Papers by Keyword: Signal Recognition

Abstract: In the speech emotion recognition system, voice signal recognition is the most critical step, the simple signal recognition can lead to errors. In this paper the cultural genetic method applied in speech recognition optimizes the voice features combination to find the optimal solution, and it provides effective method to improve the efficiency of the speech recognition.

Abstract: This paper starts with the basic process of music recognition to complete the study on extraction and realization of seven musical characteristics of the music features characterization, at the same time, the paper in-depth studies the pitch value duration, tonality characteristic extraction unit. Fourier analysis method based on short-time uses the computer programming for audio signal automatic analysis and processing, implements the characteristics recognition of the piano music playing, Experimental data show that the average recognition rate of algorithm is above 95% with the strong recognition ability, which provides the core technology support for developing the evaluation system of piano performance.

Abstract: Our country has rich coal resources. Further research is great significant to realize the automation of top coal caving mining technology. This paper presents a new method based on sparse representation for coal and gangue signal recognition. To solve the mining noise problem, the wavelet analysis is used to filter and de-noising. Sparse representation classification is based on the theory of compressed sensing. Recognition is achieved by analysis the sparse vector that the linearly optimal representation for a testing sample based on the training sample. Experimental results performed the method is accurate and stable.

Abstract: In order to improve the efficiency for phased array radar's ESM, an ACO and SVM conjoint method is used in this paper to solve the problem of phased array radar signal recognition. By introducing ACO to supervise SVM parametric selection, the method is able to quickly discover seemly parameter value and improve SVM separation efficiency. Experimental results show that textual algorithm possess upper exactness rate to phased array radar that the whole pulse signals sorting can be identified. With normal-SVM and RST-SVM means to compare, the algorithm SVM parameter access time is short, thereby shorten the monolithic hour.

Abstract: To enhance accurate Deinterleaving and identification rate of radar emitter signals to meet the requirements of modern electronic warfare, a novel method for radar emitter signals identification recognition is presented in this work. Firstly, instantaneous frequencies of radar signals are analyzed. Then additional derived characteristics and the extraction algorithm is proposed, based on which the Gray relational cluster analysis method is used to cluster and identify the radar emitter signals. The proposed method is applied to simulated six kind of typical radar emitter signals with different SNR. Simulation results show that the proposed method can achieve high accurate recognition rate.

Abstract: A kind of novel subspace pursuit method is proposed to reduce the complexity of subspace pursuit. The modified differential evolution algorithm (MDEA) is applied to the modified subspace pursuit (MSP) by choosing chirplet function as match atoms. A steel pipe with holes is detected by guided wave and the measured signal is decomposed and reconstructed by MSP. The matched result is compared to the process result from MP with DEA. The SNR of the processed signal is improved obviously, and the defect echo can be identified easily. The matched parameters get by MSP and MP are compared and analyzed. The Wigner-Ville distribution (WVD) of the detection signal and its matched result are computed and compared. The WVD of the detection signal is enhanced after processed by MSP. The defect locations and the center frequency of the excitation signal are more exactly get from MSP than from MP. The computation time by MSP is a little longer than by MP. Therefore, MSP is a useful signal recognition and defect location approach for pipes guided wave NDT.

Abstract: Using time series model, isometric transformation time series model and ARTAFIT model, we deal with acoustic signal, obtaining different sets of parameters according to different acoustic signals. We use support vector machine (SVM) to recognize different acoustic signals by analyzing different sets of parameters. When the parameter set is too large, we should first reduce order making use of principal component analysis (PCA), then we can recognize them using support vector machine. In the end, we give a case study, which indicate the results of applying our models are satisfactory.