Development of Respiratory Signal Extraction System Based on Photoplethysmography / 中国医疗器械杂志

Oxygen saturation and respiratory signals are important physiological signals of human body, respiratory monitoring plays an important role in clinical and daily life. A system was established to extract respiratory signals from photoplethysmography in this study. Including the collection of pulse wave signal, the extraction of respiratory signal, and the calculation of respiratory rate and pulse rate transmitted from the slave computer to the host computer in real time.

Chlorophyll content for millet leaf using hyperspectral imaging and an attention-convolutional neural network / Estimativa do teor de clorofila para folhas de milheto usando imagens hiperespectrais e uma rede neural atenção-convolucional

ABSTRACT: Chlorophyll is a major factor affecting photosynthesis; and consequently, crop growth and yield. In this study, we devised a chlorophyll-content detection model for millet leaves in different stages of growth based on hyperspectral data. The hyperspectral images of millet leaves were obtained under a wavelength range of 380-1000 nm using a hyperspectral imager. Threshold segmentation was performed with near-infrared (NIR) reflectance and normalized difference vegetation index (NDVI) to intelligently acquire the regions of interest (ROI). Furthermore, raw spectral data were preprocessed using multivariate scatter correction (MSC). A correlation coefficient-successive projections algorithm (CC-SPA) was used to extract the characteristic wavelengths, and the characteristic parameters were extracted based on the spectral and image information. A partial least squares regression (PLSR) prediction model was established based on the single characteristic parameter and multi-characteristic parameter fusion. The determination coefficient (Rv 2) and the root-mean-square error (RMSEv) of the validation set for the multi-characteristic parameter fusion model were reported to be 0.813 and 1.766, respectively, which are higher than those obtained by the single characteristic parameter model. Based on the multi-characteristic parameter fusion, an attention-convolutional neural network (attention-CNN) (Rv 2 = 0.839, RMSEv = 1.451, RPD = 2.355) was established, which is more effective than the PLSR (Rv 2 = 0.813, RMSEv = 1.766, RPD = 2.167) and least squares support vector machine (LS-SVM) models (Rv 2 = 0.806, RMSEv = 1.576, RPD = 2.061). These results indicated that the combination of hyperspectral imaging and attention-CNN is beneficial to the application of nutrient element monitoring of crops.

RESUMO: A clorofila é um fator importante que afeta a fotossíntese e, consequentemente, o crescimento e o rendimento das culturas. Neste estudo, um modelo de detecção de conteúdo de clorofila é construído para folhas de milheto em diferentes estágios de crescimento, com base em dados hiperespectrais. As imagens hiperespectrais dos diferentes estágios de crescimento das folhas de milheto foram obtidas para 380-1000 nm, utilizando um gerador de imagens hiperespectrais. Uma segmentação de limiar foi realizada com refletância no infravermelho próximo (NIR) e índice de vegetação com diferença normalizada (NDVI) para adquirir de forma inteligente as regiões de interesse (ROI). Além disso, os dados espectrais brutos foram pré-processados usando o método de correção de dispersão multivariada (MSC). Um algoritmo de projeção de coeficiente de correlação sucessivo (CC-SPA) foi utilizado para extrair os comprimentos de onda característicos, e os parâmetros característicos foram extraídos com base nas informações espectrais e de imagem. O modelo de previsão de regressão parcial dos mínimos quadrados (PLSR) foi estabelecido com base nos parâmetros de característica única e na fusão de parâmetros de característica múltipla. O coeficiente de determinação (Rv2) e o erro quadrático médio da raiz (RMSEv) do conjunto de validação para o modelo de fusão de parâmetros com várias características foram obtidos como 0,813 e 1,766, sendo melhores do que os do modelo de parâmetro de característica única. Com base na fusão de parâmetros com várias características, foi estabelecida uma rede neural atenção-convolucional (atenção-CNN) (Rv2 = 0,839, RMSEv = 1,451, RPD = 2,355) mais eficaz que o PLSR (Rv2 = 0,813, RMSEv = 1,766, RPD = 2,167) e mínimos quadrados que suportam modelos de máquina de vetores (LS-SVM) (Rv2 = 0,806, RMSEv = 1,576, RPD = 2,061). Estes resultados indicam que o modelo atenção-CNN atinge uma previsão efetiva do teor de clorofila nas folhas de milheto usando os dados hiperespectrais. Além disso, esta pesquisa demonstra que a combinação de imagens hiperespectrais e a atenção-CNN se mostra benéfica para a aplicação do monitoramento dos elementos nutricionais das culturas.

Methods of removing the baseline wander in ECG based on the lifting wavelet transform / 中国医学装备

Objective:To avoid the redundant computation based on the convolution operation in the traditional wavelet transform, and to remove the baseline wander noise existing in the course of collecting the ECG signal. Methods: Use the lifting wavelet transform with two wavelets, and constitute the ECG signal with the noise removed after decomposing, setting the subband coefficient including the noise to zero, and rebuilding. Results:Use MATLAB to remove the baseline wander noise in the ECG signal and bw provided by the MIT-BIH database, and the results show that the baseline wander was removed effectively. Conclusion:The baseline wander noise in the ECG signal can be removed accurately though the method mentioned above, the waveform information in the original ECG signal can be maintained effectively, and subsequently, that can provide help for detecting the characteristic parameters in the ECG signal.

Research on Noninvasive Diagnosis for Coronary Heart Disease Based on Neural Network / 航天医学与医学工程

Objective To extract characteristic parameters of ECG signals a new method of non-invasive diagnosis for coronary heart disease with artificial neural network. Methods ECG signals were digitized with A/D converter and filtered to eliminating the noise. Span of QRS interval, R-R interval,and voltage of S-T segment of filtered ECG were detected. These 3 characteristics were as the input parameters of the input layer. Samples were trained with an improved 3-layers back propagation(BP) artificial neural network, as trained samples. The non-trained samples were recognized with these BP neural networks. Results After 12 samples had been trained about 1500 times, the BP neural network could accurately distinguish samples of coronary heart disease from the trained samples and also recognize 20 non-trained samples, 19 to be correct except one. Conclusion It is showed that based on BP network and characteristic parameters of ECG, a new and promising method of non-invasive diagnosis for coronary heart disease has been found.

Measurement and analysis of multi-frequency electrical impedance in crus after long time seawater immersion / 医疗卫生装备

In order to monitor the influence of long time seawater immersion on human body,a multi-frequency electrical impedance measurement system was established.Based on this system,electrical impedance information of 10 soldiers was collected at different time during 6h of continuous seawater immersion.The results showed that as the immersion time lasting,the electrical impedance characteristic parameters R0?R∞ and ? decreased significantly.And the fc also decreased after 6h seawater immersion.Therefore,the electrical impedance technique can be used as a means to monitoring the degree of seawater immersion.

Selection of Characteristic Information for the Diagnosis of Traditional Chinese Medical Syndrome in Rheumatoid Arthritis / 广州中医药大学学报

Objective To obtain the effective characteristic information for the standardization of diagnosis of traditional Chinese medical(TCM) syndrome in rheumatoid arthritis(RA).Methods Fifty-four items of symptoms and signs in RA patients were input into the computer,and Mahalanobis distance discriminant analysis(DDA) was used for the selection of effective indexes.Results According to the weight value and the result of T test,17 items from 54 had the highest rate of discrimination accuracy,up to 96.5%.Conclusion The results of computerized pattern recognition for the syndrome diagnosis of RA are consistent with the clinical diagnosis,which indicates that computerized pattern recognition can be used for the standardization of syndrome diagnosis of RA.