Shabana Habib¹, Noreen Fayyaz Khan^2,*

CMC-Computers, Materials & Continua, Vol.69, No.3, pp. 3321-3335, 2021, DOI:10.32604/cmc.2021.015504

Abstract Vehicle type classification is considered a central part of an intelligent traffic system. In recent years, deep learning had a vital role in object detection in many computer vision tasks. To learn high-level deep features and semantics, deep learning offers powerful tools to address problems in traditional architectures of handcrafted feature-extraction techniques. Unlike other algorithms using handcrated visual features, convolutional neural network is able to automatically learn good features of vehicle type classification. This study develops an optimized automatic surveillance and auditing system to detect and classify vehicles of different categories. Transfer learning is used to quickly learn the features… More >

Qasim M. Zainel¹, Murad B. Khorsheed², Saad Darwish^3,*, Amr A. Ahmed⁴

CMC-Computers, Materials & Continua, Vol.69, No.3, pp. 3813-3828, 2021, DOI:10.32604/cmc.2021.014759

Abstract Convolutional Neural Networks (CNNs) models succeed in vast domains. CNNs are available in a variety of topologies and sizes. The challenge in this area is to develop the optimal CNN architecture for a particular issue in order to achieve high results by using minimal computational resources to train the architecture. Our proposed framework to automated design is aimed at resolving this problem. The proposed framework is focused on a genetic algorithm that develops a population of CNN models in order to find the architecture that is the best fit. In comparison to the co-authored work, our proposed framework is concerned… More >

Daxing Zhang^1,*, Erguan Cai²

CMC-Computers, Materials & Continua, Vol.69, No.3, pp. 3931-3943, 2021, DOI:10.32604/cmc.2021.012302

Abstract Previous research in the area of using deep learning algorithms to forecast stock prices was focused on news headlines, company reports, and a mix of daily stock fundamentals, but few studies achieved excellent results. This study uses a convolutional neural network (CNN) to predict stock prices by considering a great amount of data, consisting of financial news headlines. We call our model N-CNN to distinguish it from a CNN. The main concept is to narrow the diversity of specific stock prices as they are impacted by news headlines, then horizontally expand the news headline data to a higher level for… More >

Yujie Zhou¹, Jin Liu^1,*, Yurong Xie¹, Y. Ken Wang²

Intelligent Automation & Soft Computing, Vol.30, No.2, pp. 715-733, 2021, DOI:10.32604/iasc.2021.020184

Abstract Text recognition is a crucial and challenging task, which aims at translating a cropped text instance image into a target string sequence. Recently, Convolutional neural networks (CNN) have been widely used in text recognition tasks as it can effectively capture semantic and structural information in text. However, most existing methods are usually based on contextual clues. If only recognize a single character, the accuracy of these approaches can be reduced. For example, it is difficult to distinguish 0 and O in the traditional CNN network because they are very similar in composition and structure. To solve this problem, we propose… More >

Xinyue Zhang¹, Ting Jin^1,*, Mingjie Han¹, Jingsheng Lei², Zhichao Cao³

Intelligent Automation & Soft Computing, Vol.30, No.2, pp. 439-452, 2021, DOI:10.32604/iasc.2021.018643

Abstract Saliency prediction has recently gained a large number of attention for the sake of the rapid development of deep neural networks in computer vision tasks. However, there are still dilemmas that need to be addressed. In this paper, we design a visual saliency prediction model using attention-based cross-model integration strategies in RGB-D images. Unlike other symmetric feature extraction networks, we exploit asymmetric networks to effectively extract depth features as the complementary information of RGB information. Then we propose attention modules to integrate cross-modal feature information and emphasize the feature representation of salient regions, meanwhile neglect the surrounding unimportant pixels, so… More >

Xiaoli Hao^1,*, Xiaojuan Meng¹, Yueqin Zhang¹, Jindong Xue², Jinyue Xia³

Intelligent Automation & Soft Computing, Vol.30, No.2, pp. 601-613, 2021, DOI:10.32604/iasc.2021.017963

Abstract The belt conveyor is essential in coal mine underground transportation. The belt properties directly affect the safety of the conveyor. It is essential to monitor that the belt works well. Traditional non-contact detection methods are usually time-consuming, and they only identify a single instance of damage. In this paper, a new belt-tear detection method is developed, characterized by two time-scale update rules for a multi-class deep convolution generative adversarial network. To use this method, only a small amount of image data needs to be labeled, and batch normalization in the generator must be removed to avoid artifacts in the generated… More >

Wei Fang^1,2,*, Lin Pang¹, Weinan Yi¹, Victor S. Sheng³

Intelligent Automation & Soft Computing, Vol.30, No.2, pp. 453-466, 2021, DOI:10.32604/iasc.2021.016589

Abstract Precipitation nowcasting has become an essential technology underlying various public services ranging from weather advisories to citywide rainfall alerts. The main challenge facing many algorithms is the high non-linearity and temporal-spatial complexity of the radar image. Convolutional Long Short-Term Memory (ConvLSTM) is appropriate for modeling spatiotemporal variations as it integrates the convolution operator into recurrent state transition functions. However, the technical characteristic of encoding the input sequence into a fixed-size vector cannot guarantee that ConvLSTM maintains adequate sequence representations in the information flow, which affects the performance of the task. In this paper, we propose Attention ConvLSTM Encoder-Forecaster(AttEF) which allows… More >

Yanyan Zhang¹, Xiangjin Ran^2,*

CMES-Computer Modeling in Engineering & Sciences, Vol.128, No.3, pp. 1231-1245, 2021, DOI:10.32604/cmes.2021.016866

Abstract In the network security field, the network intrusion detection system (NIDS) is considered one of the critical issues in the detection accuracy and missed detection rate. In this paper, a method of two-step network intrusion detection on the basis of GoogLeNet Inception and deep convolutional neural networks (CNNs) models is proposed. The proposed method used the GoogLeNet Inception model to identify the network packets’ binary problem. Subsequently, the characteristics of the packets’ raw data and the traffic features are extracted. The CNNs model is also used to identify the multiclass intrusions by the network packets’ features. In the experimental results,… More >

Chaowei Lin^1,#, Feifei Lee^1,#,*, Jiawei Cai¹, Hanqing Chen¹, Qiu Chen^2,*

CMES-Computer Modeling in Engineering & Sciences, Vol.128, No.3, pp. 985-1006, 2021, DOI:10.32604/cmes.2021.014522

Abstract Scene recognition is a fundamental task in computer vision, which generally includes three vital stages, namely feature extraction, feature transformation and classification. Early research mainly focuses on feature extraction, but with the rise of Convolutional Neural Networks (CNNs), more and more feature transformation methods are proposed based on CNN features. In this work, a novel feature transformation algorithm called Graph Encoded Local Discriminative Region Representation (GEDRR) is proposed to find discriminative local representations for scene images and explore the relationship between the discriminative regions. In addition, we propose a method using the multi-head attention module to enhance and fuse convolutional… More >

Xiaoyan Zhao^1,*, Lin Zhou², Ying Tong¹, Yuxiao Qi¹, Jingang Shi³

Intelligent Automation & Soft Computing, Vol.30, No.1, pp. 361-371, 2021, DOI:10.32604/iasc.2021.018823

Abstract In order to improve the performance of microphone array-based sound source localization (SSL), a robust SSL algorithm using convolutional neural network (CNN) is proposed in this paper. The Gammatone sub-band steered response power-phase transform (SRP-PHAT) spatial spectrum is adopted as the localization cue due to its feature correlation of consecutive sub-bands. Since CNN has the “weight sharing” characteristics and the advantage of processing tensor data, it is adopted to extract spatial location information from the localization cues. The Gammatone sub-band SRP-PHAT spatial spectrum are calculated through the microphone signals decomposed in frequency domain by Gammatone filters bank. The proposed algorithm… More >