Biomimetic pattern recognition for speaker-independent speech recognition

In speaker-independent speech recognition, the disadvantage of the most diffused technology ( Hidden Markov Models) is not only the need of many more training samples, but also long train time requirement. This paper describes the use of Biomimetic Pattern Recognition (BPR) in recognizing some Mandarin Speech in a speaker-independent manner. The vocabulary of the system consists of 15 Chinese dish's names. Neural networks based on Multi-Weight Neuron (MWN) model are used to train and recognize the speech sounds. Experimental results are presented to show that the system, which can carry out real time recognition of the persons from different provinces speaking common Chinese speech, outperforms HMMs especially in the cases of samples of a finite size.

Continuous speech recognition based on ICA and geometrical learning

We investigate the use of independent component analysis (ICA) for speech feature extraction in digits speech recognition systems. We observe that this may be true for recognition tasks based on Geometrical Learning with little training data. In contrast to image processing, phase information is not essential for digits speech recognition. We therefore propose a new scheme that shows how the phase sensitivity can be removed by using an analytical description of the ICA-adapted basis functions. Furthermore, since the basis functions are not shift invariant, we extend the method to include a frequency-based ICA stage that removes redundant time shift information. The digits speech recognition results show promising accuracy. Experiments show that the method based on ICA and Geometrical Learning outperforms HMM in a different number of training samples.

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.

crossmodal error correction of continuous handwriting recognition by speech

In recognition-based user interface, users’ satisfaction is determined not only by recognition accuracy but also by effort to correct recognition errors. In this paper, we introduce a crossmodal error correction technique, which allows users to correct errors of Chinese handwriting recognition by speech. The focus of the paper is a multimodal fusion algorithm supporting the crossmodal error correction. By fusing handwriting and speech recognition, the algorithm can correct errors in both character extraction and recognition of handwriting. The experimental result indicates that the algorithm is effective and efficient. Moreover, the evaluation also shows the correction technique can help users to correct errors in handwriting recognition more efficiently than the other two error correction techniques.

Laser irradiation cell photothermal therapy assisted by gold nanoparticles

The strong absorption of gold nanoparticles in the visible spectral range allows the localized generation of heat in a volume of only a few tens of nanometer. The efficient conversion of strongly absorbed light by plasmonic gold nanoparticles to heat energy and their easy bioconjugation suggest that the gold nanoparticles can be used as selective photothermal agents in molecular cell targeting. The selective destruction of alkaline phosphatase, the permeabilization of the cell membrane and the selective killing of cells by laser irradiating gold nanoparticles were demonstrated. The potential of using this selective technique in molecularly targeted photothermal therapy and transfection is discussed.

Design of slow extraction system for therapy synchrotron

Based on the optimized design of the lattice for therapy synchrotron and considering the requirement of radiation therapy, the third order resonant extraction is adopted. Using the momentum-amplitude selection method, the extraction system is designed and optimized. An extraction efficiency of more than 97% and a momentum spread less than 0.11% are obtained.

Progresses of heavy-ion cancer therapy

The status of heavy-ion cancer therapy has been reviewed. The existing and constructing heavy-ion beam facilities for cancer therapy in the world are introduced. The first clinical trials of superficially placed tumor therapy at heavy ion research facility in Lanzhou (HIRFL) are presented.

Rotating wheel filter design and optimization for a uniform depth dose distribution in heavy ion therapy

Treatment planning of heavy-ion radiotherapy involves predictive calculation of not only the physical dose but also the biological dose in a patient body. The goal in designing beam-modulating devices for heavy ion therapy is to achieve uniform biological effects across the spread-out Bragg peak (SOBP). To achieve this, a mathematical model of Bragg peak movement is presented. The parameters of this model have been resolved with Monte Carlo method. And a rotating wheel filter is designed basing on the velocity of the Bragg peak movement.

Injection system design for a hadron therapy synchrotron

A synchrotron is designed for tumour therapy with C6+ ions or proton. Its injector is a cyclotron, which delivers C5+ or H-2(+) ions to the synchrotron. After comparing the methods of the single-turn injection, the multi-turn injection and the stripping injection, this paper chooses the stripping injection method. In addition, the concept design of the injection system is presented, in which the synchrotron lattice is optimized.

Design of synchrotron for hadron therapy

According to the operation and development of radiation therapy in the world, in order to further promote the radiation therapy of tumour in China, a design of a special synchrotron with two super-periodicity for hadron therapy is presented, including lattice, injection system, RF acceleration and slow extraction of the third order resonance. The synchrotron accelerates the proton beam to 250MeV and the carbon beam to 4000MeV/u.

Heavy-ion conformal irradiation in the shallow-seated tumor therapy terminal at HIRFL

Basic research related to heavy-ion cancer therapy has been done at the Institute of Modern Physics (IMP), Chinese Academy of Sciences since 1995. Now a plan of clinical trial with heavy ions has been launched at IMP. First, superficially placed tumor treatment with heavy ions is expected in the therapy terminal at the Heavy Ion Research Facility in Lanzhou (HIRFL), where carbon ion beams with energy up to 100 MeV/u can be supplied. The shallow-seated tumor therapy terminal at HIRFL is equipped with a passive beam delivery system including two orthogonal dipole magnets, which continuously scan pencil beams laterally and generate a broad and uniform irradiation field, a motor-driven energy degrader and a multi-leaf collimator. Two different types of range modulator, ripple filter and ridge filter with which Guassian-shaped physical dose and uniform biological effective dose Bragg peaks can be shaped for therapeutic ion beams respectively, have been designed and manufactured. Therefore, two-dimensional and three-dimensional conformal irradiations to tumors can be performed with the passive beam delivery system at the earlier therapy terminal. Both the conformal irradiation methods have been verified experimentally and carbon-ion conformal irradiations to patients with superficially placed tumors have been carried out at HIRFL since November 2006.