:Machine Learning(ML)algorithms have been widely used for financial time series prediction and trading through bots.In this work,we propose a Predictive Error Compensated Wavelet Neural Network(PEC-WNN)ML model that i...:Machine Learning(ML)algorithms have been widely used for financial time series prediction and trading through bots.In this work,we propose a Predictive Error Compensated Wavelet Neural Network(PEC-WNN)ML model that improves the prediction of next day closing prices.In the proposed model we use multiple neural networks where the first one uses the closing stock prices from multiple-scale time-domain inputs.An additional network is used for error estimation to compensate and reduce the prediction error of the main network instead of using recurrence.The performance of the proposed model is evaluated using six different stock data samples in the New York stock exchange.The results have demonstrated significant improvement in forecasting accuracy in all cases when the second network is used in accordance with the first one by adding the outputs.The RMSE error is 33%improved when the proposed PEC-WNN model is used compared to the Long ShortTerm Memory(LSTM)model.Furthermore,through the analysis of training mechanisms,we found that using the updated training the performance of the proposed model is improved.The contribution of this study is the applicability of simultaneously different time frames as inputs.Cascading the predictive error compensation not only reduces the error rate but also helps in avoiding overfitting problems.展开更多
As an innovative concept,an optimal predictive impedance controlle is introduced here to control a lower limb rehabilitation robo in the presence of uncertainty.The desired impedance law is considered to propose a con...As an innovative concept,an optimal predictive impedance controlle is introduced here to control a lower limb rehabilitation robo in the presence of uncertainty.The desired impedance law is considered to propose a conventional model-based impedance controller for the LLRR.However,external disturbances,model imperfection,and parameters uncertainties reduce the performance of the controller in practice.In order to cope with these uncertainties,an optimal predictive compensator is introduced as a solution for a proposed convex optimization problem,which is performed on a forward finite-length horizon.As a result,the LLRR has the desired behavior even in an uncertain environment.The performance and efficiency of the proposed controller are verified by the simulation results.展开更多
基金This study is based on the research project“Development of Cyberdroid based on Cognitive Intelligent system applications”(2019–2020)funded by Crypttech company(https://www.crypttech.com/en/)within the contract by ITUNOVA,Istanbul Technical University Technology Transfer Office.
文摘:Machine Learning(ML)algorithms have been widely used for financial time series prediction and trading through bots.In this work,we propose a Predictive Error Compensated Wavelet Neural Network(PEC-WNN)ML model that improves the prediction of next day closing prices.In the proposed model we use multiple neural networks where the first one uses the closing stock prices from multiple-scale time-domain inputs.An additional network is used for error estimation to compensate and reduce the prediction error of the main network instead of using recurrence.The performance of the proposed model is evaluated using six different stock data samples in the New York stock exchange.The results have demonstrated significant improvement in forecasting accuracy in all cases when the second network is used in accordance with the first one by adding the outputs.The RMSE error is 33%improved when the proposed PEC-WNN model is used compared to the Long ShortTerm Memory(LSTM)model.Furthermore,through the analysis of training mechanisms,we found that using the updated training the performance of the proposed model is improved.The contribution of this study is the applicability of simultaneously different time frames as inputs.Cascading the predictive error compensation not only reduces the error rate but also helps in avoiding overfitting problems.
文摘As an innovative concept,an optimal predictive impedance controlle is introduced here to control a lower limb rehabilitation robo in the presence of uncertainty.The desired impedance law is considered to propose a conventional model-based impedance controller for the LLRR.However,external disturbances,model imperfection,and parameters uncertainties reduce the performance of the controller in practice.In order to cope with these uncertainties,an optimal predictive compensator is introduced as a solution for a proposed convex optimization problem,which is performed on a forward finite-length horizon.As a result,the LLRR has the desired behavior even in an uncertain environment.The performance and efficiency of the proposed controller are verified by the simulation results.
