|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | Humoral immune response to circulating SARS-CoV-2 variants elicited by inactivated and RBD-subunit vaccines显示文摘SARS-CoV-2 variants could induce immune escape by mutations on the receptor-binding domain(RBD)and N-terminal domain(NTD).Here we report the humoral immune response to circulating SARS-CoV-2 variants,such as 501Y.V2(B.1.351),of the plasma and neutralizing antibodies(NAbs)elicited by CoronaVac(inactivated vaccine),ZF2001(RBD-subunit vaccine)and natural infection.Among 86 potent NAbs identified by high-throughput single-cell VDJ sequencing of peripheral blood mononuclear cells from vaccinees and convalescents,near half anti-RBD NAbs showed major neutralization reductions against the K417N/E484K/N501Y mutation combination,with E484K being the dominant cause.VH3-53/VH3-66 recurrent antibodies respond differently to RBD variants,and K417N compromises the majority of neutralizing activity through reduced polar contacts with complementarity determining regions.In contrast,the 242–244 deletion(242–244Δ)would abolish most neutralization activity of anti-NTD NAbs by interrupting the conformation of NTD antigenic supersite,indicating a much less diversity of anti-NTD NAbs than anti-RBD NAbs.Plasma of convalescents and CoronaVac vaccinees displayed comparable neutralization reductions against pseudo-and authentic 501Y.V2 variants,mainly caused by E484K/N501Y and 242–244Δ,with the effects being additive.Importantly,RBD-subunit vaccinees exhibit markedly higher tolerance to 501Y.V2 than convalescents,since the elicited anti-RBD NAbs display a high diversity and are unaffected by NTD mutations.Moreover,an extended gap between the third and second doses of ZF2001 leads to better neutralizing activity and tolerance to 501Y.V2 than the standard three-dose administration.Together,these results suggest that the deployment of RBD-vaccines,through a third-dose boost,may be ideal for combating SARS-CoV-2 variants when necessary,especially for those carrying mutations that disrupt the NTD supersite. | Yunlong Cao Ayijiang Yisimayi Yali Bai Weijin Huang Xiaofeng Li Zhiying Zhang Tianjiao Yuan Ran An Jing Wang Tianhe Xiao Shuo Du Wenping Ma Liyang Song Yongzheng Li Xiang Li Weiliang Song Jiajing Wu Shuo Liu Xuemei Li Yonghong Zhang Bin Su Xianghua Guo Yangyang Wei Chuanping Gao Nana Zhang Yifei Zhang Yang Dou Xiaoyu Xu Rui Shi Bai Lu Ronghua Jin Yingmin Ma Chengfeng Qin Youchun Wang Yingmei Feng Junyu Xiao Xiaoliang Sunney Xie | 2021 | Cell Research2021，31，7： | 12 |
| 2 | Advanced liquid crystal devices for augmented reality and virtual reality displays:principles and applications显示文摘Liquid crystal displays(LCDs)and photonic devices play a pivotal role to augmented reality(AR)and virtual reality(VR).The recently emerging high-dynamic-range(HDR)mini-LED backlit LCDs significantly boost the image quality and brightness and reduce the power consumption for VR displays.Such a light engine is particularly attractive for compensating the optical loss of pancake structure to achieve compact and lightweight VR headsets.On the other hand,high-resolution-density,and high-brightness liquid-crystal-on-siilicon(LCoS)is a promising image source for the see-through AR displays,especially under high ambient lighting conditions.Meanwhile,the high-speed LCoS spatial light modulators open a new door for holographic displays and focal surface displays.Finally,the ultrathin planar diffractive LC optical elements,such as geometric phase LC grating and lens,have found useful applications in AR and VR for enhancing resolution,widening fiield-of-view,suppressing chromatic aberrations,creating multiplanes to overcome the vergence-accommodation conflict,and dynamic pupil steering to achieve gaze-matched Maxwellian displays,just to name a few.The operation principles,potential applications,and future challenges of these advanced LC devices will be discussed. | Kun Yin En-Lin Hsiang Junyu Zou Yannanqi Li Zhiyong Yang Qian Yang Po-Cheng Lai Chih-Lung Lin Shin-Tson Wu | 2022 | Light(Science & Applications)2022，11，7： | 6 |
| 3 | A novel selective autophagy receptor,CCDC50,delivers K63 polyubiquitination-activated RIG-I/MDA5 for degradation during viral infection显示文摘Autophagy is a con served process that delivers cytosolic substa nces to the lysosome for degradatio n,but its direct role in the regulation of antiviral inn ate immu nity remains poorly un derstood.Here,through high-throughput screeni ng,we discovered that CCDC50 functions as a previously unknown autophagy receptor that negatively regulates the type I interferon(IFN)signaling pathway initiated by RIG-I-like receptors(RLRs),the sensors for RNA viruses.The expression of CCDC50 is enhanced by viral infection,and CCDC50 specifically recognizes K63-polyubiquitinated RLRs,thus delivering the activated RIG-I/MDA5 for autophagic degradation.The associatio n of CCDC50 with phagophore membrane protei n LC3 is con firmed by crystal structure analysis.In contrast to other known autophagic cargo receptors that associate with either the LIR-docking site(LDS)or the UIMdocking site(UDS)of LC3,CCDC50 can bind to both LDS and UDS,representing a new type of cargo receptor.In mouse models with RNA virus infection,CCDC50 deficiency reduces the autophagic degradation of RIG-I/MDA5 and promotes type I IFN responses,resulting in enhaneed viral resistance and improved survival rates.These results reveal a new link between autophagy and antiviral innate immune resp on ses and provide additional in sights into the regulatory mecha nisms of RLR-mediated antiviral signaling. | Panpan Hou Kongxiang Yang Penghui Jia Lan Liu Yuxin Lin Zibo Li Jun Li Shuliang Chen Shuting Guo Ji'An Pan Junyu Wu Hong Peng Weijie Zeng Chunmei Li Yingfang Liu Deyin Guo | 2021 | Cell Research2021，31，1： | 5 |
| 4 | Ternary organic solar cells based on polymer donor,polymer acceptor and PCBM components显示文摘In this work,ternary organic solar cells(OSCs)combining a fullerene derivative PC71BM with a nonfullerene acceptor N2200-F blended with a polymer donor PM6 were reported.Compared with the binary systems,the highest power conversion efficiency(PCE)of 8.11%was achieved in ternary solar cells with 30 wt%N2200-F content,mainly due to the improved short-circuit current density(Jsc)and fill factor(FF).Further studies showed that the improved Jsc could attribute to the complementary abso rption of the two acceptors and the enhanced FF was originated from the higher hole mobility and the fine-tuned morphology in the ternary system.These results demonstrate that the combination of fullere ne and nonfullerene acceptors in ternary organic solar cells is a promising approach to achieve high-performance OSCs. | Feng Liu Cheng Li Junyu Li Chao Wang Chengyi Xiao Yonggang Wu Weiwei Li | 2020 | Chinese Chemical Letters2020，31，3： | 3 |
| 5 | Enlightenment from the COVID-19 Pandemic:The Roles of Environmental Factors in Future Public Health Emergency Response显示文摘The coronavirus disease 2019(COVID-19)pandemic is challenging the current public health emergency response systems(PHERSs)of many countries.Although environmental factors,such as those influencing the survival of viruses and their transmission between species including humans,play important roles in PHERSs,little attention has been given to these factors.This study describes and elucidates the roles of environmental factors in future PHERSs.To improve countries’capability to respond to public health emergencies associated with viral infections such as the COVID-19 pandemic,a number of environmental factors should be considered before,during,and after the responses to such emergencies.More specifically,to prevent pandemic outbreaks,we should strengthen environmental and wildlife protection,conduct detailed viral surveillance in animals and hotspots,and improve early-warning systems.During the pandemic,we must study the impacts of environmental factors on viral behaviors,develop control measures to minimize secondary environmental risks,and conduct timely assessments of viral risks and secondary environmental effects with a view to reducing the impacts of the pandemic on human health and on ecosystems.After the pandemic,we should further strengthen surveillance for viruses and the prevention of viral spread,maintain control measures for minimizing secondary environmental risks,develop our capability to scientifically predict pandemics and resurgences,and prepare for the next unexpected resurgence.Meanwhile,we should restore the normal life and production of the public based on the“One Health”concept,that views global human and environmental health as inextricably linked.Our recommendations are essential for improving nations’capability to respond to global public health emergencies. | Xiaolei Wang Fengchang Wu Xiaoli Zhao Xiao Zhang Junyu Wang Lin Niu Weigang Liang Kenneth Mei Yee Leung John P.Giesy | 2022 | Engineering2022，8，1： | 2 |
| 6 | PTEN suppresses tumorigenesis by directly dephosphorylating Akt显示文摘Dear Editor,The serine-threonine kinase Akt plays a central role in regulating cell proliferation,migration,angiogenesis,transformation,energy metabolism,and death.1 The stimulation of growth factors recruits the PI3K to the plasma membrane and phosphatidylinositol-3A5-trisphosphate(PIP3),which in turn recruits Akt to the plasma membrane through PH domain of Akt. | Lang Bu Huan Wang Ji-an Pan Lang Chen Fan Xing Junyu Wu Shun Li Deyin Guo | 2021 | Signal Transduction and Targeted Therapy2021，6，8： | 2 |
| 7 | Spatiotemporal Mapping of Salt Marshes in the Intertidal Zone of China during 1985-2019显示文摘This study mapped the areal extent,identified the species composition,and analyzed the changes of salt marshes in the intertidal zone of China during the period 1985–2019.With the aid of the cloud platform of the Google Earth Engine,we selected Landsat 5/8 and Sentinel-2 images and used the support vector machine classification method to extract salt marsh information for the years of 1985,1990,1995,2000,2005,2010,2015,and 2019.Seven major species of salt marshes:Phragmites australis,Suaeda spp.,Spartina alterniflora,Scirpus mariqueter,Tamarix chinensis,Cyperus malaccensis,and Sesuvium portulacastrum were identified.Our results showed that salt marshes are mainly distributed in Liaoning,Shandong,Jiangsu,Shanghai,and Zhejiang,with varying patterns of shrinking,expansion,or wavering in different places.The distribution of salt marshes has declined considerably from 151,324 ha in 1985 to 115,397 ha in 2019,a drop of 23.7%.During the same period,the area of native species has dropped 95.4%from 77,741 ha to 3,563 ha for Suaeda spp.and 45.1%from 60,511 ha to 33,193 ha for P.australis;on the contrary,the area of exotic species,S.alterniflora,has exhibited a sharp rise from just 99 ha to 67,527 ha.For the past 35 years,the driving factors causing salt marsh changes are mainly land reclamation,variations in water and sand fluxes,and interspecific competition and succession of salt marsh vegetation.These results provide fundamental reference information and could form the scientific basis for formulating policies for the conservation and utilization of salt marsh resources in China. | Guangwei Chen Runjie Jin Zhanjiang Ye Qi Li Jiali Gu Min Luo Yongming Luo George Christakos James Morris Junyu He Dan Li Hengwei Wang Li Song Qiuxuan Wang Jiaping Wu | 2022 | Journal of Remote Sensing2022，，1： | 2 |
| 8 | Non-Structural Protein 5 of Zika Virus Interacts with p53 in Human Neural Progenitor Cells and Induces p53-Mediated Apoptosis显示文摘Zika virus(ZIKV) infection could disrupt neurogenesis and cause microcephaly in neonates by targeting neural progenitor cells(NPCs). The tumor suppressor p53-mediated cell cycle arrest and apoptotic cell death have been suggested to be activated upon ZIKV infection, yet the detailed mechanism is not well understood. In the present study, we investigated the effects of ZIKV-encoded proteins in the activation of p53 signaling pathway and found that, among the ten viral proteins,the nonstructural protein 5(NS5) of ZIKV most significantly activated the transcription of p53 target genes. Using the immunoprecipitation-coupled mass spectrometry approach, we identified that ZIKV-NS5 interacted with p53 protein. The NS5-p53 interaction was further confirmed by co-immunoprecipitation and GST pull-down assays. In addition, the MTase domain of NS5 and the C-terminal domain of p53 were mapped to be responsible for the interaction between these two proteins. We further showed that ZIKV-NS5 was colocalized with p53 and increased its protein level in the nuclei and able to prolong the half-life of p53. Furthermore, lentivirus-mediated expression of ZIKV-NS5 in hNPCs led to an apparent cell death phenotype. ZIKV-NS5 promoted the cleavage of PARP1 and significantly increased the cell apoptosis of h NPCs.Taken together, these findings revealed that ZIKV-NS5 is a previously undiscovered regulator of p53-mediated apoptosis in hNPCs, which may contribute to the ZIKV-caused abnormal neurodevelopment. | Ping Li Hualian Jiang Hong Peng Weijie Zeng Yongheng Zhong Miao He Luyang Xie Junhai Chen Deyin Guo Junyu Wu Chun-Mei Li | 2021 | Virologica Sinica2021，36，6： | 2 |
| 9 | Domi-nance-based rough set approach and knowledge reduetions in incomplete ordered information system显示文摘 | Xibei Yang Jingyu Yang Chen Wu Dong junYu | | 0，，04： | 1 |
| 10 | Chemical characterization of Artemisia seed polysaccharide显示文摘 | ZHANG Ji WU Jian LIANG Junyu | 2007 | Carbohydrate Polymers2007，67，2： | 1 |
| 11 | Pancreatic melatonin enhances anti-tumor immunity in pancreatic adenocarcinoma through regulating tumor-associated neutrophils infiltration and NETosis显示文摘Tumor microenvironment contributes to poor prognosis of pancreatic adenocarcinoma(PAAD)patients.Proper regulation could improve survival.Melatonin is an endogenous hormone that delivers multiple bioactivities.Here we showed that pancreatic melatonin level is associated with patients'survival.In PAAD mice models,melatonin supplementation suppressed tumor growth,while blockade of melatonin pathway exacerbated tumor progression.This anti-tumor effect was independent of cytotoxicity but associated with tumor-associated neutrophils(TANs),and TANs depletion reversed effects of melatonin.Melatonin induced TANs infiltration and activation,therefore induced cell apoptosis of PAAD cells.Cytokine arrays revealed that melatonin had minimal impact on neutrophils but induced secretion of Cxcl2 from tumor cells.Knockdown of Cxcl2 in tumor cells abolished neutrophil migration and activation.Melatonin-induced neutrophils presented an N1-like anti-tumor phenotype,with increased neutrophil extracellular traps(NETs)causing tumor cell apoptosis through cell-to-cell contact.Proteomics analysis revealed that this reactive oxygen species(ROS)-mediated inhibition was fueled by fatty acid oxidation(FAO)in neutrophils,while FAO inhibitor abolished the anti-tumor effect.Analysis of PAAD patient specimens revealed that CXCL2 expression was associated with neutrophil infiltration.CXCL2,or TANs,combined with NET marker,can better predict patients'prognosis.Collectively,we discovered an anti-tumor mechanism of melatonin through recruiting N1-neutrophils and beneficial NET formation. | Yau-tuen Chan Hor-yue Tan Yuanjun Lu Cheng Zhang Chien-shan Cheng Junyu Wu Ning Wang Yibin Feng | 2023 | Acta Pharmaceutica Sinica B2023，13，4： | 1 |
| 12 | Development and validation of a machine learning-based nomogram for prediction of intrahepatic cholangiocarcinoma in patients with intrahepatic lithiasis显示文摘Background:Accurate diagnosis of intrahepatic cholangiocarcinoma(ICC)caused by intrahepatic lithiasis(IHL)is crucial for timely and effective surgical intervention.The aim of the present study was to develop a nomogram to identify ICC associated with IHL(IHL-ICC).Methods:The study included 2,269 patients with IHL,who received pathological diagnosis after hepatectomy or diagnostic biopsy.Machine learning algorithms including Lasso regression and random forest were used to identify important features out of the available features.Univariate and multivariate logistic regression analyses were used to reconfirm the features and develop the nomogram.The nomogram was externally validated in two independent cohorts.Results:The seven potential predictors were revealed for IHL-ICC,including age,abdominal pain,vomiting,comprehensive radiological diagnosis,alkaline phosphatase(ALK),carcinoembryonic antigen(CEA),and cancer antigen(CA)19-9.The optimal cutoff value was 2.05μg/L for serum CEA and 133.65 U/mL for serum CA 19-9.The accuracy of the nomogram in predicting ICC was 82.6%.The area under the curve(AUC)of nomogram in training cohort was 0.867.The AUC for the validation set was 0.881 from The Second Affiliated Hospital of Wenzhou Medical University,and 0.938 from The First Affiliated Hospital of Fujian Medical University.Conclusions:The nomogram holds promise as a novel and accurate tool to predict IHL-ICC,which can identify lesions in IHL in time for hepatectomy or avoid unnecessary surgical resection. | Xian Shen Huanhu Zhao Xing Jin Junyu Chen Zhengping Yu Kuvaneshan Ramen Xiangwu Zheng Xiuling Wu Yunfeng Shan Jianling Bai Qiyu Zhang Qiqiang Zeng | 2021 | Hepatobiliary Surgery and Nutrition2021，10，6： | 1 |
| 13 | Chemical characterization of Artemisia seed polysaccharide显示文摘 | ZHANG Ji WU Jian LIANG Junyu | 2007 | Carbohydrate Polymers2007，67，： | 1 |
| 14 | The influence of genetic polymorphisms in drug metabolism enzymes and transporters on the pharmacokinetics of different fluvastatin formulations显示文摘The purpose of the present study was to investigate the impact of genetic polymorphism on fluvastatin pharmacokinetics.In addition,we compared the fluvastatin pharmacokinetics differences between extended-release(ER)80 mg tablet and immediate-release(IR)40 mg capsule in terms of drug metabolism enzyme and transporter genetic polymorphisms.In this open-label,randomized,two-period,two-treatment,crossover study(n=24),effects of ABCG2,SLCO1B1,ABCB1,CYP2C9 and CYP3A5 polymorphisms on the pharmacokinetics of fluvastatin were analyzed.The administration dosage for IR 40 mg and ER 80 mg were twice and once daily,respectively,for total 7 d.Blood samples for pharmacokinetic evaluation were taken on the 1st and 7th d.The lower exposure following ER was observed.For ER tablets,SLCO1B1 T521C genotype correlated with AUC 0-24 of repeat doses(P=0.010).SLCO1B1 T521C genotype had no statistically significant effect on AUC 0-24 of IR capsule of fluvastatin after single or repeated doses.In vitro study demonstrated that when the concentration of fluvastatin was low(<1μmol/l),the uptake of fluvastatin in the HEK293-OATP1B1 with SLCO1B1521TT(K m=0.18μmol/l)was faster than that with SLCO1B1521CC(K m=0.49μmol/l),On the other hand,when concentration reached to higher level(>1μmol/l),transport velocity of fluvastatin by HEK293-OATP1B1 with SLCO1B1521TT(K m=11.4μmol/l)and with SLCO1B1521TCC(K m=15.1μmol/l)tend to be the same.It suggests that the increased effect of SLCO1B1 T521C genotype on ER formulation of fluvastatin was mainly caused by lower blood concentrations.We recommend that formulation should be incorporated into future pharmacogenomics studies. | Qian Xiang Weidang Wu Nan Zhao Chuan Li Junyu Xu Lingyue Ma Xiaodan Zhang Qiufen Xie Zhuo Zhang Jiancheng Wang Weiren Xu Xia Zhao Yimin Cui | 2020 | Asian Journal of Pharmaceutical Sciences2020，15，2： | 1 |
| 15 | Two-dimensional multiple nonhomogeneous harmonic equation and its boundary integral equations显示文摘 | TAN JUNYU WU YONG ZHANG LINHUA | 2007 | Applied Mathematics and Computation2007，187，： | 1 |
| 16 | Deactivation of Cu-SAPO-34 by urea-related deposits at low temperatures and the regeneration显示文摘Selective catalytic reduction(SCR) with urea catalyzed by Cu-SAPO-34 is an effective method to eliminate NO_x from diesel exhaust. However, urea-related deposits may form during cold-start and urban driving due to low exhaust temperatures. The activity of CuSAPO-34 at 175°C is significantly degraded by urea exposure, and 300°C is required for regeneration. Through in-situ diffuse reflectance infrared Fourier transform spectroscopy(DRIFTS) and temperature-programmed hydrolysis studies, the dominant stable deposit at 175°C is identified as biuret, which can be eliminated at 300°C. The urea-derived deactivation and regeneration mechanisms of Cu-SAPO-34 were compared with those of anatase-supported catalysts. | Yue Ma Xiaodong Wu Junyu Zhang Rui Ran Zhichun Si Duan Weng | 2019 | Journal of Environmental Sciences2019，31，7： | 1 |
| 17 | Deep reinforcement learning based worker selection for distributed machine learning enhanced edge intelligence in internet of vehicles显示文摘Nowadays,Edge Information System(EIS)has received a lot of attentions.In EIS,Distributed Machine Learning(DML),which requires fewer computing resources,can implement many artificial intelligent applications efficiently.However,due to the dynamical network topology and the fluctuating transmission quality at the edge,work node selection affects the performance of DML a lot.In this paper,we focus on the Internet of Vehicles(IoV),one of the typical scenarios of EIS,and consider the DML-based High Definition(HD)mapping and intelligent driving decision model as the example.The worker selection problem is modeled as a Markov Decision Process(MDP),maximizing the DML model aggregate performance related to the timeliness of the local model,the transmission quality of model parameters uploading,and the effective sensing area of the worker.A Deep Reinforcement Learning(DRL)based solution is proposed,called the Worker Selection based on Policy Gradient(PG-WS)algorithm.The policy mapping from the system state to the worker selection action is represented by a deep neural network.The episodic simulations are built and the REINFORCE algorithm with baseline is used to train the policy network.Results show that the proposed PG-WS algorithm outperforms other comparation methods. | Junyu Dong Wenjun Wu Yang Gao Xiaoxi Wang Pengbo Si | 2020 | Intelligent and Converged Networks2020，1，3： | 1 |
| 18 | Development and Validation of a Metabolic-related Prognostic Model for Hepatocellular Carcinoma显示文摘Background and Aims:Growing evidence suggests that metabolic-related genes have a significant impact on the occurrence and development of hepatocellular carcinoma(HCC).However,the prognostic value of metabolic-related genes for HCC has not been fully revealed.Methods:mRNA sequencing and clinical data were obtained from The Cancer Genome Atlas and the GTEx Genotype-Tissue Expression comprehensive database.Differentially expressed metabolic-related genes in tumor tissues(n=374)and normal tissues(n=160)were identified by the Wilcoxon test.Time-dependent receiver operating characteristic curve analysis,univariate multivariate Cox regression analysis and Kaplan-Meier survival analysis were used to evaluate the predictive effectiveness and independence of the prognostic model.Two independent cohorts(International Cancer Genome Consortiums and GSE14520)were applied to verify the prognostic model.Results:Our study included a total of 793 patients with HCC.We constructed a risk score consisting of five metabolic-genes(BDH1,RRM2,CYP2C9,PLA2G7,and TXNRD1).For the overall survival rate,the low-risk group had a considerably higher rate than the high-risk group.Univariate and multivariate Cox regression analyses indicated that the risk score was an independent predictor for the prognosis of HCC.Conclusions:We constructed and validated a novel prognostic model,which may provide support for the precise treatment of HCC. | Junyu Huo Liqun Wu Yunjin Zang | 2021 | Journal of Clinical and Translational Hepatology2021，9，2： | 1 |
| 19 | Synergistic Combination of Biodegradable Peptide Polymer and Curcumin as Promising Antibiotic Substitution in Aquaculture to Alleviate the Global Challenge of Antimicrobial Resistance显示文摘The massive use of antibiotics in aquaculture and resulted antibacterial resistance problem urgently need antibiotic substitutions. Herein, we report a promising substitution of aquaculture antibiotics using a synergistic combination of biodegradable peptide polymers and curcumin, a natural compound from plant. The synergistic combination shows strong antibacterial activity against V. fluvialis and some other common bacteria in aquaculture. The membrane-damaging antibacterial mechanism echoes our finding that the synergistic combination will not induce bacteria to develop resistance after continuous use. The synergistic combination also displays effective cure on V. fluvialis-infected zebrafish. The biodegradability of the peptide polymer enables the combination to lose antibacterial activity and will not cause selective pressure on bacterial in the environment. Our study indicates potential application of synergistic composition, biodegradable peptide polymer and curcumin, as promising antibiotic substitution in aquaculture, which represents a promising strategy to address the global challenge of antimicrobial resistance. | Pengcheng Ma Yuan Chen Ning Shao Junyu Zhang Yueming Wu Runhui Liu | 2022 | Chinese Journal of Chemistry2022，40，24： | 1 |
| 20 | Hybrid Optimization-Based GRU Neural Network for Software Reliability Prediction显示文摘Aiming at the problems of low prediction accuracy and weak generalization ability of current reliability prediction models,this paper proposes a hybrid multi-layer heterogeneous particle swarm optimization algorithm(HMHPSO)that can simultaneously optimize the structure and parameters of the GRU neural network.It first introduced a multi-layer heteromass particle swarm optimization(MHPSO)algorithm,which sets the population topology as a hierarchical structure and introduces the concept of attractors,so as to improve the update formula of particle speed,and enhance the information interaction ability between particles,increase the diversity of the groups,thereby improving the optimization ability of the algorithm.Then the HMHPSO used the quantum particle swarm optimization(QPSO)algorithm to determine the structure of the GRU,that is,the number of hidden nodes.Experimental results show that the algorithm can generate GRU neural networks with high generalization performance and low architecture complexity,and has better prediction accuracy in software reliability prediction. | Maochuan Wu Junyu Lin Shouchuang Shi Long Ren Zhiwen Wang | 2020 | 国际计算机前沿大会会议论文集2020，，2： | 0 |
您所在的机构暂未开通此部分的功能，请联系管理员