The accuracy of data classification methods depends considerably on the data representation and on the selected features. In this work, the elastic net model selection is used to identify meaningful and important features in face recognition. Modelling the characteristics which distinguish one person from another using only subsets of features will both decrease the computational cost and incre...

Controlled deployments of sensor networks are feasible when positions of individual nodes can be altered. We study how position control can be leveraged for obtaining desired levels of coverage and connectivity. We arrive at a topology construction mechanism based on purely local and geometric conditions that can guarantee certain global network properties. The construction requires each node t...

Two approaches were explored which integrate neural net classifiers with Hidden Markov Model (HMM) speech recognizers. Both attempt to improve speech pattern discrimination while retaining the temporal processing advantages of HMMs. One approach used neural nets to provide second-stage discrimination following an HMM recognizer. On a small vocabulary task, Radial Basis Function (RBF) and back-p...

Any constructive continuous function must have a gradually varied approximation in compact space. However, the refinement of domain for σ−-net might be very small. Keeping the original discretization (square or triangulation), can we get some interesting properties related to gradual variation? In this note, we try to prove that many harmonic functions are gradually varied or near gradually var...

This research study proposes a novel method of inter-related problems in face recognition using the NeuCube neuromorphic computational platform. We investigated age classification and gender recognition. The well-known FG-NET and MORPH Album 2 image gallery were used and anthropometric features were extracted from landmark points on the face. The landmarks were pre-processed with the procrustes...

This paper describes the initial design and implementation of a cross-layer communications substrate for tactical networks. Traditional crosslayer strategies for MANETs often rely on the direct interaction between neighbor layers in the communications stack. We propose a different approach, where all lower layers (PHY, MAC and NET) directly interact with the overlying applications (or communica...

In this work, one and two-dimensional lattices are studied theoretically by a statistical mechanical approach. The nearest and next-nearest neighbor interactions are both taken into account, and the approximate thermodynamic properties of the lattices are calculated. The results of our calculations show that: (1) even though the next-nearest neighbor interaction may have an insignificant ef...