In this paper, a new blind channel identification/equalization algorithm based on multiplayer feed forward neural network is proposed, and the transmission function adapted to the neural network is analyzed. the compu...
详细信息
In this paper, a new blind channel identification/equalization algorithm based on multiplayer feed forward neural network is proposed, and the transmission function adapted to the neural network is analyzed. the computer simulations show that the convergence performance of new algorithm is better than traditional feed forward neural network algorithm.
A novel method for the estimation of areas in 2D MR images of the aorta is presented. the method uses spatio-temporal non-rigid registration in order to obtain the 2D deformation fields of the vessels during the cardi...
详细信息
In this paper, we have proposed a bandwidth efficient turbo trellis-coded modulation scheme for the noncoherent multiple-antenna Rayleigh fading channel, where the channel state information (CSI) is not necessary both...
详细信息
In this paper, we have proposed a bandwidth efficient turbo trellis-coded modulation scheme for the noncoherent multiple-antenna Rayleigh fading channel, where the channel state information (CSI) is not necessary both at the transmitter and the receiver. In this scheme, we merge the unitary space-time modulation (USTM) as constellations withthe turbo trellis-coded modulation, resulting in the turbo trellis-coded USTM (TTC-USTM), withthe trellis-coded USTM encoder as the component encoders. We have also derived the iterative maximum a posteriori (MAP) algorithm. through computer simulations, we demonstrated that without bandwidth expansion, TTC-USTM produces significant coding gains over its uncoded counterparts.
In this paper, a new method for adaptive channel equalization is presented, which is called knowledge-based adaptive filter (in short, NBA). through the knowledge of known waveform is combined with adaptive filter tec...
详细信息
In this paper, a new method for adaptive channel equalization is presented, which is called knowledge-based adaptive filter (in short, NBA). through the knowledge of known waveform is combined with adaptive filter technique by this method, slowly varied adaptive channel equalization is realized. Compared to the common adaptive equalizer based on predictive deconvolution, predictive error of output waveform from the equalizer and convergent rate of the adaptive filter are improved because the knowledge of known waveform is joined to NBA (knowledge-based adaptive filter). this paper conforms the validity of NBA method by the theory and the simulative results on computer.
the conventional methods for speech endpoint detection based on some simple features such as energy and zero-crossing cannot obtain precise results. the proposed method in this paper is based on combination of Mel-sca...
详细信息
the conventional methods for speech endpoint detection based on some simple features such as energy and zero-crossing cannot obtain precise results. the proposed method in this paper is based on combination of Mel-scale features with phoneme segmentation. the experiments show that the high accurate detection can be obtained. In addition, the detector cannot only segment vowel and consonant, but also consonants itself. It can help further to reduce recognition error in speech recognition.
the advantage of visual data exploration is that the user is directly involved in the process of data mining. there are a large number of information visualization techniques, which have been developed over the last d...
详细信息
the advantage of visual data exploration is that the user is directly involved in the process of data mining. there are a large number of information visualization techniques, which have been developed over the last decade to support the exploration of large data sets. the octree representation is a well-known hierarchical data structure that can be used to partition the 3D space into cubic voxels of varying sizes. In this paper, we describe a new approach that uses octree technique into data mining system, and design a 3D data exploration environment.
A dual unscented Kalman filter (UKF) is applied to enhance speech signals degraded by colored noise. the speech model is a nonlinear one and is modeled by a neural network. Tire state vector and the neural weight vect...
详细信息
A dual unscented Kalman filter (UKF) is applied to enhance speech signals degraded by colored noise. the speech model is a nonlinear one and is modeled by a neural network. Tire state vector and the neural weight vector are estimated by the dual UKF. the UKF to estimate the state vector is a perceptually constrained UKF. the constraints are derived from the masking properties of human auditory systems. Simulation results show that the algorithm can produce better PESQ scores than some recently published methods.
It is almost impossible to quantitatively evaluate the performance of CVIR (content based visual information retrieval) at present. A qualitative method for the task may be better. CVIR is subjected to computer vision...
详细信息
It is almost impossible to quantitatively evaluate the performance of CVIR (content based visual information retrieval) at present. A qualitative method for the task may be better. CVIR is subjected to computer vision field. the ground truth of CVIR benchmark must be calibrated by real users. therefore, the theory of computer vision and some assumptions inferred from perceptual psychophysics can be used to qualitatively evaluate the CVIR methods. In this paper, we first introduce our idea of the qualitative evaluation method. then we will summarize some of important conclusion of psychophysics and corresponding physical constraints really adopted by human vision. Finally, some examples are introduced, which show that our method work reasonably well.
Spatio-temporal data mining is one of important topics in data mining research, in which spatio-temporal forecast is the most widely used. By analyzing the limitation of current spatio-temporal forecast methods, this ...
详细信息
Spatio-temporal data mining is one of important topics in data mining research, in which spatio-temporal forecast is the most widely used. By analyzing the limitation of current spatio-temporal forecast methods, this paper presents an integrated algorithm based on data fusing and method fusing, and applies the method successfully to railway passenger flow forecast. Experimental results show the algorithm is effective.
Capacity is an important property of digital watermarking. Research of image watermarking capacity is to study how much information can be hidden in an image. Recently, wavelet transform has been applied widely in wat...
详细信息
Capacity is an important property of digital watermarking. Research of image watermarking capacity is to study how much information can be hidden in an image. Recently, wavelet transform has been applied widely in watermarking research as its excellent multi-resolution analysis property. this paper realizes a content adaptive watermarking algorithm using Watson quantization matrix and noise visibility function (NVF), and discusses the capacity problem of watermarking in wavelet domain.
暂无评论