Towards a service-oriented architecture for a mobile assistive system with real-time environmental sensing

Abstract

With the growing aging population, age-related diseases have increased considerably over the years.In response to these, ambient assistive living (AAL) systems are being developed and are continually evolving to enrich and support independent living. While most researchers investigate robust activity recognition (AR) techniques, this paper focuses on some of the architectural challenges of the AAL systems. This work proposes a system architecture that fuses varying software design patterns and integrates readily available hardware devices to create wireless sensor networks for real-time applications. The system architecture brings together the serviceoriented architecture (SOA), semantic web technologies, and other methods to address some of the shortcomings of the preceding system implementations using off-the-shelf and open source components. In order to validate the proposed architecture, a prototype is developed and tested positively to recognize basic user activities in real time.The system provides a base that can be further extended in many areas of AAL systems, including composite AR.

Semantic segmentation of real-time sensor data stream for complex activity recognition

“…This approach further enables new learnt activity models and rules to be more easily incorporated into the existing model at runtime and automatically taken in consideration during the separation and segmentation process. The future direction of this work is to implement and evaluate the proposed approach within a real-time sensing environment that was developed in the previous work [29,30]. Moreover, efficient HAR and activity learning algorithms will be investigated to enrich and expand the initial domain model incrementally over period of time to provide impersonal and personal service to the user(s).…”

“…This paper proposes a semantical approach for segmenting sensor data stream into multiple activity threads with the property description of a given sensor that it is attached with. Central to the approach is the expressive ontological model to perform terminology box (T-Box) and assertion box (A-Box) reasoning [29,30], generic and user specific logical rules, dynamic window size analyses [23] and continuous RDF querying language. In addition, different from other approaches, the proposed segmentation approach is sensitive to changes made to the ontological modal by a given activity learning algorithm, rules (non/specific to user) and user defined preferences.…”

“…9). The A-box reasoning approach defined here [29,30] and rule-based generated in SWRL [32] or SPIN [34] is employed. Furthermore, dynamic time series analysis [24] is required to calculate the window size of the overall session and sub-activity threads.…”

Real-time sensor observation segmentation for complex activity recognition within smart environments

“…The reasoning result and sensor events are broadcasted to the clients and the android application continuously capture and present information to the inhabitant. Details can be found in previous studies [27], [28]. Fig.…”

A semantics-based approach to sensor data segmentation in real-time Activity Recognition

“…An android mobile application and RESTful web service have been used to create a service-oriented architecture (SOA) system. An SOA enables the web service to execute computation tasks such as segmentation and AR on the sen- Details of the SOA implementation and multithreading concept can be found in previous studies [39,40].…”