Biomedical subjects

Bailing Zhang

Publications and source records attributed to Bailing Zhang.

4 recordsLinked to original sources

PubMed2005

Gabor wavelet associative memory for face recognition.

This letter describes a high-performance face recognition system by combining two recently proposed neural network models, namely Gabor wavelet network (GWN) and kernel associative memory (KAM), into a unified structure called Gabor wavelet associative memory (GWAM). GWAM has superior representation capability inherited from GWN and consequently demonstrates a much better recognition performance than KAM. Extensive experiments have been conducted to evaluate a GWAM-based recognition scheme using three popular face databases, i.e., FERET database, Olivetti-Oracle Research Lab (ORL) database and AR face database. The experimental results consistently show our scheme's superiority and demonstrate its very high-performance comparing favorably to some recent face recognition methods, achieving 99.3% and 100% accuracy, respectively, on the former two databases, exhibiting very robust performance on the last database against varying illumination conditions.

Algorithms↗

PubMed2005

A kernel autoassociator approach to pattern classification.

Autoassociators are a special type of neural networks which, by learning to reproduce a given set of patterns, grasp the underlying concept that is useful for pattern classification. In this paper, we present a novel nonlinear model referred to as kernel autoassociators based on kernel methods. While conventional non-linear autoassociation models emphasize searching for the non-linear representations of input patterns, a kernel autoassociator takes a kernel feature space as the nonlinear manifold, and places emphasis on the reconstruction of input patterns from the kernel feature space. Two methods are proposed to address the reconstruction problem, using linear and multivariate polynomial functions, respectively. We apply the proposed model to novelty detection with or without novelty examples and study it on the promoter detection and sonar target recognition problems. We also apply the model to mclass classification problems including wine recognition, glass recognition, handwritten digit recognition, and face recognition. The experimental results show that, compared with conventional autoassociators and other recognition systems, kernel autoassociators can provide better or comparable performance for concept learning and recognition in various domains.

Algorithms↗

PubMed2004

Detection of genomic polymorphisms associated with venous thrombosis using the invader biplex assay.

A multi-site study to assess the accuracy and performance of the biplex Invader assay for genotyping five polymorphisms implicated in venous thrombosis was carried out in seven laboratories. Genotyping results obtained using the Invader biplex assay were compared to those obtained from a reference method, either allele-specific polymerase chain reaction (AS-PCR), restriction fragment length polymorphism (PCR-RFLP) or PCR-mass spectrometry. Results were compared for five loci associated with venous thrombosis: Factor V Leiden, Factor II (prothrombin) G20210A, methylenetetrahydrofolate reductase (MTHFR) C677T and A1298C, and plasminogen activator inhibitor (PAI-1) 4G/5G. Of a total of 1448 genotypes tested in this study, there were 22 samples that gave different results between the Invader biplex assay and the PCR-based methods. On further testing, 21 were determined to be correctly genotyped by the Invader Assay and only a single discrepancy was resolved in favor of the PCR-based assays. The compiled results demonstrate that the Invader biplex assay provides results more than 99.9% concordant with standard PCR-based techniques and is a rapid and highly accurate alternative to target amplification-based methods.

DNA↗

PubMed2004

DNA-based carrier screening in the Ashkenazi Jewish population.

Several relatively rare genetic diseases are found at greater frequencies in Ashkenazi Jewish populations. Most of these conditions are untreatable and shorten life expectancy. Genetic screening using molecular detection of a few common mutations for each of these diseases facilitates their prevention by identification of carrier couples. Conversely, couples with negative results are reassured by reduced carrier risks. Using a standardized format, a brief overview for each of the nine genetic diseases is presented. Known mutations, a short clinical summary, clinical and laboratory diagnostic methods and information on supportive treatments is provided for each. Finally, a brief discussion of available DNA testing technologies and a review of platforms for expanded testing options for Ashkenazi Jewish diseases under development are presented.

DNA Mutational Analysis↗