International Journal of Intelligent Engineering and Systems

9

Authors: Cao XiaoQiang, Zhang Jun, Xiong Xing

Nowadays, along with the development of technology of the high-speed Analog to Digital Converter (ADC) and Field Programmable Gate Array (FPGA), the design and the implementation of high-speed and highaccuracy data acquisition system is also becoming economic and feasible. In this paper, we designed a high-speed, high-precision, portable data acquisition and processing system in Altera Corporation cyclone II FPGA platform, and achieved the communication between the system and PC via USB2.0 interface. The whole system is divided into four parts: the A/D module, the FPGA module, the USB module and the LABVIEW (Laboratory Virtual Instrument Engineering Workbench) module. We used AD9467 as the core chip of the A/D module, and the characteristics and specific circuit design of AD9467 are explained in detail; the FPGA module is the core of the entire system, which is not only the center of the signal conditioning but also the control center to ensure the whole system to work in an orderly manner. We also introduced the concrete realization of the design of clock part, LVDS converter module and USB control module. The programming language used verilog hardware description language. And then we introduced the design of the USB module in detail where the Lab VIEW module was the module of human-computer interaction that introduced the concrete realization of the PC display software using G language. Finally, we debugged and tested the entire system, the results show that the design can work very well and meet the requirements of the system design.

10

Authors: Yuqing Song, Dongpeng Yue, Shaoqing Mo

In this paper we introduce a graph grammar based method to fuse the low level features and apply them to object detecting and tracking. In our algorithm, the graph grammar rules are used to detect the object in the beginning of the video sequence and then dynamically adjust the tracking procedure. Our tracking algorithm consists of two phases: key points tracking and tracking by graph grammar rules. The key points are computed by using salient level set components. All key points, as well as the colors and the tangent directions, are fed to a Kalman filter for object tracking. Then the graph grammar rules are used to dynamically examine and adjust the tracking procedure to make it robust. The effectiveness of the algorithm has been demonstrated by experiments.

8

Authors: Jing Dai, Zhonghua Han, Feng Zhang

The adaptive interference cancellation algorithms(AICA) is proposed in this paper. The Matlab simulation results of the performance of six different kinds of AICA are presented. According to the comparison of the simulation results, especially the usage of resource, convergence rate and effects of cancellation, the NLMS adaptive interference cancellation algorithm and frequency-domain block LMS algorithm are selected, which are suitable for the further design on FPGA. By simulating the functions by Modelsim, and analyzing the PSD curve and the constellation of output signals, the adaptive interference cancellation algorithm system based on frequency-domain block LMS have achieved expected effect. The frequency-domain block LMS adaptive echo interference cancellation system has better flatness on the in-band PSD curve and better convergence effect on the constellation. Therefore, frequency-domain block LMS adaptive interference cancellation algorithm is chosen as the design with high performance-price ratio. The more points there are, the more obvious advantages it will perform.

9

Authors: Liyan Dong, Renbiao Wang, Yongli Li

The paper proposed a new kind of classification algorithm based on support and certainty, which scanned the same datasets several times to discover certain frequent item sets whose length complied with the fixed increment. The algorithm produced the Boolean association rules by means of the width preference-traversing mode. The experiment shows this algorithm of association rules based on certainty and support architecture could generate a accurate association rules compared with other classification algorithm and improve the accuracy and perceptiveness of association rules effectively.

8

Authors: Qing Yang, Chang Liu, Dongxu Zhang, Dongsheng Wu

A new ensemble algorithm based on K-means clustering and probabilistic neural network called K-meansPNN for classifying the industrial system faults is presented. The proposed technique consists of a preprocessing unit based on K-means clustering and probabilistic neural network. Given a set of data points, firstly the K-means algorithm is used to obtain K-temporary clusters, and then PNN is used to diagnose faults. To validate the performance and effectiveness of the proposed scheme, K-means-PNN is applied to diagnose the faults in TE Process and compared with K-means clustering and back-propagation neural network called K-means-BP, algorithm. Simulation studies show that the proposed K-means-PNN algorithm compared with K-means-BP algorithm not only improves the accuracy in fault classification but also is a reliable and computationally efficient tool.

8

Authors: Mu Li, Wang Xinwei

A laser shaft alignment based on double LD-PSD is designed in this thesis. The mathematic model is built. The mechanical device which fixes the instrument is designedand the hardware circuit is also designed. The laser shaft alignment has strong anti-jamming capacity. It can compensate the soft ground effect and temperature effect. Therefore, it can carry out alignment measurement under various conditions. The prototype test shows the measuring precision, reliability and anti-jamming ability are higher than the likewise products. It can meet the requirement of coaxiality measuring in shafting.