• The Journal of Bigdata
• /
• v.5 no.1
• /
• pp.55-63
• /
• 2020

This study proposed an approach of clustering collective users' activities of location-based social networks using check-in data of Foursquare users in Seoul. In order to cluster the collective activities, we generated sequential rules of the activities using sequential rule mining, and then constructed activity networks based on the rules. We analyzed the activity networks to identify network structure and hub activities, and clustered the activities within the networks. Unlike previous studies that analyzed activity transition patterns of location-based social network users, this study focused on analyzing the structure and clusters of successive activities. Hubs and clusters of activities with the approach proposed in this study can be used for location-based services and marketing. They could also be used in the public sector, such as infection prevention and urban policies.

• 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.

• Membrane and Water Treatment
• /
• v.7 no.2
• /
• pp.115-126
• /
• 2016

In this study, computational fluid dynamics (CFD) analysis was conducted to investigate the flow pattern and to find the occurrence of dead zones in an existing capacitive deionization (CDI) cell. Newly designed cells-specifically designed to avoid dead zones-were analyzed by CFD in accordance with the flow rates of 15, 25 and 35 ml/min. Next, the separation performances between the existing and newly designed cell were compared by conducting CDI experiments in terms of salt removal efficiency at the same flow rates. Then, the computational and experimental results were compared to each other. The salt removal efficiencies of the hexagon flow channel 1 (HFC1) and hexagon flow channel 2 (HFC2) were increased 88-124% at 15 ml/min and 49-50% at 25 ml/min, respectively. There was no difference between the existing cell and the foursquare flow cell (FFC) at 35 ml/min.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.6 no.12
• /
• pp.3197-3218
• /
• 2012

Compared with traditional itinerary planning, intention-oriented itinerary recommendations can provide more flexible activity planning without requiring the user's predetermined destinations and is especially helpful for those in unfamiliar environments. The rank and classification of points of interest (POI) from location-based social networks (LBSN) are used to indicate different user intentions. The mining of vehicles' physical trajectories can provide exact civil traffic information for path planning. This paper proposes a POI category-based itinerary recommendation framework combining physical trajectories with LBSN. Specifically, a Voronoi graph-based GPS trajectory analysis method is utilized to build traffic information networks, and an ant colony algorithm for multi-object optimization is implemented to locate the most appropriate itineraries. We conduct experiments on datasets from the Foursquare and GeoLife projects. A test of users' satisfaction with the recommended items is also performed. Our results show that the satisfaction level reaches an average of 80%.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.5-6
• /
• 2023

본 연구에서는 언텍트 소비가 일반화됨에 따라 소상공인들을 지원하기 위해 캡티브-포털을 활용하여 주문하는 등의 시스템을 구축하고 있으며, 이에 상권 내 방문자들의 주문 정보를 기반으로 개인의 선호나 취향을 고려하고 기존 방문 순서를 고려하여 다음 방문지를 추천할 수 있는 모델을 개발하고자 한다. 모델 개발을 위한 데이터셋으로는 캡티브-포털을 통해 수집되는 변수 항목과 유사한 위치기반 SNS 데이터인 Foursquare 데이터를 활용했다. 본 논문에서는 데이터셋의 변수 중 상호명을 기반으로 22개의 행동 유형 카테고리로 묶어 현재 행동 유형 이후에 다음에 이어질 행동 유형을 예측하는 것을 제안한다. 개인 별 세션 기반의 데이터셋을 LightMove 알고리즘을 활용하여 행동유형 예측을 임베딩 차원의 변경하여 실험한 결과 500차원에서 Top-5가 82.72의 성능을 보임을 확인했다. 향후 국내 상권에 맞는 방문지 추천 시스템이 개발된다면 방문지 추천을 활용하여 다양한 마케팅 전략을 수립이 가능해질 수 있고, 이를 통해 지역 상권이 활성화될 것으로 기대된다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.5
• /
• pp.1909-1928
• /
• 2020

Predicting human mobility has always been an important task in Location-based Social Network. Previous efforts fail to capture spatial dependence effectively, mainly reflected in weakening the location topology information. In this paper, we propose a neural network-based method which can capture spatial-temporal dependence to predict the next location of a person. Specifically, we involve a graph convolutional network (GCN) based on a seq2seq framework to capture the location topology information and temporal dependence, respectively. The encoder of the seq2seq framework first generates the hidden state and cell state of the historical trajectories. The GCN is then used to generate graph embeddings of the location topology graph. Finally, we predict future trajectories by aggregated temporal dependence and graph embeddings in the decoder. For evaluation, we leverage two real-world datasets, Foursquare and Gowalla. The experimental results demonstrate that our model has a better performance than the compared models.

• KIISE Transactions on Computing Practices
• /
• v.21 no.2
• /
• pp.154-159
• /
• 2015

Over the past few years, user needs in the smartphone application market have been shifted from diversity toward intelligence. Here, we propose a novel cognitive agent that plans the daily routines of users using the lifelog data collected by the smart phones of individuals. The proposed method first employs DPGMM (Dirichlet Process Gaussian Mixture Model) to automatically extract the users' POI (Point of Interest) from the lifelog data. After extraction, the POI and other meaningful features such as GPS, the user's activity label extracted from the log data is then used to learn the patterns of the user's daily routine by POMDP (Partially Observable Markov Decision Process). To determine the significant patterns within the user's time dependent patterns, collaboration was made with the SNS application Foursquare to record the locations visited by the user and the activities that the user had performed. The method was evaluated by predicting the daily routine of seven users with 3300 feedback data. Experimental results showed that daily routine scheduling can be established after seven days of lifelogged data and feedback data have been collected, demonstrating the potential of the new method of place-time-activity coupled daily routine planning systems in the intelligence application market.

• Journal of Intelligence and Information Systems
• /
• v.24 no.2
• /
• pp.85-109
• /
• 2018

Recommender system recommends the items expected to be purchased by a customer in the future according to his or her previous purchase behaviors. It has been served as a tool for realizing one-to-one personalization for an e-commerce service company. Traditional recommender systems, especially the recommender systems based on collaborative filtering (CF), which is the most popular recommendation algorithm in both academy and industry, are designed to generate the items list for recommendation by using 'overall rating' - a single criterion. However, it has critical limitations in understanding the customers' preferences in detail. Recently, to mitigate these limitations, some leading e-commerce companies have begun to get feedback from their customers in a form of 'multicritera ratings'. Multicriteria ratings enable the companies to understand their customers' preferences from the multidimensional viewpoints. Moreover, it is easy to handle and analyze the multidimensional ratings because they are quantitative. But, the recommendation using multicritera ratings also has limitation that it may omit detail information on a user's preference because it only considers three-to-five predetermined criteria in most cases. Under this background, this study proposes a novel hybrid recommendation system, which selectively uses the results from 'traditional CF' and 'CF using multicriteria ratings'. Our proposed system is based on the premise that some people have holistic preference scheme, whereas others have composite preference scheme. Thus, our system is designed to use traditional CF using overall rating for the users with holistic preference, and to use CF using multicriteria ratings for the users with composite preference. To validate the usefulness of the proposed system, we applied it to a real-world dataset regarding the recommendation for POI (point-of-interests). Providing personalized POI recommendation is getting more attentions as the popularity of the location-based services such as Yelp and Foursquare increases. The dataset was collected from university students via a Web-based online survey system. Using the survey system, we collected the overall ratings as well as the ratings for each criterion for 48 POIs that are located near K university in Seoul, South Korea. The criteria include 'food or taste', 'price' and 'service or mood'. As a result, we obtain 2,878 valid ratings from 112 users. Among 48 items, 38 items (80%) are used as training dataset, and the remaining 10 items (20%) are used as validation dataset. To examine the effectiveness of the proposed system (i.e. hybrid selective model), we compared its performance to the performances of two comparison models - the traditional CF and the CF with multicriteria ratings. The performances of recommender systems were evaluated by using two metrics - average MAE(mean absolute error) and precision-in-top-N. Precision-in-top-N represents the percentage of truly high overall ratings among those that the model predicted would be the N most relevant items for each user. The experimental system was developed using Microsoft Visual Basic for Applications (VBA). The experimental results showed that our proposed system (avg. MAE = 0.584) outperformed traditional CF (avg. MAE = 0.591) as well as multicriteria CF (avg. AVE = 0.608). We also found that multicriteria CF showed worse performance compared to traditional CF in our data set, which is contradictory to the results in the most previous studies. This result supports the premise of our study that people have two different types of preference schemes - holistic and composite. Besides MAE, the proposed system outperformed all the comparison models in precision-in-top-3, precision-in-top-5, and precision-in-top-7. The results from the paired samples t-test presented that our proposed system outperformed traditional CF with 10% statistical significance level, and multicriteria CF with 1% statistical significance level from the perspective of average MAE. The proposed system sheds light on how to understand and utilize user's preference schemes in recommender systems domain.