• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.399-401
• /
• 2022

POI (Point-of-Interest) 추천은 다양한 위치 기반 서비스에서 중요한 역할을 있다. 기존 연구에서는 사용자의 모바일 선호도를 모델링하기 위해 과거의 체크인의 공간-시간적 관계를 추출한다. 그러나 사용자 궤적에 숨겨진 개인 방문 경향을 반영할 수 있는 structured feature 는 잘 활용되지 않는다. 이 논문에서는 궤적 그래프를 결합한 시공간 인식 attention 네트워크를 제안한다. 개인의 선호도가 시간이 지남에 따라 변할 수 있다는 점을 고려하면 Dynamic GCN (Graph Convolution Network) 모듈은 POI 들의 공간적 상관관계를 동적으로 집계할 수 있다. LBSN (Location-Based Social Networks) 데이터 세트에서 검증된 새 모델은 기존 모델보다 약 9.0% 성능이 뛰어나다.

• Proceedings of the Korea Contents Association Conference
• /
• 2017.05a
• /
• pp.17-18
• /
• 2017

손쉽게 현 위치 정보를 공유하고 사용자 간 커뮤니케이션이 가능한 위치 기반 소셜 네트워크가 대중화되면서 장소 추천에 대한 연구가 활발히 진행되어 있다. 본 논문은 시간대별 사용자 선호도와 주요 활동 영역을 고려한 POI 추천 기법을 제안한다. 장소 카테고리별 사용자의 체크인(che-ck-in)정보를 시간대로 분할하여 시간에 따른 장소의 선호도를 판별하고 사용자의 과거 이력을 이용하여 사용자별 활동 영역을 선별한다. 장소의 선호도와 선별된 활동 영역에 기반하여 협업 필터링을 수행하여 POI를 추천한다.

• Database Research
• /
• v.34 no.3
• /
• pp.86-98
• /
• 2018

Point-of-Interest(POI) recommendation systems suggest the most interesting POIs to users considering the current location and time. With the rapid development of smartphones, internet-of-things, and location-based social networks, it has become feasible to accumulate huge amounts of user POI visits. Therefore, instant recommendation of interesting POIs at a given time is being widely recognized as important. To increase the performance of POI recommendation systems, several studies extracting users' POI sequential preference from POI check-in data, which is intended for implicit feedback, have been suggested. However, when constructing a model utilizing sequential preference, the model encounters possibility of data distortion because of a low number of observed check-ins which is attributed to intensified data sparsity. This paper suggests refinement of temporal intervals based on data confidence. When building a POI recommendation system using temporal intervals to model the POI sequential preference of users, our methodology reduces potential data distortion in the dataset and thus increases the performance of the recommendation system. We verify our model's effectiveness through the evaluation with the Foursquare and Gowalla dataset.

• Journal of the Korean Geographical Society
• /
• v.41 no.1 s.112
• /
• pp.1-21
• /
• 2006

Abstract The purpose of this paper is to analyze production and innovation networks of manufacturers in the rural, long-live areas of Gangwon Jeju and to suggest an ideal regional development model of rural areas in the knowledge-based information age. For this purpose, we compared the areas of Gangwon Jeju with the long-live belt areas in the rural pan of the Honan region and Gwangju Jeonju, the urban part of Honam. The findings from the study are summarized as follows. Firstly, the stronger the local networks in terms of supply of the necessary input materials and labor, the more successful the manufacturing industry is in the given area. Secondly, the more diverse and lasting the networks (in terms of the location of manufacturers, local area and national area) and cooperation agents(businesses, research institutions, the local government, the central government) they have, the more prosperous the manufacturing industry is. These results indicate that the successful development model for rural areas requires that we take the approach of fostering potential innovation capabilities of total areas by fully utilizing their innate resources so as to create an internal cooperative network and further build extensive networks encompassing external entities to create a virtual innovation cluster.

• Journal of the Economic Geographical Society of Korea
• /
• v.20 no.4
• /
• pp.486-502
• /
• 2017

This study investigated the formation process and networks of Korean Clean Development Mechanism(CDM) industry. It aimed to reveal the factors and the drivers for the formation processes of this industry in the specific place. Based on the analysis of the Project Design Documents(PDDs) of the CDM projects and the collected project data by international institutions, surveys, and interviews were done. On the basis of these data, the analysis on the industrial change as complex emergent effects by the network evolution caused by adaptive activity of firms is conducted. In the time of the genesis, a kind of serendipity that the industrial activities of Korean firms meet to new system, CDM, In the changing process of the Korean CDM industry, the role of policies fo Korean Government was important to promote the new and renewable energy projects of the power companies. In the time of restructuring, Korean government policies formed new initial conditions for the new domestic GHGs reduction industry. In this processes, the localization of knowledge acted as a key driver for the formation of the Korean CDM industry.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.42 no.2
• /
• pp.453-459
• /
• 2017

Users tend to check in and post their statuses in location-based social networks (LBSNs) to describe that their interests are related to a point-of-interest (POI). While previous studies on discovering area-of-interests (AOIs) were conducted mostly on the basis of density-based clustering methods with the collection of geo-tagged photos from LBSNs, we focus on estimating a POI boundary, which corresponds to only one cluster containing its POI center. Using geo-tagged tweets recorded from Twitter users, this paper introduces a density-based low-complexity two-phase method to estimate a POI boundary by finding a suitable radius reachable from the POI center. We estimate a boundary of the POI as the convex hull of selected geo-tags through our two-phase density-based estimation, where each phase proceeds with different sizes of radius increment. It is shown that our method outperforms the conventional density-based clustering method in terms of computational complexity.

• Journal of Korean Society for Geospatial Information Science
• /
• v.22 no.4
• /
• pp.21-30
• /
• 2014

Lately, new influentials have secured a large number of volunteers on social networks due to vitalization of various social media. There has been considerable research on these influential people in social networks but the research has limitations on location information of Location Based Social Network Service(LBSNS). Therefore, the purpose of this study is to propose a spatial detection methodology and application plan for influentials who make comments about diverse social and cultural issues in LBSNS using spatial statistical analysis methods. Twitter was used to collect analysis object data and 168,040 Twitter messages were collected in Seoul over a month-long period. In addition, 'politics,' 'economy,' and 'IT' were set as categories and hot issue keywords as given categories. Therefore, it was possible to come up with an exposure index for searching influentials in respect to hot issue keywords, and exposure index by administrative units of Seoul was calculated through a spatial joint operation. Moreover, an influential index that considers the spatial dependence of the exposure index was drawn to extract information on the influential areas at the top 5% of the influential index and analyze the spatial distribution characteristics and spatial correlation. The experimental results demonstrated that spatial correlation coefficient was relatively high at more than 0.3 in same categories, and correlation coefficient between politics category and economy category was also more than 0.3. On the other hand, correlation coefficient between politics category and IT category was very low at 0.18, and between economy category and IT category was also very weak at 0.15. This study has a significance for materialization of influentials from spatial information perspective, and can be usefully utilized in the field of gCRM in the future.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.12
• /
• pp.3836-3854
• /
• 2022

The student group division is benefit for universities to do the student management based on the group profile. With the widespread use of student smart cards on campus, especially where students living in campus residence halls, students' daily activities on campus are recorded with information such as smart card swiping time and location. Therefore, it is feasible to depict the students with the daily activity data and accordingly group students based on objective measuring from their campus behavior with some regular student attributions collected in the management system. However, it is challenge in feature representation due to diverse forms of the student data. To effectively and comprehensively represent students' behaviors for further student group division, we proposed to adopt activity data from student smart cards and student attributes as input data with taking account of activity and attribution relationship types from different perspective. Specially, we propose a novel student group division method based on a multi-view student attribute heterogeneous information network (MSA-HIN). The network nodes in our proposed MSA-HIN represent students with their multi-dimensional attribute information. Meanwhile, the edges are constructed to characterize student different relationships, such as co-major, co-occurrence, and co-borrowing books. Based on the MSA-HIN, embedded representations of students are learned and a deep graph cluster algorithm is applied to divide students into groups. Comparative experiments have been done on a real-life campus dataset collected from a university. The experimental results demonstrate that our method can effectively reveal the variability of student attributes and relationships and accordingly achieves the best clustering results for group division.

• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.9
• /
• pp.341-348
• /
• 2014

The advance in web accessibility with dissemination of smart phones gives rise to rapid increment of users on social network platforms. Many research projects are in progress to detect events using Twitter because it has a powerful influence on the dissemination of information with its open networks, and it is the representative service which generates more than 500 million Tweets a day in average; however, existing studies to detect events has been used TFIDF algorithm without any consideration of the various conditions of tweets. In addition, some of them detected predefined events. In this paper, we propose the RTFIDF VT algorithm which is a modified algorithm of TFIDF by reflecting features of Twitter. We also verified the optimal section of TF and DF for detecting events through the experiment. Finally, we suggest a system that extracts result-sets of places and related keywords at the given specific time using the RTFIDF VT algorithm and validated section of TF and DF.

• Proceedings of the National Institute of Ecology of the Republic of Korea
• /
• v.3 no.2
• /
• pp.67-72
• /
• 2022

Ecological research relies on the interpretation of large amounts of visual data obtained from extensive wildlife surveys, but such large-scale image interpretation is costly and time-consuming. Using an artificial intelligence (AI) machine learning model, especially convolution neural networks (CNN), it is possible to streamline these manual tasks on image information and to protect wildlife and record and predict behavior. Ecological research using deep-learning-based object recognition technology includes various research purposes such as identifying, detecting, and identifying species of wild animals, and identification of the location of poachers in real-time. These advances in the application of AI technology can enable efficient management of endangered wildlife, animal detection in various environments, and real-time analysis of image information collected by unmanned aerial vehicles. Furthermore, the need for school education and social use on biodiversity and environmental issues using AI is raised. School education and citizen science related to ecological activities using AI technology can enhance environmental awareness, and strengthen more knowledge and problem-solving skills in science and research processes. Under these prospects, in this paper, we compare the results of our early 2013 study, which automatically identified African cichlid fish species using photographic data of them, with the results of reanalysis by CNN deep learning method. By using PyTorch and PyTorch Lightning frameworks, we achieve an accuracy of 82.54% and an F1-score of 0.77 with minimal programming and data preprocessing effort. This is a significant improvement over the previous our machine learning methods, which required heavy feature engineering costs and had 78% accuracy.