Shu Fang¹, Lei Huang¹, Yi Wan², Weize Sun^{1, *}, Jingxin Xu³

CMC-Computers, Materials & Continua, Vol.64, No.1, pp. 541-555, 2020, DOI:10.32604/cmc.2020.010066

Abstract With the development of science and technology, the status of the water environment has received more and more attention. In this paper, we propose a deep learning model, named a Joint Auto-Encoder network, to solve the problem of outlier detection in water supply data. The Joint Auto-Encoder network first expands the size of training data and extracts the useful features from the input data, and then reconstructs the input data effectively into an output. The outliers are detected based on the network’s reconstruction errors, with a larger reconstruction error indicating a higher rate to be an outlier. For water supply… More >

Yugang Li^{1, 2, *}, Yongbin Wang¹, Zhe Chen², Yuting Zhu³

CMC-Computers, Materials & Continua, Vol.63, No.3, pp. 1575-1589, 2020, DOI:10.32604/cmc.2020.07451

Abstract Understanding an image goes beyond recognizing and locating the objects in it, the relationships between objects also very important in image understanding. Most previous methods have focused on recognizing local predictions of the relationships. But real-world image relationships often determined by the surrounding objects and other contextual information. In this work, we employ this insight to propose a novel framework to deal with the problem of visual relationship detection. The core of the framework is a relationship inference network, which is a recurrent structure designed for combining the global contextual information of the object to infer the relationship of the… More >

Mei Yang¹, Yuanjie Zheng^{1, 2, *}, Weikuan Jia^{1, *, Yunlong He3, Tongtong Che1, Jinyu Cong1}

CMC-Computers, Materials & Continua, Vol.63, No.3, pp. 1485-1498, 2020, DOI:10.32604/cmc.2020.09940

Abstract Optical Coherence Tomography (OCT) is very important in medicine and provide useful diagnostic information. Measuring retinal layer thicknesses plays a vital role in pathophysiologic factors of many ocular conditions. Among the existing retinal layer segmentation approaches, learning or deep learning-based methods belong to the state-of-art. However, most of these techniques rely on manual-marked layers and the performances are limited due to the image quality. In order to overcome this limitation, we build a framework based on gray value curve matching, which uses depth learning to match the curve for semi-automatic segmentation of retinal layers from OCT. The depth convolution network… More >

Hongping Wu¹, Yuling Liu^{1, *}, Jingwen Wang²

CMC-Computers, Materials & Continua, Vol.63, No.3, pp. 1309-1321, 2020, DOI:10.32604/cmc.2020.010172

Abstract Text classification has always been an increasingly crucial topic in natural language processing. Traditional text classification methods based on machine learning have many disadvantages such as dimension explosion, data sparsity, limited generalization ability and so on. Based on deep learning text classification, this paper presents an extensive study on the text classification models including Convolutional Neural Network-Based (CNN-Based), Recurrent Neural Network-Based (RNN-based), Attention Mechanisms-Based and so on. Many studies have proved that text classification methods based on deep learning outperform the traditional methods when processing large-scale and complex datasets. The main reasons are text classification methods based on deep learning… More >

Junshan Tan¹, Rong Duan¹, Jiaohua Qin^{1, *}, Xuyu Xiang¹, Yun Tan¹

CMC-Computers, Materials & Continua, Vol.63, No.2, pp. 675-689, 2020, DOI:10.32604/cmc.2020.07730

Abstract Hashing technology has the advantages of reducing data storage and improving the efficiency of the learning system, making it more and more widely used in image retrieval. Multi-view data describes image information more comprehensively than traditional methods using a single-view. How to use hashing to combine multi-view data for image retrieval is still a challenge. In this paper, a multi-view fusion hashing method based on RKCCA (Random Kernel Canonical Correlation Analysis) is proposed. In order to describe image content more accurately, we use deep learning dense convolutional network feature DenseNet to construct multi-view by combining GIST feature or BoW_SIFT (Bag-of-Words… More >

Hongrui Zhang¹, Wenxue Wei^{1, *}, Xinguang Xiao¹, Song Yang¹, Wanlu Shao¹

CMC-Computers, Materials & Continua, Vol.63, No.1, pp. 457-468, 2020, DOI:10.32604/cmc.2020.06988

Abstract This DC-YOLO Model was designed in order to improve the efficiency for appraising dangerous class of buildings and avoid manual intervention, thereby making the appraisal results more objective. It is an automated method designed based on deep learning and target detection algorithms to appraise the dangerous class of building masonry component. Specifically, it (1) adopted K-means clustering to obtain the quantity and size of the prior boxes; (2) expanded the grid size to improve identification to small targets; (3) introduced in deformable convolution to adapt to the irregular shape of the masonry component cracks. The experimental results show that, comparing… More >

Weibo Yang^{1, *}, Jing Li², Wei Peng², Aidong Deng³

CMC-Computers, Materials & Continua, Vol.63, No.1, pp. 283-299, 2020, DOI:10.32604/cmc.2020.07511

Abstract Based on the theory of modal acoustic emission (AE), when the convolutional neural network (CNN) is used to identify rotor rub-impact faults, the training data has a small sample size, and the AE sound segment belongs to a single channel signal with less pixel-level information and strong local correlation. Due to the convolutional pooling operations of CNN, coarse-grained and edge information are lost, and the top-level information dimension in CNN network is low, which can easily lead to overfitting. To solve the above problems, we first propose the use of sound spectrograms and their differential features to construct multi-channel image… More >

Junseob Kim¹, Beanbonyka Rim¹, Nak-Jun Sung¹, Min Hong^{2, *}

CMC-Computers, Materials & Continua, Vol.63, No.1, pp. 17-30, 2020, DOI:10.32604/cmc.2020.09044

Abstract Fingerprint security technology has attracted a great deal of attention in recent years because of its unique biometric information that does not change over an individual’s lifetime and is a highly reliable and secure way to identify a certain individuals. AFIS (Automated Fingerprint Identification System) is a system used by Korean police for identifying a specific person by fingerprint. The AFIS system, however, only selects a list of possible candidates through fingerprints, the exact individual must be found by fingerprint experts. In this paper, we designed a deep learning system using deep convolution network to categorize fingerprints as coming from… More >

M. Vilasini^{1, *}, P. Ramamoorthy²

CMC-Computers, Materials & Continua, Vol.62, No.3, pp. 1445-1472, 2020, DOI:10.32604/cmc.2020.08857

Abstract Leaf species identification leads to multitude of societal applications. There is enormous research in the lines of plant identification using pattern recognition. With the help of robust algorithms for leaf identification, rural medicine has the potential to reappear as like the previous decades. This paper discusses CNN based approaches for Indian leaf species identification from white background using smartphones. Variations of CNN models over the features like traditional shape, texture, color and venation apart from the other miniature features of uniformity of edge patterns, leaf tip, margin and other statistical features are explored for efficient leaf classification. More >

Bo Zhang¹, Haowen Wang^{1, #}, Longquan Jiang¹, Shuhan Yuan², Meizi Li^{1, *}

CMC-Computers, Materials & Continua, Vol.62, No.3, pp. 1273-1288, 2020, DOI:10.32604/cmc.2020.07269

Abstract Deep learning models have been shown to have great advantages in answer selection tasks. The existing models, which employ encoder-decoder recurrent neural network (RNN), have been demonstrated to be effective. However, the traditional RNN-based models still suffer from limitations such as 1) high-dimensional data representation in natural language processing and 2) biased attentive weights for subsequent words in traditional time series models. In this study, a new answer selection model is proposed based on the Bidirectional Long Short-Term Memory (Bi-LSTM) and attention mechanism. The proposed model is able to generate the more effective question-answer pair representation. Experiments on a question… More >