Applied Mechanics and Materials Vols. 738-739

Abstract: Micro-video label classification system (MLCS) is designed to tag and classify micro-videos by a specific set of labels, which are extracted from users’ comments on the internet. These labels not only describe the micro-video’s features in various aspects, but also deliver the audiences’ attitudes and concern. Combining the high-ranking labels can effectively organize the creative elements to help producing new video scripts and categories. It breaks the traditional limit of linear producing process and makes the micro-videos’ story more topical and integrate.

Abstract: In this paper, we describe a boundary stitching method for block-based parallel error diffusion algorithm. A blocked strategy is used to separate the original image into independent blocks. Overlapping areas across adjacent blocks and initial error of boundary pixels are introduce to eliminate the boundary artifacts. Experimental results show that the proposed method generates high quality images similar to that of the original algorithm.

Abstract: The typical fragment screening is one of the key links in the construction driving cycle. This problem is widely adopted Duration intercept method and clustering analysis method. Both methods are subjective,and the requirements for data of working conditions is huge. Aimed at these shortages, Using multivariate statistical theory discriminate analysis method, differentiate and classify the condition data. Basing on the statistical analysis of condition data, establish the discriminate function. With a city as example, Driving Cycle is established. Based on the discriminate analysis, classify the driving data. The effectiveness of the driving cycle is confirmed. The result of comparing discriminate analysis and traditional method shows that the driving cycle based on discriminate analysis can accurately reflect the characteristics of different kinds of driving conditions, and the data demand is reduced, meanwhile, the data acquisition test is simpler, the cost of establishing a driving cycle is cut, and development cycle is reduced.

Abstract: In order to extract the experimental modal analysis of the Modal frequency accurately, measuring twelve set of data during the experiment, to use the method of statistical frequency based on mathematical method to extract modal frequencies. It is helpful to avoid frequency leakage phenomenon as the reasons of excitation source select inappropriate and quickly and efficiently for a general analysis staff to extract the modal frequency values.

Abstract: Redundant Discrete Wavelet Transform (RDWT) and Wavelet Atomic Transform (WAT) are proposed in this paper as a couple of dictionaries to get the structure and texture basing on morphological component decomposition. Then, basing on the fact that the structure and texture have different characteristics, in this paper we use curvature driven diffusion model and Criminisi texture synthesis method to inpaint the structure and texture respectively. At last, compound the inpainted structure and texture and get the inpainting result. The experiment results show the new method can not only decompose the image very well, but also inpaint the image with strong and fairing edge, complete and clear texture .This method shows better results in image inpainting compared to the classical ones.

Abstract: Computer-aided diagnosis of Premature Ventricular Contraction (PVC) plays an important role in timely detection and treatment of arrhythmias. Conventional identification methods based on back propagation neural network (BPNN) get problems of overlong training time and local optimum. This paper proposes an application of improved BPNN on PVC identification and the improvements of BPNN are based on self-adaptive learning rate and momentum in training. Denoising and feature extraction of ECG signal obtained from MIT-BIH arrhythmia database are processed first. A comparison between standard BPNN and improved BPNN shows that the latter gets less training time and better accuracy.

Abstract: Modern complex circuits are described in very high speed integrated circuit hardware description language (VHDL) and difficult to verify. This paper proposes a systematic and visual dependency analysis method based on VHDL. The dependency relationships including control dependency, data dependency, signal control dependency and signal data dependency are defined. The entity dependency graph is presented and its generation algorithm, which searches the dependency relationships in hardware processes and between hardware processes, are developed. The experiment of a typical keyboard demonstrates that it is a visual and efficient method to analyze dependency relationships of VHDL for formal verification.

Abstract: In the face gender recognition system, in addition to want to obtain high recognition rate, but also want to be able to achieve recognition quickly which relates to multi-objective optimization problem. In this paper, we proposed an adaptive face gender recognition method based on NSGA-II which can make recognition performance and running time optimal at the same time. In our method, we use CS to extract features and Extreme Learning Machine (ELM) to achieve features recognition. Then, NSGA-II is used to optimize the method. Experimental results show that the proposed method using NSGA-II solving optimization problems can obtain evenly distributed Pareto optimal solution set at a fast convergence in the solution space which demonstrates feasibility and effectiveness of using NSGA-II to solve multi-objective face gender recognition problems.

Abstract: In most video systems,the carrier of camera expierences all kinds of motions which make the video ambiguous and unstable.Usually,the gray projection matching algorithm can only stabilize the translation motion between frames,but the rotation motion of frames in a video sequence.By zoning the image into few small regions,the rotation motion could be ignored,then, local movement vector is aqcuired by the grey projection matching method and compensate the movement between frames.Then for the rotation movement,it can be stabilized by the compensation with circle projection matching.

Abstract: Light Communication is one of the most common means of vessel communication, with merits of simple, easy-to-use, resistance to electromagnetic interference and so on. Compared with other means of vessel communication, the shortcomings of traditional lighting communication are highlighted, for example, it requires specialized training soldiers, and the information transfer rate is too low. In this paper, an automatic light receiver is presented, and an improved image segmentation algorithm in automatic light communication system is investigated. In the end, some conclusions are given to show the effectiveness of automatic light communication system and its particular application for military use.