Training deep neural networks (DNNs) is a structured optimization problem, because the parameters are naturally represented by matrices and tensors rather than simple vectors. Under this structural representation, it ...
详细信息
The IIoT saw rapid evolution throughout the early years of the twenty-first century. The complexity of certain services in the industrial arena, poses challenges for our understanding. The task of identifying the most...
详细信息
Pile settlement (SP) socketed to rock has taken vital regard. Despite introducing some design methods to measure SP, applying the novel and efficient prediction model with satisfactory performance is pivotal. The main...
详细信息
Pile settlement (SP) socketed to rock has taken vital regard. Despite introducing some design methods to measure SP, applying the novel and efficient prediction model with satisfactory performance is pivotal. The main goal of this study is to find out the applicability of applying two hybrid multi-layer perceptron neural network (MLP) models in predicting the SP in the Klang Valley Mass Rapid Transit (KVMRT) project constructed operated in Kuala Lumpur, Malaysia. Various hidden layers of models were examined to have comprehensive, accurate and reliable outputs. Ant lion optimizer (ALO) and grasshopper optimization algorithm (GOA) was applied to identify each hidden layer's optimal number of neurons. In this case, five parameters were considered as input variables and SP as output. Regarding ALO-MLP models, ALO-MLP1 has the lowest score (48), with R-2 stood at 0.9382 and 0.93, and PI at 0.0416 and 0.0494 for the training and testing phases, respectively. In the training phase, best values of R-2 , RMSE and PI were belonged to MLP1, while MLP2 has the smallest value of MAE. However, in the testing phase, MLP model with two hidden layer has best values for all indices, which makes it the proposed MLP model with two hidden layers. The results show that ALO is more capable than GOA for determining the optimal neuron numbers of MLP. By summation of the ranking scores obtained from performance evaluation indices, although GOA-MLP models have acceptable performance, two layers of MLP optimized with ALO could be recognized as the proposed model.
In this paper, we present a new method for calculating expectation values of operators that can be expressed as a linear combination of unitary (LCU) operators. This method allows to perform this calculation in a sing...
详细信息
Early discernment of drivers drowsy state may prevent numerous worldwide road accidents. Electroencephalogram (EEG) signals provide valuable information about the neurological changes for discrimination of alert and d...
详细信息
Early discernment of drivers drowsy state may prevent numerous worldwide road accidents. Electroencephalogram (EEG) signals provide valuable information about the neurological changes for discrimination of alert and drowsy state. A signal is decomposed into multi-components for the analysis of the physiological state. Tunable Qwavelet transform (TQWT) decomposes the signal into low-pass and high-pass sub-bands without a choice of wavelet. The information content captured by these sub-bands depends on the choice of decomposition parameters. Due to the non-stationary nature of EEG signals, the predefined decomposition parameters of TQWT lead to information loss and degrade systemperformance. Hence it is required to automate the decomposition parameters in accordance with the nature of signals. In this paper, an optimized tunable Qwavelet transform (O-TQWT) is proposed for the adaptive selection of decomposition parameters by using different optimization algorithms. Objective function as a mean square error (MSE) of decomposition is minimized by optimization algorithms. Optimum decomposition parameters are used to decompose the signals into sub-bands. Time-domain based features are excerpted from the sub-bands of O-TQWT. Highly discriminant features selected by using Kruskal Wallis test are used as an input to different classification techniques. Classification accuracy of 96.14% is achieved by least square support vector machine with radial basis function kernel which is better than the other existing methodologies using the same database. (C) 2020 AGBM. Published by Elsevier Masson SAS. All rights reserved.
Numerous real-world applications of uncertain multiobjective optimization problems (UMOPs) can be found in science, engineering, business, and management. To handle the solution of uncertain optimization problems, rob...
详细信息
This tutorial focuses on kriging-based simulation optimization, emphasizing the importance of data efficiency in optimization problems involving expensive simulation models. It discusses how kriging models contribute ...
详细信息
The present study attempts to posit a suitable strategy for the optimal production with the maximum resilience and sustainability in the industrial dairy farms. The resilience and sustainability indicator was designed...
详细信息
The present study attempts to posit a suitable strategy for the optimal production with the maximum resilience and sustainability in the industrial dairy farms. The resilience and sustainability indicator was designed by integrating 5 indexes;they include the environmental, economic, social, technology and policy indexes and were modeled using the non-linear mathematical programming. The status of the industrial dairy farms in Khorasan Razavi province, Iran, was evaluated in terms of resilience and sustainability with the utilization of this indicator during 2016. The results of the initial estimation indicated the low level of resilience and sustainability of the probed dairy farms. Therefore, in order to clarify the application of the proposed model, all variables were considered as passive;hence, an intelligent and automatic model was postulated to optimize the resilience and sustainability in the industrial dairy farms. In order to gain the best outcome, the model was gauged by both the genetic algorithm and particle swarm optimization. Although both algorithms produced the same results, the validation tests unveiled the superiority of the genetic algorithm. Based on the results, the proposed model can improve the resilience and sustainability of production in the dairy farms and can reduce the environmental degradation brought about from the production process. For instance, the resilience and sustainability indicator increased up to 0.5% and profitability to 0.23%. Moreover, the greenhouse gas emissions and the energy intensity decreased to 0.09% and 0.02%, respectively. Our model can be adopted in variegated contexts to enhance the resilience and sustainability of the dairy farms and other production systems. (C) 2019 Published by Elsevier Ltd.
The performance of online convex optimization algorithms in a dynamic environment is often expressed in terms of the dynamic regret, which measures the decision maker's performance against a sequence of time-varyi...
详细信息
The performance of online convex optimization algorithms in a dynamic environment is often expressed in terms of the dynamic regret, which measures the decision maker's performance against a sequence of time-varying comparators. In the analysis of the dynamic regret, prior works often assume Lipschitz continuity or uniform smoothness of the cost functions. However, there are many important cost functions in practice that do not satisfy these conditions. In such cases, prior analyses are not applicable and fail to guarantee the optimization performance. In this letter, we show that it is possible to bound the dynamic regret, even when neither Lipschitz continuity nor uniform smoothness is present. We adopt the notion of relative smoothness with respect to some user-defined regularization function, which is a much milder requirement on the cost functions. We first show that under relative smoothness, the dynamic regret has an upper bound based on the path length and functional variation. We then show that with an additional condition of relatively strong convexity, the dynamic regret can be bounded by the path length and gradient variation. These regret bounds provide performance guarantees to a wide variety of online optimization problems that arise in different application domains. Finally, we present numerical experiments that demonstrate the advantage of adopting a regularization function under which the cost functions are relatively smooth.
The distributed dual ascent is an established algorithm to solve strongly convex multi-agent optimization problems with separable cost functions, in the presence of coupling constraints. In this letter, we study its a...
详细信息
The distributed dual ascent is an established algorithm to solve strongly convex multi-agent optimization problems with separable cost functions, in the presence of coupling constraints. In this letter, we study its asynchronous counterpart. Specifically, we assume that each agent only relies on the outdated information received from some neighbors. Differently from the existing randomized and dual block-coordinate schemes, we show convergence under heterogeneous delays, communication and update frequencies. Consequently, our asynchronous dual ascent algorithm can be implemented without requiring any coordination between the agents.
暂无评论