• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.10 no.6
• /
• pp.580-586
• /
• 2017

The establishment of big data service environment requires both cloud-based network technology and clustering technology to improve the efficiency of information access. These cloud-based networks and clustering environments can provide variety of valuable information in real-time, which can be an intensive target of attackers attempting illegal access. In particular, attackers attempting IP spoofing can analyze information of mutual trust hosts constituting clustering, and attempt to attack directly to system existing in the cluster. Therefore, it is necessary to detect and respond to illegal attacks quickly, and it is demanded that the security policy is stronger than the security system that is constructed and operated in the existing single system. In this paper, we investigate routing pattern changes and use them as detection information to enable active correspondence and efficient information service in illegal attacks at this network environment. In addition, through the step-by -step encryption based on the routing information generated during the detection process, it is possible to manage the stable service information without frequent disconnection of the information service for resetting.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.10
• /
• pp.713-722
• /
• 2013

This paper proposes a method of using depth information to detect the hand region in real-time based on the cascade method. In order to ensure stable and speedy detection of the hand region even under conditions of lighting changes in the test environment, this study uses only features based on depth information, and proposes a method of detecting the hand region by means of a classifier that uses boosting and cascading methods. First, in order to extract features using only depth information, we calculate the difference between the depth value at the center of the input image and the average of depth value within the segmented block, and to ensure that hand regions of all sizes will be detected, we use the central depth value and the second order linear model to predict the size of the hand region. The cascade method is applied to implement training and recognition by extracting features from the hand region. The classifier proposed in this paper maintains accuracy and enhances speed by composing each stage into a single weak classifier and obtaining the threshold value that satisfies the detection rate while exhibiting the lowest error rate to perform over-fitting training. The trained classifier is used to classify the hand region, and detects the final hand region in the final merger stage. Lastly, to verify performance, we perform quantitative and qualitative comparative analyses with various conventional AdaBoost algorithms to confirm the efficiency of the hand region detection algorithm proposed in this paper.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2011.05a
• /
• pp.193-193
• /
• 2011

국제기구인 정부간 기후변화협의체(Intergovernmental Panel on Climate Change, 이하 IPCC)에서는 기후변화가 기온 상승에 따른 증발산량의 증가, 강수량 및 유출량의 시공간적 분포의 변동 등을 초래하여 수자원의 효율적 관리 및 안정적인 공급에 어려움을 증대시킬 것으로 전망하였다. 또한 IPCC 4차 보고서에 따르면 21세기말 지구의 평균기온은 현재보다 최대 $6.3^{\circ}C$정도 더 상승할 것으로 전망하였다. 전구평균기온이 $3.0^{\circ}C$ 증가할 경우 아시아에서만 연간 700만 명이상이 홍수피해 위기에 직면할 것으로 예상되고 있다. 국내의 경우 기온은 전구평균기온에 비해 2배 이상 높은 $1.5^{\circ}C$ 정도 상승하였으며, 최근 50년간의 강우일수는 감소한 반면 일강수량이 80mm 이상인 호우일수의 발생빈도는 증가되고 있다고 보고되었다. 또한 최근의 물수지 해석과 관련하여 거시적인 관점에서 기온 및 강수량 증가에 따른 물순환 과정을 모의하고, 농업용수, 댐건설, 도시화, 토지이용의 변화 등 인위적인 환경 변화 및 기후변화에 따른 유출량의 변화를 정량화하려는 연구들이 수행되고 있다(한국건설기술원, 2007). 이를 위하여 단기적이 아니라 장기적인 측면에서 유출분석을 할 필요가 있으나, 현재까지 보유하고 있는 실측 자료의 한계 및 이러한 조사를 위해 요구되는 시간 및 비용의 한계 때문에, 유출해석 모형을 주로 이용하고 있다. 본 연구에서는 장래 건설예정인 미계측 호소의 유량과 수질을 모의하기 위하여 하천, 하구, 호소 및 해역에 고루 적용할 수 있는 3차원 수리 동력학적인 모델인 EFDC 모형과 시간의 변화에 따른 수질을 모의하는데 가장 널리 이용하는 WASP 모형을 도입하였다. 향후, 내성천의 영주댐 건설과 같은 큰 변화가 발생하였을 기후 변화의 영향을 파악하기 위하여 EFDC와 WASP모형을 이용하여 대상유역에 대한 유출량과 수온의 변화를 통하여 A2, B1 기후변화 시나리오별로 2020년, 2050년, 2080년의 수질(BOD, TN, TP)변화를 분석하여 보았다. 연구의 결과는 다음과 같이 나타났다. EFDC 및 WASP 모형의 연계를 통한 기후 변화 시나리오에 따른 미래의 저수지 수질예측 모의를 수행한 결과, BOD, TN, TP 등 수질농도 변화는 2020년에서 2080년도로 갈수록 BOD, TN 다소 증가하는 경향을 나타내었고, TP농도는 감소하였다. 시나리오별 변화 특성은 TN, TP 농도는 A2 시나리오가 다소 높고, BOD 농도는 B1 시나리오가 A2보다 높은 것으로 나타났다. EFDC와 WASP을 이용하여 미계측 호소에 대한 기후변화 시나리오별로 적용하여 수질변화를 예측하여 보았는데, 향후 기후변화에 따른 기온, 유량변화와 수질 항목간의 상간관계 정립 및 수질 모의의 불확실성 등에 대한 추가 연구가 필요할 것으로 판단된다.

• Korean Journal of Social Welfare Studies
• /
• no.36
• /
• pp.281-299
• /
• 2008

The objective of this study was to examine the association between personal, housing, program, and service characteristics and quality of life among persons with severe mental illness living in supported housing. A cross sectional survey of a random sample of 237 clients residing in supported housing in Philadelphia was used to assess the association between personal and environmental characteristics, and quality of life. Data were collected from structured interviews, administrative data, the 2000 U.S. Census data file and the Philadelphia police crime database. Multiple regression analyses were used to identify personal and environment characteristics that are associated with quality of life. Clients with diagnoses of schizophrenia, those with lower levels of psychiatric symptoms, those with higher levels of physical health status, and those with higher levels of perceived supportiveness with staff had higher levels of quality of life. Findings of this study suggested that clients' clinical characteristics and consumer staff relationships can be important variables for understanding quality of life among supported housing residents. Factors associated with quality of life identified in this study may help service providers design and plan services to promote quality of life and stable independent living in the community of supported housing residents.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2016.05a
• /
• pp.281-281
• /
• 2016

기후변화로 인한 기상학적 자연재해로부터 대비하고 안정적인 용수공급을 위해 유역의 다양한 수문 요소들에 대한 분석 필요성이 증가하고 있다. 계절적 강수량의 편차가 큰 우리나라는 유역 통합 물관리가 중요하며, 효율적 수자원 관리와 물안보 확보를 위해 유역내 물순환을 이해하는 것이 중요하다. 유역의 유출을 결정하는 요소들에는 강우, 증발산량, 토양 수분 및 지하수 등이 있으며, 시간적으로는 홍수와 같이 단기에 발생하는 유출과 장기적으로 발생하는 유출이 있다. 장기 유출은 단기 유출에 비해 토양내 수분량이 무시할 수 없을 정도로 영향을 미치게 되므로, 1년 이상의 장기 유출 해석을 위해서는 강우가 발생하지 않는 기간 동안의 토양 수분량 변화와 증발산 영향을 고려할 필요가 있다. K-water에서 자체 개발된 분포형 장단기유출 모델인 K-DRUM은 유역을 격자(grid)단위로 구분하고 각 셀들에 대한 매개변수는 흐름방향도, 표고분포도, 토지이용도, 토지피복도 등을 GIS처리하여 일괄 입력할 수 있도록 함으로써 매개변수 산정과정에서 문제가 되는 경험적인 요인을 제거하였다. 흐름의 구분은 얕은면 흐름, 지표하 흐름, 지하수 흐름으로 구분하여 운동파법과 선형저류법을 적용하였다. 또한 초기 토양함수 자동보정기법으로 실제의 기저유출량을 재현하여 전체적인 유출모의 정확도를 높였으며, FAO-56 Penman-Monteith법을 적용한 증발산량 산정모듈과 Sugawara et al.(1984)이 제안한 개념적 융설 및 적설모듈을 추가하였다. K-DRUM모형을 이용한 유출분석은 용담댐 시험유역을 대상으로 2013년도 1년간의 유출모의를 수행하였다. 입력자료는 용담댐 유역의 지형, 토양 및 토지특성 정보와 시단위 강우 및 기상정보(온도, 바람, 일사 등)를 활용하였다. 분석 결과, 총 관측유출량은 7,151 ㎥/s이고 총 계산유출량 $8,257m^3/s$이며, 관측유출량 대비 계산유출량은 약 115% 정도로 나타났다. 연간 총 강우량은 1303.5 mm로 유역면적 약 $930km^2$을 적용하여 유역 총 강우량을 산정하면 $14,030m^3/s$로서 관측유출량은 유역 총 강우량 대비 51%이고 계산유출량은 59% 정도로 나타났다. 즉 유역 유출율은 약 51% 수준으로 보통의 유역과 유사한 수준이다. 관측된 토양수분량과 K-DRUM 모형의 계산된 토양수분량을 비교하기 위하여 관측 토양수분량의 비율을 이용하여 비교하였다. 모의결과 토양수분은 강우에 의해 변화하며, 관측결과와 유사한 형태로 나타남을 알 수 있었다.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.10
• /
• pp.391-398
• /
• 2021

Since the leased line is a structure that exclusively uses two connected areas for data transmission, a stable quality level and security are ensured, and despite the rapid increase in the number of switched lines, it is a line method that is continuously used a lot in companies. However, because the cost is relatively high, one of the important roles of the network operator in the enterprise is to maintain the optimal state by properly arranging and utilizing the resources of the network leased line. In other words, in order to properly support business service requirements, it is essential to properly manage bandwidth resources of leased lines from the viewpoint of data transmission, and properly predicting and managing leased line usage becomes a key factor. Therefore, in this study, various prediction models were applied and performance was evaluated based on the actual usage rate data of leased lines used in corporate networks. In general, the performance of each prediction was measured and compared by applying the smoothing model and ARIMA model, which are widely used as statistical methods, and the representative models of deep learning based on artificial neural networks, which are being studied a lot these days. In addition, based on the experimental results, we proposed the items to be considered in order for each model to achieve good performance for prediction from the viewpoint of effective operation of leased line resources.

• Journal of Internet Computing and Services
• /
• v.20 no.4
• /
• pp.91-102
• /
• 2019

In autonomous driving systems, the ability to classify pedestrians in images captured by cameras is very important for pedestrian safety. In the past, after extracting features of pedestrians with HOG(Histogram of Oriented Gradients) or SIFT(Scale-Invariant Feature Transform), people classified them using SVM(Support Vector Machine). However, extracting pedestrian characteristics in such a handcrafted manner has many limitations. Therefore, this paper proposes a method to classify pedestrians reliably and effectively using CNN's(Convolutional Neural Network) deep features and transfer learning. We have experimented with both the fixed feature extractor and the fine-tuning methods, which are two representative transfer learning techniques. Particularly, in the fine-tuning method, we have added a new scheme, called M-Fine(Modified Fine-tuning), which divideslayers into transferred parts and non-transferred parts in three different sizes, and adjusts weights only for layers belonging to non-transferred parts. Experiments on INRIA Person data set with five CNN models(VGGNet, DenseNet, Inception V3, Xception, and MobileNet) showed that CNN's deep features perform better than handcrafted features such as HOG and SIFT, and that the accuracy of Xception (threshold = 0.5) isthe highest at 99.61%. MobileNet, which achieved similar performance to Xception and learned 80% fewer parameters, was the best in terms of efficiency. Among the three transfer learning schemes tested above, the performance of the fine-tuning method was the best. The performance of the M-Fine method was comparable to or slightly lower than that of the fine-tuningmethod, but higher than that of the fixed feature extractor method.

• KIPS Transactions on Computer and Communication Systems
• /
• v.8 no.1
• /
• pp.17-28
• /
• 2019

In the financial investment management strategy, the distributed investment selecting and combining various financial assets is called portfolio management theory. In recent years, the blockchain based financial assets, such as cryptocurrencies, have been traded on several well-known exchanges, and an efficient portfolio management approach is required in order for investors to steadily raise their return on investment in cryptocurrencies. On the other hand, deep learning has shown remarkable results in various fields, and research on application of deep reinforcement learning algorithm to portfolio management has begun. In this paper, we propose an efficient financial portfolio investment management method based on Asynchronous Advantage Actor-Critic (A3C), which is a representative asynchronous reinforcement learning algorithm. In addition, since the conventional cross-entropy function can not be applied to portfolio management, we propose a proper method where the existing cross-entropy is modified to fit the portfolio investment method. Finally, we compare the proposed A3C model with the existing reinforcement learning based cryptography portfolio investment algorithm, and prove that the performance of the proposed A3C model is better than the existing one.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.9
• /
• pp.211-226
• /
• 2019

Pig CD45, the leukocyte common antigen, is encoded by the PTPRC gene and CD45 is a T cell-type specific tyrosine phosphatase with alternative splicing of its exons. The CD45 is a coordinated regulator of T cell antigen receptor (TCR) signal transduction achieved by dephosphorylating the phosphotyrosine of its substances, including $CD3{\zeta}$ chain of TCR, Lck, Fyn, and Zap-70 kinase. A dysregulation of CD45 is associated with a multitude of immune disease and has been a target for immuno-drug discovery. To characterize its key structural features with the effects of regulating TCR signaling, this study predicted the unknown structure of pig CD45RO (the smallest isoform) and the complex structure bound to the ITAM (REEpYDV) of $CD3{\zeta}$ chain via homology modeling and docking the peptide, based on the known human CD45 structures. These features were integrated into the structural plasticity of extracellular domains and functional KNRY and PTP signature motifs (the role of a narrow entrance into ITAM binding site) of the tyrosine phosphatase domains in a cytoplasmic region from pig CD45RO. This contributes to the selective recognition of phosphotyrosine from its substrates by adjusting the structural stability and binding affinity of the complex. The characterized features of pigCD45RO can be applied in virtual screening of the T-cell specific immunomodulator.

• Journal of Korea Entertainment Industry Association
• /
• v.15 no.2
• /
• pp.1-10
• /
• 2021

The purpose of this study is to explore a significant HPWS(High Performance Work System) model for the entertainment industry. HPWS is one of the most studied themes for managing human resources as well as a set of practices to elicit employees' commitment to an organization. Recently, the entertainment industry is growing rapidly, but it is difficult for entertainment firms to retain a stable profit unlike the manufacturing industry. This is because the performance of entertainment business tends to rely heavily on the capabilities and synergy of human resources. In order to suggest a systematic way to manage these, this research identified an effective HPWS model for entertainment business and provides a competitive advantage to entertainment firms, using ANP(Analytic Network Process). ANP is a multicriteria decision making technique that allows dependences and feedbacks among decision elements in the hierarchical or network structures in a holistic manner. The pairwise comparison data that prioritized the criteria of HPWS was collected from 28 team leaders in entertainment firms. According to our results, the most critical factor for HPWS in entertainment business is "employee involvement in decision-making." The sub-factors such as "open communication," "distributive decision-making," and "performance-driven reward" have a greater effect. These findings could provide implications for entertainment firms to determine which practices should be taken into account to accomplish HPWS.