Learn More
—A new technique for facial expression recognition is proposed , which uses the two-dimensional (2-D) discrete cosine transform (DCT) over the entire face image as a feature detector and a constructive one-hidden-layer feedforward neural network as a facial expression classi-fier. An input-side pruning technique, proposed previously by the authors, is also(More)
In this paper, a constructive one-hidden-layer network is introduced where each hidden unit employs a polynomial function for its activation function that is different from other units. Specifically, both a structure level as well as a function level adaptation methodologies are utilized in constructing the network. The functional level adaptation scheme(More)
Oesophageal cancer is one of the most aggressive cancers and is the sixth leading cause of cancer death worldwide. Approximately 70% of global oesophageal cancer cases occur in China, with oesophageal squamous cell carcinoma (ESCC) being the histopathological form in the vast majority of cases (>90%). Currently, there are limited clinical approaches for the(More)
In this paper a new strategy for adaptively and autonomously constructing a multi-hidden-layer feedforward neural network (FNN) is introduced. The proposed scheme belongs to a class of structure level adaptation algorithms that adds both new hidden units and new hidden layers one at a time when it is determined to be needed. Using this strategy, a FNN may(More)
Noise signals generated by rotating machines such as diesel engines, cutting machines, fans, etc., may be modeled as noisy sinusoidal signals which can be successfully suppressed by narrowband active noise control (ANC) systems. In this paper, statistical performance of such a conventional filtered-x LMS (FXLMS)-based narrowband ANC system is investigated(More)
Chinese jujube (Ziziphus jujuba Mill, 2n = 2× = 24, Rhamnaceae) is an economically important Chinese native species. It has high nutritional value, and its medicinal properties have led to extensive use in traditional oriental medicine. The characterization of genotypes using molecular markers is important for genetic studies and plant breeding. However,(More)
OBJECTIVE To investigate the genetic diversity of the HIV-1 circulating in Shanghai and to analyze the mutations in the protease (PR) gene associated with resistance to protease inhibitors (PIs). DESIGN The genetic diversity of HIV-1 and PI resistance-associated mutations was studied in 40 Shanghai HIV-1-seropositive treatment-naive residents. The(More)
Regression problem is an important application area for neural networks (NNs). Among a large number of existing NN architectures, the feedforward NN (FNN) paradigm is one of the most widely used structures. Although one-hidden-layer feedforward neural networks (OHL-FNNs) have simple structures, they possess interesting representational and learning(More)
To study HIV-1 genetic diversity among HIV-positive men who have sex with men (MSM) in China, a cohort consisting of HIV-positive MSM was established in 2005 and was monitored every 2 years. In 2007, 44 HIVpositiveMSM subjects were genotyped, and the results showed HIV-1 subtype B decreased from 77.5% to41.9%, but non-B subtypes increased rapidly(More)
BACKGROUND The B', CRF07_BC and CRF01_AE are the predominant HIV-1 subtypes in China. It is essential to determine their baseline susceptibility to HIV entry inhibitors before these drugs are used in China. METHODOLOGY/PRINCIPAL FINDINGS The baseline susceptibility of 14 representative HIV-1 isolates (5 CRF07_BC, 4 CRF01_AE, and 5 B'), most of which were(More)