Spectral-spatial classification is very important in the field of remotely sensed hyperspectral imaging. The Markov Random Field(MRF) is usually used to provide the spatial constraint. However, the traditional constru...
详细信息
Spectral-spatial classification is very important in the field of remotely sensed hyperspectral imaging. The Markov Random Field(MRF) is usually used to provide the spatial constraint. However, the traditional construction of MRF uses a neighborhood and gives the same weight for all the pixels in the same neighborhood. Without the structure information in HSI, the performance of classification is not good enough. In this paper, we propose two improvements on MRF: the adaptive MRF is constructed according to spectral similarity of the spatial patch to reflect the structure information in HSI;a regularized method with a high confidence index(HCI) rule is presented to determine the refined probabilities of each pixel that promotes spatial continuity within each class. The effect of HCI rule is utilized to treat the probabilities discriminately, where the vectors with HCI are supposed to be well labeled. And the original probabilities of the pixels belong to each class are obtained by the spectral information using nearest regularized subspace(NRS) method in the first step. Experimental results on real hyperspectral data set demonstrate that the proposed method outperforms many existing methods in terms of the overall accuracy, average accuracy and kappa statistic.
In the wireless sensor networks with multiple mobile sinks, the movement of sinks or failure of sensor nodes may lead to the breakage of the existing routes. In most routing protocols, the query packets are broadcaste...
详细信息
Context-aware computing has proven to be successful in collecting and understanding various sensor data. However, providing an intelligent service by exploiting the collected context data from heterogeneous sensors is...
详细信息
This paper presents our work on the 2015 CLEF eHealth Task 2. In particular, we propose a Web-based query expansion model and a learning-to-rank algorithm to better understand and satisfy the task.
This paper presents our work on the 2015 CLEF eHealth Task 2. In particular, we propose a Web-based query expansion model and a learning-to-rank algorithm to better understand and satisfy the task.
In China, the expressway isn’t free. When a vehicle exits, the exit toll station needs to calculate the toll according to the vehicle trajectory obtained by sending a trajectory query task to the trajectory center re...
详细信息
Recent studies have shown that utilizing a mobile sink to harvest and carry data from wireless sensor network(WSN) can enhance network operations and balance the network energy consumption. Because of the sink mobilit...
详细信息
Recent studies have shown that utilizing a mobile sink to harvest and carry data from wireless sensor network(WSN) can enhance network operations and balance the network energy consumption. Because of the sink mobility, the paths between the sensor nodes and the sink change frequently, and have profound influence on the lifetime of WSN. To find an efficient protocol that can maintain the routes between the mobile sink and nodes with few network resources are important. We propose a swarm intelligent algorithm based route maintaining protocol in this paper to resolve this issue. The protocol utilizes the concentric ring mechanism to guide the route researching direction, and the optimal routing selection to maintain the data delivery route. Using the immune based artificial bee colony(IABC) algorithm to optimize the forwarding path,the protocol could find an alternative path efficiently when sink moves. The results of our experiments demonstrate that the protocol could balance the network traffic load.
In multiobjective evolutionary algorithms, most selection operators are based on the objective values or the approximated objective values. It is arguable that the selection in evolutionary algorithms is a classificat...
详细信息
ISBN:
(纸本)9781479974931
In multiobjective evolutionary algorithms, most selection operators are based on the objective values or the approximated objective values. It is arguable that the selection in evolutionary algorithms is a classification problem in nature, i.e., selection equals to classifying the selected solutions into one class and the unselected ones into another class. Following this idea, we propose a classification based preselection for multiobjective evolutionary algorithms. This approach maintains two external populations: one is a positive data set which contains a set of 'good' solutions, and the other is a negative data set contains a set of 'bad' solutions. In each generation, the two external populations are used to train a classifier firstly, then the classifier is applied to filter the newly generated candidate solutions and only the ones labeled as positive are kept as the offspring solutions. The proposed preselection is integrated into the Pareto domination based algorithm framework in this paper. A systematic empirical study on the influence of different classifiers and different reproduction operators has been done. The experimental results indicate that the classification based preselection can improve the performance of Pareto domination based multiobjective evolutionary algorithms.
This paper presents a computer-aided design (CAD) bitmap retrieval method based the on shape characteristics of CAD bitmaps. First, using the Canny edge detection algorithm to extract edge shapes of the CAD bitmaps, t...
详细信息
ISBN:
(纸本)9781467376839
This paper presents a computer-aided design (CAD) bitmap retrieval method based the on shape characteristics of CAD bitmaps. First, using the Canny edge detection algorithm to extract edge shapes of the CAD bitmaps, the edge direction histogram of CAD bitmaps are constructed according to the edge shapes. Next, using Euclidean distance and cosine value to calculate the distances between edge histograms, the similarities between CAD bitmaps are obtained according to the distances between histograms. Finally, sorting series of CAD bitmaps are obtained according to similarity values. The experimental results show that using shape features results in better effects than using color or texture features for CAD bitmap retrieval.
To deal with the inaccuracy and the uniform distribution of the DV-Hop algorithm, it is necessary to put forward a new optimization algorithm based on DV-Hop and RSSI for the two-dimensional planar node location calle...
详细信息
To deal with the inaccuracy and the uniform distribution of the DV-Hop algorithm, it is necessary to put forward a new optimization algorithm based on DV-Hop and RSSI for the two-dimensional planar node location called RSDV-Hop. The algorithm is based on the shortest hop distance with RSSI algorithm and gets the position between the nodes and the anchors according to the difference of signal strength. Moreover, it estimate the distance between the nodes and the anchors on the basis of the difference of signal strength. Therefore it can reduce the influence of the error of signal strength and the distance as far as possible by choosing different localization algorithm based on the different relationship of the nodes and the anchors. Experimental results show that the proposed algorithm performance well on the positioning accuracy and have better success rate than the DV-Hop and WPDV-Hop.
In view of the draw backs of apple grade identification in China,which still relies on photoelectric sorting and manual separation,this paper presents a processing method on the basis of the technology of computer vis...
详细信息
In view of the draw backs of apple grade identification in China,which still relies on photoelectric sorting and manual separation,this paper presents a processing method on the basis of the technology of computer vision and digital *** image processingtechnology,the researcher calculated the length of the long-short-axis,marked the location of it and calculated the 4 parameters,color,mean square,shape,size,as the key characteristics of the BP input of network to build a network and identify the level of apple through analysis of the external characteristics of *** optimum structure parameters of the BP neural network which had 9 hidden layer neurons were determined by RP training *** showed that average accuracy for fruit classification can reach 92.5% by using this model,and the executing time of microcomputer for grading of one apple is 9.3 *** method has the characteristics of high accuracy and good real-time performance.
暂无评论