Applied Mechanics and Materials Vols. 475-476

Abstract: GEAR is an important geographic and energy aware routing protocol in wireless sensor network. As the GEAR is short of enough topology knowledge and the nodes energy is limited, routing void and routing loop will be arisen. This paper presents a smart energy aware routing protocol based on the geographic (SGEAR), which is suitable for the specific scenarios of small network. In the specific scenarios of small network, there are three major nodes to concentrate on, (1) the selected (2) the void (3) the residual energy is less than threshold. The SGEAR modifies the cost functions based on the residual energy, escaping the routing loop caused by the broadcast delay. From the simulations, the conclusions can be drawn that the smaller hop count doesnt indicate the less energy consumption, and SGEAR can reduce the void number, reducing the energy consumption of the entire network, which further prolongs the life of the network to satisfy the need of the specific scenarios of small network.

Abstract: The tracking effect is not good for the faster track with Mean Shift tracking algorithm when the difference is not obvious between the track target and background pixels in the video of global visual robotic fish.To solve the difficulty of tracking drastically moving targets in this paper, determining the position of moving targets in the next frame through comparing with two bc coefficients which have been set when the Epanechnikov has been selected core to estimate is indeed. The experimental results show the proposed algorithm can track the moving targets efficiently and precisely in video,and also can meet high real-time situation with small calculation.

Abstract: Electronic nose is an intelligent sensory analyzing instrument which simulates the biological olfaction system. Classification is very important for an electronic nose which is usually seen as the software of E-nose. In this paper, we present a model of classification based on genetic algorithm. Compared with common classification algorithms, genetic algorithm had more powerful flexibility and global searching capability. In this paper classification rules were represented in the form of chromosome by binary codes which are in accordance with the features of sensor data. F-measure was used as fitness evaluation. We also designed efficient crossover, mutation operators.

Abstract: In the model of flexible neural tree (FNT), parameters are usually optimized by particle swarm optimization algorithm (PSO). Because PSO has many shortcomings such as being easily trapped in local optimal solution and so on, an improved algorithm based on quantum-behaved particle swarm optimization (QPSO) is presented. It is combined with the factor of speed, gather and disturbance, so as to be used to optimize the parameters of FNT. This paper applies the improved quantum particle swarm optimization algorithm to the neural tree, and compares it with the standard particle swarm algorithm in the optimization of FNT. The result shows that the proposed algorithm is with a better expression, thus improves the performance of the FNT.

Abstract: This paper proposes a recursive least squares algorithm for nonlinear systemswith piece-wise linearities. By using a switching function, themodel of the nonlinear systems be changed to anidentification model, then based on the derived model, a recursive least squares algorithm is provided to estimate all theunknown parameters of the systems. An example is provided to showthe effectiveness of the proposed algorithm.

Abstract: To improve the localization accuracy of bistatic sonar in such districts as baseline district, and side districts of transmitting and receiving stations, the most effective method is to increase the number of transmitting and receiving stations, which forms a multistatic sonar system. The mature algorithm of multistatic sonar system which contains three measurements in one subset, calls the multistatic bearing-only localization (BOL) algorithm. This paper proposes a new algorithm of improving the bearing-only localization algorithm. The simulation results show that the proposed localization algorithm exhibits higher accuracy compared with the BOL algorithm and provides less time than it.

Abstract: In this paper, we present an improved text clustering algorithm. It not only maintains the self-organizing features of SOM network, but also makes up the disadvantages of the bad clustering effect caused by the inadequate selection of K-means algorithm. Firstly, data is preprocessed to form vector space model for subsequent process. Then, we analyze the features of original clustering algorithm and SOM algorithm, and plan an improved SOM clustering algorithm to overcome low stability and poor quality of original algorithm. The experimental results indicate that the improved algorithm has a higher accuracy and has a better stability, compared with the original algorithm.

Abstract: The scheduling of Out-Tree task graphs is one of the critical factors in implementing the compilers of parallel languages and improving the performance of parallel computing. When applied to Out-Tree task graphs, many previous classical heterogeneity based algorithms always ignored the economization on processors and the minimization of the schedule length, which led to low efficiency in real applications. This paper proposes a heterogeneity based greedy algorithm for scheduling Out-Tree task graphs, which is based on list and task duplication, tries to find the best point between balancing loads and shortening the schedule length and improves the schedule performance without increasing the time complexity of the algorithm. The comparative experimental results demonstrate that the proposed algorithm could achieve shorter schedule length while using less number of processors.

Abstract: Recommendation systems have achieved widespread success in E-commerce nowadays. There are several evaluation metrics for recommender systems, such as accuracy, diversity, computational efficiency and coverage. Accuracy is one of the most important measurement criteria. In this paper, to improve accuracy, we proposed a hybrid recommender algorithm by an improved similarity method (ISM), combining demographic recommendation techniques and user-based collaborative filtering (CF) algorithms. Experiments were performed to compare the present approach with the other classical similarity measures based on the MovieLens dataset. The Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE) values show the superiority of the proposed algorithm.

Abstract: The detection of moving objects are important research area for video surveillance and other video processing applications. In this paper, we propose an adaptive approach modeling background and segmenting moving object with non-parametric kernel density estimation. Unlike previous approaches to object detection which detect objects by global threshold, we use a local threshold to reflect temporal persistence. With combined of global threshold and local thresholds, the proposed approach can handle scenes containing gradual illumination variations and noise and has no bootstrapping limitations. Experimental results on different types of videos demonstrate the utility and performance of the proposed approach.