Search

This paper is a description of the designing of a new mainstream device to measure human respiration carbon dioxide concentration, based on non-dispersive infrared (NDIR) absorption technology. The device can be used to accurately monitor the cardiopulmonary status during anaesthesia and mechanical ventilation in real time. This new device can not only make up the error of real-time gas measurement of the side-stream device, but also make up the accuracy of the main-stream device. In the paper, four issues which can affect the measurement accuracy were considered: respiration gas flow, turbulence of the light source with all ranges of wavelength, temperature drift and signal noise. The experimental results showed that the device could produce a stable output signal and deviation of measurement accuracy could be achieved to within 4%. [ABSTRACT FROM AUTHOR]

Eigenvalues are intrinsic and representative values of a square matrix. They have thus been used in many image processing areas due to their important application value, but not in the image quality assessment (IQA) field. In this Letter, the authors study the correlation between local mean eigenvalues (LMEs) and perceptual quality of images, and demonstrate the applicability of LMEs in IQA. The LMEs are related to structural complexity of images. The LMEs and natural scene statistics features are utilised for a sparse dictionary learning. Experimental results conducted on promising IQA databases show their method's superiority in comparison with top-performing blind IQA metrics. [ABSTRACT FROM AUTHOR]

Weed identification helps ensure crop yield and realize precision agriculture. Although the deep learning-based methods have achieved high performance, their needed large-scale annotated data is difficult to obtain, and the massive parameters lead to difficulties in model deployment in embedded applications. To develop efficient crop weeds classification system, we propose a dissimilarity-based method to select few but representative samples and consider data diversity. Many experiments are conducted on two different datasets. Results show that the proposed method can obtain test accuracy of 90.75% with 32% amount of the DeepWeeds dataset, up to 99.18% of the baseline accuracy. For the Grass-Broadleaf dataset, our approach can obtain the test accuracy of 98.97% with 27.8% amount of the dataset, up to 99.5% of the baseline accuracy. Further, the designed model is compressed from 117.9 MB to 8.6 MB, with a compression ratio of 92.7%, while with only 1% degradation of accuracy. Finally, the compressed model is deployed to NVIDIA Jetson AGX Xavier, running at 192 fps. This work can lay a foundation for the following research about few-shot learning, data quality assessment, and model deployment in agriculture. [ABSTRACT FROM AUTHOR]

A low-frequency vibration measurement based on a camera-projector system is proposed and verified by experiment at several hertz. A CCD camera gathered deformed fringes modulated by a vibrating trumpet at a constant sampling rate. Information on amplitude and frequency are contained in a series of observed images. The height value of each pixel point in the image can be restored by using Fourier transform profilometry. Connecting the height value of every sampling frame into a motion trajectory, the frequency and amplitude of the vibrating object can be obtained from the trajectory curve. The experiment restored the vibration process of a trumpet in half a cycle while the vibrating frequency was 3 Hz. Subsequently, the measurement of different frequencies and different amplitudes are comparatively studied. The results show that slight vibration at 35 µm and above can be detected by the system, which confirms the feasibility of the proposed system in the field of industrial vibration measurement. [ABSTRACT FROM AUTHOR]

Most of the current respiratory devices for monitoring CO2concentration use the side-stream structure. In this work, we engage to design a new double-end mainstream device for monitoring CO2concentration of gas breathed out of the human body. The device can accurately monitor the cardiopulmonary status during anesthesia and mechanical ventilation in real time. Meanwhile, to decrease the negative influence of device noise and the low sample precision caused by temperature drift, wavelet packet denoising and temperature drift compensation are used. The new capnograph is proven by clinical trials to be helpful in improving the accuracy of capnography. [ABSTRACT FROM AUTHOR]