A steady signal exerts two complementary effects on a noisy acoustic environment: one is to add energy, the other is to create order. The ear has evolved mechanisms to detect both effects and encodes the fine temporal detail of a stimulus in sequences of auditory nerve discharges. Taking inspiration from these ideas, this thesis investigates the use of regular timing for sonar signal detection. Algorithms that operate on the temporal structure of a received signal are developed for the detection of merchant vessels. These ideas are explored by reappraising three areas traditionally associated with power-based detection. First of all, a time-frequency display based on timing instead of power is developed. Rather than inquiring of the display, "How much energy has been measured at this frequency? ", one would ask, "How structured is the signal at this frequency? Is this consistent with a target? " The auditory-motivated zero crossings with peak amplitudes (ZCPA) algorithm forms the starting-point for this study. Next, matters related to quantitative system performance analysis are addressed, such as how often a system will fail to detect a signal in particular conditions, or how much energy is required to guarantee a certain probability of detection. A suite of optimal temporal receivers is designed and is subsequently evaluated using the same kinds of synthetic signal used to assess power-based systems: Gaussian processes and sinusoids. The final area of work considers how discrete components on a sonar signal display, such as tonals and transients, can be identified and organised according to auditory scene analysis principles. Two algorithms are presented and evaluated using synthetic signals: one is designed to track a tonal through transient events, and the other attempts to identify groups of comodulated tonals against a noise background. A demonstration of each algorithm is provided for recorded sonar signals.
| Identifer | oai:union.ndltd.org:bl.uk/oai:ethos.bl.uk:555508 |
| Date | January 2008 |
| Creators | Mill, Robert William |
| Publisher | University of Sheffield |
| Source Sets | Ethos UK |
| Detected Language | English |
| Type | Electronic Thesis or Dissertation |
| Source | http://etheses.whiterose.ac.uk/12827/ |
Page generated in 0.0025 seconds