Advanced Materials Research Vols. 846-847

Abstract: An abnormal traffic detection method via statistical model is proposed in this paper. At first, a new feature of normal traffic that it represents significant one-order dependency is discovered. In other words, normal traffic is obviously positive correlative. But the feature rarely appears in abnormal traffic. Based on one-order dependency, an entropy-rate model which is highly relevant to Markov model is then introduced by this paper to detect abnormal traffic. The proposed method is independent of signature so that it is able to detection both known and unknown abnormal traffic. At last, contrast experiment shows that the proposed method outperforms current methods in terms of false positives and false negatives.

Abstract: In this paper,The software design of oleifera camellia seed hyperspectral detection system is completed based on visual Basic6.0, which firstly reads hyperspectral file ( the TXT file after ViewspecPro professional software ), and selects the effective hyperspectral data. Then it needs to make the pretreatment and extraction of sensitive bands for hyperspectral data, and finish the content detection of oleifera camellia seed fatty acid oleic acid, linoleic acid, and palmitic with sensitive bands hyperspectral data and the Hyperspectral model. Finally, it needs to store the results are analyzed. It realizes the method that simple, real-time and fast detection on the content of fat acid composition of oleifera camellia seed.

Abstract: Aiming at the calculating the flow of cutthroat flume in Hydraulic Engineering, the test data is processed through the nonlinear regression analysis program which is based on the principle of least square method. With 33 equations of various functions including linear, power function curve and exponential curve to be selected as the mathematical model, the regression analysis is taken through 33 equations. Comparing the regression coefficient from analysis, the optimal mathematical model is selected as the empirical formula, which has great significance in guiding the practical engineering.

Abstract: The error correction capability of BCH is very strong, especially for the short and medium length of codes, which performance reaches the theory value. Besides, it has a strict algebraic structure, which plays an important role in the encode theory. But traditional serial BCH has a low throughput, so it cannot satisfy high speed communication. This paper designed a parallel synchronization encode and decode algorithm, and used FPGA to simulate. Experiment result shows that the proposed algorithm can satisfy the requirement of code rate and hardware resources consumption, so the algorithm has a very useful practical value.

Abstract: due to the time sequence has some unique characteristics, problems with the traditional point to point distance method are realized by more and more researchers when measuring the similarity of time series. Therefore, this paper uses a new similarity measure, i.e. global characteristics, extracting values of statistical distribution, seasonal, spectral and other characteristics from time series to construct eigenvector, based on the characteristic vector clustering analysis. By conducting time series clustering of communication base stations in a region, this paper confirms the method is able to deal with global characteristics that has a larger scale of time series, and to calculate effectively large time series.

Abstract: In this paper, according to the phenomenon that the retina will strongly respond to large contrast visual stimulation and the generation mechanism of visual information in the primary visual cortex, we propose a method generating saliency map and detecting ship objects in satellite optical images. The method can detect significant contrast objects without considering the shape, edge or other forms of prior knowledge of the objects. In ship detection experiment, the results show the detection method based on visual contrast can effectively concentrate on the objects with greater contrast and achieve good detection results.

Abstract: In this paper, an outdoor wireless remote data collection system with GPRS is proposed. This system is composed by three parts: data collection system, data transmission network and data display terminal. The system uses STM32F103 as the ARM embedded processor, and integrated with humidity and temperature sensor, GPS module, GPRS module. The real-time μC/OS Operation System runs on the hardware platform, extracting required information from the collected data. The experiment results prove the practicality and effectiveness of the system.

Abstract: This paper presents a novel approach to vision-based driving posture recognition. A driving action dataset was prepared by a side-mounted camera looking at a driver's left profile. The driving actions, including operating the shift lever, talking on a cell phone, eating and smoking, are decomposed into a number of predefined action primitives, which include operation of the shift lever, interaction with the drivers head and interaction with the dashboard. A global grid-based representation for the action primitives was emphasized, which first generate the silhouette shape from the motion history image, followed by application of the Pyramid Histogram of Oriented Gradients (PHOG) for more discriminating characterization. The random forest (RF) classifier was then exploited to classify the action primitives. Comparisons with some other commonly applied classifiers, such as kNN, multiple layer perceptron (MLP) and support vector machine (SVM), were provided. Classification accuracy is over 95% for the RF classifier in holdout experiment on the four manually decomposed driving actions.

Abstract: Taking the wavelet decomposed approximate image as the main research object, a direction estimation method for moving object was proposed in this paper. Firstly, the approximate image for the frame of the video was obtained via wavelet decomposition; and furthermore, the motion estimation on the approximate image was achieved to obtain the motion vectors. Finally, the motion vectors were described as polar coordinate form to compute the number of motion vectors in specified angles and the information entropy of the motion directions. The experiment results show that the proposed method can remove the effect of noise and the results of direction estimation are consistent with the actual motion directions.

Abstract: A new method of pitch detection is proposed based on Hilbert-Huang Transform (HHT). Firstly noisy speech signal is filtered by morphological filtering to remove the noise, and then HHT is employed to get Hilbert-Huang spectrum and to calculate instantaneous energy and its derivative. Distinguish the unvoiced and voiced using mutation of instantaneous energy and track pitch.