• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 2017.04a
• /
• pp.162-162
• /
• 2017

구글에서 공개한 Tensorflow를 이용한 여러 학문 분야의 연구가 활발하다. 농업 시설환경을 대상으로 한 빅데이터의 축적이 증가함과 아울러 실효적인 정보 획득을 위한 각종 데이터 분석 및 마이닝 기법에 대한 연구 또한 활발한 상황이다. 한편, 타 분야의 성공적인 심층학습기법 응용사례에 비하여 농업 분야에서의 응용은 초기 성장 단계라 할 수 있다. 이는 농업 현장에서 취득한 정보의 난해성 및 완성도 높은 생육/환경 모델링 정보의 부재로 실효적인 전과정 처리 기술 도출에 소요되는 시간, 비용, 연구 환경이 상대적으로 부족하기 때문일 것이다. 특히, 센서 기반 데이터 취득 기술 증가에 따라 비약적으로 방대해진 수집 데이터를 시간 복잡도가 높은 심층 학습 모델링 연산에 기계적으로 단순 적용할 경우 시간 효율적인 측면에서 성공적인 결과 도출에 애로가 있을 것이다. 매우 높은 시간 복잡도를 해결하기 위하여 제시된 하드웨어 가속 기능의 경우 일부 개발환경에 국한이 되어 있다. 일례로, 구글의 Tensorflow는 오픈소스 기반 병렬 클러스터링 기술인 MPICH를 지원하는 알고리즘을 공개하지 않고 있다. 따라서, 본 연구에서는 심층학습 기법 연구에 있어서, 예상 가능한 다양한 자원을 활용하여 최대한 연산의 결과를 빨리 도출할 수 있는 하드웨어적인 접근 방법을 모색하였다. 호스트에서 수행하는 일방적인 학습 알고리즘과 달리 이기종간 심층 학습이 가능하기 위해선 우선, NFS(Network File System)를 이용하여 데이터 계층이 상호 연결이 되어야 한다. 이를 위해서 고속 네트워크를 기반으로 한 NFS의 이용이 필수적이다. 둘째로 제한된 자원의 한계를 극복하기 위한 메모 공유 라이브러리가 필요하다. 셋째로 이기종간 프로세서에 최적화된 병렬 처리용 컴파일러를 이용해야 한다. 가장 중요한 부분은 이기종간의 처리 능력에 따른 작업을 고르게 분배할 수 있는 작업 스케쥴링이 수행되어야 하며, 이는 처리하고자 하는 데이터의 형태에 따라 매우 가변적이므로 해당 데이터 도메인에 대한 엄밀한 사전 벤치마킹이 수행되어야 한다. 이러한 요구조건을 대부분 충족하는 Open-CL ver1.2(https://www.khronos.org/opencl/)를 이용하였다. 최신의 Open-CL 버전은 2.2이나 본 연구를 위하여 준비한 4가지 이기종 시스템에서 모두 공통적으로 지원하는 버전은 1.2이다. 실험적으로 선정된 4가지 이기종 시스템은 1) Windows 10 Pro, 2) Linux-Ubuntu 16.04.4 LTS-x86_64, 3) MAC OS X 10.11 4) Linux-Ubuntu 16.04.4 LTS-ARM Cortext-A15 이다. 비교 분석을 위하여 NVIDIA 사에서 제공하는 Pascal Titan X 2식을 SLI로 구성한 시스템을 준비하였다. 개별 시스템에서 별도로 컴파일 된 바이너리의 이름을 통일하고, 개별 시스템의 코어수를 동일하게 균등 배분하여 100 Hz의 데이터로 입력이 되는 온도 정보와 조도 정보를 입력으로 하고 이를 습도정보에 Linear Gradient Descent Optimizer를 이용하여 Epoch 10,000회의 학습을 수행하였다. 4종의 이기종에서 총 32개의 코어를 이용한 학습에서 17초 내외로 연산 수행을 마쳤으나, 비교 시스템에서는 11초 내외로 연산을 마치는 결과가 나왔다. 기보유 하드웨어의 적절한 활용이 가능한 심층학습 기법에 대한 연구를 지속할 것이다

• Journal of Korean Society of Transportation
• /
• v.34 no.3
• /
• pp.222-233
• /
• 2016

Recently, mobile phone data was applied in travel demand modeling as a new source of dynamic population movement. This study is also aimed to estimate "occupancy population" during a given period of time within a given spatial region using mobile phone data. An occupancy population was defined as the number of people residing or moving within a given time and space. In case of Seoul Metropolitan area, we divided the area into a number of administrative districts as zones for analysis and estimated the occupancy population of each zone by mobile phone data collected by SK telecom Co., a wireless telecommunication provider in Korea. For the expansion of mobile phone data, a new concept of "communication probability" was introduced and applied in the estimation of occupancy population of each zone by the hour. We compared the estimated number with the daytime population and the daytime population index referred by the Statistics Korea. The results showed that a positive correlation existed between the estimated number and the statistical number by nationwide survey. It was concluded that mobile phone data could be more cost-effective sources than a conventional survey method to estimate the pattern of population movement by the hour or by the day.

• Journal of The Korean Association For Science Education
• /
• v.35 no.3
• /
• pp.383-393
• /
• 2015

This study analyzed the 6th grade elementary science textbook 'Science stories' reading process of students by utilizing eye movement tracking techniques. Participants read 3 articles in the new experimental science textbooks and solved 9 problems about each article. By understanding and academic achievement results, participants were divided into high-groups, middle-groups, and low-groups. The results of eye movement characteristics of the high-groups and low-groups had the following differences. Number of fixations and number of regressions were higher in high-groups. Average fixation duration and average regressive fixation duration were longer in low-groups. Fixation time for the key sentence of the article was longer in high-groups. Analysis of a scan path and post-interview, high-groups had frequent regression between sentences and they knew where the core of the article is and paid much attention there. In contrast low-groups are sequentially read most articles and some of them had a leap of abnormal range. Problem-solving approach is also different between groups. In conclusion reading style is associated with the science stories comprehension and students who had more regressions, much core search process, effective attention distribution, high concentration showed better understanding results. Also words or sentences used in textbooks are associated with science stories comprehension.

• Korean Journal of Construction Engineering and Management
• /
• v.9 no.5
• /
• pp.159-167
• /
• 2008

This study provides a effective approach to the construction management problem with the limited number or amount of available resources using the analytic hierarchy process. Construction management is a series of decision making processes for planning and controling of cost, time and quality as main objectives in construction works. When several activities need the limited same resource at the same time, it is very hard to decide the priority of the activities in the real situations. For that the scientific decision making method and procedure for resource allocation are required. This study solves the resource allocation problem by dealing with the decision making problem which the activities are distributed to multiple projects and under multiple criteria. The analytic hierarchy process is a method devised to solve complex multi-criteria decision problems. The result shows that this study can be effectively used to make decisions in situations involving multiple objectives by evaluating the prioritized ranking and degree of the activity alternatives based on the overall preferences.

• The Journal of the Korea Contents Association
• /
• v.21 no.1
• /
• pp.541-551
• /
• 2021

Among the numerous duties of a librarian in a library, the work of arranging books is a job that the librarian has to do one by one. Thus, the cost of labor and time is large. In order to solve this problem, the interest in book-arranging robots based on artificial intelligence has recently increased. In this paper, we propose the K-ACO algorithm, which is the shortest path algorithm for multi-stops that can be applied to the library book arrangement robots. The proposed K-ACO algorithm assumes multiple robots rather than one robot. In addition, the K-ACO improves the ANT algorithm to create K clusters and provides the shortest path for each cluster. In this paper, the performance analysis of the proposed algorithm was carried out from the perspective of book arrangement time. The proposed algorithm, the K-ACO algorithm, was applied to a university library and compared with the current book arrangement algorithm. Through the simulation, we found that the proposed algorithm can allocate fairly, without biasing the work of arranging books, and ultimately significantly reduce the time to complete the entire work. Through the results of this study, we expect to improve quality services in the library by reducing the labor and time costs required for arranging books.

• Journal of Teachers' Pension
• /
• v.2
• /
• pp.47-102
• /
• 2017

오늘날 대다수의 선진 국가들은 고령화 사회에 대비하여 자국의 노후소득보장 제도를 대대적으로 개혁해 오고 있다. 우리나라의 경우에서도 지난 2015년 사학연금제도의 개혁이 이러한 취지에 해당될 수 있을 것이다. 본 연구에서는 고령화 사회의 문제가 단순히 노인부양비용의 증가 그 자체가 아니라, 평균수명의 증가에도 불구하고 늘어나게 된 노후의 삶에 대한 시간적 배분이 근로와 여가에 걸쳐 균형적으로 이루어지지 않고, 사회적 부양을 필요로 하는 노후의 여가만 일방적으로 늘어나고 있다는 점을 문제점으로 지적하였다. 따라서 이러한 차원에서 볼 때 고령화 사회의 문제는 생애근로기간의 연장을 통해서만 효과적으로 극복할 수 있을 것으로 생각된다, 하지만 이와는 반대로 개인별로 건강상태나 가족상황 등의 이유로 생애근로주기의 연장이 불가능한 사람들을 위하여 별도의 제도적 장치가 추가적으로 마련되어야 할 것이다. 종합해 보면, 고령화 사회의 노동시장 문제는 개인별로 다양한 욕구나 능력을 반영하여 각자에게 다양한 선택권을 보장해 줄 수 있는 방향으로 개선되어야 할 필요가 있다. 본 연구에서는 고령화 사회에 대비하여 연금수급연령 상향조정의 필요성을 사학연금제도를 중심으로 살펴보고, 대신 그로 인해 발생할 수 있는 소득공백문제와 연금가입경력 공백문제 등 제반의 충격을 흡수할 수 있는 제도적 장치로서 점진적 퇴직제도의 도입방안을 제안하였다. 개략적으로 사학연금제도에 있어서 점진적 퇴직모형은 법정연금수급연령의 인상 일정에 따라 다음과 같이 운영하는 방안을 제안하였다. 먼저 법정연금수급연령이 60세로 유지되는 2022년까지의 단기적 대책으로서 여기서 점진적 퇴직의 자격연령은 모든 가입자에게 60세로 적용하도록 한다. 이 경우 가입자들의 신분구분에 따라 각각 교수 5년, 교원 2년(문제해결에 대한 정책적 의지에 따라 이행구간을 확장할 수도 있음) 그리고 교직원 0년의 조기의 점진적 퇴직이 허용되므로, 현재 교원이나 교수의 임용대란문제에 효과적으로 대응을 할 수 있는 장점이 있다. 다음으로는 2023년 이후 2033년 사이 법정연금수급연령의 인상단계에 해당되는 기간 동안의 대책으로서 여기서는 교수, 교원, 교직원에게 적용되는 정년연령과 매년도 법정연금수급연령 사이의 기간을 조기의 점진적 퇴직 이행구간으로 정하도록 한다. 그리고 이러한 이행구간에 상당하는 기간만큼 후기의 점진적 퇴직 이행구간을 별도로 설정하여 그에 적절한 혜택이 주어질 수 있도록 한다. 마지막으로 2033년 이후부터는 교수, 교사, 교직원의 신분구분 없이 모두에게 적용되는 사항으로서 65세를 기준으로 그 이전의 5년은 사학연금의 적용을 받는 조기의 점진적 퇴직 그리고 그 이후의 5년은 국민연금의 적용을 받는 후기의 점진적 퇴직이 이루어질 수 있도록 한다. 그리고 전체 10년의 점진적 퇴직 이행구간 동안 개인별로 퇴직시점이나 퇴직형태의 선택이 자유롭게 이루어질 수 있도록 하기 위하여 보험수리의 원칙에 입각한 감액률 또는 가산율의 엄격한 적용을 제안하였다. 그리고 고령계층이 자신의 근로시간을 단계적으로 단축할 수 있도록 하고, 그 과정에서 발생하게 되는 소득의 감소부분은 별도의 제도적 방법(가교연금, 시간가치적립계정 등)으로 충당하도록 하는 방안을 제안하였다. 나아가 점진적 퇴직제도의 운영방식은 근로시간의 단축뿐만 아니라 작업부담의 경감 등에 대해서도 인정을 해주도록 해줌으로써 임금피크제도의 기능과 연계가 가능할 수 있도록 할 것을 제안하였다.

• Journal of Intelligence and Information Systems
• /
• v.16 no.3
• /
• pp.121-145
• /
• 2010

University timetabling depending on the educational environments of universities is an NP-hard problem that the amount of computation required to find solutions increases exponentially with the problem size. For many years, there have been lots of studies on university timetabling from the necessity of automatic timetable generation for students' convenience and effective lesson, and for the effective allocation of subjects, lecturers, and classrooms. Timetables are classified into a course timetable and an examination timetable. This study focuses on the former. In general, a course timetable for liberal arts is scheduled by the office of academic affairs and a course timetable for major subjects is scheduled by each department of a university. We found several problems from the analysis of current course timetabling in departments. First, it is time-consuming and inefficient for each department to do the routine and repetitive timetabling work manually. Second, many classes are concentrated into several time slots in a timetable. This tendency decreases the effectiveness of students' classes. Third, several major subjects might overlap some required subjects in liberal arts at the same time slots in the timetable. In this case, it is required that students should choose only one from the overlapped subjects. Fourth, many subjects are lectured by same lecturers every year and most of lecturers prefer the same time slots for the subjects compared with last year. This means that it will be helpful if departments reuse the previous timetables. To solve such problems and support the effective course timetabling in each department, this study proposes a university timetabling support system based on two phases. In the first phase, each department generates a timetable template from the most similar timetable case, which is based on case-based reasoning. In the second phase, the department schedules a timetable with the help of interactive user interface under the timetabling criteria, which is based on rule-based approach. This study provides the illustrations of Hanshin University. We classified timetabling criteria into intrinsic and extrinsic criteria. In intrinsic criteria, there are three criteria related to lecturer, class, and classroom which are all hard constraints. In extrinsic criteria, there are four criteria related to 'the numbers of lesson hours' by the lecturer, 'prohibition of lecture allocation to specific day-hours' for committee members, 'the number of subjects in the same day-hour,' and 'the use of common classrooms.' In 'the numbers of lesson hours' by the lecturer, there are three kinds of criteria : 'minimum number of lesson hours per week,' 'maximum number of lesson hours per week,' 'maximum number of lesson hours per day.' Extrinsic criteria are also all hard constraints except for 'minimum number of lesson hours per week' considered as a soft constraint. In addition, we proposed two indices for measuring similarities between subjects of current semester and subjects of the previous timetables, and for evaluating distribution degrees of a scheduled timetable. Similarity is measured by comparison of two attributes-subject name and its lecturer-between current semester and a previous semester. The index of distribution degree, based on information entropy, indicates a distribution of subjects in the timetable. To show this study's viability, we implemented a prototype system and performed experiments with the real data of Hanshin University. Average similarity from the most similar cases of all departments was estimated as 41.72%. It means that a timetable template generated from the most similar case will be helpful. Through sensitivity analysis, the result shows that distribution degree will increase if we set 'the number of subjects in the same day-hour' to more than 90%.

• Journal of Yeungnam Medical Science
• /
• v.4 no.2
• /
• pp.139-148
• /
• 1987

The community health practitioners (CHP) play an important role in primary health care services to the underserved population in rural area. Time and motion study of 26 CHPs in Kyungpook Province was conducted through work diary method for 6 consecutive days from the time they arrived until they left the primary health post(PHP) during the past 3 weeks from November 16 to December 5, 1987. The allocation of activity time by working category, service category, location of activity and CHP's function was analyzed according to the characteristics of CHPs i. e., age, marital status and experience as CHP. The major findings are as follows : The mean activity time per CHP in a week was 2,918 minutes. The length of their working hours was longer for older, married and more experienced CHPs than others. About 80% of the CHP's activities took place within the PHP and only about 20% occured outside of the PHP. Working hours for the outdoor activities were longer for younger, single and less experienced CHPs than others. The allocation of activity time by working category showed 46.3% in the technical work and 18.7% in the administrative work. Working hours for the technical activities were longer for younger, single and less experienced CHPs than others. The percentage of activity time revealed greatest as much as 63.1% for direct patient care in technical work and 61.6% for record keeping in administrative work. Of the total working hours in a week, direct patient care and public health activities accounted for 29.2% and 16.2%, respectively. Of the indoor activities, working hours for direct patient care were longer than those for public health activities. However, of the outdoor activities, working hours for public health activities were longer than those for direct patient care. The allocation of activity time by CHP's function showed 49.7% in management of common disease, 31.8% in management of PHP and technical supervision of village health workers, 9.5% in MCH and family planning, 6.6% in community health management and 2.4% in community approach. Based on these findings, it was found that CHPs were mainly working in the PHP with a majority of their time being spent for direct patient care rather than preventive and promotive health cares. To enhance the preventive and promotive health services of the CHPs and to involve the activities for community development, refresher course for CHPs should be reinforced and supervision mechanism of the CHPs should be established and operated in Gun- and province-level.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.17 no.6
• /
• pp.69-78
• /
• 2017

Shannon of the 5G smartphone and Fourier of the signal processing meet in the sampling theorem (2 times the highest frequency 1). In this paper, the initial Shannon Theorem finds the Shannon capacity at the point-to-point, but the 5G shows on the Relay channel that the technology has evolved into Multi Point MIMO. Fourier transforms are signal processing with fixed parameters. We analyzed the performance by proposing a 2N-1 multivariate Fourier-Jacket transform in the multimedia age. In this study, the authors tackle this signal processing complexity issue by proposing a Jacket-based fast method for reducing the precoding/decoding complexity in terms of time computation. Jacket transforms have shown to find applications in signal processing and coding theory. Jacket transforms are defined to be $n{\times}n$ matrices $A=(a_{jk})$ over a field F with the property $AA^{\dot{+}}=nl_n$, where $A^{\dot{+}}$ is the transpose matrix of the element-wise inverse of A, that is, $A^{\dot{+}}=(a^{-1}_{kj})$, which generalise Hadamard transforms and centre weighted Hadamard transforms. In particular, exploiting the Jacket transform properties, the authors propose a new eigenvalue decomposition (EVD) method with application in precoding and decoding of distributive multi-input multi-output channels in relay-based DF cooperative wireless networks in which the transmission is based on using single-symbol decodable space-time block codes. The authors show that the proposed Jacket-based method of EVD has significant reduction in its computational time as compared to the conventional-based EVD method. Performance in terms of computational time reduction is evaluated quantitatively through mathematical analysis and numerical results.

• Journal of Korea Water Resources Association
• /
• v.53 no.8
• /
• pp.569-582
• /
• 2020

Recently, Korea has faced a change in the pattern of water use due to urbanization, which has caused difficulties in understanding the rainfall-runoff process and optimizing the allocation of available water resources. In this perspective, spatially downscaled analysis of the water balance is required for the efficient operation of water resources in the National Water Management Plan and the River Basin Water Resource Management Plan. However, the existing water balance analysis does not fully consider water circulation and availability in the basin, thus, the obtained results provide limited information in terms of decision making. This study aims at developing a novel water circulation analysis model that is designed to support a quasi-real-time assessment of water availability along the river. The water circulation model proposed in this study improved the problems that appear in the existing water balance analysis. More importantly, the results showed a significant improvement over the existing model, especially in the low flow simulation. The proposed modeling framework is expected to provide primary information for more realistic hydrological drought monitoring and drought countermeasures by providing streamflow information in quasi-real-time through a more accurate natural flow estimation approach with highly complex network.