End-to-end versus hop-by-hop state refresh in soft state signaling protocols

The concept of soft state (i.e., the state that will expire unless been refreshed) has been widely used in the design of network signaling protocols. The approaches of refreshing state in multi-hop networks can be classified to end-to-end (E2E) and hop-by-hop (HbH) refreshes. In this article we propose an effective Markov chain based analytical model for both E2E and HbH refresh approaches. Simulations verify the analytical models, which can be used to study the impacts of link characteristics on the performance (e.g., state synchronization and message overhead), as a guide on configuration and optimization of soft state signaling protocols. © 2009 IEEE.

Resource allocation in multi-user telecommunication networks

This dissertation discussed resource allocation mechanisms in several network topologies including infrastructure wireless network, non-infrastructure wireless network and wire-cum-wireless network. Different networks may have different resource constrains. Based on actual technologies and implementation models, utility function, game theory and a modern control algorithm have been introduced to balance power, bandwidth and customers' satisfaction in the system. ^ In infrastructure wireless networks, utility function was used in the Third Generation (3G) cellular network and the network was trying to maximize the total utility. In this dissertation, revenue maximization was set as an objective. Compared with the previous work on utility maximization, it is more practical to implement revenue maximization by the cellular network operators. The pricing strategies were studied and the algorithms were given to find the optimal price combination of power and rate to maximize the profit without degrading the Quality of Service (QoS) performance. ^ In non-infrastructure wireless networks, power capacity is limited by the small size of the nodes. In such a network, nodes need to transmit traffic not only for themselves but also for their neighbors, so power management become the most important issue for the network overall performance. Our innovative routing algorithm based on utility function, sets up a flexible framework for different users with different concerns in the same network. This algorithm allows users to make trade offs between multiple resource parameters. Its flexibility makes it a suitable solution for the large scale non-infrastructure network. This dissertation also covers non-cooperation problems. Through combining game theory and utility function, equilibrium points could be found among rational users which can enhance the cooperation in the network. ^ Finally, a wire-cum-wireless network architecture was introduced. This network architecture can support multiple services over multiple networks with smart resource allocation methods. Although a SONET-to-WiMAX case was used for the analysis, the mathematic procedure and resource allocation scheme could be universal solutions for all infrastructure, non-infrastructure and combined networks. ^

Routing and dimensioning of 3G multi-service networks

Mémoire numérisé par la Direction des bibliothèques de l'Université de Montréal.

Radiotherapy Treatment Assessment using DCE-MRI

Abstract

The goal of modern radiotherapy is to precisely deliver a prescribed radiation dose to delineated target volumes that contain a significant amount of tumor cells while sparing the surrounding healthy tissues/organs. Precise delineation of treatment and avoidance volumes is the key for the precision radiation therapy. In recent years, considerable clinical and research efforts have been devoted to integrate MRI into radiotherapy workflow motivated by the superior soft tissue contrast and functional imaging possibility. Dynamic contrast-enhanced MRI (DCE-MRI) is a noninvasive technique that measures properties of tissue microvasculature. Its sensitivity to radiation-induced vascular pharmacokinetic (PK) changes has been preliminary demonstrated. In spite of its great potential, two major challenges have limited DCE-MRI’s clinical application in radiotherapy assessment: the technical limitations of accurate DCE-MRI imaging implementation and the need of novel DCE-MRI data analysis methods for richer functional heterogeneity information.

This study aims at improving current DCE-MRI techniques and developing new DCE-MRI analysis methods for particular radiotherapy assessment. Thus, the study is naturally divided into two parts. The first part focuses on DCE-MRI temporal resolution as one of the key DCE-MRI technical factors, and some improvements regarding DCE-MRI temporal resolution are proposed; the second part explores the potential value of image heterogeneity analysis and multiple PK model combination for therapeutic response assessment, and several novel DCE-MRI data analysis methods are developed.

I. Improvement of DCE-MRI temporal resolution. First, the feasibility of improving DCE-MRI temporal resolution via image undersampling was studied. Specifically, a novel MR image iterative reconstruction algorithm was studied for DCE-MRI reconstruction. This algorithm was built on the recently developed compress sensing (CS) theory. By utilizing a limited k-space acquisition with shorter imaging time, images can be reconstructed in an iterative fashion under the regularization of a newly proposed total generalized variation (TGV) penalty term. In the retrospective study of brain radiosurgery patient DCE-MRI scans under IRB-approval, the clinically obtained image data was selected as reference data, and the simulated accelerated k-space acquisition was generated via undersampling the reference image full k-space with designed sampling grids. Two undersampling strategies were proposed: 1) a radial multi-ray grid with a special angular distribution was adopted to sample each slice of the full k-space; 2) a Cartesian random sampling grid series with spatiotemporal constraints from adjacent frames was adopted to sample the dynamic k-space series at a slice location. Two sets of PK parameters’ maps were generated from the undersampled data and from the fully-sampled data, respectively. Multiple quantitative measurements and statistical studies were performed to evaluate the accuracy of PK maps generated from the undersampled data in reference to the PK maps generated from the fully-sampled data. Results showed that at a simulated acceleration factor of four, PK maps could be faithfully calculated from the DCE images that were reconstructed using undersampled data, and no statistically significant differences were found between the regional PK mean values from undersampled and fully-sampled data sets. DCE-MRI acceleration using the investigated image reconstruction method has been suggested as feasible and promising.

Second, for high temporal resolution DCE-MRI, a new PK model fitting method was developed to solve PK parameters for better calculation accuracy and efficiency. This method is based on a derivative-based deformation of the commonly used Tofts PK model, which is presented as an integrative expression. This method also includes an advanced Kolmogorov-Zurbenko (KZ) filter to remove the potential noise effect in data and solve the PK parameter as a linear problem in matrix format. In the computer simulation study, PK parameters representing typical intracranial values were selected as references to simulated DCE-MRI data for different temporal resolution and different data noise level. Results showed that at both high temporal resolutions (<1s) and clinically feasible temporal resolution (~5s), this new method was able to calculate PK parameters more accurate than the current calculation methods at clinically relevant noise levels; at high temporal resolutions, the calculation efficiency of this new method was superior to current methods in an order of 102. In a retrospective of clinical brain DCE-MRI scans, the PK maps derived from the proposed method were comparable with the results from current methods. Based on these results, it can be concluded that this new method can be used for accurate and efficient PK model fitting for high temporal resolution DCE-MRI.

II. Development of DCE-MRI analysis methods for therapeutic response assessment. This part aims at methodology developments in two approaches. The first one is to develop model-free analysis method for DCE-MRI functional heterogeneity evaluation. This approach is inspired by the rationale that radiotherapy-induced functional change could be heterogeneous across the treatment area. The first effort was spent on a translational investigation of classic fractal dimension theory for DCE-MRI therapeutic response assessment. In a small-animal anti-angiogenesis drug therapy experiment, the randomly assigned treatment/control groups received multiple fraction treatments with one pre-treatment and multiple post-treatment high spatiotemporal DCE-MRI scans. In the post-treatment scan two weeks after the start, the investigated Rényi dimensions of the classic PK rate constant map demonstrated significant differences between the treatment and the control groups; when Rényi dimensions were adopted for treatment/control group classification, the achieved accuracy was higher than the accuracy from using conventional PK parameter statistics. Following this pilot work, two novel texture analysis methods were proposed. First, a new technique called Gray Level Local Power Matrix (GLLPM) was developed. It intends to solve the lack of temporal information and poor calculation efficiency of the commonly used Gray Level Co-Occurrence Matrix (GLCOM) techniques. In the same small animal experiment, the dynamic curves of Haralick texture features derived from the GLLPM had an overall better performance than the corresponding curves derived from current GLCOM techniques in treatment/control separation and classification. The second developed method is dynamic Fractal Signature Dissimilarity (FSD) analysis. Inspired by the classic fractal dimension theory, this method measures the dynamics of tumor heterogeneity during the contrast agent uptake in a quantitative fashion on DCE images. In the small animal experiment mentioned before, the selected parameters from dynamic FSD analysis showed significant differences between treatment/control groups as early as after 1 treatment fraction; in contrast, metrics from conventional PK analysis showed significant differences only after 3 treatment fractions. When using dynamic FSD parameters, the treatment/control group classification after 1st treatment fraction was improved than using conventional PK statistics. These results suggest the promising application of this novel method for capturing early therapeutic response.

The second approach of developing novel DCE-MRI methods is to combine PK information from multiple PK models. Currently, the classic Tofts model or its alternative version has been widely adopted for DCE-MRI analysis as a gold-standard approach for therapeutic response assessment. Previously, a shutter-speed (SS) model was proposed to incorporate transcytolemmal water exchange effect into contrast agent concentration quantification. In spite of richer biological assumption, its application in therapeutic response assessment is limited. It might be intriguing to combine the information from the SS model and from the classic Tofts model to explore potential new biological information for treatment assessment. The feasibility of this idea was investigated in the same small animal experiment. The SS model was compared against the Tofts model for therapeutic response assessment using PK parameter regional mean value comparison. Based on the modeled transcytolemmal water exchange rate, a biological subvolume was proposed and was automatically identified using histogram analysis. Within the biological subvolume, the PK rate constant derived from the SS model were proved to be superior to the one from Tofts model in treatment/control separation and classification. Furthermore, novel biomarkers were designed to integrate PK rate constants from these two models. When being evaluated in the biological subvolume, this biomarker was able to reflect significant treatment/control difference in both post-treatment evaluation. These results confirm the potential value of SS model as well as its combination with Tofts model for therapeutic response assessment.

In summary, this study addressed two problems of DCE-MRI application in radiotherapy assessment. In the first part, a method of accelerating DCE-MRI acquisition for better temporal resolution was investigated, and a novel PK model fitting algorithm was proposed for high temporal resolution DCE-MRI. In the second part, two model-free texture analysis methods and a multiple-model analysis method were developed for DCE-MRI therapeutic response assessment. The presented works could benefit the future DCE-MRI routine clinical application in radiotherapy assessment.

Routing and dimensioning of 3G multi-service networks

Mémoire numérisé par la Direction des bibliothèques de l'Université de Montréal.

FPGA-based soft-core processors for image processing applications

With security and surveillance, there is an increasing need to process image data efficiently and effectively either at source or in a large data network. Whilst a Field-Programmable Gate Array (FPGA) has been seen as a key technology for enabling this, the design process has been viewed as problematic in terms of the time and effort needed for implementation and verification. The work here proposes a different approach of using optimized FPGA-based soft-core processors which allows the user to exploit the task and data level parallelism to achieve the quality of dedicated FPGA implementations whilst reducing design time. The paper also reports some preliminary
progress on the design flow to program the structure. An implementation for a Histogram of Gradients algorithm is also reported which shows that a performance of 328 fps can be achieved with this design approach, whilst avoiding the long design time, verification and debugging steps associated with conventional FPGA implementations.

Multi-Disciplinary Applications of Oceanographic Geophysical Data Collection

Thesis (Ph.D.)--University of Washington, 2016-08

Soft tissue sarcoma: biology and therapeutic correlates

Soft tissue sarcomas (STS) comprise a heterogenenous group of greater than 50 malignancies of putative mesenchymal cell origin and as such they may arise in diverse tissue types in various anatomical locations throughout the whole body. Collectively they account for approximately 1% of all human malignancies yet have a spectrum of aggressive behaviours amongst their subtypes. They thus pose a particular challenge to manage and remain an under investigated group of cancers with no generally applicable new therapies in the past 40 years and an overall 5-year survival rate that remains stagnant at around 50%. From September 2000 to July 2006 I undertook a full time post-doctoral level research fellowship at the MD Anderson Cancer Center, Houston, Texas, USA in the department of Surgical Oncology to investigate the biology of soft tissue sarcoma and test novel anti- sarcoma adenovirus-based therapy in the preclinical nude rat model of isolated limb perfusion against human sarcoma xenografts. This work, in collaboration with colleagues as indicated herein, led to a number of publications in the scientific literature furthering our understanding of the malignant phenotype of sarcoma and reported preclinical studies with wild-type p53, in a replication deficient adenovirus vector, and oncolytic adenoviruses administered by isolated limb perfusion. Additional collaborative and pioneering preclinical studies reported the molecular imaging of sarcoma response to systemically delivered therapeutic phage RGD-4c AAVP. Doxorubicin chemotherapy is the single most active broadly applicable anti-sarcoma chemotherapeutic yet only has an approximate 30% overall response rate with additional breakthrough tumour progression and recurrence after initial chemo-responsiveness further problematic features in STS management. Doxorubicin is a substrate for the multi- drug resistance (mdr) gene product p-glycoprotein drug efflux pump and exerts its main mode of action by induction of DNA double-strand breaks during the S-phase of the cell cycle. Two papers in my thesis characterise different aspects of chemoresistance in sarcoma. The first shows that wild-type p53 suppresses Protein Kinase Calpha (PKCα) phosphorylation (and activation) of p-glycoprotein by transcriptional repression of PKCα through a Sp-1 transcription factor binding site in its -244/-234 promoter region. The second paper demonstrates that Rad51 (a central mediator of homologous recombination repair of double strand breaks) has elevated levels in sarcoma and particularly in the S- G2 phase of the cell cycle. Suppression of Rad51 with small interfering RNA in sarcoma cell culture led to doxorubicin chemosensitisation. Reintroduction of wild-type p53 into STS cell lines resulted in decreased Rad51 protein and mRNA expression via transcriptional repression of the Rad51 promoter through increased AP-2 binding. In light of poor response rates to chemotherapy, escape from local control portends a poor prognosis for patients with sarcoma. Two papers in my thesis characterise aspects of sarcoma angiogenesis, invasion and metastasis. Human sarcoma samples were found to have high levels of matrix metalloproteinase-9 (MMP-9) with expression levels that correlated with p53 mutational status. MMP-9 is known to degrade extracellular collagen, contribute to the control of the angiogenic switch necessary in primary tumour progression and facilitate invasion and metastasis. Reconstitution of wild-type p53 function led to decreased levels of MMP-9 protein and mRNA as well as zymography-assessed MMP-9 proteolytic activity and decreased tumour cell invasiveness. Reintroduction of wild-type p53 into human sarcoma xenografts in-vivo decreased tumour growth and MMP-9 protein expression. Wild-type p53 was found to suppress mmp-9 transcription via decreased binding of NF-κB to its -607/-595 mmp-9 promoter element. Studies on the role of the VEGF165 in sarcoma found that sarcoma cells stably transfected with VEGF165 formed more aggressive xenografted tumours with increased vascularity, growth rate, metastasis, and resistance to chemotherapy. Use of the anti-VEGFR2 antibody DC101 enhanced doxorubicin sensitivity at sub-conventional dosing, inhibited tumour growth, decreased development of metastases, and reduced tumour micro-vessel density while increasing the vessel maturation index. These effects were explained primarily through effects on endothelial cells (e.c.s), rather than the tumour cells per se, where DC101 induced e.c. sensitivity to doxorubicin and suppressed e.c. production of MMPs. The p53 tumour suppressor pathway is the most frequently mutated pathway in sarcoma. Recapitulation of wild-type p53 function in sarcoma exerts a number of anti-cancer outcomes such as growth arrest, resensitisation to chemotherapy, suppression of invasion, and attenuation of angiogenesis. Using a modified nude rat-human sarcoma xenograft model for isolated limb perfusion (ILP) delivery of wild-type p53 in a replication deficient adenovirus vector I showed that functionally competent wild-type p53 could be delivered to and detected in human leiomyosarcoma xenografts confirming preclinical feasibility - although not efficacious due to low transgene expression. Viral fibre modification to express the RGD tripeptide motif led to greater viral uptake by sarcoma cells in vitro (transductional targeting) and changing the transgene promoter to a response element active in cells with active telomerase expression restricted the transgene expression to the tumour intracellular environment (transcriptional targeting). Delivery of the fibre-modified, selectively replication proficient oncolytic adenovirus Ad.hTC.GFP/ E1a.RGD by ILP demonstrated a more robust, and tumour-restricted, transgene expression with evidence of anti-sarcoma effect confirmed microscopically. Collaborative studies using the fibre modified phage RGD-4C AAVP confirmed that systemic delivery specifically, efficiently, and repeatedly targets human sarcoma xenografts, binds to αv integrins in tumours, and demonstrates a durable, though heterogeneous, transgene expression of 1-4 weeks. Incorporation of the Herpes Simplex Virus thymidine kinase (HSVtk) transgene into RGD-4C AAVP permitted CT-PET spatial and temporal molecular imaging in vivo of transgene expression and allowed quantification of tumour metabolic activity both before and after interval administration of a systemic cytotoxic with predictable and measurable response to treatment before becoming apparent clinically. These papers further the medical and scientific community’s understanding of the biology of soft tissue sarcoma and report preclinical studies with novel and promising anti- sarcoma therapeutics.

MLCut: exploring multi-level cuts in dendrograms for biological data.

Choosing a single similarity threshold for cutting dendrograms is not sufficient for performing hierarchical clustering analysis of heterogeneous data sets. In addition, alternative automated or semi-automated methods that cut dendrograms in multiple levels make assumptions about the data in hand. In an attempt to help the user to find patterns in the data and resolve ambiguities in cluster assignments, we developed MLCut: a tool that provides visual support for exploring dendrograms of heterogeneous data sets in different levels of detail. The interactive exploration of the dendrogram is coordinated with a representation of the original data, shown as parallel coordinates. The tool supports three analysis steps. Firstly, a single-height similarity threshold can be applied using a dynamic slider to identify the main clusters. Secondly, a distinctiveness threshold can be applied using a second dynamic slider to identify “weak-edges” that indicate heterogeneity within clusters. Thirdly, the user can drill-down to further explore the dendrogram structure - always in relation to the original data - and cut the branches of the tree at multiple levels. Interactive drill-down is supported using mouse events such as hovering, pointing and clicking on elements of the dendrogram. Two prototypes of this tool have been developed in collaboration with a group of biologists for analysing their own data sets. We found that enabling the users to cut the tree at multiple levels, while viewing the effect in the original data, is a promising method for clustering which could lead to scientific discoveries.

Soft computing based parameter identification in pavements and geomechanical systems

Accurate estimation of road pavement geometry and layer material properties through the use of proper nondestructive testing and sensor technologies is essential for evaluating pavement’s structural condition and determining options for maintenance and rehabilitation. For these purposes, pavement deflection basins produced by the nondestructive Falling Weight Deflectometer (FWD) test data are commonly used. The nondestructive FWD test drops weights on the pavement to simulate traffic loads and measures the created pavement deflection basins. Backcalculation of pavement geometry and layer properties using FWD deflections is a difficult inverse problem, and the solution with conventional mathematical methods is often challenging due to the ill-posed nature of the problem. In this dissertation, a hybrid algorithm was developed to seek robust and fast solutions to this inverse problem. The algorithm is based on soft computing techniques, mainly Artificial Neural Networks (ANNs) and Genetic Algorithms (GAs) as well as the use of numerical analysis techniques to properly simulate the geomechanical system. A widely used pavement layered analysis program ILLI-PAVE was employed in the analyses of flexible pavements of various pavement types; including full-depth asphalt and conventional flexible pavements, were built on either lime stabilized soils or untreated subgrade. Nonlinear properties of the subgrade soil and the base course aggregate as transportation geomaterials were also considered. A computer program, Soft Computing Based System Identifier or SOFTSYS, was developed. In SOFTSYS, ANNs were used as surrogate models to provide faster solutions of the nonlinear finite element program ILLI-PAVE. The deflections obtained from FWD tests in the field were matched with the predictions obtained from the numerical simulations to develop SOFTSYS models. The solution to the inverse problem for multi-layered pavements is computationally hard to achieve and is often not feasible due to field variability and quality of the collected data. The primary difficulty in the analysis arises from the substantial increase in the degree of non-uniqueness of the mapping from the pavement layer parameters to the FWD deflections. The insensitivity of some layer properties lowered SOFTSYS model performances. Still, SOFTSYS models were shown to work effectively with the synthetic data obtained from ILLI-PAVE finite element solutions. In general, SOFTSYS solutions very closely matched the ILLI-PAVE mechanistic pavement analysis results. For SOFTSYS validation, field collected FWD data were successfully used to predict pavement layer thicknesses and layer moduli of in-service flexible pavements. Some of the very promising SOFTSYS results indicated average absolute errors on the order of 2%, 7%, and 4% for the Hot Mix Asphalt (HMA) thickness estimation of full-depth asphalt pavements, full-depth pavements on lime stabilized soils and conventional flexible pavements, respectively. The field validations of SOFTSYS data also produced meaningful results. The thickness data obtained from Ground Penetrating Radar testing matched reasonably well with predictions from SOFTSYS models. The differences observed in the HMA and lime stabilized soil layer thicknesses observed were attributed to deflection data variability from FWD tests. The backcalculated asphalt concrete layer thickness results matched better in the case of full-depth asphalt flexible pavements built on lime stabilized soils compared to conventional flexible pavements. Overall, SOFTSYS was capable of producing reliable thickness estimates despite the variability of field constructed asphalt layer thicknesses.

Defining efficient policies in a general equilibrium model: a multi-objective approach

Macroeconomic policy makers are typically concerned with several indicators of economic performance. We thus propose to tackle the design of macroeconomic policy using Multicriteria Decision Making (MCDM) techniques. More specifically, we employ Multiobjective Programming (MP) to seek so-called efficient policies. The MP approach is combined with a computable general equilibrium (CGE) model. We chose use of a CGE model since they have the dual advantage of being consistent with standard economic theory while allowing one to measure the effect(s) of a specific policy with real data. Applying the proposed methodology to Spain (via the 1995 Social Accounting Matrix) we first quantified the trade-offs between two specific policy objectives: growth and inflation, when designing fiscal policy. We then constructed a frontier of efficient policies involving real growth and inflation. In doing so, we found that policy in 1995 Spain displayed some degree of inefficiency with respect to these two policy objectives. We then offer two sets of policy recommendations that, ostensibly, could have helped Spain at the time. The first deals with efficiency independent of the importance given to both growth and inflation by policy makers (we label this set: general policy recommendations). A second set depends on which policy objective is seen as more important by policy makers: increasing growth or controlling inflation (we label this one: objective-specific recommendations).

In vitro and in vivo delivery of the secretagogue diadenosine tetraphosphate from conventional and silicone hydrogel soft contact lenses

Purpose To evaluate the possible use of soft contact lenses (CL) to improve the secretagogue role of diadenosine tetraphosphate (Ap4A) promoting tear secretion. Methods Two conventional hydrogel CL (Omafilcon A and Ocufilcon D) and two silicone hydrogel (SiH) CL (Comfilcon A and Balafilcon A) were used. Ap4A was loaded into the lenses by soaking in a 1 mM Ap4A solution during 12 h. In vitro experiments were performed by placing the lenses in multi-wells during 2 h containing 1 ml of ultrapure water. 100 μl aliquots were taken at time zero and every minute for the first 10 min, and then every 15 min. In vivo experiments were performed in New Zealand rabbits and both the dinucleotide release from SiH and tear secretion were measured by means of Schirmer strips and high-pressure liquid chromatography (HPLC) analysis. Results Ap4A in vitro release experiments in hydrogel CL presented a release time 50 (RT50) of 3.9 ± 0.2 min and 3.1 ± 0.1 min for the non-ionic and the ionic CL, respectively. SiH CL released also Ap4A with RT50 values of 5.1 ± 0.1 min for the non-ionic and 2.7 ± 0.1 min for the ionic CL. In vivo experiments with SiH CL showed RT50 values of 9.3 ± 0.2 min and 8.5 ± 0.2 min for the non-ionic and the ionic respectively. The non-ionic lens Ap4A release was able to induce tear secretion above baseline tear levels for almost 360 min. Conclusion The delivery of Ap4A is slower and the effect lasts longer with non-ionic lenses than ionic lenses.

A survey on multi-output regression

In recent years, a plethora of approaches have been proposed to deal with the increasingly challenging task of multi-output regression. This paper provides a survey on state-of-the-art multi-output regression methods, that are categorized as problem transformation and algorithm adaptation methods. In addition, we present the mostly used performance evaluation measures, publicly available data sets for multi-output regression real-world problems, as well as open-source software frameworks.

An investigation of imputation methods for discrete databases and multi-variate time series

When it comes to information sets in real life, often pieces of the whole set may not be available. This problem can find its origin in various reasons, describing therefore different patterns. In the literature, this problem is known as Missing Data. This issue can be fixed in various ways, from not taking into consideration incomplete observations, to guessing what those values originally were, or just ignoring the fact that some values are missing. The methods used to estimate missing data are called Imputation Methods. The work presented in this thesis has two main goals. The first one is to determine whether any kind of interactions exists between Missing Data, Imputation Methods and Supervised Classification algorithms, when they are applied together. For this first problem we consider a scenario in which the databases used are discrete, understanding discrete as that it is assumed that there is no relation between observations. These datasets underwent processes involving different combina- tions of the three components mentioned. The outcome showed that the missing data pattern strongly influences the outcome produced by a classifier. Also, in some of the cases, the complex imputation techniques investigated in the thesis were able to obtain better results than simple ones. The second goal of this work is to propose a new imputation strategy, but this time we constrain the specifications of the previous problem to a special kind of datasets, the multivariate Time Series. We designed new imputation techniques for this particular domain, and combined them with some of the contrasted strategies tested in the pre- vious chapter of this thesis. The time series also were subjected to processes involving missing data and imputation to finally propose an overall better imputation method. In the final chapter of this work, a real-world example is presented, describing a wa- ter quality prediction problem. The databases that characterized this problem had their own original latent values, which provides a real-world benchmark to test the algorithms developed in this thesis.

A Soft Computing Approach to Acute Coronary Syndrome

Acute Coronary Syndrome (ACS) is transversal to a broad and heterogeneous set of human beings, and assumed as a serious diagnosis and risk stratification problem. Although one may be faced with or had at his disposition different tools as biomarkers for the diagnosis and prognosis of ACS, they have to be previously evaluated and validated in different scenarios and patient cohorts. Besides ensuring that a diagnosis is correct, attention should also be directed to ensure that therapies are either correctly or safely applied. Indeed, this work will focus on the development of a diagnosis decision support system in terms of its knowledge representation and reasoning mechanisms, given here in terms of a formal framework based on Logic Programming, complemented with a problem solving methodology to computing anchored on Artificial Neural Networks. On the one hand it caters for the evaluation of ACS predisposing risk and the respective Degree-of-Confidence that one has on such a happening. On the other hand it may be seen as a major development on the Multi-Value Logics to understand things and ones behavior. Undeniably, the proposed model allows for an improvement of the diagnosis process, classifying properly the patients that presented the pathology (sensitivity ranging from 89.7% to 90.9%) as well as classifying the absence of ACS (specificity ranging from 88.4% to 90.2%).