Multichannel biomedical time series clustering via hierarchical probabilistic latent semantic analysis

Biomedical time series clustering that automatically groups a collection of time series according to their internal similarity is of importance for medical record management and inspection such as bio-signals archiving and retrieval. In this paper, a novel framework that automatically groups a set of unlabelled multichannel biomedical time series according to their internal structural similarity is proposed. Specifically, we treat a multichannel biomedical time series as a document and extract local segments from the time series as words. We extend a topic model, i.e., the Hierarchical probabilistic Latent Semantic Analysis (H-pLSA), which was originally developed for visual motion analysis to cluster a set of unlabelled multichannel time series. The H-pLSA models each channel of the multichannel time series using a local pLSA in the first layer. The topics learned in the local pLSA are then fed to a global pLSA in the second layer to discover the categories of multichannel time series. Experiments on a dataset extracted from multichannel Electrocardiography (ECG) signals demonstrate that the proposed method performs better than previous state-of-the-art approaches and is relatively robust to the variations of parameters including length of local segments and dictionary size. Although the experimental evaluation used the multichannel ECG signals in a biometric scenario, the proposed algorithm is a universal framework for multichannel biomedical time series clustering according to their structural similarity, which has many applications in biomedical time series management.

A new insight into growth mechanism and kinetics of mesoporous silica nanoparticles by in situ small angle x-ray scattering

The growth mechanism and kinetics of mesoporous silica nanoparticles (MSNs) were investigated for the first time by using a synchrotron time-resolved small-angle X-ray scattering (SAXS) analysis. The synchrotron SAXS offers unsurpassed time resolution and the ability to detect structural changes of nanometer sized objects, which are beneficial for the understanding of the growth mechanism of small MSNs (∼20 nm). The Porod invariant was used to quantify the conversion of tetraethyl orthosilicate (TEOS) in silica during MSN formation, and the growth kinetics were investigated at different solution pH and temperature through calculating the scattering invariant as a function of reaction time. The growth of MSNs was found to be accelerated at high temperature and high pH, resulting in a higher rate of silica formation. Modeling SAXS data of micelles, where a well-defined electrostatic interaction is assumed, determines the size and shape of hexadecyltrimethylammonium bromide (CTAB) micelles before and after the addition of TEOS. The results suggested that the micelle size increases and the micelle shape changes from ellipsoid to spherical, which might be attributed to the solubilization of TEOS in the hydrophobic core of CTAB micelles. A new "swelling-shrinking" mechanism is proposed. The mechanism provides new insights into understanding MSN growth for the formation of functional mesoporous materials exhibiting controlled morphologies. The SAXS analyses were correlated to the structure of CTAB micelles and chemical reaction of TEOS. This study has provided critical information to an understanding of the growth kinetics and mechanism of MSNs.