This paper develops a feedforward neural network based input output model for a general unknown nonlinear dynamic system identification when only the inputs and outputs are accessible observations. In the developed m...This paper develops a feedforward neural network based input output model for a general unknown nonlinear dynamic system identification when only the inputs and outputs are accessible observations. In the developed model, the size of the input space is directly related to the system order. By monitoring the identification error characteristic curve, we are able to determine the system order and subsequently an appropriate network structure for systems identification. Simulation results are promising and show that generic nonlinear systems can be identified, different cases of the same system can also be discriminated by our model.展开更多
Towards virtual keyboard design and realization, the work in this paper presents a robust key input method for deployment in virtual keyboard systems. The proposed scheme harnesses the information contained within sha...Towards virtual keyboard design and realization, the work in this paper presents a robust key input method for deployment in virtual keyboard systems. The proposed scheme harnesses the information contained within shadows towards robustifying virtual key input. This scheme allows for input efficiency to be guaranteed in situations of relatively lower illumination, a core challenge associated with virtual keyboards. Contributions of the paper are two-fold. Firstly the paper pre-sents an approach towards effectively applying shadow information towards robustifying virtual key input systems;Secondly, through morphological operations, the performance of this input method is boosted by means of effectively alleviating noise and its impacts on overall algorithm performance, while highlighting the necessary features towards an efficient performance. While previous contributions have followed a similar trend, the contribution of this paper stresses on the intensification and improvement of both shadow and finger-tip feature highlighting schemes towards overall performance improvement. Experimental results presented in the paper demon-strate the efficiency and robustness of the approach. The attained results suggest that the scheme is capable of attaining high performances in terms of accuracy while being capable of addressing false touch situations.展开更多
Electronic throttle control (ETC) system has worked its way to becoming a standard subsystem in most of the current automobiles as it has contributed much to the improvement of fuel economy, emissions, drivability and...Electronic throttle control (ETC) system has worked its way to becoming a standard subsystem in most of the current automobiles as it has contributed much to the improvement of fuel economy, emissions, drivability and safety. Precision control of the subsystem, which consists of a dc motor driving a throttle plate, a pre-loaded return spring and a set of gear train to regulate airflow into the engine, seems rather straightforward and yet complex. The difficulties lie in the unknown system parameters, hard nonlinearity of the pre-loaded spring that pulls the throttle plate to its default position, and friction, among others. In this paper, we extend our previous results obtained for the modeling, unknown system parameters identification and control of a commercially available Bosch’s DV-E5 ETC system. Details of modeling and parameters identification based on laboratory experiments, data analysis, and knowledge of the system are provided. The parameters identification results were verified and validated by a real-time PID control implemented with an xPC Target. A nonlinear control design was then proposed utilizing the input-output feedback linearization approach and technique. In view of a recent massive auto recalls due to the controversial uncontrollable engine accelerations, the results of this paper may inspire further research interest on the drive-by-wire technology.展开更多
文摘This paper develops a feedforward neural network based input output model for a general unknown nonlinear dynamic system identification when only the inputs and outputs are accessible observations. In the developed model, the size of the input space is directly related to the system order. By monitoring the identification error characteristic curve, we are able to determine the system order and subsequently an appropriate network structure for systems identification. Simulation results are promising and show that generic nonlinear systems can be identified, different cases of the same system can also be discriminated by our model.
文摘Towards virtual keyboard design and realization, the work in this paper presents a robust key input method for deployment in virtual keyboard systems. The proposed scheme harnesses the information contained within shadows towards robustifying virtual key input. This scheme allows for input efficiency to be guaranteed in situations of relatively lower illumination, a core challenge associated with virtual keyboards. Contributions of the paper are two-fold. Firstly the paper pre-sents an approach towards effectively applying shadow information towards robustifying virtual key input systems;Secondly, through morphological operations, the performance of this input method is boosted by means of effectively alleviating noise and its impacts on overall algorithm performance, while highlighting the necessary features towards an efficient performance. While previous contributions have followed a similar trend, the contribution of this paper stresses on the intensification and improvement of both shadow and finger-tip feature highlighting schemes towards overall performance improvement. Experimental results presented in the paper demon-strate the efficiency and robustness of the approach. The attained results suggest that the scheme is capable of attaining high performances in terms of accuracy while being capable of addressing false touch situations.
文摘Electronic throttle control (ETC) system has worked its way to becoming a standard subsystem in most of the current automobiles as it has contributed much to the improvement of fuel economy, emissions, drivability and safety. Precision control of the subsystem, which consists of a dc motor driving a throttle plate, a pre-loaded return spring and a set of gear train to regulate airflow into the engine, seems rather straightforward and yet complex. The difficulties lie in the unknown system parameters, hard nonlinearity of the pre-loaded spring that pulls the throttle plate to its default position, and friction, among others. In this paper, we extend our previous results obtained for the modeling, unknown system parameters identification and control of a commercially available Bosch’s DV-E5 ETC system. Details of modeling and parameters identification based on laboratory experiments, data analysis, and knowledge of the system are provided. The parameters identification results were verified and validated by a real-time PID control implemented with an xPC Target. A nonlinear control design was then proposed utilizing the input-output feedback linearization approach and technique. In view of a recent massive auto recalls due to the controversial uncontrollable engine accelerations, the results of this paper may inspire further research interest on the drive-by-wire technology.
