Engineering Commons^™

High Accuracy Distributed Target Detection And Classification In Sensor Networks Based On Mobile Agent Framework, Xiaoling Wang

Doctoral Dissertations

High-accuracy distributed information exploitation plays an important role in sensor networks. This dissertation describes a mobile-agent-based framework for target detection and classification in sensor networks. Specifically, we tackle the challenging problems of multiple- target detection, high-fidelity target classification, and unknown-target identification.

In this dissertation, we present a progressive multiple-target detection approach to estimate the number of targets sequentially and implement it using a mobile-agent framework. To further improve the performance, we present a cluster-based distributed approach where the estimated results from different clusters are fused. Experimental results show that the distributed scheme with the Bayesian fusion method have better performance …

Development Of An Fpga-Based Hardware Evaluation System For Use With Ga-Designed Artificial Neural Networks, Dennis Duncan Earl

Doctoral Dissertations

The Hardware-Evolved Digital Artificial Neural Network (HEDANN) design platform is a circuit design platform built to evolve complex architecture ANN circuits using re-configurable hardware. By using genetic algorithms to evolve complex architecture ANN designs in field programmable gate arrays, this system is the first design system to evolve physical ANN circuits with unconstrained network architectures. With the HEDANN design system, the evolution of ANNs with recursive, non-layered, complex architectural connections is made possible. In addition, the HEDANN design system is capable of evolving device-independent circuit designs that can operate properly across a wide range of operating temperatures. This system is …

Space-Time Codes Concatenated With Turbo Codes Over Fading Channels, Junghoon Suh

Doctoral Dissertations

The uses of space-time code (STC) and iterative processing have enabled robust communications over fading channels at previously unachievable signal-to-noise ratios. Maintaining desired transmission rate while improving the diversity from STC is challenging, and the performance of the STC suffers considerably due to lack of channel state information (CSI). This dissertation research addresses issues of considerable importance in the design of STC with emphasis on efficient concatenation of channel coding and STC with theoretical bound derivation of the proposed schemes, iterative space-time trellis coding (STTC), and differential space-time codes.

First, we concatenate space-time block code (STBC) with turbo code for …

Automated Exploration Of The Asic Design Space For Minimum Power-Delay-Area Product At The Register Transfer Level, Fuat Karakaya

Doctoral Dissertations

Exploring the integrated circuit design space for minimum power-delay-area (PDA) product can be time-consuming and tedious, especially when the target standard-cell library has hundreds of options. In this dissertation, heuristic algorithms that automate this process have been developed, implemented and validated at the reg- ister transfer level. In some cases, the PDA product was 1.9 times better than the initial baseline solution. The parallel search algorithm exhibited 9x speed up when executed on 10 machines simultaneously. These two new methods also characterize the design space for the given RTL code by generating power-delay-area points in addition to the minimum PDA …