A new approach for image segmentation based on visual attention mechanism is proposed. Motivated biologically, this approach simulates the bottom-up human visual selective attention mechanism, extracts early vision features of the image and constructs the saliency map. Multiple image features such as intensity, color and orientation in multiple scales are extracted to get some feature maps. The phase spectra of the feature maps are analyzed in frequency spectrum domain. Then the corresponding feature saliency maps are constructed in spatial domain and theses feature saliency maps are combined to an integrated saliency map.

<span style="font-size: 10pt; font-family: &quot;Times New Roman&quot;; mso-fareast-font-family: 宋体; mso-ansi-language: EN-US; mso-fareast-language: EN-US; mso-bidi-language: AR-SA;" lang="EN-US">Salient region detection in images is very useful </span><span style="font-size: 10pt; font-family: &quot;Times New Roman&quot;; mso-fareast-font-family: 宋体; mso-ansi-language: EN-US; mso-fareast-language: ZH-CN; mso-bidi-language: AR-SA;" lang="EN-US">for image processing applications like image compressing, image segmentation, object detection and recognition. In this paper, an improved approach to detect salient region is presented</span><span style="font-size: 10pt; font-family: &quot;Times New Roman&quot;; mso-fareast-font-family: 宋体; mso-ansi-language: EN-US; mso-fareast-language: EN-US; mso-bidi-language: AR-SA;" lang="EN-US">. </span><span style="font-size: 10pt; font-family: &quot;Times New Roman&quot;; mso-fareast-font-family: 宋体; mso-ansi-language: EN-US; mso-fareast-language: ZH-CN; mso-bidi-language: AR-SA;" lang="EN-US">The proposed method can generate a robust saliency map and extract salient regions with precise boundaries. In the proposed method, local saliency, global saliency and rarity saliency of three kinds of low-level feature contrast of intensity, color and orientation are used to compute the visual saliency. A new feature integration strategy is proposed in this paper. This method can select features and compute the weights of the features dynamically by analyzing the effect of different features on the saliency. Then a more robust saliency map is obtained. It has been tested on many images to evaluate the validity and effectiveness of the proposed method. We also compare our method with other salient region detection methods and our method outperforms other methods in detection results.</span><span style="font-size: 10pt; font-family: &quot;Times New Roman&quot;; mso-fareast-font-family: 宋体; mso-ansi-language: EN-US; mso-fareast-language: EN-US; mso-bidi-language: AR-SA; mso-bidi-font-size: 9.0pt;" lang="EN-US"> </span>

The Non-negative matrix factorization (NMF) can be formulated as a minimization problem with bound constraints. NMF is capable to produce a region- or part- based representations of the wood images. We present an extension to the NMF and discuss the development as well as the use of damped Newton optimization approach for update matrices W and H called iterative DNNMF with good convergence property for wood defects detection by adding a diagonal correction to the stiffness matrix and employing a Newton direction in the line search until any constraints become active. We also provide algorithms for computing these new factorizations and the supporting theoretical analysis. DNNMF is tested with color wood images based on the statistical features extracted by local binary pattern (LBP) from the feature spaces. Finally, we present experimental results that explore the properties of the proposed method. After many comparative experiments, the test results show DNNMF is effectual and practical with good research values and potential applications.

A new global path planning approach based on binary particle swarm optimization algorithm (BPSO) for a mobile robot is presented. The detailed realization of the approach is illustrated. The obstacles in the robot's environment are described as polygons and the vertexes of obstacles are numbered from 1 to n. Binary particle swarm optimization is used to plan the path. The length of the particle is the number of the vertexes. Every bit in the particle may be 1 or 0 which represents whether the vertex is in the path or not. To avoid converging too fast (the algorithm stops when the optimal path is not found), the algorithm is improved and the mutation operation is used. Simulation results are provided to verify the effectiveness and practicability of this approach.

Learning performance prediction can help teachers find students who tend to fail as early as possible so as to give them timely help, which is of great significance for online education. With the availability of online data and the continuous de-velopment of machine learning technology, learning performance prediction in large-scale online education is gaining new momentum. In order to understand the performance of different machine learning algorithms in predicting multi-category learning performance in large-scale online education, this study com-pares five machine learning algorithms including logic regression, decision tree algorithm, naive Bayes, support vector machine and deep neural network. Based on 100000 data records in the edX open dataset, this study models and forecasts students' learning performance with six online learning behaviors as the eigenval-ues. In the process of modeling, missing value estimation and normalization pre-processing are carried out on the original data at first. After that, six datasets of different sizes are divided as input data. Next, the performance of the five algo-rithms is tested on data sets of different sizes. Finally, SFS, SBS and multiple re-gression analysis are used to explore the effect of behavioral feature selection on algorithm performance. The research was validated and evaluated by three met-rics: precision, recall and F1 score. The results show that the F1 score of the deep neural network with multiple regression analysis feature selection achieves 99.25% in the large-scale dataset, outperforming the related other models by 1.25%.