• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2011년도 한국컴퓨터종합학술대회논문집 Vol.38 No.1(B)
• /
• pp.305-306
• /
• 2011

The Wireless sensor networks (WSN) continuously generates large volumes of raw data which own natural heterogeneity. These networks are normally application specific with no sharing or reusability of sensor data among applications. In order for applications and services to be developed independently of particular network, sensor data need to be available in more standardized form. In this paper, we propose Architecture for Sensory data management. This Extensible Markup Language (XML) oriented architecture allows the sensor data to be understood and processed in a meaningful way by a variety of applications with different purposes. We developed a middle layer which performs transformation on raw sensory data to XML and vice versa.

• 지능정보연구
• /
• 제24권2호
• /
• pp.1-19
• /
• 2018

주가 예측은 학문적으로나 실용적으로나 중요한 문제이기에, 주가 예측에 관련된 연구가 활발히 진행되었다. 빅 데이터 시대에 도입하면서, 빅 데이터를 결합한 주가 예측 연구도 활발히 진행되고 있다. 다수의 데이터를 기반으로 기계 학습을 이용한 연구가 주를 이룬다. 특히 언론의 효과를 접목한 연구 방법들이 주목을 받고 있는데, 그중 온라인 뉴스를 분석하여 주가 예측에 활용하는 연구가 주를 이루고 있다. 기존 연구들은 온라인 뉴스가 개별 회사에 대한 미치는 영향을 주로 살펴보았다. 또한, 관련성이 높은 기업끼리 서로 영향을 주는 것을 고려하는 방법도 최근에 연구되고 있다. 이는 동질성을 가지는 산업군에 대한 효과를 살펴본 것인데, 기존 연구에서 동질성을 가지는 산업군은 국제 산업 분류 표준에 따른다. 즉, 기존 연구들은 국제 산업 분류 표준으로 나뉜 산업군이 동질성을 가진다는 가정하에서 분석을 시행하였다. 하지만 기존 연구들은 영향력을 가지는 회사를 고려하지 못한 채 예측하였거나 산업군 내에서 이질성이 존재하는 점을 반영하지 못했다는 한계점을 가진다. 본 연구는 산업군 내에 이질성이 존재함을 밝히고, 이질성을 반영하지 못한 기존 연구의 한계점을 K-평균 군집 분석을 적용하여, 주가에 영향을 미치는 산업군의 동질적인 효과를 반영할 수 있는 방법론을 제안하였다. 방법론이 적합하다는 것을 증명하기 위해 3년간의 온라인 뉴스와 주가를 통해 실험한 결과, 다수의 경우에서 본 논문에서 제시한 방법이 좋은 결과를 나타냄을 확인할 수 있었으며, 국제 산업 분류 표준 산업군 내에서 이질성이 클수록 본 논문에서 제시한 방법이 좋은 효과를 보인다는 것을 확인할 수 있었다. 본 연구는 국제 산업 분류 표준으로 나누어진 기업들이 높은 동질성을 가지지 않는 다는것을 밝히고 이를 반영한 예측 모형의 효율성을 입증하였다는 점에서 의의를 가진다.

• ETRI Journal
• /
• 제46권3호
• /
• pp.513-525
• /
• 2024

Deep neural networks trained on labeled medical data face major challenges owing to the economic costs of data acquisition through expensive medical imaging devices, expert labor for data annotation, and large datasets to achieve optimal model performance. The heterogeneity of diseases, such as Alzheimer's disease, further complicates deep learning because the test cases may substantially differ from the training data, possibly increasing the rate of false positives. We propose a reconstruction-based self-supervised anomaly detection model to overcome these challenges. It has a dual-subnetwork encoder that enhances feature encoding augmented by skip connections to the decoder for improving the gradient flow. The novel encoder captures local and global features to improve image reconstruction. In addition, we introduce an entropy-based image conversion method. Extensive evaluations show that the proposed model outperforms benchmark models in anomaly detection and classification using an encoder. The supervised and unsupervised models show improved performances when trained with data preprocessed using the proposed image conversion method.

• 한국지역지리학회지
• /
• 제22권1호
• /
• pp.251-266
• /
• 2016

데시메트릭 매핑은 행정구역 단위로 집계된 인구자료를 행정구역 내부의 공간적 변이에 따라 재집계하여 고해상도의 인구분포 자료를 작성하는 가장 보편적인 기법이다. 본 연구에서는 데시메트릭 매핑을 이용한 인구분포 추정의 장단점을 검토하고, 그 개선방안으로서 지리가중회귀모형을 이용한 다변량 데시메트릭 매핑 기법을 제안하였다. 기존의 지표피복 데이터와 인구센서스 자료를 기반으로 지리가중회귀모형을 적용하여 각 집계단위별로 지표피복 유형과 인구밀도의 상관관계를 분석하고, 모형에서 산출된 회귀계수를 이용해 하위 공간구획의 인구 총수를 산정하였다. 그 결과 지리가중회귀모형 기반 다변량 데시메트릭 매핑 기법을 이용했을 때, 면적가중 보간법, 이진 데시메트릭 매핑, 피크노필렉틱 보간법, 최소자승회귀모형 기반 데시메트릭 매핑 기법 등 다른 지능형 보간법에 비해 정확한 인구분포 추정이 가능하다는 것을 확인하였다. 이는 지리가중회귀모형을 통해서 인구센서스 집계 단위별로 상이한 구역 내 공간적 이질성이 인구분포 추정에 적절히 반영되었기 때문인 것으로 평가할 수 있다.

• 대한교통학회지
• /
• 제36권2호
• /
• pp.141-154
• /
• 2018

지속적으로 증가하는 국제선 항공수요에 대웅하기 위해 지방 광역권에도 새로운 공항 건설 및 기존 공항 확장 계획이 이루어지고 있다. 그러나 기존 항공수요예측은 우리나라 전체 항공수요 또는 주요 도시 간의 항공수요에 대해서 수행되어 왔으며, 지방의 고유 특성을 고려한 지역별 항공수요예측은 많이 이루어지지 않았다. 본 연구에서는 영남권 국제선 항공수요를 대상으로 하였고, 현실적으로 관측하기 어려운 지방 광역권의 고유 특성을 반영할 수 있는 패널 자료를 활용한 fixed-effects model을 최적 모형으로 제안하였다. 모형 검증결과를 살펴보면 패널 자료 분석은 시계열 특성을 가지는 몇 개의 거시 사회경제지표만을 사용한 모형에서 다루기 어려운 허구적 회귀와 미관찰 이질성을 효과적으로 처리하고 있음을 알 수 있다. 다양한 통계적 검증과 적합성 평가를 통해서 본 연구에서 제안한 fixed-effects model이 다른 계량경제 모형들에 비해서 영남권 국제선 수요예측에 있어서 우수함을 증명하였다.

• The Journal of Asian Finance, Economics and Business
• /
• 제7권12호
• /
• pp.853-861
• /
• 2020

The study aims to measure the productivity of the Saudi banking sector at the retail level using secondary data for 11 local banks from the period 2015-2019. The study uses an extended version of the Cobb-Douglas production function to account for the fact that as banks openup more retail branches, they will need to employ more labor. The extended Cobb-Douglas production function was estimated using the two-way fixed effect model to account for unobserved heterogeneity across Saudi banks resulting from differences in labor competencies and leadership style. Besides, the model accounts for unobserved heterogeneity among Saudi banks due to the advancement in electronic services over time. The results showed that labor, branches, customers' deposits, and fixed deposits have a positive effect on the total value of generated loans. Conversely, ATM has an insignificant effect on generated loans. The average scale elasticity shows that the Saudi banks at the retail level are operating under decreasing returns to scale. The average marginal rate of technical substitution shows that Saudi banks need at least one ATM to replace one unit of labor at the retail level while keeping the same level of output.

• Journal of Ecology and Environment
• /
• 제34권2호
• /
• pp.237-249
• /
• 2011

Land-use changes due to the socio-economic environment influence landscape patterns and processes, which affect habitats and biodiversity. This study considers the effects of such land-use changes, particularly on the traditional rural "Maeul" forested landscape, by analyzing landscape structure and vegetation changes. Three study areas were examined that have seen their populations decrease and age over the last few decades. Five types of plant life-forms (Raunkier life-forms) were distinguished to investigate ecosystem function. Principle component analysis was used to understand vegetation dynamics and community characteristics based on a vegetation similarity index. Ordination analysis transformed species-coverage data was introduced to clarify vegetation dynamics. Landscape indices, such as area metrics, edge metrics, and shape metrics, showed that spatial heterogeneity has increased over time in all areas. Pinus densiflora was the main land-use plant type in all study areas but decreased over time, whereas Quercus spp. increased. Over a decade, P. densiflora communities shifted to deciduous oak and plantation. These findings indicate that the impact of human activities on the Maeul landscape is twofold. While forestry activities caused heavy disturbances, the abandonment of traditional human activities has led to natural succession. Furthermore, it can be concluded that the type and intensity of these human impacts on landscape heterogeneity relate differently to vegetation succession. This reflects the cause and consequence of patch dynamics. We discuss an approach for sustainable landscape planning and management of the Maeul landscape based on traditional management.

• 한국컴퓨터정보학회논문지
• /
• 제23권3호
• /
• pp.71-77
• /
• 2018

The purpose of this study was to investigate the effectiveness of elastic band resistance training for muscle strength among community-dwelling older adults. The systematic review and meta-analysis was conducted by following the Preferred Reporting Items for Systematic Reviews and Meta-analyses (PRISMA). Data were pooled using fixed effect models. Sit to stand, arm curl, and grip strength were analyzed for main effects. Heterogeneity between studies was assessed using the I2 statistics and publication bias was evaluated by funnel plots. Twelves studies were included representing 611 participants. Elastic band resistance training was effective for lower (d=3.89, 95% CI: 3.03, 4.75) and upper extremity muscle strength (d=4.08, 95% CI: 2.94, 5.23). Heterogeneity was moderate and no significant publication bias was detected. Based on these findings, there is clear evidence that elastic band resistance training has significant positive effects on muscle strength among community-dwelling older adults. Further study will be needed to perform subgroup analysis using number of sessions and exercise intensity as predictors.

• Genomics & Informatics
• /
• 제13권4호
• /
• pp.132-136
• /
• 2015

Studies of cancer heterogeneity have received considerable attention recently, because the presence or absence of resistant sub-clones may determine whether or not certain therapeutic treatments are effective. Previously, we have reported G64, a co-regulated gene module composed of 64 different genes, can differentiate tumor intra- or inter-subpopulations in lung adenocarcinomas (LADCs). Here, we investigated whether the G64 module genes were also expressed distinctively in different subpopulations of other cancers. RNA sequencing-based transcriptome data derived from 22 cancers, except LADC, were downloaded from The Cancer Genome Atlas (TCGA). Interestingly, the 22 cancers also expressed the G64 genes in a correlated manner, as observed previously in an LADC study. Considering that gene expression levels were continuous among different tumor samples, tumor subpopulations were investigated using extreme expressional ranges of G64-i.e., tumor subpopulation with the lowest 15% of G64 expression, tumor subpopulation with the highest 15% of G64 expression, and tumor subpopulation with intermediate expression. In each of the 22 cancers, we examined whether patient survival was different among the three different subgroups and found that G64 could differentiate tumor subpopulations in six other cancers, including sarcoma, kidney, brain, liver, and esophageal cancers.

• The Journal of Asian Finance, Economics and Business
• /
• 제8권2호
• /
• pp.15-23
• /
• 2021

This study investigates the presence of the day-of-the-week anomaly in exchange rate for 30 developing countries with free floating exchange rate regimes using daily data from January 2, 2011 to December 31, 2019. First, we apply the GARCH panel to estimate the intraday effect for all the sampled countries. Second, we run poolability test to check whether the coefficients of the GARCH panel are the same for all countries sampled. The result of poolability test rejects the homogeneity assumption. This implies that our sample countries contain heterogeneity. Third, we apply mean-group estimation by averaging the coefficients for all individual GARCH estimations. Fourth, we divided our sample of developing countries into three groups based on capital restriction index for the reason that the effect of monetary policy on the exchange rate depends on the degree of capital account liberalization. The empirical evidence for the return equation suggests that Mondays are connected with lower volatility whereas Thursdays experiences higher return compared to Tuesdays. The lowest estimated coefficient for full sample, group 1 and group 2, is Friday, but for group 2 is Thursday. We find similar result for the volatility equations, which show that Monday returns are lower compared to Tuesday.