检索结果-内蒙古大学图书馆

GCINet: global convolution interaction network with a pre-trained reversible normalization method for long-term time series forecasting

引用

Neural Computing and applications 2025年第5期37卷 3227-3244页

作者： Fan, Jin Yang, Baoshun Sun, Danfeng Liu, Jie Chen, Qikai Wang, Zhipeng Wu, Jia Hangzhou Dianzi University Hangzhou China Key Laboratory of Intelligent Education Technology and Application of Zhejiang Province Zhejiang Normal University Hangzhou China School of Computing Macquarie University Sydney Australia

Long-term time series forecasting is crucial in various domains, such as weather forecasting and disease forecasting. With the rise of Transformer-based models, we have witnessed a significant improvement in long-term prediction accuracy, as these models use self-attention to capture long-term temporal features in the data during feature extraction. However, this approach has several drawbacks: Firstly, self-attention has quadratic complexity, and reducing its complexity often results in reduced prediction accuracy. Secondly, the distribution of time series data frequently changes over time, a phenomenon known as distribution shift, which is not taken into consideration in most Transformer-based models. This leads to decreased prediction accuracy as the distribution deviates from the one used for model training. Therefore, we have developed a new time series forecasting model, GCINet, which introduces a new mode of interaction based on a convolutional network. This captures both long-term and short-term temporal features while reducing complexity during feature extraction. Additionally, GCINet includes an Inverse Trained Normalization method to address distribution shift, bringing a fresh perspective to the design of time series forecasting models. Our experiments on long-term forecasting tasks demonstrate that GCINet outperforms other commonly used models. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Efficiency evaluation of blockchain-based iot network

Efficiency evaluation of blockchain-based IoT network

引用

2024 International Conference on Computer application and Information Security, ICCAIS 2024

作者： Zheng, Kai Jiangsu Key Construction Laboratory of IoT Application Technology Wuxi Taihu University Wuxi214064 China

ISBN: (纸本)9781510689312

In recent years, blockchain has gained increasing attention of researchers. Blockchain scenarios show that their security and credibility are higher than centralized scenarios. Blockchain technology is also used in many domains including healthcare, finance, smart grid, and so on. However, research about the efficiency evaluation of blockchain networks is still lacking. If the efficiency of the blockchain network can be evaluated before implementation, the performance of the blockchain network will be improved. This is very meaningful. What’s more, the usage of blockchain in healthcare networks is increasing. So, in this paper, the application area of blockchain is the iot network. Continuous-time Markov chain (CTMC) models are constructed in PRISM to assess the efficiency of blockchain-based iot *** consensus mechanism of the the network is the Practical Byzantine Fault Tolerance (PBFT) mechanism. The influence of node number, problem nodes, and internet speed are analyzed. The optimized strategies are given. © The Authors.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

A Combined Adaptive Zebra Optimization and Perturb & Observe MPPT Algorithm in PV System under Partial Shading Conditions 6

A Combined Adaptive Zebra Optimization and Perturb & Observe...

引用

6th IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference, IMCEC 2024

作者： Zhao, Haoheng Xie, Sichao Zhang, Chengyang Yan, Chenxu Liu, Guangyu Hangzhou Dianzi University Zhejiang Provincial Key Laboratory of IoT and Information Fusion Technology School of Automation Zhejiang Hangzhou China

ISBN: (纸本)9798350316520

Photovoltaic (PV) system faces challenges like partial shading, significantly affecting power output and efficiency. Developing an advanced maximum power point tracking (MPPT) controller is vital for enhancing the performance of PV system. Although extensive research has been conducted on MPPT control under partial shading conditions, focusing on convergence speed and tracking accuracy, the studies on oscillations during the convergence process and the tracking response of the maximum power point (MPP) in changing environments are still insufficient. In this study, we have proposed the adaptive zebra optimization algorithm (AZOA) and combined it with the perturb & observe (P&O) method to specifically address the aforementioned issues of oscillations and tracking response. The newly proposed algorithm, AZOA-P&O, introducing adaptive coefficients and integrating it with P&O, enhances the performance of traditional zebra optimization algorithm (ZOA). Ensuring accurate and rapid convergence to the MPP, AZOA-P&O significantly reduces oscillations during the convergence process and markedly enhances dynamic response to changing environments. The proposed work is carried out in MAT-LAB/Simulink platform, which is compared with perturb & observe (P&O), tasmanian devil optimization (TDO), driving training-based optimization (DTBO) techniques in terms of convergence speed, response speed, and the oscillations during the convergence process. The results significantly demonstrate the superiority of proposed MPPT technology over other MPPT techniques. © 2024 IEEE.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Self-assembled co-delivery system of gold nanoparticles and paclitaxel based on in-situ dynamic covalent chemistry for synergistic chemo-photothermal therapy

引用

Rare Metals 2025年第1期44卷 417-429页

作者： Xiao-Xia Wu Ding-Hu Zhang Yi-Nan Ding Fei Cao Yang Li Jun-Lie Yao Xin-Yu Miao Lu-Lu He Jun Luo Jian-Wei Li Jie Lin Ai-Guo Wu Jia-Ping Zheng Department of Interventional Radiology Zhejiang Key Laboratory of Imaging and Interventional MedicineZhejiang Cancer HospitalHangzhou Institute of Medicine(HIM)Chinese Academy of SciencesHangzhou 310022China Laboratory of Advanced Theranostic Materials and Technology Ningbo Key Laboratory of Biomedical Imaging Probe Materials and TechnologyZhejiang International Cooperation Base of Biomedical Materials Technology and ApplicationNingbo Cixi Institute of Biomedical EngineeringNingbo Institute of Materials Technology and EngineeringChinese Academy of SciencesNingbo 315201China MediCity Research Laboratory University of TurkuTurku 20520Finland

Recently,stimuli-responsive nanocarriers capable of precision drug release have garnered significant attention in the field of drug ***,an in-situ dynamic covalent self-assembled(DCS)strategy was utilized to develop a co-delivery *** assembly was based on a thiol-disulfide-exchange reaction,producing disulfide macrocycles in an oxidizing aerial *** macrocycles encapsulated the anti-cancer drug(paclitaxel,PTX)on the surface of gold nanoparticles,which served as photothermal therapy agents during the *** the DCS process,the kinetic control over the concentration of each building unit within the reaction system led to the formation of a stable co-delivery nanosystem with optimal drug-loading ***,the high glutathione(GSH)concentrations in tumor cells caused the disulfide macrocycles in nanostructures to break,resulting in drug *** stimuli-responsive performances of the prepared nanosystems were determined by observing the molecular structures and drug *** results revealed that the self-assembled nanosystem exhibited GSH-triggered drug release and good photothermal conversion capability under near-infrared ***,the in vitro and in vivo results revealed that conjugating the targeting molecule of cRGD with co-delivery nanosystem enhanced its biocompatibility,chemo-photothermal anti-cancer ***,our findings indicated that in-situ DCS strategy enhanced the control over drug loading during the construction of the co-delivery system,paving a way for the development of more functional carriers in nanomedicine.

关键词： in-situ dynamic covalent self-assembly(DCS) Disulfide macrocycles Host-guest interaction Glutathione(GSH)stimuli-response Chemo-photothermal therapy

来源：评论

学校读者我要写书评

暂无评论

Representing Multiview Time-Series Graph Structures for Multivariate Long-Term Time-Series Forecasting

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第6期5卷 2651-2662页

作者： Wang, Zehao Fan, Jin Wu, Huifeng Sun, Danfeng Wu, Jia Hangzhou Dianzi University Department of Computer Science and Technology Hangzhou310018 China Zhejiang Provincial Key Laboratory of Industrial Internet in Discrete Industries Hangzhou310018 China Zhejiang Normal University Laboratory of Intelligent Education Technology and Application of Zhejiang Province Hangzhou310018 China Macquarie University School of Computing SydneyNSW2113 Australia

Multivariate long-term time-series forecasting tasks are very challenging tasks in many real-world application areas. Recently, researchers focus on designing robust and effective methods, and have made considerable progress. However, there are several issues with existing models that need to be overcome. First, the lack of a relationship structure between multivariate variables needs to be addressed. Second, most models only have a weak ability to capture local dynamic changes across the entire long-term time-series. Third, current models suffer from high computational complexity and unsatisfactory accuracy. To figure out the abovementioned issues, we propose an effective and efficient method called multiview time-series graph structure representation (MTGSR). MTGSR uses GCNs to construct topological relationships in the multivariate time-series from three different perspectives: time, dimension, and crossing segments. Variation trends in different dimensions are extracted through a difference operation to construct topological maps that reflect the correlations between different dimensions. To capture the dynamically changing characteristics of fluctuation correlations between adjacent local sequences, MTGSR constructs a cross graph by calculating correlation coefficients between adjacent local sequences. Extensive experiments show that MTGSR reduces errors by 17.41% over the state of the art. In addition, memory use is decreased by 66.52% and the running time is reduced by 78.09%. © 2020 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Bioinspired zinc-mediated umpolung thiolation of alkyl electrophiles: reaction development, scope and mechanism

引用

Science China Chemistry 2024年第3期67卷 898-907页

作者： Yuenian Xu Yan Zhang Yong Liu Wen-Wu Sun Jie Huang Hui He Yingjie Wu Wen Liu Shao-Fei Ni Xu-Qiong Xiao Xinxin Shao College of Material Chemistry and Chemical EngineeringKey Laboratory of Organosilicon Chemistry and Material Technology of Ministry of EducationHangzhou Normal UniversityHangzhou 311121China School of Pharmaceutical Sciences South-Central Minzu UniversityWuhan 430074China Department of Chemistry and Key Laboratory for Preparation and Application of Ordered Structural Materials of Guang-dong Province Shantou UniversityShantou 515063China

Zinc-promoted umpolung thiolation of alkyl electrophiles with masked sulfur transfer reagents in the absence of nickel or copper catalysis is described. This protocol proceeds via a SET process of Zn to electrophilic sulfur reagent followed by insertion of Zn into disulfide and nucleophilic thiolation, providing straightforward access to a wide range of alkyl sulfides with broad substrate scope. A neutral TMEDA-ligated four-coordinated zinc thiolate with tetrahedra geometry was synthesized, isolated and fully characterized by NMR, IR and X-ray analysis. More importantly, the chemical reactivity of this active intermediate has been investigated, enabling the construction of C-Se, C-Te, Sb-S and Bi-S bonds to prepare valuable sulfur-containing molecules and beyond.

关键词： umpolung thiolation C(sp^(3))-S bond formation masked sulfur reagents reductive coupling

来源：评论

学校读者我要写书评

暂无评论

Image inpainting via Smooth Tucker decomposition and Low-rank Hankel constraint

引用

International Journal of Computers and applications 2023年第6期45卷 421-432页

作者： Cai, Jing Jiang, Jiawei Wang, Yibing Zheng, Jianwei Xu, Honghui Department of Forensic Science Zhejiang Police College Hangzhou China Key Laboratory of Public Security Information Application Based on Big-Data Architecture Hangzhou China College of Computer Science and Technology Zhejiang University of Technology Hangzhou China

Image inpainting, aiming at exactly recovering missing pixels from partially observed entries, is typically an ill-posed problem. As a powerful constraint, low-rank priors have been widely applied in image inpainting to transform such problems into well-posed ones. However, the low-rank assumption of original visual data is only in an approximate mode, which in turn results in suboptimal recovery of fine-grained details, particularly when the missing rate is extremely high. Moreover, a single prior cannot faithfully capture the complex texture structure of an image. In this paper, we propose a joint usage of Smooth Tucker decomposition and Low-rank Hankel constraint (STLH) for image inpainting, which enables simultaneous capturing of the global low-rankness and local piecewise smoothness. Specifically, based on the Hankelization operation, the original image is mapped to a high-order structure for capturing more spatial and spectral information. By employing Tucker decomposition for optimizing the Hankel tensor and simultaneously applying Discrete Total Variation (DTV) to the Tucker factors, sharper edges are generated and better isotropic properties are enhanced. Moreover, to approximate the essential rank of the Tucker decomposition and avoid facing the uncertainty problem of the upper-rank limit, a reverse strategy is adopted to approximate the true rank of the Tucker decomposition. Finally, the overall image inpainting model is optimized by the well-known alternate least squares (ALS) algorithm. Extensive experiments show that the proposed method achieves state-of-the-art performance both quantitatively and qualitatively. Particularly, in the extreme case with 99% pixels missed, the results from STLH are averagely ahead of others at least 0.9dB in terms of PSNR values. © 2023 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Predictive control for greenhouse temperature and humidity and energy optimization by improved NMPC objective function algorithm

引用

International Journal of Agricultural and Biological Engineering 2024年第5期17卷 128-136页

作者： Lina Wang Ying Zhang Mengjie Xu Qiuhui Liu Binrui Wang Institute of Mechanical and Electrical Engineering China Jiliang UniversityHangzhou 310018China Zhejiang Province Key Laboratory of On-line Testing Equipment Calibration Technology Research China Jiliang UniversityHangzhou 310018China Zhejiang Provincial Key Laboratory of Intelligent Manufacturing Quality Big Data Traceability and Application China Jiliang UniversityHangzhou 310018China

Persistent low temperatures in autumn and winter have a huge impact on crops,and greenhouses rely on solar radiation and heating equipment to meet the required indoor *** the energy cost of frequent operation of the actuators is exceptionally *** relationship between greenhouse environmental control accuracy and energy consumption is one of the key issues faced in greenhouse *** this study,a non-linear model predictive control method with an improved objective function was *** improved objective function used tolerance intervals and boundary constraints to optimize the objective *** nonlinear model predictive control(NMPC)controller design was based on the wavelet neural network(WNN)data-driven model and applied the interior point method to solve the optimal solution of the objective function control,thus balancing the contradiction between energy consumption and control *** simulation results showed that the improved NMPC method reduced energy consumption by 21.02%and 9.54%compared with the model predictive control and regular NMPC,which proved the method achieved good results in a low-temperature *** research can provide an important reference for the field as it offers a more efficient approach to managing greenhouse climates,potentially leading to substantial energy savings and enhanced sustainability in agricultural practices.

关键词： greenhouse environmental control greenhouse energy optimization nonlinear model predictive control objective function improvement

来源：评论

学校读者我要写书评

暂无评论

In situ observation of the electrochemical behavior of Li–CO_(2)/O_(2)batteries in an environmental transmission electron microscope

引用

Carbon Energy 2024年第4期6卷 244-255页

作者： Peng Jia Yunna Guo Dongliang Chen Jingming Yao Xuedong Zhang Jianguo Lu Yuqing Qiao Liqiang Zhang Hebei Key Laboratory of Applied Chemistry College of Environmental and Chemical EngineeringYanshan UniversityQinhuangdaoChina State Key Laboratory of Metastable Materials Science and Technology Clean Nano Energy CenterYanshan UniversityQinhuangdaoChina State Key Laboratory of Silicon and Advanced Semiconductor Materials School of Materials Science and EngineeringZhejiang UniversityHangzhouChina Key Laboratory of Low Dimensional Materials and Application Technology of Ministry of Education School of Materials Science and EngineeringXiangtan UniversityXiangtanChina

Li–CO_(2)/O_(2)batteries,a promising energy storage technology,not only provide ultrahigh discharge capacity but also capture CO_(2)and turn it into renewable *** electrochemical reaction pathways'ambiguity,however,creates a hurdle for their practical *** study used copper selenide(CuSe)nanosheets as the air cathode medium in an environmental transmission electron microscope to in situ study Li–CO_(2)/O_(2)(mix CO_(2)as well as O_(2)at a volume ratio of 1:1)and Li–O_(2)batteries as well as Li–CO_(2)*** discharge reactions take place successively in the Li–CO_(2)/O_(2)–CuSe nanobattery:(I)4Li^(+)+O_(2)+4e^(−)→2Li_(2)O;(II)Li_(2)O+CO_(2)→Li_(2)CO_(3).The charge reaction proceeded via(III)2Li_(2)CO_(3)→4Li^(+)+2CO_(2)+O_(2)+4e^(−).However,Li–O_(2)and Li–CO_(2)nanobatteries showed poor cycling stability,suggesting the difficulty in the direct decomposition of the discharge *** fluctuations of the Li–CO_(2)/O_(2)battery's electrochemistry were also shown to depend heavily on O_(2).The CuSe‐based Li–CO_(2)/O_(2)battery showed exceptional electrochemical *** Li^–CO_(2)/O_(2)battery offered a discharge capacity apex of 15,492 mAh g^(−1) and stable cycling 60 times at 100 mA g^(−1).Our research offers crucial insight into the electrochemical behavior of Li–CO_(2)/O_(2),Li–O_(2),and Li–CO_(2)nanobatteries,which may help the creation of high‐performance Li–CO_(2)/O_(2)batteries for energy storage applications.

关键词： CuSe nanosheets electrochemical reaction in situ environmental transmission electron microscopy Li-CO_(2)battery Li-CO_(2)/O_(2)battery Li-O_(2)battery

来源：评论

学校读者我要写书评

暂无评论

Epidermal visualized health monitoring system based on stretchable and washable TPU hybrid conductive microtextiles

引用

Rare Metals 2024年第7期43卷 3185-3193页

作者： Jing-Bo Yuan Zhi-Hong Feng Dong-Chan Li Yang Luo Yun-Lei Zhou School of Chemical Engineering Hebei University of Technology Engineering Research Center of Chemical Technology for Efficient Utilization of Seawater ResourcesMinistry of EducationTianjin 300401China National Key Laboratory of Application Specific Integrated Circuit Shijiazhuang050000China Department of Materials ETH Zürich8093 ZurichSwitzerland Hangzhou Institute of Technology Xidian UniversityHangzhou 311231China

Electronic textiles,an emerging class of electronic technology,offer exciting opportunities for seamless integration with the human *** applications have been developed based on electronic ***,researches on integrating multiple electronic textilebased devices are still *** this study,we present a system integrated with an electrocardiogram monitoring sensor and an electroluminescence device based on stretchable and washable conductive micro *** signal is acquired by an electrocardiograph amplifier and displayed by a dual-color electroluminescence device based on the processed *** integrated electronic device has excellent moisture permeability and comfort for long-term *** system reported in this study opens a new avenue for the application of electronic textiles in health monitoring,robotic prosthetics,and competitive sports.

关键词： Conductive microtextile Textile composite Electronic textile Electroluminescent displays

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：