Use this URL to cite or link to this record in EThOS: https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.785505
Title: Multi-sensor data fusion and modelling in mobile devices for enhanced user experience
Author: Al-Marhoubi, Asmaa H. A.
ISNI:       0000 0004 7971 0127
Awarding Body: Loughborough University
Current Institution: Loughborough University
Date of Award: 2016
Availability of Full Text:
Access from EThOS:
Access from Institution:
Abstract:
Recent advances in mobile technology have, in particular, being driven by user demand. Mobile handheld devices are now an important part of day-to-day life of every individual and thus the user experience provided by such a device is of significant importance. Automatic Backlight Adjustment approaches are being used at present to enhance user experience when image/video content is being viewed under extreme illumination conditions. However, such approaches suffer from content in some regions of the frame being completely destroyed due to the global adjustment of brightness that is made to vary dependent on illumination surrounding the mobile device display. A solution to this has been recently being proposed by a commercially patented technology, Iridix™. However this technology suffers from the shortcomings of the present generation Ambient Light Sensors (ALS) used for sensing illumination surrounding a screen, namely latency of operation and narrow angle sensitivity. In this research we make use of the data gathered via various sensors available within a mobile device to accurately predict illumination within the 3D space surrounding a mobile device, even when a user is freely using the device. The data gathered from two motion based sensors, namely the accelerometer and gyroscope are used to model and predict the usage of the mobile device. This information is then used in identifying the exact motion of the mobile device within a 3D space that is lit up by a complex configuration of multiple light sources in order to model usage dependent illumination changes that a user experience around the mobile device. This way the more accurate values of illumination are determined that are used to enhance the performance of the Iridix™ technology, which in turn is able to significantly enhance the user experience when watching image/video content on a device screen. The thesis investigates the use of various mathematical models and machine learning algorithms to serve the above purpose.
Supervisor: Not available Sponsor: Not available
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID: uk.bl.ethos.785505  DOI: Not available
Keywords: Information and Computing Sciences not elsewhere classified ; Sensor fusion ; Ambient Light Sensors (ALS) ; Machine learning ; Accelerometer ; Gyroscope ; Modelling ; Illumination ; 2D space ; 3D space ; Mobile handheld devices
Share: