APPLICATION OF COMPRESSIVE SENSING AND IMPROVED DEEP WAVELET NEURAL NETWORK IN BEARING FAULT DIAGNOSIS by DU XiaoLei, CHEN ZhiGang, ZHANG Nan, XU Xu

“…Secondly,the improved wavelet auto-encoder was designed to construct the DWNN,and the " crosslayer" connection was introduced to alleviate the gradient disappearance of the network. …”
Get full text

Establishment and performance analysis of RIS-assisted coded relay cooperation system based on LDPC product codes by Shunwai ZHANG, Jin WANG

“…To pursue the ultra-reliable information transmission, the system which combined the reconfigurable intelligent surface (RIS) technology and coded relay cooperation technology was investigated.The RIS-assisted coded relay cooperation system model based on low density parity check (LDPC) product codes was established.Based on LDPC product codes, the information matrix was row-encoded by the source node and column-encoded by the relay node, respectively.An efficient joint iterative decoding algorithm was proposed.The two received signals at the destination were row-decoded and column-decoded iteratively to update the logarithmic likelihood ratios of information bits, and then the decoding decision was made.The closed-form solutions of the outage probability and the channel capacity with finite codelength were theoretically derived.Theoretical analysis and simulation results show that the proposed system obviously outperforms the traditional coded relay cooperation.The more number of RIS elements, the more significant advantage can be obtained.Simulation results also demonstrate that the channel capacity with finite codelength approaches the ideal channel capacity with the codelength of LDPC product codes increasing.…”
Get full text

Temporal dependent rate-distortion optimization based on distortion backward propagation by Hongwei GUO, Ce ZHU, Xu YANG, Lei LUO

“…Rate-distortion optimization (RDO) is a crucial technique in block based hybrid video encoders.However, the widely used independent RDO is far from obtaining optimal coding performance.To improve the rate-distortion (R-D) performance of high efficiency video coding (HEVC), a temporal dependent RDO algorithm was proposed.Firstly, the formula to calculate temporal distortion propagation factor was derived by using an exponential R-D function.Then, the coding distortion and motion compensation predicted error were obtained by pre-encoding, and the temporal distortion propagation factor was estimated by using distortion backward propagation.Finally, the Lagrange multiplier and quantization parameter of coding tree unit were adaptively adjusted to optimize bit resources allocation.Experimental results show that compared with the original RDO method in HEVC under the low-delay configuration, the proposed algorithm achieves an average 4.4% bit rate reduction for all test sequences, and up to 13.0% bit rate reduction for test sequence BasketballDrill, at the same reconstructed video quality.…”
Get full text

Deep Learning in Cybersecurity: A Hybrid BERT–LSTM Network for SQL Injection Attack Detection by Yixian Liu, Yupeng Dai

“…This paper presents a novel deep learning framework that integrates Bidirectional Encoder Representations from Transformers (BERT) and Long Short-Term Memory (LSTM) networks, enhancing the detection of SQL injection attacks. …”
Get full text

APT attack threat-hunting network model based on hypergraph Transformer by Yuancheng LI, Yukun LIN

“…To solve the problem that advanced persistent threat (APT) in the Internet of things (IoT) environment had the characteristics of strong concealment, long duration, and fast update iterations, it was difficult for traditional passive detection models to quickly search, a hypergraph Transformer threat-hunting network (HTTN) was proposed.The HTTN model had the function of quickly locating and discovering APT attack traces in IoT systems with long time spans and complicated information concealment.The input cyber threat intelligence (CTI) log graph and IoT system kernel audit log graph were encoded into hypergraphs by the model, and the global information and node features of the log graph were calculated through the hypergraph neural network (HGNN) layer, and then they were extracted for hyperedge position features by the Transformer encoder, and finally the similarity score was calculated by the hyperedge, thus the threat-hunting of APT was realized in the network environment of the Internet of things system.It is shown by the experimental results in the simulation environment of the Internet of things that the mean square error is reduced by about 20% compared to mainstream graph matching neural networks, the Spearman level correlation coefficient is improved by about 0.8%, and improved precision@10 is improved by about 1.2% by the proposed HTTN model.…”
Get full text

Domain-generalization human activity recognition model based on CSI instance normalization by WANG Yang, XU Jiawei, WANG Ao, XIA Huijuan, ZHAO Chuanxin, JI Yimu

“…By employing activity bias learning and adversarial domain learning, the model biased the features extracted from the encoding layer towards signal variations caused by human actions while moving away from domain signals. …”
Get full text

Prioritization of genes associated with the pathogenesis of leukosis in cattle by N. S. Yudin, N. L. Podkolodnyy, T. A. Agarkova, E. V. Ignatieva

“…The following criteria were used to prioritize 446 genes from the catalog: (1) the gene is associated with leukemia according to a genome-wide association study; (2) the gene is associated with leukemia according to a case-control study; (3) the role of the gene in leukemia development has been studied using knockout mice; (4) protein-protein interactions exist between the gene-encoded protein and either viral particles or individual viral proteins; (5) the gene is annotated with Gene Ontology terms that are overrepresented for a given list of genes; (6) the gene participates in biological pathways from the KEGG or REACTOME databases, which are over-represented for a given list of genes; (7) the protein encoded by the gene has a high number of protein-protein interactions with proteins encoded by other genes from the catalog. …”
Get full text

An automated privacy-preserving self-supervised classification of COVID-19 from lung CT scan images minimizing the requirements of large data annotation by Sadia Sultana Chowa, Md Rahad Islam Bhuiyan, Mst. Sazia Tahosin, Asif Karim, Sidratul Montaha, Md. Mehedi Hassan, Mohd Asif Shah, Sami Azam

“…Three subsets of the dataset are used to train the local BYOL model, which together optimizes the central encoder. The labeled dataset is employed to train the central encoder (updated VGG19 + attention CNN), resulting in an accuracy of 97.19%, a precision of 97.43%, and a recall of 98.18%. …”
Get full text

Assessment of biofilm formation, antibiotic resistance patterns, and the prevalence of adhesion-related genes in clinical Staphylococcus aureus isolates by Nabi Jomehzadeh, Sogol Seif Emrani

“…The most prevalent biofilm-encoding genes were icaA (76.7 %), followed by icaD (70 %), clfA (65.0 %), and fnbA (53.3 %). …”
Get full text

The pneumococcal bacteriocin streptococcin B is produced as part of the early competence cascade and promotes intraspecies competition by J. D. Richardson, Emily Guo, Ryan M. Wyllie, Paul Jensen, Suzanne Dawid

“…In this work, we demonstrate that three-fourths of S. pneumoniae strains contain a highly conserved scb locus that encodes an active lactococcin 972-like bacteriocin called streptococcin B. …”
Get full text

A U-Net-based denoising method for semi-airborne transient electromagnetic data and its application by Dong LIU, Hao FENG, Yongxin WANG, Xiaosheng ZHOU, Yuhong YAO, Huaifeng SUN

“…The encoder learns and extracts noise features from data, while the decoder reconstructs the noise features and restores denoised data. …”
Get full text

MFFTNet: A Novel 3D Point Cloud Segmentation Network Based on Multi-Scale Feature Fusion and Transformer Architecture by Hao Bai, Xiongwei Li, Qing Meng, Shulong Zhuo, Lili Yan

“…Specifically, MFFTNet divides the segmentation task into encoding and decoding stages. The encoder is designed as a hierarchical pyramid structure that extracts relatively sparse local center points and fuses local features during progressive downsampling. …”
Get full text

Screening and Whole-Genome Sequencing Analysis of Fructofuranose-Metabolizing Lactiplantibacillus plantarum 19M03 by SUN Daqing, QI He, DI Ziqing, GE Xianglin, HONG Qingping, DU Xinrui, YAO Yuxi, LI Hongfei

“…The results of gene function annotation showed that its genome sequence contained a total of 357 genes encoding carbohydrate-active enzymes (CAZymes) and 351 genes encoding carbohydrate transport proteins in the Clusters of Orthologous Groups of proteins (COGs), Gene Ontology (GO), Kyoto Encyclopedia of Genes and Genomes (KEGG) and CAZy databases, as well as 12 genes related to fructan metabolism and transport, respectively. …”
Get full text

A speech recognition method with enhanced transformer decoder by Hengbo Hu, Tong Niu, Zhenhua He

“…Experimental results on the Mandarin Aishell-1 dataset demonstrate that when the encoder is a Conformer, the enhanced decoder achieves a 16.1% reduction in character error rate compared to the Transformer decoder. …”
Get full text

Some New Constructions of Authentication Codes with Arbitration and Multi-Receiver from Singular Symplectic Geometry by You Gao, Huafeng Yu

“…The parameters are computed. Assuming that the encoding rules are chosen according to a uniform probability distribution, the probabilities of success for different types of deception are also computed.…”
Get full text

Diel changes in the expression of a marker gene and candidate genes for intracellular amorphous CaCO3 biomineralization in Microcystis by Bruley, Apolline, Gaëtan, Juliette, Gugger, Muriel, Pancrace, Claire, Millet, Maxime, Gaschignard, Geoffroy, Dezi, Manuela, Humbert, Jean-François, Leloup, Julie, Skouri-Panet, Fériel, Callebaut, Isabelle, Benzerara, Karim, Duprat, Elodie

“…Moreover, several genes directly co-localized upstream and downstream of ccyA, on the same DNA strand show a similar expression pattern, including a cax gene encoding a calcium/proton exchanger and a gene encoding a protein with a domain also present in the N-terminal region of calcyanins in many iACC-forming cyanobacteria. …”
Get full text

Akabane virus isolated from biting midges and its infection in local domestic animal, Yunnan, China: a field and laboratory investigation by Jinxin Meng, Yuwen He, Nan Li, Zhenxing Yang, Si Fu, Dongmei Wang, Aiguo Xin, Jinglin Wang, Guodong Liang

“…The S segment (856 nucleotides) encoded a 233-amino-acid nucleocapsid protein and a 91-amino-acid nonstructural protein, while the M segment (4309 nucleotides) encoded a 1401-amino-acid polyprotein. …”
Get full text

The β-Lactamase Gene Profile and a Plasmid-Carrying Multiple Heavy Metal Resistance Genes of Enterobacter cloacae by Chongyang Wu, Chaoqin Lin, Xinyi Zhu, Hongmao Liu, Wangxiao Zhou, Junwan Lu, Licheng Zhu, Qiyu Bao, Cong Cheng, Yunliang Hu

“…The extended-spectrum β-lactamases (ESBLs) (blaSHV-12 and blaCTX-M-9a) and AmpC (blaMIR) were encoded on the chromosome, and the pY546 plasmid contained several clusters of genes conferring resistance to metals, such as copper (pco), arsenic (ars), tellurite (ter), and tetrathionate (ttr), and genes encoding many divalent cation transporter proteins. …”
Get full text

Anomaly detection model for multivariate time series based on stochastic Transformer by Weigang HUO, Rui LIANG, Yonghua LI

“…Aiming at the problem that the existing multivariate time series anomaly detection models based on variational autoencoders could not propagate long-term temporal dependencies between stochastic variables in latent space, the stochastic Transformer for MTS anomaly detection (ST-MTS-AD) model which combined Transformer encoder with VAE was proposed.In the inference network of the ST-MTS-AD, the MTS long-term temporal dependent features generated by Transformer encoder and the sampled values of the stochastic variables at the previous moment were inputted into the multilayer perceptron, the approximate posterior distribution of the stochastic variables at the current moment was generated by the multilayer perceptron, and the temporal dependencies between stochastic variables were realized.The gated transition function(GTF) was used to generate the prior distribution of stochastic variables.The generation network of the ST-MTS-AD reconstructed the distribution of the MTS values at each moment by the multilayer perceptron whose input was the MTS long-term temporal dependent features generated by the inference network and the approximate posterior sampling values of stochastic variables.The distribution of normal MTS dataset was learned by the variational inference technology, and the abnormal MTS segment was determined by the log-likelihood of the reconstruction probability.Experiments on four public datasets show that the ST-MTS-AD model significantly improves the F1 score over the typical baseline models.…”
Get full text

Low-Rank Variational Quantum Algorithm for the Dynamics of Open Quantum Systems by Sara Santos, Xinyu Song, Vincenzo Savona

“…Here, a variational quantum algorithm is developed to simulate the real-time evolution of the density matrix governed by the Lindblad master equation, under the assumption that the quantum state has a bounded entropy along the dynamics, entailing a low-rank representation of its density matrix. The algorithm encodes each pure state of the statistical mixture as a parametrized quantum circuit, and the associated probabilities as additional variational parameters stored classically, thereby requiring a significantly lower number of qubits than algorithms where the full density matrix is encoded in the quantum memory. …”
Get full text