Learn More
In this paper, adaptive learning algorithms to obtain better generalization performance are proposed. We speci"cally designed cost terms for the additional functionality based on the "rst-and second-order derivatives of neural activation at hidden layers. In the course of training, these additional cost functions penalize the input-to-output mapping(More)
Previously, we reported that Lactobacillus gasseri BNR17 (BNR17), a probiotic strain isolated from human breast milk, inhibited increases in body weight and adipocyte tissue weight in high-sucrose diet-fed Sprague-Dawley (SD) rats and reduced glucose levels in type 2 diabetes mice. In the current study, we conducted further experiments to extend these(More)
In a search for novel target genes related to Parkinson's disease (PD), two full-length cDNA libraries were constructed from a human normal substantia nigra (SN) and a PD patient's SN. An analysis of the gene expression profiles between them was done using the expressed sequence tags (ESTs) frequency. Data for the differently expressed genes were verified(More)
BACKGROUND Parkinson's disease (PD) is one of the most common neurodegenerative disorders, clinically characterized by impaired motor function. Since the etiology of PD is diverse and complex, many researchers have created PD-related research resources. However, resources for brain and PD studies are still lacking. Therefore, we have constructed a database(More)
We present a dual-channel noise reduction method for small mobile devices. Our method incorporates phase difference between channels into the conventional MMSE spectral amplitude estimator. It is possible to suppress unwanted directional noise signals, whose incident direction is different from that of the target speech signal. Experimental results show(More)
In this paper, we present a SNR-adaptive soft mask filter for multi-channel noisy speech enhancement. Incorporating frame-by-frame spectral magnitude ratios into the time-frequency(T-F) mask filter framework, the adaptive filter can be designed robust to changing environments. Experimental results show that the proposed adaptive mask filter can effectively(More)
We present a novel noise power estimation method based on smoothed spectral minima tracking and subtractive blocking matrix for dual-channel speech enhancement. By combining spectral characteristics of the noisy mixture signals with spatial null beam-forming, noise over- and under-estimation problem can be substantially mitigated. The proposed noise(More)
We present a semi-blind non-negative matrix factorization(NMF) approach to suppress interference noise signals from a single channel mixture signal. By enforcing a disjointness constraint into the NMF error criterion under the semi-blind denoising framework, it is possible to decompose the mixture spectrogram into target and noise components by minimizing(More)
Congenital afibrinogenemia/hypofibrinogenemia is a rare inherited hematologic disorder in which a patient lacks or has insufficient level of fibrinogen, the blood coagulation factor I. The incidence of this uncommon disease is 1 to 2 per 1 million individuals. Hence, massive hemoperitoneum caused by ovulation in a woman with congenital afibrogenemia is also(More)