Advanced Materials Research Vols. 926-930

Abstract: This paper studies adaptive learning for diagnostic image recognition and expounds that adaptive resonance theory is utilized to achieve ART artificial neural network of self-stability and self-makeup for recognition, which meets the requirement of learning and adaption. In terms of the principle, an algorithm of self-stability and classifier learning is also provided.

Abstract: In this paper, we research the wireless resource allocation problem with packet scheduling in both MAC layer and physical layer in multi-user orthogonal frequency division multiplexing (OFDM) systems. Under the practical environment where mobile users receiving signal with different SNR levels in a cell or around a Wi-Fi hot spot, our designed algorithm can execute relatively fair packet scheduling from MAC layer consideration and make efficient use of wireless resources at physical layer. simulation results show that our proposed scheme satisfy most users in various SNR and have better average performance in packet drop rate, packet delay and total throughput.

Abstract: This paper presents an improved weighted centroid algorithm. The inverse of n multiply cubic distance algorithm was used as the weight, thus avoiding data swamping in the weighted centroid algorithm and preventing information loss. Under the same conditions, the improved weighted centroid algorithm is better than the traditional weighted centroid algorithm. The accuracy is improved by 7.14%.

Abstract: This paper presents an improved algorithm of test vector based on GA and LFSR method, to improve the TPG first, then using GA and LFSR algorithm generate test vector, finally establish the algorithm to test vector for sorting, make the bit jump number of sorted sequence at least, and uses the improved output circuit TC test method are analyzed in the response, through the experimental data, verify the advantages of this scheme is to improve the test fault coverage, reduce power consumption and improve test speed.

Abstract: One-unit independent component analysis with reference (ICA-R) is an efficient method capable of extracting a desired source signal by using reference signal. In this paper, a new fast one-unit ICA-R algorithm is derived by using kurtosis contrast function based on new constrained independent component analysis (cICA) theory. The proposed algorithm has lower computational complexity and accurate extraction. Experiments with synthetic signals demonstrate the efficacy and accuracy of the proposed algorithm.

Abstract: This paper summarizes the characteristics of high-dimensional data and the difficulties of high-dimensional data clustering, points out the shortcomings of traditional clustering algorithm in performing clustering high-dimensional data, and proposes an improved K-means algorithm to complete the high-dimensional data clustering, the algorithm has better scalability and high efficiency, suitable for handling large document sets.

Abstract: The basic principle of the NAS-RIF algorithm is described and this algorithm has a simple structure, but it tends to amplify the noise and produce excessive smoothing in the iterative process. This paper takes some measures and focuses on overcoming these shortcomings. Firstly we use an adaptive denoising method based on total variation to reduce noise in turbulence-degraded images. Then, a regularized term is added into the cost function to preserve the edges effectively and a new form of the cost function is also improved to guarantee the convergence of the algorithm. Comparing with the traditional NAS-RIF algorithm, the proposed algorithm has a positive improvement in restraining the noise enlargement, preserving the detail features and the image restoration effect is obviously better.

Abstract: The soft collision algorithm is implemented on MicroStation platform. First determine the pipeline location relationship, In view of the parallel or vertical piping and other non-parallel and non-vertical line spacing using different algorithms calculate the shortest distance. The algorithm can Meet the design requirements and reduce the amount of arithmetic operations.

Abstract: The limitations of basic active deception jamming model against SAR reconnaissance were analyzed detailed, and the necessary conditions of false target deployment for the model were derived. Some modifications and adjustment of the basic model were made, for which target-centric signal transmission schedule was proposed instead of jammer-centric schedule, time-varying repetition delay and time-varying Doppler parameters of false signal were made instead fixed parameters. The modified model extended false target’s displacement and improved the fidelity of false target. And some calculation examples and discussions were done in the end.

Abstract: This paper further analyzes some existent problems of coupling vibration equations of water hammer, based on the improved continuity equation, it is derived simply for calculating coupled water hammer vibration, comparison with continuity equation that is to be used widely, the new continuity equation is basically consistent with commonly used continuity equations, so, the improved continuity equation can be used to calculate water hammer based on fluid-structure interaction (FSI).