Sensitive and accurate characterization of nanoparticle size in aqueous matrices at environmentally relevant concentrations is still challenging for current nano-analysis techniques. Single particle inductively coupled plasma mass spectrometry (spICP-MS) is an emerging method to characterize the size distribution of nanoparticles and determine their concentrations. Herein for the first time the K-means clustering algorithm is applied to signal processing of spICP-MS raw data. Compared with currently used data processing approaches, the K-means algorithm improved discrimination of particle signals from background signals and provides a sophisticated, statistically based method to quantitatively resolve different size groups contained within a nanoparticle suspension. In tests with commercial Au nanoparticles (AuNPs), spICP-MS with the K-means clustering algorithm can quantitatively discriminate secondary “impurity-size nanoparticles,” present at fractions of less than 2% by mass, from primary-size nanoparticles with the minimum resolvable size difference between the primary and secondary nanoparticles at ∼20 nm. AuNP mixtures in which 80 nm particles act as the “primary size group” and 20 nm, 50 nm, or 100 nm particles act as the “impurity size group” were analyzed by spICP-MS, which reliably measured percentages of secondary impurity-size nanoparticles that are consistent with the expected experimentally determined values. Compared with dynamic light scattering (DLS), spICP-MS has remarkably better particle size resolution capability. We also demonstrated the size measurement advantage of spICP-MS over DLS for commercial CeO2 nanoparticles that are commonly used in the semiconductor industry, where quality control of the nanoparticle size distribution is critical for the wafer polishing process.
11 April 2011 in Analog Integrated Circuits and Signal Processing
Kernel fusion is a popular and effective approach for combining multiple features that characterize different aspects of data. Traditional approaches for Multiple Kernel Learning (MKL) attempt to learn the parameters for combining the kernels through sophisticated optimization procedures. In this paper, we propose an alternative approach that creates dense embeddings for data using the kernel similarities and adopts a deep neural network architecture for fusing the embeddings. In order to improve the effectiveness of this network, we introduce the kernel dropout regularization strategy coupled with the use of an expanded set of composition kernels. Experiment results on a real-world activity recognition dataset show that the proposed architecture is effective in fusing kernels and achieves state-of-the-art performance.
1 November 2017 in IBM Journal of Research and Development
Innovation is a key factor driving economic growth in countries worldwide. However, innovation is hard to define and, therefore, even harder to measure. To help policy makers and business leaders better understand how to foster innovation, we need robust ways to quantify innovation at local and global scales. In this work, we use a data-driven, machine-learning approach for measuring innovation. Analyzing a large number of country-level metrics, we aim to automatically discover actionable “levers” of innovation. Using unsupervised learning methods, we determine groups of related world development indicators among a collection compiled by the World Bank. We then train a Group Lasso predictive model using data from the World Economic Forum (WEF) that captures the perceived level of innovation in 150 countries. Aside from providing high predictive accuracy, the Group Lasso also provides a model that is easily interpretable. The result is the Open Innovation Index (OII), an automatic global model for measuring innovation using machine learning algorithms and open data. We predict the OII scores for countries that only have World Development Indicators data and no existing WEF innovation scores. Furthermore, we also present case studies for which the innovation levers of a few representative countries are uncovered automatically by the proposed model.