For training the present Neural Network(NN)models,the standard technique is to utilize decaying Learning Rates(LR).While the majority of these techniques commence with a large LR,they will decay multiple times over ti...For training the present Neural Network(NN)models,the standard technique is to utilize decaying Learning Rates(LR).While the majority of these techniques commence with a large LR,they will decay multiple times over time.Decaying has been proved to enhance generalization as well as optimization.Other parameters,such as the network’s size,the number of hidden layers,drop-outs to avoid overfitting,batch size,and so on,are solely based on heuristics.This work has proposed Adaptive Teaching Learning Based(ATLB)Heuristic to identify the optimal hyperparameters for diverse networks.Here we consider three architec-tures Recurrent Neural Networks(RNN),Long Short Term Memory(LSTM),Bidirectional Long Short Term Memory(BiLSTM)of Deep Neural Networks for classification.The evaluation of the proposed ATLB is done through the various learning rate schedulers Cyclical Learning Rate(CLR),Hyperbolic Tangent Decay(HTD),and Toggle between Hyperbolic Tangent Decay and Triangular mode with Restarts(T-HTR)techniques.Experimental results have shown the performance improvement on the 20Newsgroup,Reuters Newswire and IMDB dataset.展开更多
2019年5月Lancet Neurol杂志发表了RESTART研究的亚组分析,题目为"Effects of antiplatelet therapy on stroke risk by brain imaging features of intracerebral haemorrhage and cerebral small vessel diseases:subgroup analy...2019年5月Lancet Neurol杂志发表了RESTART研究的亚组分析,题目为"Effects of antiplatelet therapy on stroke risk by brain imaging features of intracerebral haemorrhage and cerebral small vessel diseases:subgroup analyses of the RESTART randomised,open-label trial"。1研究介绍1.1研究背景既往研究提示具有脑出血和脑小血管病的影像学特征与脑出血复发风险增加有关。目前指南及一些学者等建议根据这些影像学特征可用于指导脑出血后是否重启抗血小板治疗。展开更多
The Galerkin and least-squares methods are two classes of the most popular Krylov subspace methOds for solving large linear systems of equations. Unfortunately, both the methods may suffer from serious breakdowns of t...The Galerkin and least-squares methods are two classes of the most popular Krylov subspace methOds for solving large linear systems of equations. Unfortunately, both the methods may suffer from serious breakdowns of the same type: In a breakdown situation the Galerkin method is unable to calculate an approximate solution, while the least-squares method, although does not really break down, is unsucessful in reducing the norm of its residual. In this paper we first establish a unified theorem which gives a relationship between breakdowns in the two methods. We further illustrate theoretically and experimentally that if the coefficient matrix of a lienar system is of high defectiveness with the associated eigenvalues less than 1, then the restarted Galerkin and least-squares methods will be in great risks of complete breakdowns. It appears that our findings may help to understand phenomena observed practically and to derive treatments for breakdowns of this type.展开更多
The existing LCC-HVDC transmission project adopts the fixed-time delay restarting method.This method has disadvantages such as non-selectivity,long restart process,and high probability of restart failure.These issues ...The existing LCC-HVDC transmission project adopts the fixed-time delay restarting method.This method has disadvantages such as non-selectivity,long restart process,and high probability of restart failure.These issues cause a secondary impact on equipment and system power fluctuation.To solve this problem,an adaptive restarting method based on the principle of fault location by current injection is proposed.First,an additional control strategy is proposed to inject a current detection signal.Second,the propagation law of the current signal in the line is analyzed based on the distributed parameter model of transmission line.Finally,a method for identifying fault properties based on the principle of fault location is proposed.The method fully considers the influence of the long-distance transmission line with earth capacitance and overcomes the influence of the increasing effect of the opposite terminal.Simulation results show that the proposed method can accurately identify the fault properties under various complex fault conditions and subsequently realize the adaptive restarting process.展开更多
In this paper we present a new type of Restarted Krylov methods for calculating peripheral eigenvalues of symmetric matrices. The new framework avoids the Lanczos tridiagonalization process, and the use of polynomial ...In this paper we present a new type of Restarted Krylov methods for calculating peripheral eigenvalues of symmetric matrices. The new framework avoids the Lanczos tridiagonalization process, and the use of polynomial filtering. This simplifies the restarting mechanism and allows the introduction of several modifications. Convergence is assured by a monotonicity property that pushes the eigenvalues toward their limits. The Krylov matrices that we use lead to fast rate of convergence. Numerical experiments illustrate the usefulness of the proposed approach.展开更多
Industry 4.0 and Cyber Physical Production Systems (CPPS) are often discussed and partially already sold. One important feature of CPPS is fault tolerance and as a consequence self-configuration and restart to increas...Industry 4.0 and Cyber Physical Production Systems (CPPS) are often discussed and partially already sold. One important feature of CPPS is fault tolerance and as a consequence self-configuration and restart to increase Overall Equipment Effectiveness. To understand this challenge at first the state of the art of fault handling in industrial automated production systems (aPS) is discussed as a result of a case study analysis in eight companies developing aPS. In the next step, metrics to evaluate the concept of self-configuration and restart for aPS focusing on real-time capabilities, fault coverage and effort to increase fault coverage are proposed. Finally, two different lab size case studies prove the applicability of the concepts of self-configuration, restart and the proposed metrics.展开更多
The main purpose of this paper is to provide a restarting direction for improving on the standard conjugate gradient method.If a drastic non-quadratic behaviour of the objective function is observed in the neighbour o...The main purpose of this paper is to provide a restarting direction for improving on the standard conjugate gradient method.If a drastic non-quadratic behaviour of the objective function is observed in the neighbour of xk,then a restart should be done.The scaling symmetric rank-one update with Davidon’s optimal criterion is applied to generate the restarting direction.It is proved that the conjugate gradient method with this strategy retains the quadratic termination.Numerical experiments show that it is successful.展开更多
Predicting essential proteins is crucial for discovering the process of cellular organization and viability.We propose biased random walk with restart algorithm for essential proteins prediction,called BRWR.Firstly,th...Predicting essential proteins is crucial for discovering the process of cellular organization and viability.We propose biased random walk with restart algorithm for essential proteins prediction,called BRWR.Firstly,the common process of practice walk often sets the probability of particles transferring to adjacent nodes to be equal,neglecting the influence of the similarity structure on the transition probability.To address this problem,we redefine a novel transition probability matrix by integrating the gene express similarity and subcellular location similarity.The particles can obtain biased transferring probabilities to perform random walk so as to further exploit biological properties embedded in the network structure.Secondly,we use gene ontology(GO)terms score and subcellular score to calculate the initial probability vector of the random walk with restart.Finally,when the biased random walk with restart process reaches steady state,the protein importance score is obtained.In order to demonstrate superiority of BRWR,we conduct experiments on the YHQ,BioGRID,Krogan and Gavin PPI networks.The results show that the method BRWR is superior to other state-of-the-art methods in essential proteins recognition performance.Especially,compared with the contrast methods,the improvements of BRWR in terms of the ACC results range in 1.4%–5.7%,1.3%–11.9%,2.4%–8.8%,and 0.8%–14.2%,respectively.Therefore,BRWR is effective and reasonable.展开更多
We extend a results presented by Y.F. Hu and C.Storey (1991) [1] on the global convergence result for conjugate gradient methods with different choices for the parameter β k . In this note, the condit...We extend a results presented by Y.F. Hu and C.Storey (1991) [1] on the global convergence result for conjugate gradient methods with different choices for the parameter β k . In this note, the conditions given on β k are milder than that used by Y.F. Hu and C. Storey.展开更多
Based on Arnoldi's method, a version of generalized Arnoldi algorithm has been developed for the reduction of gyroscopic eigenvalue problems. By utilizing the skew symmetry of system matrix, a very simple recurren...Based on Arnoldi's method, a version of generalized Arnoldi algorithm has been developed for the reduction of gyroscopic eigenvalue problems. By utilizing the skew symmetry of system matrix, a very simple recurrence scheme, named gyroscopic Arnoldi reduction algorithm has been obtained, which is even simpler than the Lanczos algorithm for symmetric eigenvalue problems. The complex number computation is completely avoided. A restart technique is used to enable the reduction algorithm to have iterative characteristics. It has been found that the restart technique is not only effective for the convergence of multiple eigenvalues but it also furnishes the reduction algorithm with a technique to check and compute missed eigenvalues. By combining it with the restart technique, the algorithm is made practical for large-scale gyroscopic eigenvalue problems. Numerical examples are given to demonstrate the effectiveness of the method proposed.展开更多
This paper proposes a new pre-processing technique to separate the most effective features from those that might deteriorate the performance of the machine learning classifiers in terms of computational costs and clas...This paper proposes a new pre-processing technique to separate the most effective features from those that might deteriorate the performance of the machine learning classifiers in terms of computational costs and classification accuracy because of their irrelevance,redundancy,or less information;this pre-processing process is often known as feature selection.This technique is based on adopting a new optimization algorithm known as generalized normal distribution optimization(GNDO)supported by the conversion of the normal distribution to a binary one using the arctangent transfer function to convert the continuous values into binary values.Further,a novel restarting strategy(RS)is proposed to preserve the diversity among the solutions within the population by identifying the solutions that exceed a specific distance from the best-so-far and replace them with the others created using an effective updating scheme.This strategy is integrated with GNDO to propose another binary variant having a high ability to preserve the diversity of the solutions for avoiding becoming stuck in local minima and accelerating convergence,namely improved GNDO(IGNDO).The proposed GNDO and IGNDO algorithms are extensively compared with seven state-of-the-art algorithms to verify their performance on thirteen medical instances taken from the UCI repository.IGNDO is shown to be superior in terms of fitness value and classification accuracy and competitive with the others in terms of the selected features.Since the principal goal in solving the FS problem is to find the appropriate subset of features that maximize classification accuracy,IGNDO is considered the best.展开更多
Two new versions of accelerated first-order methods for minimizing convex composite functions are proposed. In this paper, we first present an accelerated first-order method which chooses the step size 1/ Lk to be 1/ ...Two new versions of accelerated first-order methods for minimizing convex composite functions are proposed. In this paper, we first present an accelerated first-order method which chooses the step size 1/ Lk to be 1/ L0 at the beginning of each iteration and preserves the computational simplicity of the fast iterative shrinkage-thresholding algorithm. The first proposed algorithm is a non-monotone algorithm. To avoid this behavior, we present another accelerated monotone first-order method. The proposed two accelerated first-order methods are proved to have a better convergence rate for minimizing convex composite functions. Numerical results demonstrate the efficiency of the proposed two accelerated first-order methods.展开更多
文摘For training the present Neural Network(NN)models,the standard technique is to utilize decaying Learning Rates(LR).While the majority of these techniques commence with a large LR,they will decay multiple times over time.Decaying has been proved to enhance generalization as well as optimization.Other parameters,such as the network’s size,the number of hidden layers,drop-outs to avoid overfitting,batch size,and so on,are solely based on heuristics.This work has proposed Adaptive Teaching Learning Based(ATLB)Heuristic to identify the optimal hyperparameters for diverse networks.Here we consider three architec-tures Recurrent Neural Networks(RNN),Long Short Term Memory(LSTM),Bidirectional Long Short Term Memory(BiLSTM)of Deep Neural Networks for classification.The evaluation of the proposed ATLB is done through the various learning rate schedulers Cyclical Learning Rate(CLR),Hyperbolic Tangent Decay(HTD),and Toggle between Hyperbolic Tangent Decay and Triangular mode with Restarts(T-HTR)techniques.Experimental results have shown the performance improvement on the 20Newsgroup,Reuters Newswire and IMDB dataset.
文摘2019年5月Lancet Neurol杂志发表了RESTART研究的亚组分析,题目为"Effects of antiplatelet therapy on stroke risk by brain imaging features of intracerebral haemorrhage and cerebral small vessel diseases:subgroup analyses of the RESTART randomised,open-label trial"。1研究介绍1.1研究背景既往研究提示具有脑出血和脑小血管病的影像学特征与脑出血复发风险增加有关。目前指南及一些学者等建议根据这些影像学特征可用于指导脑出血后是否重启抗血小板治疗。
文摘The Galerkin and least-squares methods are two classes of the most popular Krylov subspace methOds for solving large linear systems of equations. Unfortunately, both the methods may suffer from serious breakdowns of the same type: In a breakdown situation the Galerkin method is unable to calculate an approximate solution, while the least-squares method, although does not really break down, is unsucessful in reducing the norm of its residual. In this paper we first establish a unified theorem which gives a relationship between breakdowns in the two methods. We further illustrate theoretically and experimentally that if the coefficient matrix of a lienar system is of high defectiveness with the associated eigenvalues less than 1, then the restarted Galerkin and least-squares methods will be in great risks of complete breakdowns. It appears that our findings may help to understand phenomena observed practically and to derive treatments for breakdowns of this type.
基金supported by Science and Technology Project of State Grid Corporation of China(52094020006U)National Natural Science Foundation of China(NSFC)(52061635105)China Postdoctoral Science Foundation(2021M692525).
文摘The existing LCC-HVDC transmission project adopts the fixed-time delay restarting method.This method has disadvantages such as non-selectivity,long restart process,and high probability of restart failure.These issues cause a secondary impact on equipment and system power fluctuation.To solve this problem,an adaptive restarting method based on the principle of fault location by current injection is proposed.First,an additional control strategy is proposed to inject a current detection signal.Second,the propagation law of the current signal in the line is analyzed based on the distributed parameter model of transmission line.Finally,a method for identifying fault properties based on the principle of fault location is proposed.The method fully considers the influence of the long-distance transmission line with earth capacitance and overcomes the influence of the increasing effect of the opposite terminal.Simulation results show that the proposed method can accurately identify the fault properties under various complex fault conditions and subsequently realize the adaptive restarting process.
文摘In this paper we present a new type of Restarted Krylov methods for calculating peripheral eigenvalues of symmetric matrices. The new framework avoids the Lanczos tridiagonalization process, and the use of polynomial filtering. This simplifies the restarting mechanism and allows the introduction of several modifications. Convergence is assured by a monotonicity property that pushes the eigenvalues toward their limits. The Krylov matrices that we use lead to fast rate of convergence. Numerical experiments illustrate the usefulness of the proposed approach.
文摘Industry 4.0 and Cyber Physical Production Systems (CPPS) are often discussed and partially already sold. One important feature of CPPS is fault tolerance and as a consequence self-configuration and restart to increase Overall Equipment Effectiveness. To understand this challenge at first the state of the art of fault handling in industrial automated production systems (aPS) is discussed as a result of a case study analysis in eight companies developing aPS. In the next step, metrics to evaluate the concept of self-configuration and restart for aPS focusing on real-time capabilities, fault coverage and effort to increase fault coverage are proposed. Finally, two different lab size case studies prove the applicability of the concepts of self-configuration, restart and the proposed metrics.
基金The Project Supported by National Natural Foundation of China
文摘The main purpose of this paper is to provide a restarting direction for improving on the standard conjugate gradient method.If a drastic non-quadratic behaviour of the objective function is observed in the neighbour of xk,then a restart should be done.The scaling symmetric rank-one update with Davidon’s optimal criterion is applied to generate the restarting direction.It is proved that the conjugate gradient method with this strategy retains the quadratic termination.Numerical experiments show that it is successful.
基金Project supported by the National Natural Science Foundation of China(Grant Nos.11861045 and 62162040)。
文摘Predicting essential proteins is crucial for discovering the process of cellular organization and viability.We propose biased random walk with restart algorithm for essential proteins prediction,called BRWR.Firstly,the common process of practice walk often sets the probability of particles transferring to adjacent nodes to be equal,neglecting the influence of the similarity structure on the transition probability.To address this problem,we redefine a novel transition probability matrix by integrating the gene express similarity and subcellular location similarity.The particles can obtain biased transferring probabilities to perform random walk so as to further exploit biological properties embedded in the network structure.Secondly,we use gene ontology(GO)terms score and subcellular score to calculate the initial probability vector of the random walk with restart.Finally,when the biased random walk with restart process reaches steady state,the protein importance score is obtained.In order to demonstrate superiority of BRWR,we conduct experiments on the YHQ,BioGRID,Krogan and Gavin PPI networks.The results show that the method BRWR is superior to other state-of-the-art methods in essential proteins recognition performance.Especially,compared with the contrast methods,the improvements of BRWR in terms of the ACC results range in 1.4%–5.7%,1.3%–11.9%,2.4%–8.8%,and 0.8%–14.2%,respectively.Therefore,BRWR is effective and reasonable.
文摘We extend a results presented by Y.F. Hu and C.Storey (1991) [1] on the global convergence result for conjugate gradient methods with different choices for the parameter β k . In this note, the conditions given on β k are milder than that used by Y.F. Hu and C. Storey.
基金This research is supported by The National Science FoundationThe Doctoral Training Foundation
文摘Based on Arnoldi's method, a version of generalized Arnoldi algorithm has been developed for the reduction of gyroscopic eigenvalue problems. By utilizing the skew symmetry of system matrix, a very simple recurrence scheme, named gyroscopic Arnoldi reduction algorithm has been obtained, which is even simpler than the Lanczos algorithm for symmetric eigenvalue problems. The complex number computation is completely avoided. A restart technique is used to enable the reduction algorithm to have iterative characteristics. It has been found that the restart technique is not only effective for the convergence of multiple eigenvalues but it also furnishes the reduction algorithm with a technique to check and compute missed eigenvalues. By combining it with the restart technique, the algorithm is made practical for large-scale gyroscopic eigenvalue problems. Numerical examples are given to demonstrate the effectiveness of the method proposed.
基金This work has supported by the National Research Foundation of Korea(NRF)grant funded by the Korea government(MSIT)(No.NRF-2021R1A2C1010362)and the Soonchunhyang University Research Fund.
文摘This paper proposes a new pre-processing technique to separate the most effective features from those that might deteriorate the performance of the machine learning classifiers in terms of computational costs and classification accuracy because of their irrelevance,redundancy,or less information;this pre-processing process is often known as feature selection.This technique is based on adopting a new optimization algorithm known as generalized normal distribution optimization(GNDO)supported by the conversion of the normal distribution to a binary one using the arctangent transfer function to convert the continuous values into binary values.Further,a novel restarting strategy(RS)is proposed to preserve the diversity among the solutions within the population by identifying the solutions that exceed a specific distance from the best-so-far and replace them with the others created using an effective updating scheme.This strategy is integrated with GNDO to propose another binary variant having a high ability to preserve the diversity of the solutions for avoiding becoming stuck in local minima and accelerating convergence,namely improved GNDO(IGNDO).The proposed GNDO and IGNDO algorithms are extensively compared with seven state-of-the-art algorithms to verify their performance on thirteen medical instances taken from the UCI repository.IGNDO is shown to be superior in terms of fitness value and classification accuracy and competitive with the others in terms of the selected features.Since the principal goal in solving the FS problem is to find the appropriate subset of features that maximize classification accuracy,IGNDO is considered the best.
基金Sponsored by the National Natural Science Foundation of China(Grant No.11461021)the Natural Science Basic Research Plan in Shaanxi Province of China(Grant No.2017JM1014)
文摘Two new versions of accelerated first-order methods for minimizing convex composite functions are proposed. In this paper, we first present an accelerated first-order method which chooses the step size 1/ Lk to be 1/ L0 at the beginning of each iteration and preserves the computational simplicity of the fast iterative shrinkage-thresholding algorithm. The first proposed algorithm is a non-monotone algorithm. To avoid this behavior, we present another accelerated monotone first-order method. The proposed two accelerated first-order methods are proved to have a better convergence rate for minimizing convex composite functions. Numerical results demonstrate the efficiency of the proposed two accelerated first-order methods.