Functional near-infrared spectroscopy(fNIRS),as a new optical functional neuroimaging method,has been widely used in neuroscience research.In some research fields with NIRS,heartrate(HR)(or heartbeat)is needed as usef...Functional near-infrared spectroscopy(fNIRS),as a new optical functional neuroimaging method,has been widely used in neuroscience research.In some research fields with NIRS,heartrate(HR)(or heartbeat)is needed as useful information to evaluate its influence,or to know the state ofsubject,or to remove its artifact.If HR(or heartbeat)can be detected with high accuracy from theoptical intensity,this will undoubtedly benefit a lot to many NIRS studies.Previous studies haveused the moving time window method or mathematical morphology method(MMM)to detectheartbeats in the optical intensity.However,there are some disadvantages in these methods.In thisstudy,we proposed a method combining the periodic information of heartbeats and the operator ofmathematical morphology to automatically detect heartbeats in the optical intensity.First theoptical intensity is smoothed using a moving average flter.Then,the opening operator of math-ematical morphology extracts peaks in the smoothed optical intensity.Finally,one peak is iden-tified as a heartbeat peak if this peak is the maximum in a predefined point range.Throughvalidation on experimental data,our method can overcome the disadvantages of previous methods,and detet heartbeats in the optical signal of fNIRS with nearly 100%accuracy.展开更多
Working conditions of rolling bearings of wind turbine generators are complicated, and their vibration signals often show non-linear and non-stationary characteristics. In order to improve the efficiency of feature ex...Working conditions of rolling bearings of wind turbine generators are complicated, and their vibration signals often show non-linear and non-stationary characteristics. In order to improve the efficiency of feature extraction of wind turbine rolling bearings and to strengthen the feature information, a new structural element and an adaptive algorithm based on the peak energy are proposed,which are combined with spectral correlation analysis to form a fault diagnosis algorithm for wind turbine rolling bearings. The proposed method firstly addresses the problem of impulsive signal omissions that are prone to occur in the process of fault feature extraction of traditional structural elements and proposes a "W" structural element to capture more characteristic information. Then, the proposed method selects the scale of multi-scale mathematical morphology, aiming at the problem of multi-scale mathematical morphology scale selection and structural element expansion law. An adaptive algorithm based on peak energy is proposed to carry out morphological scale selection and structural element expansion by improving the computing efficiency and enhancing the feature extraction effect.Finally, the proposed method performs spectral correlation analysis in the frequency domain for an unknown signal of the extracted feature and identifies the fault based on the correlation coefficient. The method is verified by numerical examples using experimental rig bearing data and actual wind field acquisition data and compared with traditional triangular and flat structural elements. The experimental results show that the new structural elements can more effectively extract the pulses in the signal and reduce noise interference,and the fault-diagnosis algorithm can accurately identify the fault category and improve the reliability of the results.展开更多
为实现对高光谱图像海面舰艇目标进行有效探测,通过对传统的目标探测算法进行改进,解决了加权自相关约束能量最小化算法(Constrained Energy Minimization,CEM)对于大目标地物提取效果不佳的问题.对高光谱图像做降维和端元提取处理,并...为实现对高光谱图像海面舰艇目标进行有效探测,通过对传统的目标探测算法进行改进,解决了加权自相关约束能量最小化算法(Constrained Energy Minimization,CEM)对于大目标地物提取效果不佳的问题.对高光谱图像做降维和端元提取处理,并利用提取的端元进行光谱角匹配(Spectral Angle Mapping,SAM)分类来确定两个重要的分类:舰船类和海水类;从所有像元中减去舰船类像元作为背景像元,通过基于纯背景像元加权自相关矩阵的SAM-CEM算法计算探测结果;通过分类图像来获得只包含海水和舰船的灰度图像,并进行二值化和数学形态学处理,寻找范围最大的白色区域为海水区域;通过对目标探测图像进行二值化,利用舰船目标在海水中的特点,去除不在海水区域内的虚警目标,从而确定最终的舰船目标.实验结果表明:该算法能够更好地增强目标信号而抑制背景信号,从而避免了加权自相关CEM算法中目标信号作为背景信号参与运算而对探测结果的影响,在对海面舰艇的目标探测中取得了令人满意的结果.展开更多
基金support from the PhD research startup foundation of Guangdong Medical University(2XB14006).
文摘Functional near-infrared spectroscopy(fNIRS),as a new optical functional neuroimaging method,has been widely used in neuroscience research.In some research fields with NIRS,heartrate(HR)(or heartbeat)is needed as useful information to evaluate its influence,or to know the state ofsubject,or to remove its artifact.If HR(or heartbeat)can be detected with high accuracy from theoptical intensity,this will undoubtedly benefit a lot to many NIRS studies.Previous studies haveused the moving time window method or mathematical morphology method(MMM)to detectheartbeats in the optical intensity.However,there are some disadvantages in these methods.In thisstudy,we proposed a method combining the periodic information of heartbeats and the operator ofmathematical morphology to automatically detect heartbeats in the optical intensity.First theoptical intensity is smoothed using a moving average flter.Then,the opening operator of math-ematical morphology extracts peaks in the smoothed optical intensity.Finally,one peak is iden-tified as a heartbeat peak if this peak is the maximum in a predefined point range.Throughvalidation on experimental data,our method can overcome the disadvantages of previous methods,and detet heartbeats in the optical signal of fNIRS with nearly 100%accuracy.
基金supported by National Natural Science Foundation of China (No. 61763037)Inner Mongolia Autonomous Region Natural Science Foundation of China(No. 2019LH06007)Science and Technology Plan Project of Inner Mongolia (No. 2019,2020GG028)。
文摘Working conditions of rolling bearings of wind turbine generators are complicated, and their vibration signals often show non-linear and non-stationary characteristics. In order to improve the efficiency of feature extraction of wind turbine rolling bearings and to strengthen the feature information, a new structural element and an adaptive algorithm based on the peak energy are proposed,which are combined with spectral correlation analysis to form a fault diagnosis algorithm for wind turbine rolling bearings. The proposed method firstly addresses the problem of impulsive signal omissions that are prone to occur in the process of fault feature extraction of traditional structural elements and proposes a "W" structural element to capture more characteristic information. Then, the proposed method selects the scale of multi-scale mathematical morphology, aiming at the problem of multi-scale mathematical morphology scale selection and structural element expansion law. An adaptive algorithm based on peak energy is proposed to carry out morphological scale selection and structural element expansion by improving the computing efficiency and enhancing the feature extraction effect.Finally, the proposed method performs spectral correlation analysis in the frequency domain for an unknown signal of the extracted feature and identifies the fault based on the correlation coefficient. The method is verified by numerical examples using experimental rig bearing data and actual wind field acquisition data and compared with traditional triangular and flat structural elements. The experimental results show that the new structural elements can more effectively extract the pulses in the signal and reduce noise interference,and the fault-diagnosis algorithm can accurately identify the fault category and improve the reliability of the results.
文摘为实现对高光谱图像海面舰艇目标进行有效探测,通过对传统的目标探测算法进行改进,解决了加权自相关约束能量最小化算法(Constrained Energy Minimization,CEM)对于大目标地物提取效果不佳的问题.对高光谱图像做降维和端元提取处理,并利用提取的端元进行光谱角匹配(Spectral Angle Mapping,SAM)分类来确定两个重要的分类:舰船类和海水类;从所有像元中减去舰船类像元作为背景像元,通过基于纯背景像元加权自相关矩阵的SAM-CEM算法计算探测结果;通过分类图像来获得只包含海水和舰船的灰度图像,并进行二值化和数学形态学处理,寻找范围最大的白色区域为海水区域;通过对目标探测图像进行二值化,利用舰船目标在海水中的特点,去除不在海水区域内的虚警目标,从而确定最终的舰船目标.实验结果表明:该算法能够更好地增强目标信号而抑制背景信号,从而避免了加权自相关CEM算法中目标信号作为背景信号参与运算而对探测结果的影响,在对海面舰艇的目标探测中取得了令人满意的结果.
