No abstract

This paper presents a neural network-based adaptive compensation scheme to cancel the effect of uncertain, highly complex and dynamic synthetic jet actuator nonlinearities. Approximation of a nonlinearly parameterized model of synthetic jet actuator characteristics by a linearly parameterized function is performed using neural network approximators. The nonlinearity function is approximated over a range of rotor rotational speed of a wind turbine blade. An adaptive inverse is employed for cancelling the effect of actuator nonlinearities, which is accomplished by use if another neural network. Adaptive update laws are also employed for estimation of blade physical dimensional prameters. A state feedback control law is designed to control the nonlinear wind turbine dynamics in presence of signal dependent actuator nonlinearities.

No abstract

This paper presents a classification scheme for audio signals using high-level feature descriptors. The descriptor is designed to capture the relevance of each acoustic feature group (or feature set like mel-frequency cepstral coefficients, perceptual features etc.) in recognizing an audio class. For this, a bank of RVM classifiers are modeled for each 'audio class'-'feature group' pair. The response of an input signal to this bank of RVM classifiers forms the entries of the descriptor. Each entry of the descriptor thus measures the proximity of the input signal to an audio class based on a single feature group. This form of signal representation offers twofold advantages. First, it helps to determine the effectiveness of each feature group in classifying a specific audio class. Second, the descriptor offers higher discriminability than the low-level feature groups and a simple SVM classifier trained on the descriptor produces better performance than several state-of-the-art methods.

No abstract