Search scope:
排序: Display mode:
Software development in the age of intelligence: embracing large language models with the right approach Perspective
Xin PENG
Frontiers of Information Technology & Electronic Engineering 2023, Volume 24, Issue 11, Pages 1513-1519 doi: 10.1631/FITEE.2300537
Keywords: 大语言模型;ChatGPT;软件工程;软件开发
Pre-Trained Language Models and Their Applications Review
Haifeng Wang, Jiwei Li, Hua Wu, Eduard Hovy, Yu Sun
Engineering 2023, Volume 25, Issue 6, Pages 51-65 doi: 10.1016/j.eng.2022.04.024
Pre-trained language models have achieved striking success in natural language processing (NLP), leading to a paradigm shift from supervised learning to pre-training followed by fine-tuning. The NLP community has witnessed a surge of research interest in improving pre-trained models. This article presents a comprehensive review of representative work and recent progress in the NLP field and introduces the taxonomy of pre-trained models. We first give a brief introduction of pre-trained models, followed by characteristic methods and frameworks. We then introduce and analyze the impact and challenges of pre-trained models and their downstream applications. Finally, we briefly conclude and address future research directions in this field.
Progress in Neural NLP: Modeling, Learning, and Reasoning Review
Ming Zhou, Nan Duan, Shujie Liu, Heung-Yeung Shum
Engineering 2020, Volume 6, Issue 3, Pages 275-290 doi: 10.1016/j.eng.2019.12.014
Natural language processing (NLP) is a subfield of artificial intelligence (AI) that focuses on enabling computers to understand and process human languages. In the last five years, we have witnessed the rapid development of NLP in tasks such as machine translation, question-answering, and machine reading comprehension based on deep learning and an enormous volume of annotated and unannotated data. In this paper, we will review the latest progress in the neural network-based NLP framework (neural NLP) from three perspectives: modeling, learning, and reasoning. In the modeling section, we will describe several fundamental neural network-based modeling paradigms, such as word embedding, sentence embedding, and sequence-to-sequence modeling, which are widely used in modern NLP engines. In the learning section, we will introduce widely used learning methods for NLP models, including supervised, semi-supervised, and unsupervised learning; multitask learning; transfer learning; and active learning. We view reasoning as a new and exciting direction for neural NLP, but it has yet to be well addressed. In the reasoning section, we will review reasoning mechanisms, including the knowledge, existing non-neural inference methods, and new neural inference methods. We emphasize the importance of reasoning in this paper because it is important for building interpretable and knowledge-driven neural NLP models to handle complex tasks. At the end of this paper, we will briefly outline our thoughts on the future directions of neural NLP.
Keywords: Natural language processing Deep learning Modeling learning and Reasoning
Indeterminacy Causal Inductive Automatic Reasoning Mechanism Based On Fuzzy State Describing
Yang Bingru,Tang Jing
Strategic Study of CAE 2000, Volume 2, Issue 5, Pages 44-50
New framework of knowledge representation of fuzzy language field and fuzzy language value structure is shown in this paper. Then the generalized cell automation that can synthetically process fuzzy indeterminacy and random indeterminacy and the generalized inductive logic causal model are brought forward. On this basis, the new logic indeterminate causal inductive automatic reasoning mechanism which is based on fuzzy state describing is brought forward. At the end of this paper its application in the development of intelligent controller is discussed.
Keywords: language field language value structure generalized cell automation generalized inductive logic causal model automatic reasoning intelligent controller
Study on the synergistic experimental model of long span steel bridge deck pavement system
Xia Guoxing,Qian Zhendong,Chen Chun and Liu Yan
Strategic Study of CAE 2012, Volume 14, Issue 5, Pages 96-100
In order to reflect the synergistic effect and working environment of the long-span steel bridge deck-pavement system truly in laboratory experiments, this paper studies the synergistic experimental model of flexible long-span steel bridge deck-pavement system. Firstly, the local box girder FEM(finite element method) model considering the whole bridge deformation is established. And the deck pavement's stress and strain are analyzed. The entire bridge effect parameter is 1.17. Then, the synergistic experimental model is established.Taking the maximum stress and strain value of local beam section as reference value, the related structure parameters of early model scheme are revised. On this basis, to ensure the consistency of designing for the synergy model and the prototype, stress value of the revised test model and local beam section model in the control point is compared. Eventually, the synergistic experimental model of long-span steel bridge deck-pavement system is obtained in this paper. The results may provide theoretical basis for designing of laboratory experiment model on steel bridge deck.
Keywords: synergistic experimental model long-span steel bridge deck-pavement system
Effect analysis of fire location on fire growth in large space
Shi Long,Zhang Ruifang,Xie Qiyuan,Fu Lihua
Strategic Study of CAE 2008, Volume 10, Issue 11, Pages 37-42
Fire design is the basis of quantitative evaluation in performance-based fire design, which includes the determination of fire location and heat release rate (HRR). Take large-scale exhibition hall for example, utilizing fire radiation model and smoke radiation model and combining the simulate result of CFAST 6.0, analysis of fire grown situation is taken with different fire locations in large space. Research reveals: only considering fire radiation, when fire develops in a location of bilateral symmetry, fire grows faster with HRR peak values are larger and the time of attain HRR peak value earlier and duration time are shorter than others. Thereinto, fire grow fastest when fire develops in the location of center symmetry. Moreover, combining fire radiation and smoke radiation, HRR peak values consumedly increases and almost the same in each scenarios. But other rules, which contain fire growth and the correlative time, when considering fire radiation and smoke radiation, is the same as the situation of just considering fire radiation.
Keywords: fire growth fire design in large space fire location fire radiation model smoke radiation model
Incorporating target language semantic roles into a string-to-tree translation model Article
Chao SU, Yu-hang GUO, He-yan HUANG, Shu-min SHI, Chong FENG
Frontiers of Information Technology & Electronic Engineering 2017, Volume 18, Issue 10, Pages 1534-1542 doi: 10.1631/FITEE.1601349
Keywords: Machine translation Semantic role Syntax tree String-to-tree
Emerging topic identification from app reviews via adaptive online biterm topic modeling Research Article
Wan ZHOU, Yong WANG, Cuiyun GAO, Fei YANG,yongwang@ahpu.edu.cn
Frontiers of Information Technology & Electronic Engineering 2022, Volume 23, Issue 5, Pages 678-691 doi: 10.1631/FITEE.2100465
Keywords: App reviews Emerging topic identification Topic model Natural language processing
Reduced torque ripple for rotational load with high inertia of HY-2A satellite
Zhou Yong,Li Zhengjun,Ma Chao and Wang Xiaoning
Strategic Study of CAE 2014, Volume 16, Issue 3, Pages 43-49
Taking into account attitude stability,microwave scattermeter and microwave radiometer while rotating need to reduce torque ripple. Permanent-magnet motors using vector control technique are used to drive directly both sensors. Restraining cogging torque of motor, eliminating quantization error with fix angle timing,compensating dead time,these are presented. The control system and motor has been simulated by accurate model,results show that the torque ripple is reduced. The orbital attitude speed results are presented to validate this scheme.
Keywords: high inertia torque ripple quantization error dead time accurate model
Chen Zhijian,Zhou Shizhong ,Zhuo Jiashou
Strategic Study of CAE 2002, Volume 4, Issue 6, Pages 20-24
After stating the complexity of stability problem and the importance and technical difficulty to make safety monitoring model for layered rocky slope of foundation of the south tower and resistance body of south anchorage in Jiangyin Yangtze Bridge, this paper introduces the technical methods to wake the model of tower load distribution, the monitoring and alarm model of residual anchorage thrust, j. e. , cause factor of slope stability, the comprehensive fuzzy evaluation model for slope safety based on external deformation observation results and the forecast model for the stability of layered rocky slope based on observed internal shear displacement.
Keywords: layered rock mass slope monitoring and forecast model technical methods
A Comparative Assessment of Aerodynamic Models for Buffeting and Flutter of Long-Span Bridges
Igor Kavrakov, Guido Morgenthal
Engineering 2017, Volume 3, Issue 6, Pages 823-838 doi: 10.1016/j.eng.2017.11.008
Wind-induced vibrations commonly represent the leading criterion in the design of long-span bridges. The aerodynamic forces in bridge aerodynamics are mainly based on the quasi-steady and linear unsteady theory. This paper aims to investigate different formulations of self-excited and buffeting forces in the time domain by comparing the dynamic response of a multi-span cable-stayed bridge during the critical erection condition. The bridge is selected to represent a typical reference object with a bluff concrete box girder for large river crossings. The models are viewed from a perspective of model complexity, comparing the influence of the aerodynamic properties implied in the aerodynamic models, such as aerodynamic damping and stiffness, fluid memory in the buffeting and self-excited forces, aerodynamic nonlinearity, and aerodynamic coupling on the bridge response. The selected models are studied for a windspeed range that is typical for the construction stage for two levels of turbulence intensity. Furthermore, a simplified method for the computation of buffeting forces including the aerodynamic admittance is presented, in which rational approximation is avoided. The critical flutter velocities are also compared for the selected models under laminar flow.
Keywords: Buffeting Flutter Long-span bridges Bridge aerodynamics Bridge aeroelasticity Erection stage
Bulk Glassy Alloys: Historical Development and Current Research Review
Akihisa Inoue
Engineering 2015, Volume 1, Issue 2, Pages 185-191 doi: 10.15302/J-ENG-2015038
This paper reviews the development of current research in bulk glassy alloys by focusing on the trigger point for the synthesis of the first bulk glassy alloys by the conventional mold casting method. This review covers the background, discovery, characteristics, and applications of bulk glassy alloys, as well as recent topics regarding them. Applications of bulk glassy alloys have been expanding, particularly for Fe-based bulk glassy alloys, due to their unique properties, high glass-forming ability, and low cost. In the near future, the engineering importance of bulk glassy alloys is expected to increase steadily, and continuous interest in these novel metallic materials for basic science research is anticipated.
Keywords: bulk glassy alloys mold casting metallic materials structural relaxation
Design and Application of Clinical Big Data Management System for Oncology
Ma Lin, Bao Chenlu, Li Qing,Wu Jingyi, Pan Hong’an, Li Pengfei, Zhang Luxia, Zhan Qimin
Strategic Study of CAE 2022, Volume 24, Issue 6, Pages 127-136 doi: 10.15302/J-SSCAE-2022.06.011
Cancer is a serious threat to human life and health. Along with the development of medical informatization in China, healthcare institutions have cumulated a great quantity of clinical data in oncology; however, these data have not been fully explored owing to the disunity of data standards and great difficulties in data management. Hence, establishing a national clinical big data management system for oncology based on artificial intelligence could potentially promote the application of clinical data in oncology, further improving the quality and efficiency of clinical management for oncology. This study conducted an in-depth analysis of the problems and challenges of clinical data management and application for oncology and presented the significant values of an oncology clinical data management system. Considering the complexity of multi-source and multi-modal data in oncology, we explored the possible mechanisms and pathways of applying artificial intelligence to the management and research of clinical data for oncology Furthermore, a full-circle solution was designed, and the construction framework and technology systems were promoted for the clinical data management system for oncology, including the development of common data models for oncology, data collection and security management, data standardization and structuring, data analysis and application, and data quality control. Besides, we validated the feasibility and benefits of the promoted system in clinical practice by taking the clinical data management for lung cancer in a tertiary hospital as an example. Finally, we proposed some suggestions on the research directions of the clinical big data management system for oncology.
Keywords: clinical big data management system oncology artificial intelligence common data model natural language processing
A framework for an integrated unified modeling language
Mohammad ALSHAYEB,Nasser KHASHAN,Sajjad MAHMOOD
Frontiers of Information Technology & Electronic Engineering 2016, Volume 17, Issue 2, Pages 143-159 doi: 10.1631/FITEE.1500094
The unified modeling language (UML) is one of the most commonly used modeling languages in the software industry.It simplifies the complex process of design by providing a set of graphical notations, which helps express the objectoriented analysis and design of software projects. Although UML is applicable to different types of systems, domains, methods,and processes, it cannot express certain problem domain needs. Therefore, many extensions to UML have been proposed. In this paper, we propose a framework for integrating the UML extensions and then use the framework to propose an integrated unified modeling language-graphical (iUML-g) form. iUML-g integrates the existing UML extensions into one integrated form. This includes an integrated diagram for UML class, sequence, and use case diagrams. The proposed approach is evaluated using a case study. The proposed iUML-g is capable of modeling systems that use different domains.
Keywords: Unified modeling language (UML) Integration Modeling System analysis and design
Active Virtual Server and a Novel Mechanism for Data Integration over Internet
He Xingui,Yang Lianghuai,Tang Shiwei,Yang Dongqing,Chen Lijun,Zhang Zhen,Lin Bin
Strategic Study of CAE 2001, Volume 3, Issue 5, Pages 55-60
Aiming at solving the problems of information retrieval and data integration over Internet, the idea of “active virtual server” is proposed, and a novel mechanism for data integration based on the virtual server is presented. Active virtual servers can be regarded as the uniform storage and processor of massive data over Internet, with the function of active services. By only using a unified extendable language (UXL) to wrap each kind of server with a uniform interface “active service coat”,the “active virtual server” can be constructed as needed without changing the original DBMS on the server. The above “coat” needs to be done only once for each kind of server, and can be exploited uniformly all over the Internet, hence it plays the role as Java Virtual Machine does.
Keywords: active virtual server data integration extendable markup language (XML) unified extendable (UXL) information agent
Title Author Date Type Operation
Software development in the age of intelligence: embracing large language models with the right approach
Xin PENG
Journal Article
Pre-Trained Language Models and Their Applications
Haifeng Wang, Jiwei Li, Hua Wu, Eduard Hovy, Yu Sun
Journal Article
Progress in Neural NLP: Modeling, Learning, and Reasoning
Ming Zhou, Nan Duan, Shujie Liu, Heung-Yeung Shum
Journal Article
Indeterminacy Causal Inductive Automatic Reasoning Mechanism Based On Fuzzy State Describing
Yang Bingru,Tang Jing
Journal Article
Study on the synergistic experimental model of long span steel bridge deck pavement system
Xia Guoxing,Qian Zhendong,Chen Chun and Liu Yan
Journal Article
Effect analysis of fire location on fire growth in large space
Shi Long,Zhang Ruifang,Xie Qiyuan,Fu Lihua
Journal Article
Incorporating target language semantic roles into a string-to-tree translation model
Chao SU, Yu-hang GUO, He-yan HUANG, Shu-min SHI, Chong FENG
Journal Article
Emerging topic identification from app reviews via adaptive online biterm topic modeling
Wan ZHOU, Yong WANG, Cuiyun GAO, Fei YANG,yongwang@ahpu.edu.cn
Journal Article
Reduced torque ripple for rotational load with high inertia of HY-2A satellite
Zhou Yong,Li Zhengjun,Ma Chao and Wang Xiaoning
Journal Article
Technical Methods to Make Safety Monitoring and Forecast Models for the Foundation of Long Suspension Bridges
Chen Zhijian,Zhou Shizhong ,Zhuo Jiashou
Journal Article
A Comparative Assessment of Aerodynamic Models for Buffeting and Flutter of Long-Span Bridges
Igor Kavrakov, Guido Morgenthal
Journal Article
Design and Application of Clinical Big Data Management System for Oncology
Ma Lin, Bao Chenlu, Li Qing,Wu Jingyi, Pan Hong’an, Li Pengfei, Zhang Luxia, Zhan Qimin
Journal Article
A framework for an integrated unified modeling language
Mohammad ALSHAYEB,Nasser KHASHAN,Sajjad MAHMOOD
Journal Article