providing the information that effects on the prediction of the target value. Motivated by this remark, in this paper, we suggest an efficient one-class classifier using hyper-rectangles (H-RTGLs) that can be produced from intervals including observations. Specifically, we generate intervals for each feature and integrate them. For generating intervals, we consider two approaches : (i) interval merging and (ii) clustering. We evaluate the performance of the suggested methods by computing classification accuracy using area under the roc curve and compare them with other one-class classification algorithms using four datasets from UCI repository. Since H-RTGLs constructed for a given data set enable classification factors to be visible, we can discern which features effect on the classification result and extract patterns that a data set originally has.

• Journal of the Korea Society of Computer and Information
• /
• v.21 no.3
• /
• pp.65-71
• /
• 2016

To reduce the expenses for development a novel drug, systems biology has been studied actively. Target prediction, a part of systems biology, contributes to finding a new purpose for FDA(Food and Drug Administration) approved drugs and development novel drugs. In this paper, we propose a classification model for predicting novel target genes based on relation between target genes and disease related genes. After collecting known target genes from TTD(Therapeutic Target Database) and disease related genes from OMIM(Online Mendelian Inheritance in Man), we analyzed the effect of target genes on disease related genes based on PPI(Protein-Protein Interactions) network. We focused on the distinguishing characteristics between known target genes and random target genes, and used the characteristics as features for building a classifier. Because our model is constructed using information about only a disease and its known targets, the model can be applied to unusual diseases without similar drugs and diseases, while existing models for finding new drug-disease associations are based on drug-drug similarity and disease-disease similarity. We validated accuracy of the model using LOOCV of ten times and the AUCs were 0.74 on Alzheimer's disease and 0.71 on Breast cancer.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.15 no.6
• /
• pp.579-589
• /
• 2004

The radar signals are generally very sensitive to relative orientations between radar and target. Thus, the performance of a target recognition system significantly deteriorates as the region of aspect angles becomes broader. To address this difficulty, in this paper, we propose a method based on the multi-aspect information in order to improve the classification capability ever for a wide angular region. First, range profiles are used to extract feature vectors based on the central moments and principal component analysis(PCA). Then, a classifier with the use of multi-aspect information is applied to them, yielding an additional improvement of target recognition capability. There are two different strategies among the classifiers that can fuse the information from multi-aspect radar signals: independent methodology and dependent methodology. In this study, the performances of the two strategies are compared within the frame work of target recognition. The radar cross section(RCS) data of six aircraft models measured at compact range of Pohang University of Science and Technology are used to demonstrate and compare the performances of the two strategies.

• The Journal of the Acoustical Society of Korea
• /
• v.38 no.5
• /
• pp.549-557
• /
• 2019

The acoustical scattering characteristics of a target are influenced by the material properties and structural characteristics of the target, which are critical information for acoustic detection and identification of underwater target. In particular, for thin elastic target, unique scattered signals are generated around the target by the Lamb wave. In this paper, the results of scattered signal measurement of aluminum spherical shell in the water tank using the stepped frequency sweep sine signal are presented. In particular, the scattering of the water-filled aluminum spherical shell is compared with that of the air-filled one both theoretically and experimentally. The difference of the scattered signals are analyzed using the pseudo Wigner-Ville distribution in terms of average frequency, frequency distribution, and energy of the scattered signal. The result shows that all observed parameters increased when the aluminum sphere was water-filled, and it is well matched to the theoretical expectation.

• The Journal of the Acoustical Society of Korea
• /
• v.40 no.4
• /
• pp.330-336
• /
• 2021

In bistatic sonar operation, the scattering strength of a sonar target is characterized by the probe signal frequency, the aspect angle and the bistatic angle. Therefore, the target detection and identification performance of the bistatic sonar may vary depending on how the positions of the target, sound source, and receiver are changed during sonar operation. In this study, it was evaluated which variable is advantageous to change by comparing the target identification performance between the case of changing the aspect angle and the case of changing the bistatic angle during the operation. A scenario of identifying a hollow sphere and a cylinder was assumed, and performance was compared by classifying two targets with a support vector machine and comparing their accuracy using a finite element method-based acoustic scattering simulation. As a result of comparison, using the scattering strength defined by the frequency and the bistatic angle with the aspect angle fixed showed superior average classification accuracy. It means that moving the receiver to change the bistatic angle is more effective than moving the sound source to change the aspect angle for target identification.

• Transactions on Electrical and Electronic Materials
• /
• v.14 no.4
• /
• pp.187-192
• /
• 2013

Because of the importance of small target detection in infrared images, many studies have been carried out in this area. Using a Kalman filter and mean shift algorithm, this study proposes an algorithm to track multiple small moving targets even in cases of target disappearance and appearance in serial infrared images in an environment with many noises. Difference images, which highlight the background images estimated with a background estimation filter from the original images, have a relatively very bright value, which becomes a candidate target area. Multiple target tracking consists of a Kalman filter section (target position prediction) and candidate target classification section (target selection). The system removes error detection from the detection results of candidate targets in still images and associates targets in serial images. The final target detection locations were revised with the mean shift algorithm to have comparatively low tracking location errors and allow for continuous tracking with standard model updating. In the experiment with actual marine infrared serial images, the proposed system was compared with the Kalman filter method and mean shift algorithm. As a result, the proposed system recorded the lowest tracking location errors and ensured stable tracking with no tracking location diffusion.

• Journal of the Korean Data and Information Science Society
• /
• v.14 no.2
• /
• pp.167-175
• /
• 2003

In document classification, target of analysis is not document itself but words appeared in the document. Word information, therefore, is a significant factor in document classification. In this study, we are dealing with the classification of Korean document based on words and feature vectors. First, we present the performance of document classification using nouns and keywords. Second, we compare to the results for the size of feature vectors.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.24 no.67
• /
• pp.77-82
• /
• 2001

A study was conducted to develop a better classification method of Consumer Attributes that can enhance user-centered product design process. A modified QFD(Quality Function Deployment) survey form based upon Fuzzy set theory was proposed which contains 9 steps of importance level, and Certainty and Necessity function to improve the reliability of extracted consumer attributes. To verify the betterment and advantage of proposed classification method, a series of questionnaire survey was performed. Thirty male and 30 female university students were participated in the survey using a VCR as a target product. The result of the study showed that 80% of subjects were preferred the proposed classification over existing method. A cluster analysis was performed to further verify the betterment of the proposed method. The result also supported that the proposed classification method is more reliable and enhanced method in extracting consumer attributes and can be applied in the product design.