Sextant. A spatial data infrastructure for marine environments

At national and European levels, in various projects, data products are developed to provide end-users and stakeholders with homogeneously qualified observation compilation or analysis. Ifremer has developed a spatial data infrastructure for marine environment, called Sextant, in order to manage, share and retrieve these products for its partners and the general public. Thanks to the OGC and ISO standard and INSPIRE compliance, the infrastructure provides a unique framework to federate homogeneous descriptions and access to marine data products processed in various contexts, at national level or European level for DG research (SeaDataNet), DG Mare (EMODNET) and DG Growth (Copernicus MEMS). The discovery service of Sextant is based on the metadata catalogue. The data description is normalized according to ISO 191XX series standards and Inspire recommendations. Access to the catalogue is provided by the standard OGC service, Catalogue Service for the Web (CSW 2.0.2). Data visualization and data downloading are available through standard OGC services, Web Map Services (WMS) and Web Feature Services (WFS). Several OGC services are provided within Sextant, according to marine themes, regions and projects. Depending on the file format, WMTS services are used for large images, such as hyperspectral images, or NcWMS services for gridded data, such as climatology models. New functions are developped to improve the visualization, analyse and access to data, eg : data filtering, online spatial processing with WPS services and acces to sensor data with SOS services.

Exploring Hidden Coherent Feature Groups and Temporal Semantics for Multimedia Big Data Analysis

Thanks to the advanced technologies and social networks that allow the data to be widely shared among the Internet, there is an explosion of pervasive multimedia data, generating high demands of multimedia services and applications in various areas for people to easily access and manage multimedia data. Towards such demands, multimedia big data analysis has become an emerging hot topic in both industry and academia, which ranges from basic infrastructure, management, search, and mining to security, privacy, and applications. Within the scope of this dissertation, a multimedia big data analysis framework is proposed for semantic information management and retrieval with a focus on rare event detection in videos. The proposed framework is able to explore hidden semantic feature groups in multimedia data and incorporate temporal semantics, especially for video event detection. First, a hierarchical semantic data representation is presented to alleviate the semantic gap issue, and the Hidden Coherent Feature Group (HCFG) analysis method is proposed to capture the correlation between features and separate the original feature set into semantic groups, seamlessly integrating multimedia data in multiple modalities. Next, an Importance Factor based Temporal Multiple Correspondence Analysis (i.e., IF-TMCA) approach is presented for effective event detection. Specifically, the HCFG algorithm is integrated with the Hierarchical Information Gain Analysis (HIGA) method to generate the Importance Factor (IF) for producing the initial detection results. Then, the TMCA algorithm is proposed to efficiently incorporate temporal semantics for re-ranking and improving the final performance. At last, a sampling-based ensemble learning mechanism is applied to further accommodate the imbalanced datasets. In addition to the multimedia semantic representation and class imbalance problems, lack of organization is another critical issue for multimedia big data analysis. In this framework, an affinity propagation-based summarization method is also proposed to transform the unorganized data into a better structure with clean and well-organized information. The whole framework has been thoroughly evaluated across multiple domains, such as soccer goal event detection and disaster information management.

A text mining approach to materiality assessment

Worldwide companies currently make a significant effort in performing the materiality analysis, whose aim is to explain corporate sustainability in an annual report. Materiality reflects what are the most important social, economic and environmental issues for a company and its stakeholders. Many studies and standards have been proposed to establish what are the main steps to follow to identify the specific topics to be included in a sustainability report. However, few existing quantitative and structured approaches help understanding how to deal with the identified topics and how to prioritise them to effectively show the most valuable ones. Moreover, the use of traditional approaches involves a long-lasting and complex procedure where a lot of people have to be reached and interviewed and several companies' reports have to be read to extrapolate the material topics to be discussed in the sustainability report. This dissertation aims to propose an automated mechanism to gather stakeholders and the company's opinions identifying relevant issues. To accomplish this purpose, text mining techniques are exploited to analyse textual documents written by either a stakeholder or the reporting company. It is then extracted a measure of how much a document deals with some defined topics. This kind of information is finally manipulated to prioritise topics based on how the author's opinion matters. The entire work is based upon a real case study in the domain of telecommunications.

Edge-aware Graph Attention Networks: Joint Reasoning On Text and Knowledge Graphs for Biomedical Question Answering

Much of the real-world dataset, including textual data, can be represented using graph structures. The use of graphs to represent textual data has many advantages, mainly related to maintaining a more significant amount of information, such as the relationships between words and their types. In recent years, many neural network architectures have been proposed to deal with tasks on graphs. Many of them consider only node features, ignoring or not giving the proper relevance to relationships between them. However, in many node classification tasks, they play a fundamental role. This thesis aims to analyze the main GNNs, evaluate their advantages and disadvantages, propose an innovative solution considered as an extension of GAT, and apply them to a case study in the biomedical field. We propose the reference GNNs, implemented with methodologies later analyzed, and then applied to a question answering system in the biomedical field as a replacement for the pre-existing GNN. We attempt to obtain better results by using models that can accept as input both node and edge features. As shown later, our proposed models can beat the original solution and define the state-of-the-art for the task under analysis.

Chicken skeletal muscle-associated macroarray for gene discovery

Macro- and microarrays are well-established technologies to determine gene functions through repeated measurements of transcript abundance. We constructed a chicken skeletal muscle-associated array based on a muscle-specific EST database, which was used to generate a tissue expression dataset of similar to 4500 chicken genes across 5 adult tissues (skeletal muscle, heart, liver, brain, and skin). Only a small number of ESTs were sufficiently well characterized by BLAST searches to determine their probable cellular functions. Evidence of a particular tissue-characteristic expression can be considered an indication that the transcript is likely to be functionally significant. The skeletal muscle macroarray platform was first used to search for evidence of tissue-specific expression, focusing on the biological function of genes/transcripts, since gene expression profiles generated across tissues were found to be reliable and consistent. Hierarchical clustering analysis revealed consistent clustering among genes assigned to 'developmental growth', such as the ontology genes and germ layers. Accuracy of the expression data was supported by comparing information from known transcripts and tissue from which the transcript was derived with macroarray data. Hybridization assays resulted in consistent tissue expression profile, which will be useful to dissect tissue-regulatory networks and to predict functions of novel genes identified after extensive sequencing of the genomes of model organisms. Screening our skeletal-muscle platform using 5 chicken adult tissues allowed us identifying 43 'tissue-specific' transcripts, and 112 co-expressed uncharacterized transcripts with 62 putative motifs. This platform also represents an important tool for functional investigation of novel genes; to determine expression pattern according to developmental stages; to evaluate differences in muscular growth potential between chicken lines, and to identify tissue-specific genes.

Knowledge discovery and data mining in biological databases

The new technologies for Knowledge Discovery from Databases (KDD) and data mining promise to bring new insights into a voluminous growing amount of biological data. KDD technology is complementary to laboratory experimentation and helps speed up biological research. This article contains an introduction to KDD, a review of data mining tools, and their biological applications. We discuss the domain concepts related to biological data and databases, as well as current KDD and data mining developments in biology.

Spatial data mining for enhanced soil map modelling

The principle of using induction rules based on spatial environmental data to model a soil map has previously been demonstrated Whilst the general pattern of classes of large spatial extent and those with close association with geology were delineated small classes and the detailed spatial pattern of the map were less well rendered Here we examine several strategies to improve the quality of the soil map models generated by rule induction Terrain attributes that are better suited to landscape description at a resolution of 250 m are introduced as predictors of soil type A map sampling strategy is developed Classification error is reduced by using boosting rather than cross validation to improve the model Further the benefit of incorporating the local spatial context for each environmental variable into the rule induction is examined The best model was achieved by sampling in proportion to the spatial extent of the mapped classes boosting the decision trees and using spatial contextual information extracted from the environmental variables.

The application of adaptive partitioned random search in feature selection problem

Feature selection is one of important and frequently used techniques in data preprocessing. It can improve the efficiency and the effectiveness of data mining by reducing the dimensions of feature space and removing the irrelevant and redundant information. Feature selection can be viewed as a global optimization problem of finding a minimum set of M relevant features that describes the dataset as well as the original N attributes. In this paper, we apply the adaptive partitioned random search strategy into our feature selection algorithm. Under this search strategy, the partition structure and evaluation function is proposed for feature selection problem. This algorithm ensures the global optimal solution in theory and avoids complete randomness in search direction. The good property of our algorithm is shown through the theoretical analysis.

Knowledge cities: a taxonomy for analyzing software and information service clusters

Software and information services (SIS) have become a field of increasing opportunities for international trade due to the worldwide diffusion of a combination of technological and organizational innovations. In several regions, the software industry is organized in clusters, usually referred to as "knowledge cities" because of the growing importance of knowledge-intensive services in their economy. This paper has two primary objectives. First, it raises three major questions related to the attractiveness of different cities in Argentina and Brazil for hosting software companies and to their impact on local development. Second, a new taxonomy is proposed for grouping clusters according to their dominant business segment, ownership pattern and scope of operations. The purpose of this taxonomy is to encourage further studies and provide an exploratory analytical tool for analyzing software clusters.

SIAT:sistema de informações e alertas de trânsito

A evolução tecnológica e das sociedades permitiu que, hoje em dia, uma boa parte da população tenha acesso a dispositivos móveis com funcionalidades avançadas. Com este tipo de dispositivos, temos acesso a inúmeras fontes de informação em tempo-real, mas esta característica ainda não é, hoje em dia, aproveitada na sua totalidade. Este projecto tenta tirar partido desta realidade para, utilizando os diversos dispositivos móveis, criar uma rede de troca de informações de trânsito. O utilizador apenas necessita de servir-se do seu dispositivo móvel para, automaticamente, obter as mais recentes informações de trânsito enquanto, paralelamente, partilha com os outros utilizadores a sua informação. Apesar de existirem outras alternativas no mercado, com soluções que permitem usufruir do mesmo tipo de funcionalidades, nenhuma utiliza este tipo de dispositivos (GPS’s convencionais, por exemplo). Um dos requisitos necessário na implementação deste projecto é uma solução de geocoding. Após terem sido testadas várias soluções, nenhuma cumpria, na totalidade, os requisitos deste projecto, o que originou o desenvolvimento de uma nova solução que cumpre esses requisitos. A solução é, toda ela, muito modular, formada por vários componentes, cada um com responsabilidades bem identificadas. A arquitectura desta solução baseia-se nos padrões de desenvolvimento de uma Service Oriented Architecture. Todos os componentes disponibilizam as suas operações através de web services, e a sua descoberta recorre ao protocolo WS-Discovery. Estes vários componentes podem ser divididos em duas categorias: os do núcleo, responsáveis por criar e oferecer as funcionalidades requisitadas neste projecto e os módulos externos, nos quais se incluem as aplicações que apresentam as funcionalidades ao utilizador. Foram criadas duas formas de consumir a informação oferecida pelo serviço SIAT: a aplicação móvel e um website. No âmbito dos dispositivos móveis, foi desenvolvida uma aplicação para o sistema operativo Windows Phone 7.

Data mining framework for fatty liver disease classification in ultrasound: a hybrid feature extraction paradigm

PURPOSE: Fatty liver disease (FLD) is an increasing prevalent disease that can be reversed if detected early. Ultrasound is the safest and ubiquitous method for identifying FLD. Since expert sonographers are required to accurately interpret the liver ultrasound images, lack of the same will result in interobserver variability. For more objective interpretation, high accuracy, and quick second opinions, computer aided diagnostic (CAD) techniques may be exploited. The purpose of this work is to develop one such CAD technique for accurate classification of normal livers and abnormal livers affected by FLD. METHODS: In this paper, the authors present a CAD technique (called Symtosis) that uses a novel combination of significant features based on the texture, wavelet transform, and higher order spectra of the liver ultrasound images in various supervised learning-based classifiers in order to determine parameters that classify normal and FLD-affected abnormal livers. RESULTS: On evaluating the proposed technique on a database of 58 abnormal and 42 normal liver ultrasound images, the authors were able to achieve a high classification accuracy of 93.3% using the decision tree classifier. CONCLUSIONS: This high accuracy added to the completely automated classification procedure makes the authors' proposed technique highly suitable for clinical deployment and usage.

Towards the detection of deception in interactive multimedia environments

A classical application of biosignal analysis has been the psychophysiological detection of deception, also known as the polygraph test, which is currently a part of standard practices of law enforcement agencies and several other institutions worldwide. Although its validity is far from gathering consensus, the underlying psychophysiological principles are still an interesting add-on for more informal applications. In this paper we present an experimental off-the-person hardware setup, propose a set of feature extraction criteria and provide a comparison of two classification approaches, targeting the detection of deception in the context of a role-playing interactive multimedia environment. Our work is primarily targeted at recreational use in the context of a science exhibition, where the main goal is to present basic concepts related with knowledge discovery, biosignal analysis and psychophysiology in an educational way, using techniques that are simple enough to be understood by children of different ages. Nonetheless, this setting will also allow us to build a significant data corpus, annotated with ground-truth information, and collected with non-intrusive sensors, enabling more advanced research on the topic. Experimental results have shown interesting findings and provided useful guidelines for future work. Pattern Recognition

Feature selection for clustering categorical data with an embedded modelling approach

Research on the problem of feature selection for clustering continues to develop. This is a challenging task, mainly due to the absence of class labels to guide the search for relevant features. Categorical feature selection for clustering has rarely been addressed in the literature, with most of the proposed approaches having focused on numerical data. In this work, we propose an approach to simultaneously cluster categorical data and select a subset of relevant features. Our approach is based on a modification of a finite mixture model (of multinomial distributions), where a set of latent variables indicate the relevance of each feature. To estimate the model parameters, we implement a variant of the expectation-maximization algorithm that simultaneously selects the subset of relevant features, using a minimum message length criterion. The proposed approach compares favourably with two baseline methods: a filter based on an entropy measure and a wrapper based on mutual information. The results obtained on synthetic data illustrate the ability of the proposed expectation-maximization method to recover ground truth. An application to real data, referred to official statistics, shows its usefulness.