Building smart home environments which automatically or semi-automatically assist and comfort occupants is an important topic in the pervasive computing field, especially with the coming of cheap, easy-to-install sensors. This has given rise to the indispensable need for human activity recognition from ubiquitous sensors whose purpose is to observe and understand what occupants are trying to do from sensory data. The main approach to the problem of human activity recognition is a probabilistic one so as to handle the complication of uncertainty, the overlapping of human behaviours and environmental noise. This thesis develops a probabilistic model as a framework for human activity recognition using multiple multi-modal sensors in complex pervasive environments. The probabilistic model to be developed is adapted and based on the abstract hidden Markov model (AHMM) with one layer to fuse multiple sensors. The concept of factored state representation is employed in the model to parsimoniously represent the state transitions for reducing the number of required parameters. The exact method is used in learning the model’s parameters and performing inference. To be able to incorporate a large number of sensors, several more parsimonious representations including the mixtures of smaller multinomials and sigmoid functions are investigated to model the state transitions, resulting in a reduction of the number of parameters and time required for training. / We examine the approximate variational method to significantly reduce the time required for training the model instead of using the exact method. A system of fixed point equations is derived to iteratively update the free variational parameters. We also present the factored model in the case where all variables are continuous with the use of the conditional Gaussian distribution to model state transitions. The variational method is still employed in this case to speed up the model’s training process. The developed model is implemented and applied in recognizing daily activity in our smart home and the Nokia lab from multiple sensors. The experimental results show that the model is appropriate for fusing multiple sensors in activity recognition with a reasonable recognition performance.

Smart Grid research is growing around the world due to the need to replace the ageing old electricity grid with an intelligent, reliable electricity network. The smart grid aims at creating a reliable power distribution and efficient power usage in homes. One of the key issues focused in this project is providing real time energy feedback to users, which is minimal or non-existent in the current grid system. This thesis investigates about using smart TVs to provide real time energy feedback in homes. Since its introduction in 2009 smart TVs are growing in popularity in European market. To provide real time energy feedback on smart TVs three features are identified Smart TV application, ambilighting and push notification. The Human-centered design process is used for designing the Smart TV interface system using the identified features. A literature study is conducted to gather the user requirements for the smart TV interface. The information gathered during the study is used for the design and implementation of the interface prototype. As an example platform the Philips smart TV 2013 is chosen to demonstrate the various features that can be used to provide energy feedback. The usability of the Smart TV interface is evaluated with users and the results are recorded. The smart TV application, ambient lighting and push notification system in Smart TVs is demonstrated for providing real-time energy feedback. The interface is evaluated with users and results are discussed. The result suggests that Smart TVs can serve as an informational display in homes. The Smart TV interface should be interlinked with Smart Phone and Tablet applications to be effective, further the users prefer the Smart Phone over the Smart TV application to control the household devices. / The thesis work evaluates the potential of using smart TVs to provide real time energy feedback in homes. The results of the thesis showed that smart phone are the primary interaction medium suitable for home environment while smart TVs can serve as an informative medium to provide ambient feedback in homes. / praveenjelish@ymail.com +46727700788