Modelling human behaviour and event detection from videos

Automatic analysis of human behaviour in large collections of videos is gaining interest, even more so with the advent of file sharing sites such as YouTube. However, challenges still exist owing to several factors such as inter- and intra-class variations, cluttered backgrounds, occlusion, camera motion, scale, view and illumination changes. This research focuses on modelling human behaviour for action recognition in videos. The developed techniques are validated on large scale benchmark datasets and applied on real-world scenarios such as soccer videos. Three major contributions are made. The first contribution is in the area of proper choice of a feature representation for videos. This involved a study of state-of-the-art techniques for action recognition, feature extraction processing and dimensional reduction techniques so as to yield the best performance with optimal computational requirements. Secondly, temporal modelling of human behaviour is performed. This involved frequency analysis and temporal integration of local information in the video frames to yield a temporal feature vector. Current practices mostly average the frame information over an entire video and neglect the temporal order. Lastly, the proposed framework is applied and further adapted to real-world scenario such as soccer videos. A dataset consisting of video sequences depicting events of players falling is created from actual match data to this end and used to experimentally evaluate the proposed framework.

Preservation through Access: Minimal Processing at the Heinz History Center

Presentation from the MARAC conference in Roanoke, VA on October 7–10, 2015. S8 - Minimal Processing and Preservation: Friends or Foes?

Archival Collections and TMS at Reynolda House Museum of American Art

Presentation from the MARAC conference in Roanoke, VA on October 7–10, 2015. S8 - Minimal Processing and Preservation: Friends or Foes?

Contributions to 3D Data Registration and Representation

Nowadays, new computers generation provides a high performance that enables to build computationally expensive computer vision applications applied to mobile robotics. Building a map of the environment is a common task of a robot and is an essential part to allow the robots to move through these environments. Traditionally, mobile robots used a combination of several sensors from different technologies. Lasers, sonars and contact sensors have been typically used in any mobile robotic architecture, however color cameras are an important sensor due to we want the robots to use the same information that humans to sense and move through the different environments. Color cameras are cheap and flexible but a lot of work need to be done to give robots enough visual understanding of the scenes. Computer vision algorithms are computational complex problems but nowadays robots have access to different and powerful architectures that can be used for mobile robotics purposes. The advent of low-cost RGB-D sensors like Microsoft Kinect which provide 3D colored point clouds at high frame rates made the computer vision even more relevant in the mobile robotics field. The combination of visual and 3D data allows the systems to use both computer vision and 3D processing and therefore to be aware of more details of the surrounding environment. The research described in this thesis was motivated by the need of scene mapping. Being aware of the surrounding environment is a key feature in many mobile robotics applications from simple robotic navigation to complex surveillance applications. In addition, the acquisition of a 3D model of the scenes is useful in many areas as video games scene modeling where well-known places are reconstructed and added to game systems or advertising where once you get the 3D model of one room the system can add furniture pieces using augmented reality techniques. In this thesis we perform an experimental study of the state-of-the-art registration methods to find which one fits better to our scene mapping purposes. Different methods are tested and analyzed on different scene distributions of visual and geometry appearance. In addition, this thesis proposes two methods for 3d data compression and representation of 3D maps. Our 3D representation proposal is based on the use of Growing Neural Gas (GNG) method. This Self-Organizing Maps (SOMs) has been successfully used for clustering, pattern recognition and topology representation of various kind of data. Until now, Self-Organizing Maps have been primarily computed offline and their application in 3D data has mainly focused on free noise models without considering time constraints. Self-organising neural models have the ability to provide a good representation of the input space. In particular, the Growing Neural Gas (GNG) is a suitable model because of its flexibility, rapid adaptation and excellent quality of representation. However, this type of learning is time consuming, specially for high-dimensional input data. Since real applications often work under time constraints, it is necessary to adapt the learning process in order to complete it in a predefined time. This thesis proposes a hardware implementation leveraging the computing power of modern GPUs which takes advantage of a new paradigm coined as General-Purpose Computing on Graphics Processing Units (GPGPU). Our proposed geometrical 3D compression method seeks to reduce the 3D information using plane detection as basic structure to compress the data. This is due to our target environments are man-made and therefore there are a lot of points that belong to a plane surface. Our proposed method is able to get good compression results in those man-made scenarios. The detected and compressed planes can be also used in other applications as surface reconstruction or plane-based registration algorithms. Finally, we have also demonstrated the goodness of the GPU technologies getting a high performance implementation of a CAD/CAM common technique called Virtual Digitizing.

SCOR WG 142: Quality Control Procedures for Oxygen and Other Biogeochemical Sensors on Floats and Gliders. Recommendation for oxygen measurements from Argo floats, implementation of in-air-measurement routine to assure highest long-term accuracy

Recommendation for Oxygen Measurements from Argo Floats: Implementation of In-Air-Measurement Routine to Assure Highest Long-term Accuracy As Argo has entered its second decade and chemical/biological sensor technology is improving constantly, the marine biogeochemistry community is starting to embrace the successful Argo float program. An augmentation of the global float observatory, however, has to follow rather stringent constraints regarding sensor characteristics as well as data processing and quality control routines. Owing to the fairly advanced state of oxygen sensor technology and the high scientific value of oceanic oxygen measurements (Gruber et al., 2010), an expansion of the Argo core mission to routine oxygen measurements is perhaps the most mature and promising candidate (Freeland et al., 2010). In this context, SCOR Working Group 142 “Quality Control Procedures for Oxygen and Other Biogeochemical Sensors on Floats and Gliders” (www.scor-int.org/SCOR_WGs_WG142.htm) set out in 2014 to assess the current status of biogeochemical sensor technology with particular emphasis on float-readiness, develop pre- and post-deployment quality control metrics and procedures for oxygen sensors, and to disseminate procedures widely to ensure rapid adoption in the community.

The Impact of the Eye in Dementia: The Eye and its Role in Diagnosis and Follow‐up

Over the last few decades, the importance of ophthalmic examination in neurodegenerative diseases of the CNS has reportedly increased. The retina is an extension of the CNS and thus should not be surprising to find abnormal results in both the test exploring visual processing and those examining the retina of patients with CNS degeneration. Current in vivo imaging techniques are allowing ophthalmologists to detect and quantify data consistent with the histopathological findings described in the retinas of Alzheimer’s disease (AD) patients and may help to reveal unsuspected retinal and optic‐nerve repercussions of other CNS diseases. In this chapter, we perform an analysis of the physiological changes in ocular and cerebral ageing. We analyse the ocular manifestations in CNS disorders such as stroke, AD and Parkinson’s disease. In addition, the pathophysiology of both the eye and the visual pathway in AD are described. The value of the visual psychophysical tests in AD diagnosis is reviewed as well as the main findings of the optical coherence tomography as a contribution to the diagnosis and monitoring of the disease. Finally, we examine the association of two neurodegenerative diseases, AD and glaucoma, as mere coincidence or possible role in the progression of the neurodegeneration.

ENVIRONMENTAL INFLUENCES AND EPIGENETIC MECHANISMS IN RISK FOR DEPRESSION

Thesis (Ph.D, Psychology) -- Queen's University, 2016-10-04 17:37:07.888

Evaluation of physicochemical and glycaemic properties of commercial plant-based milk substitutes

The market for plant-based dairy-type products is growing as consumers replace bovine milk in their diet, for medical reasons or as a lifestyle choice. A screening of 17 different commercial plant-based milk substitutes based on different cereals, nuts and legumes was performed, including the evaluation of physicochemical and glycaemic properties. Half of the analysed samples had low or no protein contents (<0.5 %). Only samples based on soya showed considerable high protein contents, matching the value of cow’s milk (3.7 %). An in-vitro method was used to predict the glycaemic index. In general, the glycaemic index values ranged from 47 for bovine milk to 64 (almond-based) and up to 100 for rice-based samples. Most of the plant-based milk substitutes were highly unstable with separation rates up to 54.39 %/h. This study demonstrated that nutritional and physicochemical properties of plant-based milk substitutes are strongly dependent on the plant source, processing and fortification. Most products showed low nutritional qualities. Therefore, consumer awareness is important when plant-based milk substitutes are used as an alternative to cow’s milk in the diet.

Enhancement of the total phenolic compounds and antioxidant activity of aqueous Citrus limon L. pomace extracts using microwave pre-treatment on the dry powder

The effect of microwave pre-treatment on the levels of total phenolic compounds, flavonoids, proanthocyanidins and individual major compounds as well as the total antioxidant activity of the dried lemon pomace was investigated. The results showed that microwave pre-treatment significantly affected all the examined parameters. The total phenolic content, total flavonoids, proanthocyanidins, as well as the total antioxidant activity significantly increased as the microwave radiation time and power increased (e.g., 2.5 folds for phenolics, 1.4 folds for flavonoids and 5.5 folds for proanthocyanidins), however irradiation more than 480 W for 5 min resulted in the decrease of these parameters. These findings indicate that microwave irradiation time and power may enhance higher levels of the phenolic compounds as well as the antioxidant capacity of the dried lemon pomace powder. However, higher and longer irradiation may lead to a degradation of phenolic compounds and lower the antioxidant capacity of the dried lemon pomace.

Structural brain connectivity and cognitive ability differences: A multivariate distance matrix regression analysis

Neuroimaging research involves analyses of huge amounts of biological data that might or might not be related with cognition. This relationship is usually approached using univariate methods, and, therefore, correction methods are mandatory for reducing false positives. Nevertheless, the probability of false negatives is also increased. Multivariate frameworks have been proposed for helping to alleviate this balance. Here we apply multivariate distance matrix regression for the simultaneous analysis of biological and cognitive data, namely, structural connections among 82 brain regions and several latent factors estimating cognitive performance. We tested whether cognitive differences predict distances among individuals regarding their connectivity pattern. Beginning with 3,321 connections among regions, the 36 edges better predicted by the individuals' cognitive scores were selected. Cognitive scores were related to connectivity distances in both the full (3,321) and reduced (36) connectivity patterns. The selected edges connect regions distributed across the entire brain and the network defined by these edges supports high-order cognitive processes such as (a) (fluid) executive control, (b) (crystallized) recognition, learning, and language processing, and (c) visuospatial processing. This multivariate study suggests that one widespread, but limited number, of regions in the human brain, supports high-level cognitive ability differences. Hum Brain Mapp, 2016. © 2016 Wiley Periodicals, Inc.

Using syntactic and semantic features for classifying mo- dal values in the portuguese language

This paper presents a study made in a field poorly explored in the Portuguese language – modality and its automatic tagging. Our main goal was to find a set of attributes for the creation of automatic tag- gers with improved performance over the bag-of-words (bow) approach. The performance was measured using precision, recall and F1. Because it is a relatively unexplored field, the study covers the creation of the corpus (composed by eleven verbs), the use of a parser to extract syntac- tic and semantic information from the sentences and a machine learning approach to identify modality values. Based on three different sets of attributes – from trigger itself and the trigger’s path (from the parse tree) and context – the system creates a tagger for each verb achiev- ing (in almost every verb) an improvement in F1 when compared to the traditional bow approach.

Mathematical skills: intergenerational features and relationships with cognitive and linguistic abilities

This thesis aimed to investigate the cognitive underpinnings of math skills, with particular reference to cognitive, and linguistic markers, core mechanisms of number processing and environmental variables. In particular, the issue of intergenerational transmission of math skills has been deepened, comparing parents’ and children’s basic and formal math abilities. This pattern of relationships amongst these has been considered in two different age ranges, preschool and primary school children. In the first chapter, a general introduction on mathematical skills is offered, with a description of some seminal works up to recent studies and latest findings. The first chapter concludes with a review of studies about the influence of environmental variables. In particular, a review of studies about home numeracy and intergenerational transmission is examined. The first study analyzed the relationship between mathematical skills of children attending primary school and those of their mothers. The objective of this study was to understand the influence of mothers' math abilities on those of their children. In the second study, the relationship between parents’ and children numerical processing has been examined in a sample of preschool children. The goal was to understand how mathematical skills of parents were relevant for the development of the numerical skills of children, taking into account children’s cognitive and linguistic skills as well as the role of home numeracy. The third study had the objective of investigating whether the verbal and nonverbal cognitive skills presumed to underlie arithmetic are also related to reading. Primary school children were administered measures of reading and arithmetic to understand the relationships between these two abilities and testing for possible shared cognitive markers. Finally, in the general discussion a summary of main findings across the study is presented, together with clinical and theoretical implications.

Integration of by-products and waste from agri-food supply chains into the «water-energy-food» nexus (RECOW-ER): the role of fungi

The agricultural sector is undoubtedly one of the sectors that has the greatest impact on the use of water and energy to produce food. The circular economy allows to reduce waste, obtaining maximum value from products and materials, through the extraction of all possible by-products from resources. Circular economy principles for agriculture include recycling, processing, and reusing agricultural waste in order to produce bioenergy, nutrients, and biofertilizers. Since agro-industrial wastes are principally composed of lignin, cellulose, and hemicellulose they can represent a suitable substrate for mushroom growth and cultivation. Mushrooms are also considered healthy foods with several medicinal properties. The thesis is structured in seven chapters. In the first chapter an introduction on the water, energy, food nexus, on agro-industrial wastes and on how they can be used for mushroom cultivation is given. Chapter 2 details the aims of this dissertation thesis. In chapters three and four, corn digestate and hazelnut shells were successfully used for mushroom cultivation and their lignocellulosic degradation capacity were assessed by using ATR-FTIR spectroscopy. In chapter five, through the use of the Surface-enhanced Raman Scattering (SERS) spectroscopy was possible to set-up a new method for studying mushroom composition and for identifying different mushroom species based on their spectrum. In chapter six, the isolation of different strains of fungi from plastic residues collected in the fields and the ability of these strains to growth and colonizing the Low-density Polyethylene (LDPE) were explored. The structural modifications of the LDPE, by the most efficient fungal strain, Cladosporium cladosporioides Clc/1 strain were monitored by using the Scanning Electron Microscope (SEM) and ATR-FTIR spectroscopy. Finally, chapter seven outlines the conclusions and some hints for future works and applications are provided.

Concepts and methods for efficient decentralized learning in federated settings

Deep Neural Networks (DNNs) have revolutionized a wide range of applications beyond traditional machine learning and artificial intelligence fields, e.g., computer vision, healthcare, natural language processing and others. At the same time, edge devices have become central in our society, generating an unprecedented amount of data which could be used to train data-hungry models such as DNNs. However, the potentially sensitive or confidential nature of gathered data poses privacy concerns when storing and processing them in centralized locations. To this purpose, decentralized learning decouples model training from the need of directly accessing raw data, by alternating on-device training and periodic communications. The ability of distilling knowledge from decentralized data, however, comes at the cost of facing more challenging learning settings, such as coping with heterogeneous hardware and network connectivity, statistical diversity of data, and ensuring verifiable privacy guarantees. This Thesis proposes an extensive overview of decentralized learning literature, including a novel taxonomy and a detailed description of the most relevant system-level contributions in the related literature for privacy, communication efficiency, data and system heterogeneity, and poisoning defense. Next, this Thesis presents the design of an original solution to tackle communication efficiency and system heterogeneity, and empirically evaluates it on federated settings. For communication efficiency, an original method, specifically designed for Convolutional Neural Networks, is also described and evaluated against the state-of-the-art. Furthermore, this Thesis provides an in-depth review of recently proposed methods to tackle the performance degradation introduced by data heterogeneity, followed by empirical evaluations on challenging data distributions, highlighting strengths and possible weaknesses of the considered solutions. Finally, this Thesis presents a novel perspective on the usage of Knowledge Distillation as a mean for optimizing decentralized learning systems in settings characterized by data heterogeneity or system heterogeneity. Our vision on relevant future research directions close the manuscript.

Role of organic acids and phytonutrients as natural alternatives to antibiotics in supporting intestinal functionality

The gastrointestinal tract (GIT) represents the major portion of the body that interfaces with the external environment, with the double function of food processing and line of defense of the body. Numerous components support and regulate the barrier function of the GIT, such as tight junctions (TJs), cytokines, commensal and pathogenic microorganisms, and other systems of the organism, as the endocannabinoid system (ECS). The ECS can control several gastrointestinal functions, as well as the regulation of intestinal inflammation. Failure of the intestinal barrier function triggers an increase of the concentration of pro-inflammatory cytokines and leads to a reduction in intestinal functionality. This thesis aimed to explore the potential of natural compounds as a new alternative approach to antibiotics not only as antimicrobial, but also supporting intestinal maturation and integrity, and as immune-boosting agents. Different experiments were performed to evaluate the potential of nature-identical compounds (NICs), organic acids (OAs), and essential oils (EOs) to support and fight various stressful stimuli. In vitro, a well characterized blend of NICs and OAs were able to improve TJs and transepithelial electrical resistance (TEER) in an intestinal cell line, exerting an anti-inflammatory potential. EOs enhanced TEER and TJs mRNA levels, with a reduction of paracellular permeability, showing antioxidant and antimicrobial properties. In vivo, thymol modulates the gene expression of ECS and gut chemosensing in the GIT of piglets, where the precise localization of the cannabinoid receptors was immunohistochemically confirmed, suggesting an anti-inflammatory potential. In conclusion, natural alternative molecules represent an effective alternative to support or replace the classical pharmacological prophylaxis. These alternative molecules act not only as antimicrobial agents, but also exerted a crucial role in supporting the intestinal barrier function, preventing oxidative stress, and reducing inflammation. Moreover, thymol seems able to modulate the ECS, representing a novel frontier to support animal health and productivity.