Performance assessment of electrically small antennas for implantable microsystems with wireless power and communications

Dissertação de mestrado integrado em Engenharia Biomédica (área de especialização em Eletrónica Médica)

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.

Towards effective control of P2P traffic aggregates in network infrastructures

Nowadays, many P2P applications proliferate in the Internet. The attractiveness of many of these systems relies on the collaborative approach used to exchange large resources without the dependence and associated constraints of centralized approaches where a single server is responsible to handle all the requests from the clients. As consequence, some P2P systems are also interesting and cost-effective approaches to be adopted by content-providers and other Internet players. However, there are several coexistence problems between P2P applications and In- ternet Service Providers (ISPs) due to the unforeseeable behavior of P2P traffic aggregates in ISP infrastructures. In this context, this work proposes a collaborative P2P/ISP system able to underpin the development of novel Traffic Engi- neering (TE) mechanisms contributing for a better coexistence between P2P applications and ISPs. Using the devised system, two TE methods are described being able to estimate and control the impact of P2P traffic aggregates on the ISP network links. One of the TE methods allows that ISP administrators are able to foresee the expected impact that a given P2P swarm will have in the underlying network infrastructure. The other TE method enables the definition of ISP friendly P2P topologies, where specific network links are protected from P2P traffic. As result, the proposed system and associated mechanisms will contribute for improved ISP resource management tasks and to foster the deployment of innovative ISP-friendly systems.

Automated network resilience optimization using computational intelligence methods

This paper presents an automated optimization framework able to provide network administrators with resilient routing configurations for link-state protocols, such as OSPF or IS-IS. In order to deal with the formulated NP-hard optimization problems, the devised framework is underpinned by the use of computational in- telligence optimization engines, such as Multi-objective Evolutionary Algorithms (MOEAs). With the objective of demonstrating the framework capabilities, two il- lustrative Traffic Engineering methods are described, allowing to attain routing con- figurations robust to changes in the traffic demands and maintaining the network stable even in the presence of link failure events. The presented illustrative results clearly corroborate the usefulness of the proposed automated framework along with the devised optimization methods.

Modeling microbes: New methods for integrated metabolic and regulatory network reconstruction

PhD Thesis in Bioengineering

Abstract computation in schizophrenia detection through artificial neural network based systems

Schizophrenia stands for a long-lasting state of mental uncertainty that may bring to an end the relation among behavior, thought, and emotion; that is, it may lead to unreliable perception, not suitable actions and feelings, and a sense of mental fragmentation. Indeed, its diagnosis is done over a large period of time; continuos signs of the disturbance persist for at least 6 (six) months. Once detected, the psychiatrist diagnosis is made through the clinical interview and a series of psychic tests, addressed mainly to avoid the diagnosis of other mental states or diseases. Undeniably, the main problem with identifying schizophrenia is the difficulty to distinguish its symptoms from those associated to different untidiness or roles. Therefore, this work will focus on the development of a diagnostic support system, in terms of its knowledge representation and reasoning procedures, based on a blended of Logic Programming and Artificial Neural Networks approaches to computing, taking advantage of a novel approach to knowledge representation and reasoning, which aims to solve the problems associated in the handling (i.e., to stand for and reason) of defective information.

Thrombophilia screening: An artificial neural network approach

Thrombotic disorders have severe consequences for the patients and for the society in general, being one of the main causes of death. These facts reveal that it is extremely important to be preventive; being aware of how probable is to have that kind of syndrome. Indeed, this work will focus on the development of a decision support system that will cater for an individual risk evaluation with respect to the surge of thrombotic complaints. The Knowledge Representation and Reasoning procedures used will be based on an extension to the Logic Programming language, allowing the handling of incomplete and/or default data. The computational framework in place will be centered on Artificial Neural Networks.

Search for vector-like B quarks in events with one isolated lepton, missing transverse momentum and jets at s√= 8 TeV with the ATLAS detector

A search has been performed for pair production of heavy vector-like down-type (B) quarks. The analysis explores the lepton-plus-jets final state, characterized by events with one isolated charged lepton (electron or muon), significant missing transverse momentum and multiple jets. One or more jets are required to be tagged as arising from b-quarks, and at least one pair of jets must be tagged as arising from the hadronic decay of an electroweak boson. The analysis uses the full data sample of pp collisions recorded in 2012 by the ATLAS detector at the LHC, operating at a center-of-mass energy of 8 TeV, corresponding to an integrated luminosity of 20.3 fb−1. No significant excess of events is observed above the expected background. Limits are set on vector-like B production, as a function of the B branching ratios, assuming the allowable decay modes are B→Wt/Zb/Hb. In the chiral limit with a branching ratio of 100% for the decay B→Wt, the observed (expected) 95% CL lower limit on the vector-like B mass is 810 GeV (760 GeV). In the case where the vector-like B quark has branching ratio values corresponding to those of an SU(2) singlet state, the observed (expected) 95% CL lower limit on the vector-like B mass is 640 GeV (505 GeV). The same analysis, when used to investigate pair production of a colored, charge 5/3 exotic fermion T5/3, with subsequent decay T5/3→Wt, sets an observed (expected) 95% CL lower limit on the T5/3 mass of 840 GeV (780 GeV).

Search for a Charged Higgs Boson Produced in the Vector-boson Fusion Mode with Decay H±→W±Z using pp Collisions at s√=8 TeV with the ATLAS Experiment

A search for a charged Higgs boson, H±, decaying to a W± boson and a Z boson is presented. The search is based on 20.3 fb−1 of proton-proton collision data at a center-of-mass energy of 8 TeV recorded with the ATLAS detector at the LHC. The H± boson is assumed to be produced via vector-boson fusion and the decays W±→qq′¯ and Z→e+e−/μ+μ− are considered. The search is performed in a range of charged Higgs boson masses from 200 to 1000 GeV. No evidence for the production of an H± boson is observed. Upper limits of 31--1020 fb at 95% CL are placed on the cross section for vector-boson fusion production of an H± boson times its branching fraction to W±Z. The limits are compared with predictions from the Georgi-Machacek Higgs Triplet Model.

Search for production of vector-like quark pairs and of four top quarks in the lepton-plus-jets final state in pp collisions at root 8=8 TeV with the ATLAS detector

A search for pair production of vector-like quarks, both up-type (T) and down-type (B), as well as for four-top-quark production, is presented. The search is based on pp collisions at s√=8 TeV recorded in 2012 with the ATLAS detector at the CERN Large Hadron Collider and corresponding to an integrated luminosity of 20.3 fb−1. Data are analysed in the lepton-plus-jets final state, characterised by an isolated electron or muon with high transverse momentum, large missing transverse momentum and multiple jets. Dedicated analyses are performed targeting three cases: a T quark with significant branching ratio to a W boson and a b-quark (TT¯→Wb+X), and both a T quark and a B quark with significant branching ratio to a Higgs boson and a third-generation quark (TT¯→Ht+X and BB¯→Hb+X respectively). No significant excess of events above the Standard Model expectation is observed, and 95% CL lower limits are derived on the masses of the vector-like T and B quarks under several branching ratio hypotheses assuming contributions from T→Wb, Zt, Ht and B→Wt, Zb, Hb decays. The 95% CL observed lower limits on the T quark mass range between 715 GeV and 950 GeV for all possible values of the branching ratios into the three decay modes, and are the most stringent constraints to date. Additionally, the most restrictive upper bounds on four-top-quark production are set in a number of new physics scenarios.

MOEA/VAN: Multiobjective Evolutionary Algorithm based on Vector Angle Neighborhood

Natural selection favors the survival and reproduction of organisms that are best adapted to their environment. Selection mechanism in evolutionary algorithms mimics this process, aiming to create environmental conditions in which artificial organisms could evolve solving the problem at hand. This paper proposes a new selection scheme for evolutionary multiobjective optimization. The similarity measure that defines the concept of the neighborhood is a key feature of the proposed selection. Contrary to commonly used approaches, usually defined on the basis of distances between either individuals or weight vectors, it is suggested to consider the similarity and neighborhood based on the angle between individuals in the objective space. The smaller the angle, the more similar individuals. This notion is exploited during the mating and environmental selections. The convergence is ensured by minimizing distances from individuals to a reference point, whereas the diversity is preserved by maximizing angles between neighboring individuals. Experimental results reveal a highly competitive performance and useful characteristics of the proposed selection. Its strong diversity preserving ability allows to produce a significantly better performance on some problems when compared with stat-of-the-art algorithms.

Differential activation of the default mode network in jet lagged individuals

Long-term exposure to transmeridian flights has been shown to impact cognitive functioning. Nevertheless, the immediate effects of jet lag in the activation of specific brain networks have not been investigated. We analyzed the impact of short-term jet lag on the activation of the default mode network (DMN). A group of individuals who were on a transmeridian flight and a control group went through a functional magnetic resonance imaging acquisition. Statistical analysis was performed to test for differences in the DMN activation between groups. Participants from the jet lag group presented decreased activation in the anterior nodes of the DMN, specifically in bilateral medial prefrontal and anterior cingulate cortex. No areas of increased activation were observed for the jet lag group. These results may be suggestive of a negative impact of jet lag on important cognitive functions such as introspection, emotional regulation and decision making in a few days after individuals arrive at their destination.

A network approach to brain aging through multimodal neuroimaging

Tese de Doutoramento em Ciências da Saúde.

Evolution of the gene regulatory network controlling flower dorsoventral asymmetry

Tese de Doutoramento em Biologia de Plantas.

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

Dissertação de mestrado integrado em Engenharia Civil