• The Journal of Society for e-Business Studies
• /
• v.27 no.2
• /
• pp.37-64
• /
• 2022

As the social acceptance of artificial intelligence increases, the number of cases of applying machine learning methods to companies is also increasing. Technical factors such as accuracy and interpretability have been the main criteria for selecting machine learning methods. However, the success of implementing machine learning also affects management factors such as IT departments, operation departments, leadership, and organizational culture. Unfortunately, there are few integrated studies that understand the success factors of machine learning selection in which technical and management factors are considered together. Therefore, the purpose of this paper is to propose and empirically analyze a technology-management integrated model that combines task-tech fit, IS Success Model theory, and John Rice's algorithm selection process model to understand machine learning selection within the company. As a result of a survey of 240 companies that implemented machine learning, it was found that the higher the algorithm quality and data quality, the higher the algorithm-problem fit was perceived. It was also verified that algorithm-problem fit had a significant impact on the organization's innovation and productivity. In addition, it was confirmed that outsourcing and management support had a positive impact on the quality of the machine learning system and organizational cultural factors such as data-driven management and motivation. Data-driven management and motivation were highly perceived in companies' performance.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.30 no.5A
• /
• pp.433-442
• /
• 2010

A control of chloride diffusion coefficient is very essential for service life of reinforced concrete (RC) structures exposed to chloride attack so that much studies have been focused on this work. The purpose of this study is to derive the intended diffusion coefficient which satisfies intended service life and propose a technique for optimum concrete mixture through genetic algorithm(GA). For this study, 30 data with mixture proportions and related diffusion coefficients are analyzed. Utilizing 27 data, fitness function for diffusion coefficient is obtained with variables of water to binder ratio(W/B), weight of cement, mineral admixture(slag, flay ash, and silica fume), sand, and coarse aggregate. 3 data are used for verification of the results from GA. Average error from fitness function is observed to 18.7% for 27 data for diffusion coefficient with 16.0% of coefficient of variance. For the verification using 3 data, a range of error for mixture proportions through GA is evaluated to 0.3~9.3% in 3 given diffusion coefficients. Assuming the durability design parameters like intended service life, cover depth, surface chloride content, and replacement ratio of mineral admixture, target diffusion coefficient, where exterior conditions like relative humidity(R.H.) and temperature, is derived and optimum design mixtures for concrete are proposed. In this paper, applicability of GA is attempted for durability mixture design and the proposed technique would be improved with enhancement of comprehensive data set including wider range of diffusion coefficients.

• Journal of the Korean Geographical Society
• /
• v.43 no.2
• /
• pp.235-252
• /
• 2008

Many cartographers have for many years searched for a way to construct cartograms in which the sizes of geographic areas such as states, counties or census tracts are reseated in proportion to their population or some other socio-economic properties. While many techniques and algorithms for creating cartograms have been proposed, some of them are still extremely complex to generate in a proper manner, and many of them suffer either from this lack of readability or from seamless integration with GIS software. This paper, therefore, presents a simple population cartogam technique based on the Circular Cartogram Algorithm(CCA) by Dorling(1996) to tackle these drawbacks by drawing the areas as simple circles for use as a base map and linking the construction with GIS mapping processes. For an automated approach in the cartogram generation, this paper proposes a close coupling method of ArcView GIS 3.3. package in order for users to access to the cartopam algorithm. Then, they will be available through an interface that the ArcView GIS system allows user-written routines to be accessed easily. The CCA and its coupling architecture ensure to improve the potential applicability of the use of cartograms to census mapping at practical levels. As the cartogram examples, cartograms of population and property types in 2005 Korea census data sets are illustrated in the end, by which viewers can easily identify the residential concentration and their relative ratio in Seoul metropolitan area.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.45 no.2
• /
• pp.1-9
• /
• 2008

As the security requirements of mobile phones have been increasing, there have been extensive researches using one biometric feature (e.g., an iris, a fingerprint, or a face image) for authentication. Due to the limitation of uni-modal biometrics, we propose a method that combines face and iris images in order to improve accuracy in mobile environments. This paper presents four advantages and contributions over previous research. First, in order to capture both face and iris image at fast speed and simultaneously, we use a built-in conventional mega pixel camera in mobile phone, which is revised to capture the NIR (Near-InfraRed) face and iris image. Second, in order to increase the authentication accuracy of face and iris, we propose a score level fusion method based on SVM (Support Vector Machine). Third, to reduce the classification complexities of SVM and intra-variation of face and iris data, we normalize the input face and iris data, respectively. For face, a NIR illuminator and NIR passing filter on camera are used to reduce the illumination variance caused by environmental visible lighting and the consequent saturated region in face by the NIR illuminator is normalized by low processing logarithmic algorithm considering mobile phone. For iris, image transform into polar coordinate and iris code shifting are used for obtaining robust identification accuracy irrespective of image capturing condition. Fourth, to increase the processing speed on mobile phone, we use integer based face and iris authentication algorithms. Experimental results were tested with face and iris images by mega-pixel camera of mobile phone. It showed that the authentication accuracy using SVM was better than those of uni-modal (face or iris), SUM, MAX, NIN and weighted SUM rules.

• Journal of the Korean Society for information Management
• /
• v.34 no.1
• /
• pp.177-195
• /
• 2017

This study attempts to infer research fronts using factor graph model based on heterogeneous features. The model suggested by this study infers research fronts having documents with the potential to be cited multiple times in the future. To this end, the documents are represented by bibliographic, network, and content features. Bibliographic features contain bibliographic information such as the number of authors, the number of institutions to which the authors belong, proceedings, the number of keywords the authors provide, funds, the number of references, the number of pages, and the journal impact factor. Network features include degree centrality, betweenness, and closeness among the document network. Content features include keywords from the title and abstract using keyphrase extraction techniques. The model learns these features of a publication and infers whether the document would be an RF using sum-product algorithm and junction tree algorithm on a factor graph. We experimentally demonstrate that when predicting RFs, the FG predicted more densely connected documents than those predicted by RFs constructed using a traditional bibliometric approach. Our results also indicate that FG-predicted documents exhibit stronger degrees of centrality and betweenness among RFs.

• The KIPS Transactions:PartB
• /
• v.9B no.2
• /
• pp.139-146
• /
• 2002

The robot soccer simulation game is a dynamic multi-agent environment. In this paper we suggest a new reinforcement learning approach to each agent's dynamic positioning in such dynamic environment. Reinforcement learning is the machine learning in which an agent learns from indirect, delayed reward an optimal policy to choose sequences of actions that produce the greatest cumulative reward. Therefore the reinforcement learning is different from supervised learning in the sense that there is no presentation of input-output pairs as training examples. Furthermore, model-free reinforcement learning algorithms like Q-learning do not require defining or learning any models of the surrounding environment. Nevertheless these algorithms can learn the optimal policy if the agent can visit every state-action pair infinitely. However, the biggest problem of monolithic reinforcement learning is that its straightforward applications do not successfully scale up to more complex environments due to the intractable large space of states. In order to address this problem, we suggest Adaptive Mediation-based Modular Q-Learning (AMMQL) as an improvement of the existing Modular Q-Learning (MQL). While simple modular Q-learning combines the results from each learning module in a fixed way, AMMQL combines them in a more flexible way by assigning different weight to each module according to its contribution to rewards. Therefore in addition to resolving the problem of large state space effectively, AMMQL can show higher adaptability to environmental changes than pure MQL. In this paper we use the AMMQL algorithn as a learning method for dynamic positioning of the robot soccer agent, and implement a robot soccer agent system called Cogitoniks.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.7
• /
• pp.205-215
• /
• 2013

In digital imaging system, Bayer pattern is widely used and the observed image is degraded by optical blur during image acquisition process. Generally, demosaicing and deblurring process are separately performed in order to convert a blurred Bayer image to a high resolution color image. However, the demosaicing process often generates visible artifacts such as zipper effect and Moire artifacts when performing interpolation across edge direction in Bayer pattern image. These artifacts are emphasized by the deblurring process. In order to solve this problem, this paper proposes a deblurring algorithm combined with edge directional color demosaicing method. The proposed method is consisted of interpolation step and region classification step. Interpolation and deblurring are simultaneously performed according to horizontal and vertical directions, respectively during the interpolation step. In the region classification step, characteristics of local regions are determined at each pixel position and the directionally obtained values are region adaptively fused. Also, the proposed method uses blur model based on wave optics and deblurring filter is calculated by using estimated characteristics of local regions. The simulation results show that the proposed deblurring algorithm prevents the boosting of artifacts and outperforms conventional approaches in both objective and subjective terms.

• Proceedings of the Korean Society of Soil and Groundwater Environment Conference
• /
• 2003.09a
• /
• pp.298-301
• /
• 2003

생물학적 토양오염 복원기술은 산소와 영양염류를 오염토양에 공급하여 호기성 미생물의 대사작용을 자극함으로써 유류를 생분해 하는 방법으로 널리 사용되고 있다. 유류에 오염된 토양은 혐기성 상태인 경우가 대부분이기 때문에, 호기성 미생물을 이용하기 위해서는 충분한 산소를 공급하여야 하므로 운전비가 많이 드는 단점이 있다. 최근에는 혐기성 미생물을 이용하여 유류오염 토양을 정화하는 방법이 보고되고 있다. 혐기성 생분해 방법은 다소 분해 속도는 느리지만 산소를 공급하지 않기 때문에 경제적인 유류오염토양 복원 방법으로 주목받고 있다. 본 연구에서는 디젤을 사용하여 인위적으로 10000 mg/kg.TPH soil의 농도로 오염시킨 토양 50g을 100$m\ell$ 용적의 vial에 주입하고 하수처리장의 혐기성 소화조 슬러지를 15$m\ell$, 30$m\ell$을 주입하여 배양하였으며 TPH의 분해량과 CH$_4$ 및 $CO_2$ 발생량을 측정하였다. vial의 기상을 $N_2$가스로 치환함으로써 혐기성 상태가 되도록 하였으며, 35$^{\circ}C$에서 90일간 배양하였다. 그 결과, 슬러지를 주입하지 않은 대조군의 경우에는 TPH의 분해가 거의 없었지만, 슬러지를 주입한 경우에는 TPH(Total Petroleum Hydrocarbon)농도가 55% 제거된 것으로 나타났다. TPH의 분해는 CH$_4$ 및 $CO_2$ 발생량과 밀접한 상관관계를 보였다. 본 연구의 결과로부터 하수처리장의 혐기성 소화조 슬러지를 이용한 유류오염 토양의 복원 가능성을 확인할 수 있었다.양에서 유동 가능성이 있는 중금속만을 추출하였다. 분석실험은 토양의 Cd2+ 와 Pb2+를 대상으로 행하여졌으며, 여러 토양에서 추출 분석한 결과를 EDTA분석결과와 비교하였다. 실험결과, 중금속은 매우 신속하게 고분자 자성체와 결합하였고, 그 후 자성체를 외부 자장으로 모은 후 산으로 용해시키고, 결합된 중금속은 Graphite furnace AAS로 분석함으로써 빠르고 효율적으로 분석실험을 수행할 수 있음을 알 수 있었다. 한편, 실험에서 나타난 수치들을 비교 검토한 결과 토양 분석시 sandy soil에서는 자성체를 이용한 분석이 EDTA에 의한 방법보다 더 높은 추출도를 보인 반면, silt 함량이 많은 토양의 경우에서 EDTA분석에서 더 높은 중금속 추출도를 보였다.s 중에서 490nm와 555nm의 복합밴드를 포함하는 OC2 알고리즘(ocean color chlorophyll 2 algorithm)을 사용하는 것이 OC2 series 및 OC4 알고리즘보다 좋은 추정 값을 도출할 수 있을 것으로 기대된다.환경에서는 5일에서 7월에 주로 이 충체의 유충이 발육되고 전파되는 것으로 추측되었다.러 가지 방법들을 적극 적용하여 금후 검토해볼 필요가 있을 것이다.잡은 전혀 삭과가 형성되지 않았다. 이 결과는 종간 교잡종을 자방친으로 하고 그 자방친의 화분친을 사용할 때만 교잡이 이루어지고 있음을 나타내고 있다. 따라서 여교잡을 통한 종간잡종 품종육성 활용방안을 금후 적극 확대 검토해야 할 것이다하였다.함을 보이고 있다.X> , ZnCl$_{3}$$^{-}$같은 이온과 MgCl$^{+}$, MgCl$_{2}$같은 이온종을 형성하기 때문인것 같다. 한편 어떠한 용리액에서

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.11 no.4
• /
• pp.331-339
• /
• 2018

The IEEE 1588, commonly known as a precision time protocol (PTP), is a standard for precise clock synchronization that maintains networked measurements and control systems. The best master clock (BMC) algorithm is currently used to establish the master-slave hierarchy for PTP. The BMC allows a slave clock to automatically take over the duties of the master when the slave is disconnected due to a link failure and loses its synchronization; the slave clock depends on a timer to compensate for the failure of the master. However, the BMC algorithm does not provide a fast recovery mechanism in the case of a master failure. In this paper, we propose a technique that combines the IEEE 1588 with network bonding to provide a faster recovery mechanism in the case of a master failure. This technique is implemented by utilizing a pre-existing library PTP daemon (Ptpd) in Linux system, with a specific profile of the IEEE 1588 and it's controlled through bonding modes. Network bonding is a process of combining or joining two or more network interfaces together into a single interface. Network bonding offers performance improvements and redundancy. If one link fails, the other link will work immediately. It can be used in situations where fault tolerance, redundancy, or load balancing networks are needed. The results show combining IEEE 1588 with network bonding enables an incredible shorter recovery time than simply just relying on the IEEE 1588 recovery method alone.

• Proceedings of the Korean Society of Soil and Groundwater Environment Conference
• /
• 2003.04a
• /
• pp.438-441
• /
• 2003

남해 동부 연안 지역 지하수의 해수 침투 영향을 광역적으로 파악하기 위하여, 202개소의 지하수 시료를 채취하고 수리지구화학적 연구를 수행하였다. 전체 시료 중 14.4%가 500 $\mu\textrm{m}$/cm을 초과하는 높은 EC값을 나타내어 해수 영향을 시사해 주었다. 해수 영향 판단의 또 다른 파라메터로 사용되는 CI/HCO$_3$ 몰비는 전체 시료의 23.3%가 1.3 이상의 값을 나타내었다. 한편, 대표적으로 해수침투 영향 및 인위적 오염의 영향을 각각 반영하는 것으로 알려진 Cl과 NO$_3$의 농도에 관한 누적도수분포도를 작성하여 배경수질군과 오염영향군을 구분짓는 배경치(background concentration)를 구한 결과, 각각 Cl = 22.3 mg/1 및 NO$_3$= 23.1 mg/l로 나타났다. 이 두 파라메터의 농도 분포를 기준으로 하여 채취된 지하수 시료를 크게 4개의 그룹으로 나눌 수 있었다. 그 결과, 자연적 또는 인위적 기원의 오염이 배제된 그룹 1은 전체 시료의 31%, 자연적 오염(해수 영향)을 반영하는 그룹 2는 전체의 24%, 인위적 오염의 영향을 반영하는 그룹 3은 전체의 9%, 해수 영향 및 인위적 오염을 동시에 반영하는 그룹4는 전체의 36%로 나타났다. 또한 그룹2와 그룹4는 대부분 Na-Cl유형으로 진화하는 Ca-Cl유형을 나타내었다. 따라서, 여러 지구화학 방법에 의한 해수 영향 판단 결과는 서로 잘 일치하고 있음을 알 수 있다. 결국, 지구화학적 파라메터를 종합적으로 활용함으로써, 연안 지역 해수침투의 효과적인 파악은 물론 예측 및 방지, 복구에 효과적으로 사용될 수 있을 것으로 판단된다.으로 토양에서 유동 가능성이 있는 중금속만을 추출하였다. 분석실험은 토양의 Cd2+ 와 Pb2+를 대상으로 행하여졌으며, 여러 토양에서 추출 분석한 결과를 EDTA분석결과와 비교하였다. 실험결과, 중금속은 매우 신속하게 고분자 자성체와 결합하였고, 그 후 자성체를 외부 자장으로 모은 후 산으로 용해시키고, 결합된 중금속은 Graphite furnace AAS로 분석함으로써 빠르고 효율적으로 분석실험을 수행할 수 있음을 알 수 있었다. 한편, 실험에서 나타난 수치들을 비교 검토한 결과 토양 분석시 sandy soil에서는 자성체를 이용한 분석이 EDTA에 의한 방법보다 더 높은 추출도를 보인 반면, silt 함량이 많은 토양의 경우에서 EDTA분석에서 더 높은 중금속 추출도를 보였다.s 중에서 490nm와 555nm의 복합밴드를 포함하는 OC2 알고리즘(ocean color chlorophyll 2 algorithm)을 사용하는 것이 OC2 series 및 OC4 알고리즘보다 좋은 추정 값을 도출할 수 있을 것으로 기대된다.환경에서는 5일에서 7월에 주로 이 충체의 유충이 발육되고 전파되는 것으로 추측되었다.러 가지 방법들을 적극 적용하여 금후 검토해볼 필요가 있을 것이다.잡은 전혀 삭과가 형성되지 않았다. 이 결과는 종간 교잡종을 자방친으로 하고 그 자방친의 화분친을 사용할 때만 교잡이 이루어지고 있음을 나타내고 있다. 따라서 여교잡을 통한 종간잡종 품종육성 활용방안을 금후 적극 확대 검토해야 할 것이다하였다.함을 보이고 있다.X> , ZnCl$_{3}$$^{-}$같은 이온과 MgCl$^{+}$, MgCl$_{2}$같은 이온종을 형성하기 때문인것 같다. 한편 어