http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Genetic Outlier Detection for a Robust Support Vector Machine
Heesung Lee,Euntai Kim 한국지능시스템학회 2015 INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGE Vol.15 No.2
Support vector machine (SVM) has a strong theoretical foundation and also achieved excellent empirical success. It has been widely used in a variety of pattern recognition applications. Unfortunately, SVM also has the drawback that it is sensitive to outliers and its performance is degraded by their presence. In this paper, a new outlier detection method based on genetic algorithm (GA) is proposed for a robust SVM. The proposed method parallels the GA-based feature selection method and removes the outliers that would be considered as support vectors by the previous soft margin SVM. The proposed algorithm is applied to various data sets in the UCI repository to demonstrate its performance.
A Symbiotic Evolutionary Design of Error-Correcting Code with Minimal Power Consumption
Heesung Lee,김은태 한국전자통신연구원 2008 ETRI Journal Vol.30 No.6
In this paper, a new design for an error correcting code (ECC) is proposed. The design is aimed to build an ECC circuitry with minimal power consumption. The genetic algorithm equipped with the symbiotic mechanism is used to design a power-efficient ECC which provides single-error correction and double-error detection (SEC-DED). We formulate the selection of the parity check matrix into a collection of individual and specialized optimization problems and propose a symbiotic evolution method to search for an ECC with minimal power consumption. Finally, we conduct simulations to demonstrate the effectiveness of the proposed method.
Distance Based Outlier Detection for Nearest Neighborhood
Heesung Lee,Sungjun Hong,Byungyun Lee,Euntai Kim 대한전자공학회 2010 ICEIC:International Conference on Electronics, Inf Vol.1 No.1
By appropriate editing of the outlier, we can obtain Nearest Neighbor (NN) classifier that maximizes the accuracy of classification and saves computational time and memory resources. In this paper, we propose a new distance based outlier detection method for robust nearest neighbor classifier. The proposed method locates the outliers among the samples and removes them completely from the training set. In the proposed method, distance based data investigation detects and removes the outliers. To demonstrate the performance of the proposed method, we perform experiments on three databases.
Heesung Lee,Junyeap Kim,Jaewon Kim,Seong Kwang Kim,Yongwoo Lee,Jae-Young Kim,Jun Tae Jang,Jaewon Park,Sung-Jin Choi,Dae Hwan Kim,Dong Myong Kim IEEE 2017 IEEE electron device letters Vol.38 No.5
<P>Amorphous InGaZnO (a-IGZO) thin-film transistors (TFTs) are investigated for a possible application to infrared (IR) photodetector through subgap density-ofstates over the forbidden bandgap. The origin of the sub-bandgap(hν <;E<SUB>g</SUB>) photo-response in a-IGZO TFTs is due to optically pumped electrons from the photo-responsive subgap states (E<SUB>C</SUB>-E<SUB>ph</SUB><;E<SUB>t</SUB><;E<SUB>F</SUB>). Among the sub-bandgap lights, we investigate the reproducible IR photo-response in a-IGZO TFTs as a photodetector without the persistent photoconductivity(PPC) effect. In this letter, we characterize the IR photo-response mechanism through various optical and electrical measurements on the wavelength, optical power, bias-modulated quasi-Fermi level, and photoresponsive states. This result is expected to provide independent and/or integrated IR detector with transparent substrate combined with a-IGZO TFTs.</P>
Heesung Lee(이희승),Yunseon Jin(진윤선),Ohbyung Kwon(권오병) 한국지능정보시스템학회 2016 지능정보연구 Vol.22 No.2
Despite expectations of short- or long-term positive effects of corporate social responsibility (CSR) on firm performance, the results of existing research into this relationship are inconsistent partly due to lack of clarity about subordinate CSR concepts. In this study, keywords related to CSR concepts are extracted from atypical sources, such as newspapers, using text mining techniques to examine the relationship between CSR and firm performance. The analysis is based on data from the New York Times, a major news publication, and Google Scholar. We used text analytics to process unstructured data collected from open online documents to explore the effects of CSR on short- and long-term firm performance. The results suggest that the CSR index computed using the proposed text – online media - analytics predicts long-term performance very well compared to short-term performance in the absence of any internal firm reports or CSR institute reports. Our study demonstrates the text analytics are useful for evaluating CSR performance with respect to convenience and cost effectiveness.