Media convergence is a media change led by technological innovation. Applying media convergence technology to the study of clustering in Chinese medicine can significantly exploit the advantages of media fusion. Obtaining consistent and complementary information among multiple modalities through media convergence can provide technical support for clustering. This article presents an approach based on Media Convergence and Graph convolution Encoder Clustering (MCGEC) for traditonal Chinese medicine (TCM) clinical data. It feeds modal information and graph structure from media information into a multi-modal graph convolution encoder to obtain the media feature representation learnt from multiple modalities. MCGEC captures latent information from various modalities by fusion and optimises the feature representations and network architecture with learnt clustering labels. The experiment is conducted on real-world multimodal TCM clinical data, including information like images and text. MCGEC has improved clustering results compared to the generic single-modal clustering methods and the current more advanced multi-modal clustering methods. MCGEC applied to TCM clinical datasets can achieve better results. Integrating multimedia features into clustering algorithms offers significant benefits compared to single-modal clustering approaches that simply concatenate features from different modalities. It provides practical technical support for multi-modal clustering in the TCM field incorporating multimedia features.

Flexible electrolyte-gated graphene field effect transistors (Eg-GFETs) are widely developed as sensors because of fast response, versatility and low-cost. However, their sensitivities and responding ranges are often altered by different gate voltages. These bias-voltage-induced uncertainties are an obstacle in the development of Eg-GFETs. To shield from this risk, a machine-learning-algorithm-based LgGFETs’ data analyzing method is studied in this work by using Ca2+ detection as a proof-of-concept. For the as-prepared Eg-GFET-Ca2+ sensors, their transfer and output features are first measured. Then, eight regression models are trained with the use of different machine learning algorithms, including linear regression, support vector machine, decision tree and random forest, etc. Then, the optimized model is obtained with the random-forest-method-treated transfer curves. Finally, the proposed method is applied to determine Ca2+ concentration in a calibration-free way, and it is found that the relation between the estimated and real Ca2+ concentrations is close-to y = x. Accordingly, we think the proposed method may not only provide an accurate result but also simplify the traditional calibration step in using Eg-GFET sensors.

Photoplethysmography (PPG) is a non-invasive technology and widely used in medical monitoring. Nowadays, dynamic vital signs monitoring based on PPG technology is in emergence and shows great potential for commercialization, however, it is still challenged by massive noise evoked by respiration and muscle contraction. Herein, a portable PPG signal's dynamic acquisition and denoise system is constructed and applied to blood pressure (BP) estimation, in which an improved PPG denoise method based on complete ensemble empirical mode decomposition with adaptive noise and wavelet transform (CEEMDAN-WT), is described. Firstly, original PPG signal is measured by the proposed hardware, then CEEMDAN decomposes it into a group of components. Secondly, the noise dominated components are found by calculating the coefficients between the components and original signal, and removed by WT. Thirdly, fast Fourier transform is performed to remove the component whose dominant frequency exceeds 0.5–20 Hz. Fourthly, a fresh PPG signal is reconstructed and compared with the signal rebuilt by other methods, which proves that CEEMDAN-WT has higher signal-to-noise ratio and lower root mean square error. Last but not least, the reconstructed signal is applied to estimate systolic and diastolic BP, according to Windkessel model and aided by neural network algorithm. Overall, this work demonstrates the feasibility of the portable PPG dynamic acquisition and its application for dynamic vital signs monitoring, in which CEEMDAN-WT algorithm can effectively remove most of the noises in dynamic PPG signal. In conclusion, it demonstrates CEEMDAN-WT method can effectively remove noise from PPG signals in the state of motion, it may have a good potential for calculating other physiological indexes besides BP, and push PPG applications from professional medical to daily life.

No abstract