Robust Location-Aware Activity Recognition Using Wireless Sensor Network in an Attentive Home

This paper presents a robust location-aware activity recognition approach for establishing ambient intelligence applications in a smart home. With observations from a variety of multimodal and unobtrusive wireless sensors seamlessly integrated into ambient-intelligence compliant objects (AICOs), the approach infers a single resident's interleaved activities by utilizing a generalized and enhanced Bayesian Network fusion engine with inputs from a set of the most informative features. These features are collected by ranking their usefulness in estimating activities of interest. Additionally, each feature reckons its corresponding reliability to control its contribution in cases of possible device failure, therefore making the system more tolerant to inevitable device failure or interference commonly encountered in a wireless sensor network, and thus improving overall robustness. This work is part of an interdisciplinary Attentive Home pilot project with the goal of fulfilling real human needs by utilizing context-aware attentive services. We have also created a novel application called Activity Map to graphically display ambient-intelligence-related contextual information gathered from both humans and the environment in a more convenient and user-accessible way. All experiments were conducted in an instrumented living lab and their results demonstrate the effectiveness of the system. Note to Practitioners-This system aims to achieve non-obtrusive and location-aware activity recognition, and the authors have successfully prototyped several AICOs to naturally collect interactions from residents or status from the environment. In addition, these AICOs have the potential to be commercialized in the future due to practicability and near-term advances in embedded systems. Furthermore, other potential advantages of an AICO lie in its applicability to other domains beyond just the home environment. Our initial work has yielded high overall accuracy, therefore, suggesting that it is a feasible approach that may lead to practical ambient intelligent applications (such as the Activity Map in this work). The limitations are that some currently available sensors cannot measure specific desired observations, or, in some cases, require users to carry them to operate.