Search

An unsupervised single channel audio separation method from pattern recognition viewpoint is presented. The proposed method does not require training knowledge and the separation system is based on non-uniform time-frequency (TF) analysis and feature extraction. Unlike conventional research that concentrates on the use of spectrogram or its variants, the proposed separation algorithm uses an alternative TF representation based on the gammatone filterbank. In particular, the monaural mixed audio signal is shown to be considerably more separable in this non-uniform TF domain. The analysis of signal separability to verify this finding is provided. In addition, a variational Bayesian approach is derived to learn the sparsity parameters for optimizing the matrix factorization. Experimental tests have been conducted, which show that the extraction of the spectral dictionary and temporal codes is more efficient using sparsity learning and subsequently leads to better separation performance. [ABSTRACT FROM AUTHOR]

Background: COX-2 is overexpressed in some cancers, including prostate cancer; however, little is known about the effect of COX-2 overexpression on outcome in radiation-treated patients with prostate cancer. We aimed to study COX-2 overexpression and outcome in a well-defined cohort of men who received treatment with short-term androgen deprivation (STAD) plus radiotherapy or long-term androgen deprivation (LTAD) plus radiotherapy.Methods: Men with prostate cancer who had participated in the Radiation Therapy Oncology Group (RTOG) 92-02 trial and for whom sufficient diagnostic tissue was available for immunohistochemical staining and image analysis of COX-2 expression were enrolled in this study. Patients in the 92-02 trial had been randomly assigned to treatment with STAD plus radiotherapy or LTAD plus radiotherapy. Multivariate analyses by Cox proportional hazards models were done to assess whether associations existed between COX-2 staining intensity and the RTOG 92-02 primary endpoints of biochemical failure (assessed by the American Society for Therapeutic Radiology and Oncology [ASTRO] and Phoenix criteria), local failure, distant metastasis, cause-specific mortality, overall mortality, and any failure.Findings: 586 patients with sufficient diagnostic tissue for immunohistochemical staining and image analysis of COX-2 expression were included in this study. In the multivariate analyses, the intensity of COX-2 staining as a continuous covariate was an independent predictor of distant metastasis (hazard ratio [HR] 1.181 [95% CI 1.077-1.295], p=0.0004); biochemical failure by two definitions (ASTRO HR 1.073 [1.018-1.131], p=0.008; Phoenix HR 1.073 [1.014-1.134], p=0.014); and any failure (HR 1.068 [1.015-1.124], p=0.011). The higher the expression of COX-2, the greater the chance of failure. As a dichotomous covariate, COX-2 overexpression seemed to be most discriminating of outcome for those who received STAD compared with those who received LTAD.Interpretation: To our knowledge, this is the first study to establish an association of COX-2 expression with outcome in patients with prostate cancer who have had radiotherapy. Increasing COX-2 expression was significantly associated with biochemical failure, distant metastasis, and any failure. COX-2 inhibitors might improve patient response to radiotherapy in those treated with or without androgen deprivation. Our findings suggest that LTAD might overcome the effects of COX-2 overexpression. Therefore, COX-2 expression might be useful in selecting patients who need LTAD. [ABSTRACT FROM AUTHOR]

A new learning algorithm is proposed to solve the separation problem of the blind nonlinear underdetermined mixtures. The mixing system is characterised by the post-nonlinear structure and concurrently the number of sensors is less than the number of sources. The proposed algorithm utilises the generalised Gaussian distribution to model the prior probability distribution of the source signals and the mixing variables. A novel iterative technique based on alternate optimisation within the Bayesian framework has been developed for estimating the source signals, mixing matrix and the nonlinear distortion. It is shown that through formal Bayesian derivation, the update of the mixing matrix can be decomposed into two separate constituents given by linear and nonlinear parts. Furthermore, the post-nonlinear distortion functions in the mixing model are approximated by a set of polynomials and the coefficients are found by solving a least square error problem. Simulations have been carried out to verify the effectiveness in separating signals under nonlinear and underdetermined conditions. An average margin of 130% improvement has been obtained when compared with the existing linear algorithm. [ABSTRACT FROM AUTHOR]

This paper proposes a new nonlinear blind source separation algorithm with hybridisation of fuzzy logic based learning rate control and simulated annealing to improve the global solution search. Benefits of fuzzy systems and simulated annealing are incorporated into a multilayer perceptron network. Fuzzy logic control allows adjustments of learning rate to enhance the rate of convergence of the algorithm. Simulated annealing is implemented to avoid the algorithm becoming trapped in local minima. A simple and computationally efficient method for controlling learning rate and ensuring a global solution is proposed. The performance of the proposed algorithm in terms of convergence of entropy, is studied alongside other techniques of learning rate adaptation. Simulations show that the proposed nonlinear algorithm outperforms other existing nonlinear algorithms based on fixed learning rates. [ABSTRACT FROM AUTHOR]

Presents an abstract of the study 'The relationship between deep hypothermic circulatory arrest, pump prime and serum lactate levels in young infants undergoing complex cardiac surgery.' Presentation at the 2001 conference of the Association of Paediatric Anaesthetists of Great Britain and Ireland.