• ETRI Journal
• /
• 제44권2호
• /
• pp.208-219
• /
• 2022

Crime amount prediction is crucial for optimizing the police patrols' arrangement in each region of a city. First, we analyzed spatiotemporal correlations of the crime data and the relationships between crime and related auxiliary data, including points-of-interest (POI), public service complaints, and demographics. Then, we proposed a crime amount prediction model based on 2D convolution and long short-term memory neural network (2DCONV-LSTM). The proposed model captures the spatiotemporal correlations in the crime data, and the crime-related auxiliary data are used to enhance the regional spatial features. Extensive experiments on real-world datasets are conducted. Results demonstrated that capturing both temporal and spatial correlations in crime data and using auxiliary data to extract regional spatial features improve the prediction performance. In the best case scenario, the proposed model reduces the prediction error by at least 17.8% and 8.2% compared with support vector regression (SVR) and LSTM, respectively. Moreover, excessive auxiliary data reduce model performance because of the presence of redundant information.

• 대한교통학회지
• /
• 제32권6호
• /
• pp.638-650
• /
• 2014

본 연구의 목적은 서울 도심지역의 행정동별 지역적 요소와 계획적 요소가 목적지로의 통행수단으로서 보행을 결정하는 것에 미치는 영향의 정도를 파악하고, 이에 대한 분석 결과 및 보행의 공간적 특성을 통해 지역별 특성을 파악하고자 함에 있다. 보행 결정에 영향을 미치는 요소들의 영향 정도를 파악하기 위해 본 연구에서는 전역적 차원의 회귀분석 모형인 최소자승모형을 사용하였고, 이와 더불어 다양한 공간통계 분석모형 중 지역별 보행특성을 기반으로 공간적 이질성을 고려하는 지리가중회귀모형의 적용을 통해 지역별 특성을 파악하고자 하였다. 전역적 차원의 회귀분석 결과 목적지로의 보행 선택에 영향을 주는 요소로는 지역적 요소 중 교통시설 지역 및 상업지역, 대학교 면적이, 계획적 요소 중에서는 교육.연구시설 및 계획시설 면적이 보행 선택에 정의 영향을 주었다. 마지막으로 지리가중회귀모형의 분석 결과를 통해 서울 도심지역 중 교통중심지 및 취약지, 상업 업무 중심지, 대학가 중심지, 연구시설 밀집지를 파악할 수 있었다. 본 연구의 결과를 통해 지역 및 공간적 이질성에 대한 이해 없이 진행되었던 기존의 계획 및 정책들에 지역적 특성이라는 정보를 제공함으로 이에 대한 반영의 여지를 주어 보다 지역발전 차원의 계획 수립에 기여할 수 있을 것이라는 점에 본 연구의 의의가 있을 것이라 여겨진다.

• 한국실내디자인학회논문집
• /
• 제15권5호
• /
• pp.209-220
• /
• 2006

The goal to establish one multipurpose senior center in one district of Seoul city has been nearly completed. However, since it is behind the schedule by about 6 years, nearly all senior centers are saturated currently. Therefore, additional foundation plan of senior centers is in progress. Also, the main function of the center has changed from health and leisure to various welfare programs that the elderly living in a community need. In order to supplement these problems, many existing senior centers are using center to the most through addition and change of rooms. To establish the direction of spatial plan at establishing senior centers according to the regional characteristics, 20 cases of Seoul multipurpose senior centers in operation were site surveyed and the results of spatial features by types established and changed corresponding to each condition were suggested as follows: 1. The types were classified according to the shape of floor plan, sectional planning, entry traffic line, linkage with attached facilities and addition method etc. by the characteristics of the elderly in multipurpose senior centers, program operation, linkage of spatial composition by the function, positional relation between centers, management and operation method, and center complication method etc. and the respective features were suggested. 2. By analyzing the gross floor area and the area of each room of senior centers, the features of area by types and the features of area by each detailed center were suggested.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권1호
• /
• pp.272-287
• /
• 2016

Recently, various and effective contrast based salient object detection models to focus on a single target have been proposed. However, there is a lack of research on detection of multiple objects, and also it is a more challenging task than single target process. In the multiple target problem, we are confronted by new difficulties caused by distinct difference between properties of objects. The characteristic of existing models depending on the global maximum distribution of data point would become a drawback for detection of multiple objects. In this paper, by analyzing limitations of the existing methods, we have devised three main processes to detect multiple salient objects. In the first stage, regional features are extracted from over-segmented regions. In the second stage, the regional features are categorized into homogeneous cluster using the mean-shift algorithm with the kernel function having various sizes. In the final stage, we compute saliency scores of the categorized regions using only spatial features without the contrast features, and then all scores are integrated for the final salient regions. In the experimental results, the scheme achieved superior detection accuracy for the SED2 and MSRA-ASD benchmarks with both a higher precision and better recall than state-of-the-art approaches. Especially, given multiple objects having different properties, our model significantly outperforms all existing models.

• 한국농촌건축학회논문집
• /
• 제2권2호
• /
• pp.1-10
• /
• 2000

The traditional farm houses in Yongdong area of Kangwon province have a different spatial structure from those of the other areas because of the characteristics of the climatic, geographic and sociocultural circumstances between the Taebaek mountains and the East Sea. So the purpose of this study is aimed at grasping how the spatial features of traditional farm houses in Yongdong area have been different in each regional circle. The plans of traditional farm houses of this region which are four types - ㅡ typed house without floor, ㅡ typed house with floor, ㄱ typed house without floor, ㄱ typed house with floor - show very similar but different space arrangements.

• 국제초고층학회논문집
• /
• 제10권1호
• /
• pp.9-16
• /
• 2021

Being the origin of Shanghai City, the Old Town presents a high-density spatial texture, a characteristic of local living conditions in the Shanghai context. However, the Old Town is faced with competing interests: the preservation of historic urban features and the improvement of contemporary living conditions. In view of its high density and poor living conditions, this paper focuses on two types of blocks for urban design research, and proposes two spatial regeneration strategies, as "overlapping lilong" and "texture continuity". It is expected to inherit the regional characteristics of urban space, improve the plot ratio and supplement the mix of functions, through the translation of the traditional lilong typology and the reproduction of historical streets and alleys, so as to provide operable spatial strategies and design methods for the organic renewal of Old Town and other historic districts.

• Journal of Electrical Engineering and Technology
• /
• 제13권2호
• /
• pp.961-968
• /
• 2018

Recently, researches on automatic recognition of human activities have been actively carried out with the emergence of various intelligent systems. Since a large amount of visual data can be secured through Closed Circuit Television, it is required to recognize human behavior in a dynamic situation rather than a static situation. In this paper, we propose new intelligent human activity recognition model using the trajectory information extracted from the video sequence. The proposed model consists of three steps: segmentation and partitioning of trajectory step, feature extraction step, and behavioral learning step. First, the entire trajectory is fuzzy partitioned according to the motion characteristics, and then temporal features and spatial features are extracted. Using the extracted features, four pedestrian behaviors were modeled by decision tree learning algorithm and performance evaluation was performed. The experiments in this paper were conducted using Caviar data sets. Experimental results show that trajectory provides good activity recognition accuracy by extracting instantaneous property and distinctive regional property.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2004년도 학술발표회
• /
• pp.875-877
• /
• 2004

We analyze the changes of the Palmer Drought Severity Index (PDSI) over Korea to assess the regional climate change associated with global warming. For the regional-scale analysis, we used the MM5 simulation in 27 km horizontal resolution for the period of 1971-2100, which is driven by ECHAM4/HOPE-G under the greenhouse gas omission scenario. The downscaled climate variables capture improved regional features consistent with the observation. Based on the simulation, we investigated the temporal and spatial distributions of PDSI over Korea. The area-averaged PDSI is expected to decrease in global warming. Considering the horizontal distribution of climate change, the negative peak values of PDSI anomalies appear in the southern part of Korea.

• Journal of the Korean Institute of Landscape Architecture International Edition
• /
• 제1호
• /
• pp.136-142
• /
• 2001

Beijing Chuan Di Xia can be traced back to Ming and Qing Dynasties. It is located beside the old post way in the west of Beijing. At present, there are more than seventy units of traditional courtyard houses of Ming and Qing Dynasties and the antique features of the surroundings still survive. The dwelling suited to the historical and regional context and the profound cultural values accumulations etc., have precious historic and cultural values. Associated with the investigation of Chuan Di Xia, the paper explores the site selection, the layout, the spatial constructiveness and the underlying consciousness of Chinese traditional dwellings, unveils the common philosophic basis of traditional dwellings and offers new though for sustainable human settlements.

• 한국통신학회논문지
• /
• 제27권6C호
• /
• pp.610-618
• /
• 2002

본 논문에서는 질러 공간과 블록영역 정보에 기반한 새로운 화상검색 방법을 제시한다. 각 화상에 대한 컬러 공간 정보는 컬러 이진세트에 의해 구해지고 블록영역 정보는 영역 세그멘테이션에 의해서 구해진다. 화상 검색 과정에서, 질의 화상과 데이터베이스 화상들의 컬러 및 화상 이진세트들을 비교하여 검색될 후보 화상의 집합을 결정한다. 특히, 유사도 측정 시 컬러 공간 분포와 객체의 블록영역 특징에 가중치를 고려한 검색이 가능하도록 하였다. 제안된 방법을 구현하고 6,000개의 화상들로 이루어진 화상 데이터베이스에 대해 적용함으로써 컬러 공간 및 블록영역특징을 이용한 화상 검색이 매우 효과적임을 보였다.