• Journal of Korean Society of Forest Science
• /
• v.101 no.3
• /
• pp.480-487
• /
• 2012

This study was conducted to search the effects of debris barrier on the benthic macroinvertebrate. Gimcheon was selected as the survey site as it has relatively stable ecosystem with constantly running water. The survey was conducted 6 times before and after the construction of debris barrier from February in 2009 to October in 2010. In the first survey before construction, the identified species were 36 species belonged to 22 families, 9 order, 4 class, and 4 phylum. The figure slightly decreased to 30 species belonged to 18 families, 7 order, 2 class, and 2 phylum in the sixth survey after construction. Before construction, occupation ratio of EPT taxa was showed in the following order: Ephemeroptera (50.0%, 85.0%), Trichoptera (35.3%, 10.0%), and Plecopteran (14.8%, 5.0%). After construction, it was showed in the following order: Trichoptera (50.3%, 68.0%), Ephemeroptera (42.1%, 29.4%), and Plecopteran (7.5%, 2.7%). Ephemeroptera was the highest before construction. Trichoptera increased rapidly after construction. The Diversity, Richness, Evenness, and Dominance indices were all turned low in the second survey right after the construction. However, each index tended to increase with the course of time. In Functional Feeding Groups, GC type was the highest of 60.7% before construction. After construction, SC(53.1%) and FC(35.4%) increased rapidly and they became stabilized since the third survey. The result of this study reveals that debris barrier greatly affects the Aquatic Ecosystem right after its construction, but the system becomes stable and returns to normal with the course of time (about 18 months). Therefore, the study considering various influence factors such as time is required to recover completely through further long-term monitoring.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.54 no.8
• /
• pp.12-19
• /
• 2017

In this paper a super-resolution time delay estimation algorithm that estimates the time delays of spread spectrum signals using sparse signal reconstruction approach is introduced. So far, the correlation method has been mostly used to estimate the time delays of spread spectrum signals. However it fails to accurately estimate the time delays in the case where the signals are spaced within approximately 1 PN chip duration and a further processing should be applied to the correlation outputs in order to enhance the resolution capability. Recently sparse signal approaches attract much interest in the area of directions-of-arrival estimation, of which SPICE is the most representative. Thus we introduce a super-resolution time delay estimation algorithm based on the SPICE approach and compare its performance with that of MUSIC algorithm by applying them to the ISO/IEC 24730-2.1 RTLS system.

• Proceedings of The KACE
• /
• 2017.08a
• /
• pp.201-204
• /
• 2017

빅 데이터의 시대가 도래하면서 이전보다 데이터로부터 유의미한 정보를 추출하는 것에 대한 연구가 활발하게 진행되고 있다. 딥러닝은 텍스트, 이미지, 동영상 등 다양한 데이터에 대한 학습을 가능하게 할 뿐만 아니라 높은 학습 정확도를 보임으로써 차세대 머선러닝 기술로 각광 받고 있다. 그러나 딥러닝은 일반적으로 학습해야하는 데이터가 많을 뿐만 아니라 학습에 요구되는 시간이 매우 길다. 또한 데이터의 전처리 수준과 학습 모델 튜닝에 의해 학습정확도가 크게 영향을 받기 때문에 활용이 어렵다. 딥러닝에서 학습에 요구되는 데이터의 양과 연산량이 많아지면서 분산 처리 프레임워크 기반 분산 학습을 통해 학습 정확도는 유지하면서 학습시간을 단축시키는 사례가 많아지고 있다. 본 연구에서는 범용 분산 처리 프레임워크인 아파치 스파크에서 데이터 병렬화 기반 분산 학습 모델을 활용하여 모바일 빅 데이터 분석을 위한 딥러닝을 구현한다. 딥러닝을 구현할 때 분산학습을 통해 학습 속도를 높이면서도 학습 정확도를 높이기 위한 모델 튜닝 방법을 연구한다. 또한 스파크의 분산 병렬처리 효율을 최대한 끌어올리기 위해 파티션 병렬 최적화 기법을 적용하여 딥러닝의 학습속도를 향상시킨다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2017.01a
• /
• pp.15-16
• /
• 2017

IoT 시대가 도래함에 따라 실시간으로 대규모 데이터가 발생하고 있으며 이를 효율적으로 처리하고 활용하기 위한 분산 처리 및 기계 학습에 대한 관심이 높아지고 있다. 아파치 스파크는 RDD 기반의 인 메모리 처리 방식을 지원하는 분산 처리 플랫폼으로 다양한 기계 학습 라이브러리와의 연동을 지원하여 최근 차세대 빅 데이터 분석 엔진으로 주목받고 있다. 본 논문에서는 아파치 스파크 기반 기계 학습 라이브러리 성능 비교를 통해 아파치 스파크와 연동 가능한 기계 학습라이브러리인 MLlib와 아파치 머하웃, SparkR의 데이터 처리 성능을 비교한다. 이를 위해, 대표적인 기계 학습 알고리즘인 나이브 베이즈 알고리즘을 사용했으며 학습 시간 및 예측 시간을 비교하여 아파치 스파크 기반에서 실시간 데이터 처리에 적합한 기계 학습 라이브러리를 확인한다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.172-174
• /
• 2021

In the existing industry, maintenance was carried out in the form of preventive maintenance such as occurrence of unnecessary idle time due to limited monitoring and maintenance. However, with the advent of the Fourth Industrial Revolution, real-time monitoring is possible in many industries including mining, manufacturing, oil and gas, and commercial agriculture, and it is desired to minimize idle time due to maintenance. In particular, there is a growing interest in predictive maintenance that can reduce costs and maximize operational efficiency by predicting and maintaining a failure before equipment and equipment fail. In this study, we look at the predictive maintenance technology that can verify the abnormal condition of the equipment of the smart factory in advance and monitor the abnormal condition in real time.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.19 no.1
• /
• pp.1-16
• /
• 2020

With the advent of the fourth industrial revolution era, there has been a growing interest in deep learning using big data, and studies using deep learning have been actively conducted in various fields. In the transportation sector, there are many advantages to using deep learning in research as much as using deep traffic big data. In this study, a short -term travel speed prediction model using LSTM, a deep learning technique, was constructed to predict the travel speed. The LSTM model suitable for time series prediction was selected considering that the travel speed data, which is used for prediction, is time series data. In order to predict the travel speed more precisely, we constructed a model that reflects both temporal and spatial effects. The model is a short-term prediction model that predicts after one hour. For the analysis data, the 5minute travel speed collected from the Seoul Transportation Information Center was used, and the analysis section was selected as a part of Gangnam where traffic was congested.

• Proceedings of the Korean Society of Disaster Information Conference
• /
• 2022.10a
• /
• pp.325-326
• /
• 2022

통계청에 의하면 65세 이상 인구가 2024년 1,000만명을 도래할 것으로 예측하고 있으며, 노인인구 증가와 함께 노인치안 이슈들은 매년 증가하고 있다. 특히, 경찰청 자료에 따르면 최근 5년간 노인범죄피해는 매년 증가하고 있는 것으로 나타났다(경찰청, 2021). 치안서비스 대상에서 주요한 영역을 차지하게 될 노인을 대상으로 한 범죄예방정책을 마련하기 위하여 범죄피해노인의 특성에 관한 연구를 함에 있어 연도별 노인의 범죄피해영향요인의 차이가 있는지를 이 연구에서는 분석하고자 하였다. 따라서 이 연구에서는 한국형사·법무정책연구원의 2014년, 2016년, 2018년 전국범죄피해조사 2차 자료를 활용하였으며, 그 중 만65세 노인대상 자료만을 추출하여 2014년 1.921명, 2016년, 2,935명, 2018년 2,707명을 각각 최종분석에 활용하였다. Spss ver 21. 통계프로그램을 활용하여 로지스틱회귀분석을 실시하였으며, 연구결과 2014년에는 사회적 무질서 수준과 노인범죄피해와의 관계성이 높았다면, 2016년에는 물리적 무질서 수준과 노인범죄피해와의 관계성이 높았고, 2016년과 2018년에는 독거노인과 빈 집으로 가구가 노출되는 시간이 긴 정도가 노인범죄피해와의 관계성이 높은 것으로 볼 수 있었다. 이러한 연도별 노인 범죄피해 영향요인의 변화를 실증연구를 통해 검증함으로써 추후 노인범죄예방을 위한 정책마련의 자료로 활용하고자 한다.

• Korean Journal of Environment and Ecology
• /
• v.19 no.3
• /
• pp.279-286
• /
• 2005

This study was conducted to analyze the changing pattern of the bird community after the construction of artificial wetland at Sihwah lake from may 2000 to January 2002. Total seventy seven bird species were recorded at Sihwa artificial wetland area during the survey. Number of the bird species and individuals were increased in second year than first survey year. Especially shorebirds and raptors were more increased than other groups. Long-term and continuous monitoring of bird community would be needed to clarify the reasons of increasing pattern of bird species and individuals in artificial wetlands of Sihwa lake. Until now, this area has been considered as suitable habitat for dabbling ducks than shore birds and has simple habitat environment consisting of open water surface and reed beds. Therefore, we suggest the follows for creation of diverse habitat types: 1) seasonal water-level manipulation 2) management of diverse aquatic plants and 3) creation of diverse land cover; sandy fields, gravelly fields, grasslands, etc.

• Informatization Policy
• /
• v.24 no.2
• /
• pp.87-104
• /
• 2017

The Fourth Industrial Revolution, which is based on the development of information and communication technology (ICT), is expected to replace human knowledge work, which will cause problems of mass unemployment and wide income gap from job polarization. Furthermore, the change is expected to be rapid and wide, demanding proactive measures to respond to such abrupt social changes. However, previous literatures assume that the traditional form of employment will continue and provide limited solutions only. On the other hand, the Fourth Industrial Revolution will enable transition to the Prosumer Economy, which will ultimately lead consumers to become producers through increased job flexibility. If the prosumer economy arrives and the consumers become producers, it will no longer be the matter of finding workplace but rather, the matter of finding the work itself. In this regard, the new technologies of the Fourth Industrial Revolution can be the fundamental solution to such job issues. This paper suggests stable transition to the Prosumer Economy in order to solve the job issues in the age of the Fourth Industrial Revolution. In order to effectively support the process, this paper suggests first, ensuring the amount of education by shortening labor time; second, facilitating life-time education through free online education service; and third, closing the digital divide through mandatory use of the e-government system.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.46 no.3
• /
• pp.244-250
• /
• 2018

Multilateration acquires the transponder signal of target from receivers installed on the ground and calculates the position of the target using the difference of the signal acquisition time of each receiver. One of the factors that influence the positioning accuracy of Multilateration using the TDOA calculation method is the error due to the precision measurement of signal input time. When measuring the signal input time at the receiver, the input signal is sampled using the reference clock of the receiver and a reference sample having the same sampling rate is applied to the cross correlation technique. Therefore, the accuracy of the signal input time is proportional to the reference clock. In this paper, the algorithm for precisely measuring the signal input time by performing cross correlation between the input signal of the receiver and DRS(Delayed Reference Sample) is proposed. In order to verify this, we implemented the pulse signal of the transponder that is transmitted from the target using Matlab. Through the simulation, cross correlation between the proposed DRS and the input signal was performed. From this result, the performance of the precise measurement of signal input time was analyzed.