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
基于台架采集数据,采用外部输入非线性自回归(nonlinear autoregressive model with exogenous input,NARX)神经网络建立了具备瞬态特性的柴油机排气温度计算模型作为虚拟传感器,并采用并发式训练方法对模型进行训练。将结果与前馈神经...基于台架采集数据,采用外部输入非线性自回归(nonlinear autoregressive model with exogenous input,NARX)神经网络建立了具备瞬态特性的柴油机排气温度计算模型作为虚拟传感器,并采用并发式训练方法对模型进行训练。将结果与前馈神经网络、长短期记忆网络(long short term memory,LSTM)神经网络及量产发动机的排温传感器采集结果进行对比。经验证,稳态工况下,两种神经网络均能达到较高精度;欧洲瞬态循环(European transient cycle,ETC)工况下,NARX神经网络计算温度的最大偏差为6.6℃,量产发动机排温传感器测得温度最大偏差为45.9℃。NARX神经网络所需的计算时间约为现有电控单元排温模型的2.5倍。展开更多
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.
文摘基于台架采集数据,采用外部输入非线性自回归(nonlinear autoregressive model with exogenous input,NARX)神经网络建立了具备瞬态特性的柴油机排气温度计算模型作为虚拟传感器,并采用并发式训练方法对模型进行训练。将结果与前馈神经网络、长短期记忆网络(long short term memory,LSTM)神经网络及量产发动机的排温传感器采集结果进行对比。经验证,稳态工况下,两种神经网络均能达到较高精度;欧洲瞬态循环(European transient cycle,ETC)工况下,NARX神经网络计算温度的最大偏差为6.6℃,量产发动机排温传感器测得温度最大偏差为45.9℃。NARX神经网络所需的计算时间约为现有电控单元排温模型的2.5倍。
