检索结果-南通市图书馆

Diffusionmodels for time-series applications: a survey

在线全文

学校读者我要写书评

暂无评论

Frontiers of Information Technology & Electronic Engineering 2024年第1期25卷 19-41页

作者： Lequan liN Zhengkun li Ruikun li Xuliang li Junbin GAO Discipline of Business Analytics The University of Sydney Business SchoolCamperdownNSW 2006Australia Postdoctoral Programme of Zhongtai Securities Co. Ltd.Jinan 250000China

Diffusion models, a family of generative models based on deep learning, have become increasinglyprominent in cutting-edge machine learning research. With distinguished performance in generating samples thatresemble the observed data, diffusion models are widely used in image, video, and text synthesis nowadays. Inrecent years, the concept of diffusion has been extended to time-series applications, and many powerful models havebeen developed. Considering the deficiency of a methodical summary and discourse on these models, we providethis survey as an elementary resource for new researchers in this area and to provide inspiration to motivate futureresearch. For better understanding, we include an introduction about the basics of diffusion models. Except forthis, we primarily focus on diffusion-based methods for time-series forecasting, imputation, and generation, andpresent them, separately, in three individual sections. We also compare different methods for the same applicationand highlight their connections if applicable. Finally, we conclude with the common limitation of diffusion-basedmethods and highlight potential future research directions.

关键词： Diffusion models Time-series forecasting Time-series imputation Denoising diffusion probabilistic models Score-based generative models Stochastic differential equations

Adaptive and augmented active anomaly detection on dynamic network traffic streams

在线全文

学校读者我要写书评

暂无评论

Frontiers of Information Technology & Electronic Engineering 2024年第3期25卷 446-460页

作者： Bin li Yijie WANG li CHENG National Key Laboratory of Parallel and Distributed Computing College of ComputerNational University of Defense TechnologyChangsha 410073China College of System Engineering National University of Defense TechnologyChangsha 410073China

Active anomaly detection queries labels of sampled instances and uses them to incrementally update the detection model,and has been widely adopted in detecting network ***,existing methods cannot achieve desirable performance on dynamic network traffic streams because(1)their query strategies cannot sample informative instances to make the detection model adapt to the evolving stream and(2)their model updating relies on limited query instances only and fails to leverage the enormous unlabeled instances on *** address these issues,we propose an active tree based model,adaptive and augmented active prior-knowledge forest(A3PF),for anomaly detection on network trafic streams.A prior-knowledge forest is constructed using prior knowledge of network attacks to find feature subspaces that better distinguish network anomalies from normal *** one hand,to make the model adapt to the evolving stream,a novel adaptive query strategy is designed to sample informative instances from two aspects:the changes in dynamic data distribution and the uncertainty of *** the other hand,based on the similarity of instances in the neighborhood,we devise an augmented update method to generate pseudo labels for the unlabeled neighbors of query instances,which enables usage of the enormous unlabeled instances during model *** experiments on two benchmarks,CIC-IDS2017 and UNSW-NB15,demonstrate that A3PF achieves significant improvements over previous active methods in terms of the area under the receiver operating characteristic curve(AUC-ROC)(20.9%and 21.5%)and the area under the precision-recall curve(AUC-PR)(44.6%and 64.1%).

关键词： Active anomaly detection Network traffic streams Pseudo labels Prior knowledge of network attacks

Phosphorylation Promotes the Accumulation of PERIOD Protein Foci

在线全文

学校读者我要写书评

暂无评论

Research 2024年第1期2023卷 59-69页

作者： Mengna li Shujing li Luoying Zhang Key Laboratory of Molecular Biophysics of Ministry of Education College of Life Science and TechnologyHuazhong University of Science and TechnologyWuhanHubei 430074China Department of life Sciences Bengbu Medical CollegeBengbuAnhui 233030China Hubei Province Key Laboratory of Oral and Maxillofacial Development and Regeneration WuhanHubei 430022China

Circadian clock drives the 24-h rhythm in our behavior and *** molecular clock consists of a series of transcriptional/translational feedback loops operated by a number of clock genes.A very recent study reported that the clock protein PERIOD(PER)is organized into discrete foci at the nuclear envelope in fly circadian neurons,which is believed to be important for controlling the subcellular localization of clock *** of inner nuclear membrane protein lamin B receptor(LBR)leads to disruption of these foci,but how they are regulated is yet ***,we found that PER foci are likely phase-separated condensates,the formation of which is mediated by intrinsically disordered region in *** promotes the accumulation of these *** phosphatase 2A,which is known to dephosphorylate PER,hampers the accumulation of the *** the other hand,the circadian kinase DOUBLETIME(DBT)which phosphorylates PER enhances the accumulation of the *** likely facilitates PER foci accumulation by destabilizing the catalytic subunit of protein phosphatase 2A,MICROTUBULE STAR(MTS).In conclusion,here,we demonstrate a key role for phosphorylation in promoting the accumulation of PER foci,while LBR modulates this process by impinging on the circadian phosphatase MTS.

关键词： conclusion separated translational

Challenges in li-ion battery high-voltage technology and recent advances in high-voltage electrolytes

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

Journal of Energy Chemistry 2024年第4期91卷 73-98页

作者： Jianguo liu Baohui li Jinghang Cao Xiao Xing Gan Cui Shandong Key Laboratory of Oil&Gas Storage and Transportation Safety College of Pipeline and Civil EngineeringChina University of Petroleum(East China)Qingdao 266580ShandongChina

The electrolyte directly contacts the essential parts of a lithium-ion battery,and as a result,the electrochemical properties of the electrolyte have a significant impact on the voltage platform,charge discharge capacity,energy density,service life,and rate discharge *** raising the voltage at the charge/discharge plateau,the energy density of the battery is ***,this causes transition metal dissolution,irreversible phase changes of the cathode active material,and parasitic electrolyte oxidation *** article presents an overview of these concerns to provide a clear explanation of the issues involved in the development of electrolytes for high-voltage lithium-ion ***,solidstate electrolytes enable various applications and will likely have an impact on the development of batteries with high energy *** is necessary to improve the high-voltage performance of electrolytes by creating solvents with high thermal stabilities and high voltage resistance and additives with superior film forming performance,multifunctional capabilities,and stable lithium *** offer suggestions for the future development of high-energy lithium-ion batteries,we conclude by offering our own opinions and insights on the current development of lithium-ion batteries.

关键词： lithium-ion battery High voltage Electrolyte additive Solid electrolyte

Nonlinear encoding in diffractive information processing using linear optical materials

在线全文

学校读者我要写书评

暂无评论

light(Science & Applications) 2024年第8期13卷 1675-1688页

作者： Yuhang li Jingxi li Aydogan Ozcan Electrical&Computer Engineering Department University of CaliforniaLos AngelesCA 90095USA Bioengineering Department University of CaliforniaLos AngelesCA 90095USA California NanoSystems Institute(CNSI) University of CaliforniaLos AngelesCA 90095USA

Nonlinear encoding of optical information can be achieved using various forms of data ***,we analyze the performances of different nonlinear information encoding strategies that can be employed in diffractive optical processors based on linear materials and shed light on their utility and performance gaps compared to the state-of-the-art digital deep neural *** a comprehensive evaluation,we used different datasets to compare the statistical inference performance of simpler-to-implement nonlinear encoding strategies that involve,e.g.,phase encoding,against data repetition-based nonlinear encoding *** show that data repetition within a diffractive volume(e.g.,through an optical cavity or cascaded introduction of the input data)causes the loss of the universal linear transformation capability of a diffractive optical ***,data repetition-based diffractive blocks cannot provide optical analogs to fully connected or convolutional layers commonly employed in digital neural ***,they can still be effectively trained for specific inference tasks and achieve enhanced accuracy,benefiting from the nonlinear encoding of the input *** results also reveal that phase encoding of input information without data repetition provides a simpler nonlinear encoding strategy with comparable statistical inference accuracy to data repetition-based diffractive *** analyses and conclusions would be of broad interest to explore the push-pull relationship between linear material-based diffractive optical systems and nonlinear encoding strategies in visual information processors.

关键词： nonlinear simpler Nonlinear

Meta label associated loss for fine-grained visual recognition

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

Science China(Information Sciences) 2024年第6期67卷 230-247页

作者： Yanchao li Fu XIAO Hao li Qun li Shui YU School of Computer Science Nanjing University of Posts and Telecommunications School of Network Engineering Zhoukou Normal University School of Computer Science University of Technology Sydney

Recently, intensive attempts have been made to design robust models for fine-grained visual recognition, most notably are the impressive gains for training with noisy labels by incorporating a reweighting strategy into a meta-learning framework. However, it is limited to up or downweighting the contribution of an instance for label reweighting approaches in the learning process. To solve this issue, a novel noise-tolerant method with auxiliary web data is proposed. Specifically, first, the associations made from embeddings of well-labeled data with those of web data and back at the same class are measured. Next, its association probability is employed as a weighting fusion strategy into angular margin-based loss, which makes the trained model robust to noisy datasets. To reduce the influence of the gap between the well-labeled and noisy web data, a bridge schema is proposed via the corresponding loss that encourages the learned embeddings to be coherent. Lastly, the formulation is encapsulated into the meta-learning framework, which can reduce the overfitting of models and learn the network parameters to be noise-tolerant. Extensive experiments are performed on benchmark datasets, and the results clearly show the superiority of the proposed method over existing state-of-the-art approaches.

关键词： label associated loss weighting noisy samples fine-grained visual recognition noise-tolerant learning meta-learning

New insights into the pre-lithiation kinetics of single-crystalline Ni-rich cathodes for long-life li-ion batteries

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Green Energy & Environment 2024年第3期9卷 556-564页

作者： Qiang Han Lele Cai Zhaofeng Yang Yanjie Hu Hao Jiang Chunzhong li Shanghai Engineering Research Center of Hierarchical Nanomaterials School of Chemical EngineeringEast China University of Science and TechnologyShanghai200237China Key Laboratory for Ultrafine Materials of Ministry of Education School of Materials Science and EngineeringEast China University of Science and TechnologyShanghai200237China

Developing single-crystalline Ni-rich cathodes is an effective strategy to improve the safety and cycle life of li-ion batteries(liBs).However,the easy-to-loss of li and O in high-temperature lithiation results in unsatisfactory ordered layered structure and ***,we demonstrate the synthesis of highly-ordered and fully-stoichiometric single-crystalline liNi_(0.83)Co_(0.12)Mn_(0.05)O_(2)(SC-NCM83)cathodes by the regulation of pre-lithiation *** well-balanced pre-lithiation kinetics have been proved to greatly improve the proportion of layered phase in the intermediate by inhibiting the formation of metastable spinel phase,which promoted the rapid transformation of the intermediate into highly-ordered layered SC-NCM83 in the subsequent lithiation *** coating a layer of li_(2)O–B_(2)O_(3),the resultant cathodes deliver superior cycling stability with 90.9%capacity retention at 1C after 300 cycles in pouch-type full *** enhancement mechanism has also been *** findings exhibit fundamental insights into the pre-lithiation kinetics process for guiding the synthesis of high-quality singlecrystalline Ni-rich cathodes.

关键词： Single-crystalline cathode Ni-rich oxides Pre-lithiation li-ion batteries Surface modification

Development of EPDM composites reinforced by CNTs@SiO_(2)for thermal protection systems of aerospace propulsion:Significant improvement in oxidation and ablation resistance properties

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Aeronautics 2024年第2期37卷 471-481页

作者： li WANG Jiang li Kang li Yiwei WANG Chenyang MA Science and Technology on Combustion Internal Flow and Thermal-Structure LaboratoryNorthwestern Polytechnical UniversityXi’an 710072China

Carbon Nanotubes(CNTs)reinforced Polymer-Matrix Composites(PMCs)is widely used as insulation materials in thermal protection system of aerospace ***,CNTs are prone to oxidation and have high thermal conductivities,which makes it difficult to improve the ablation resistance of insulation materials that contain ***_(2)was encapsulated onto the surface of CNTs(CNTs@SiO_(2)),which were then added to Ethylene Propylene Diene Monomer(EPDM)rubber to prepare the insulation *** analysis and ablation test were used to evaluate the resistance of the insulation materials to thermal oxidation and ***,scanning electron microscopy was performed to analyze their *** revealed that the addition of CNTs@SiO_(2)could visibly reduce the effects of hot corrosion and ablation on insulation *** C-CNTs@SiO_(2)-1 formulation had the best ablative ***,compared with the unencapsulated formulation(C-CNTs-10),the C-CNTs@SiO_(2)-1 formulation reduced the line ablation rate by 51%to 0.0130 mm/s after oxygen-acetylene ***,the ablation mechanism was investigated based on the effects of the CNTs@SiO_(2)additive on their ***,the improvement in ablation performance may be attributed to CNTs@SiO_(2)-induced decreases in thermal conductivity,improvement in the hot corrosion resistance in the char layer,and changes in the microstructure.

关键词： Polymer-Matrix Composites(PMCs) Carbon Nanotubes(CNTs) Thermal properties Ablation Oxidation

Multi-Physics Coupled Acoustic-Mechanics Analysis and Synergetic Optimization for a Twin-Fluid Atomization Nozzle

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Mechanical Engineering 2024年第3期37卷 204-223页

作者： Wenying li Yanying li Yingjie Lu Jinhuan Xu Bo Chen li Zhang Yanbiao li College of Mechanical Engineering Zhejiang University of TechnologyHangzhou 310023China State Key Laboratory of Fluid Power and Mechatronic Systems Zhejiang UniversityHangzhou 310027China School of Materials Science and Engineering Northwestern Polytechnical UniversityXian 710072China Guizhou Anda Aviation Forging Co. Ltd.Anshun 561005China

Fine particulate matter produced during the rapid industrialization over the past decades can cause significant harm to human ***-fluid atomization technology is an effective means of controlling fine particulate matter *** this paper,the influences of the main parameters on the droplet size,effective atomization range and sound pressure level(SPL)of a twin-fluid nozzle(TFN)are investigated,and in order to improve the atomization performance,a multi-objective synergetic optimization algorithm is presented.A multi-physics coupled acousticmechanics model based on the discrete phase model(DPM),large eddy simulation(LES)model,and Ffowcs Williams-Hawkings(FW-H)model is established,and the numerical simulation results of the multi-physics coupled acoustic-mechanics method are verified via experimental *** on the analysis of the multi-physics coupled acoustic-mechanics numerical simulation results,the effects of the water flow on the characteristics of the atomization flow distribution were obtained.A multi-physics coupled acoustic-mechanics numerical simulation result was employed to establish an orthogonal test database,and a multi-objective synergetic optimization algorithm was adopted to optimize the key parameters of the *** optimal parameters are as follows:A gas flow of 0.94 m^(3)/h,water flow of 0.0237 m^(3)/h,orifice diameter of the self-excited vibrating cavity(SVC)of 1.19 mm,SVC orifice depth of 0.53 mm,distance between SVC and the outlet of nozzle of 5.11 mm,and a nozzle outlet diameter of 3.15 *** droplet particle size in the atomization flow field was significantly reduced,the spray distance improved by 71.56%,and the SPL data at each corresponding measurement point decreased by an average of 38.96%.The conclusions of this study offer a references for future TFN research.

关键词： Twin-fluid nozzle BP neural network Multi-objective optimization Multi-physics coupled Acousticmechanics analysis Genetic algorithm