The Experts below are selected from a list of 184170 Experts worldwide ranked by ideXlab platform

Raymond R. Tan - One of the best experts on this subject based on the ideXlab platform.

  • short term wind power forecasting based on support vector machine with improved dragonfly algorithm
    Journal of Cleaner Production, 2020
    Co-Authors: Xue Zhao, Ming-lang Tseng, Raymond R. Tan
    Abstract:

    Abstract It is hard to predict wind power with high-precision due to its non-stationary and stochastic nature. The wind power has developed rapidly around the world as a promising renewable energy industry. The uncertainty of wind power brings difficult challenges to the operation of the power system with the integration of wind farms into power grid. Accurate wind power prediction is increasingly important for the stable operation of wind farms and the power grid. This study is combined support vector machine and improved dragonfly algorithm to forecast short-term wind power for a hybrid prediction model. The adaptive Learning Factor and differential evolution strategy are introduced to improve the performance of traditional dragonfly algorithm. The improved dragonfly algorithm is used to choose the optimal parameters of support vector machine. The effectiveness of the proposed model has been confirmed on the real datasets derived from La Haute Borne wind farm in France. The proposed model has shown better prediction performance compared with the other models such as back propagation neural network and Gaussian process regression. The proposed model is suitable for short-term wind power prediction.

  • Improving the Reliability of Photovoltaic and Wind Power Storage Systems Using Least Squares Support Vector Machine Optimized by Improved Chicken Swarm Algorithm
    Applied Sciences, 2019
    Co-Authors: Zhi-feng Liu, Ming-lang Tseng, Raymond R. Tan, Kathleen B. Aviso
    Abstract:

    In photovoltaic and wind power storage systems, the reliability of the battery directly affects the overall reliability of the energy storage system. Failed batteries can seriously affect the stable operation of energy storage systems. This paper aims to improve the reliability of the storage systems by accurately predicting battery life and identifying failing batteries in time. The current prediction models mainly use artificial neural networks, Gaussian process regression and hybrid models. Although these models can achieve high prediction accuracy, the computational cost is high due to model complexity. Least squares support vector machine (LSSVM) is a computationally efficient alternative. Hence, this study combines the improved chicken swarm optimization algorithm (ICSO) and LSSVM into a hybrid ICSO-LSSVM model for the reliability of photovoltaic and wind power storage systems. The following are the contributions of this work. First, the optimal penalty parameter and kernel width are determined. Second, the chicken swarm optimization algorithm (CSO) is improved by introducing chaotic search behavior in the hen and an adaptive Learning Factor in the chicks. The performance of the ICSO algorithm is shown to be better than CSO using standard test problems. Third, the prediction accuracy of the three models is compared. For NMC1 battery, the predicted relative error of ICSO-LSSVM is 0.94%; for NMC2 battery, the relative error of ICSO-LSSVM is 1%. These findings show that the proposed model is suitable for predicting the failure of batteries in energy storage systems, which can improve preventive and predictive maintenance of such systems.

Ming-lang Tseng - One of the best experts on this subject based on the ideXlab platform.

  • short term wind power forecasting based on support vector machine with improved dragonfly algorithm
    Journal of Cleaner Production, 2020
    Co-Authors: Xue Zhao, Ming-lang Tseng, Raymond R. Tan
    Abstract:

    Abstract It is hard to predict wind power with high-precision due to its non-stationary and stochastic nature. The wind power has developed rapidly around the world as a promising renewable energy industry. The uncertainty of wind power brings difficult challenges to the operation of the power system with the integration of wind farms into power grid. Accurate wind power prediction is increasingly important for the stable operation of wind farms and the power grid. This study is combined support vector machine and improved dragonfly algorithm to forecast short-term wind power for a hybrid prediction model. The adaptive Learning Factor and differential evolution strategy are introduced to improve the performance of traditional dragonfly algorithm. The improved dragonfly algorithm is used to choose the optimal parameters of support vector machine. The effectiveness of the proposed model has been confirmed on the real datasets derived from La Haute Borne wind farm in France. The proposed model has shown better prediction performance compared with the other models such as back propagation neural network and Gaussian process regression. The proposed model is suitable for short-term wind power prediction.

  • Improving the Reliability of Photovoltaic and Wind Power Storage Systems Using Least Squares Support Vector Machine Optimized by Improved Chicken Swarm Algorithm
    Applied Sciences, 2019
    Co-Authors: Zhi-feng Liu, Ming-lang Tseng, Raymond R. Tan, Kathleen B. Aviso
    Abstract:

    In photovoltaic and wind power storage systems, the reliability of the battery directly affects the overall reliability of the energy storage system. Failed batteries can seriously affect the stable operation of energy storage systems. This paper aims to improve the reliability of the storage systems by accurately predicting battery life and identifying failing batteries in time. The current prediction models mainly use artificial neural networks, Gaussian process regression and hybrid models. Although these models can achieve high prediction accuracy, the computational cost is high due to model complexity. Least squares support vector machine (LSSVM) is a computationally efficient alternative. Hence, this study combines the improved chicken swarm optimization algorithm (ICSO) and LSSVM into a hybrid ICSO-LSSVM model for the reliability of photovoltaic and wind power storage systems. The following are the contributions of this work. First, the optimal penalty parameter and kernel width are determined. Second, the chicken swarm optimization algorithm (CSO) is improved by introducing chaotic search behavior in the hen and an adaptive Learning Factor in the chicks. The performance of the ICSO algorithm is shown to be better than CSO using standard test problems. Third, the prediction accuracy of the three models is compared. For NMC1 battery, the predicted relative error of ICSO-LSSVM is 0.94%; for NMC2 battery, the relative error of ICSO-LSSVM is 1%. These findings show that the proposed model is suitable for predicting the failure of batteries in energy storage systems, which can improve preventive and predictive maintenance of such systems.

Andrew Y Ng - One of the best experts on this subject based on the ideXlab platform.

  • Learning Factor graphs in polynomial time and sample complexity
    Journal of Machine Learning Research, 2006
    Co-Authors: Pieter Abbeel, Daphne Koller, Andrew Y Ng
    Abstract:

    We study the computational and sample complexity of parameter and structure Learning in graphical models. Our main result shows that the class of Factor graphs with bounded degree can be learned in polynomial time and from a polynomial number of training examples, assuming that the data is generated by a network in this class. This result covers both parameter estimation for a known network structure and structure Learning. It implies as a corollary that we can learn Factor graphs for both Bayesian networks and Markov networks of bounded degree, in polynomial time and sample complexity. Importantly, unlike standard maximum likelihood estimation algorithms, our method does not require inference in the underlying network, and so applies to networks where inference is intractable. We also show that the error of our learned model degrades gracefully when the generating distribution is not a member of the target class of networks. In addition to our main result, we show that the sample complexity of parameter Learning in graphical models has an O(1) dependence on the number of variables in the model when using the KL-divergence normalized by the number of variables as the performance criterion.

Zainab Namh Alsultani - One of the best experts on this subject based on the ideXlab platform.

  • hybrid system of Learning vector quantization and enhanced resilient backpropagation artificial neural network for intrusion classification
    2013
    Co-Authors: Reyadh Shaker Naoum, Zainab Namh Alsultani
    Abstract:

    Network-based computer systems play increasingly vital roles in modern society; they have become the target of intrusions by our enemies and criminals. Intrusion detection system attempts to detect computer attacks by examining various data records observed in processes on the network. This paper presents a hybrid intrusion detection system models, using Learning Vector Quantization and an enhanced resilient backpropagation artificial neural network. The proposed system is divided into five phases: environment phase, dataset features and preprocessing phase, Learning Vector Quantization phase, enhanced resilient backpropagation neural network phase and testing the hybrid system phase. A Supervised Learning Vector Quantization (LVQ) as the first stage of classification was trained to detect intrusions; it consists of two layers with two different transfer functions, competitive and linear. A multilayer perceptron as the second stage of classification was trained using an enhanced resilient backpropagation training algorithm. Best number of hidden layers and hidden neurons were calculated to train the enhanced resilient backpropagation neural network. One hidden layer with 32 hidden neurons was used in resilient backpropagation artificial neural network training process. An optimal Learning Factor was derived to speed up the convergence of the resilient backpropagation neural network performance. The evaluations were performed using the NSL-KDD99 network anomaly intrusion detection dataset. The experiments results demonstrate that the proposed system (LVQ_ERBP) has a detection rate about 97.06% with a false negative rate of 2%.

  • hybrid system of Learning vector quantization and enhanced resilient backpropagation artificial neural network for intrusion classification
    2013
    Co-Authors: Reyadh Shaker Naoum, Zainab Namh Alsultani
    Abstract:

    Network-based computer systems play increasingly vital roles in modern society; they have become the target of intrusions by our enemies and criminals. Intrusion detection system attempts to detect computer attacks by examining various data records observed in processes on the network. This paper presents a hybrid intrusion detection system models, using Learning Vector Quantization and an enhanced resilient backpropagation artificial neural network. The proposed system is divided into five phases: environment phase, dataset features and preprocessing phase, Learning Vector Quantization phase, enhanced resilient backpropagation neural network phase and testing the hybrid system phase. A Supervised Learning Vector Quantization (LVQ) as the first stage of classification was trained to detect intrusions; it consists of two layers with two different transfer functions, competitive and linear. A multilayer perceptron as the second stage of classification was trained using an enhanced resilient backpropagation training algorithm. Best number of hidden layers and hidden neurons were calculated to train the enhanced resilient backpropagation neural network. One hidden layer with 32 hidden neurons was used in resilient backpropagation artificial neural network training process. An optimal Learning Factor was derived to speed up the convergence of the resilient backpropagation neural network performance. The evaluations were performed using the NSL-KDD99 network anomaly intrusion detection dataset. The experiments results demonstrate that the proposed system (LVQ_ERBP) has a detection rate about 97.06% with a false negative rate of 2%.

  • an enhanced resilient backpropagation artificial neural network for intrusion detection system
    2012
    Co-Authors: Reyadh Shaker Naoum, Namh Abdula Abid, Zainab Namh Alsultani
    Abstract:

    Summary The potential threats and attacks that can be caused by intrusions have been increased rapidly due to the dependence on network and internet connectivity. In order to prevent such attacks, Intrusion Detection Systems were designed. Different soft computing based methods have been proposed for the development of Intrusion Detection Systems. In this paper a multilayer perceptron is trained using an enhanced resilient backpropagation training algorithm for intrusion detection. In order to increase the convergence speed an optimal or ideal Learning Factor was added to the weight update equation. The performance and evaluations were performed using the NSLKDD anomaly intrusion detection dataset. The experiments results demonstrate that the system has promising results in terms of accuracy, storage and time; the designed system was capable to classify records with a detection rate about 94.7%.

Pieter Abbeel - One of the best experts on this subject based on the ideXlab platform.

  • Learning Factor graphs in polynomial time sample complexity
    arXiv: Learning, 2012
    Co-Authors: Pieter Abbeel, Daphne Koller
    Abstract:

    We study computational and sample complexity of parameter and structure Learning in graphical models. Our main result shows that the class of Factor graphs with bounded Factor size and bounded connectivity can be learned in polynomial time and polynomial number of samples, assuming that the data is generated by a network in this class. This result covers both parameter estimation for a known network structure and structure Learning. It implies as a corollary that we can learn Factor graphs for both Bayesian networks and Markov networks of bounded degree, in polynomial time and sample complexity. Unlike maximum likelihood estimation, our method does not require inference in the underlying network, and so applies to networks where inference is intractable. We also show that the error of our learned model degrades gracefully when the generating distribution is not a member of the target class of networks.

  • Learning Factor graphs in polynomial time and sample complexity
    Journal of Machine Learning Research, 2006
    Co-Authors: Pieter Abbeel, Daphne Koller, Andrew Y Ng
    Abstract:

    We study the computational and sample complexity of parameter and structure Learning in graphical models. Our main result shows that the class of Factor graphs with bounded degree can be learned in polynomial time and from a polynomial number of training examples, assuming that the data is generated by a network in this class. This result covers both parameter estimation for a known network structure and structure Learning. It implies as a corollary that we can learn Factor graphs for both Bayesian networks and Markov networks of bounded degree, in polynomial time and sample complexity. Importantly, unlike standard maximum likelihood estimation algorithms, our method does not require inference in the underlying network, and so applies to networks where inference is intractable. We also show that the error of our learned model degrades gracefully when the generating distribution is not a member of the target class of networks. In addition to our main result, we show that the sample complexity of parameter Learning in graphical models has an O(1) dependence on the number of variables in the model when using the KL-divergence normalized by the number of variables as the performance criterion.