Inferring distant-time location in low-sampling-rate trajectories

Abstract

With the growth of location-based services and social services, lowsampling-rate trajectories from check-in data or photos with geotag information becomes ubiquitous. In general, most detailed moving information in low-sampling-rate trajectories are lost. Prior works have elaborated on distant-time location prediction in highsampling-rate trajectories. However, existing prediction models are pattern-based and thus not applicable due to the sparsity of data points in low-sampling-rate trajectories. To address the sparsity in low-sampling-rate trajectories, we develop a Reachability-based prediction model on Time-constrained Mobility Graph (RTMG) to predict locations for distant-time queries. Specifically, we design an adaptive temporal exploration approach to extract effective supporting trajectories that are temporally close to the query time. Based on the supporting trajectories, a Time-constrained mobility Graph (TG) is constructed to capture mobility information at the given query time. In light of TG, we further derive the reachability probabilities among locations in TG. Thus, a location with maximum reachability from the current location among all possible locations in supporting trajectories is considered as the prediction result. To efficiently process queries, we proposed the index structure Sorted Interval-Tree (SOIT) to organize location records. Extensive experiments with real data demonstrated the effectiveness and efficiency of RTMG. First, RTMG with adaptive temporal exploration significantly outperforms the existing pattern-based prediction model HPM [2] over varying data sparsity in terms of higher accuracy and higher coverage. Also, the proposed index structure SOIT can efficiently speedup RTMG in large-scale trajectory dataset. In the future, we could extend RTMG by considering more factors (e.g., staying durations in locations, application usages in smart phones) to further improve the prediction accuracy.

Efficient Route Recommendation System Based On Keyword Using Candidate Route Generation And Travel Route Exploration

“…The paper [3]showing an sequence of travel recommendations which are personalized individually. It using both travelogues and [33], [34] community photos, tagged images, location, and date etc. Unlike existing approaches, this approach is recommending a travel sequence were will not only taking individual interests but also the time of visiting and seasons etc, so that the travel gap between different locations can be avoided.…”

Mining and Planning Time-aware Routes from Check-in Data

“…Sadilek et al [15] predict the most likely location of an individual at any time, given the historical trajectories of his/her friends. Chiang [5] consider the current time to predict locations. They construct a Time-constrained Mobility Graph that captures a user's moving behavior within a certain time interval, and compute the reachability between locations to infer next one.…”

“…We add to initialize the . After setting the final route as the initial one (line 3), we perform the iterative expansion search process until the route is constructed up to length (line [5][6][7][8][9][10][11][12][13]. For each iteration, the last location in the route with the highest RVG score is identified (line 6 and line 13) and each possible next visiting location from the routable map H is put into a candidate set (line 7).…”

Mineração de trajetórias em redes sociais geolocalizadas

“…Para a inferência das possíveis rotas, o textitInferTra utiliza amostragem de Gibb (CASELLA; GEORGE, 1992) para aprender a partir de um banco de dados de trajetórias e gerar um Modelo de Mobilidade de Rede que será usado pelo algoritmo de inferência. Entre os trabalhos que utilizam a informação das ruas com maior destaque, tem-se: Hunter, Abbeel e Bayen (2013), Zheng et al (2012), Li, Ahmed e Smola (2015) e Chiang et al (2013).…”