检索结果-南通市图书馆

维普期刊数据库

Mitigate noisy data for smart IoT via GAN based machine unlearning

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第3期67卷 62-78页

作者： Zhuo MA Yilong YANG Yang LIU xinjing LIU Jianfeng MA School of Cyber Engineering Xidian University State Key Laboratory of Integrated Services Networks (ISN)

With the development of IoT applications, machine learning dramatically improves the utility of variable IoT systems such as autonomous driving. Although the pretrain-finetune framework can cope well with data heterogeneity in complex IoT scenarios, the data collected by sensors often contain unexpected noisy data, e.g., out-of-distribution(OOD) data, which leads to the reduced performance of fine-tuned models. To resolve the problem, this paper proposes Mu GAN, a method that can mitigate the side-effect of OOD data via the generative adversarial network(GAN)-based machine unlearning. Mu GAN follows a straightforward but effective idea to mitigate the performance loss caused by OOD data, i.e., “flashbacking” the model to the condition where OOD data are excluded from model training. To achieve the goal, we design an adversarial game, where a discriminator is trained to identify whether a sample belongs to the training set by observing the confidence score. Meanwhile, a generator(i.e., the target model) is updated to fool the discriminator into believing that the OOD data are not included in the training set but others do. The experimental results show that benefiting from the high unlearning rate(more than 90%) and retention rate(99%), Mu GAN succeeds in lowering the model performance degradation caused by OOD data from 5.88% to 0.8%.

关键词： machine unlearning generative adversarial network out of distribution data Internet of Thing neural network

同方期刊数据库

Synthesis of Site specifically Phosphate-caged siRNAs and Evaluation of their RNAi Activity and Stability

在线全文

学校读者我要写书评

暂无评论

Synthesis of Site specifically Phosphate-caged siRNAs and Ev...

A Photochemical Avenue to Photoluminescence Nitrogen Rich Quantum Dots（N-dots）

中国化学会第29届学术年会

作者： xinjing tang State Key Laboratory of Natural and Biomimetic Drugs the School of Pharmaceutical SciencesPeking University

＜正＞A complete set of new photolabile nucleoside phosphoramidites were synthesized and then site-specifically incorporated in a siRNA strands for phosphate *** caging modification was made along siRNA strands and their photomodulation of gene silencing were *** key phosphate positions were then *** multiple caging modifications at these key positions led to significantly enhanced photomodulation of gene

关键词：

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

A Photochemical Avenue to Photoluminescence Nitrogen Rich Qu...

Reduce off-target effect of RNA interference with circular siRNAs

中国化学会第30届学术年会-第二十七分会：光化学

作者： Qingqing Jin xinjing tang School of Pharmaceutical Sciences Peking University

Quantum dots have been widely studied since 1990 s owing to their useful electronic and photonic *** our previous work, we discovered a nitrogen rich quantum dots（N-dots, up to 34% nitrogen and 10% more nitrogen than carbon element） by heating 2-azidoimidizole in methanol or aqueous solution and these N-dots showed excellent photoluminescence properties. Now, we, for the first time, demonstrated a photochemical avenue to synthesize N-dots from a small organic molecule, and further proposed a mechanism of N-dots *** N-dots could easily collected and the yield of collected N-dots was up to 92.7%, which was higher than that of thermodynamic preparation of *** N-dots have a small size（less than 10 nm） and contain a high percentage of the element nitrogen up to 35.70%, and show unique and distinct photoluminescence *** the N-dots were characterized by FTIR, HRTEM, and AFM,and their optical properties were evaluated in detail. These N-dots have also shown promising applications in two-photon fluorescence imaging.

关键词： bioimaging quantum dots N-Dots

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Reduce off-target effect of RNA interference with circular s...

An economic way to achieve all-weather CO2 reduction

中国化学会第30届学术年会-第二十八分会：化学生物学

作者： Yuan Wang xinjing tang State Key Laboratory of Natural and Biomimetic Drugs Peking University

Small interfering RNAs（siRNAs）play important roles in gene function study and drug ***,chemical modifications of siRNAs on backbone have been intensively investigated to increase the stability and specificity,*** of off-target effect of ***,we developed a novel type of circular siRNAs that are synthesized by cyclizing two ends of a single strand RNA（sense or antisense）using a T4 RNA *** newly synthesized circular siRNAs were more resistant to the degradation at the presence of SPVD or RNase *** addition,siRNA with circular antisense strand showed little effect on gene silencing,but siRNA with circular sense stand successfully knocked down gene expression of GFP or Luciferase in HEK293 *** results show that this new promising strategy could be used to overcome the off-target effect of strand selection on RNAi induced gene target.

关键词： siRNA circular RNA off-target effect gene expression

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

National Science Review 2024年第3期11卷 46-47页

作者： Junwang tang Department of Chemical Engineering University College London

Utilising solar power to convert carbon dioxide（CO2） into hydrocarbon fuels presents an eco-friendly method to address dependence on fossil fuels and contribute to a net-zero CO2emission goal[1,2].

关键词：

Highly effective design of high GFA alloys with different metalbased and various components by machine learning

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Science China(Technological Sciences) 2024年第5期67卷 1431-1442页

作者： tang YiChuan HE YiFan FAN ZhuoQun WANG ZhongQi tang ChengYing Guangxi Key Laboratory for Informational Materials School of Materials Science and EngineeringGuilin University of Electronic TechnologyGuilin541004China

The glass-forming ability(GFA)is of great significance for the development of novel functional metal-based metallic *** this study,seven popular machine learning(ML)algorithms were employed to design novel M-based(M=Fe,Co,Ni,Ti,Zr,and rare earth metal(RE))and X-component(X=2,3,4,5,6,and>6)alloys with excellent GFA.A GFA containing 6957 data points with structural analysis was *** engineering was used to analyze the importance and correlation of *** algorithms were utilized for GFA prediction,revealing that Xtreme Gradient Boosting Trees exhibited the strongest predictive capability,achieving a high accuracy of 94.0%,a true positive rate of 97.6%,and a root mean squared error of 0.3705 across the entire ***,the GFA of ternary to hexahydroxy alloys based on Fe,Co,Ni,Zr,Ti,and Y was predicted using all possible compositions generated through ***,a series of alloys with good GFA was successfully designed and *** present work suggests that the proposed ML method can be utilized to design novel multiple-M-based amorphous alloys with high GFA.

关键词： machine learning amorphous alloy feature engineering materials design glass forming ability

维普期刊数据库

Bazi Bushen alleviates reproductive aging in aged male mice

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Natural Medicines 2024年第5期22卷 416-425页

作者： MA Kun LI Mengnan SONG Yahui MAO xinjing ZHANG Shaolan ZHANG Yaping JIANG Yuning JI Chuanyuan NIU Kunxu LI Hongrong HOU Yunlong WEI Cong Graduate School Hebei University of Chinese MedicineShijiazhuang 050091China State Key Laboratory for Innovation and Transformation of Luobing Theory Shijiazhuang 050035China Key Laboratory of State Administration of TCM(Cardio-Cerebral Vessel Collateral Disease) Shijiazhuang 050035China College of Traditional Chinese Medicine·College of Integrated Traditional Chinese and Western Medicine Nanjing University of Chinese MedicineNanjing 210023China Hebei Provincial Key Laboratory of Luobing Shijiazhuang 050035China Key Disciplines of State Administration of TCM for Luobing Shijiazhuang 050035China

Bazi Bushen(BZBS),a traditional Chinese medicine(TCM),has demonstrated therapeutic efficacy in testicular dysfunction within D-galactose and NaNO_(2)mouse *** study aimed to ascertain if BZBS could also mitigate the decline in testicular function associated with natural ***,male aged mice were employed to evaluate the preventive effects of BZBS on male reproductive *** was achieved by assessing sex hormone production,testicular histomorphology,and *** to the untreated aged control group,BZBS administration elevated the levels of sex hormones and spermatocyte populations and preserved normal testicular structure in aged ***,spermatogenesis was *** analyses,including malondialdehyde(MDA)assays and real-time PCR,indicated that BZBS diminished testicular oxidative stress and the inflammatory *** these findings,mice treated with BZBS exhibited reductions in the populations of senescent and apoptotic cells within the seminiferous tubules,suggesting alleviated cellular *** contrast,we observed that rapamycin,a drug known for its longevity benefits,induced excessive testicular apoptosis and did not decrease lipid ***,our results highlight BZBS’s promising clinical potential in counteracting male reproductive aging,underlining its mechanisms of action.

关键词： Traditional Chinese medicine Male reproductive aging Spermatogenic cells Cell senescence Apoptosis

Nuclear charge radius predictions by kernel ridge regression with odd-even effects

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Nuclear Science and Techniques 2024年第2期35卷 94-102页

作者： Lu tang Zhen-Hua Zhang Mathematics and Physics Department North China Electric Power UniversityBeijing 102206China Hebei Key Laboratory of Physics and Energy Technology North China Electric Power UniversityBaoding 071000China

The extended kernel ridge regression(EKRR)method with odd-even effects was adopted to improve the description of the nuclear charge radius using five commonly used nuclear *** are:(i)the isospin-dependent A^(1∕3) formula,(ii)relativistic continuum Hartree-Bogoliubov(RCHB)theory,(iii)Hartree-Fock-Bogoliubov(HFB)model HFB25,(iv)the Weizsacker-Skyrme(WS)model WS*,and(v)HFB25**** the last two models,the charge radii were calculated using a five-parameter formula with the nuclear shell corrections and deformations obtained from the WS and HFB25 models,*** each model,the resultant root-mean-square deviation for the 1014 nuclei with proton number Z≥8 can be significantly reduced to 0.009-0.013 fm after considering the modification with the EKRR *** best among them was the RCHB model,with a root-mean-square deviation of 0.0092 *** extrapolation abilities of the KRR and EKRR methods for the neutron-rich region were examined,and it was found that after considering the odd-even effects,the extrapolation power was improved compared with that of the original KRR *** strong odd-even staggering of nuclear charge radii of Ca and Cu isotopes and the abrupt kinks across the neutron N=126 and 82 shell closures were also calculated and could be reproduced quite well by calculations using the EKRR method.

关键词： Nuclear charge radius Machine learning Kernel ridge regression method

维普期刊数据库

UAV-assisted data collection for wireless sensor networks with dynamic working modes

在线全文

学校读者我要写书评

暂无评论

Digital Communications and Networks 2024年第3期10卷 805-812页

作者： Jie Chen Jianhua tang Shien-Ming Wu School of Intelligent Engineering South China University of TechnologyGuangzhou511442China

Wireless Sensor Network(WSN)is a cornerstone of Internet of Things(IoT)and has rich application *** this work,we consider a heterogeneous WSN whose sensor nodes have a diversity in their Residual Energy(RE).In this work,to protect the sensor nodes with low RE,we investigate dynamic working modes for sensor nodes which are determined by their RE and an introduced energy ***,we employ an Unmanned Aerial Vehicle(UAV)to collect the stored data from the heterogeneous *** aim to jointly optimize the cluster head selection,energy threshold and sensor nodes’working mode to minimize the weighted sum of energy con-sumption from the WSN and UAV,subject to the data collection rate *** this end,we propose an efficient search method to search for an optimal energy threshold,and develop a penalty-based successive convex approximation algorithm to select the cluster *** we present a low-complexity iterative approach to solve the joint optimization problem and discuss the implementation *** results justify that our proposed approach is able to reduce the energy consumption of the sensor nodes with low RE significantly and also saves energy for the whole WSN.

关键词： Unmanned aerial vehicle Wireless sensor networks Cluster heads Dynamic working modes