Advanced Materials Research Vols. 756-759

Abstract: RFID is widely used in indoor positioning, as one of the typical system LANDMARK introduced reference label, used the nearest neighbor data correlation algorithm. This article uses the Taylor series expansion method, by the LANDMARK law get positioning results for further processing, resulting in more accurate positioning results.

Abstract: Traffic classification is a critical technology in the areas of network management and security monitoring. Traditional port-based and payload-based classification are no longer effective due to the fact that many applications utilize unpredictable port numbers and packet encryption. Researchers tend to apply machine learning (ML) techniques to identify the traffic flows by recognizing statistical features. Unfortunately, looking back upon the related work, most of the ML-based classification algorithms have similar performance, and what really matters now is how to optimize these techniques. In this paper, we analyzed two critical issues (Feature Selection, Configuration of Parameters) of ML classification, and presented the corresponding viable methods to optimize the classification model. This paper also reported the experimental evaluation to assess the performance improvements introduced by our optimized methods; experimental results on real-life datasets and network traffic show that the classification model successfully achieves significant accuracy improvement.

Abstract: This paper realizes the license plate image preprocessing, segmentation and positioning using MATLAB software. By image processing, it indicates the convenient, simple, and effectiveness of MATLAB recognition, achieving the desired effect.

Abstract: The main objective of designing skin color model is to determine whether the pixel is skin color pixels and generate the skin color mask images. The paper discusses the choise of color space and skin color model designing in skin color detection system, analysis the problems often needed to solve in it and put forward an improved skin color detection algorithm model based on ellipse boundary. The skin color detection experiment is completed. The result of experiment shows the skin color detection algorithm model is good.

Abstract: Channel estimation plays a crucial role in improving the overall system performance in long term evolution (LTE) systems. However, it is demonstrated that conventional channel estimation algorithms have poor performance in the presence of a large Doppler frequency shift. To mitigate the adverse effect of Doppler frequency shift on transmission signals, an adaptive anti-Doppler shift method based on polynomial fitting for LTE uplink is proposed in this paper. Furthermore, an adaptive strategy is exploited to improve estimation accuracy and reduce estimation mean square error (MSE), achieving better system performance. Simulations results validate the effectiveness of anti-Doppler algorithm.

Abstract: With the growing popularity of location-based service (LBS), wireless local area networks (WLAN) indoor positioning has gained widespread attention. Unlike the traditional algorithm concentrating on positioning accuracy, we discuss how to improve the real-time property in WLAN indoor fingerprinting localization systems. In this paper, we present a novel algorithm which first divides the positioning area into sub-areas utilizing k-means clustering, and then selects appropriate access points (APs) for positioning to make the calculated amount as less as possible. By collecting data and performing in the real WLAN environment, our proposed algorithm shows high positioning accuracy while the computational burden has been decreased almost 93.7%.

Abstract: Three-channel polarization images must be registered before pixel-level fusion processing to acquire accurate polarization characteristics information. In the condition of serial processing, the image registration efficiency is bad, and then the real-time of polarization imaging application is poor. The multi-core DSP chip which type is TMS320C6670 is selected as the polarization images processing platform. Fourier-Mellin Transform (FMT) is selected as the registration algorithm. The parallel processing of the polarization image registration is studied based on data flow model. The hierarchical task graph is designed in the parallel processing tasks partitioning. According to processing performance and functions, four DSP cores and two FFT coprocessors are divided into different processor groups in each task processing stage. Same hierarchical tasks are assigned to each processor group. According to principles including load balancing and reducing inter-processor communication, algorithms and data of each hierarchical task are assigned manually to each processing unit in the processor group. Experimental results show that the average processing time is 0.429 second while the average registration accuracy achieves 0.5 pixel, the propose parallel processing method improves the efficiency of the polarization image registration.

Abstract: This paper constructs a new P-DY conjugate gradient projection method, the parameter contains parameters, it can be good to adjust the parameters of, this method makes the problem much faster, and more accurate results can be obtained iteratively. The decline of this algorithm and search convergence principle under the condition of Wolfe line, and will test new estimation algorithm, it is applied to the linear model with equality constraints and the results show that the effect is very good.

Abstract: In order to solve the problem of spectral distortion and the fuzzy texture in visible and infrared image fusion technology, a novel visible and infrared image fusion method based on the Nonsubsampled Contourlet Transform (NSCT) and Pulse Coupled Neural Networks (PCNN) is proposed in this paper. First, we gain three components of visible image, luminance I, chrominance H and saturation S, using the IHS transform. Then, we gain three coefficients, low frequency sub-band, passband sub-band and high frequency coefficient by decomposing the component I and infrared image with the help of the NSCT. Next, we use weighted-sum method to fuse the low frequency sub-band and PCNN method to fuse the other sub-band coefficient respectively. At last, we gain the fusion image by using the inverse IHS transform on the fusion component I gained by the inverse NSCT transform. Experiments show that our method have better fusion quality and can be more better to keep the visible spectral and detail information than some traditional methods such as, Laplace method, Wavelet method and Lifting Wavelet method.

Abstract: In the current study, using methods of signal processing to manage gene prediction has attracted great attention. At first, the voss mapping which can map the DNA alphabetic sequence into the numerical sequence and the 3-base periodicity of exon are introduced. Then a fixed-length sliding window approach and its feasibility are analyzed. It can be proved that when two exons are very close, gene prediction by only setting a threshold to the spectrum could not have good effect. To overcome this shortcoming, a new method based on one-dimensional image segmentation is proposed. Finally, simulation shows the short introns are culled commendably. Two evaluation indices are also introduced to demonstrate the effectiveness of this method.