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 other algorithms. More >

Nazish Naheed¹, Muhammad Shaheen¹, Sajid Ali Khan¹, Mohammed Alawairdhi^2,*, Muhammad Attique Khan^3,*

CMES-Computer Modeling in Engineering & Sciences, Vol.125, No.1, pp. 315-344, 2020, DOI:10.32604/cmes.2020.011380

Abstract In the area of pattern recognition and machine learning, features play a key role in prediction. The famous applications of features are medical imaging, image classification, and name a few more. With the exponential growth of information investments in medical data repositories and health service provision, medical institutions are collecting large volumes of data. These data repositories contain details information essential to support medical diagnostic decisions and also improve patient care quality. On the other hand, this growth also made it difficult to comprehend and utilize data for various purposes. The results of imaging data can become biased because of… More >

Wei Sun^{1, 2, *}, Xiaorui Zhang^{2, 3}, Xiaozheng He⁴, Yan Jin¹, Xu Zhang³

CMC-Computers, Materials & Continua, Vol.65, No.3, pp. 2489-2510, 2020, DOI:10.32604/cmc.2020.012343

Abstract Vehicle type recognition (VTR) is an important research topic due to its significance in intelligent transportation systems. However, recognizing vehicle type on the real-world images is challenging due to the illumination change, partial occlusion under real traffic environment. These difficulties limit the performance of current stateof-art methods, which are typically based on single-stage classification without considering feature availability. To address such difficulties, this paper proposes a twostage vehicle type recognition method combining the most effective Gabor features. The first stage leverages edge features to classify vehicles by size into big or small via a similarity k-nearest neighbor classifier (SKNNC). Further… More >

Zheng Fang^1,∗, Junyun Cai¹, Lifang Tian²

Computer Systems Science and Engineering, Vol.35, No.4, pp. 299-305, 2020, DOI:10.32604/csse.2020.35.299

Abstract Payment is a necessary thing in people’s daily life, and the development of the Internet makes it possible that people can shop at home. As for chip bank card, it is an important payment method that has been developed in recent years and plays a key role in remote payment. In this study, firstly, the risk features of chip bank cards were analyzed from the general remote payment scheme. Then, based on the security technology theory, a chip bank card remote payment model using elliptic curve hybrid encryption algorithm and identity authentication technology was constructed. In terms of security testing,… More >

Deisy Chaves^1,5,*, Maria Trujillo¹, Edward Garcia², Juan Barraza², Edward Lester³, Maribel Barajas⁴, Billy Rodriguez⁴, Manuel Romero⁴, Laura Fernández-Robles⁵

Intelligent Automation & Soft Computing, Vol.26, No.3, pp. 397-405, 2020, DOI:10.32604/iasc.2020.013916

Abstract Precise automated determination of char morphologies formed by coal during combustion can lead to more efficient industrial control systems for coal combustion. Commonly, char particles are manually classified following the ICCP decision tree which considers four morphological features. One of these features is unfused material, and this class of material not characteristic of Colombian coals. In this paper, we propose new machine learning algorithms to classify the char particles in an image based system. Our hypothesis is that supervised classification methods can outperform the 4 ‘class’ ICCP criteria. In this paper we evaluate several morphological features and specifically assess the… More >

Rongyu Chen¹, Lili Pan^{1, *}, Cong Li¹, Yan Zhou¹, Aibin Chen¹, Eric Beckman²

CMC-Computers, Materials & Continua, Vol.65, No.2, pp. 1691-1706, 2020, DOI:10.32604/cmc.2020.011706

Abstract With the development of Deep Convolutional Neural Networks (DCNNs), the extracted features for image recognition tasks have shifted from low-level features to the high-level semantic features of DCNNs. Previous studies have shown that the deeper the network is, the more abstract the features are. However, the recognition ability of deep features would be limited by insufficient training samples. To address this problem, this paper derives an improved Deep Fusion Convolutional Neural Network (DF-Net) which can make full use of the differences and complementarities during network learning and enhance feature expression under the condition of limited datasets. Specifically, DF-Net organizes two… More >

Jing Jia^a, Tinghuai Ma^b, Fan Xing^a, William Farah^a, Donghai Guan^a,c

Intelligent Automation & Soft Computing, Vol.24, No.4, pp. 819-827, 2018, DOI:10.1080/10798587.2017.1355656

Abstract Ego networks consist of a user and his/her friends and depending on the number of friends a user has, makes them cumbersome to deal with. Social Networks allow users to manually categorize their “circle of friends”, but in today’s social networks due to the unlimited number of friends a user has, it is imperative to find a suitable method to automatically administrate these friends. Manually categorizing friends means that the user has to regularly check and update his circle of friends whenever the friends list grows. This may be time consuming for users and the results may not be accurate… More >

Yue Li¹, Guangquan Xu^2,3, Hequn Xian^1,*, Longlong Rao³, Jiangang Shi^4,*

Intelligent Automation & Soft Computing, Vol.25, No.3, pp. 637-647, 2019, DOI:10.31209/2019.100000118

Abstract In order to prevent the spread of Android malware and protect privacy information from being compromised, this study proposes a novel multidimensional hybrid features extraction and analysis method for Android malware detection. This method is based primarily on a multidimensional hybrid features vector by extracting the information of permission requests, API calls, and runtime behaviors. The innovation of this study is to extract greater amounts of static and dynamic features information and combine them, that renders the features vector for training completer and more comprehensive. In addition, the feature selection algorithm is used to further optimize the extracted information to… More >

Lu Wu, Quan Liu, Ping Lou

Intelligent Automation & Soft Computing, Vol.25, No.2, pp. 249-257, 2019, DOI:10.31209/2018.100000010

Abstract The scheme of spatial pyramid matching (SPM) causes feature ambiguity near dividing lines because it divides an image into different scales in a fixed manner. A new method called soft SPM (sSPM) is proposed in this paper to reduce feature ambiguity. First, an auxiliary area rotating around a dividing line in four orientations is used to correlate the feature relativity. Second, sSPM is performed to combine these four orientations to describe the image. Finally, an optimized multiple kernel learning (MKL) algorithm with three basic kernels for the support vector machine is applied. Specifically, for each level, a suitable kernel is… More >

Shi Li¹, Xinyan Cao^{1, *}, Yiting Nan²

CMC-Computers, Materials & Continua, Vol.65, No.1, pp. 777-788, 2020, DOI:10.32604/cmc.2020.010870

Abstract Stance detection is the task of attitude identification toward a standpoint. Previous work of stance detection has focused on feature extraction but ignored the fact that irrelevant features exist as noise during higher-level abstracting. Moreover, because the target is not always mentioned in the text, most methods have ignored target information. In order to solve these problems, we propose a neural network ensemble method that combines the timing dependence bases on long short-term memory (LSTM) and the excellent extracting performance of convolutional neural networks (CNNs). The method can obtain multi-level features that consider both local and global features. We also… More >