Biometric identification is crucial to information assurance and national security. With the rapid development of artificial intelligence technologies, various approaches have been successfully applied to the biometric identification, like the neural network, fuzzy logic, principal component analysis, independent component analysis and wavelet transform (1D and 2D). A typical fingerprint image usually appears as an arbitrary picture with a unique pattern whose reoccurring data are reflected within each individual print. The 2D discrete wavelet transform can be used to digitally compress fingerprints and reconstruct original images via components of the approximation, horizontal detail, vertical detail and diagonal detail from the input image transformation. At the same time, some quantitative measures are needed in order to evaluate the quality of the wavelet transform. In this research, several measures are proposed to evaluate information flow of the 2D discrete wavelet transform. The gray level energy, discrete entropy and relative entropy are used to measure the outcomes of the biometric fingerprint identification via the 2D discrete wavelet transform.

No abstract

No abstract

No abstract

Unmanned aerial vehicle (UAV) is an autopiloted and remote-controlled vehicle sustained by the aerodynamic lift over its whole flight profile. It has many applications such as weather forecast, terrain surveying, environment surveillance, hazardous cleanup, military defense, and so on. In this paper, a simplified nonlinear equational modeling of UAV dynamics is conducted and then linearization and adaptive control approaches are designed. The objective is to apply aerodynamic theory and adaptive control theory on accurate UAV explicit modeling to enhance capabilities of UAV navigation and prediction against various severe conditions.