Smart Unit

The Unit is conducting research in the areas of Intelligent User Interfaces, Information Visualisation and Mobile Technology for the ICT sector of South Africa. The project efforts of the CoE are intended to deliver highly skilled graduates, intellectual property and prototype software products which are of interest to the industry partners.

Design a model for a smart environment using advanced technology that can improve people’s lives. The interaction with this environment will incorporate natural interaction, including gesture-based interaction, multimodal interaction and smart devices. Personalisation will be used to recognize the user and allow customisation. This smart environment will serve as a prototype for a smart home or a smart office.

Include ambient intelligence in the design of the smart environment. Ambient intelligence is an emerging discipline that brings intelligence to our everyday environments and makes these environments sensitive to us. Ambient intelligence research builds on advances in sensors and sensor networks, pervasive computing and artificial intelligence. The resulting technologies promise to revolutionise daily human life by making people’s surroundings flexible and adaptive. The ambient intelligence algorithm perceives the state of the environment and users with sensors, reasons about the data using a variety of AI techniques, and acts upon the environment using controllers in such a way that the algorithm achieves its intended goal.

Incorporate context-awareness in the smart environment. Context-awareness is a key feature of ambient intelligence systems and is dependent on the characteristics of the environment. Some elements in these environments are more recurrent than others across different applications. For example, the location as well as the time and duration of the states, events and activities are essential to understand the latest developments in a specific environment. Identifying the actors is also very relevant and is not a trivial task. An important aspect of ambient intelligence is interaction. The system is supposed to use its intelligence to infer situations and user needs from the recorded activities. On the other hand, a diversity of users may need direct interaction with the system to indicate preferences, needs, etc. In some cases, diverse interface mechanisms are combined to form multimodal interfaces.

Incorporate personalisation in the smart environment. Smart homes have also been defined as a residence equipped with computing technology that anticipates and responds to the needs of the occupants, working to promote their comfort, security and entertainment through the management of the technology within the home and connections to the world beyond (Carla, Correia, Miranda, & Hornung, 2013). Smart environments need to acquire and apply knowledge about the environment and its inhabitants in order to improve the inhabitants’ experience with the environment. 

Consider accessibility needs in the context of the smart environment. Accessibility is considered to be an essential component of robotics. Some studies propose multimodal interfaces for gesture and voice, aiming to include a wider diversity of users. This is especially relevant in the case of elderly and disabled users. Changing the way people interact with the environment highlights new aspects of accessibility that require more research. Although usability guidelines are widely used for traditional solutions, new guidelines or the adaptation of existing ones are required for natural user interfaces.