ToA estimation system for efficient cycling in Smart Cities Theodoros Anagnostopoulos Department of Infocommunication Technologies ITMO University Russia thanag@di.uoa.gr Klimis Ntalianis Department of Marketing Athens University of Applied Sciences Greece kntal@teiath.gr Christos Skourlas Department of Informatics Athens University of Applied Sciences Greece cskourlas@teiath.gr Inna Sosunova Department of Infocommunication Technologies ITMO University Russia 190765@niuitmo.ru Petr Fedchenkov Department of Infocommunication Technologies ITMO University Russia pvfedchenkov@corp.ifmo.ru Arkady Zaslavsky Information Engineering Laboratory CSIRO Computational Informatics Australia Arkady.Zaslavsky@csiro.au ABSTRACT Smartphone sensing enables efficient Time-of-Arrival (ToA) estimation of moving cyclists towards traffic lights in a Smart City. GPS sensors locate the actual position of cyclists on their way to traffic lights. Since the constant use of GPS sensors drain the battery of the smartphones there is a need of efficient energy consumption techniques. In this paper we propose a velocity based ToA estimation system to face the GPS energy consumption inefficiency. In addition we aim to enable efficient cycling in Smart Cities by turning traffic lights to green proactively thus achieving overall citizen’s wellbeing. CCS CONCEPTS ∙ Human-centered computing → Ubiquitous and mobile computing → Ubiquitous and mobile computing systems and tools ∙ Computer systems organization → Embedded and cyber-physical systems → Sensors and actuators KEYWORDS ToA estimation, smartphone GPS sensor, energy efficiency, cycling, Smart Cities 1 INTRODUCTION Contemporary research in ToA estimation focuses on static models for inferring the system behavior. However, ToA estimation systems, and especially in the case of cycling in Smart Cities, interact with users to provide them advanced Quality of Service (QoS) in extreme weather conditions. Such systems incorporate dynamic models for estimating ToA towards traffic lights. Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for third- party components of this work must be honored. For all other uses, contact the owner/author(s). PCI 2017, September 2017, Larissa, Greece © 2017 Copyright held by the owner/author(s). $15.00 DOI: 10.1145/3139367.3139412 In addition, GPS sensors drain the battery of the smartphones. This, emerges a need for efficient energy consumption ToA estimation. In this paper we propose a ToA estimation system, which sets GPS sensor inactive for certain period of time until the cyclist approaches the traffic light. The system is stable even in the case of traces with many traffic lights. The rest of the paper is structured as follows. Section 2, presents the related work in the research area. Section 3, defines the dynamic ToA estimation model for efficient cycling in Smart Cities. Section 4, describes the experimental setup. Section 5, presents the results of the experiments. Section 6, discusses the results, while Section 7 concludes the paper and proposes future work. 2 RELATED WORK Location prediction of cyclists can be achieved by using a variety of sensors, including GPS, available on smartphones. Specifically, location prediction for outdoor settings is possible either by analyzing the relative position of movement handovers within a cellular network [1-4], or by exploiting the recorded GPS position of a moving entity. In the second case, analysis of GPS position data may rely solely on GPS coordinates [5], GPS coordinates enhanced with time [6,7], or GPS coordinates along with velocity and direction [8,9]. Actually, predicting the future location of a cyclist is the first step towards predicting the time-of- arrival (ToA) to particular locations of interest, which in our case are the traffic lights of a city. Currently, the literature on ToA estimation contains a variety of computational approaches based on: historical trajectories [10], real-time map matching [11], shared locations [12], and mobile phone participatory urban sensing [13,14]. In addition, ToA estimation of cyclists is also feasible by developing models that incorporate GPS coordinates, time, velocity and direction enhanced with bearing [15]. In this paper, we perform ToA estimation of cyclists in Smart