The Experts below are selected from a list of 157599 Experts worldwide ranked by ideXlab platform

David Zhang - One of the best experts on this subject based on the ideXlab platform.

  • robust visual knowledge transfer via extreme Learning machine based domain adaptation
    IEEE Transactions on Image Processing, 2016
    Co-Authors: Lei Zhang, David Zhang
    Abstract:

    We address the problem of visual knowledge adaptation by leveraging labeled patterns from source domain and a very limited number of labeled instances in target domain to learn a robust classifier for visual categorization. This paper proposes a new extreme Learning machine (ELM)-based cross-domain network Learning framework, that is called ELM-based Domain Adaptation (EDA). It allows us to learn a category transformation and an ELM classifier with random projection by minimizing the $\ell _{2,1}$ -norm of the network output weights and the Learning Error simultaneously. The unlabeled target data, as useful knowledge, is also integrated as a fidelity term to guarantee the stability during cross-domain Learning. It minimizes the matching Error between the learned classifier and a base classifier, such that many existing classifiers can be readily incorporated as the base classifiers. The network output weights cannot only be analytically determined, but also transferrable. In addition, a manifold regularization with Laplacian graph is incorporated, such that it is beneficial to semisupervised Learning. Extensively, we also propose a model of multiple views, referred as MvEDA. Experiments on benchmark visual datasets for video event recognition and object recognition demonstrate that our EDA methods outperform the existing cross-domain Learning methods.

  • robust visual knowledge transfer via extreme Learning machine based domain adaptation
    IEEE Transactions on Image Processing, 2016
    Co-Authors: Lei Zhang, David Zhang
    Abstract:

    We address the problem of visual knowledge adaptation by leveraging labeled patterns from source domain and a very limited number of labeled instances in target domain to learn a robust classifier for visual categorization. This paper proposes a new extreme Learning machine (ELM)-based cross-domain network Learning framework, that is called ELM-based Domain Adaptation (EDA). It allows us to learn a category transformation and an ELM classifier with random projection by minimizing the l 2,1 -norm of the network output weights and the Learning Error simultaneously. The unlabeled target data, as useful knowledge, is also integrated as a fidelity term to guarantee the stability during cross-domain Learning. It minimizes the matching Error between the learned classifier and a base classifier, such that many existing classifiers can be readily incorporated as the base classifiers. The network output weights cannot only be analytically determined, but also transferrable. In addition, a manifold regularization with Laplacian graph is incorporated, such that it is beneficial to semisupervised Learning. Extensively, we also propose a model of multiple views, referred as MvEDA. Experiments on benchmark visual datasets for video event recognition and object recognition demonstrate that our EDA methods outperform the existing cross-domain Learning methods.

Lei Zhang - One of the best experts on this subject based on the ideXlab platform.

  • robust visual knowledge transfer via extreme Learning machine based domain adaptation
    IEEE Transactions on Image Processing, 2016
    Co-Authors: Lei Zhang, David Zhang
    Abstract:

    We address the problem of visual knowledge adaptation by leveraging labeled patterns from source domain and a very limited number of labeled instances in target domain to learn a robust classifier for visual categorization. This paper proposes a new extreme Learning machine (ELM)-based cross-domain network Learning framework, that is called ELM-based Domain Adaptation (EDA). It allows us to learn a category transformation and an ELM classifier with random projection by minimizing the $\ell _{2,1}$ -norm of the network output weights and the Learning Error simultaneously. The unlabeled target data, as useful knowledge, is also integrated as a fidelity term to guarantee the stability during cross-domain Learning. It minimizes the matching Error between the learned classifier and a base classifier, such that many existing classifiers can be readily incorporated as the base classifiers. The network output weights cannot only be analytically determined, but also transferrable. In addition, a manifold regularization with Laplacian graph is incorporated, such that it is beneficial to semisupervised Learning. Extensively, we also propose a model of multiple views, referred as MvEDA. Experiments on benchmark visual datasets for video event recognition and object recognition demonstrate that our EDA methods outperform the existing cross-domain Learning methods.

  • robust visual knowledge transfer via extreme Learning machine based domain adaptation
    IEEE Transactions on Image Processing, 2016
    Co-Authors: Lei Zhang, David Zhang
    Abstract:

    We address the problem of visual knowledge adaptation by leveraging labeled patterns from source domain and a very limited number of labeled instances in target domain to learn a robust classifier for visual categorization. This paper proposes a new extreme Learning machine (ELM)-based cross-domain network Learning framework, that is called ELM-based Domain Adaptation (EDA). It allows us to learn a category transformation and an ELM classifier with random projection by minimizing the l 2,1 -norm of the network output weights and the Learning Error simultaneously. The unlabeled target data, as useful knowledge, is also integrated as a fidelity term to guarantee the stability during cross-domain Learning. It minimizes the matching Error between the learned classifier and a base classifier, such that many existing classifiers can be readily incorporated as the base classifiers. The network output weights cannot only be analytically determined, but also transferrable. In addition, a manifold regularization with Laplacian graph is incorporated, such that it is beneficial to semisupervised Learning. Extensively, we also propose a model of multiple views, referred as MvEDA. Experiments on benchmark visual datasets for video event recognition and object recognition demonstrate that our EDA methods outperform the existing cross-domain Learning methods.

Okyay Kaynak - One of the best experts on this subject based on the ideXlab platform.

  • sliding mode control approach for online Learning as applied to type 2 fuzzy neural networks and its experimental evaluation
    IEEE Transactions on Industrial Electronics, 2012
    Co-Authors: Erdal Kayacan, Ozkan Cigdem, Okyay Kaynak
    Abstract:

    Type-2 fuzzy logic systems (FLSs) are proposed in the literature as an alternative to type-1 FLSs because of their ability to more effectively model uncertainties that may exist in the rule base. However, the parameters of the system still need to be optimized. For this purpose, the use of a sliding mode control theory-based Learning algorithm is proposed in this paper. In the approach, instead of trying to minimize an Error function, the parameters of the network are tuned by the proposed algorithm in such a way that the Learning Error is enforced to satisfy a stable equation. The update rules to achieve this are derived, and the convergence of the parameters is proved by Lyapunov stability method. The performance of the proposed algorithm is tested by simulations on a Duffing oscillator and also by real-time experiments on a laboratory servo system. The results indicate that the given type-2 fuzzy neural network with the proposed Learning algorithm can handle the uncertainties in a better way as compared to its type-1 counterpart. Moreover, it is computationally easier to implement in real-time systems.

  • neuro fuzzy control of antilock braking system using sliding mode incremental Learning algorithm
    Neurocomputing, 2011
    Co-Authors: Andon V Topalov, Erdal Kayacan, Yesim Oniz, Okyay Kaynak
    Abstract:

    A neuro-fuzzy adaptive control approach for nonlinear dynamical systems, coupled with unknown dynamics, modeling Errors, and various sorts of disturbances, is proposed and used to design a wheel slip regulating controller. The implemented control structure consists of a conventional controller and a neuro-fuzzy network-based feedback controller. The former is provided both to guarantee global asymptotic stability in compact space and as an inverse reference model of the response of the controlled system. Its output is used as an Error signal by an incremental Learning algorithm to update the parameters of the neuro-fuzzy controller. In this way the latter is able to gradually replace the conventional controller from the control of the system. The proposed new Learning algorithm makes direct use of the variable structure systems theory and establishes a sliding motion in terms of the neuro-fuzzy controller parameters, leading the Learning Error toward zero. In the simulations and in the experimental studies, it has been tested on the control of antilock breaking system model and the analytical claims have been justified under the existence of uncertainty and large nonzero initial Errors.

  • sliding mode control of a three degrees of freedom anthropoid robot by driving the controller parameters to an equivalent regime
    Journal of Dynamic Systems Measurement and Control-transactions of The Asme, 2000
    Co-Authors: Okyay Kaynak, Xinghuo Yu
    Abstract:

    Noise rejection, handling the difficulties coming from the mathematical representation of the system under investigation and alleviation of structural or unstructural uncertainties constitute prime challenges that are frequently encountered in the practice of systems and control engineering. Designing a controller has primarily the aim of achieving the tracking precision as well as a degree of robustness against the difficulties stated. From this point of view, variable structure systems theory offer well formulated solutions to such ill-posed problems containing uncertainty and imprecision. In this paper, a simple controller structure is discussed. The architecture is known as Adaptive Linear Element (ADALINE) in the framework of neural computing. The parameters of the controller evolve dynamically in time such that a sliding motion is obtained. The inner sliding motion concerns the establishment of a sliding mode in controller parameters, which aims to minimize the Error on the controller outputs. The outer sliding motion is designed for the plant. The algorithm discussed drives the Error on the output of the controller toward zero Learning Error level, and the state tracking Error vector of the plant is driven toward the origin of the phase space simultaneously. The paper gives the analysis of the equivalence between the two sliding motions and demonstrates the performance of the algorithm on a three degrees of freedom, anthropoid robotic manipulator. In order to clarify the performance of the scheme, together with the dynamic complexity of the plant, the adverse effects of observation noise and nonzero initial conditions are studied. @S0022-0434~00!01704-4#

Jenhsiang Chou - One of the best experts on this subject based on the ideXlab platform.

  • an adaptive supervisory sliding fuzzy cerebellar model articulation controller for sensorless vector controlled induction motor drive systems
    Sensors, 2015
    Co-Authors: Shunyuan Wang, Chwanlu Tseng, Shouchuang Lin, Chunjung Chiu, Jenhsiang Chou
    Abstract:

    This paper presents the implementation of an adaptive supervisory sliding fuzzy cerebellar model articulation controller (FCMAC) in the speed sensorless vector control of an induction motor (IM) drive system. The proposed adaptive supervisory sliding FCMAC comprised a supervisory controller, integral sliding surface, and an adaptive FCMAC. The integral sliding surface was employed to eliminate steady-state Errors and enhance the responsiveness of the system. The adaptive FCMAC incorporated an FCMAC with a compensating controller to perform a desired control action. The proposed controller was derived using the Lyapunov approach, which guarantees Learning-Error convergence. The implementation of three intelligent control schemes—the adaptive supervisory sliding FCMAC, adaptive sliding FCMAC, and adaptive sliding CMAC—were experimentally investigated under various conditions in a realistic sensorless vector-controlled IM drive system. The root mean square Error (RMSE) was used as a performance index to evaluate the experimental results of each control scheme. The analysis results indicated that the proposed adaptive supervisory sliding FCMAC substantially improved the system performance compared with the other control schemes.

Huang Kaibin - One of the best experts on this subject based on the ideXlab platform.

  • Reconfigurable Intelligent Surface Assisted Edge Machine Learning
    2021
    Co-Authors: Huang Shanfeng, Wang Shuai, Wang Rui, Wen Miaowen, Huang Kaibin
    Abstract:

    The ever-growing popularity and rapid improving of artificial intelligence (AI) have raised rethinking on the evolution of wireless networks. Mobile edge computing (MEC) provides a natural platform for AI applications since it provides rich computation resources to train AI models, as well as low-latency access to the data generated by mobile and Internet of Things devices. In this paper, we present an infrastructure to perform machine Learning tasks at an MEC server with the assistance of a reconfigurable intelligent surface (RIS). In contrast to conventional communication systems where the principal criteria are to maximize the throughput, we aim at optimizing the Learning performance. Specifically, we minimize the maximum Learning Error of all users by jointly optimizing the beamforming vectors of the base station and the phase-shift matrix of the RIS. An alternating optimization-based framework is proposed to optimize the two terms iteratively, where closed-form expressions of the beamforming vectors are derived, and an alternating direction method of multipliers (ADMM)-based algorithm is designed together with an Error level searching framework to effectively solve the nonconvex optimization problem of the phase-shift matrix. Simulation results demonstrate significant gains of deploying an RIS and validate the advantages of our proposed algorithms over various benchmarks.Comment: 6 pages, 4 figures, to appear in IEEE International Conference on Communications 2021. arXiv admin note: substantial text overlap with arXiv:2012.1353

  • Reconfigurable Intelligent Surface Assisted Mobile Edge Computing with Heterogeneous Learning Tasks
    2020
    Co-Authors: Huang Shanfeng, Wang Shuai, Wang Rui, Wen Miaowen, Huang Kaibin
    Abstract:

    The ever-growing popularity and rapid improving of artificial intelligence (AI) have raised rethinking on the evolution of wireless networks. Mobile edge computing (MEC) provides a natural platform for AI applications since it is with rich computation resources to train machine Learning (ML) models, as well as low-latency access to the data generated by mobile and internet of things (IoT) devices. In this paper, we present an infrastructure to perform ML tasks at an MEC server with the assistance of a reconfigurable intelligent surface (RIS). In contrast to conventional communication systems where the principal criterions are to maximize the throughput, we aim at maximizing the Learning performance. Specifically, we minimize the maximum Learning Error of all participating users by jointly optimizing transmit power of mobile users, beamforming vectors of the base station (BS), and the phase-shift matrix of the RIS. An alternating optimization (AO)-based framework is proposed to optimize the three terms iteratively, where a successive convex approximation (SCA)-based algorithm is developed to solve the power allocation problem, closed-form expressions of the beamforming vectors are derived, and an alternating direction method of multipliers (ADMM)-based algorithm is designed together with an Error level searching (ELS) framework to effectively solve the challenging nonconvex optimization problem of the phase-shift matrix. Simulation results demonstrate significant gains of deploying an RIS and validate the advantages of our proposed algorithms over various benchmarks. Lastly, a unified communication-training-inference platform is developed based on the CARLA platform and the SECOND network, and a use case (3D object detection in autonomous driving) for the proposed scheme is demonstrated on the developed platform.Comment: 30 pages, 8 figures, submitted to IEEE Transactions on Cognitive Communications and Networkin