Agatha: Predicting Daily Activities from Place Visit History for Activity-Aware Mobile Services in Smart Cities

Abstract

We present a place-history-based activity prediction system called Agatha, in order to enable activity-aware mobile services in smart cities. The system predicts a user's potential subsequent activities that are highly likely to occur given a series of information about activities done before or activity-related contextual information such as visit place and time. To predict the activities, we develop a causality-based activity prediction model using Bayesian networks. The basic idea of the prediction is that where a person has been and what he/she has done so far influence what he/she will do next. To show the feasibility, we evaluate the prediction model using the American Time-Use Survey (ATUS) dataset, which includes more than 10,000 people's location and activity history. Our evaluation shows that Agatha can predict users' potential activities with up to 90% accuracy for the top 3 activities, more than 80% for the top 2 activities, and about 65% for the top 1 activity while considering a relatively large number of daily activities defined in the ATUS dataset, that is, 17 activities.

Building University-Industry Co-Innovation Networks in Transnational Innovation Ecosystems: Towards a Transdisciplinary Approach of Integrating Social Sciences and Artificial Intelligence

“…Many AI-based methodologies have been put forward to construct models based on mobility patterns and predict the behavior of people individually or as a group [112,113]. These include stochastic models such as Markov Models MM) [114] and Bayesian Networks (BN), as well as non-stochastic models such as Artificial Neural Networks (ANN) and Decision Trees (DT) [115]. While researchers have used ML techniques such as ANN and DT [116], the stochastic models are preferred over these due to the uncertainty in or unpredictability of human behavior [116].…”

“…While researchers have used ML techniques such as ANN and DT [116], the stochastic models are preferred over these due to the uncertainty in or unpredictability of human behavior [116]. In several studies e.g., [115,116] researchers have also used Bayesian Networks.…”

A Review of Internet of Things Technologies for Ambient Assisted Living Environments

“…For example, IoT has started to be used for entertainment and education such as the intelligent cultural spaces presented in [50] or the IoT-aware services for smart museums [51], based on an indoor localization method (using Bluetooth), wearable devices and the users' mobile devices to display and share cultural contents in the cloud. Smart parking system [52], blind navigation system [53], dangerous situations detection system [54] or activity prediction system for mobile services [55] are also good examples of the IoT AAL applications in the context of smart cities and connected smart environments.…”

A Survey for the Ranking of Trajectory Prediction Algorithms on Ubiquitous Wireless Sensors

“…A detailed discussion on each approach was incorporated for better insight. Finally, the top three algorithms, which were NextPlace [7], the Markov model [8], and the hidden Markov model [9], were proposed. This research describes the selected studies and discuss the results of these trajectory prediction algorithms highlighted in the literature.…”

“…A detailed discussion on each approach was incorporated for better insight. Finally, the top three algorithms, which were NextPlace [ 7 ], the Markov model [ 8 ], and the hidden Markov model [ 9 ], were proposed.…”