Hui Li¹, Wei Zeng^1,*, Guorong Xiao², Huabin Wang¹

Intelligent Automation & Soft Computing, Vol.26, No.4, pp. 841-846, 2020, DOI:10.32604/iasc.2020.010118

Abstract Recent progress on image colorization is substantial and benefiting mostly from the great development of the deep convolutional neural networks. However, one type of object can be colored by different kinds of colors. Due to the uncertain relationship between the object and color, the deep neural network is unstable and difficult to converge during the training process. In order to solve this problem, this paper proposes an instance-aware automatic image colorization algorithm, which uses the semantic features of the object instance as prior knowledge to guide the deep neural network to do the colorization task. More >

Lei Feng^1,2, Haibin Li^1,*, Yakun Gao¹, Yakun Zhang¹

Intelligent Automation & Soft Computing, Vol.26, No.4, pp. 831-839, 2020, DOI:10.32604/iasc.2020.010117

Abstract In the paper, we apply the sparse reconstruction algorithm of improved background dictionary to saliency detection. Firstly, after super-pixel segmentation, two bottom features are extracted: the color information of LAB and the texture features of the image by Gabor filter. Secondly, the convex hull theory is used to remove object region in boundary region, and K-means clustering algorithm is used to continue to simplify the background dictionary. Finally, the saliency map is obtained by calculating the reconstruction error. Compared with the mainstream algorithms, the accuracy and efficiency of this algorithm are better than those of More >

U. Venkateshkumar^1,*, S. Ramakrishnan²

Intelligent Automation & Soft Computing, Vol.26, No.4, pp. 817-830, 2020, DOI:10.32604/iasc.2020.010116

Abstract A hybrid form of the genetic algorithm and the modified K-Means cluster algorithm forms as a Gencluster to detect a spectrum hole among n-number of primary users (PUs) is present in the cooperative spectrum sensing model. The fusion center (FC), applies the genetic algorithm to identify the best chromosome, which contains many PUs cluster centers and by applying the modified K-Means cluster algorithm identifies the cluster with the PU vacant spectrum showing high accuracy, and maximum probability of detection with minimum false alarm rates are achieved. The graphical representation of the performance metric of the More >

Na Li^*

Intelligent Automation & Soft Computing, Vol.26, No.4, pp. 807-815, 2020, DOI:10.32604/iasc.2020.010115

Abstract The study of the English language has always been a focus of education and teaching in China. The traditional English language teaching model no longer meets the needs of modern education, especially when spoken in English. Spoken English represents the actual effect of English teaching to a certain extent. Good oral English ability reflects one's English level. The traditional oral English teaching mode is only limited to the interactive training of the oral mechanization between the teacher and student, or the non-targeted dialogue training with foreign teachers, which ignores the factors such as environment, language… More >

B. Indira^1,*, K. Valarmathi²

Intelligent Automation & Soft Computing, Vol.26, No.4, pp. 795-805, 2020, DOI:10.32604/iasc.2020.010114

Abstract Packet classification is a major bottleneck in Software Defined Network (SDN). Each packet has to be classified based on the action specified in each rule in the given flow table. To perform classification, the system requires much of the CPU clock time. Therefore, developing an efficient packet classification algorithm is critical for high speed inter networking. Existing works make use of exact matching, range matching and longest prefix matching for classification and these techniques sometime enlarges rule databases, thus resulting in huge memory consumption and inefficient searching performance. In order to select an efficient packet… More >

Rui Zhang¹, Xiaoxiong Zhao^2,*

Intelligent Automation & Soft Computing, Vol.26, No.4, pp. 783-793, 2020, DOI:10.32604/iasc.2020.010113

Abstract At the end of the 20th century, the emergence and development of virtual reality display methods based on virtual reality technology is one of the most remarkable achievements in the field of digital design. In the late 20th century, rapidly developing virtual reality technology was gradually combined with computer multimedia display technology, and emerging digital information display means thus quickly became widely used in the design field. In today's information multimedia display field, multimedia display design using virtual reality technology has become one of the most important means of information display. In fact, in many More >

Qixue Guan^*, Yueqiu Jiang

Intelligent Automation & Soft Computing, Vol.26, No.4, pp. 773-781, 2020, DOI:10.32604/iasc.2020.010112

Abstract It is known that congestion in the reverse direction happens in advance of the congestion in the forward direction due to the significant bandwidth asymmetry in the two directions of the space networks, especially in the satellite networks, which enables the TCP Vegas to enter the phase of the congestion avoidance blindly and reduce the throughput of the forward direction. To solve this problem, a congestion control model, TCP Vegas-DDA, which maintains the frequency of the acknowledgments in the reverse direction is proposed. The model sets the interval time between acknowledgments dynamically based on the More >

Xiaoyan Wang^*, Shui Jing

Intelligent Automation & Soft Computing, Vol.26, No.4, pp. 765-771, 2020, DOI:10.32604/iasc.2020.010111

Abstract The organic combination of the independent innovation and open innovation opens a new pattern of innovation. Under the background of the open independent innovation, the cooperative innovation model of the school and enterprise is established, and an optimal development path model of the cooperative innovation of the school and enterprise based on the fuzzy decision control algorithm is proposed. Based on the rough set theory, a path search model of the cooperative innovation between a school and enterprise is established under the background of the open independent innovation. Under the background of the open independent… More >

Xinbao Wang^*, Dawu Huang, Xuemin Zhao

Intelligent Automation & Soft Computing, Vol.26, No.4, pp. 755-763, 2020, DOI:10.32604/iasc.2020.010110

Abstract In order to improve the judgment decision ability of the sports training effect, a design method of the sports training decision support system based on the improved association rule, the Apriori algorithm is proposed, and a phase space model of the sports training decision support data association rule distribution is constructed. The association rule mining method is used to support the data mining model of sports training, and the decision judgment of the sports training effect is carried out in the mixed cloud computing environment. The fuzzy information fusion and the data structure feature reorganization… More >

Kun Liu^*

Intelligent Automation & Soft Computing, Vol.26, No.4, pp. 749-754, 2020, DOI:10.32604/iasc.2020.010109

Abstract In the English network examination system, the big data distribution is highly coupled, the cost of data query is large, and the precision is not good. In order to improve the ability of the data classification and query in the English network examination system, a method of data classification and query in the English network examination system is proposed based on the grid region clustering and frequent itemset feature extraction of the association rules. Using the grid image analysis to improve the statistical analysis of the English performance analysis, the collection and storage structure analysis… More >