Resource Type

Journal Article 505

Year

2023 50

2022 33

2021 39

2020 23

2019 29

2018 28

2017 39

2016 12

2015 10

2014 11

2013 11

2012 13

2011 15

2010 14

2009 11

2008 25

2007 24

2006 22

2005 26

2004 17

open ︾

Keywords

Deep learning 13

Machine learning 8

Artificial intelligence 7

mathematical model 7

numerical simulation 7

COVID-19 5

Additive manufacturing 3

model test 3

1) 2

Accelerator 2

DX pile 2

Game theory 2

Model 2

Model predictive control 2

Multi-model 2

Natural language processing 2

Random forest 2

Unsupervised domain adaptation 2

Weibull distribution 2

open ︾

Search scope:

排序: Display mode:

A Survey of Accelerator Architectures for Deep Neural Networks Review

Yiran Chen, uan Xie, Linghao Song, Fan Chen, Tianqi Tang

Engineering 2020, Volume 6, Issue 3,   Pages 264-274 doi: 10.1016/j.eng.2020.01.007

Abstract:

Recently, due to the availability of big data and the rapid growth of computing power, artificial intelligence (AI) has regained tremendous attention and investment. Machine learning (ML) approaches have been successfully applied to solve many problems in academia and in industry. Although the explosion of big data applications is driving the development of ML, it also imposes severe challenges of data processing speed and scalability on conventional computer systems. Computing platforms that are dedicatedly designed for AI applications have been considered, ranging from a complement to von Neumann platforms to a “must-have” and standalone technical solution. These platforms, which belong to a larger category named “domain-specific computing,” focus on specific customization for AI. In this article, we focus on summarizing the recent advances in accelerator designs for deep neural networks (DNNs)—that is, DNN accelerators. We discuss various architectures that support DNN executions in terms of computing units, dataflow optimization, targeted network topologies, architectures on emerging technologies, and accelerators for emerging applications. We also provide our visions on the future trend of AI chip designs.

Keywords: Deep neural network     Domain-specific architecture     Accelerator    

Learning natural ordering of tags in domain-specific Q&A sites

Junfang Jia, Guoqiang Li,jiajunfang816@163.com,li.g@sjtu.edu.cn

Frontiers of Information Technology & Electronic Engineering 2021, Volume 22, Issue 2,   Pages 141-286 doi: 10.1631/FITEE.1900645

Abstract: is a defining characteristic of Web 2.0. It allows users of social computing systems (e.g., ) to use free terms to annotate content. However, is really a free action? Existing work has shown that users can develop implicit consensus about what tags best describe the content in an online community. However, there has been no work studying the regularities in how users order tags during . In this paper, we focus on the ing of tags in domain-specific Q&A sites. We study tag sequences of millions of questions in four Q&A sites, i.e., CodeProject, SegmentFault, Biostars, and CareerCup. Our results show that users of these Q&A sites can develop implicit consensus about in which order they should assign tags to questions. We study the relationships between tags that can explain the emergence of ing of tags. Our study opens the path to improve existing tag recommendation and Q&A site navigation by leveraging the ing of tags.

Keywords: Question and answering (Q&     A) sites     Tagging     Natural order     Skip gram    

A Screening Model for Probiotics Against Specific Metabolic Diseases Based on Caco-2 Monolayer Membrane Article

Yang Liu, Jiang Peng, Shiya Zhu, Leilei Yu, Fengwei Tian, Jianxin Zhao, Hao Zhang, Wei Chen, Qixiao Zhai

Engineering 2023, Volume 25, Issue 6,   Pages 222-233 doi: 10.1016/j.eng.2022.02.014

Abstract:

Recent studies have revealed the potency of probiotics in alleviating metabolic diseases associated with intestinal barrier dysfunction. However, an efficient model for screening probiotic strains against specific metabolic diseases has not been well developed. In the present study, a Caco-2 cell monolayer membrane model treated with tumor necrosis factor (TNF-α) or alcohol was used to evaluate the effect of 139 Lactobacillus strains on intestinal barrier function in vitro. We then selected 11 Lactobacillus strains with different regulatory abilities on the gut barrier to determine their effect against ovariectomy-induced osteoporosis or chronic alcoholic liver injury in vivo. Our results showed that the Pearson coefficient between the data of cell and animal models were 0.82 and −0.97 for the protection of probiotics against osteoporosis and alcoholic liver disease, respectively, suggesting the reliability of the cell model to simulate the in vivo protective effects of probiotics. This study established a potential in vitro approach based on a Caco-2 cell monolayer membrane model for the efficient screening of potential probiotics against specific metabolic diseases such as osteoporosis and chronic alcoholic liver disease.

Keywords: Lactobacillus     Intestinal barrier     Caco-2 cells     Screening model     Metabolic diseases    

Research on Features of Energy Utilized in the Field of Consumption

Jiang Yi,Zhu Andong and Guo Siyue

Strategic Study of CAE 2015, Volume 17, Issue 8,   Pages 122-131

Abstract:

According to the features of using process, the energy use could be divided into two categories including the energy use in the field of consumption (EUFC) to provide services and the energy using in the field of production (EUFP) to provide products. The feature of EUFC is different with EUFP, including evaluation methods, energy saving approach and developing strategy, etc. Considering its potential to be the main growing sector in the next period of energy consumption, more attention should be paid to EUFC. In this paper, based on the analysis of its features, the measure of EUFC and the energy saving approach are recommended, as well as the suggestions to the present situation in China.

Keywords: the field of consumption     the field of production     energy consumption     feature    

Technology Foresight Research on China’s Agricultural Engineering Science and Technology to 2035

Task Force for the Research on China’s Engineering Science and Technology Development Strategy 2035 Agriculture Research Group

Strategic Study of CAE 2017, Volume 19, Issue 1,   Pages 87-95 doi: 10.15302/J-SSCAE-2017.01.013

Abstract:

To improve the scientific judgment of the development strategy for China's agricultural engineering science and technology to 2035, the technology foresight method was used. This method entailed a wide collection of detailed technology foresight lists and two rounds of a questionnaire survey. Based on the survey results, which were studied and judged by specialists, overall development characteristics of agricultural engineering science and technology were confirmed, and then 12 directions for key technologies in agriculture were put forward. Furthermore, a development strategy for key technologies in agriculture was proposed in order to overcome a lack of talent and of R&D inputs in agriculture. In conclusion, technology foresight results can provide important support for creating development strategies for China's agricultural engineering science and technology to 2035.

Keywords: agricultural engineering science and technology     technology foresight     key technology     strategic research     Delphi method    

Internet of things for military engineering: Conceptual model, supporting technologies and domain applications

Yang Qiliang,Xing Jianchun,Wang Ping,Wang Shuangqing,Xie Liqiang,Wang Ronghao

Strategic Study of CAE 2013, Volume 15, Issue 5,   Pages 95-105

Abstract:

With the aim to promote the amalgamation between military engineering and command systems or weapon platforms, this paper introduces the ideas and technologies of internet of things (IoT) into the research area of military engineering, proposes the research concept: IoT of military engineering (MEIoT). In the paper, the basic concept of MEIoT is defined, and the conceptual model of it is also established. On the basis of discussing the technology challenges of MEIoT, this paper presents several research advances and fruits of the authors on the military-engineering-sensing technologies, network transportation technologies in special spaces of military engineering, the data mining and managing technologies for multi-mode data in military engineering, and software paradigm of MEIoT. Finally, an example of MEIoT applied in naval ports is provided. The research of MEIoT will be of great significance to enhance the integrated supporting and protective ability of military engineering.

Keywords: military engineering     internet of things     sensing engineering     data mining     software technology    

Multi-domain Knowledge Convergence Trajectory Analysis of Strategic Emerging Industries Based on Citation Network and Text Information

Liu Yufei, Miao Zhongzhen, Li Lingfeng, Kong Dejing

Strategic Study of CAE 2020, Volume 22, Issue 2,   Pages 120-129 doi: 10.15302/J-SSCAE-2020.02.016

Abstract:

 The analysis of technology convergence process for strategic emerging industries is helpful to deeply understand the generation process and development law of industrial technology, thereby helping master the development trend of the field and promoting the healthy development of the industry. To identify the trajectory and degree of technology convergence of the strategic emerging industries, this study conducts a multi-case study on four fields which present a trend of convergence and attract social attention, namely, high-end equipment manufacturing, new-generation information technology, new medicine, and new energy. This study adopts a knowledge convergence trajectory analysis method based on citation network and text information. It utilizes a graph neural network model and encodes the citation network, title, and abstract of the publications as vectors. Five knowledge convergence trajectories are identified, after analyzing the data of the selected four technical fields. The research results show that information technology and numerical control equipment, biomedicine and solar photovoltaic technology have shown a trend of deep convergence, respectively; and the convergence of the information technology and numerical control equipment is deeper. Numerical control equipment and solar photovoltaic technology, information technology and solar photovoltaic technology have shown a converging trend, respectively; however, the current degree of convergence is still insufficient, due to the late start of convergence. Numerical control equipment and biomedicine have not shown any trend of convergence.

Keywords: emerging industries     knowledge convergence     graph neural networks     citation network     topic model    

The Roles of Nuclear Energy in Hydrogen Production Views & Comments

Shinji Kubo

Engineering 2022, Volume 16, Issue 9,   Pages 16-20 doi: 10.1016/j.eng.2021.12.024

A Review of the Application of Additive Manufacturing in Prosthetic and Orthotic Clinics from a Biomechanical Perspective Review

Yan Wang, Qitao Tan, Fang Pu, David Boone, Ming Zhang

Engineering 2020, Volume 6, Issue 11,   Pages 1258-1266 doi: 10.1016/j.eng.2020.07.019

Abstract:

Prostheses and orthoses are common assistive devices to meet the biomechanical needs of people with physical disabilities. The traditional fabrication approach for prostheses or orthoses is a materialwasting, time-consuming, and labor-intensive process. Additive manufacturing (AM) technology has advantages that can solve these problems. Many trials have been conducted in fabricating prostheses and orthoses. However, there is still a gap between the hype and the expected realities of AM in prosthetic and orthotic clinics. One of the key challenges is the lack of a systematic framework of integrated technologies with the AM procedure; another challenge is the need to design a prosthetic or orthotic product that can meet the requirements of both comfort and function. This study reviews the current state of application of AM technologies in prosthesis and orthosis fabrication, and discusses optimal design using computational methods and biomechanical evaluations of product performance. A systematic framework of the AM procedure is proposed, which covers the scanning of affected body parts through to the final designed adaptable product. A cycle of optimal design and biomechanical evaluation of products using finite-element analysis is included in the framework. A mature framework of the AM procedure and sufficient evidence that the resulting products show satisfactory biomechanical performance will promote the application of AM in prosthetic and orthotic clinics.

Keywords: Additive manufacturing     Biomechanics of the musculoskeletal system     Computational model     Prostheses and orthoses     3D printing    

Development Strategy and Key Areas of China5 s Space Activities

Sun Laiyan

Strategic Study of CAE 2006, Volume 8, Issue 10,   Pages 6-12

Abstract:

This paper reviews the achievements of China´s space industry made in the past 50 years, summarizes the experiences and problems, and, against the backdrop of the developing trend of international space activities, describes the future development strategy and key areas of China´s space industry.

Keywords: China's space activities     development strategy     key areas    

Domain knowledge enhanced deep learning for electrocardiogram arrhythmia classification Research Article

Jie SUN,sunjie@nbut.edu.cn

Frontiers of Information Technology & Electronic Engineering 2023, Volume 24, Issue 1,   Pages 59-72 doi: 10.1631/FITEE.2100519

Abstract: Deep learning provides an effective way for automatic classification of s, but in , pure data-driven methods working as black-boxes may lead to unsatisfactory results. A promising solution is combining with deep learning. This paper develops a flexible and extensible framework for integrating with a deep neural network. The model consists of a deep neural network to capture the statistical pattern between input data and the ground-truth label, and a knowledge module to guarantee consistency with the . These two components are trained interactively to bring the best of both worlds. The experiments show that the is valuable in refining the neural network prediction and thus improves accuracy.

Keywords: Domain knowledge     Cardiac arrhythmia     Electrocardiogram (ECG)     Clinical decision-making    

U.S. green BIM application situation and its influence on Chinese construction field

Yang Yu,Yin Hang

Strategic Study of CAE 2011, Volume 13, Issue 8,   Pages 103-112

Abstract:

In recent years, the green BIM(building information model) has caught the attention of the U.S. and other developed countries in the field of construction, and most of the projects that use Green BIM technology have already achieved good effect which combines sustainability with economy. Although there are still many problems in Green BIM practice, green BIM has become the inevitable trend of construction. Based on the application situation of green BIM in the U.S., this article analyzes its influence on construction field in China. In the author’s opinion, compared with green BIM in America, green BIM in China starts so late that there is a huge gap in technology between the two countries. In the process of development, China should fully absorb the practical experience of green BIM in America and combine the characteristics of construction field in China to form a proper green BIM operation process which accords with the situation of China. It is proposed that more attention should be paid to Green BIM application in different types of project and in the choice of building product material and renewable energy. Meanwhile, technical localization should be strengthened and government should invest more in it to promote the development of green building and achieve the goals of energy saving and emission reduction.

Keywords: BIM     green BIM     green building     sustainability     economy     construction fiel    

Preliminary Study on Impact of Disruptive Technologies in Chemical, Metallurgical, and Material Fields

The Research Group of Chemical, Metallurgical, and Material Fields

Strategic Study of CAE 2018, Volume 20, Issue 6,   Pages 34-41 doi: 10.15302/J-SSCAE-2018.06.006

Abstract:

The chemical, metallurgical and material industries re-process natural resources to produce materials, chemicals, and secondary energies necessary for human life, thereby providing an important material basis for social development and economic construction. This paper reviews the recognized disruptive technologies in the history of chemical, metallurgical, and material industries, and analyzes the impact of such technologies on people's daily lives, the progress of human society, and the disruption of traditional technologies. According to vision driving, problem orientation, and the world technology development trend, we forecast the future sustainable science development models, which are efficient, safe, energy-saving, and environment-friendly, in the chemical, metallurgical, and material industries, and predict the impacts of possible disruptive technologies on national economy and people’s livelihood. The slurry bed hydro-conversion technology, the metallurgical manufacturing process function expansion technology, grapheme, and other disruptive technologies are proposed. Finally, relevant policies and suggestions are put forward for the cultivation, development, and environment of disruptive technologies.

Keywords: chemical industry     metallurgy     material     disruptive technology     national economy and people’s livelihood    

Cognition Field of Chinese Medical Knowledge and Some Special Topics

Fu Jinghua

Strategic Study of CAE 2006, Volume 8, Issue 3,   Pages 7-10

Abstract:

The strategic position of TCM has increasingly been attracting peoples' attention. In order to make TCM more understood, the paper describes the cognition field, cognition process, the scope and network and the practice goal of Chinese medical knowledge, as well as some special topics such as the yin-yang and five elements, the visceral outward manifestation and the channels and collaterals, the pathogeny, the rule of treatment and material medica, etc.

Keywords: Chinese medical knowledge     cognition field     theory of TCM    

Words alignment based on association rules for cross-domain sentiment classification None

Xi-bin JIA, Ya JIN, Ning LI, Xing SU, Barry CARDIFF, Bir BHANU

Frontiers of Information Technology & Electronic Engineering 2018, Volume 19, Issue 2,   Pages 260-272 doi: 10.1631/FITEE.1601679

Abstract: Automatic classification of sentiment data (e.g., reviews, blogs) has many applications in enterprise user management systems, and can help us understand people’s attitudes about products or services. However, it is difficult to train an accurate sentiment classifier for different domains. One of the major reasons is that people often use different words to express the same sentiment in different domains, and we cannot easily find a direct mapping relationship between them to reduce the differences between domains. So, the accuracy of the sentiment classifier will decline sharply when we apply a classifier trained in one domain to other domains. In this paper, we propose a novel approach called words alignment based on association rules (WAAR) for cross-domain sentiment classification, which can establish an indirect mapping relationship between domain-specific words in different domains by learning the strong association rules between domain-shared words and domain-specific words in the same domain. In this way, the differences between the source domain and target domain can be reduced to some extent, and a more accurate cross-domain classifier can be trained. Experimental results on AmazonR datasets show the effectiveness of our approach on improving the performance of cross-domain sentiment classification.

Keywords: Sentiment classification     Cross-domain     Association rules    

Title Author Date Type Operation

A Survey of Accelerator Architectures for Deep Neural Networks

Yiran Chen, uan Xie, Linghao Song, Fan Chen, Tianqi Tang

Journal Article

Learning natural ordering of tags in domain-specific Q&A sites

Junfang Jia, Guoqiang Li,jiajunfang816@163.com,li.g@sjtu.edu.cn

Journal Article

A Screening Model for Probiotics Against Specific Metabolic Diseases Based on Caco-2 Monolayer Membrane

Yang Liu, Jiang Peng, Shiya Zhu, Leilei Yu, Fengwei Tian, Jianxin Zhao, Hao Zhang, Wei Chen, Qixiao Zhai

Journal Article

Research on Features of Energy Utilized in the Field of Consumption

Jiang Yi,Zhu Andong and Guo Siyue

Journal Article

Technology Foresight Research on China’s Agricultural Engineering Science and Technology to 2035

Task Force for the Research on China’s Engineering Science and Technology Development Strategy 2035 Agriculture Research Group

Journal Article

Internet of things for military engineering: Conceptual model, supporting technologies and domain applications

Yang Qiliang,Xing Jianchun,Wang Ping,Wang Shuangqing,Xie Liqiang,Wang Ronghao

Journal Article

Multi-domain Knowledge Convergence Trajectory Analysis of Strategic Emerging Industries Based on Citation Network and Text Information

Liu Yufei, Miao Zhongzhen, Li Lingfeng, Kong Dejing

Journal Article

The Roles of Nuclear Energy in Hydrogen Production

Shinji Kubo

Journal Article

A Review of the Application of Additive Manufacturing in Prosthetic and Orthotic Clinics from a Biomechanical Perspective

Yan Wang, Qitao Tan, Fang Pu, David Boone, Ming Zhang

Journal Article

Development Strategy and Key Areas of China5 s Space Activities

Sun Laiyan

Journal Article

Domain knowledge enhanced deep learning for electrocardiogram arrhythmia classification

Jie SUN,sunjie@nbut.edu.cn

Journal Article

U.S. green BIM application situation and its influence on Chinese construction field

Yang Yu,Yin Hang

Journal Article

Preliminary Study on Impact of Disruptive Technologies in Chemical, Metallurgical, and Material Fields

The Research Group of Chemical, Metallurgical, and Material Fields

Journal Article

Cognition Field of Chinese Medical Knowledge and Some Special Topics

Fu Jinghua

Journal Article

Words alignment based on association rules for cross-domain sentiment classification

Xi-bin JIA, Ya JIN, Ning LI, Xing SU, Barry CARDIFF, Bir BHANU

Journal Article