检索结果-南通市图书馆

Biderivations of Hom-Lie Algebras and Superalgebras

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Acta Mathematica Sinica,English Series 2024年第10期40卷 2337-2358页

作者： La Mei YUAN jia Xin LI School of Mathematics Harbin Institute of Technology

On Hom-Lie algebras and superalgebras, we introduce the notions of biderivations and linear commuting maps, and compute them for some typical Hom-Lie algebras and superalgebras,including the q-deformed W(2, 2) algebra... 详细信息

关键词： 17A30 17A60 17B05 17B60 17B70 biderivations Hom-Lie algebras linear commuting maps q-deformed W(2 2) algebra q-deformed Witt algebra q-deformed Witt superalgebra

Enhancing Image Description Generation through Deep Reinforcement Learning:Fusing Multiple Visual Features and Reward Mechanisms

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第2期78卷 2469-2489页

作者： Yan Li Qiyuan Wang Kaidi jia School of Cyber Security Gansu University of Political Science and LawLanzhou730070China

Image description task is the intersection of computer vision and natural language processing,and it has important prospects,including helping computers understand images and obtaining information for the visually *** study presents an innovative approach employing deep reinforcement learning to enhance the accuracy of natural language descriptions of *** method focuses on refining the reward function in deep reinforcement learning,facilitating the generation of precise descriptions by aligning visual and textual features more *** approach comprises three key ***,it utilizes Residual Network 101(ResNet-101)and Faster Region-based Convolutional Neural Network(Faster R-CNN)to extract average and local image features,respectively,followed by the implementation of a dual attention mechanism for intricate feature ***,the Transformer model is engaged to derive contextual semantic features from textual ***,the generation of descriptive text is executed through a two-layer long short-term memory network(LSTM),directed by the value and reward *** with the image description method that relies on deep learning,the score of Bilingual Evaluation Understudy(BLEU-1)is 0.762,which is 1.6%higher,and the score of BLEU-4 is ***-based Image Description Evaluation(CIDEr)scored 0.998,Recall-Oriented Understudy for Gisting Evaluation(ROUGE)scored 0.552,the latter improved by 0.36%.These results not only attest to the viability of our approach but also highlight its superiority in the realm of image *** research can explore the integration of our method with other artificial intelligence(AI)domains,such as emotional AI,to create more nuanced and context-aware systems.

关键词： Image description deep reinforcement learning attention mechanism

A dynamical neural network approach for distributionally robust chance-constrained Markov decision process

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 Mathematics 2024年第6期67卷 1395-1418页

作者： Tian Xia jia Liu Zhiping Chen School of Mathematics and Statistics Xi’an Jiaotong UniversityXi’an710049China

In this paper,we study the distributionally robust joint chance-constrained Markov decision *** the logarithmic transformation technique,we derive its deterministic reformulation with bi-convex terms under the moment-based uncertainty *** cope with the non-convexity and improve the robustness of the solution,we propose a dynamical neural network approach to solve the reformulated optimization *** results on a machine replacement problem demonstrate the efficiency of the proposed dynamical neural network approach when compared with the sequential convex approximation approach.

关键词： Markov decision process chance constraints distributionally robust optimization moment-based ambiguity set dynamical neural network

维普期刊数据库

A New Encrypted Traffic Identification Model Based on VAE-LSTM-DRN

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第1期78卷 569-588页

作者： Haizhen Wang Jinying Yan Na jia College of Computer and Control Engineering Qiqihar UniversityQiqihar161006China Heilongjiang Key Laboratory of Big Data Network Security Detection and Analysis Qiqihar UniversityQiqiharChina

Encrypted traffic identification pertains to the precise acquisition and categorization of data from traffic datasets containing imbalanced and obscured *** extraction of encrypted traffic attributes and their subsequent identification presents a formidable *** existing models have predominantly relied on direct extraction of encrypted traffic data from imbalanced datasets,with the dataset’s imbalance significantly affecting the model’s *** the present study,a new model,referred to as UD-VLD(Unbalanced Dataset-VAE-LSTM-DRN),was proposed to address above *** proposed model is an encrypted traffic identification model for handling unbalanced *** encoder of the variational autoencoder(VAE)is combined with the decoder and Long-short term Memory(LSTM)in UD-VLD model to realize the data enhancement processing of the original unbalanced *** enhanced data is processed by transforming the deep residual network(DRN)to address neural network gradient-related ***,the data is classified and *** UD-VLD model integrates the related techniques of deep learning into the encrypted traffic recognition technique,thereby solving the processing problem for unbalanced *** UD-VLD model was tested using the publicly available Tor dataset and VPN *** UD-VLD model is evaluated against other comparative models in terms of accuracy,loss rate,precision,recall,F1-score,total time,and ROC *** results reveal that the UD-VLD model exhibits better performance in both binary and multi classification,being higher than other encrypted traffic recognition models that exist for unbalanced ***,the evaluation performance indicates that the UD-VLD model effectivelymitigates the impact of unbalanced data on traffic *** can serve as a novel solution for encrypted traffic identification.

关键词： Data enhancement LSTM deep residual network VAE

Towards imbalanced motion:part-decoupling network for video portrait segmentation

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7期67卷 197-210页

作者： Tianshu YU Changqun XIA jia LI State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and EngineeringBeihang University Peng Cheng Laboratory

Video portrait segmentation(VPS), aiming at segmenting prominent foreground portraits from video frames, has received much attention in recent years. However, the simplicity of existing VPS datasets leads to a limitation on extensive research of the task. In this work, we propose a new intricate large-scale multi-scene video portrait segmentation dataset MVPS consisting of 101 video clips in 7 scenario categories,in which 10843 sampled frames are finely annotated at the pixel level. The dataset has diverse scenes and complicated background environments, which is the most complex dataset in VPS to our best *** the observation of a large number of videos with portraits during dataset construction, we find that due to the joint structure of the human body, the motion of portraits is part-associated, which leads to the different parts being relatively independent in motion. That is, the motion of different parts of the portraits is imbalanced. Towards this imbalance, an intuitive and reasonable idea is that different motion states in portraits can be better exploited by decoupling the portraits into parts. To achieve this, we propose a part-decoupling network(PDNet) for VPS. Specifically, an inter-frame part-discriminated attention(IPDA)module is proposed which unsupervisedly segments portrait into parts and utilizes different attentiveness on discriminative features specified to each different part. In this way, appropriate attention can be imposed on portrait parts with imbalanced motion to extract part-discriminated correlations, so that the portraits can be segmented more accurately. Experimental results demonstrate that our method achieves leading performance with the comparison to state-of-the-art methods.

关键词： video portrait segmentation imbalanced motion unsupervised part decoupling motion correlation inter-frame attention

Machine Learning Security Defense Algorithms Based on Metadata Correlation Features

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第2期78卷 2391-2418页

作者： Ruchun jia jianwei Zhang Yi Lin College of Computer Science Sichuan UniversityChengdu610065China

With the popularization of the Internet and the development of technology,cyber threats are increasing day by *** such as malware,hacking,and data breaches have had a serious impact on *** network security environment in the era of big data presents the characteristics of large amounts of data,high diversity,and high real-time *** security defense methods and tools have been unable to cope with the complex and changing network security *** paper proposes a machine-learning security defense algorithm based on metadata association *** control over unauthorized users through privacy,integrity,and *** user model is established and the mapping between the user model and the metadata of the data source is *** analyzing the user model and its corresponding mapping relationship,the query of the user model can be decomposed into the query of various heterogeneous data sources,and the integration of heterogeneous data sources based on the metadata association characteristics can be *** and classify customer information,automatically identify and perceive sensitive data,build a behavior audit and analysis platform,analyze user behavior trajectories,and complete the construction of a machine learning customer information security defense *** experimental results show that when the data volume is 5×103 bit,the data storage integrity of the proposed method is 92%.The data accuracy is 98%,and the success rate of data intrusion is only 2.6%.It can be concluded that the data storage method in this paper is safe,the data accuracy is always at a high level,and the data disaster recovery performance is *** method can effectively resist data intrusion and has high air traffic control *** can not only detect all viruses in user data storage,but also realize integrated virus processing,and further optimize the security defense effect of user big data.

关键词： Data-oriented architecture metadata correlation features machine learning security defense data source integration

Towards efficient generative AI and beyond-AI computing:New trends on ISSCC 2024 machine learning accelerators

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 Semiconductors 2024年第4期45卷 12-15页

作者： Bohan Yang jia Chen Fengbin Tu Department of Electronic and Computer Engineering The Hong Kong University of Science and TechnologyHong KongChina AI Chip Center for Emerging Smart Systems The Hong Kong University of Science and TechnologyHong KongChina School of the Gifted Young University of Science and Technology of ChinaHefei 230026Chin

Compared to the last decade when the convolution neu-ral network(CNN)dominated the research field,machine learn-ing(ML)algorithms have reached a pivotal moment called the generative artificial intelligence(AI)*** the emer-gence of large-scale foundation models[1],such as large multi-modal model(LMM)GPT-4[2]and text-to-image generative model DALL·E[3].

关键词： ISSCC beyond AI

维普期刊数据库

Synthesis,Characterization of Polyethylene Ionomers and Their Antibacterial Properties

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Polymer Science 2024年第8期42卷 1077-1084页

作者： jia-jia Wu Fei Wang Peng-Qi Wan Li Pan Chun-Sheng Xiao Zhe Ma Yue-Sheng Li Tianjin Key Lab Composite&Functional Materials School of Materials Science and EngineeringTianjin UniversityTianjin 300350China Key Lab Polymer Ecomaterials Changchun Institute of Applied ChemistryChinese Academy of SciencesChangchun 130022China

Owing to its high production volume and wide range of application s,polyethylene has gained a great deal of attention,but its low surface energy and non-polar nature have limited its application in some important *** this study,ethylene/11-iodo-1-undecene copolymers were prepared and used as the intermediates to afford a series of imidazolium-based ionomers bearing methanesulfonate(CH_(3)SO_(3)^(-)),trifluoromethanesulfonate(CF_(3)SO_(3)^(-)),or bis(trifluoromethane)sulfonimide(Tf_(2)N^(-))*** tensile test results showed that the stress-at-break(7.8-25.6 MPa)and the elongation-at-break(445%-847%)of the ionomers could be adjusted by changing the counterion species and the ionic group *** importantly,the ionomers exhibited marvelous antibacterial activities against Staphylococcus aureus(***)and Escherichia coli(***).The ionomers bearing Tf_(2)N^(-)exhibited antibacterial activities>99%against both *** and *** when ionic content reached 9.1%.The imidazolium-based ionomers prepared in this work demonstrated excellent comprehensive properties,especially highefficient and broad-spectrum antibacterial ability,exhibiting the potential fo r the application as the antibacterial materials in packaging,medical,and other fields.

关键词： Polyethylene Ionomer Polymerization catalysis Imidazolium Antibacterial material

维普期刊数据库

Designing hierarchical structures for innovative cooling textile

在线全文

学校读者我要写书评

暂无评论

Nano Research 2024年第10期17卷 9202-9224页

作者： Xiran Du Jinlei Li Bin Zhu jia Zhu National Laboratory of Solid State Microstructures College of Engineering and Applied SciencesJiangsu Key Laboratory of Artificial Functional MaterialsNanjing UniversityNanjing 210023China School of Sustainable Energy and Resources Nanjing UniversitySuzhou 215163China

The potential of personal cooling technologies in reducing air conditioning energy consumption and enhancing human thermal comfort is *** review focuses on recent advancements in hierarchical structure design for innovative cooling *** with insights into fundamental heat transfer processes between the human body,textile,and the surroundings,we uncover key control *** the advanced hierarchical structure designs enabling effective radiation,sweat evaporation,conduction management,and integration of cold energy sources for realizing effective human body cooling are systematically ***,we explore multifunctional designs beyond cooling,including switchable cooling-heating and ***,we engage in discussions on unifying cooling performance tests and additional multiple requirements to make strides toward practical *** review is anticipated to be a valuable resource,providing the scientific and industrial communities with a quick grasp of past advancements,current challenges,and future directions in achieving effective human body cooling.

关键词： thermal comfort personal cooling textile hierarchical structures