Detecting obfuscated malware using reduced opcode set and optimised runtime trace

The research presented, investigates the optimal set of operational codes (opcodes) that create a robust indicator of malicious software (malware) and also determines a program’s execution duration for accurate classification of benign and malicious software. The features extracted from the dataset are opcode density histograms, extracted during the program execution. The classifier used is a support vector machine and is configured to select those features to produce the optimal classification of malware over different program run lengths. The findings demonstrate that malware can be detected using dynamic analysis with relatively few opcodes.

Network signatures based on gene pair expression ratios improve classification and the analysis of muscle-invasive urothelial cancer

Urothelial cancer (UC) is highly recurrent and can progress from non-invasive (NMIUC) to a more aggressive muscle-invasive (MIUC) subtype that invades the muscle tissue layer of the bladder. We present a proof of principle study that network-based features of gene pairs can be used to improve classifier performance and the functional analysis of urothelial cancer gene expression data. In the first step of our procedure each individual sample of a UC gene expression dataset is inflated by gene pair expression ratios that are defined based on a given network structure. In the second step an elastic net feature selection procedure for network-based signatures is applied to discriminate between NMIUC and MIUC samples. We performed a repeated random subsampling cross validation in three independent datasets. The network signatures were characterized by a functional enrichment analysis and studied for the enrichment of known cancer genes. We observed that the network-based gene signatures from meta collections of proteinprotein interaction (PPI) databases such as CPDB and the PPI databases HPRD and BioGrid improved the classification performance compared to single gene based signatures. The network based signatures that were derived from PPI databases showed a prominent enrichment of cancer genes (e.g., TP53, TRIM27 and HNRNPA2Bl). We provide a novel integrative approach for large-scale gene expression analysis for the identification and development of novel diagnostical targets in bladder cancer. Further, our method allowed to link cancer gene associations to network-based expression signatures that are not observed in gene-based expression signatures.

Runtime Support for Adaptive Power Capping on Heterogeneous SoCs

Power capping is a fundamental method for reducing the energy consumption of a wide range of modern computing environments, ranging from mobile embedded systems to datacentres. Unfortunately, maximising performance and system efficiency under static power caps remains challenging, while maximising performance under dynamic power caps has been largely unexplored. We present an adaptive power capping method that reduces the power consumption and maximizes the performance of heterogeneous SoCs for mobile and server platforms. Our technique combines power capping with coordinated DVFS, data partitioning and core allocations on a heterogeneous SoC with ARM processors and FPGA resources. We design our framework as a run-time system based on OpenMP and OpenCL to utilise the heterogeneous resources. We evaluate it through five data-parallel benchmarks on the Xilinx SoC which allows fully voltage and frequency control. Our experiments show a significant performance boost of 30% under dynamic power caps with concurrent execution on ARM and FPGA, compared to a naive separate approach.

Educação em ciências no pré-escolar: contributos de um programa de formação de educadores de infância para implementação do trabalho experimental

A educação em ciências em conformidade com as orientações dimanadas do Ministério da Educação deve iniciar-se desde os primeiros anos e por consequência tem de ser uma das áreas a trabalhar no âmbito da educação pré-escolar. No entanto, vários investigadores referem que os educadores não atribuem a devida importância a esta área e explicam que esta postura se pode dever à insegurança científica e didáctica destes profissionais que, por sua vez, pode estar associada à escassez de formação no domínio das ciências durante todo o seu percurso académico. Tendo em conta este contexto, desenvolvemos este estudo de natureza empírica. As questões a que pretendemos dar resposta tinham a ver com: (i) que formação inicial e continuada os educadores tiveram no domínio das ciências?; (ii) quais as suas necessidades para trabalharem esta área no jardim-de-infância?; e (iii) qual o impacte de um programa de formação (PF) nas práticas didáctico-pedagógicas dos educadores? A investigação, de natureza qualitativa, assumiu o formato de estudo de caso e envolveu seis educadoras de infância do Distrito de Bragança. Para desenvolvimento do estudo tivemos em consideração quatro fases: numa primeira começamos por fazer a caracterização das necessidades de formação dos educadores para trabalharem as ciências no pré-escolar; a partir das ideias identificadas concebemos, produzimos e implementamos o PF; posteriormente fizemos o acompanhamento e observação de sessões desenvolvidas pelas educadoras na sala de jardim-deinfância; a quarta fase correspondeu à avaliação do impacte do PF nas práticas didáctico-pedagógicas das educadoras. Utilizámos várias técnicas e instrumentos para recolha dos dados que nos possibilitaram conhecer a formação oferecida aos educadores, ao nível do trabalho experimental de ciências nos cursos de formação inicial e continuada e caracterizar: (i) as concepções sobre CTS antes e após a implementação do PF; e (ii) as práticas didáctico-pedagógicas das educadoras colaboradoras. Os dados recolhidos e, posteriormente, analisados evidenciaram a diminuição do numero de respostas ingénuas permitindo-nos afirmar que o PF contribuiu para que as seis educadoras colaboradoras alterassem as suas concepções sobre CTS e passaram a desenvolver as suas práticas didáctico-pedagógicas na área das ciências de acordo com esta perspectiva. Assim, podemos concluir que o PF teve um impacte muito positivo, pois permitiu às educadoras compreender a importância da abordagem das ciências na educação préescolar e despertar o seu interesse para práticas didáctico-pedagógicas inovadoras com orientação CTS, que privilegiem como estratégia a realização do trabalho prático e experimental. Cotejando minuciosamente o nosso estudo com as opiniões contidas na vasta literatura que compendiámos e revimos, consideramos que este estudo representa um contributo, ainda que modesto, a ter em conta na organização de programas de formação continuada de educadores de infância que vão ao encontro das suas necessidades e que favoreçam o seu desenvolvimento profissional, social e pessoal, opinião que sustentamos por tudo aquilo que dimana e flui, com meridiana clarividência, das conclusões que fomos extraindo ao longo de todo o estudo e consubstanciámos na síntese conclusiva final.

Enhancing Security Requirements Engineering by Organisational Learning

More and more software projects today are security-related in one way or the other. Requirements engineers often fail to recognise indicators for security problems which is a major source of security problems in practice. Identifying security-relevant requirements is labour-intensive and errorprone. In order to facilitate the security requirements elicitation process, we present an approach supporting organisational learning on security requirements by establishing company-wide experience resources, and a socio-technical network to benefit from them. The approach is based on modelling the flow of requirements and related experiences. Based on those models, we enable people to exchange experiences about security-requirements while they write and discuss project requirements. At the same time, the approach enables participating stakeholders to learn while they write requirements. This can increase security awareness and facilitate learning on both individual and organisational levels. As a basis for our approach, we introduce heuristic assistant tools which support reuse of existing security-related experiences. In particular, they include Bayesian classifiers which issue a warning automatically when new requirements seem to be security-relevant. Our results indicate that this is feasible, in particular if the classifier is trained with domain specific data and documents from previous projects. We show how the ability to identify security-relevant requirements can be improved using this approach. We illustrate our approach by providing a step-by-step example of how we improved the security requirements engineering process at the European Telecommunications Standards Institute (ETSI) and report on experiences made in this application.

Fuzzy Ensembles for Embedding Adaptive Behaviours in Semi-Autonomous Avatars in 3D Virtual Worlds

Semi-autonomous avatars should be both realistic and believable. The goal is to learn from and reproduce the behaviours of the user-controlled input to enable semi-autonomous avatars to plausibly interact with their human-controlled counterparts. A powerful tool for embedding autonomous behaviour is learning by imitation. Hence, in this paper an ensemble of fuzzy inference systems cluster the user input data to identify natural groupings within the data to describe the users movement and actions in a more abstract way. Multiple clustering algorithms are investigated along with a neuro-fuzzy classifier; and an ensemble of fuzzy systems are evaluated.

Concepções alternativas de alunos do 5º ano de escolaridade sobre estrutura e propriedades do ar: identificação de estratégias de mudança conceptual

Dissertação de Mestrado, Ciências da Educação, Escola Superior de Educação, Universidade do Algarve, 1998

Metodologia bayesiana e adequação de modelos

Tese de doutoramento, Estatística e Investigação Operacional (Probabilidades e Estatística), Universidade de Lisboa, Faculdade de Ciências, 2014

Robust handling of out-of-vocabulary words in deep language processing

Tese de doutoramento, Informática (Ciências da Computação), Universidade de Lisboa, Faculdade de Ciências, 2014

Contribuições para a localização e mapeamento em robótica através da identificação visual de lugares

Tese de doutoramento, Informática (Engenharia Informática), Universidade de Lisboa, Faculdade de Ciências, 2015

Detecting Adverse Events in Clinical Trial Free Text

Thesis (Master's)--University of Washington, 2013

Automatic Video Analysis for Fisheries Survey Systems

Thesis (Ph.D.)--University of Washington, 2015

Risk Modelling Framework for Emergency Hospital Readmission, Using Hospital Episode Statistics Inpatient Data

The objective of this study was to develop, test and benchmark a framework and a predictive risk model for hospital emergency readmission within 12 months. We performed the development using routinely collected Hospital Episode Statistics data covering inpatient hospital admissions in England. Three different timeframes were used for training, testing and benchmarking: 1999 to 2004, 2000 to 2005 and 2004 to 2009 financial years. Each timeframe includes 20% of all inpatients admitted within the trigger year. The comparisons were made using positive predictive value, sensitivity and specificity for different risk cut-offs, risk bands and top risk segments, together with the receiver operating characteristic curve. The constructed Bayes Point Machine using this feature selection framework produces a risk probability for each admitted patient, and it was validated for different timeframes, sub-populations and cut-off points. At risk cut-off of 50%, the positive predictive value was 69.3% to 73.7%, the specificity was 88.0% to 88.9% and sensitivity was 44.5% to 46.3% across different timeframes. Also, the area under the receiver operating characteristic curve was 73.0% to 74.3%. The developed framework and model performed considerably better than existing modelling approaches with high precision and moderate sensitivity.

DESENVOLVIMENTO DE UM CLASSIFICADOR PARA ANÁLISE BIOMÉTRICA DE UM COLETE INSTRUMENTADO PARA REEDUCAÇÃO POSTURAL

Ao longo dos tempos tem existido um avanço, nas empresas, dirigido à preocupação com o bemestar dos trabalhadores, adotando por isso medidas preventivas. A formação especializada em Medicina do Trabalho é indispensável para o exercício de atividades de prevenção dos riscos profissionais e de promoção da saúde. A postura corporal pode ser definida como a posição e a orientação global do corpo e membros relativamente uns aos outros. Qualquer desvio na forma da coluna vertebral pode gerar solicitações funcionais prejudiciais que ocasionam um aumento de fadiga no trabalhador e leva ao longo do tempo a lesões graves. Cada vez mais surgem doenças profissionais provocadas pela adoção de más posturas, na realização de tarefas diárias dos trabalhadores. A boa postura corporal é uma tarefa específica que representa uma interação complexa entre a função biomecânica e neuromuscular. No presente plano de dissertação foram estudados diferentes classificadores tendo como objetivo classificar boas e más posturas corporais de trabalhadores em contexto de trabalho. Assim foram estudados diferentes classificadores de machine learnig, redes neuronais artificiais, support vector machine, árvores de decisão, análise discriminante, regressão logística, treebagger e naíve bayes. Para treino de classificadores foi realizada a aquisição tridimensional da postura da espinha a 100 pessoas, passando por uma parametrização e treino de diferentes classificadores para a determinação automática do tipo de postura corporal. O classificador que obteve melhor desempenho foi o Treebagger com uma classificação para True Positive de 93,3% e True Negative de 96,2%.

Statistical classification of road pavements using near field vehicle rolling noise measurements

Low noise surfaces have been increasingly considered as a viable and cost-effective alternative to acoustical barriers. However, road planners and administrators frequently lack information on the correlation between the type of road surface and the resulting noise emission profile. To address this problem, a method to identify and classify different types of road pavements was developed, whereby near field road noise is analyzed using statistical learning methods. The vehicle rolling sound signal near the tires and close to the road surface was acquired by two microphones in a special arrangement which implements the Close-Proximity method. A set of features, characterizing the properties of the road pavement, was extracted from the corresponding sound profiles. A feature selection method was used to automatically select those that are most relevant in predicting the type of pavement, while reducing the computational cost. A set of different types of road pavement segments were tested and the performance of the classifier was evaluated. Results of pavement classification performed during a road journey are presented on a map, together with geographical data. This procedure leads to a considerable improvement in the quality of road pavement noise data, thereby increasing the accuracy of road traffic noise prediction models.