Entity

Time filter

Source Type


Zhang Y.,East China University of Science and Technology | Wang Y.,Shanghai Ruanzhong Information Technology Co. | Jin J.,East China University of Science and Technology | Wang X.,East China University of Science and Technology
International Journal of Neural Systems | Year: 2016

Effective common spatial pattern (CSP) feature extraction for motor imagery (MI) electroencephalogram (EEG) recordings usually depends on the filter band selection to a large extent. Subband optimization has been suggested to enhance classification accuracy of MI. Accordingly, this study introduces a new method that implements sparse Bayesian learning of frequency bands (named SBLFB) from EEG for MI classification. CSP features are extracted on a set of signals that are generated by a filter bank with multiple overlapping subbands from raw EEG data. Sparse Bayesian learning is then exploited to implement selection of significant features with a linear discriminant criterion for classification. The effectiveness of SBLFB is demonstrated on the BCI Competition IV IIb dataset, in comparison with several other competing methods. Experimental results indicate that the SBLFB method is promising for development of an effective classifier to improve MI classification. © 2016 World Scientific Publishing Company Source


Zhang Y.,East China University of Science and Technology | Jin J.,East China University of Science and Technology | Wang X.,East China University of Science and Technology | Wang Y.,Shanghai Ruanzhong Information Technology Co.
6th International Conference on Information Science and Technology, ICIST 2016 | Year: 2016

Motor imagery is usually hard to be classified with a high accuracy, since the task-related electroencephalogram (EEG) responses are likely to be contaminated by some ongoing noises. Design of an efficient classifier is considerably important for the realization of a brain-computer interface (BCI) system based on motor imagery. This study introduces a Bayesian extreme learning machine (BELM) based method for accurate classification of motor imagery. By combing ELM and Bayesian inference, BELM achieves the smallest norm of output weights with automatically estimated regularization for alleviating the possible overfitting during calibration procedure. Effectiveness of the BELM-based method is validated on a public BCI dataset, in comparison with other two competing methods. © 2016 IEEE. Source


Jiao Y.,Fudan University | Jiao Y.,Shanghai Ruanzhong Information Technology Co. | Zhang S.,Shanghai Ruanzhong Information Technology Co. | Li Y.,Tongji University | And 2 more authors.
Automation in Construction | Year: 2013

Huge progress has been made on 'Augmented Reality' (AR) techniques such as registration, tracking, and display hardware. However, a construction AR system should be more convenient and combined with in-use applications to support multi-disciplinary users throughout construction lifecycle. This paper presents a video-based on-line AR environment and a pilot cloud framework. The contribution lies in two aspects: firstly, an environment utilizing web3D is demonstrated, in which on-site images are rendered to box nodes and registered with virtual objects through a three-step method; secondly, it is further extended to be "cloud" through federation of BIM (building information modeling) and BSNS (business social networking services). Technical solutions to key issues such as authoring, publishing, and composition are designed. The proposed environment is seamlessly integrated into in-use information systems and therefore enjoys greater usability. Implementations demonstrate how this framework and environment work. Although preliminary, it is conclusive for proof of concept. © 2012 Elsevier B.V. Source


Jiao Y.,Fudan University | Jiao Y.,Shanghai Key Laboratory of Software Testing and Evaluation | Jiao Y.,Shanghai Ruanzhong Information Technology Co. | Wang Y.,Shanghai Ruanzhong Information Technology Co. | And 2 more authors.
Proceedings of the 2012 IEEE 16th International Conference on Computer Supported Cooperative Work in Design, CSCWD 2012 | Year: 2012

The intrinsic construction project nature of one-of-a-kind and the requirement of massive data exchange make collaboration one of the critical factors towards success. However, due to the complexity of multiple phases and multi-disciplinary participants in project life cycle, industry level collaboration in Architecture, Engineering, and Construction (AEC) sector remains a challenge. This paper proposes an integrated solution based mainly on social network services (SNS) and cloud computing. We present a novel platform named Construction Business Social Network Service (CBSNS), which is promising to be adopted as an industrial scope collaboration cloud. We describe its main functions as well as its privacy control mechanism. To better support its deployment as a community cloud, a three-pass load balance algorithm is proposed. The first pass sorts initial virtual machines (VMs) and physical machines (PMs) using bubble algorithm, during which parameters such as hungry threshold are considered. The second pass builds mappings between allocable PM queue and requesting VM queue using first come first served strategy, and groups Non-allocable VMs after designated time slice. The third pass handles possible exceptions when finally such ones existing. The actual time complexity of the algorithm is O(n). While the commercial implementation of the algorithm is ongoing, the proposed CBSNS has been developed and used in real life application. © 2012 IEEE. Source


Jiao Y.,Fudan University | Jiao Y.,Shanghai Key Laboratory of Computer Software Testing and Evaluating | Jiao Y.,Shanghai Ruanzhong Information Technology Co. | Li L.,Shanghai Ruanzhong Information Technology Co. | Ye N.,Shanghai Ruanzhong Information Technology Co.
Proceedings of the 2010 14th International Conference on Computer Supported Cooperative Work in Design, CSCWD 2010 | Year: 2010

The demand for quickly delivering robust enterprise applications has increasingly become a business imperative today. Semantic web technologies have received much interest due to their prospect in facilitating seamless legacy system integration in support of new functionality development. In this article, we present a team collaboration oriented development framework (SSC-I) for designing and developing enterprise applications by applying technologies and methodologies offered by software engineering, Web 2.0(AJAX), and semantic web technologies, together with a set of semantic tools to facilitate both the integration of heterogeneous relational databases and reuse of software functionalities. We adopt a component-based and lightweight framework aims at flexibly interleaving manual labor and automated functionality in environments where annotations are incomplete and even inconsistent. An initial version of this framework has been implemented and applied in SSTAMS Project. © 2010 IEEE. Source

Discover hidden collaborations