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.

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

Dissertação de mestrado integrado em Engenharia Civil

Artificial thymus: a tissue engineering strategy

The thymus is the central organ responsible for the generation of T lymphocytes (1). Various diseases cause the thymus to produce in- sufficient T cells, which can lead to immune-suppression (2). Since T cells are essential for the protection against pathogens, it is crucial to promote de novo differentiation of T cells on diseased individuals. The available clinical solutions are: 1) one protocol involving the transplant of thymic stroma from unrelated children only applicable for athymic children (3); 2) for patients with severe peripheral T cell depletion and reduced thymic activity, the administration of stimu- lating molecules stimulating the activity of the endogenous thymus (4). A scaffold (CellFoam) was suggested to support thymus regen- eration in vivo (5), although this research was discontinued. Herein, we propose an innovative strategy to generate a bioartificial thymus. We use a polycaprolactone nanofiber mesh (PCL-NFM) seeded and cultured with human thymic epithelial cells (hTECs). The cells were obtained from infant thymus collected during pediatric cardio-tho- racic surgeries. We report new data on the isolation and characterization of those cells and their interaction with PCL-NFM, by expanding hTECs into relevant numbers and by optimizing cell seeding methods.

Stromal vascular fraction cell sheets angiogenic potential for tissue engineering and regenerative medicine applications

One of the biggest concerns in the Tissue Engineering field is the correct vascularization of engineered constructs. Strategies involving the use of endothelial cells are promising but adequate cell sourcing and neo-vessels stability are enduring challenges. In this work, we propose the hypoxic pre-conditioning of the stromal vascular fraction (SVF) of human adipose tissue to obtain highly angiogenic cell sheets (CS). For that, SVF was isolated after enzymatic dissociation of adipose tissue and cultured until CS formation in normoxic (pO2=21%) and hypoxic (pO2=5%) conditions for 5 and 8 days, in basal medium. Immunocytochemistry against CD31 and CD146 revealed the presence of highly branched capillary-like structures, which were far more complex for hypoxia. ELISA quantification showed increased VEGF and TIMP-1 secretion in hypoxia for 8 days of culture. In a Matrigel assay, the formation of capillary-like structures by endothelial cells was more prominent when cultured in conditioned medium recovered from the cultures in hypoxia. The same conditioned medium increased the migration of adipose stromal cells in a scratch assay, when compared with the medium from normoxia. Histological analysis after implantation of 8 days normoxic- and hypoxic-conditioned SVF CS in a hindlimb ischemia murine model showed improved formation of neo-blood vessels. Furthermore, Laser Doppler results demonstrated that the blood perfusion of the injured limb after 30 days was enhanced for the hypoxic CS group. Overall, these results suggest that SVF CS created under hypoxia can be used as functional vascularization units for tissue engineering and regenerative medicine.

Establishing guidelines for obtaining optimal cell sources to use in tendon tissue engineering strategies

Cell-based approaches in tissue engineering (TE) have been barely explored for the treatment of tendon and ligament (T/L) tissues, requiring the establishment of a widely available cell source with tenogenic potential. As T/L cells are scarce, stem cells may provide a good alternative. Understanding how resident cells behave in vitro, might be useful for recapitulating the tenogenic potential of stem cells for tendon TE applications. Therefore, we propose to isolate and characterize human T/L-derived cells (hTDCs and hLDCs) and compare their regenerative potential with stem cells from adipose tissue (hASCs) and amniotic fluid (hAFSCs)(1). T/L cells were isolated using different procedures and stem cells isolated as described elsewhere(1). Moreover, T/L cells were stimu- lated into the three mesenchymal lineages, using standard differentia- tion media. Cells were characterized for the typical stem cell markers as well as T/L related markers, namely tenascin-C, collagen I and III, decorin and scleraxis, using different complementary techniques such as real time RT-PCR, immunocytochemistry and flow cytometry. No differences were observed between T/L in gene expression and protein deposition. T/L cells were mostly positive for stem ness markers (CD73/CD90/CD105), and have the potential to differentiate towards osteogenesis, chondrogenesis and adipogenesis, demonstrated by the positive staining for AlizarinRed, SafraninO, ToluidineBlue and OilRed. hASCs and hAFSCs exhibit positive expression of all tenogenic mark- ers, although at lower levels than hTDCs and hLDCs. Nevertheless, stem cells availability is key factor in TE strategies, despite that it’s still required optimization to direct their tenogenic phenotype.

Advancing tendon regeneration through the development of bio-stimulating tissue engineering approaches

Tendon tissue engineering (TE) requires tailoring scaffolds designs and properties to the anatomical and functional requirements of tendons located in different regions of the body. Cell sourcing is also of utmost importance as tendon cells are scarce. Recently, we have found that it is possible to direct the tenogenic differentiation of Amniotic fluid and Adipose tissue derived stem cells (hAFSCs and hASCs), and also that there are hASCs subpopulations that might be more prone to tenogenic differentiation. Nevertheless, biochemical stimulation may not be enough to develop functional TE substitutes for a tissue that is known to be highly dependent on mechanical loading.

Compact saloplastic membranes of natural polysaccharides for soft tissue engineering

The regeneration of soft biological tissues requires new substitutes that exhibit mechanical properties similar to the native tissue. Herein, thin saloplastic membranes with tunable physical properties are prepared by complexation of chitosan and alginate solutions containing different concentrations of sodium chloride. Polyelectrolyte complexes (PECs) are transferred to flat Petri dishes for compaction into membrane shapes by sedimentation and solvent evaporation. All membranes are resistant to degradation by lysozyme and are stable in solutions with pH values between 1 and 13. Immersing the different membranes in new doping solutions of increasing salt concentrations triggers the typical saloplastic behavior, with a high water absorption and decrease of the rigidity and ultimate tensile strength. The range of such variations is tuned by the sodium chloride amount used in the synthesis: high salt concentrations increase water uptake and tensile moduli, while decreasing the ultimate strength. Cellular assays demonstrate high proliferation rates and viability of L929 fibroblasts seeded onto the most rigid membranes. The results validate the use of saloplastic membranes as soft tissue substitutes for future biomedical applications.

Using data mining for prediction of hospital length of stay: an application of the CRISP-DM Methodology

Hospitals are nowadays collecting vast amounts of data related with patient records. All this data hold valuable knowledge that can be used to improve hospital decision making. Data mining techniques aim precisely at the extraction of useful knowledge from raw data. This work describes an implementation of a medical data mining project approach based on the CRISP-DM methodology. Recent real-world data, from 2000 to 2013, were collected from a Portuguese hospital and related with inpatient hospitalization. The goal was to predict generic hospital Length Of Stay based on indicators that are commonly available at the hospitalization process (e.g., gender, age, episode type, medical specialty). At the data preparation stage, the data were cleaned and variables were selected and transformed, leading to 14 inputs. Next, at the modeling stage, a regression approach was adopted, where six learning methods were compared: Average Prediction, Multiple Regression, Decision Tree, Artificial Neural Network ensemble, Support Vector Machine and Random Forest. The best learning model was obtained by the Random Forest method, which presents a high quality coefficient of determination value (0.81). This model was then opened by using a sensitivity analysis procedure that revealed three influential input attributes: the hospital episode type, the physical service where the patient is hospitalized and the associated medical specialty. Such extracted knowledge confirmed that the obtained predictive model is credible and with potential value for supporting decisions of hospital managers.

Business intelligence in banking: A literature analysis from 2002 to 2013 using Text Mining and latent Dirichlet allocation

telligence applications for the banking industry. Searches were performed in relevant journals resulting in 219 articles published between 2002 and 2013. To analyze such a large number of manuscripts, text mining techniques were used in pursuit for relevant terms on both business intelligence and banking domains. Moreover, the latent Dirichlet allocation modeling was used in or- der to group articles in several relevant topics. The analysis was conducted using a dictionary of terms belonging to both banking and business intelli- gence domains. Such procedure allowed for the identification of relationships between terms and topics grouping articles, enabling to emerge hypotheses regarding research directions. To confirm such hypotheses, relevant articles were collected and scrutinized, allowing to validate the text mining proce- dure. The results show that credit in banking is clearly the main application trend, particularly predicting risk and thus supporting credit approval or de- nial. There is also a relevant interest in bankruptcy and fraud prediction. Customer retention seems to be associated, although weakly, with targeting, justifying bank offers to reduce churn. In addition, a large number of ar- ticles focused more on business intelligence techniques and its applications, using the banking industry just for evaluation, thus, not clearly acclaiming for benefits in the banking business. By identifying these current research topics, this study also highlights opportunities for future research.

Combining data mining and evolutionary computation for multi-criteria optimization of earthworks

Earthworks tasks aim at levelling the ground surface at a target construction area and precede any kind of structural construction (e.g., road and railway construction). It is comprised of sequential tasks, such as excavation, transportation, spreading and compaction, and it is strongly based on heavy mechanical equipment and repetitive processes. Under this context, it is essential to optimize the usage of all available resources under two key criteria: the costs and duration of earthwork projects. In this paper, we present an integrated system that uses two artificial intelligence based techniques: data mining and evolutionary multi-objective optimization. The former is used to build data-driven models capable of providing realistic estimates of resource productivity, while the latter is used to optimize resource allocation considering the two main earthwork objectives (duration and cost). Experiments held using real-world data, from a construction site, have shown that the proposed system is competitive when compared with current manual earthwork design.

Industrial engineering and management curriculum profile: Developing a framework of competences

This paper presents a framework of competences developed for Industrial Engineering and Management that can be used as a tool for curriculum analysis and design, including the teaching and learning processes as well as the alignment of the curriculum with the professional profile. The framework was applied to the Industrial Engineering and Management program at University of Minho (UMinho), Portugal, and it provides an overview of the connection between IEM knowledge areas and the competences defined in its curriculum. The framework of competences was developed through a process of analysis using a combination of methods and sources for data collection. The framework was developed according to four main steps: 1) characterization of IEM knowledge areas; 2) definition of IEM competences; 3) survey; 4) application of the framework at the IEM curriculum. The findings showed that the framework is useful to build an integrated vision of the curriculum. The most visible aspect in the learning outcomes of IEM program is the lack of balance between technical and transversal competences. There was not almost any reference to the transversal competences and it is fundamentally concentrated on Project-Based Learning courses. The framework presented in this paper provides a contribution to the definition of IEM professional profile through a set of competences which need to be explored further. In addition, it may be a relevant tool for IEM curriculum analysis and a contribution for bridging the gap between universities and companies.

Predicting preterm birth in maternity care by means of data mining

Worldwide, around 9% of the children are born with less than 37 weeks of labour, causing risk to the premature child, whom it is not prepared to develop a number of basic functions that begin soon after the birth. In order to ensure that those risk pregnancies are being properly monitored by the obstetricians in time to avoid those problems, Data Mining (DM) models were induced in this study to predict preterm births in a real environment using data from 3376 patients (women) admitted in the maternal and perinatal care unit of Centro Hospitalar of Oporto. A sensitive metric to predict preterm deliveries was developed, assisting physicians in the decision-making process regarding the patients’ observation. It was possible to obtain promising results, achieving sensitivity and specificity values of 96% and 98%, respectively.

Clustering barotrauma patients in ICU–A data mining based approach using ventilator variables

Lecture Notes in Computer Science, 9273

Predicting type of delivery by identification of obstetric risk factors through data mining

In Maternity Care, a quick decision has to be made about the most suitable delivery type for the current patient. Guidelines are followed by physicians to support that decision; however, those practice recommendations are limited and underused. In the last years, caesarean delivery has been pursued in over 28% of pregnancies, and other operative techniques regarding specific problems have also been excessively employed. This study identifies obstetric and pregnancy factors that can be used to predict the most appropriate delivery technique, through the induction of data mining models using real data gathered in the perinatal and maternal care unit of Centro Hospitalar of Oporto (CHP). Predicting the type of birth envisions high-quality services, increased safety and effectiveness of specific practices to help guide maternity care decisions and facilitate optimal outcomes in mother and child. In this work was possible to acquire good results, achieving sensitivity and specificity values of 90.11% and 80.05%, respectively, providing the CHP with a model capable of correctly identify caesarean sections and vaginal deliveries.

Engineering of fatty acid production and secretion in Saccharomyces cerevisiae

Tese de Doutoramento em Ciências - Especialidade em Biologia