- Title
- An intelligent multimodal interface for in-car communication systems
- Creator
- Sielinou, Patrick Tchankue
- Subject
- Automotive telematics
- Subject
- Automobiles -- Electronic equipment
- Date Issued
- 2011
- Date
- 2011
- Type
- Thesis
- Type
- Masters
- Type
- MSc
- Identifier
- vital:10461
- Identifier
- http://hdl.handle.net/10948/1495
- Identifier
- Automotive telematics
- Identifier
- Automobiles -- Electronic equipment
- Description
- In-car communication systems (ICCS) are becoming more frequently used by drivers. ICCS are used in order to minimise the driving distraction due to using a mobile phone while driving. Several usability studies of ICCS utilising speech user interfaces (SUIs) have identified usability issues that can affect the workload, performance, satisfaction and user experience of the driver. This is due to current speech technologies which can be a source of errors that may frustrate the driver and negatively affect the user experience. The aim of this research was to design a new multimodal interface that will manage the interaction between an ICCS and the driver. Unlike the current ICCS, it should make more voice input available, so as to support tasks (e.g. sending text messages; browsing the phone book, etc), which still require a cognitive workload from the driver. An adaptive multimodal interface was proposed in order to address current ICCS issues. The multimodal interface used both speech and manual input; however only the speech channel is used as output. This was done in order to minimise the visual distraction that graphical user interfaces or haptics devices can cause with current ICCS. The adaptive interface was designed to minimise the cognitive distraction of the driver. The adaptive interface ensures that whenever the distraction level of the driver is high, any information communication is postponed. After the design and the implementation of the first version of the prototype interface, called MIMI, a usability evaluation was conducted in order to identify any possible usability issues. Although voice dialling was found to be problematic, the results were encouraging in terms of performance, workload and user satisfaction. The suggestions received from the participants to improve the system usability were incorporated in the next implementation of MIMI. The adaptive module was then implemented to reduce driver distraction based on the driver‟s current context. The proposed architecture showed encouraging results in terms of usability and safety. The adaptive behaviour of MIMI significantly contributed to the reduction of cognitive distraction, because drivers received less information during difficult driving situations.
- Format
- xii, 138 leaves
- Format
- Publisher
- Nelson Mandela Metropolitan University
- Publisher
- Faculty of Science
- Language
- English
- Rights
- Nelson Mandela Metropolitan University
- Hits: 1124
- Visitors: 1234
- Downloads: 141
Collections
NMMU School of Computer Science, Mathematics, Physics and Statistics
| Thumbnail | File | Description | Size | Format | |||
|---|---|---|---|---|---|---|---|
| View Details Download | SOURCEPDF | 2 MB | Adobe Acrobat PDF | View Details Download |