Adversarial sample generation algorithm for vertical federated learning by Xiaolin CHEN, Daoguang ZAN, Bingchao WU, Bei GUAN, Yongji WANG

“…To adapt to the scenario characteristics of vertical federated learning (VFL) applications regarding high communication cost, fast model iteration, and decentralized data storage, a generalized adversarial sample generation algorithm named VFL-GASG was proposed.Specifically, an adversarial sample generation framework was constructed for the VFL architecture.A white-box adversarial attack in the VFL was implemented by extending the centralized machine learning adversarial sample generation algorithm with different policies such as L-BFGS, FGSM, and C＆amp;W.By introducing deep convolutional generative adversarial network (DCGAN), an adversarial sample generation algorithm named VFL-GASG was designed to address the problem of universality in the generation of adversarial perturbations.Hidden layer vectors were utilized as local prior knowledge to train the adversarial perturbation generation model, and through a series of convolution-deconvolution network layers, finely crafted adversarial perturbations were produced.Experiments show that VFL-GASG can maintain a high attack success while achieving a higher generation efficiency, robustness, and generalization ability than the baseline algorithm, and further verify the impact of relevant settings for adversarial attacks.…”
Get full text

Handwriting Digital Image Generation based on GAN: A Comparative Study of Basic GAN and CGAN Models by Zeng Hongzhi

“…Furthermore, an investigation of other cutting-edge generating models indicates that there is still room for optimization in the CGAN network structure to improve its performance for increasingly intricate generative tasks.…”
Get full text

Evaluation of Natural Image Generation and Reconstruction Capabilities Based on the β-VAE Model by Zhang Honghao

“…Natural image generation models are crucial in computer vision. However, the Variational Autoencoder (VAE) has limitations in image quality and diversity, while β-VAE achieves a balance between the decoupling of latent space and generative quality by adjusting the coefficient β. …”
Get full text

Bayesian Classifier with Simplified Learning Phase for Detecting Microcalcifications in Digital Mammograms by Imad Zyout, Ikhlas Abdel-Qader, Christina Jacobs

“…This proposed work extracts textural, spectral, and statistical features of each input mammogram and generates models of real MCs to be used as training samples through a simplified learning phase of the Bayesian classifier. …”
Get full text

Research on Self-Organization in Resilient Recovery of Cluster Supply Chains by Liang Geng, Renbin Xiao, Shanshan Xie

“…Second, a cluster supply chain network structure generation model is proposed. And based on cascading effect model, it makes analysis of dynamic evolution process when cluster supply chain failure happens. …”
Get full text

Classification of Prominent Cacao Pod Diseases Using Multi-Feature Visual Analysis and k-Nearest Neighbors Algorithm by Earl Clarence San Diego, Seph Gerald Rodrin, Edwin Arboleda

“…The study's outcome suggested the continuous practicality of fusing visual feature extraction processes with supervised machine learning to generate models that can be applied to improve agricultural methods.         …”
Get full text

An IoT-enhanced automatic music composition system integrating audio-visual learning with transformer and SketchVAE by Yifei Zhang

“…Experimental results show that TransVAE-Music has 1.10 and 1.12 reconstruction errors on the POP909 and FMA datasets, respectively, which significantly outperforms other mainstream automatic music generation models. In addition, the model reached 4.8 and 4.9 in perceived quality score (PQS), and 4.4 and 4.5 in user satisfaction score (USS), respectively. …”
Get full text

Discovery of Novel Inhibitors for Nek6 Protein through Homology Model Assisted Structure Based Virtual Screening and Molecular Docking Approaches by P. Srinivasan, P. Chella Perumal, A. Sudha

“…The three-dimensional structure of Nek6 was constructed by molecular modeling studies and the best model was further assessed by PROCHECK, ProSA, and ERRAT plot in order to analyze the quality and consistency of generated model. The overall quality of computed model showed 87.4% amino acid residues under the favored region. …”
Get full text

Adversarial example generation method for SAR images based on mask extraction by ZHANG Jianwu, NAI Hao, LI Jie, QIAN Jianhua, FANG Yinfeng

“…To solve the above problems, a SAR image adversarial sample generation model was proposed. The model was based on the AdvGAN model architecture. …”
Get full text

Single-cell RNA-seq data augmentation using generative Fourier transformer by Nima Nouri

“…Deep learning-based generative models (GMs) designed to address data scarcity often face similar limitations due to their reliance on pre-training or fine-tuning, inadvertently perpetuating a cycle of data inadequacy. …”
Get full text

A simplified computational liver perfusion model, with applications to organ preservation by Daniel Emerson, Yoed Rabin, Levent Burak Kara

“…Finally, we simulate steady state machine perfusion of the generated models and demonstrate how they can be used to quickly test the effect of different boundary conditions when designing organ preservation protocols.…”
Get full text

A review of university chatbots for student support: FAQs and beyond by Kevin Peyton, Saritha Unnikrishnan, Brian Mulligan

“…Finally, the review suggests approaches that take advantage of already existing data and newer generative models and frameworks that can help in the development of student focused chatbots.…”
Get full text

Optimisation of phytoremediation of zinc ion by Lemnaceae using response surface methodology by Tai Jia Wei, Pang Yean Ling, Lim Steven, Chong Woon Chan

“…Furthermore, the analysis of variance (ANOVA) was conducted to assess the adequacy and significance of the generated model. The optimal zinc ion removal of 88 % could be achieved by Spirodela polyrhiza, Wolffia arrhiza and Lemna minor at the initial zinc ion concentration of 92.92 mg/L, 39.5 mg/L, and 21.08 mg/L and duckweed mass of 22.56 g, 22.38 g, and 24.81 g under the exposure of ambient conditions with sufficient daylight exposure.…”
Get full text

Study on River System Flood Forecasting Scheme for Longtan Hydropower Station Interval in Hongshui River by DU Yong, FU Yupeng, WEI Yongjiang, LI Zongtai

“…Longtan Hydropower Station is a flood control project in the Pearl River Basin,but there is currently a lack of a comprehensive river system flood forecasting scheme.In order to give full play to the flood control and storage function of Longtan Hydropower Station,tributary control stations such as Leigongtan,Moyang,Pinglihe,Pinghu,and Xianrenqiao are selected,and the key areas of concern are determined through the analysis of important sub-intervals.The river system flood forecasting scheme for the Longtan Hydropower Station interval is constructed by using the Xin'an River three-source runoff generation model,three-source lag routing convergence model,and Maskingen convergence algorithm.The research results show that the proportion of the maximum inflow flood volume of Longtan Hydropower Station is usually in uncontrolled intervals,followed by the tributaries in Guizhou Province (Mengjiang River,Bawang River,Caodu River,and Liudong River),which are the focus of flood forecasting.The total average relative peak flow error and the average relative flood volume error in the river system flood forecasting scheme are both 10%,and the average deterministic coefficients are above 0.75.The overall results are relatively accurate.Therefore,the river system flood forecasting scheme for the Longtan Hydropower Station interval can be applied to real-time flood operation forecasting,and it lays a solid foundation for further improving the “forecast,early warning,rehearsal,and contingency plan” capability.…”
Get full text

Improving the Operational Methodology of Tropical Cyclone Seasonal Prediction in the Australian and the South Pacific Ocean Regions by J. S. Wijnands, K. Shelton, Y. Kuleshov

“…Correlation analysis and subsequent cross-validation of the generated models showed that the Dipole Mode Index (DMI) performs well as an explanatory variable for TC prediction in both AR and SPO, Niño4 SST anomalies—in AR and Niño1+2 SST anomalies—in SPO. …”
Get full text

Bubble Flow Analysis of High Speed Cylindrical Roller Bearing under Fluid-Solid Thermal Coupling by Li Cui, Wenxia Wang, Zhang Yanlei

“…Heat generation model of high speed cylindrical roller bearing is constructed by calculating the local friction in the bearing. …”
Get full text

Exploring Route Choice Behaviours Accommodating Stochastic Choice Set Generations by Shin-Hyung Cho, Seung-Young Kho

“…The reliability level is defined to explore the travellers’ heterogeneity in the choice set generation model. The heterogeneous K-reliable shortest path- (HKαRSP-) based route choice model is established to incorporate travellers’ heterogeneity in route choice behaviour. …”
Get full text

Advertisement Synthesis Network for Automatic Advertisement Image Synthesis by Qin Wu, Peizi Zhou

“…To solve this problem, this paper proposes a new two-stage automatic advertisement image generation model, called Advertisement Synthesis Network (ASNet), which explores a two-stage generation framework to synthesise consistent-looking product advertisement images. …”
Get full text

A New Wireless Generation Technology for Video Streaming by Sarmad K. Ibrahim, Nasser N. Khamiss

“…This research proposes a mobile generation model based on the updated technologies of the fourth- and fifth-generation mobile systems, which is called Proposed Generation (Pro-G). …”
Get full text

Image Inpainting of Portraits Artwork Design and Implementation by Zhang Hongting

“…In modern society, the restoration of artwork has become increasingly important. Generative models can provide reference images for the damaged or blurred core areas of these artworks. …”
Get full text