• Journal of the Korea Society for Simulation
• /
• v.29 no.1
• /
• pp.11-21
• /
• 2020

Cardio-cerebrovascular diseases (CCD) account for 24% of the causes of death to Koreans and its proportion is the highest except cancer. Currently, the risk of the cardiovascular disease for domestic patients is based on the Framingham risk score (FRS), but accuracy tends to decrease because it is a foreign guideline. Also, it can't score the risk of cerebrovascular disease. CCD is hard to predict, because it is difficult to analyze the features of early symptoms for prevention. Therefore, proper prediction method for Koreans is needed. The purpose of this paper is validating IG-MLP (Information Gain - Multilayer Perceptron) evaluation based feature selection method using CCD data with simulation. The proposed method uses the raw data of the 4^th ~ 7^th of The Korea National Health and Nutrition Examination Survey (KNHANES). To select the important feature of CCD, analysis on the attributes using IG-MLP are processed, finally CCD prediction ANN model using optimize feature set is provided. Proposed method can find important features of CCD prediction of Koreans, and ANN model could predict more accurate CCD for Koreans.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.10
• /
• pp.1855-1861
• /
• 2017

In this paper, the gain enhancement of an SDPA using a director and two parasitic patches is studied. The modified balun is used to increase the bandwidth, whereas the director and two parasitic patches are appended to the SDPA to enhance the gain in the middle and high frequency bands. The effects of the distance between the director and parasitic patches on the antenna performance are analyzed, and the SDPA with a gain over 7 dBi at 1.54-2.99 GHz band is designed. The proposed SDPA is fabricated on an FR4 substrate with a dimension of $90mm(L){\times}135mm(W)$ in order to validate its performance. The fabricated antenna shows a frequency band of 1.56-3.10 GHz for a VSWR < 2, and it is confirmed by measurement that gain maintains over 7 dBi in the frequency range of 1.54-3.00 GHz.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.05a
• /
• pp.471-472
• /
• 2015

In this paper, a design method for enhancing the gain of a series-fed dipole pair (SDP) antenna using mutiple directors is studied. Strip-type directors are located above the second dipole of the SDP antenna, and the variations of the input VSWR bandwidth and gain depending on the length of the second dipole and the number of directors are analyzed. The antenna is optimized to obtain gain > 8 dBi in the frequency range of 1.7-2.7 GHz, which has three directors in the optimum design. The optimized antenna is designed on an FR4 substrate with a dimension of 86.2 mm by 152.3 mm, and it has frequency bands of 1.67-2.79 GHz for a VSWR < 2 and 1.69-2.72 GHz for a gain > 8 dBi.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.05a
• /
• pp.59-60
• /
• 2017

In this paper, the bandwidth and gain enhancement of a series-fed dipole pair antenna (SDPA) using a modified balun., a director, and two parasitic patches is studied. The proposed SDPA consists of two strip dipoles with different lengths, a ground reflector, which are connected through a coplanar strip line, a director, and two parasitic patches. The modified balun is used to increase the bandwidth, whereas the director and two parasitic patches are appended to the SDPA to enhance the gain in the middle and high frequency band. A prototype of the proposed SDPA is fabricated on an FR4 substrate, and the experimental results show that the antenna has a frequency band of 1.56-3.10 GHz for a VSWR < 2, and measured gain maintains over 7 dBi in the frequency range of 1.55-3.00 GHz.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.10a
• /
• pp.61-62
• /
• 2015

In this paper, a design method for a dual-band compact slot antenna using SRR(split-ring resonator) conductor is studied. The SRR conductor is loaded inside of a rectangular slot of the proposed antenna for dual-band operation. Final design parameters are obtained by analyzing the effects of the gap between the SRR conductor and slot, and the width of the SRR conductor on the input reflection coefficient and gain characteristics. A prototype of the proposed dual-band slot antenna operating at 2.45 GHz WLAN band and 3.40-5.35 GHz band is designed on an FR4 substrate with a dimension of 30 mm by 30 mm.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.05a
• /
• pp.61-62
• /
• 2017

In this study, a circular polarization patch antenna operates at the wide bandwidth of 1.5GHz~1.7GHz was designed. To obtain the wide bandwidth and high gain, the high air substrate was applied. The impedance bandwidth is improved by adjusting the sizes of patch, the distance between main patch and ground plate, the length of internal slots, the position of feeding point, the length of external stub, etc. The antenna is designed by simulation for an operation in the frequency range of 1.5GHz~1.7GHz band, and the antenna characteristics such as return loss, gain, radiation patterns are examined.

• Journal of information and communication convergence engineering
• /
• v.14 no.4
• /
• pp.222-226
• /
• 2016

A design method for a compact square loop antenna fed by a microstrip (MS) line for indoor digital television (DTV) applications is proposed. The proposed antenna consists of a square loop, circular sectors, and an MS line. The square loop combined with circular sectors is printed on one side of a substrate, and a $75-{\Omega}$ MS line is printed on the other side. The circular sectors are used as a wideband balun or transition to connect the MS line and the square loop. A prototype of the proposed square loop antenna operating in the DTV band (470-806 MHz) is designed and fabricated on an FR4 substrate. Experimental results show that the proposed antenna has the desired impedance characteristics in the frequency band of 464-1,220 MHz (89.8%) for a voltage standing wave ratio (VSWR) of <2 covering the DTV band, and a broadside gain of 0.8-3.3 dBi in the DTV band.

• Journal of Digital Convergence
• /
• v.17 no.2
• /
• pp.163-170
• /
• 2019

Over the past decade, the development of the Web explosively increased the data. Feature selection step is an important step in extracting valuable data from a large amount of data. This study proposes a novel opinion mining model based on combining feature selection (FS) methods with Word embedding to vector (Word2vec) and BOW (Bag-of-words). FS methods adopted for this study are CFS (Correlation based FS) and IG (Information Gain). To select an optimal FS method, a number of classifiers ranging from LR (logistic regression), NN (neural network), NBN (naive Bayesian network) to RF (random forest), RS (random subspace), ST (stacking). Empirical results with electronics and kitchen datasets showed that LR and ST classifiers combined with IG applied to BOW features yield best performance in opinion mining. Results with laptop and restaurant datasets revealed that the RF classifier using IG applied to Word2vec features represents best performance in opinion mining.

• Journal of the Korean Society for Library and Information Science
• /
• v.39 no.1
• /
• pp.45-58
• /
• 2005

This Paper is a comparative study of feature selection methods for Korean web documents clustering. First, we focused on how the term feature and the co-link of web documents affect clustering performance. We clustered web documents by native term feature, co-link and both, and compared the output results with the originally allocated category. And we selected term features for each category using $X^2$, Information Gain (IG), and Mutual Information (MI) from training documents, and applied these features to other experimental documents. In addition we suggested a new method named Max Feature Selection, which selects terms that have the maximum count for a category in each experimental document, and applied $X^2$ (or MI or IG) values to each term instead of term frequency of documents, and clustered them. In the results, $X^2$ shows a better performance than IG or MI, but the difference appears to be slight. But when we applied the Max Feature Selection Method, the clustering Performance improved notably. Max Feature Selection is a simple but effective means of feature space reduction and shows powerful performance for Korean web document clustering.

• Journal of Digital Convergence
• /
• v.17 no.3
• /
• pp.107-117
• /
• 2019

In the era of SNS, many people relies on it to express their emotions about various kinds of products and services. Therefore, for the companies eagerly seeking to investigate how their products and services are perceived in the market, emotion mining tasks using dataset from SNSs become important much more than ever. Basically, emotion mining is a branch of sentiment analysis which is based on BOW (bag-of-words) and TF-IDF. However, there are few studies on the emotion mining which adopt feature selection (FS) methods to look for optimal set of features ensuring better results. In this sense, this study aims to propose FS methods to conduct emotion mining tasks more effectively with better outcomes. This study uses Twitter and SemEval2007 dataset for the sake of emotion mining experiments. We applied three FS methods such as CFS (Correlation based FS), IG (Information Gain), and ReliefF. Emotion mining results were obtained from applying the selected features to nine classifiers. When applying DT (decision tree) to Tweet dataset, accuracy increases with CFS, IG, and ReliefF methods. When applying LR (logistic regression) to SemEval2007 dataset, accuracy increases with ReliefF method.