Big data in multi-block data analysis: An approach to parallelizing Partial Least Squares Mode B algorithm.

Partial Least Squares (PLS) Mode B is a multi-block method and a tightly coupled algorithm for estimating structural equation models (SEMs). Describing key aspects of parallel computing, we approach the parallelization of the PLS Mode B algorithm to operate on large distributed data. We show the scalability and performance of the algorithm at a very fine-grained level thanks to the versatility of pbdR, a R-project library for parallel computing. We vary several factors under different data distribution schemes in a supercomputing environment. Shorter elapsed times are obtained for the square-blocking factor 16 × 16 using a grid of processors as square as possible and non-square blocking factors 1000 × 4 and 10000 × 4 using an one-column grid of processors. Depending on the configuration, distributing data in a larger number of cores allows reaching speedups of up to 121 over the CPU implementation. Moreover, we show that SEMs can be estimated with big data sets using current state-of-the-art algorithms for multi-block data analysis.

The Malaria System MicroApp: A New, Mobile Device-Based Tool for Malaria Diagnosis.

BACKGROUND: Malaria is a public health problem that affects remote areas worldwide. Climate change has contributed to the problem by allowing for the survival of Anopheles in previously uninhabited areas. As such, several groups have made developing news systems for the automated diagnosis of malaria a priority. OBJECTIVE: The objective of this study was to develop a new, automated, mobile device-based diagnostic system for malaria. The system uses Giemsa-stained peripheral blood samples combined with light microscopy to identify the Plasmodium falciparum species in the ring stage of development. METHODS: The system uses image processing and artificial intelligence techniques as well as a known face detection algorithm to identify Plasmodium parasites. The algorithm is based on integral image and haar-like features concepts, and makes use of weak classifiers with adaptive boosting learning. The search scope of the learning algorithm is reduced in the preprocessing step by removing the background around blood cells. RESULTS: As a proof of concept experiment, the tool was used on 555 malaria-positive and 777 malaria-negative previously-made slides. The accuracy of the system was, on average, 91%, meaning that for every 100 parasite-infected samples, 91 were identified correctly. CONCLUSIONS: Accessibility barriers of low-resource countries can be addressed with low-cost diagnostic tools. Our system, developed for mobile devices (mobile phones and tablets), addresses this by enabling access to health centers in remote communities, and importantly, not depending on extensive malaria expertise or expensive diagnostic detection equipment.

Individual-Based Modeling of Tuberculosis in a User-Friendly Interface: Understanding the Epidemiological Role of Population Heterogeneity in a City.

For millennia tuberculosis (TB) has shown a successful strategy to survive, making it one of the world's deadliest infectious diseases. This resilient behavior is based not only on remaining hidden in most of the infected population, but also by showing slow evolution in most sick people. The course of the disease within a population is highly related to its heterogeneity. Thus, classic epidemiological approaches with a top-down perspective have not succeeded in understanding its dynamics. In the past decade a few individual-based models were built, but most of them preserved a top-down view that makes it difficult to study a heterogeneous population. We propose an individual-based model developed with a bottom-up approach to studying the dynamics of pulmonary TB in a certain population, considered constant. Individuals may belong to the following classes: healthy, infected, sick, under treatment, and treated with a probability of relapse. Several variables and parameters account for their age, origin (native or immigrant), immunodeficiency, diabetes, and other risk factors (smoking and alcoholism). The time within each infection state is controlled, and sick individuals may show a cavitated disease or not that conditions infectiousness. It was implemented in NetLogo because it allows non-modelers to perform virtual experiments with a user-friendly interface. The simulation was conducted with data from Ciutat Vella, a district of Barcelona with an incidence of 67 TB cases per 100,000 inhabitants in 2013. Several virtual experiments were performed to relate the disease dynamics with the structure of the infected subpopulation (e.g., the distribution of infected times). Moreover, the short-term effect of health control policies on modifying that structure was studied. Results show that the characteristics of the population are crucial for the local epidemiology of TB. The developed user-friendly tool is ready to test control strategies of disease in any city in the short-term.