Resource Type

Journal Article 297

Year

2024 1

2023 40

2022 29

2021 25

2020 27

2019 31

2018 21

2017 23

2016 16

2015 6

2014 5

2013 6

2012 6

2011 5

2010 6

2009 6

2008 7

2007 7

2006 7

2005 3

open ︾

Keywords

Big data 9

Machine learning 8

big data 6

data mining 6

Blockchain 5

Deep learning 5

Artificial intelligence 4

Data-driven 3

Anomaly detection 2

Big data analytics 2

Cyber-physical systems 2

Data mining 2

Data privacy 2

Data science 2

Data-driven method 2

Database schemata 2

Fog computing 2

Information schema constructs 2

Materials design 2

open ︾

Search scope:

排序： Display mode:

Information Sunshine: the Collisionless Information Sharing Architecture

Li Youping

Strategic Study of CAE 2000, Volume 2, Issue 1,   Pages 24-27

Abstract:

The novel information sharing architecture, Information Sunshine, is presented in the paper. It is collisionless, and based on data broadcasting networks other than bi-directional TCP/IPs. Two core concepts of the Information Sunshine idea are Data Stream Environment (DSE) and Personal Demanding Code (PDC). The DSE means that several hundreds gigabytes stream to each household everyday utilizing the great data push .capacity of DVB, and then the nationwide flow of the high speed data stream forms a digital environment. The data flux is so great that thousands of papers, periodicals, Web Server and courseware could be rolling broadcast for several dozens times per day. The PDC code helps each user distinguish favorite contents from broadcasting data stream and intercept them into local hard disk. After storing, users can locally interact with the information without remote connection requirement. Only single-way broadcasting network required by the Information Sunshine architecture, so it is low cost and will drastically eliminate inherent bandwidth collision of bi-directional IP architecture.

Keywords： Data broadcasting     DVB     network     collisionless    

HTML PDF Collect

Learning to select pseudo labels: a semi-supervised method for named entity recognition Research Articles

Zhen-zhen Li, Da-wei Feng, Dong-sheng Li, Xi-cheng Lu,lizhenzhen14@nudt.edu.cn,davyfeng.c@gmail.com,dsli@nudt.edu.cn,xclu@nudt.edu.cn

Frontiers of Information Technology & Electronic Engineering 2020, Volume 21, Issue 6,   Pages 809-962 doi: 10.1631/FITEE.1800743

Abstract: models have achieved state-of-the-art performance in (NER); the good performance, however, relies heavily on substantial amounts of labeled data. In some specific areas such as medical, financial, and military domains, labeled data is very scarce, while is readily available. Previous studies have used to enrich word representations, but a large amount of entity information in is neglected, which may be beneficial to the NER task. In this study, we propose a for NER tasks, which learns to create high-quality labeled data by applying a pre-trained module to filter out erroneous pseudo labels. Pseudo labels are automatically generated for and used as if they were true labels. Our semi-supervised framework includes three steps: constructing an optimal single neural model for a specific NER task, learning a module that evaluates pseudo labels, and creating new labeled data and improving the NER model iteratively. Experimental results on two English NER tasks and one Chinese clinical NER task demonstrate that our method further improves the performance of the best single neural model. Even when we use only pre-trained static word embeddings and do not rely on any external knowledge, our method achieves comparable performance to those state-of-the-art models on the CoNLL-2003 and OntoNotes 5.0 English NER tasks.

Keywords： 命名实体识别；无标注数据；深度学习；半监督学习方法    

HTML PDF Collect

Interactive visual labelling versus active learning: an experimental comparison Research

Mohammad CHEGIN, Jürgen BERNARD, Jian CUI, Fatemeh CHEGINI, Alexei SOURIN, Keith Keith, Tobias SCHRECK

Frontiers of Information Technology & Electronic Engineering 2020, Volume 21, Issue 4,   Pages 524-535 doi: 10.1631/FITEE.1900549

Abstract: Methods from supervised machine learning allow the classification of new data automatically and are tremendously helpful for data analysis. The quality of supervised maching learning depends not only on the type of algorithm used, but also on the quality of the labelled dataset used to train the classifier. Labelling instances in a training dataset is often done manually relying on selections and annotations by expert analysts, and is often a tedious and time-consuming process. Active learning algorithms can automatically determine a subset of data instances for which labels would provide useful input to the learning process. Interactive visual labelling techniques are a promising alternative, providing effective visual overviews from which an analyst can simultaneously explore data records and select items to a label. By putting the analyst in the loop, higher accuracy can be achieved in the resulting classifier. While initial results of interactive visual labelling techniques are promising in the sense that user labelling can improve supervised learning, many aspects of these techniques are still largely unexplored. This paper presents a study conducted using the mVis tool to compare three interactive visualisations, similarity map, scatterplot matrix (SPLOM), and parallel coordinates, with each other and with active learning for the purpose of labelling a multivariate dataset. The results show that all three interactive visual labelling techniques surpass active learning algorithms in terms of classifier accuracy, and that users subjectively prefer the similarity map over SPLOM and parallel coordinates for labelling. Users also employ different labelling strategies depending on the visualisation used.

Keywords： Interactive visual labelling     Active learning     Visual analytics    

HTML PDF Collect

FAAD: an unsupervised fast and accurate anomaly detectionmethod for amulti-dimensional sequence over data stream Regular Papers

Bin LI, Yi-jie WANG, Dong-sheng YANG, Yong-mou LI, Xing-kong MA

Frontiers of Information Technology & Electronic Engineering 2019, Volume 20, Issue 3,   Pages 388-404 doi: 10.1631/FITEE.1800038

Abstract:

Recently, sequence anomaly detection has been widely used in many fields. Sequence data in these fields are usually multi-dimensional over the data stream. It is a challenge to design an anomaly detection method for a multi-dimensional sequence over the data stream to satisfy the requirements of accuracy and high speed. It is because: (1) Redundant dimensions in sequence data and large state space lead to a poor ability for sequence modeling; (2) Anomaly detection cannot adapt to the high-speed nature of the data stream, especially when concept drift occurs, and it will reduce the detection rate. On one hand, most existing methods of sequence anomaly detection focus on the single-dimension sequence. On the other hand, some studies concerning multi-dimensional sequence concentrate mainly on the static database rather than the data stream. To improve the performance of anomaly detection for a multi-dimensional sequence over the data stream, we propose a novel unsupervised fast and accurate anomaly detection (FAAD) method which includes three algorithms. First, a method called “information calculation and minimum spanning tree cluster” is adopted to reduce redundant dimensions. Second, to speed up model construction and ensure the detection rate for the sequence over the data stream, we propose a method called “random sampling and subsequence partitioning based on the index probabilistic suffix tree.” Last, the method called “anomaly buffer based on model dynamic adjustment” dramatically reduces the effects of concept drift in the data stream. FAAD is implemented on the streaming platform Storm to detect multi-dimensional log audit data. Compared with the existing anomaly detection methods, FAAD has a good performance in detection rate and speed without being affected by concept drift.

Keywords： Data stream     Multi-dimensional sequence     Anomaly detection     Concept drift     Feature selection    

HTML PDF Collect

A Preliminary Study on the Strategy of Construction a “No-Waste Society” by Piloting “No-Waste City” to Promote the Resource Utilization of Solid Waste

Du Xiangwan,Liu Xiaolong,Ge Qin,Jiang Lingling and Cui Leilei

Strategic Study of CAE 2017, Volume 19, Issue 4,   Pages 119-123 doi: 10.15302/J-SSCAE-2017.04.019

Abstract:

The large amount of solid waste in China, if not properly handled, will cause serious environmental problems, lead to a waste of resources, and bring about adverse effects on society. Solid waste is a misplaced resource; thus, reducing or resource utilization solid waste to build a "no-waste society" will yield significant environmental, social, and economic benefits. Based on an analysis of significant existing problems hindering the construction of a "no-waste society" in China, along with feasibility studies, this paper suggests that it is necessary to promote the resource utilization of solid waste by piloting "no-waste city," from which to build a "no-waste society." Other strategic suggestions such as strengthening the top-level design, consolidating a foundation, defining stage objectives, and increasing policy support are also proposed in this paper.

Keywords： “no-waste society”     “no-waste city”     solid waste     resource utilization     strategic suggestions    

HTML PDF Collect

Unstressed state control method for process control of structure formed by stages

Qin Shunquan

Strategic Study of CAE 2009, Volume 11, Issue 10,   Pages 72-78

Abstract:

This paper establishes a mechanical equilibrium equation for structure in any construction process of bridge formed by stages, and thus concludes that the core of process control for stage-constructed bridge is the quantity of unstressed state of structural elements. The control and adjustment of quantity of unstressed state of the structural elements provides a solution to the problem of rection calculation for bridge constructed by stages. Based on the principle that internal force and displacement have nothing to do with the construction process on the premise of a constant quantity of unstressed state, parallel operation of multiple working procedures can be put into practice, and the automatic filtration of influences from temporary load and temperature during construction can be therefore well realized.

Keywords： bridge constructed by stages     unstressed length     unstressed curvature     parallel operation     erection calculation    

HTML PDF Collect

A Survey of the Observability for Single Observer Passive Location

Deng Xinpu

Strategic Study of CAE 2007, Volume 9, Issue 11,   Pages 54-62

Abstract:

A basic requirement for passive state estimation using single observer is the existence of a unique tracking solution.  This leads to the question of observability. The target state is observable over the time interval if,  and only if,  it is uniquely determined by the measurements taken in that interval.  In this paper,  the state-observability problem for passive target tracking by angle measurements is analyzed using three methods: the geometrical method,  the elementary algebraic method and linear system method.  The observability for target tracking with frequency measurements is also analyzed.  Degree of observability is discussed.  And a concise review of papers on observability analysis is presented.

Keywords： passive location     TMA     observability    

HTML PDF Collect

Constructing a “No-Waste Society”

Liu Xiaolong, Jiang Lingling, Ge Qin, Huhetaoli, Chen Ying, Cui Leilei, Li Bin, Du Xiangwan

Strategic Study of CAE 2019, Volume 21, Issue 5,   Pages 144-150 doi: 10.15302/J-SSCAE-2019.05.003

Abstract:

Solid waste reduction and resource utilization is a sign of national progress and modernization. The massive amount of solid wastes produced in industrial production and daily life in China has not been well treated, and the annual output of solid wastes is growing year by year. It is proposed in this paper that “no-waste society” is not a society without solid waste production, but a society where most of its solid wastes are properly reused as resources. “No-waste society” is guided by the new development concepts of innovation, coordination, green, openness, and sharing, and promotes green and recycling development and living modes, thus to achieve source reduction, resource utilization, and harmless treatment of solid wastes to the maximum extent. This paper further clarifies the boundary and scope for the “no-waste society”, depicts its characteristics, and proposes the general idea and direction of developing from “no-waste city” to “no-waste society”. Furthermore, policy measures are proposed including strengthening collaboration and supervision; advocating a diligent and thrifty life concept; and enhancing international exchange to actively participate in the construction of a global system for environment governance.

Keywords： no-waste society     no-waste city     solid waste     resource utilization     production mode     life mode    

HTML PDF Collect

Deformation monitoring and assessment technology for substructure of unballasted track on railway passenger dedicated line

Li Mingling

Strategic Study of CAE 2009, Volume 11, Issue 1,   Pages 48-59

Abstract:

The criterion for residual deformation of Substructure of unballasted track on railway passenger dedicated line is extremely strict in order to satisfy the safety and comfort requirements of the high-speed train. Based on new Wuhan(Guangzhou railway passenger dedicated line engineering practice,this paper introuduces the key technologies for the deformation monitoring, data management and analysis system, the prediction method and assessment criterion are put forward to determine the reasonable time of unballasted track laying to guarantee the quality of unballasted track. Some advice provide reference for the ongoing unballasted track on railway passenger dedicated line construction.

Keywords： unballasted track     deformation monitoring     analysis and assessment     condiction for unballasted track laying    

HTML PDF Collect

Passive Intermodulation Measurement: Challenges and Solutions Review

Zhanghua Cai, Lie Liu, Francesco de Paulis, Yihong Qi

Engineering 2022, Volume 14, Issue 7,   Pages 181-191 doi: 10.1016/j.eng.2022.02.012

Abstract:

In modern wireless communication systems, the signal-to-noise ratio (SNR) is one of the most important performance indicators. When the other radio frequency (RF) performance of the components is well designed, passive intermodulation (PIM) interference may become an important factor limiting the system’s SNR. Whether it is a base station, an indoor distributed antenna system, or a satellite system, there are stringent PIM level requirements to minimize interference and enhance network capacity in multicarrier networks. Especially for systems of high power and wide bandwidth such as 5G wireless communication, PIM interference is even more serious. Due to the complexity and uncertainty of PIM, measurement is the most important means to study and evaluate the PIM performance of wireless communication systems. In this review, the current main PIM measurement methods recommended by International Electrotechnical Commission (IEC) and other standard organizations are introduced, and several key challenges in PIM measurement and their solutions (including the design of PIM tester, the location of the PIM sources, the design of compact PIM anechoic chambers, and the evaluation methods of PIM anechoic chambers) are highlighted. These challenges are of great significance to solve PIM problems that may arise during device characterization and verification in real wireless communication systems.

Keywords： Passive intermodulation (PIM)     PIM source location     Anechoic chamber    

HTML PDF Collect

Study on Decoupling Control of Bearingless Permanent Magnet Synchronous Motors Based on Inverse System Theory

Fei Decheng,Zhu Huangqiu

Strategic Study of CAE 2005, Volume 7, Issue 11,   Pages 48-54

Abstract:

A decoupling control approach based on dynamic inverse system theory has been developed for the bearingless permanent magnet synchronous motor (BPMSM), which is a multi-variable, nonlinear and strong-coupled system. Firstly, inverse system theory is briefly introduced. Secondly, the principle of suspension forces is expounded, and the state equations of torque force and radial suspension forces are set up. Then feasibility of decoupling control based on dynamic inversion theory for BPMSM is discussed in detail, and the dynamic decoupling control arithmetic based on inverse system is deduced. Finally, the simulation results have showed that this kind of control strategy can realize dynamic decoupling control between torque force and radial suspension forces, and the control system has fine dynamic and static performance.

Keywords： BPMSM     inverse system     dynamic feedback linearization     decoupling control    

HTML PDF Collect

The Research of Discovery Feature Sub-space Model (DFSSM) Based on Complex Type Data

Yang Bingru,Tang Qing

Strategic Study of CAE 2003, Volume 5, Issue 1,   Pages 56-61

Abstract:

This paper discusses the macroscopic and important problem in the field of KDD. First, it is very difficult to describe the complex type data by general knowledge representation method. So the authors use pattern, which is defined as the vector in Hilbert Space, to represent the characteristic of complex type data. It also can be used to describe the rule of knowledge discovery. Second, the general structure model is constructed based on complex type data—DFSSM (discovery feature sub-space model ) following by the research on inner mechanism of knowledge discovery system. At last, the authors prove the practicability and validity of this general structure model i. e. DFSSM which can guide the knowledge discovery of textual data and image data (meteorological echogram data). It will beapplied in other complex type data in future.

Keywords： complex type data     data mining     text mining    

HTML PDF Collect

Unsupervised feature selection via joint local learning and group sparse regression Regular Papers

Yue WU, Can WANG, Yue-qing ZHANG, Jia-jun BU

Frontiers of Information Technology & Electronic Engineering 2019, Volume 20, Issue 4,   Pages 538-553 doi: 10.1631/FITEE.1700804

Abstract:

Feature selection has attracted a great deal of interest over the past decades. By selecting meaningful feature subsets, the performance of learning algorithms can be effectively improved. Because label information is expensive to obtain, unsupervised feature selection methods are more widely used than the supervised ones. The key to unsupervised feature selection is to find features that effectively reflect the underlying data distribution. However, due to the inevitable redundancies and noise in a dataset, the intrinsic data distribution is not best revealed when using all features. To address this issue, we propose a novel unsupervised feature selection algorithm via joint local learning and group sparse regression (JLLGSR). JLLGSR incorporates local learning based clustering with group sparsity regularized regression in a single formulation, and seeks features that respect both the manifold structure and group sparse structure in the data space. An iterative optimization method is developed in which the weights finally converge on the important features and the selected features are able to improve the clustering results. Experiments on multiple real-world datasets (images, voices, and web pages) demonstrate the effectiveness of JLLGSR.

Keywords： Unsupervised     Local learning     Group sparse regression     Feature selection    

HTML PDF Collect

Big data storage technologies: a survey Review

Aisha SIDDIQA, Ahmad KARIM, Abdullah GANI

Frontiers of Information Technology & Electronic Engineering 2017, Volume 18, Issue 8,   Pages 1040-1070 doi: 10.1631/FITEE.1500441

Abstract: There is a great thrust in industry toward the development of more feasible and viable tools for storing fast-growing volume, velocity, and diversity of data, termed ‘big data’. The structural shift of the storage mechanism from traditional data management systems to NoSQL technology is due to the intention of fulfilling big data storage requirements. However, the available big data storage technologies are inefficient to provide consistent, scalable, and available solutions for continuously growing heterogeneous data. Storage is the preliminary process of big data analytics for real-world applications such as scientific experiments, healthcare, social networks, and e-business. So far, Amazon, Google, and Apache are some of the industry standards in providing big data storage solutions, yet the literature does not report an in-depth survey of storage technologies available for big data, investigating the performance and magnitude gains of these technologies. The primary objective of this paper is to conduct a comprehensive investigation of state-of-the-art storage technologies available for big data. A well-defined taxonomy of big data storage technologies is presented to assist data analysts and researchers in understanding and selecting a storage mechanism that better fits their needs. To evaluate the performance of different storage architectures, we compare and analyze the existing approaches using Brewer’s CAP theorem. The significance and applications of storage technologies and support to other categories are discussed. Several future research challenges are highlighted with the intention to expedite the deployment of a reliable and scalable storage system.

Keywords： Big data     Big data storage     NoSQL databases     Distributed databases     CAP theorem     Scalability     Consistency- partition resilience     Availability-partition resilience    

HTML PDF Collect

Prompting the construction of national land observation data center and improving data sharing

Guo Jianning,Lu Shuning,Zhao Xiang

Strategic Study of CAE 2008, Volume 10, Issue 6,   Pages 70-75

Abstract:

This paper discussed the developing trend of the foreign land observation data processing center and the problems of our country land observation data management. The developing trend of the foreign land observation data processing center are: building up the concentrative data processing center and providing comprehensive service;building up the data sharing mechanism, improving the data sharing and servicing;reforming and integrating data resources. In order to improve the land observation data sharing and applications, it is necessary to build up the national land observation data center. The construction of the national land observation data center includes the facility of comprehensive data processing, archiving, distributing and service and so on. The national land observation data center will improve the land observation data sharing and application; satisfy the requirement of land observation data.

Keywords： satellite of remote sensing     land observation     data sharing     data center    

HTML PDF Collect

Title Author Date Type Operation

Information Sunshine: the Collisionless Information Sharing Architecture

Li Youping

Journal Article

Learning to select pseudo labels: a semi-supervised method for named entity recognition

Zhen-zhen Li, Da-wei Feng, Dong-sheng Li, Xi-cheng Lu,lizhenzhen14@nudt.edu.cn,davyfeng.c@gmail.com,dsli@nudt.edu.cn,xclu@nudt.edu.cn

Journal Article

Interactive visual labelling versus active learning: an experimental comparison

Mohammad CHEGIN, Jürgen BERNARD, Jian CUI, Fatemeh CHEGINI, Alexei SOURIN, Keith Keith, Tobias SCHRECK

Journal Article

FAAD: an unsupervised fast and accurate anomaly detectionmethod for amulti-dimensional sequence over data stream

Bin LI, Yi-jie WANG, Dong-sheng YANG, Yong-mou LI, Xing-kong MA

Journal Article

A Preliminary Study on the Strategy of Construction a “No-Waste Society” by Piloting “No-Waste City” to Promote the Resource Utilization of Solid Waste

Du Xiangwan,Liu Xiaolong,Ge Qin,Jiang Lingling and Cui Leilei

Journal Article

Unstressed state control method for process control of structure formed by stages

Qin Shunquan

Journal Article

A Survey of the Observability for Single Observer Passive Location

Deng Xinpu

Journal Article

Constructing a “No-Waste Society”

Liu Xiaolong, Jiang Lingling, Ge Qin, Huhetaoli, Chen Ying, Cui Leilei, Li Bin, Du Xiangwan

Journal Article

Deformation monitoring and assessment technology for substructure of unballasted track on railway passenger dedicated line

Li Mingling

Journal Article

Passive Intermodulation Measurement: Challenges and Solutions

Zhanghua Cai, Lie Liu, Francesco de Paulis, Yihong Qi

Journal Article

Study on Decoupling Control of Bearingless Permanent Magnet Synchronous Motors Based on Inverse System Theory

Fei Decheng,Zhu Huangqiu

Journal Article

The Research of Discovery Feature Sub-space Model (DFSSM) Based on Complex Type Data

Yang Bingru,Tang Qing

Journal Article

Unsupervised feature selection via joint local learning and group sparse regression

Yue WU, Can WANG, Yue-qing ZHANG, Jia-jun BU

Journal Article

Big data storage technologies: a survey

Aisha SIDDIQA, Ahmad KARIM, Abdullah GANI

Journal Article

Prompting the construction of national land observation data center and improving data sharing

Guo Jianning,Lu Shuning,Zhao Xiang

Journal Article