Continuous speech research based on HyperSausage Neuron

In this paper, we presents HyperSausage Neuron based on the High-Dimension Space(HDS), and proposes a new algorithm for speaker independent continuous digit speech recognition. At last, compared to HMM-based method, the recognition rate of HyperSausage Neuron method is higher than that of in HMM-based method.

Continuous speech research based on HyperSausage Neuron

In this paper, we presents HyperSausage Neuron based on the High-Dimension Space(HDS), and proposes a new algorithm for speaker independent continuous digit speech recognition. At last, compared to HMM-based method, the recognition rate of HyperSausage Neuron method is higher than that of in HMM-based method.

Image Ratio Features for Facial Expression Recognition Application

Video-based facial expression recognition is a challenging problem in computer vision and human-computer interaction. To target this problem, texture features have been extracted and widely used, because they can capture image intensity changes raised by skin deformation. However, existing texture features encounter problems with albedo and lighting variations. To solve both problems, we propose a new texture feature called image ratio features. Compared with previously proposed texture features, e. g., high gradient component features, image ratio features are more robust to albedo and lighting variations. In addition, to further improve facial expression recognition accuracy based on image ratio features, we combine image ratio features with facial animation parameters (FAPs), which describe the geometric motions of facial feature points. The performance evaluation is based on the Carnegie Mellon University Cohn-Kanade database, our own database, and the Japanese Female Facial Expression database. Experimental results show that the proposed image ratio feature is more robust to albedo and lighting variations, and the combination of image ratio features and FAPs outperforms each feature alone. In addition, we study asymmetric facial expressions based on our own facial expression database and demonstrate the superior performance of our combined expression recognition system.

Sensitive detection of protein by an aptamer-based label-free fluorescing molecular switch

We report an aptamer-based method for the sensitive detection of proteins by a label-free fluorescing molecular switch (ethidium bromide), which shows promising potential in making protein assay simple and economical.

ZnO-based hollow microspheres: Biopolymer-assisted assemblies from ZnO nanorods

Many efforts have been made in fabricating three-dimensional (3D) ordered zinc oxide (ZnO) nanostructures due to their growing applications in separations, sensors, catalysis, bioscience, and photonics. Here, we developed a new synthetic route to 3D ZnO-based hollow microspheres by a facile solution-based method through a water-soluble biopolymer (sodium alginate) assisted assembly from ZnO nanorods. The products were characterized by X-ray diffraction, field emission scanning electron microscopy, transmission electron microscopy, selected area electron diffraction, and X-ray photoelectron spectroscopy. Raman and photoluminescence spectra of the ZnO-based hollow microspheres were obtained at room temperature to investigate their optical properties. The hollow microspheres exhibit exciting emission features with a wide band covering nearly all the visible region. The calculated CIE (Commission Internationale d'Eclairage) coordinates are 0.24 and 0.31, which fall at the edge of the white region (the 1931 CIE diagram). A possible growth mechanism of the 3D ZnO superstructures based on typical biopolymer-crystal interactions in aqueous solution is tentatively proposed, which might be really interesting because of the participation of the biopolymer.

Aggregation-based fabrication and assembly of roughened composite metallic nanoshells: Application in surface-enhanced Raman scattering

This paper reports an aggregation-based method for the fabrication of composite Au/Ag nanoshells with tunable thickness and surface roughness. It is found that the resultant roughened composite Au/Ag nanoshells can attract each other spontaneously to form films at the air-water interface. Importantly, such films can be transferred onto the solid substrates without being destroyed and show excellent surface-enhanced Raman scattering (SERS) enhancement ability. Their strong enhancement ability may stem from the unique two-dimensional structure itself.

改进的基于区域的运动目标分割方法

针对视频监控系统,提出了一种改进的基于区域的运动目标分割方法。与传统方法相比,在运动检测阶段,结合时域差分和背景差分进行运动检测,并通过自适应方法进行背景更新;在差分图像二值化时,采用自适应阈值方法来代替传统的手工确定阈值法;对于区域分割,使用基于加权平方欧式距离的均值聚类算法代替传统的均值聚类算法。实验结果表明该改进方法比传统方法具有更好的实时性、鲁棒性和有效性。

一种基于视觉的水下机器人动力定位方法

以7 000 m载人潜水器的工程需求为背景,以水下单目摄像机为视觉传感器,进行了水下机器人动力定位方法研究。该动力定位方法利用视觉系统测量得到水下机器人与被观察目标之间的三维位姿关系,通过路径规划、位置控制和姿态控制分解,逐步使机器人由初始位姿逼近期望位姿并最终定位于期望位姿,从而实现了机器人的4自由度动力定位。通过水池实验验证了提出的动力定位方法,并且机器人能够抵抗恒定水流干扰和人工位置扰动。同时,该动力定位方法还可以实现机器人对被观察目标的自动跟踪。

Color Region Grouping and Shape Recognition with Deformable Models

A new deformable shape-based method for color region segmentation is described. The method includes two stages: over-segmentation using a traditional color region segmentation algorithm, followed by deformable model-based region merging via grouping and hypothesis selection. During the second stage, region merging and object identification are executed simultaneously. A statistical shape model is used to estimate the likelihood of region groupings and model hypotheses. The prior distribution on deformation parameters is precomputed using principal component analysis over a training set of region groupings. Once trained, the system autonomously segments deformed shapes from the background, while not merging them with similarly colored adjacent objects. Furthermore, the recovered parametric shape model can be used directly in object recognition and comparison. Experiments in segmentation and image retrieval are reported.

Numerical simulation of the charge balance in an EBIT

The electron beam ions traps (EBITs) are widely used to study highly charged ions (HCIs). In an EBIT, a high energy electron beam collides with atoms and ions to generate HCIs in the trap region. It is important to study the physics in the trap. The atomic processes, such as electron impact ionisation (EI), radiative recombination (RR), dielectronic recombination (DR) and charge exchange (CX), occur in the trap and numerical simulation can give some parameters for design, predict the composition and describe charge state evolution in an EBIT [Phys. Rev. A 43 (199 1) 4861]. We are presently developing a new code, which additionally includes a description of the overlaps between the ion clouds of the various charge-states. It has been written so that it can simulate experiments where various machine parameters (e.g. beam energy and current) can vary throughout the simulation and will be able to use cross- sections either based on scaling laws or derived from atomic structure calculations. An object-oriented method is used in developing the new software, which is an efficient way to organize and write code. (C) 2003 Elsevier Science B.V. All rights reserved.

HOS-Based Semi-Blind Spatial Equalization for MIMO Rayleigh Fading Channels

In this paper we concentrate on the direct semi-blind spatial equalizer design for MIMO systems with Rayleigh fading channels. Our aim is to develop an algorithm which can outperform the classical training based method with the same training information used, and avoid the problems of low convergence speed and local minima due to pure blind methods. A general semi-blind cost function is first constructed which incorporates both the training information from the known data and some kind of higher order statistics (HOS) from the unknown sequence. Then, based on the developed cost function, we propose two semi-blind iterative and adaptive algorithms to find the desired spatial equalizer. To further improve the performance and convergence speed of the proposed adaptive method, we propose a technique to find the optimal choice of step size. Simulation results demonstrate the performance of the proposed algorithms and comparable schemes.

Design, optimisation and characterisation of polymeric microneedle arrays prepared by a novel laser-based micromoulding technique.

PURPOSE:
Design and evaluation of a novel laser-based method for micromoulding of microneedle arrays from polymeric materials under ambient conditions. The aim of this study was to optimise polymeric composition and assess the performance of microneedle devices that possess different geometries.
METHODS:
A range of microneedle geometries was engineered into silicone micromoulds, and their physicochemical features were subsequently characterised.
RESULTS:
Microneedles micromoulded from 20% w/w aqueous blends of the mucoadhesive copolymer Gantrez® AN-139 were surprisingly found to possess superior physical strength than those produced from commonly used pharma polymers. Gantrez® AN-139 microneedles, 600 µm and 900 µm in height, penetrated neonatal porcine skin with low application forces (>0.03 N per microneedle). When theophylline was loaded into 600 µm microneedles, 83% of the incorporated drug was delivered across neonatal porcine skin over 24 h. Optical coherence tomography (OCT) showed that drug-free 600 µm Gantrez® AN-139 microneedles punctured the stratum corneum barrier of human skin in vivo and extended approximately 460 µm into the skin. However, the entirety of the microneedle lengths was not inserted.
CONCLUSION:
In this study, we have shown that a novel laser engineering method can be used in micromoulding of polymeric microneedle arrays. We are currently carrying out an extensive OCT-informed study investigating the influence of microneedle array geometry on skin penetration depth, with a view to enhanced transdermal drug delivery from optimised laser-engineered Gantrez® AN-139 microneedles.

A rapid PCR-based assay for identification of cryptic Myotis spp (Myotis mystacinus, Myotis brandtii and Myotis alcathoe).

The development of a quick PCR-based method to distinguish European cryptic Myotis spp., Myotis mystacinus, Myotis brandtii and Myotis alcathoe is described. Primers were designed around species-specific single nucleotide polymorphisms (SNP’s) in the ND1 mitochondrial gene, and a pair of control primers was designed in the 12S mitochondrial gene. A multiplex of seven primer combinations produces clear species-specific bands using gel electrophoresis. Robustness of the method was tested on 33 M. mystacinus, 16 M. brandtii and 15 M. alcathoe samples from across the European range of these species. The method worked well on faecal samples collected from maternity roosts of M. mystacinus. The test is intended to aid collection of data on these species through a rapid and easy identification method with the ability to use DNA obtained from a range of sources including faecal matter.

Fast automatic two-stage nonlinear model identification based on the extreme learning machine

It is convenient and effective to solve nonlinear problems with a model that has a linear-in-the-parameters (LITP) structure. However, the nonlinear parameters (e.g. the width of Gaussian function) of each model term needs to be pre-determined either from expert experience or through exhaustive search. An alternative approach is to optimize them by a gradient-based technique (e.g. Newton’s method). Unfortunately, all of these methods still need a lot of computations. Recently, the extreme learning machine (ELM) has shown its advantages in terms of fast learning from data, but the sparsity of the constructed model cannot be guaranteed. This paper proposes a novel algorithm for automatic construction of a nonlinear system model based on the extreme learning machine. This is achieved by effectively integrating the ELM and leave-one-out (LOO) cross validation with our two-stage stepwise construction procedure [1]. The main objective is to improve the compactness and generalization capability of the model constructed by the ELM method. Numerical analysis shows that the proposed algorithm only involves about half of the computation of orthogonal least squares (OLS) based method. Simulation examples are included to confirm the efficacy and superiority of the proposed technique.

Robust automated tumour segmentation on histological and immunohistochemical tissue images

Tissue microarray (TMA) is a high throughput analysis tool to identify new diagnostic and prognostic markers in human cancers. However, standard automated method in tumour detection on both routine histochemical and immunohistochemistry (IHC) images is under developed. This paper presents a robust automated tumour cell segmentation model which can be applied to both routine histochemical tissue slides and IHC slides and deal with finer pixel-based segmentation in comparison with blob or area based segmentation by existing approaches. The presented technique greatly improves the process of TMA construction and plays an important role in automated IHC quantification in biomarker analysis where excluding stroma areas is critical. With the finest pixel-based evaluation (instead of area-based or object-based), the experimental results show that the proposed method is able to achieve 80% accuracy and 78% accuracy in two different types of pathological virtual slides, i.e., routine histochemical H&E and IHC images, respectively. The presented technique greatly reduces labor-intensive workloads for pathologists and highly speeds up the process of TMA construction and provides a possibility for fully automated IHC quantification.