Detection of Dangerous Situations Using a Smart Internet of Things System - New Contributions in Information Systems and Technologies - page 364

Detection of Dangerous Situations Using a Smart Internet
of Things System

Nuno Vasco Lopes, Henrique Santos, and Ana Isabel Azevedo

Department of Information Systems, School of Engineering,
University of Minho, Portugal
[e-mail], [e-mail],
[e-mail]

Abstract. The Internet of Things (IoT) is a concept that can foster the emer-
gence of innovative applications. In order to minimize parents's concerns about
their children's safety, this paper presents the design of a smart Internet of
Things system for identifying dangerous situations. The system will be based
on real time collection and analysis of physiological signals monitored by non-
invasive and non-intrusive sensors, Frequency IDentification (RFID) tags and a
Global Positioning System (GPS) to determine when a child is in danger. The
assumption of a state of danger is made taking into account the validation of a
certain number of biometric reactions to some specific situations and according
to a self-learning algorithm developed for this architecture. The results of the
analysis of data collected and the location of the child will be able in real time
to child's care holders in a web application.

Keywords: Internet of Things, IoT, dangerous situations, sensor network, child,
self-learning algorithm.

1 Introduction

The use of Internet of Things may include a lot of devices such as Radio-Frequency
IDentification tags, sensors, actuators, mobile phones, etc. - which are able to interact
with each other creating an ubiquitous system [1]. There are many applications for
IoT with the ability to influence user's life. The detection of dangerous situations can
be useful in many domains such as smart environment, crime detection, e-health and
so on. The pervasive nature of information sources allows the computation of a great
amount of data [2].
Sensor networks consist on using several sensors to collect data and communicate
it wirelessly. After receiving the information, sensing nodes must send it to other
sensors called sinks [1].
Affective Computing is the domain of computing that recognizes the advantages of
adding emotional features to human-computer interaction. When associated to the use
of sensor networks, affective computing makes possible the detection of user's affec-
tive state [3].
By mixing these three concepts, our research attempts to create a system capable
of identifying through the use of a sensors network, the moment when a child is in