Learn More
In this paper, a sinusoidal model has been proposed for characterization and classification of different stress classes (emotions) in a speech signal. Frequency, amplitude and phase features of the sinusoidal model are analyzed and used as input features to a stressed speech recognition system. The performances of sinusoidal model features are evaluated for(More)
A new novel wavelet-threshold based ECG signal compression method is proposed using linear phase biorthogonal 9/7 discrete wavelet transform, uniform scalar zero zone quantizer (USZZQ) and Huffman coding of the difference between two consecutive index of the significant coefficients. The compression performance of the proposed method is better compared to(More)
One of the emerging issues in telehealth care system is how effectively the limited and well established mobile technologies that are now almost globally usable are exploited. The main challenge is to develop a mobile telemedicine system to transmit biosignals directly to a specialist in an emergency medical care unit for monitoring/diagnosis using an(More)
The analysis of diagnostic features such as the optic disc(OD) provides important clues for the diagnosis of various retinopathic diseases. In this paper, a wavelet based distortion measure for the optic disc (WODDM) in retinal image is proposed. The wavelet analysis shows that different subbands carry optic disc information to a different level. The(More)
A novel and simple quality controlled ECG compression algorithm is proposed using Wavelet energy based diagnostic distortion (WEDD) measure, which localizes the error between the original and the reconstructed signals in the feature space. The compression algorithm is based on Wavelet transform, energy based thresholding and an adaptive quantization scheme.(More)
  • 1