2DPCA versus PCA for face recognition

Dimensionality reduction methods play an important role in face recognition. Principal component analysis(PCA) and two-dimensional principal component analysis(2DPCA) are two kinds of important methods in this field. Recent research seems like that 2DPCA method is superior to PCA method. To prove if this conclusion is always true, a comprehensive comparison study between PCA and 2DPCA methods was carried out. A novel concept, called column-image difference(CID), was proposed to analyze the difference between PCA and 2DPCA methods in theory. It is found that there exist some restrictive conditions when2 DPCA outperforms PCA. After theoretical analysis, the experiments were conducted on four famous face image databases. The experiment results confirm the validity of theoretical claim.

A QoS-aware vertical handoff algorithm based on predictive network information

In converged heterogeneous wireless networks, vertical handoff is an important issue in radio resource management and occurs when an end user switches from one network to another (e.g., from wireless local area network to wideband code division multiple access). Efficient vertical handoff should allocate network resources efficiently and maintain good quality of service (QoS) for the end users. The objective of this work is to determine conditions under which vertical handoff can be performed. The channel usage situation of each access network is formulated as a birth-death process with the objective of predicting the available bandwidth and the blocking probability. A reward function is used to capture the network bandwidth and the blocking probability is expressed as a cost function. An end user will access the certain network which maximizes the total function defined as the combination of the reward function and the cost function. Simulation results show that the proposed algorithm can significantly improve the network performance, including higher bandwidth for end users and lower new call blocking and handoff call blocking probability for networks.

Contrast enhancement of medical ultrasound imaging with reversal phase-inversion pulse technology

A new ultrasound contrast imaging technique was proposed for eliminating the harmonic components from the emission signal transmitted by the broadband ultrasonic system.Reversal phase-inversion pulse was used for the first time to separate the contrast harmonics from the harmonics in the emission signal to improve the detection of contrast micro-bubbles.Based on the nonlinear acoustic theory of finite-amplitude effects and the associated distortion of the propagating wave,the Bessel-Fubini series model was applied to describe the nonlinear propagation effects of the reversal phase-inversion pulse,and the Church's equation for zero-thickness encapsulation model was used to produce the scattering-pulse of the bubble.For harmonic imaging,the experiment was performed using a 64-element linear array,which was simulated by Field II.The results show that the harmonic components from the emission signal can be completely cancelled,and the harmonics generated by the nonlinear propagation of the wave through the tissue,can be reduced by 15-30 dB.Compared with the short pulse,the reversal phase-inversion pulse can improve the contrast and definition of the harmonic image significantly.