Activity Recognition (AR) is key in context-aware assistive living systems. One challenge in AR is the segmentation of observed sensor events when interleaved or concurrent activities of daily living (ADLs) are performed. Several studies have proposed methods of separating and organising sensor observations and recognise generic ADLs performed in a simple or composite manner. However, little has been explored in semantically distinguishing individual sensor events directly and passing it to the relevant ongoing/new atomic activities. This paper proposes Semiotic theory inspired ontological model, capturing generic knowledge and inhabitant-specific preferences for conducting ADLs to support the segmentation process. A multithreaded decision algorithm and system prototype were developed and evaluated against 30 use case scenarios where each event was simulated at 10sec interval on a machine with i7 2.60GHz CPU, 2 cores and 8GB RAM. The result suggests that all sensor events were adequately segmented with 100% accuracy for single ADL scenarios and minor improvement of 97.8% accuracy for composite ADL scenario. However, the performance has suffered to segment each event with the average classification time of 3971ms and 62183ms for single and composite ADL scenarios, respectively.

Data segmentation plays a critical role in performing human activity recognition (HAR) in the ambient assistant living (AAL) systems. It is particularly important for complex activity recognition when the events occur in short bursts with attributes of multiple sub-tasks. Although past efforts were made in segmenting the real-time sensor data stream such as static/dynamic window sizing approaches, little has been explored to use the description of the activity of daily living (ADL) to support generic/user-specific preferences at segmentation stage. Therefore, this paper proposes semanticbased segmentation approach which uses ontology to perform terminology-box (T-Box) and assertion-box (A-Box) reasoning, along with logical rules to infer whether the incoming sensor event is related to a given sequences of the activity. A use-case scenario is used to illustrate how the proposed approach conducts semantic segmentation of real-time sensor data stream to recognise an elderly persons complex activities.

As the aging population grows, age-related diseases show a cohesive increase. Ambient Assistive Living (AAL) systems are being developed and are continually evolving in various areas. While most researchers focus on robust Activity Recognition techniques, this paper investigates some of the architectural challenges of the AAL systems. This study proposes a new system architecture that brings together the service-oriented architecture (SOA), Semantic Web technologies and other methods to address some of the shortfalls in the predecessor system implementations using off-the-shelf and open source components. A partial system implementation is then presented using the proposed system architecture. The system takes some of the key design aspects such as extensibility, reusability, scalability, and maintainability into consideration that can then be seen as a base to further extend the capability of monitoring, collecting, processing and accurately recognising complex or concurrent activities in its overall aim to support assistive living.

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.

No abstract