He Gong^1,3,4, Lin Chen¹, Haohong Pan¹, Shijun Li^2,5, Yin Guo¹, Lili Fu¹, Tianli Hu^1,3,4,*, Ye Mu^1,3, Thobela Louis Tyasi⁶

CMC-Computers, Materials & Continua, Vol.72, No.3, pp. 6015-6027, 2022, DOI:10.32604/cmc.2022.027160

Abstract The scale of deer breeding has gradually increased in recent years and better information management is necessary, which requires the identification of individual deer. In this paper, a deer face dataset is produced using face images obtained from different angles, and an improved residual neural network (ResNet)-based recognition model is proposed to extract the features of deer faces, which have high similarity. The model is based on ResNet-50, which reduces the depth of the model, and the network depth is only 29 layers; the model connects Squeeze-and-Excitation (SE) modules at each of the four layers where the channel changes to… More >

Yintong Wang^1,2,*, Yingjie Yang², Haiyan Chen³, Hao Zheng¹, Heyou Chang¹

Intelligent Automation & Soft Computing, Vol.34, No.1, pp. 371-388, 2022, DOI:10.32604/iasc.2022.027146

Abstract Handwritten Chinese recognition which involves variant writing style, thousands of character categories and monotonous data mark process is a long-term focus in the field of pattern recognition research. The existing methods are facing huge challenges including the complex structure of character/line-touching, the discriminate ability of similar characters and the labeling of training datasets. To deal with these challenges, an end-to-end residual attention handwritten Chinese paragraph text recognition method is proposed, which uses fully convolutional neural networks as the main structure of feature extraction and employs connectionist temporal classification as a loss function. The novel residual attention gate block is more… More >

Haichao Wang¹, Yingying Fan^2,3,*, Weigao Meng⁴, Qiaoran Yang⁵

Energy Engineering, Vol.119, No.3, pp. 1075-1101, 2022, DOI:10.32604/ee.2022.019584

Abstract Sustainability evaluation of regional microgrid interconnection system is conducive to a profound and comprehensive understanding of the impact of interconnection system projects. In order to realize the comprehensive and scientific intelligent evaluation of the system, this paper proposes an evaluation model based on combination entropy weight rank order-technique for order preference by similarity to an ideal solution (TOPSIS) and Niche Immune Lion Algorithm-Extreme Learning Machine with Kernel (NILA-KELM). Firstly, the sustainability evaluation indicator system of the regional microgrid interconnection system is constructed from four aspects of economic, environmental, social, and technical characteristics, and the evaluation indicators are explained. Then, the… More >

Xiaosha Qi¹, Genlin Ji^2,*, Jie Zhang², Bo Sheng³

Intelligent Automation & Soft Computing, Vol.33, No.3, pp. 1861-1875, 2022, DOI:10.32604/iasc.2022.027182

Abstract Video anomaly detection is essential to distinguish abnormal events in large volumes of surveillance video and can benefit many fields such as traffic management, public security and failure detection. However, traditional video anomaly detection methods are unable to accurately detect and locate abnormal events in real scenarios, while existing deep learning methods are likely to omit important information when extracting features. In order to avoid omitting important features and improve the accuracy of abnormal event detection and localization, this paper proposes a novel method called Multi Chunk Learning based Skip Connected Convolutional Auto Encoder (MCSCAE). The proposed method improves the… More >

P. Saravanakumar¹, T. V. P. Sundararajan², Rajesh Kumar Dhanaraj³, Kashif Nisar^4,*, Fida Hussain Memon^5,6, Ag. Asri Bin Ag. Ibrahim⁴

Intelligent Automation & Soft Computing, Vol.33, No.3, pp. 1835-1847, 2022, DOI:10.32604/iasc.2022.018953

Abstract Confidentiality and data integrity are essential paradigms in data aggregation owing to the various cyberattacks in wireless sensor networks (WSNs). This study proposes a novel technique named Lamport certificateless signcryption-based shift-invariant connectionist artificial deep neural networks (LCS-SICADNN) by using artificial deep neural networks to develop the data aggregation security model. This model utilises the input layer with several sensor nodes, four hidden layers to overcome different attacks (data injection, compromised node, Sybil and black hole attacks) and the output layer to analyse the given input. The Lamport one-time certificateless signcryption technique involving three different processes (key generation, signcryption and unsigncryption)… More >

Ling Sun^1,#, Chengcheng Pang^1,#, Xiaoyan Wang^2,#, Mingguo Xu³, Zhiwei Zhang^1,*, Shushui Wang^1,*

Congenital Heart Disease, Vol.17, No.2, pp. 201-214, 2022, DOI:10.32604/chd.2022.018453

Abstract Background: Partial anomalous pulmonary venous connection (PAPVC) is frequently associated with atrial septal defect (ASD), especially sinus venosus defect (SVD). Although Waggstaffe described the pathology of SVDs in 1868, the exact anatomic features and the nature of SVD remains controversial. SVDs with no posterior atrial rim were observed in recent years. However, no studies suggested that absence of the residual posterior atrial septal tissue might be the key feature of SVD. The aims of this study were to investigate if absence of posterior rim of atrial septum played a crucial role in patients with SVD. Methods: From January 2011 to… More >

Hua Yan^1,2,3, Bo Song^1,3,*, Dongsheng Xu², Guodong Zhang²

CMES-Computer Modeling in Engineering & Sciences, Vol.131, No.1, pp. 199-217, 2022, DOI:10.32604/cmes.2022.016312

Abstract In this paper, three kinds of shear walls with full sleeve grouting, fully defective sleeve and partially defective are designed for finite element analysis to analyze the influence of defects on the seismic performance of shear walls. The research shows that at the beginning of loading (5 s), the three models begin to appear compressive damage at the bottom of the wall in all three models. The damage of the defect-free model develops rapidly, and the damage of the fully defective model is basically the same as that of the partially defective model. With the gradual increase of displacement control (15 s),… More >

Ting Huang, Xin Zhuo^*

Journal of Renewable Materials, Vol.10, No.4, pp. 993-1005, 2022, DOI:10.32604/jrm.2022.017373

Abstract The construction of grouting butt joints of bamboo tubes is simple and efficient. However, when the joint is bent, the low tensile strength of the mortar easily leads to cracking of the mortar prior to the failure of the bamboo tube. In this paper, a comparative test of the bending capacity was performed on grouting butt joints reinforced by nonperforated, fully perforated, and semiperforated steel plates embedded in bamboo tubes to obtain the load-displacement curves and ultimate bearing capacity of various specimens. The strengthening effect of CFRP pasted on bamboo tubes was also studied. The results show that the opening… More > Graphic Abstract

Shi-Joon Yoo^1,2,*, Sanga Lee³, Regina de la Mora⁴, Ankavipar Saprungruang², Christoph Haller⁵, Lee N. Benson², Vladimiro Vida⁶, Alvise Guariento⁶, Christopher Z. Lam¹

Congenital Heart Disease, Vol.17, No.1, pp. 5-23, 2022, DOI:10.32604/CHD.2022.018728

Abstract Sinus venosus defects include two varieties, superior and inferior sinus venosus defects. The superior sinus venosus defect is characterized by abnormal communication between two closely related venoatrial structures: 1) the normally positioned superior vena cava-right atrium complex and 2) the right pulmonary vein-left atrium complex that is displaced leftward, forward and upward. Inferior sinus venosus defects primarily involve the inferior vena cava-right atrial junction while the right pulmonary vein-left atrial junction can also be affected. Because of the rarity and wide variation of the defects, the morphological characterization of sinus venosus defects is inconsistent among investigators and often inaccurate. Modern… More >

Linfang Yu, Zhen Qin^*, Yi Ding, Zhiguang Qin

CMES-Computer Modeling in Engineering & Sciences, Vol.129, No.2, pp. 805-828, 2021, DOI:10.32604/cmes.2021.017332

Abstract As an important part of the new generation of information technology, the Internet of Things (IoT) has been widely concerned and regarded as an enabling technology of the next generation of health care system. The fundus photography equipment is connected to the cloud platform through the IoT, so as to realize the real-time uploading of fundus images and the rapid issuance of diagnostic suggestions by artificial intelligence. At the same time, important security and privacy issues have emerged. The data uploaded to the cloud platform involves more personal attributes, health status and medical application data of patients. Once leaked, abused… More >