Rockburst laboratory tests database - Application of data mining techniques

Rockburst is characterized by a violent explosion of a block causing a sudden rupture in the rock and is quite common in deep tunnels. It is critical to understand the phenomenon of rockburst, focusing on the patterns of occurrence so these events can be avoided and/or managed saving costs and possibly lives. The failure mechanism of rockburst needs to be better understood. Laboratory experiments are undergoing at the Laboratory for Geomechanics and Deep Underground Engineering (SKLGDUE) of Beijing and the system is described. A large number of rockburst tests were performed and their information collected, stored in a database and analyzed. Data Mining (DM) techniques were applied to the database in order to develop predictive models for the rockburst maximum stress (σRB) and rockburst risk index (IRB) that need the results of such tests to be determined. With the developed models it is possible to predict these parameters with high accuracy levels using data from the rock mass and specific project.

A continuous solvent- and oil-free method to prepare injectable PEGylated fibrinogen cell-laden microparticles

Injectable biomaterials with in situ cross-linking reactions have been suggested to minimize the invasiveness associated with most implantation procedures. However, problems related with the rapid liquid-to-gel transition reaction can arise because it is difficult to predict the reliability of the reaction and its end products, as well as to mitigate cytotoxicity to the surrounding tissues. An alternative minimally invasive approach to deliver solid implants in vivo is based on injectable microparticles, which can be processed in vitro with high fidelity and reliability, while showing low cytotoxicity. Their delivery to the defect can be performed by injection through a small diameter syringe needle. We present a new methodology for the continuous, solvent- and oil-free production of photopolymerizable microparticles containing encapsulated human dermal fibroblasts. A precursor solution of cells in photo-reactive PEG-fibrinogen (PF) polymer was transported through a transparent injector exposed to light-irradiation before being atomized in a jet-in-air nozzle. Shear rheometry data provided the cross-linking kinetics of each PF/cell solution, which was then used to determine the amount of irradiation required to partially polymerize the mixture prior to atomization. The partially polymerized drops fell into a gelation bath for further polymerization. The system was capable of producing cell-laden microparticles with high cellular viability, with an average diameter of between 88.1 µm to 347.1 µm and a dispersity of between 1.1 and 2.4, depending on the parameters chosen.

Innovative method for the continuous monitoring of concrete viscoelastic properties since early ages: concept and pilot experiments

The experimental evaluation of viscoelastic properties of concrete is traditionally made upon creep tests that consist in the application of sustained loads either in compression or in tension. This kind of testing demands for specially devised rigs and requires careful monitoring of the evolution of strains, whereas assuring proper load constancy. The characterization of creep behaviour at early ages offers additional challenges due to the strong variations in viscoelastic behaviour of concrete during such stages, demanding for several testing ages to be assessed. The present research work aims to assist in reducing efforts for continuous assessment of viscoelastic properties of concrete at early ages, by application of a dynamic testing technique inspired in methodologies used in polymer science: Dynamic Mechanical Analyses. This paper briefly explains the principles of the proposed methodology and exhibits the first results obtained in a pilot application. The results are promising enough to encourage further developments.

A bayesian approach for NDT data fusion: The Saint Torcato Church case study

This paper presents a methodology based on the Bayesian data fusion techniques applied to non-destructive and destructive tests for the structural assessment of historical constructions. The aim of the methodology is to reduce the uncertainties of the parameter estimation. The Young's modulus of granite stones was chosen as an example for the present paper. The methodology considers several levels of uncertainty since the parameters of interest are considered random variables with random moments. A new concept of Trust Factor was introduced to affect the uncertainty related to each test results, translated by their standard deviation, depending on the higher or lower reliability of each test to predict a certain parameter.

The effect of secular trends in the classroom furniture mismatch: support for continuous update of school furniture standards

In order to create safer schools, the Chilean authorities published a Standard regarding school furniture dimensions. The aims of this study are twofold: to verify the existence of positive secular trend within the Chilean student population and to evaluate the potential mismatch between the anthropometric characteristics and the school furniture dimensions defined by the mentioned standard. The sample consists of 3078 subjects. Eight anthropometric measures were gathered, together with six furniture dimensions from the mentioned standard. There is an average increase for some dimensions within the Chilean student population over the past two decades. Accordingly, almost 18% of the students will find the seat height to be too high. Seat depth will be considered as being too shallow for 42.8% of the students. It can be concluded that the Chilean student population has increased in stature, which supports the need to revise and update the data from the mentioned Standard. Practitioner Summary: Positive secular trend resulted in high levels of mismatch if furniture is selected according to the current Chilean Standard which uses data collected more than 20 years ago. This study shows that school furniture standards need to be updated over time.

Using customer lifetime value to improve the prediction of bank deposit subscription in telemarketing campaigns

Customer lifetime value (LTV) enables using client characteristics, such as recency, frequency and monetary (RFM) value, to describe the value of a client through time in terms of profitability. We present the concept of LTV applied to telemarketing for improving the return-on-investment, using a recent (from 2008 to 2013) and real case study of bank campaigns to sell long- term deposits. The goal was to benefit from past contacts history to extract additional knowledge. A total of twelve LTV input variables were tested, un- der a forward selection method and using a realistic rolling windows scheme, highlighting the validity of five new LTV features. The results achieved by our LTV data-driven approach using neural networks allowed an improvement up to 4 pp in the Lift cumulative curve for targeting the deposit subscribers when compared with a baseline model (with no history data). Explanatory knowledge was also extracted from the proposed model, revealing two highly relevant LTV features, the last result of the previous campaign to sell the same product and the frequency of past client successes. The obtained results are particularly valuable for contact center companies, which can improve pre- dictive performance without even having to ask for more information to the companies they serve.

From a NoSQL data source to a business intelligence solution: An experiment

We are living in the era of Big Data. A time which is characterized by the continuous creation of vast amounts of data, originated from different sources, and with different formats. First, with the rise of the social networks and, more recently, with the advent of the Internet of Things (IoT), in which everyone and (eventually) everything is linked to the Internet, data with enormous potential for organizations is being continuously generated. In order to be more competitive, organizations want to access and explore all the richness that is present in those data. Indeed, Big Data is only as valuable as the insights organizations gather from it to make better decisions, which is the main goal of Business Intelligence. In this paper we describe an experiment in which data obtained from a NoSQL data source (database technology explicitly developed to deal with the specificities of Big Data) is used to feed a Business Intelligence solution.

Development of computational tools for the integrated analysis of DNA microarray data with applications in cancer research

The MAP-i Doctoral Program of the Universities of Minho, Aveiro and Porto

Integrating data from heterogeneous DNA microarray platforms

DNA microarrays are one of the most used technologies for gene expression measurement. However, there are several distinct microarray platforms, from different manufacturers, each with its own measurement protocol, resulting in data that can hardly be compared or directly integrated. Data integration from multiple sources aims to improve the assertiveness of statistical tests, reducing the data dimensionality problem. The integration of heterogeneous DNA microarray platforms comprehends a set of tasks that range from the re-annotation of the features used on gene expression, to data normalization and batch effect elimination. In this work, a complete methodology for gene expression data integration and application is proposed, which comprehends a transcript-based re-annotation process and several methods for batch effect attenuation. The integrated data will be used to select the best feature set and learning algorithm for a brain tumor classification case study. The integration will consider data from heterogeneous Agilent and Affymetrix platforms, collected from public gene expression databases, such as The Cancer Genome Atlas and Gene Expression Omnibus.

Nonparametric estimation of time-dependent ROC curves conditional on a continuous covariate

The receiver-operating characteristic (ROC) curve is the most widely used measure for evaluating the performance of a diagnostic biomarker when predicting a binary disease outcome. The ROC curve displays the true positive rate (or sensitivity) and the false positive rate (or 1-specificity) for different cut-off values used to classify an individual as healthy or diseased. In time-to-event studies, however, the disease status (e.g. death or alive) of an individual is not a fixed characteristic, and it varies along the study. In such cases, when evaluating the performance of the biomarker, several issues should be taken into account: first, the time-dependent nature of the disease status; and second, the presence of incomplete data (e.g. censored data typically present in survival studies). Accordingly, to assess the discrimination power of continuous biomarkers for time-dependent disease outcomes, time-dependent extensions of true positive rate, false positive rate, and ROC curve have been recently proposed. In this work, we present new nonparametric estimators of the cumulative/dynamic time-dependent ROC curve that allow accounting for the possible modifying effect of current or past covariate measures on the discriminatory power of the biomarker. The proposed estimators can accommodate right-censored data, as well as covariate-dependent censoring. The behavior of the estimators proposed in this study will be explored through simulations and illustrated using data from a cohort of patients who suffered from acute coronary syndrome.

Sistema de aquisição e comunicação para sensores magnetoelétricos

Dissertação de mestrado integrado em Engenharia Eletrónica Industrial e Computadores

Estimativa dos parâmetros de compactação de solos usando técnicas de data mining

Dissertação de mestrado integrado em Engenharia Civil

Reforço à flexão de lajes de betão armado com laminados de CFRP pré-esforçados

Dissertação de mestrado integrado em Engenharia Civil (área de especialização em Estruturas e Geotecnia)

Real-Time decision support using data mining to predict blood pressure critical events in intensive medicine patients

Patient blood pressure is an important vital signal to the physicians take a decision and to better understand the patient condition. In Intensive Care Units is possible monitoring the blood pressure due the fact of the patient being in continuous monitoring through bedside monitors and the use of sensors. The intensivist only have access to vital signs values when they look to the monitor or consult the values hourly collected. Most important is the sequence of the values collected, i.e., a set of highest or lowest values can signify a critical event and bring future complications to a patient as is Hypotension or Hypertension. This complications can leverage a set of dangerous diseases and side-effects. The main goal of this work is to predict the probability of a patient has a blood pressure critical event in the next hours by combining a set of patient data collected in real-time and using Data Mining classification techniques. As output the models indicate the probability (%) of a patient has a Blood Pressure Critical Event in the next hour. The achieved results showed to be very promising, presenting sensitivity around of 95%.