• 한국빅데이터학회지
• /
• 제1권1호
• /
• pp.9-17
• /
• 2016

본 연구에서는 상수관망에 설치된 유량, 압력 센서를 통해 취득한 빅데이터에 대해 데이터마이닝 기법을 활용하여 해당 공급권역의 특성을 파악하고 그 정보에 기반하여 상수 공급에 있어서 유의할 점 등을 도출해보고자 하였다. 또한, 상수 사용에 대한 단기 수요예측을 수행하는데 있어서도 통계적 방법인 다중회귀분석과 데이터마이닝의 인공신경망 기법을 비교하여 좀 더 정확한 수요예측을 할 수 있는 모델을 제시해보고자 하였다. 데이터 수집과 테스트를 위하여 지자체 한 군의 소블록 지역을 대상으로 선정하였다. 해당 지역은 가정용 수요 외에도 관공서, 병원 등의 대형 업무용 수요도 일부 존재하고 있는 지역이다. 해당 지역의 센서를 통해 취득되는 연속 발생 데이터를 수집하였다. 이런 방식을 통해 취득된 데이터는 총 2,728건이며 이 중 2,632건은 예측모델을 생성하는데 96건은 예측모델의 예측력을 테스트 하는 데에 활용하였다. 이러한 테스트를 수행한 결과 상수 수요예측에 있어서 인공신경망이 다중회귀분석에 비교하여 더 좋은 예측율을 보였다.

• 한국정보통신학회논문지
• /
• 제25권9호
• /
• pp.1244-1253
• /
• 2021

본 논문에서는 보행자 경로 예측 기법을 이용하여 보행자들이 현재 시점 이후로 위험구역으로 진입하는지 사전에 예측하는 방법과 경로 예측 네트워크의 효율적인 간소화 방법을 제안한다. 그리고 임베디드 환경에서 실시간 운용을 위해 작은 네트워크에 대하여 KD(Knowledge Distillation)을 적용하는 방법을 제안한다. 예측된 미래 경로와 위험구역 간의 상관관계를 이용하여 진입 여부를 판단하였으며 작은 네트워크를 학습할 때 효율적인 KD를 적용하여 성능저하를 최소화하였다. 실험을 통하여, 제안하는 간소화 기법을 적용한 모델이 기존 모델과 비교하여 37.49%의 속도향상 대비 미미한 정확도 저하를 이끌어 내는 것을 보여 주었다. 또한, 91.43%의 정확도를 가진 작은 네트워크를 KD를 이용하여 학습한 결과 94.76%의 향상된 정확도를 보임을 확인하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권8호
• /
• pp.2030-2052
• /
• 2023

Analysis of a bipartite (two-mode) network is a significant research area to understand the formation of social communities, economic systems, drug side effect topology, etc. in complex information systems. Most of the previous works talk about a projection-based model or latent feature model, which predicts the link based on singular similarity. The projection-based models suffer from the loss of structural information in the projected network and the latent feature is hardly present. This work proposes a novel method for link prediction in the bipartite network based on an ensemble of composite similarities, overcoming the issues of model-based and latent feature models. The proposed method analyzes the structure, neighborhood nodes as well as latent attributes between the nodes to predict the link in the network. To illustrate the proposed method, experiments are performed with five real-world data sets and compared with various state-of-art link prediction methods and it is inferred that this method outperforms with ~3% to ~9% higher using area under the precision-recall curve (AUC-PR) measure. This work holds great significance in the study of biological networks, e-commerce networks, complex web-based systems, networks of drug binding, enzyme protein, and other related networks in understanding the formation of such complex networks. Further, this study helps in link prediction and its usability for different purposes ranging from building intelligent systems to providing services in big data and web-based systems.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2005년도 추계종합학술대회
• /
• pp.39-42
• /
• 2005

H.264, a recently proposed international video coding standard, has adopted context-based adaptive variable length coding (CAVLC) as the entropy coding tool in the baseline profile. By combining an adaptive variable length coding technique with context modeling, we can achieve a high degree of redundancy reduction. However, CAVLC in H.264 has weakness that the correct prediction rate of the variable length coding (VLC) table is low in a complex area, such as the boundary of an object. In this paper, we propose a VLC table prediction scheme considering multiple reference blocks; the same position block of the previous frame and the neighboring blocks of the current frame. The proposed algorithm obtains the new weighting values considering correctness of the VLC table for each reference block. Using this method, we can enhance the prediction rate of the VLC table and reduce the bit-rate.

• 한국추진공학회지
• /
• 제5권2호
• /
• pp.38-43
• /
• 2001

본 논문은 Finocyl형 그레인의 이중추력형 로켓모타에 대한 성능예측기법을 개발하여 이를 실제 연소 시험 데이터와 비교, 분석하였다. 성능예측은 I-DEAS를 이용한 면적분석과 보정계수를 이용한 성능계산으로 나누어 수행되었다. 비교분석 결과 연소 중 압력이 지속적으로 변화하는 이중추력형 모타의 경우는 단순추력형과는 달리 부스팅과 서스테이닝 단계에서 각각 다른 보정개수를 적용하여 성능을 예측해야하며 이를 이용하여 재예측한 결과 0.5% 오차 안에서 일치함을 확인하였다.

• 한국환경과학회지
• /
• 제9권6호
• /
• pp.469-474
• /
• 2000

The traffic accidents in large cities such as Pusan metropolitan city have been increased every year due to increasing of vehicles numbers as well as the gravitation of the population. In addition to the carelessness of drivers, many meteorological factors have a great influence on the traffic accidents. Especially, the number of traffic accidents is governed by precipitation, visibility, cloud amounts temperature, etc. In this study, we have analyzed various data of meteorological factors from 1992 to 1997 and determined the standardized values for contributing to each traffic accident. Using the relationship between meteorological factors(visibility, precipitation, relative humidity and cloud amounts) and the total automobile mishaps, and experimental prediction formula for their traffic accident rates was seasonally obtained at Pusan city in 1997. Therefore, these prediction formulas at each meteorological factor may by used to predict the seasonal traffic accident numbers and contributed to estimate the variation of its value according to the weather condition it Pusan city.

• 한국조경학회지
• /
• 제25권3호
• /
• pp.89-100
• /
• 1997

The purpose of this paper was to analyze the content of impact prediction in EISS, in order to find the degree of the acuracy of impact prediction . 30 EISS were selected as analysis objects through variance miximization strategy. Content analysis of the selected EISS was performed by 5 analysis items, such as quantification of measurement, range of impact area, time frame of impact, likelihood of impact, and explict characterization of impact significance. The results showed that the accuracy investigated by the 5 items was very low. In conclusion, 5 suggestions were proposed in order to improve the credibility of EIS as a scientific report. The 5 suggestions were : 1) impact prediction should be described by quantitative measurement; 2) In establishing the time frame of the impact and the referent populatioin influenced by the impact, the characteristics of the proposed action should be carefully considerd; 3) the significance of the predicted impact should be quantitatively described; 4) specific description should also be used in the likelihood or the probability of the predicted impact in a real world; 5) equal emphasis should be put on the three environment, including natural and social as well as living environment.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2006년도 Proceedings of ISRS 2006 PORSEC Volume I
• /
• pp.332-335
• /
• 2006

Red tide(harmful algae) in the Korean Coastal Waters has a given a great damage to the fishery every year. However, the aim of our study understands the influence of meteorological factors (air and water temperature, precipitation, sunshine, solar radiation, winds) relating to the mechanism of red tide occurrence and monitors red tide by satellite remote sensing, and analyzes the potential area for red tide occurrence by GIS. The meteorological factors have directly influenced on red tide formation. Thus, We want to predict and apply to red tide formation from statistical analyses on the relationships between red tide formation and meteorological factors. In future, it should be realized the near real time monitoring for red tide by the development of remote sensing technique and the construction of integrated model by the red tide information management system (the data base of red tide - meteorological informations). Finally our purpose is support to the prediction information for the possible red tide occurrence by coastal meteorological information and contribute to reduce the red tide disaster by the prediction technique for red tide.

• 한국태양에너지학회:학술대회논문집
• /
• 한국태양에너지학회 2008년도 춘계학술발표대회 논문집
• /
• pp.304-310
• /
• 2008

Currently energy use planning council system is mandatory especially for the urban development project planned on a specified scale or more. The goal of existing demand prediction was to calculate the maximum load by multiplying energy load per unit area by building size. The result of this method may be exaggerated and has a limit in the information of period load. The paper suggests a new forecasting process based on standard unit household in order to upgrade the limit in demand prediction method of multi-family housing complex. The new process was verified by comparing actual using amount of multi-family housing complex to forecasting value of energy use plan.

• 유체기계공업학회:학술대회논문집
• /
• 유체기계공업학회 2005년도 연구개발 발표회 논문집
• /
• pp.378-383
• /
• 2005

The performances of side channel type regenerative blowers were evaluated by the blower performance test, 1-D performance prediction and CFD. The performance prediction method was modified using the results of the performance test and CFD and applied to the design of the new regenerative blowers. The major geometric parameters such as channel height, channel area and expansion angle were decided from the performance prediction method for the improved models and the predicted results were compared with CFD and experimental data. Both of the modified models showed improved efficiency at the operating condition. Especially, model3 could be possible to reduce operating rotating speed, that is benefit to noise performance, because of the high head performance at the design point. The CFD results showed that the performance of the regenerative blower was influenced by the secondary circulatory flow in the channel.