Adam Livingston, Ph.D.

Ph.D.

Computer Engineering

Old Dominion University

2012

M.S.

Computer Engineering

Old Dominion University

2006

B.S.

Computer Engineering

Old Dominion University

2004

Outstanding Masters Research Award, ODU ECE Department

2006

Faculty Award, ODU ECE Department

2004

Design of a real time system for nonlinear enhancement of video streams by an integrated neighborhood dependent approach

IEEE Computer Society Proceedings of the International Symposium on VLSI, ISVLSI 2005  Tampa, Florida, May 11 -12, 2005

A visibility improvement system for low vision drivers by nonlinear enhancement of fused visible and infrared video

IEEE 1st Workshop on Computer Vision Applications for the Visually Impaired  San Diego, CA, June 20 -25, 2005

An efficient VLSI architecture for 2-D convolution with quadrant symmetric kernels

IEEE Computer Society Proceedings of the International Symposium on VLSI, ISVLSI 2005  Tampa, Florida, May 11 - 12, 2005

Operating Systems

I teach courses in the use of general purpose OSs and real-time embedded OSs.

Computer Architecture

I teach courses in digital logic and computer architecture, building up the assembly language and ARM processor design.

Embedded Systems

I teach courses in both introductory and advanced embedded systems topics.

A high performance architecture for implementation of 2-D convolution with quadrant symmetric kernels

Zhang, M.Z., Ngo, H.T., Livingston, A.R., Asari, V.K.

2008

The design of a high performance digital architecture for computing 2-D convolution, utilizing the quadrant symmetry of the kernels, is proposed in this paper. Pixels in the four quadrants of the kernel region, with respect to an image pixel, are considered simultaneously for computing the partial products of the convolution sum. A novel data handling strategy, to identify pixels to be fed to different processing elements, helps reduce the data storage requirements significantly in the circuitry. The systolic architecture employs parallel and pipelined processing and is able to produce one output every clock cycle. The new design resulted in, approximately, a 75% reduction in number of multipliers and a 50% reduction in the number of adders, when compared to the conventional systolic architecture. The proposed architecture design is capable of performing convolution operations for 57 1,024 × 1,024 frames, or 59.77 million outputs per second, in a Xilinx's Virtex 2v2000ff896-4 FPGA at maximum clock frequency of 59.77 MHz. The error analysis performed in two image processing applications, namely noise filtering and edge detection, shows that the hardware implementation with the proposed design provides results similar to that of the software implementation.

View more

A real-time emotion detection system for human computer interaction: A binary decision tree approach

Seow, M.J., Asari, V.K., Livingston, A.

2010

A method to embed N dimensional, multi-valued patterns into an auto-associative memory represented as a nonlinear line of attraction in a fully connected recurrent neural network is presented in this paper. The curvature of the nonlinear attractor is defined by the Kth degree polynomial line which best fits the training data in N dimensional state space. The width of the nonlinear line is then characterized by the statistical characteristics of the training patterns. Stability of the recurrent network is verified by analyzing the trajectory of the points in the state space during convergence. The performance of the network is benchmarked through the reconstruction of original gray-scale images from their corrupted versions. It is observed that the proposed method can quickly and successfully reconstruct each image with an average convergence rate of 3.10 iterations.

View more

Learning as a nonlinear line of attraction in a recurrent neural network

Seow, M.J., Asari, V.K., Livingston, A.

2010

A method to embed N dimensional, multi-valued patterns into an auto-associative memory represented as a nonlinear line of attraction in a fully connected recurrent neural network is presented in this paper. The curvature of the nonlinear attractor is defined by the Kth degree polynomial line which best fits the training data in N dimensional state space. The width of the nonlinear line is then characterized by the statistical characteristics of the training patterns. Stability of the recurrent network is verified by analyzing the trajectory of the points in the state space during convergence. The performance of the network is benchmarked through the reconstruction of original gray-scale images from their corrupted versions. It is observed that the proposed method can quickly and successfully reconstruct each image with an average convergence rate of 3.10 iterations.

View more