Standardized evaluation of algorithms for computer-aided diagnosis of dementia based on structural MRI: The CADDementia challenge

Algorithms for computer-aided diagnosis of dementia based on structural MRI have demonstrated high performance in the literature, but are difficult to compare as different data sets and methodology were used for evaluation. In addition, it is unclear how the algorithms would perform on previously unseen data, and thus, how they would perform in clinical practice when there is no real opportunity to adapt the algorithm to the data at hand. To address these comparability, generalizability and clinical applicability issues, we organized a grand challenge that aimed to objectively compare algorithms based on a clinically representative multi-center data set. Using clinical practice as the starting point, the goal was to reproduce the clinical diagnosis. Therefore, we evaluated algorithms for multi-class classification of three diagnostic groups: patients with probable Alzheimer's disease, patients with mild cognitive impairment and healthy controls. The diagnosis based on clinical criteria was used as reference standard, as it was the best available reference despite its known limitations. For evaluation, a previously unseen test set was used consisting of 354 T1-weighted MRI scans with the diagnoses blinded. Fifteen research teams participated with a total of 29 algorithms. The algorithms were trained on a small training set (n = 30) and optionally on data from other sources (e.g., the Alzheimer's Disease Neuroimaging Initiative, the Australian Imaging Biomarkers and Lifestyle flagship study of aging). The best performing algorithm yielded an accuracy of 63.0% and an area under the receiver-operating-characteristic curve (AUC) of 78.8%. In general, the best performances were achieved using feature extraction based on voxel-based morphometry or a combination of features that included volume, cortical thickness, shape and intensity. The challenge is open for new submissions via the web-based framework: http://caddementia.grand-challenge.org.

Using Multi-Objective Optimization To Maximize Multiple Benefits For Sustainable Drainage Design

For many years, drainage design was mainly about providing sufficient network capacity. This traditional approach had been successful with the aid of computer software and technical guidance. However, the drainage design criteria had been evolving due to rapid population growth, urbanisation, climate change and increasing sustainability awareness. Sustainable drainage systems that bring benefits in addition to water management have been recommended as better alternatives to conventional pipes and storages. Although the concepts and good practice guidance had already been communicated to decision makers and public for years, network capacity still remains a key design focus in many circumstances while the additional benefits are generally considered secondary only. Yet, the picture is changing. The industry begins to realise that delivering multiple benefits should be given the top priority while the drainage service can be considered a secondary benefit instead. The shift in focus means the industry has to adapt to new design challenges. New guidance and computer software are needed to assist decision makers. For this purpose, we developed a new decision support system. The system consists of two main components – a multi-criteria evaluation framework for drainage systems and a multi-objective optimisation tool. Users can systematically quantify the performance, life-cycle costs and benefits of different drainage systems using the evaluation framework. The optimisation tool can assist users to determine combinations of design parameters such as the sizes, order and type of drainage components that maximise multiple benefits. In this paper, we will focus on the optimisation component of the decision support framework. The optimisation problem formation, parameters and general configuration will be discussed. We will also look at the sensitivity of individual variables and the benchmark results obtained using common multi-objective optimisation algorithms. The work described here is the output of an EngD project funded by EPSRC and XP Solutions.

MCDA: análise de decisão multicritério como ferramenta de avaliação de instalações portuárias: o caso dos terminais de contêineres brasileiros

Este trabalho busca avaliar, com suporte da metodologia MCDA - análise de decisão multicritério, os terminais de contêineres brasileiros quanto a suas potencialidades como vetores de crescimento sustentado da economia, no médio e longo prazo, para priorização de investimentos públicos e privados. O trabalho se consubstancia em um levantamento bibliográfico do tema decisório, que lhe serve de base, seguido de um estudo do tema portuário, a fim de levantar os fatores que tornam viável o florescimento e desenvolvimento de um sítio portuário, além de buscar tendências do setor de contêineres no Brasil. Após estas etapas, foi desenvolvido uma modelagem para o problema de avaliação dos terminais, com ajuda do software Expert Choice. Os resultados obtidos apontam para uma alteração sensível de paradigma no panorama portuário nacional em um cenário futuro. Portos que hoje se localizam na parte superior da lista de movimentação de contêineres, à frente nas estatísticas, podem não ter para onde se expandir, enquanto outros, que se encontram menos pujantes, podem florescer nas próximas décadas, devido às características de cada sítio portuário. As mais relevantes foram selecionadas como critérios do modelo desenvolvido, são eles: águas abrigadas, retroáreas, acessos terrestres e marítimos, equacionamento de questões ambientais, localização estratégica, vocação regional, extensão de cais e áreas de expansão. Entre as conclusões deste estudo, pode-se citar: 1 - O Porto de Santos, tradicional líder do ranking nacional em movimentação de contêineres, deve se manter entre os primeiros, graças à sua proximidade com o principal centro econômico e industrial nacional, a região da grande São Paulo, embora esteja com sua capacidade perto do limite operacional, conta com áreas de expansão, como o projeto Barnabé-Bagres. 2 - Outro porto que se destacou na classificação final foi o de Itaguaí, já hoje com movimentação crescente e enorme potencial de crescimento na área de contêineres. Possui excelente condição de águas abrigadas, boa localização estratégica, entre Rio de Janeiro e São Paulo, dois pólos econômicos fortes, com influência decisiva no cenário nacional, e que dispõe de consistente plano de expansão, especialmente relacionado ao aumento de contêineres.

Is what you say what you do? Analyzing and comparing the effect of buyer-supplier relationship in the Brazilian and Chinese supplier selection criteria

Choosing properly and efficiently a supplier has been challenging practitioners and academics since 1960’s. Since then, countless studies had been performed and relevant changes in the business scenario were considered such as global sourcing, quality-orientation, just-in-time practices. It is almost consensus that quality should be the selection driver, however, some polemical findings questioned this general agreement. Therefore, one of the objectives of the study was to identify the supplier selection criteria and bring this discussion back again. Moreover, Dickson (1966) suggested existing business relationship as selection criterion, then it was reviewed the importance of business relationship for the company and noted a set of potential negative effects that could rise from it. By considering these side effects of relationship, this research aimed to investigate how the relationship could influence the supplier selection and how its harmful effects could affect the selection process. The impact of this phenomenon was investigated cross-nationally. The research strategy adopted was a controlled experiment via vignette combined with discrete choice analysis. The data collections were performed in China and Brazil. By examining the results, it could be drawn five major findings. First, when purchasers were asked to declare their supplier selection priorities, quality was stated as the most important independently of country and relationship. This result was consistent with diverse studies since 60’s. However, when purchasers were exposed to a multi-criteria trade-off situation, their actual selection priorities deviate from what they had declared. In the actual decision-making without influence of buyer-supplier relationship, Brazilian purchasers focused on price and Chinese buyers prioritized delivery then price. This observation reinforced some controversial prior studies of Verma & Pullman (1998) and Hirakubo & Kublin (1998). Second, through the introduction of the buyer-supplier relationship (operationalized via relational capital) in the supplier selection process, this research extended the existing studies and found that Brazilian buyers still focused on price. The relationship became just another criterion for supplier selection such as quality and delivery. However, from the Chinese sample, the results suggested that quality was totally discarded and the decision was majorly made through price and relationship. The third finding suggested that relational capital could legitimate the quality and sustainability of the supplier and replaces these selection criteria and made the decisional task less complex. Additionally, with the relational capital, the decision-makings were associated to few biases such as availability cognition, commitment, confirmatory and perceived biases. By analyzing the purchasers’ behavior, relational capital inducted buyers of both countries to relax in their purchasing requirements (quality, delivery and sustainability) leading to potential negative effects. In the Brazilian sample, the phenomenon of willing to pay a higher price for a lower quality offer demonstrated to be a potential counterproductive and suboptimal decision. Finally, the last finding was associated to the cultural effect on the buyers’ decisions. From the outcome, it is possible to observe that if a purchaser’s cultural background is more relation-oriented, the more he will tend to use relational capital as a decision heuristic, thus, the purchaser will be more susceptible to the potential relationship’s side effects

Modelagem da decisão por pacotes de viagem: um estudo usando processo de hierarquia analítica AHP

The objective of this dissertation is to propose a Multi Criteria Decision Aid Model to be used by the costumers of the travel agencies and help them to choose the best package travel. The main objective is to contribute for the simplification of the travel package decision choice from the identification of the models of values and preference of the customers and applying them to the existing package. It is used the Analytic Hierarchy Process (AHP) method to structuralize a decision hierarchic model composed by six criteria (package cost, hotel category, security of the city, travel time, direct flight and position in ranking of the 10 most visited destination) and five real alternatives of packages for a holiday of three days created from travel agency data. The decision analysis was realized for the choice of a travel package by a group composed by two couples that regularly travels together, to which was asked to do a pairwise judgment of the criteria and the alternatives. The mains results show that, although been a group that travels together, there are different models of values in the weights of the criteria and a certain convergence in the scales of preferences of the alternatives in the criteria. It was not pointed a dominant alternative for all the members of the group separately, but an analysis of a total utility of the group shows a classification and an order of the travel packages and an alternative clearly in front of the others. The sensitivity analysis revels that there are changes in the ranking, but the two alternatives best classified in the normal analysis are the same ones in the sensitivity analysis, although with the positions changed. The analysis also led to a simplification of the process with the exclusion of alternatives dominated for the others ones. As main conclusion, it is evaluated that the model and method suggested allow a simplification of the decision process in the choice of travel packages

Proposta para indicação de áreas para a implantação de aterro sanitário no município de Bauru-SP, utilizando análise multi critério de decisão e técnicas de geoprocessamento

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Determinação de áreas prioritárias para o restabelecimento da cobertura florestal, apoiada no uso de geotecnologias

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Un modello multicriteriale di supporto alla pianificazione territoriale finalizzato alla classificazione del territorio rurale e alla caratterizzazione dell’Impronta Agro ambientale delle aree agricole periurbane.

La ricerca proposta si pone l’obiettivo di definire e sperimentare un metodo per un’articolata e sistematica lettura del territorio rurale, che, oltre ad ampliare la conoscenza del territorio, sia di supporto ai processi di pianificazione paesaggistici ed urbanistici e all’attuazione delle politiche agricole e di sviluppo rurale. Un’approfondita disamina dello stato dell’arte riguardante l’evoluzione del processo di urbanizzazione e le conseguenze dello stesso in Italia e in Europa, oltre che del quadro delle politiche territoriali locali nell’ambito del tema specifico dello spazio rurale e periurbano, hanno reso possibile, insieme a una dettagliata analisi delle principali metodologie di analisi territoriale presenti in letteratura, la determinazione del concept alla base della ricerca condotta. E’ stata sviluppata e testata una metodologia multicriteriale e multilivello per la lettura del territorio rurale sviluppata in ambiente GIS, che si avvale di algoritmi di clustering (quale l’algoritmo IsoCluster) e classificazione a massima verosimiglianza, focalizzando l’attenzione sugli spazi agricoli periurbani. Tale metodo si incentra sulla descrizione del territorio attraverso la lettura di diverse componenti dello stesso, quali quelle agro-ambientali e socio-economiche, ed opera una sintesi avvalendosi di una chiave interpretativa messa a punto allo scopo, l’Impronta Agroambientale (Agro-environmental Footprint - AEF), che si propone di quantificare il potenziale impatto degli spazi rurali sul sistema urbano. In particolare obiettivo di tale strumento è l’identificazione nel territorio extra-urbano di ambiti omogenei per caratteristiche attraverso una lettura del territorio a differenti scale (da quella territoriale a quella aziendale) al fine di giungere ad una sua classificazione e quindi alla definizione delle aree classificabili come “agricole periurbane”. La tesi propone la presentazione dell’architettura complessiva della metodologia e la descrizione dei livelli di analisi che la compongono oltre che la successiva sperimentazione e validazione della stessa attraverso un caso studio rappresentativo posto nella Pianura Padana (Italia).

Markov blanket-based approach for learning multi-dimensional Bayesian network classifiers: An application to predict the European Quality of Life-5 Dimensions (EQ-5D) from the 39-item Parkinson's Disease Questionnaire (PDQ-39)

Multi-dimensional Bayesian network classifiers (MBCs) are probabilistic graphical models recently proposed to deal with multi-dimensional classification problems, where each instance in the data set has to be assigned to more than one class variable. In this paper, we propose a Markov blanket-based approach for learning MBCs from data. Basically, it consists of determining the Markov blanket around each class variable using the HITON algorithm, then specifying the directionality over the MBC subgraphs. Our approach is applied to the prediction problem of the European Quality of Life-5 Dimensions (EQ-5D) from the 39-item Parkinson’s Disease Questionnaire (PDQ-39) in order to estimate the health-related quality of life of Parkinson’s patients. Fivefold cross-validation experiments were carried out on randomly generated synthetic data sets, Yeast data set, as well as on a real-world Parkinson’s disease data set containing 488 patients. The experimental study, including comparison with additional Bayesian network-based approaches, back propagation for multi-label learning, multi-label k-nearest neighbor, multinomial logistic regression, ordinary least squares, and censored least absolute deviations, shows encouraging results in terms of predictive accuracy as well as the identification of dependence relationships among class and feature variables.

Efficient Monte Carlo optimization for multi-label classifier chains

Multi-label classification (MLC) is the supervised learning problem where an instance may be associated with multiple labels. Modeling dependencies between labels allows MLC methods to improve their performance at the expense of an increased computational cost. In this paper we focus on the classifier chains (CC) approach for modeling dependencies. On the one hand, the original CC algorithm makes a greedy approximation, and is fast but tends to propagate errors down the chain. On the other hand, a recent Bayes-optimal method improves the performance, but is computationally intractable in practice. Here we present a novel double-Monte Carlo scheme (M2CC), both for finding a good chain sequence and performing efficient inference. The M2CC algorithm remains tractable for high-dimensional data sets and obtains the best overall accuracy, as shown on several real data sets with input dimension as high as 1449 and up to 103 labels.

Efficient Monte Carlo methods for multi-dimensional learning with classifier chains

Multi-dimensional classification (MDC) is the supervised learning problem where an instance is associated with multiple classes, rather than with a single class, as in traditional classification problems. Since these classes are often strongly correlated, modeling the dependencies between them allows MDC methods to improve their performance – at the expense of an increased computational cost. In this paper we focus on the classifier chains (CC) approach for modeling dependencies, one of the most popular and highest-performing methods for multi-label classification (MLC), a particular case of MDC which involves only binary classes (i.e., labels). The original CC algorithm makes a greedy approximation, and is fast but tends to propagate errors along the chain. Here we present novel Monte Carlo schemes, both for finding a good chain sequence and performing efficient inference. Our algorithms remain tractable for high-dimensional data sets and obtain the best predictive performance across several real data sets.

New definitions of margin for multi-class Boosting algorithms

La familia de algoritmos de Boosting son un tipo de técnicas de clasificación y regresión que han demostrado ser muy eficaces en problemas de Visión Computacional. Tal es el caso de los problemas de detección, de seguimiento o bien de reconocimiento de caras, personas, objetos deformables y acciones. El primer y más popular algoritmo de Boosting, AdaBoost, fue concebido para problemas binarios. Desde entonces, muchas han sido las propuestas que han aparecido con objeto de trasladarlo a otros dominios más generales: multiclase, multilabel, con costes, etc. Nuestro interés se centra en extender AdaBoost al terreno de la clasificación multiclase, considerándolo como un primer paso para posteriores ampliaciones. En la presente tesis proponemos dos algoritmos de Boosting para problemas multiclase basados en nuevas derivaciones del concepto margen. El primero de ellos, PIBoost, está concebido para abordar el problema descomponiéndolo en subproblemas binarios. Por un lado, usamos una codificación vectorial para representar etiquetas y, por otro, utilizamos la función de pérdida exponencial multiclase para evaluar las respuestas. Esta codificación produce un conjunto de valores margen que conllevan un rango de penalizaciones en caso de fallo y recompensas en caso de acierto. La optimización iterativa del modelo genera un proceso de Boosting asimétrico cuyos costes dependen del número de etiquetas separadas por cada clasificador débil. De este modo nuestro algoritmo de Boosting tiene en cuenta el desbalanceo debido a las clases a la hora de construir el clasificador. El resultado es un método bien fundamentado que extiende de manera canónica al AdaBoost original. El segundo algoritmo propuesto, BAdaCost, está concebido para problemas multiclase dotados de una matriz de costes. Motivados por los escasos trabajos dedicados a generalizar AdaBoost al terreno multiclase con costes, hemos propuesto un nuevo concepto de margen que, a su vez, permite derivar una función de pérdida adecuada para evaluar costes. Consideramos nuestro algoritmo como la extensión más canónica de AdaBoost para este tipo de problemas, ya que generaliza a los algoritmos SAMME, Cost-Sensitive AdaBoost y PIBoost. Por otro lado, sugerimos un simple procedimiento para calcular matrices de coste adecuadas para mejorar el rendimiento de Boosting a la hora de abordar problemas estándar y problemas con datos desbalanceados. Una serie de experimentos nos sirven para demostrar la efectividad de ambos métodos frente a otros conocidos algoritmos de Boosting multiclase en sus respectivas áreas. En dichos experimentos se usan bases de datos de referencia en el área de Machine Learning, en primer lugar para minimizar errores y en segundo lugar para minimizar costes. Además, hemos podido aplicar BAdaCost con éxito a un proceso de segmentación, un caso particular de problema con datos desbalanceados. Concluimos justificando el horizonte de futuro que encierra el marco de trabajo que presentamos, tanto por su aplicabilidad como por su flexibilidad teórica. Abstract The family of Boosting algorithms represents a type of classification and regression approach that has shown to be very effective in Computer Vision problems. Such is the case of detection, tracking and recognition of faces, people, deformable objects and actions. The first and most popular algorithm, AdaBoost, was introduced in the context of binary classification. Since then, many works have been proposed to extend it to the more general multi-class, multi-label, costsensitive, etc... domains. Our interest is centered in extending AdaBoost to two problems in the multi-class field, considering it a first step for upcoming generalizations. In this dissertation we propose two Boosting algorithms for multi-class classification based on new generalizations of the concept of margin. The first of them, PIBoost, is conceived to tackle the multi-class problem by solving many binary sub-problems. We use a vectorial codification to represent class labels and a multi-class exponential loss function to evaluate classifier responses. This representation produces a set of margin values that provide a range of penalties for failures and rewards for successes. The stagewise optimization of this model introduces an asymmetric Boosting procedure whose costs depend on the number of classes separated by each weak-learner. In this way the Boosting procedure takes into account class imbalances when building the ensemble. The resulting algorithm is a well grounded method that canonically extends the original AdaBoost. The second algorithm proposed, BAdaCost, is conceived for multi-class problems endowed with a cost matrix. Motivated by the few cost-sensitive extensions of AdaBoost to the multi-class field, we propose a new margin that, in turn, yields a new loss function appropriate for evaluating costs. Since BAdaCost generalizes SAMME, Cost-Sensitive AdaBoost and PIBoost algorithms, we consider our algorithm as a canonical extension of AdaBoost to this kind of problems. We additionally suggest a simple procedure to compute cost matrices that improve the performance of Boosting in standard and unbalanced problems. A set of experiments is carried out to demonstrate the effectiveness of both methods against other relevant Boosting algorithms in their respective areas. In the experiments we resort to benchmark data sets used in the Machine Learning community, firstly for minimizing classification errors and secondly for minimizing costs. In addition, we successfully applied BAdaCost to a segmentation task, a particular problem in presence of imbalanced data. We conclude the thesis justifying the horizon of future improvements encompassed in our framework, due to its applicability and theoretical flexibility.

Optimal Choice of a Firm in Conducting Auction

Силвия К. Баева, Цветана Хр. Недева - Важен аспект в системата на Министерството на регионалното развитие и благоустройство е работата по Оперативна програма “Регионално развитие” с приоритетна ос “Устойчиво и интегрирано градско развитие” по операция “Подобряване на физическата среда и превенция на риска”. По тази програма са включени 86 общини. Финансовият ресурс на тази операция е на стойност 238 589 939 евро, от които 202 801 448 евро са европейско финансиране [1]. Всяка от тези 86 общини трябва да реши задачата за възлагане на обществена поръчка на определена фирма по тази операция. Всъщност, тази задача е задача за провеждане на общински търг за избор на фирма-изпълнител. Оптималният избор на фирма-изпълнител е много важен. Задачата за провеждане на търг ще формулираме като задача на многокритериалното вземане на решения, като чрез подходящо изграждане на критерии и методи може да се трансформира до задача на еднокритериалната оптимизация.

A multi-method approach for the assessment of composite indices and rankings

There is growing popularity in the use of composite indices and rankings for cross-organizational benchmarking. However, little attention has been paid to alternative methods and procedures for the computation of these indices and how the use of such methods may impact the resulting indices and rankings. This dissertation developed an approach for assessing composite indices and rankings based on the integration of a number of methods for aggregation, data transformation and attribute weighting involved in their computation. The integrated model developed is based on the simulation of composite indices using methods and procedures proposed in the area of multi-criteria decision making (MCDM) and knowledge discovery in databases (KDD). The approach developed in this dissertation was automated through an IT artifact that was designed, developed and evaluated based on the framework and guidelines of the design science paradigm of information systems research. This artifact dynamically generates multiple versions of indices and rankings by considering different methodological scenarios according to user specified parameters. The computerized implementation was done in Visual Basic for Excel 2007. Using different performance measures, the artifact produces a number of excel outputs for the comparison and assessment of the indices and rankings. In order to evaluate the efficacy of the artifact and its underlying approach, a full empirical analysis was conducted using the World Bank's Doing Business database for the year 2010, which includes ten sub-indices (each corresponding to different areas of the business environment and regulation) for 183 countries. The output results, which were obtained using 115 methodological scenarios for the assessment of this index and its ten sub-indices, indicated that the variability of the component indicators considered in each case influenced the sensitivity of the rankings to the methodological choices. Overall, the results of our multi-method assessment were consistent with the World Bank rankings except in cases where the indices involved cost indicators measured in per capita income which yielded more sensitive results. Low income level countries exhibited more sensitivity in their rankings and less agreement between the benchmark rankings and our multi-method based rankings than higher income country groups.

Broad-scale mapping of seafloor habitats in the north-east Atlantic using existing environmental data

If marine management policies and actions are to achieve long-term sustainable use and management of the marine environment and its resources, they need to be informed by data giving the spatial distribution of seafloor habitats over large areas. Broad-scale seafloor habitat mapping is an approachwhich has the benefit of producing maps covering large extents at a reasonable cost. This approach was first investigated by Roff et al. (2003), who, acknowledging that benthic communities are strongly influenced by the physical characteristics of the seafloor, proposed overlaying mapped physical variables using a geographic information system (GIS) to produce an integrated map of the physical characteristics of the seafloor. In Europe the method was adapted to the marine section of the EUNIS (European Nature Information System) classification of habitat types under the MESH project, andwas applied at an operational level in 2011 under the EUSeaMap project. The present study compiled GIS layers for fundamental physical parameters in the northeast Atlantic, including (i) bathymetry, (ii) substrate type, (iii) light penetration depth and (iv) exposure to near-seafloor currents andwave action. Based on analyses of biological occurrences, significant thresholds were fine-tuned for each of the abiotic layers and later used in multi-criteria raster algebra for the integration of the layers into a seafloor habitat map. The final result was a harmonised broad-scale seafloor habitat map with a 250 m pixel size covering four extensive areas, i.e. Ireland, the Bay of Biscay, the Iberian Peninsula and the Azores. The map provided the first comprehensive perception of habitat spatial distribution for the Iberian Peninsula and the Azores, and fed into the initiative for a pan- European map initiated by the EUSeaMap project for Baltic, North, Celtic and Mediterranean seas.