Activity location recognition from mobile phone data using improved HAC and Bi‐LSTM

Abstract

Existing studies on activity location recognition based on mobile phone data has made great progresses. However, current studies generally assume constant distance threshold when performing activity location clustering, and ignore the influence of base station layout on positioning accuracies of mobile phone data. Given different recognition accuracy requirements, the authors propose two methods to recognise activity locations: (1) An improved hierarchical agglomerative clustering algorithm that integrates a genetic algorithm component to search and dynamically adjust optimal distance thresholds based on base station densities; (2) The recognition method based on Bi‐directional long short‐term memory network that classifies travel statuses of mobile phone traces. Results show that, compared with existing methods, the activity location recognition accuracy of the proposed hierarchical agglomerative clustering algorithm increases by about 5%. The Bi‐directional long short‐term memory network model further outperforms the improved hierarchical agglomerative clustering, especially in the aspect of recognising non‐commuting activity locations. However, the Bi‐directional long short‐term memory network model training requires the users’ actual travel information, so there are certain obstacles in popularising Bi‐directional long short‐term memory network in practice.

Next Place Prediction Model: A Literature Review

“…Techniques such as clustering, frequent pattern mining, and association rule mining are used to discover spatial-temporal patterns in mobility data [26,27,38,41]. Clustering allows the classification of variables based on their features or characteristics (e.g., population density), grouping individual inputs with similar properties into the same category [15,23,27]. Flow-based algorithm [39] is an approach that models complex systems able to represent the interconnected flows between nodes and measures the spatiotemporal variation, predicting the trip.…”

“…Flow-based algorithm [39] is an approach that models complex systems able to represent the interconnected flows between nodes and measures the spatiotemporal variation, predicting the trip. It is suitable to understand mobility flows across city areas, providing valuable insights into the next place prediction problem [15,20,23,24,31]. Probabilistic models utilize probability theory to estimate the likelihood of an individual visiting a particular place next.…”

“…The purposes of the studies can be divided between individual mobility prediction, which captures regularities, and tendencies of individual's mobility behaviours using mobility data, and population mobility prediction, which captures mobility behaviours at a population/group of individual level, capturing aggregated trends. The first predictions are carried out mainly by means of statistic or machine learning techniques according to the data availability [8][9][10][11][12][13][20][21][22][23][24][25][26][27][28][29][30][31][32][33][34][35][36], while the latter can also exploit data mining techniques or agent-based modelling [6,11,24,[37][38][39][40][41][42][43][44][45][46]. The identified purposes can be further segmented from a spatial perspective by varying the unit of analysis, resulting in three prediction outcomes per purpose, i.e., trajectory recognition, next location prediction, and next trip prediction.…”

“…Instead, next location prediction, relying more on statistical analysis, focuses on estimating the most likely destination that a person will visit after the visited one, exploiting historical trajectories and contextual information. By exploiting past behaviours, possible areas where an individual will be in the future can be identified [11,15,23,24,33,37,39,41]. Finally, next trip prediction, similarly to next place prediction, by exploiting historical data, aims to predict the whole trip performed, identifying starting, intermediate and final points [10,12,16,21,35].…”