Resource Type

Journal Article 219

Conference Videos 3

Year

2023 33

2022 25

2021 21

2020 10

2019 15

2018 10

2017 12

2016 11

2015 4

2014 4

2013 4

2012 2

2011 6

2010 9

2009 8

2008 13

2007 11

2006 2

2005 6

2004 6

open ︾

Keywords

compressive strength 6

self-assembly 6

Attention 4

Attention mechanism 4

Deep learning 3

1 2

COVID-19 2

Energy harvesting 2

Semi-supervised learning 2

different 2

organogelator 2

parametric study 2

self-centering 2

self-compacting concrete 2

self-powered devices 2

-xylene 1

12-phase rectification 1

2 1

2-DOF orthogonal spherical parallel mechanism 1

open ︾

Search scope:

排序： Display mode:

Efficient decoding self-attention for end-to-end speech synthesis Research Article

Wei ZHAO, Li XU

Frontiers of Information Technology & Electronic Engineering 2022, Volume 23, Issue 7,   Pages 1127-1138 doi: 10.1631/FITEE.2100501

Abstract: has been innovatively applied to text-to-speech (TTS) because of its parallel structure and superior strength in modeling sequential data. However, when used in with an autoregressive decoding scheme, its inference speed becomes relatively low due to the quadratic complexity in sequence length. This problem becomes particularly severe on devices without graphics processing units (GPUs). To alleviate the dilemma, we propose an (EDSA) module as an alternative. Combined with a dynamic programming decoding procedure, TTS model inference can be effectively accelerated to have a linear computation complexity. We conduct studies on Mandarin and English datasets and find that our proposed model with EDSA can achieve 720% and 50% higher inference speed on the central processing unit (CPU) and GPU respectively, with almost the same performance. Thus, this method may make the deployment of such models easier when there are limited GPU resources. In addition, our model may perform better than the baseline Transformer TTS on out-of-domain utterances.

Keywords： Efficient decoding     End-to-end     Self-attention     Speech synthesis    

HTML PDF Collect

LDformer: a parallel neural network model for long-term power forecasting

田冉,李新梅,马忠彧,刘颜星,王晶霞,王楚

Frontiers of Information Technology & Electronic Engineering 2023, Volume 24, Issue 9,   Pages 1287-1301 doi: 10.1631/FITEE.2200540

Abstract: parallel encoder module to improve the robustness of the model and combine convolutional layers with an attentionmechanism to avoid value redundancy in the attention mechanism.Finally, we propose a probabilistic sparse (ProbSparse) self-attention mechanism combined with UniDrop

Keywords： Long-term power forecasting     Long short-term memory (LSTM)     UniDrop     Self-attention mechanism    

HTML Collect

Clean air captures attention whereas pollution distracts: evidence from brain activities

Frontiers of Environmental Science & Engineering 2023, Volume 18, Issue 4, doi: 10.1007/s11783-024-1801-x

Abstract:

● We find air pollution distracts attention and reveal the neurocognitive

Keywords： Air pollution     Attention     Disengagement     Performance     Event-related potential    

HTML PDF Collect

Prediction and cause investigation of ozone based on a double-stage attention mechanism recurrent neural

Frontiers of Environmental Science & Engineering 2023, Volume 17, Issue 2, doi: 10.1007/s11783-023-1621-4

Abstract:

● Used a double-stage attention mechanism model to predict ozone.

Keywords： Ozone prediction     Deep learning     Time series     Attention     Volatile organic compounds    

HTML PDF Collect

Less attention paid to waterborne SARS-CoV-2 spreading in Beijing urban communities

Frontiers of Environmental Science & Engineering 2021, Volume 15, Issue 5, doi: 10.1007/s11783-021-1398-2

Abstract:

• A survey on individual’s perception of SARS-CoV-2 transmission was conducted.

Keywords： Environmental dissemination     Risk communication     Individual perception    

HTML PDF Collect

Erratum to: Meter-scale variation within a single transect demands attention to taxon accumulation curves

Frontiers of Environmental Science & Engineering 2022, Volume 16, Issue 6, doi: 10.1007/s11783-022-1560-5

HTML PDF Collect

Meter-scale variation within a single transect demands attention to taxon accumulation curves in riverine

Frontiers of Environmental Science & Engineering 2022, Volume 16, Issue 5, doi: 10.1007/s11783-022-1543-6

Abstract:

● Riverine microbiomes exhibited hyperlocal variation within a single transect.

Keywords： Microbiome     Freshwater     Taxon accumulation curve     Community assembly    

HTML PDF Collect

Exploring self-organization and self-adaption for smart manufacturing complex networks

Frontiers of Engineering Management 2023, Volume 10, Issue 2,   Pages 206-222 doi: 10.1007/s42524-022-0225-1

Abstract: In this context, this paper investigates the mechanisms and methodology of self-organization and self-adaptionSubsequently, analytical target cascading is used to formulate the processes of self-organizing optimalconfiguration and self-adaptive collaborative control for multilevel key manufacturing resources whilework potentially enables managers and practitioners to implement active perception, active response, self-organization, and self-adaption solutions in discrete manufacturing enterprises.

Keywords： cyber–physical systems     Industrial Internet of Things     smart manufacturing complex networks     self-organizationand self-adaption     analytical target cascading     collaborative optimization    

HTML PDF Collect

Endothelial dysfunction in COVID-19 calls for immediate attention: the emerging roles of the endothelium

Weijian Hang, Chen Chen, Xin A. Zhang, Dao Wen Wang

Frontiers of Medicine 2021, Volume 15, Issue 4,   Pages 638-643 doi: 10.1007/s11684-021-0831-z

Abstract: We are calling for closer attention to endothelial dysfunction in COVID-19 not only for fully revealing

Keywords： COVID-19     endothelial dysfunction     inflammation reaction     cytokine storm    

HTML PDF Collect

NGAT: attention in breadth and depth exploration for semi-supervised graph representation learning Research Articles

Jianke HU, Yin ZHANG,yinzh@zju.edu.cn

Frontiers of Information Technology & Electronic Engineering 2022, Volume 23, Issue 3,   Pages 409-421 doi: 10.1631/FITEE.2000657

Abstract: Recently, graph neural networks (GNNs) have achieved remarkable performance in representation learning on graph-structured data. However, as the number of network layers increases, GNNs based on the neighborhood aggregation strategy deteriorate due to the problem of oversmoothing, which is the major bottleneck for applying GNNs to real-world graphs. Many efforts have been made to improve the process of feature information aggregation from directly connected nodes, i.e., breadth exploration. However, these models perform the best only in the case of three or fewer layers, and the performance drops rapidly for deep layers. To alleviate oversmoothing, we propose a nested graph network (NGAT), which can work in a semi-supervised manner. In addition to breadth exploration, a -layer NGAT uses a layer-wise aggregation strategy guided by the mechanism to selectively leverage feature information from the -order neighborhood, i.e., depth exploration. Even with a 10-layer or deeper architecture, NGAT can balance the need for preserving the locality (including root node features and the local structure) and aggregating the information from a large neighborhood. In a number of experiments on standard tasks, NGAT outperforms other novel models and achieves state-of-the-art performance.

Keywords： Graph learning     Semi-supervised learning     Node classification     Attention    

HTML PDF Collect

Emerging trends in self-healable nanomaterials for triboelectric nanogenerators: A comprehensive review

Frontiers in Energy   Pages 727-750 doi: 10.1007/s11708-023-0896-2

Abstract: A thorough analysis of triboelectric nanogenerators (TENGs) that make use of self-healable nanomaterialsTENGs, on the other hand, provide unique opportunities for future self-powered systems and might encourageExamining the many approaches used to improve nanogenerators by employing materials with shape memory and self-healableAdditionally, the cost-effectiveness, social acceptability, and regulatory implications of self-healing

Keywords： triboelectric nanogenerator (TENG)     self-healable nanomaterials     self-powered devices     energy    

HTML PDF Collect

Attention-based encoder-decoder model for answer selection in question answering Article

Yuan-ping NIE, Yi HAN, Jiu-ming HUANG, Bo JIAO, Ai-ping LI

Frontiers of Information Technology & Electronic Engineering 2017, Volume 18, Issue 4,   Pages 535-544 doi: 10.1631/FITEE.1601232

Abstract: In this paper, we introduce an attention-based deep learning model to address the answer selection taskOur model also uses a step attention mechanism which allows the question to focus on a certain part of

Keywords： Question answering     Answer selection     Attention     Deep learning    

HTML PDF Collect

Modular structure of a self-reconfigurable robot

FEI Yanqiong, DONG Qinglei, ZHAO Xifang

Frontiers of Mechanical Engineering 2007, Volume 2, Issue 1,   Pages 116-119 doi: 10.1007/s11465-007-0020-z

Abstract: This paper proposes a novel, hermaphroditic, and lattice self-reconfigurable modular robot.

Keywords： compact     self-reconfigurable modular     hermaphroditic     cone-shaped     clutch    

HTML PDF Collect

Signal separation technology for diphase opposition giant magnetostrictive self-sensing actuator

Xinhua WANG, Shuwen SUN, Jian ZHEN, Qianyi YA, Deguo WANG,

Frontiers of Mechanical Engineering 2010, Volume 5, Issue 2,   Pages 176-183 doi: 10.1007/s11465-010-0001-5

Abstract: The structure and principle of a new type of a diphase opposition giant magnetostrictive self-sensingDynamic balance separation technology for the giant magnetostrictive self-sensing actuator comes trueby the least means square (LMS) self-adapting algorithm.

Keywords： giant magnetostrictive material (GMM) self-sensing actuator     least means square (LMS) self-adapting algorithm     design of self-adaptive circuit    

HTML PDF Collect

Behaviour of self-centring shear walls——A state of the art review

Frontiers of Structural and Civil Engineering 2023, Volume 17, Issue 1,   Pages 53-77 doi: 10.1007/s11709-022-0850-0

Abstract: application of unbonded post-tensioning (PT) in structural walls has led to the development of advanced self-centringIn this research a comprehensive state-of-the-art literature review was performed on self-centring shearAn extensive study was carried out to collect a database of 100 concrete, masonry, and self-centringwalls, ductility, and seismic response factors, were critically reviewed and analysed for different self-centringThe outcome of this research can be used to better understand the behaviour of self-centring wall system

Keywords： self-centring shear walls     rocking walls     energy dissipation     seismic performance factors     PT loss     residual    

HTML PDF Collect

Title Author Date Type Operation

Efficient decoding self-attention for end-to-end speech synthesis

Wei ZHAO, Li XU

Journal Article

LDformer: a parallel neural network model for long-term power forecasting

田冉,李新梅,马忠彧,刘颜星,王晶霞,王楚

Journal Article

Clean air captures attention whereas pollution distracts: evidence from brain activities

Journal Article

Prediction and cause investigation of ozone based on a double-stage attention mechanism recurrent neural

Journal Article

Less attention paid to waterborne SARS-CoV-2 spreading in Beijing urban communities

Journal Article

Erratum to: Meter-scale variation within a single transect demands attention to taxon accumulation curves

Journal Article

Meter-scale variation within a single transect demands attention to taxon accumulation curves in riverine

Journal Article

Exploring self-organization and self-adaption for smart manufacturing complex networks

Journal Article

Endothelial dysfunction in COVID-19 calls for immediate attention: the emerging roles of the endothelium

Weijian Hang, Chen Chen, Xin A. Zhang, Dao Wen Wang

Journal Article

NGAT: attention in breadth and depth exploration for semi-supervised graph representation learning

Jianke HU, Yin ZHANG,yinzh@zju.edu.cn

Journal Article

Emerging trends in self-healable nanomaterials for triboelectric nanogenerators: A comprehensive review

Journal Article

Attention-based encoder-decoder model for answer selection in question answering

Yuan-ping NIE, Yi HAN, Jiu-ming HUANG, Bo JIAO, Ai-ping LI

Journal Article

Modular structure of a self-reconfigurable robot

FEI Yanqiong, DONG Qinglei, ZHAO Xifang

Journal Article

Signal separation technology for diphase opposition giant magnetostrictive self-sensing actuator

Xinhua WANG, Shuwen SUN, Jian ZHEN, Qianyi YA, Deguo WANG,

Journal Article

Behaviour of self-centring shear walls——A state of the art review

Journal Article