Inverse-Free Extreme Learning Machine With Optimal Information Updating

Li, Shuai; You, Zhu-Hong; Guo, Hongliang; Luo, Xin; Zhao, Zhong-Qiu

doi:10.1109/tcyb.2015.2434841

Cited by 115 publications

(66 citation statements)

References 56 publications

(48 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…, 6 defines the kinematic relation between the actuation variables and the pose variables. For a six-dimensional reference pose, the desired leg length r i can be directly obtained from (11). However, in real applications, the reference are usually not six-dimensional.…”

Section: A Geometric Relationmentioning

confidence: 99%

“…Compared to (11) and (18) significantly simplifies the problem asṙ in (18) is now affine to theπ while the relation between r i and π (or p and Q) in (11) are nonlinear, or even nonconvex to the pose variables. Similar to our analysis before, in the case that the reference pose velocity is given in six dimensions, the solution ofṙ can be solved directly from (18).…”

Section: Problem Formulation As Constrained Optimizationmentioning

confidence: 99%

See 1 more Smart Citation

Dynamic Neural Networks for Kinematic Redundancy Resolution of Parallel Stewart Platforms

Mirza

2016

IEEE Trans. Cybern.

Self Cite

View full text Add to dashboard Cite

Redundancy resolution is a critical problem in the control of parallel Stewart platform. The redundancy endows us with extra design degree to improve system performance. In this paper, the kinematic control problem of Stewart platforms is formulated to a constrained quadratic programming. The Karush-Kuhn-Tucker conditions of the problem is obtained by considering the problem in its dual space, and then a dynamic neural network is designed to solve the optimization problem recurrently. Theoretical analysis reveals the global convergence of the employed dynamic neural network to the optimal solution in terms of the defined criteria. Simulation results verify the effectiveness in the tracking control of the Stewart platform for dynamic motions.

show abstract

Section: A Geometric Relationmentioning

confidence: 99%

Section: Problem Formulation As Constrained Optimizationmentioning

confidence: 99%

Dynamic Neural Networks for Kinematic Redundancy Resolution of Parallel Stewart Platforms

Mirza

2016

IEEE Trans. Cybern.

Self Cite

View full text Add to dashboard Cite

show abstract

“…As a beneficial supplement to biological methods, a number of computational methods have been developed to predict protein interactions through different source of information, such as protein domains, phylogenetic profiles, gene co-expression and secondary structures [9–12]. However, such methods need specific domain knowledge which prevents their further applications.…”

Section: Introductionmentioning

confidence: 99%

Accurate prediction of protein-protein interactions by integrating potential evolutionary information embedded in PSSM profile and discriminative vector machine classifier

You

Chen

et al. 2017

Oncotarget

Self Cite

View full text Add to dashboard Cite

Identification of protein-protein interactions (PPIs) is of critical importance for deciphering the underlying mechanisms of almost all biological processes of cell and providing great insight into the study of human disease. Although much effort has been devoted to identifying PPIs from various organisms, existing high-throughput biological techniques are time-consuming, expensive, and have high false positive and negative results. Thus it is highly urgent to develop in silico methods to predict PPIs efficiently and accurately in this post genomic era. In this article, we report a novel computational model combining our newly developed discriminative vector machine classifier (DVM) and an improved Weber local descriptor (IWLD) for the prediction of PPIs. Two components, differential excitation and orientation, are exploited to build evolutionary features for each protein sequence. The main characteristics of the proposed method lies in introducing an effective feature descriptor IWLD which can capture highly discriminative evolutionary information from position-specific scoring matrixes (PSSM) of protein data, and employing the powerful and robust DVM classifier. When applying the proposed method to Yeast and H. pylori data sets, we obtained excellent prediction accuracies as high as 96.52% and 91.80%, respectively, which are significantly better than the previous methods. Extensive experiments were then performed for predicting cross-species PPIs and the predictive results were also pretty promising. To further validate the performance of the proposed method, we compared it with the state-of-the-art support vector machine (SVM) classifier on Human data set. The experimental results obtained indicate that our method is highly effective for PPIs prediction and can be taken as a supplementary tool for future proteomics research.

show abstract

“…Because of these reasons, these computational methods are not fit for detecting SIPs. N Zaki et al [6] proposed an approach called as PPI-PS (Pairwise Similarity) to predict PPIs. The PPI-PS combined pairwise similarity score with support vector machine (SVM) for detecting PPIs.…”

Section: Introductionmentioning

confidence: 99%

Identification of self-interacting proteins by exploring evolutionary information embedded in PSI-BLAST-constructed position specific scoring matrix

You

Chen

et al. 2016

Oncotarget

Self Cite

View full text Add to dashboard Cite

Self-interacting Proteins (SIPs) play an essential role in a wide range of biological processes, such as gene expression regulation, signal transduction, enzyme activation and immune response. Because of the limitations for experimental self-interaction proteins identification, developing an effective computational method based on protein sequence to detect SIPs is much important. In the study, we proposed a novel computational approach called RVMBIGP that combines the Relevance Vector Machine (RVM) model and Bi-gram probability (BIGP) to predict SIPs based on protein sequence. The proposed prediction model includes as following steps: (1) an effective feature extraction method named BIGP is used to represent protein sequences on Position Specific Scoring Matrix (PSSM); (2) Principal Component Analysis (PCA) method is employed for integrating the useful information and reducing the influence of noise; (3) the robust classifier Relevance Vector Machine (RVM) is used to carry out classification. When performed on yeast and human datasets, the proposed RVMBIGP model can achieve very high accuracies of 95.48% and 98.80%, respectively. The experimental results show that our proposed method is very promising and may provide a cost-effective alternative for SIPs identification. In addition, to facilitate extensive studies for future proteomics research, the RVMBIGP server is freely available for academic use at http://219.219.62.123:8888/RVMBIGP.

show abstract

Inverse-Free Extreme Learning Machine With Optimal Information Updating

Cited by 115 publications

References 56 publications

Dynamic Neural Networks for Kinematic Redundancy Resolution of Parallel Stewart Platforms

Dynamic Neural Networks for Kinematic Redundancy Resolution of Parallel Stewart Platforms

Accurate prediction of protein-protein interactions by integrating potential evolutionary information embedded in PSSM profile and discriminative vector machine classifier

Identification of self-interacting proteins by exploring evolutionary information embedded in PSI-BLAST-constructed position specific scoring matrix

Contact Info

Product

Resources

About