Open Access. Powered by Scholars. Published by Universities.®
- Institution
-
- TÜBİTAK (60)
- Universitas Indonesia (7)
- Cleveland State University (3)
- Marquette University (3)
- University of Nebraska - Lincoln (2)
-
- University of Nevada, Las Vegas (2)
- University of New Mexico (2)
- Air Force Institute of Technology (1)
- Edith Cowan University (1)
- Georgia Southern University (1)
- Syracuse University (1)
- University of Arkansas, Fayetteville (1)
- University of Kentucky (1)
- University of Mississippi (1)
- University of South Carolina (1)
- University of Texas at Arlington (1)
- University of Texas at El Paso (1)
- Utah State University (1)
- Washington University in St. Louis (1)
- West Virginia University (1)
- Western University (1)
- Publication Year
- Publication
-
- Turkish Journal of Electrical Engineering and Computer Sciences (60)
- Makara Journal of Technology (7)
- Electrical and Computer Engineering Faculty Publications (3)
- Electrical and Computer Engineering Faculty Research and Publications (3)
- Department of Electrical and Computer Engineering: Faculty Publications (2)
-
- Electrical & Computer Engineering Faculty Research (2)
- Electrical and Computer Engineering ETDs (2)
- All Graduate Theses and Dissertations, Spring 1920 to Summer 2023 (1)
- Computer Science and Engineering Theses (1)
- Dissertations - ALL (1)
- Electrical and Computer Engineering Publications (1)
- Graduate Theses and Dissertations (1)
- Graduate Theses, Dissertations, and Problem Reports (1)
- Honors Theses (1)
- McKelvey School of Engineering Theses & Dissertations (1)
- Open Access Theses & Dissertations (1)
- Phi Kappa Phi Research Symposium (2012-2016) (1)
- Publications (1)
- Research outputs 2014 to 2021 (1)
- Theses and Dissertations (1)
- Theses and Dissertations--Electrical and Computer Engineering (1)
- Publication Type
Articles 91 - 93 of 93
Full-Text Articles in Computer Engineering
Training Radial Basis Neural Networks With The Extended Kalman Filter, Daniel J. Simon
Training Radial Basis Neural Networks With The Extended Kalman Filter, Daniel J. Simon
Electrical and Computer Engineering Faculty Publications
Radial basis function (RBF) neural networks provide attractive possibilities for solving signal processing and pattern classification problems. Several algorithms have been proposed for choosing the RBF prototypes and training the network. The selection of the RBF prototypes and the network weights can be viewed as a system identification problem. As such, this paper proposes the use of the extended Kalman filter for the learning procedure. After the user chooses how many prototypes to include in the network, the Kalman filter simultaneously solves for the prototype vectors and the weight matrix. A decoupled extended Kalman filter is then proposed in order …
A Comparative Analysis Of Networks Of Workstations And Massively Parallel Processors For Signal Processing, David C. Gindhart
A Comparative Analysis Of Networks Of Workstations And Massively Parallel Processors For Signal Processing, David C. Gindhart
Theses and Dissertations
The traditional approach to parallel processing has been to use Massively Parallel Processors (MPPs). An alternative design is commercial-off-the-shelf (COTS) workstations connected to high-speed networks. These networks of workstations (NOWs) typically have faster processors, heterogeneous environments, and most importantly, offer a lower per node cost. This thesis compares the performance of MPPs and NOWs for the two-dimensional fast Fourier transform (2-D FFT). Three original, high-performance, portable 2-D FFTs have been implemented: the vector-radix, row-column and pipeline. The performance of these algorithms was measured on the Intel Paragon, IBM SP2 and the AFIT NOW, which consists of 6 Sun Ultra workstations …
The Application Of Neural Networks To Optimal Robot Trajectory Planning, Daniel J. Simon
The Application Of Neural Networks To Optimal Robot Trajectory Planning, Daniel J. Simon
Electrical and Computer Engineering Faculty Publications
Interpolation of minimum jerk robot joint trajectories through an arbitrary number of knots is realized using a hardwired neural network. Minimum jerk joint trajectories are desirable for their similarity to human joint movements and their amenability to accurate tracking. The resultant trajectories are numerical rather than analytic functions of time. This application formulates the interpolation problem as a constrained quadratic minimization problem over a continuous joint angle domain and a discrete time domain. Time is discretized according to the robot controller rate. The neuron outputs define the joint angles (one neuron for each discrete value of time) and the Lagrange …