The increasing availability of GPS-enabled devices is changing the way people interact with the Web, and brings us a large amount of GPS trajectories representing people's location histories. In this paper, based on multiple users' GPS trajectories, we aim to mine interesting locations and classical travel sequences in a given geospatial region. Here, interesting locations mean the culturally important places, such as Tiananmen Square in Beijing, and frequented public areas, like shopping malls and restaurants, etc. Such information can help users understand surrounding locations, and would enable travel recommendation. In this work, we first model multiple individuals' location histories with a tree-based hierarchical graph (TBHG). Second, based on the TBHG, we propose a HITS (Hypertext Induced Topic Search)-based inference model, which regards an individual's access on a location as a directed link from the user to that location. This model infers the interest of a location by taking into account the following three factors. 1) The interest of a location depends on not only the number of users visiting this location but also these users' travel experiences. 2) Users' travel experiences and location interests have a mutual reinforcement relationship. 3) The interest of a location and the travel experience of a user are relative values and are region-related. Third, we mine the classical travel sequences among locations considering the interests of these locations and users' travel experiences. We evaluated our system using a large GPS dataset collected by 107 users over a period of one year in the real world. As a result, our HITS-based inference model outperformed baseline approaches like rank-by-count and rank-by-frequency. Meanwhile, when considering the users' travel experiences and location interests, we achieved a better performance beyond baselines, such as rank-by-count and rank-by-interest, etc.

/pdf/mining-interesting-locations-and-travel-sequences-from-gps-33g2tbk5p5.pdf

Mining interesting locations and travel sequences from GPS trajectories

Map-matching is the process of aligning a sequence of observed user positions with the road network on a digital map. It is a fundamental pre-processing step for many applications, such as moving object management, traffic flow analysis, and driving directions. In practice there exists huge amount of low-sampling-rate (e.g., one point every 2--5 minutes) GPS trajectories. Unfortunately, most current map-matching approaches only deal with high-sampling-rate (typically one point every 10--30s) GPS data, and become less effective for low-sampling-rate points as the uncertainty in data increases. In this paper, we propose a novel global map-matching algorithm called ST-Matching for low-sampling-rate GPS trajectories. ST-Matching considers (1) the spatial geometric and topological structures of the road network and (2) the temporal/speed constraints of the trajectories. Based on spatio-temporal analysis, a candidate graph is constructed from which the best matching path sequence is identified. We compare ST-Matching with the incremental algorithm and Average-Frechet-Distance (AFD) based global map-matching algorithm. The experiments are performed both on synthetic and real dataset. The results show that our ST-matching algorithm significantly outperform incremental algorithm in terms of matching accuracy for low-sampling trajectories. Meanwhile, when compared with AFD-based global algorithm, ST-Matching also improves accuracy as well as running time.

/pdf/map-matching-for-low-sampling-rate-gps-trajectories-4hstm6zk4l.pdf

Map-matching for low-sampling-rate GPS trajectories

Over the past two decades, a large amount of research effort has been devoted to developing algorithms that generate recommendations. The resulting research progress has established the importance of the user-item (U-I) matrix, which encodes the individual preferences of users for items in a collection, for recommender systems. The U-I matrix provides the basis for collaborative filtering (CF) techniques, the dominant framework for recommender systems. Currently, new recommendation scenarios are emerging that offer promising new information that goes beyond the U-I matrix. This information can be divided into two categories related to its source: rich side information concerning users and items, and interaction information associated with the interplay of users and items. In this survey, we summarize and analyze recommendation scenarios involving information sources and the CF algorithms that have been recently developed to address them. We provide a comprehensive introduction to a large body of research, more than 200 key references, with the aim of supporting the further development of recommender systems exploiting information beyond the U-I matrix. On the basis of this material, we identify and discuss what we see as the central challenges lying ahead for recommender system technology, both in terms of extensions of existing techniques as well as of the integration of techniques and technologies drawn from other research areas.

Collaborative Filtering beyond the User-Item Matrix: A Survey of the State of the Art and Future Challenges

With the increasing popularity of location-based services, such as tour guide and location-based social network, we now have accumulated many location data on the Web. In this paper, we show that, by using the location data based on GPS and users' comments at various locations, we can discover interesting locations and possible activities that can be performed there for recommendations. Our research is highlighted in the following location-related queries in our daily life: 1) if we want to do something such as sightseeing or food-hunting in a large city such as Beijing, where should we go? 2) If we have already visited some places such as the Bird's Nest building in Beijing's Olympic park, what else can we do there? By using our system, for the first question, we can recommend her to visit a list of interesting locations such as Tiananmen Square, Bird's Nest, etc. For the second question, if the user visits Bird's Nest, we can recommend her to not only do sightseeing but also to experience its outdoor exercise facilities or try some nice food nearby. To achieve this goal, we first model the users' location and activity histories that we take as input. We then mine knowledge, such as the location features and activity-activity correlations from the geographical databases and the Web, to gather additional inputs. Finally, we apply a collective matrix factorization method to mine interesting locations and activities, and use them to recommend to the users where they can visit if they want to perform some specific activities and what they can do if they visit some specific places. We empirically evaluated our system using a large GPS dataset collected by 162 users over a period of 2.5 years in the real-world. We extensively evaluated our system and showed that our system can outperform several state-of-the-art baselines.

/pdf/collaborative-location-and-activity-recommendations-with-gps-32xzsk6czm.pdf

Collaborative location and activity recommendations with GPS history data

The pervasiveness of location-acquisition technologies (GPS, GSM networks, etc.) enable people to conveniently log the location histories they visited with spatio-temporal data. The increasing availability of large amounts of spatio-temporal data pertaining to an individual's trajectories has given rise to a variety of geographic information systems, and also brings us opportunities and challenges to automatically discover valuable knowledge from these trajectories. In this paper, we move towards this direction and aim to geographically mine the similarity between users based on their location histories. Such user similarity is significant to individuals, communities and businesses by helping them effectively retrieve the information with high relevance. A framework, referred to as hierarchical-graph-based similarity measurement (HGSM), is proposed for geographic information systems to consistently model each individual's location history and effectively measure the similarity among users. In this framework, we take into account both the sequence property of people's movement behaviors and the hierarchy property of geographic spaces. We evaluate this framework using the GPS data collected by 65 volunteers over a period of 6 months in the real world. As a result, HGSM outperforms related similarity measures, such as the cosine similarity and Pearson similarity measures.

/pdf/mining-user-similarity-based-on-location-history-58mvxud24d.pdf

Mining user similarity based on location history

Recommendation systems, which automatically understand user preferences and make recommendations, are now widely used in online shopping. However, so far there have been few attempts of applying them to real-world shopping. In this paper, we propose a novel real-world recommendation system, which makes recommendations of shops based on users’ past location data history. The system uses a newly devised place learning algorithm, which can efficiently find users’ frequented places, complete with their proper names (e.g. “The Ueno Royal Museum”). Users’ frequented shops are used as input to the item-based collaborative filtering algorithm to make recommendations. In addition, we provide a method for further narrowing down shops based on prediction of user movement and geographical conditions of the city. We have evaluated our system at a popular shopping district inside Tokyo, and the results demonstrate the effectiveness of our overall approach.

CityVoyager: an outdoor recommendation system based on user location history

Recommendation systems are now widely used in online shopping sites, but so far there have been few attempts of applying them to real-world shopping. In this paper we propose a novel real-world recommendation system, which recommends shops to users based on their individual preferences and needs, estimated by analyzing their past location history acquired using GPS. The system automatically figures out each user's frequently visited shops using a custom estimation algorithm, and makes recommendations by using the shops as input to the item-based collaborative filtering algorithm. Furthermore, to provide more timely recommendations, our system takes into account the user's usual shopping routes, and the ease of access from the user's current location to each shop. We have conducted an evaluation test using a prototype of our system at Daikanyama, Tokyo, and the results show great promise in the system's ability to make accurate recommendations.

/pdf/an-outdoor-recommendation-system-based-on-user-location-l894qtrl2t.pdf

An Outdoor Recommendation System based on User Location History

In this paper, we describe an intelligent location-aware city guide system, which adapts to each user's preferences, and uses an intuitive "metal detector" interface for navigation. Our system analyzes each user's past location data history to estimate individual preferences, and allows users to find shops that match their tastes in the same way a metal detector would be used to detect metal objects. The procedure with which the system picks out shops that match each user's preferences includes a newly developed place learning algorithm, which can efficiently find frequented places, complete with their proper names (e.g. "The Ueno Royal Museum"). We have conducted a series of evaluation tests at a popular shopping district inside Tokyo, and the results validate the effectiveness of our overall approach.

A user-adaptive city guide system with an unobtrusive navigation interface

We developed a new system called CarettaKids that supports face-to-face collaborative learning by children. CarettaKids uses a sensing board based on the Radio Frequency Identification (RFID) technology to support collaboration in a shared space, and the Personal Digital Assistant (PDA) device to support activity in personal spaces. We also introduced this system into an actual classroom environment to evaluate its performance in support for children's collaborative learning, by analyzing the childrens' interaction. As a result, we have confirmed that CarettaKids's feature of transition between two spaces, makes it possible for children to reflect on problems detected in the shared space so as to find solutions in their respective personal space, and to engage in an active exchange of opinions in the shared space, based on ideas generated from personal-space learning.

/pdf/carettakids-a-system-for-supporting-children-s-face-to-face-1uqbya39md.pdf

CarettaKids: a system for supporting children's face-to-face collaborative learning by integrating personal and shared spaces

In this paper, we propose a user-adaptive video summarization system which accounts for individual preferences by analyzing contents of the user's personal photo library. Nowadays, it is common practice for people to keep thousands of photos in their PCs, taken with their digital cameras. Due to the similarities in characteristics between video and still photos, we assume that these libraries can be used to infer each user's preferences on video summarization. The system uses image classification techniques to determine which sections of the movie are "important" to the user, and performs summarization by cutting off sections regarded as unimportant, while taking care not to overly disrupt the continuity of the video. We have implemented a prototype of the system, and conducted a series of evaluation tests to assess its effectiveness. The results show that our overall approach has the potential to serve as a powerful automatic/semi-automatic video summarization solution.

Yuichiro Takeuchi

Papers

CityVoyager: an outdoor recommendation system based on user location history

An Outdoor Recommendation System based on User Location History

A user-adaptive city guide system with an unobtrusive navigation interface

CarettaKids: a system for supporting children's face-to-face collaborative learning by integrating personal and shared spaces

User-adaptive home video summarization using personal photo libraries