OPPORTUNITY: Towards opportunistic activity and context recognition systems

Abstract

Opportunistic sensing allows to efficiently collect information about the physical world and the persons behaving in it. This may mainstream human context and activity recognition in wearable and pervasive computing by removing requirements for a specific deployed infrastructure. In this paper we introduce the newly started European research project OPPORTUNITY within which we develop mobile opportunistic activity and context recognition systems. We outline the project's objective, the approach we follow along opportunistic sensing, data processing and interpretation, and autonomous adaptation and evolution to environmental and user changes, and we outline preliminary results.

Collecting complex activity datasets in highly rich networked sensor environments

“…Thus, the mapping between sensor signals and activities cannot be learned at design time. Within the EU project OPPORTUNITY we investigate how to address these challenges [8].…”

“…Within the EU FP7 FET-Open project OPPORTUNITY, we develop mobile systems to recognize human activity in opportunistic sensor setups [8]. We envision developments along self-organized sensing, opportunistic context recognition methods and autonomous adaptation (see figure 1).…”

Unsupervised adaptation for acceleration-based activity recognition: robustness to sensor displacement and rotation

“…In our case, the estimated shift provides a direct estimation of the changes in the feature distribution [2]. Such measure can be used to infer an online estimation of the system reliability, a critical point for systems that have to deal with dynamic changing environments [13,21]. For example, if a sensor is considered non reliable (e.g., when the estimated shift Θ exceeds a given threshold), compensatory actions can be taken, such as its removal from a sensor network [13,23,22].…”

A Self-organizing Approach to Activity Recognition with Wireless Sensors

“…For example, a person which is running in the woods and equipped with a body sensor network for monitoring his activities, may lose sensors, carry more or less sensors, or their on-body locations may vary due to his movement. In the recently started European research project OPPORTUNITY [3], an alternative approach is proposed, which is based on an opportunistic recognition of activities with sensors that are currently available.…”

“…This means, that from a set of available sensors, just those which are capable of providing the relevant information cooperate to achieve the goal. In [3], goal-oriented sensing is achieved based on (i) the formulation of a recognition goal which represents the activities to be recognized and (ii) its transformation into a coordinated sensing mission which is communicated to the sensor network. The scope of the present paper is the interaction between body-worn sensors, which is necessary for their ad-hoc formation according to a received sensing mission.…”