Human activity recognition with accelerometry: novel time and frequency features

Human Activity Recognition systems require objective and reliable methods that can be used in the daily routine and must offer consistent results according with the performed activities. These systems are under development and offer objective and personalized support for several applications such as the healthcare area. This thesis aims to create a framework for human activities recognition based on accelerometry signals. Some new features and techniques inspired in the audio recognition methodology are introduced in this work, namely Log Scale Power Bandwidth and the Markov Models application. The Forward Feature Selection was adopted as the feature selection algorithm in order to improve the clustering performances and limit the computational demands. This method selects the most suitable set of features for activities recognition in accelerometry from a 423th dimensional feature vector. Several Machine Learning algorithms were applied to the used accelerometry databases – FCHA and PAMAP databases - and these showed promising results in activities recognition. The developed algorithm set constitutes a mighty contribution for the development of reliable evaluation methods of movement disorders for diagnosis and treatment applications.

Analysis and treatment of a nineteenth century oil painting

This thesis focused on the study and treatment of a 19th century female portrait in oil from ECOMUSEU Municipal do Seixal, Portugal. The portrait, which depicts Isabel Maria Lourenço Affonso was in poor condition and a large strip of paint and canvas was missing (approximately 9cm by 66cm, almost 11% of the total surface area). The portrait is a companion piece to a male portrait (the relationship was established as part of this study), therefore a technical study of both paintings was considered essential to support the choices made during the treatment. The project involved three main areas: - The study of the history, condition, materials and techniques of both paintings. This allowed their comparison and understanding of their relationship; - The treatment of Isabel Maria Lourenço Affonso. The choices made and problems encountered are described. - The production of a replacement for the missing strip of paint and canvas. The practical solution developed to overcome such an unusual challenge is described along with the creative and flexible thinking required. Because not all traditional infill materials cope well on a mechanical level with thin layers over a very large surface (many are too brittle), strict criteria had to be employed to choose the appropriate material. The primary goal was to find a fill which would remain flexible and be capable of accepting surface texture, such that there would be a good visual match with the painting. Analysis and testing was carried out to evaluate the physical properties of the fill material chosen, BEVA® Gesso-P. The successful creation of the replacement strip has resulted in two publications and one presentation: Publication pending in The Picture Restorer, Leslie Carlyle, Raquel Marques, Isabel Pombo Cardoso and Sara Babo, “Creating a Textured Replacement Strip for the Missing Lower Portion of an Oil Portrait: Problem Solving and Practical Solutions”. Abstract accepted for presentation and publication, International Meeting on Retouching of Cultural Heritage (2RECH), Raquel Marques, Leslie Carlyle and Isabel Pombo Cardoso, “Textured Replacement Strip for a Missing Portion of a Portrait: Problem Solving and Practical Solutions”.

Archaeometallurgical study of the Proto-historic collection of Moinhos de Golas (North Portugal): a forecast for technological changes?

This work presents the archaeometallurgical study of a group of metallic artefacts found in Moinhos de Golas site, Vila Real (North of Portugal), that can generically be attributed to Proto-history (1st millennium BC, Late Bronze Age and Iron Age). The collection is composed by 35 objects: weapons, ornaments and tools, and others of difficult classification, as rings, bars and one small thin bent sheet. Some of the objects can typologically be attributed to Late Bronze Age, others are of more difficult specific attribution. The archaeometallurgical study involved x-ray digital radiography, elemental analysis by micro-energy dispersive X-ray fluorescence spectrometry and scanning electron microscopy with energy dispersive spectroscopy, microstructural observations by optical microscopy and scanning electron microscopy. The radiographic images revealed structural heterogeneities frequently related with the degradation of some artefacts and the elemental analysis showed that the majority of the artefacts was produced in a binary bronze alloy (Cu-Sn) (73%), being others produced in copper (15%) and three artefacts in brass (Cu-Zn(-Sn-Pb)). Among each type of alloy there’s certain variability in the composition and in the type of inclusions. The microstructural observations revealed that the majority of the artefacts suffered cycles of thermo-mechanical processing after casting. The diversity of metals/alloys identified was a discovery of great interest, specifically due to the presence of brasses. Their presence can be interpreted as importations related to the circulation of exogenous products during the Proto-history and/or to the deposition of materials during different moments at the site, from the transition of Late Bronze Age/Early Iron Age (Orientalizing period) onwards, as during the Roman period.

Bits, Atoms, and Information Sharing: new opportunities for participation

The particular characteristics and affordances of technologies play a significant role in human experience by defining the realm of possibilities available to individuals and societies. Some technological configurations, such as the Internet, facilitate peer-to-peer communication and participatory behaviors. Others, like television broadcasting, tend to encourage centralization of creative processes and unidirectional communication. In other instances still, the affordances of technologies can be further constrained by social practices. That is the case, for example, of radio which, although technically allowing peer-to-peer communication, has effectively been converted into a broadcast medium through the legislation of the airwaves. How technologies acquire particular properties, meanings and uses, and who is involved in those decisions are the broader questions explored here. Although a long line of thought maintains that technologies evolve according to the logic of scientific rationality, recent studies demonstrated that technologies are, in fact, primarily shaped by social forces in specific historical contexts. In this view, adopted here, there is no one best way to design a technological artifact or system; the selection between alternative designs—which determine the affordances of each technology—is made by social actors according to their particular values, assumptions and goals. Thus, the arrangement of technical elements in any technological artifact is configured to conform to the views and interests of those involved in its development. Understanding how technologies assume particular shapes, who is involved in these decisions and how, in turn, they propitiate particular behaviors and modes of organization but not others, requires understanding the contexts in which they are developed. It is argued here that, throughout the last century, two distinct approaches to the development and dissemination of technologies have coexisted. In each of these models, based on fundamentally different ethoi, technologies are developed through different processes and by different participants—and therefore tend to assume different shapes and offer different possibilities. In the first of these approaches, the dominant model in Western societies, technologies are typically developed by firms, manufactured in large factories, and subsequently disseminated to the rest of the population for consumption. In this centralized model, the role of users is limited to selecting from the alternatives presented by professional producers. Thus, according to this approach, the technologies that are now so deeply woven into human experience, are primarily shaped by a relatively small number of producers. In recent years, however, a group of three interconnected interest groups—the makers, hackerspaces, and open source hardware communities—have increasingly challenged this dominant model by enacting an alternative approach in which technologies are both individually transformed and collectively shaped. Through a in-depth analysis of these phenomena, their practices and ethos, it is argued here that the distributed approach practiced by these communities offers a practical path towards a democratization of the technosphere by: 1) demystifying technologies, 2) providing the public with the tools and knowledge necessary to understand and shape technologies, and 3) encouraging citizen participation in the development of technologies.

SDAR: a package for plotting and analyzing stratigraphy data in R

Stratigraphic Columns (SC) are the most useful and common ways to represent the eld descriptions (e.g., grain size, thickness of rock packages, and fossil and lithological components) of rock sequences and well logs. In these representations the width of SC vary according to the grain size (i.e., the wider the strata, the coarser the rocks (Miall 1990; Tucker 2011)), and the thickness of each layer is represented at the vertical axis of the diagram. Typically these representations are drawn 'manually' using vector graphic editors (e.g., Adobe Illustrator®, CorelDRAW®, Inskape). Nowadays there are various software which automatically plot SCs, but there are not versatile open-source tools and it is very di cult to both store and analyse stratigraphic information. This document presents Stratigraphic Data Analysis in R (SDAR), an analytical package1 designed for both plotting and facilitate the analysis of Stratigraphic Data in R (R Core Team 2014). SDAR, uses simple stratigraphic data and takes advantage of the exible plotting tools available in R to produce detailed SCs. The main bene ts of SDAR are: (i) used to generate accurate and complete SC plot including multiple features (e.g., sedimentary structures, samples, fossil content, color, structural data, contacts between beds), (ii) developed in a free software environment for statistical computing and graphics, (iii) run on a wide variety of platforms (i.e., UNIX, Windows, and MacOS), (iv) both plotting and analysing functions can be executed directly on R's command-line interface (CLI), consequently this feature enables users to integrate SDAR's functions with several others add-on packages available for R from The Comprehensive R Archive Network (CRAN).

Analysis and Treatment of a male portrait in oil and a study of the size layer with reconstructions from Vibert’s recipe (1892)

This thesis project concentrated on both the study and treatment of an early 20th century male portrait in oil from Colecção Caixa Geral de Depósitos, Lisbon, Portugal. The portrait of Januário Correia de Almeida, exhibits a tear (approximately 4.0 cm by 2.3 cm) associated with paint loss on the right upper side, where it is possible to observe an unusually thick size layer (approximately 50 microns) and an open weave mesh canvas. Size layers made from animal glue remain subject to severe dimensional changes due to changes in relative humidity (RH), thereby affecting the stability of the painting. In this case, the response to moisture of the size layer is minimal and the painting is largely uncracked with very little active flaking. This suggests that the size layer has undergone pre-treatment to render it unresponsive to moisture or water. Reconstructions based on late nineteenth century recipes using historically appropriate materials are used to explore various options for modifying the characteristics of gelatine, some of which may relate to the Portrait’s size layer. The thesis is separated into two parts: Part 1: Describes the history, condition, materials and techniques of the painting. It also details the treatment of Januário Correia de Almeida as well as the choices made and problems encountered during the treatment. Part 2: Discusses the history of commercial gelatine production, the choice of the appropriate animal source to extract the collagen to produce reconstructions of the portrait’s size layer as well as the characterization of selected reconstructions. The execution of a shallow textured infill led to one publication and one presentation: Abstract accepted for presentation and publication, International Meeting on Retouching of Cultural Heritage (RECH3), Francisco Brites, Leslie Carlyle and Raquel Marques, ‘’Hand building a Low Profile Textured Fill for a Large Loss’’.