疲劳驾驶是导致交通事故的主要原因之一,及时检测疲劳驾驶,并提醒驾驶员集中注意力,对保证安全行车具有重要意义.本文基于CAN(Controller Area Network)总线采集的车辆运行状态数据,提取了18项与驾驶行为相关的特征,并采用随机森林算法...疲劳驾驶是导致交通事故的主要原因之一,及时检测疲劳驾驶,并提醒驾驶员集中注意力,对保证安全行车具有重要意义.本文基于CAN(Controller Area Network)总线采集的车辆运行状态数据,提取了18项与驾驶行为相关的特征,并采用随机森林算法对疲劳驾驶进行识别,结果表明整体的识别准确率为0.785,其中召回率为0.61,即61%的疲劳驾驶状态可被识别出来.实验表明,基于车辆运行状态的疲劳驾驶检测具有一定的效果,且与其他客观的疲劳驾驶检测方法(基于驾驶员生理指标和图像面部特征)相比,具有简单方便,不影响驾驶,且成本低的优势.展开更多
This paper presents the knee-joint vibration signal processing and pathological localization procedures using the empirical mode decomposition for patients with chondrom alacia patellae.The artifacts of baseline wande...This paper presents the knee-joint vibration signal processing and pathological localization procedures using the empirical mode decomposition for patients with chondrom alacia patellae.The artifacts of baseline wander and random noise were identified in the decomposed monotonic trend and intrinsic mode functions (IMF) using the modeling method of probability density function and the confidence limit criterion.Then, the fluctuation parts in the signal were detected by the signal method turning for count. The results demonstrated that the quality of reconstructed signal can be greatly improved, with the removal of the baseline wander(adaptive trend) and the Gaussian distributed random noise. By detecting the turn signals in the artifact-free signal, the pathological segments related to chondrom alacia patellae can be effectively localized with the beginning and ending points of the span of turn signals.展开更多
文摘疲劳驾驶是导致交通事故的主要原因之一,及时检测疲劳驾驶,并提醒驾驶员集中注意力,对保证安全行车具有重要意义.本文基于CAN(Controller Area Network)总线采集的车辆运行状态数据,提取了18项与驾驶行为相关的特征,并采用随机森林算法对疲劳驾驶进行识别,结果表明整体的识别准确率为0.785,其中召回率为0.61,即61%的疲劳驾驶状态可被识别出来.实验表明,基于车辆运行状态的疲劳驾驶检测具有一定的效果,且与其他客观的疲劳驾驶检测方法(基于驾驶员生理指标和图像面部特征)相比,具有简单方便,不影响驾驶,且成本低的优势.
基金The Fundamental Research Funds for the Central Universities of Chinagrant number:2010121061 and 2010121062+3 种基金The Natural Science Foundation of Fujiangrant number:2011J01371The National Natural Science Foundation of Chinagrant number:81101115
文摘This paper presents the knee-joint vibration signal processing and pathological localization procedures using the empirical mode decomposition for patients with chondrom alacia patellae.The artifacts of baseline wander and random noise were identified in the decomposed monotonic trend and intrinsic mode functions (IMF) using the modeling method of probability density function and the confidence limit criterion.Then, the fluctuation parts in the signal were detected by the signal method turning for count. The results demonstrated that the quality of reconstructed signal can be greatly improved, with the removal of the baseline wander(adaptive trend) and the Gaussian distributed random noise. By detecting the turn signals in the artifact-free signal, the pathological segments related to chondrom alacia patellae can be effectively localized with the beginning and ending points of the span of turn signals.
