Generative Adversarial learning with Negative Data Augmentation for Semi-supervised Text Classification by Shahriar Shayesteh, Diana Inkpen

“…One of the techniques used in these models to mitigate the generator from mode collapse is feature matching (FM). Although FM addresses some of the critical issues of SS-GANs, these models still suffer from mode collapse with missing coverage outside the data manifold. …”
Get full text

Fault diagnosis of power transformers based on dissolved gas analysis and improved LightGBM hybrid integrated model with dual‐branch structure by Xuebin Lv, Fuzheng Liu, Mingshun Jiang, Faye Zhang, Lei Jia

“…Firstly, multi‐characteristic dissolved gas ratio analysis is used to construct multi‐dimensional supplementary feature vectors, which enrich the characterisation features of transformers and facilitate efficient diagnosis of classification models. …”
Get full text

A Parts Detection Network for Switch Machine Parts in Complex Rail Transit Scenarios by Jiu Yong, Jianwu Dang, Wenxuan Deng

“…However, in the detection of complex rail transit switch machine parts such as augmented reality and automatic inspection, existing algorithms have problems such as insufficient feature extraction, large computational complexity, and high demand for hardware resources. …”
Get full text

Optimising the Selection of Input Variables to Increase the Predicting Accuracy of Shear Strength for Deep Beams by Mohammed Majeed Hameed, Faidhalrahman Khaleel, Mohamed Khalid AlOmar, Siti Fatin Mohd Razali, Mohammed Abdulhakim AlSaadi

“…The deep beam in load transfer is very important as well as difficult to design due to its shear stress problems. Accurate estimation of shear stress would help engineers to get a safer design. …”
Get full text

Lightweight construction safety behavior detection model based on improved YOLOv8 by Kan Huang, Mideth B. Abisado

“…Traditional YOLO models often have problems of missed detection and insufficient feature processing when dealing with complex scenes, especially when facing large-scale data sets. …”
Get full text

The Creation, Analysis and Applications of τ-Σ Chart in the Pulsed Neutron Attenuation by KANG Xiaoquan, HU Youliang, FAN Leyuan, LIU Houwu, FU Xin, TIAN Jian

“…Pulsed neutron attenuation logging data traditionally calculate capture cross section by slope change, and a new analysis and processing method is proposed to solve the problems of information loss and complex parameters setting. …”
Get full text

Transmission Tower Tilt State Recognition Based on Parameter Optimization of VMD-SVD and LSTM by Long ZHAO, Guanru WEN, Zhicheng LIU, Peng YUAN, Xinsheng DONG

“…Finally, the LSTM neural network is introduced for feature classification to form a fault diagnosis model. …”
Get full text

CBSNet: An Effective Method for Potato Leaf Disease Classification by Yongdong Chen, Wenfu Liu

“…Firstly, a convolution module called Channel Reconstruction Multi-Scale Convolution (CRMC) is designed to extract the upper and lower features by separating the channel features and applying a more optimized convolution to the upper and lower features, followed by a multi-scale convolution operation to capture the key changes more effectively. …”
Get full text

Blockchain covert communication scheme based on the cover of normal transactions by Pengkun JIANG, Wenyin ZHANG, Jiuru WANG, Shanyun HUANG, Wanshui SONG

“…With the development of computer technology, the situation of modern network attack and defense is becoming increasingly severe, and the problem of secure transmission of secret information needs to be solved urgently.Covert communication technology embeds secret information into the carrier and transmits the information safely through the covert channel.However, the traditional covert channels face the challenges of data damaging, attack, detection and so on, which cannot meet the higher security requirements.As a public data platform, blockchain can embed secret information under the cover of a large number of transactions.With its tamper proof, anonymity, decentralization and other characteristics, blockchain can well solve the problems of traditional covert channels and achieve secure covert communication.However, the existing blockchain covert communication schemes are limited by low communication efficiency and poor security.How to improve safety and efficiency of covert communication is a research focus of blockchain covert communication.Motivated by this issue, a blockchain covert communication scheme based on the cover of normal transactions was proposed.The hash algorithm was used to build a transmission-free password table to embed secret information without changing any transaction data.Using the elliptic curve feature, transactions with hidden information can be quickly screened out from a large number of transactions, to extract secret information quickly.This scheme improves the security and efficiency of covert communication and has strong portability.Theoretical analysis shows that attackers cannot distinguish between ordinary transactions and special transactions.This scheme has high anti-detection and scalability.Besides, the experimental results of the bitcoin test network show the high efficiency of this scheme.…”
Get full text

Rolling Bearing Fault Diagnosis Method Based on Fusion of CNN and CSSVM by LI Yunfeng, LAN Xiaosheng, SHEN Hongchang, XU Tongle

“…Then, the improved convolutional neural network model was used to train the divided two-dimensional image set to extract the deep features of time-frequency images. Finally, the extracted feature vectors were input into the support vector machine classification layer with optimized parameters by cuckoo search algorithm to realize the fault classification of rolling bearings. …”
Get full text

Influence of the Gut Microbiota on the Development of Neurodegenerative Diseases by Mahendra P. Singh, Riya Chakrabarty, Shabnam Shabir, Sumaira Yousuf, Ahmad A. Obaid, Mahmoud Moustafa, Mohammed Al-Shehri, Ahmed Al-Emam, Abdulhakeem S. Alamri, Walaa F. Alsanie, Majid Alhomrani, Anastasiia D. Shkodina, Sandeep K. Singh

“…An altered microbiome of the gut, which is considered to play a central role in diseases as well as health, has recently been identified as another potential feature seen in neurodegenerative disorders. An array of microbial molecules that are released in the digestive tract may mediate gut-brain connections and permeate many organ systems, including the nervous system. …”
Get full text

BPFun: a deep learning framework for bioactive peptide function prediction using multi-label strategy by transformer-driven and sequence rich intrinsic information by Lun Zhu, Hao Sun, Sen Yang

“…Meanwhile, adopting data augmentation to solve the problem of data imbalance. We combine convolutional networks of different scales and Bi-LSTM layers to obtain high-level feature vectors of different features. …”
Get full text

Advanced leukocyte classification using attention mechanisms and dual channel U-Net architecture by Gauri Kalnoor, Vijayalaxmi Kadrolli

“…Different conventional leukocyte analysis approaches often face several problems like inaccuracies, demanding the need for sophisticated approaches to improve diagnostic precision. …”
Get full text

Aircraft Sensor Fault Diagnosis Based on GraphSage and Attention Mechanism by Zhongzhi Li, Jinyi Ma, Rong Fan, Yunmei Zhao, Jianliang Ai, Yiqun Dong

“…Traditional deep learning-based fault diagnosis methods often face challenges, such as limited data representation and insufficient feature extraction. To address these problems, this paper proposes an enhanced GraphSage-based fault diagnosis method that incorporates attention mechanisms. …”
Get full text

Object Detection Method of Inland Vessel Based on Improved YOLO by Yaoqi Wang, Jiasheng Song, Yichun Wang, Rongjie Wang, Hongyu Chen

“…Firstly, the CAA attention module is introduced into the Backbone network, and the C2f_CAA module is constructed at the same time to enhance the features of the central region and improve the understanding ability of complex scenes. …”
Get full text

Expression Recognition Algorithm of Deeply Separable Residual Network under Joint Loss by LI Jingyu, CHENG Weiyue, LIN Kezheng, MIAO Zhuang, LI Ao

“… In order to enhance the feature extraction ability of neural network and further improve the accuracy of facial expression recognition, this paper proposes a deep separable residual network model under joint loss DSResNet-Jloss.This network is a lightweight network model based on deep separable convolution and residual learning methods.The method of channel-by-channel convolution and point-by-point convolution is used to replace the conventional convolution operation, which solves the problems of traditional convolutional neural network with large parameter redundancy, long training time, slow convergence, and easy overfitting.And add residual unit to the network, use shortcut connection, through identity mapping, to solve the problem of gradient explosion or attenuation caused by too many layers of the network model.A joint loss function is proposed, which fully combines the advantages of cross-entropy loss, center loss and contrast loss to reduce the intra-class distance of expression features and increase the inter-class distance.Experiments show that the model has achieved good results on the two public data sets of FERPlus and RAF-DB, showing good generalization ability and robustness.…”
Get full text

An Ensemble Classification Method Based on a Stacking Strategy for Ship Type Classification with AIS Data by Lei Deng, Shichen Yang, Limin Jia, Danyang Geng

“…Traditional ship type classification methods with AIS data are often plagued by problems such as data imbalance, insufficient feature extraction, reliance on single-model approaches, or unscientific model combination methods, which reduce the accuracy of classification. …”
Get full text

Intelligent Identification Method of Wind Farm Sub-synchronous/Super-synchronous Oscillation Parameters Based on RA-CNN and Synchrophasor by Youwen LU, Hao CUI, Jianing CHEN, Xiangjia PENG, Shuang FENG, Dong LIU

“…Meanwhile, this method introduces residual connections to solve the problems of gradient vanishing and network degradation in the deep convolutional neural network. …”
Get full text

Use of machine learning for simplification of University Personality Inventory (UPI) by Weihua Guo, Jinsheng Hu, Qi Qiang, Xianke Chen

“…Additionally, we analyzed individual features and feature combinations. Results: Among the three models, the Random Forest model performed the best, with an accuracy of 89.4 %. …”
Get full text

Integration of interior design strategies and computer-aided design technology guided by morphogenetic theory by Jie Zhang, Zhongxian Ren

“…In response to the problems of low efficiency and insufficient intelligence in traditional interior design, this study integrates deep learning-based interior design strategies with computer-aided design technology under the guidance of morphogenesis theory. …”
Get full text