• Journal of Digital Contents Society
• /
• v.17 no.6
• /
• pp.509-521
• /
• 2016

A novel Samples Balanced Genetic Algorithm combined with Extreme Learning Machine (SBGA-ELM) for Parkinson's Disease diagnosis and detecting bio-markers is presented in this paper. Proposed approach uses genes' expression data of 22,283 genes from open source ParkDB data base for accurate PD diagnosis and detecting bio-markers. Proposed SBGA-ELM includes two major steps: feature (genes) selection and classification. Feature selection procedure is based on proposed Samples Balanced Genetic Algorithm designed specifically for genes expression data from ParkDB. Proposed SBGA searches a robust subset of genes among 22,283 genes available in ParkDB for further analysis. In the "classification" step chosen set of genes is used to train an Extreme Learning Machine (ELM) classifier for an accurate PD diagnosis. Discovered robust subset of genes creates ELM classifier with stable generalization performance for PD diagnosis. In this research the robust subset of genes is also used to discover 24 bio-markers probably responsible for Parkinson's Disease. Discovered robust subset of genes was verified by using existing PD diagnosis approaches such as SVM and PBL-McRBFN. Both tested methods caused maximum generalization performance.

• Korean Journal of Remote Sensing
• /
• v.31 no.5
• /
• pp.449-459
• /
• 2015

The conventional National Forest Inventory(NFI)-based forest carbon stock estimation method is suitable for national-scale estimation, but is not for regional-scale estimation due to the lack of NFI plots. In this study, for the purpose of regional-scale carbon stock estimation, we created grid-based forest carbon stock maps using spatial ancillary data and two types of up-scaling methods. Chungnam province was chosen to represent the study area and for which the $5^{th}$ NFI (2006~2009) data was collected. The first method (method 1) selects forest type map as ancillary data and uses regression model for forest carbon stock estimation, whereas the second method (method 2) uses satellite imagery and k-Nearest Neighbor(k-NN) algorithm. Additionally, in order to consider uncertainty effects, the final AGB carbon stock maps were generated by performing 200 iterative processes with Monte Carlo simulation. As a result, compared to the NFI-based estimation(21,136,911 tonC), the total carbon stock was over-estimated by method 1(22,948,151 tonC), but was under-estimated by method 2(19,750,315 tonC). In the paired T-test with 186 independent data, the average carbon stock estimation by the NFI-based method was statistically different from method2(p<0.01), but was not different from method1(p>0.01). In particular, by means of Monte Carlo simulation, it was found that the smoothing effect of k-NN algorithm and mis-registration error between NFI plots and satellite image can lead to large uncertainty in carbon stock estimation. Although method 1 was found suitable for carbon stock estimation of forest stands that feature heterogeneous trees in Korea, satellite-based method is still in demand to provide periodic estimates of un-investigated, large forest area. In these respects, future work will focus on spatial and temporal extent of study area and robust carbon stock estimation with various satellite images and estimation methods.

• Journal of Digital Contents Society
• /
• v.17 no.6
• /
• pp.565-579
• /
• 2016

In this paper a novel cancer subtype's classifier based on Hybrid Samples Balanced Genetic Algorithm with Extreme Learning Machine (hSBGA-ELM) is presented. Proposed cancer subtype's classifier uses genes' expression data of 16063 genes from open Global Cancer Map (GCM) data base for accurate cancer subtype's classification. Proposed method efficiently classifies 14 subtypes of cancer (breast, prostate, lung, colorectal, lymphoma, bladder, melanoma, uterus, leukemia, renal, pancreas, ovary, mesothelioma and CNS). Proposed hSBGA-ELM unifies genes' selection procedure and cancer subtype's classification into one framework. Proposed Hybrid Samples Balanced Genetic Algorithm searches a reduced robust set of genes responsible for cancer subtype's classification from 16063 genes available in GCM data base. Selected reduced set of genes is used to build cancer subtype's classifier using Extreme Learning Machine (ELM). As a result, reduced set of robust genes guarantees stable generalization performance of the proposed cancer subtype's classifier. Proposed hSBGA-ELM discovers 95 genes probably responsible for cancer. Comparison with existing cancer subtype's classifiers clear indicates efficiency of the proposed method.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2018.05a
• /
• pp.436-436
• /
• 2018

하천의 조도계수는 하상 입자들의 크기 및 형상, 식생, 수로의 만곡 등 흐름특성에 영향을 주는 복합적인 경험적 매개변수이므로 그 값을 정확히 산정하는 것은 매우 어렵다(Chow, 1959). 제주도 산지하천은 하상이 매우 불규칙하고 조도계수의 불확실성으로 인해 정확한 홍수위, 홍수량 산정이 어렵다. 또한 하상경사가 매우 급하여 상류와 사류가 복합적으로 발생하므로 수치모의 시 수위차가 크게 발생할 우려가 있다. 따라서 현장실측 기반의 하천 조도계수 산정을 통한 홍수위, 홍수량 산정에 정확도를 향상시킬 필요가 있다. 이 연구에서는 제주도 북부지역의 건천(한천, 병문천, 독사천, 산지천)을 대상으로 하상재료를 직접 실측하여 하상 입경을 이용한 조도계수를 산정하였다. 실측 방법은 대상하천의 현장답사 및 현장조사를 사전에 실시하였으며, 하천의 종단 방향으로 1km 간격, 100개 이상의 하상재료를 표본으로 취하고 선격자법을 적용하였다. 대상하천 하류부의 좌안, 우안은 대부분 하천 정비에 의한 제방 구축이 되었으며, 상류부는 경사가 급한 암질로 구성되어 있으므로 하상을 중심으로 구성물질의 입경과 조고를 측정하여 상류 흐름의 영향범위를 고려한 조도계수를 산정하였다. 표본 측정시 점 사주, 여울, 웅덩이 등 국부적으로 하상재료의 변화가 심한 구역은 피하고 가급적 해당 구역에서 보편적으로 산재된 하상재료를 선택하였다. 향후 부정류 모형인 HEC-RAS를 이용하여 실측 유량과 수위를 적용한 조도계수를 산정한다면 보다 정밀한 조도계수를 산정할 것으로 판단된다.

• Environmental and Resource Economics Review
• /
• v.31 no.1
• /
• pp.1-30
• /
• 2022

This study is to investigate consumers' acceptance and their willingness to pay for clothes made of materials with low microplastic emissions as an alternative to synthetic fibers made of plastics by applying the contingent valuation method. A nationwide web-based survey was conducted for 1,052 respondents proportional to region, age, and gender during February 2021. More than 75% of the sample expressed intentions to purchase microplastic emission-reducing clothing instead of synthetic fiber clothing, and more than 80% of them have stated their willingness to pay for additional prices. A variation of Heckman's sample selection model was adopted to estimate factors affecting respondents' intentions to pay for additional prices, in which the probit model of intentions to purchase the clothing with alternative materials was used as a sample selection equation. While respondents were sensitive to the amounts of price increases suggested in the CV scenario, they expressed high acceptance and preferences for eco-friendly materials regardless of the microplastic emission-reducing levels. Consumers in the circular economy were willing to pay for the range of 41,000 to 51,000 won for a pair of clothing made with microplastic emission-reducing materials. In addition, as the microplastic emission-reducing rate has increased from 50% to 80%, the willingness to pay estimates were also significantly increased, ranging from 41,000~50,500 to 42,000~51,700 won.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.5
• /
• pp.624-630
• /
• 2010

As electrocardiogram(ECG) signals are generally sampled with a frequency of over 200Hz, a method to compress diagnostic information without losing data is required to store and transmit them efficiently. In this paper, an ECG signal compression method, which uses feature points based on curvature, is proposed. The feature points of P, Q, R, S, T waves, which are critical components of the ECG signal, have large curvature values compared to other vertexes. Thus, these vertexes are extracted with the proposed method, which uses local extremum of curvatures. Furthermore, in order to minimize reconstruction errors of the ECG signal, extra vertexes are added according to the iterative vertex selection method. Through the experimental results on the ECG signals from MIT-BIH Arrhythmia database, it is concluded that the vertexes selected by the proposed method preserve all feature points of the ECG signals. In addition, they are more efficient than the AZTEC(Amplitude Zone Time Epoch Coding) method.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2016.10a
• /
• pp.386-389
• /
• 2016

최근 남녀노소를 불문하고 피부 관리에 대한 관심이 증가하면서, 피부 개선에 효과적인 화장품의 선택에 관심이 높아지고 있다. 하지만 다양한 화장품들을 대상으로 자동화된 고객 맞춤형 화장품 추천은 그 발전이 더디고, 이와 관련된 연구 또한 아직 미미한 실정이다. 또한, 다양한 특성을 가지는 고객 피부 데이터 셋의 확보가 어려운 상황에서, 소수의 데이터 표본만을 이용하여 화장품 추천이 진행되고 있어 추천의 정확도를 확보하지 못하고 있다. 본 논문은 스마트폰용 휴대용 카메라를 이용하여 고객의 피부 상태를 진단한 후, 고객의 피부 개선에 적합한 화장품을 자동으로 추천하는 기법을 제안한다. 먼저, 화장품 추천을 위해 사용자의 SNS 데이터와 피부 데이터를 수집 및 분석하여 추천 리스트를 생성한다. 이를 기반으로, 추천된 각 화장품의 스코어를 계산한다. 그 다음, 피부 개선 순위와 스코어 기반의 화장품 특성 순위 간의 상관계수를 이용하여 가장 높은 상관계수의 화장품을 우선 추천한다. 성능 평가를 위해 실제 화장품 회사에서 제시한 화장품 추천 리스트와 본 논문에서 제안한 방법을 적용한 화장품 추천 리스트를 비교함으로써 효용성과 타당성을 입증하였다.

• The Journal of the Korea Contents Association
• /
• v.10 no.5
• /
• pp.210-219
• /
• 2010

Consumers differ in both horizontally and vertically. Market segmentation aims to divide horizontally different (or heterogeneous) consumers into more similar (or homogeneous) small segments. A specific consumer, however, may differ in vertically. He (or she) may belong to a different market segment from another one where he (or she) belonged to before. In consumer panel data, the vertical difference can be observed by his (or her) choice among brand alternatives are changing over time. The consumer's vertical difference has been defined as 'dynamics'. In this research, we have developed a binary probit model with random-walk coefficients to capture the consumer's dynamics. With an application to a consumer panel data, we have examined how have the random-walk coefficients changed over time.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.5 s.305
• /
• pp.123-136
• /
• 2005

We propose a recognition system for superimposed patterns based on selective attention model and SVM which produces better performance than artificial neural network. The proposed selective attention model includes attention layer prior to SVM which affects SVM's input parameters. It also behaves as selective filter. The philosophy behind selective attention model is to find the stopping criteria to stop training and also defines the confidence measure of the selective attention's outcome. Support vector represents the other surrounding sample vectors. The support vector closest to the initial input vector in consideration is chosen. Minimal euclidean distance between the modified input vector based on selective attention and the chosen support vector defines the stopping criteria. It is difficult to define the confidence measure of selective attention if we apply common selective attention model, A new way of doffing the confidence measure can be set under the constraint that each modified input pixel does not cross over the boundary of original input pixel, thus the range of applicable information get increased. This method uses the following information; the Euclidean distance between an input pattern and modified pattern, the output of SVM, the support vector output of hidden neuron that is the closest to the initial input pattern. For the recognition experiment, 45 different combinations of USPS digit data are used. Better recognition performance is seen when selective attention is applied along with SVM than SVM only. Also, the proposed selective attention shows better performance than common selective attention.

• The Journal of the Korea Contents Association
• /
• v.11 no.2
• /
• pp.22-30
• /
• 2011

In the IT convergence environment changed with not only the quality but also the material abundance, it is the most crucial factor for the strategy of personalized recommendation services to investigate the context information. In this paper, we proposed the recommendation using the service ontology based context awareness modeling. The proposed method establishes a data acquisition model based on the OSGi framework and develops a context information model based on ontology in order to perform the device environment between different kinds of systems. In addition, the context information will be extracted and classified for implementing the recommendation system used for the context information model. This study develops the ontology based context awareness model using the context information and applies it to the recommendation of the collaborative filtering. The context awareness model reflects the information that selects services according to the context using the Naive Bayes classifier and provides it to users. To evaluate the performance of the proposed method, we conducted sample T-tests so as to verify usefulness. This evaluation found that the difference of satisfaction by service was statistically meaningful, and showed high satisfaction.