Task recommendation for group users in public ioT environments

Abstract

There are an increasing number of public Internet of Things (IoT) devices installed in urban environments with which users can perform a wide variety of tasks. Due to the nature of public places, these IoT devices must support groups of users rather than only individuals. However, because the type and quality of IoT devices in public environments varies, it may be difficult for groups of users to recognize the opportunities to perform such tasks. Moreover, group users are usually new to a public place and have not previously performed tasks in IoT-enriched public places. In this paper, we propose a two-phase task recommendation approach for groups of IoT users in public environments. In the first phase, we use a random walk with restart (RWR) algorithm to overcome the problem of sparse historical data on performing user tasks in public IoT environments. We utilize data from neighboring user groups with similar member organization as targets for effectively predicting tasks for new user groups. The second phase predicts a set of operations (IoT device functionalities) that are most appropriate for each candidate task. In this phase, for more effective prediction of the IoT operations for a user task, we consider the contextual semantics of users via a classification model. We evaluate our approach using real-world datasets collected from practical IoT testbed environments. Our results demonstrate that task recommendation using the RWR algorithm based on member organization better recommends tasks to new user groups than baseline approaches. In addition, we show that an appropriate set of task operations can be effectively predicted by considering task types and contextual semantics.