Algorithms for Geometric Matching, Clustering, and Covering

With the popularization of GPS-enabled devices such as mobile phones, location data are becoming available at an unprecedented scale. The locations may be collected from many different sources such as vehicles moving around a city, user check-ins in social networks, and geo-tagged micro-blogging photos or messages. Besides the longitude and latitude, each location record may also have a timestamp and additional information such as the name of the location. Time-ordered sequences of these locations form trajectories, which together contain useful high-level information about people's movement patterns.

The first part of this thesis focuses on a few geometric problems motivated by the matching and clustering of trajectories. We first give a new algorithm for computing a matching between a pair of curves under existing models such as dynamic time warping (DTW). The algorithm is more efficient than standard dynamic programming algorithms both theoretically and practically. We then propose a new matching model for trajectories that avoids the drawbacks of existing models. For trajectory clustering, we present an algorithm that computes clusters of subtrajectories, which correspond to common movement patterns. We also consider trajectories of check-ins, and propose a statistical generative model, which identifies check-in clusters as well as the transition patterns between the clusters.

The second part of the thesis considers the problem of covering shortest paths in a road network, motivated by an EV charging station placement problem. More specifically, a subset of vertices in the road network are selected to place charging stations so that every shortest path contains enough charging stations and can be traveled by an EV without draining the battery. We first introduce a general technique for the geometric set cover problem. This technique leads to near-linear-time approximation algorithms, which are the state-of-the-art algorithms for this problem in either running time or approximation ratio. We then use this technique to develop a near-linear-time algorithm for this

shortest-path cover problem.

Forces of agglomeration and dispersal in rural business networks: a social network analysis

Two concepts in rural economic development policy have been the focus of much research and policy action: the identification and support of clusters or networks of firms and the availability and adoption by rural businesses of Information and Communication Technologies (ICT). From a theoretical viewpoint these policies are based on two contrasting models, with clustering seen as a process of economic agglomeration, and ICT-mediated communication as a means of facilitating economic dispersion. The study’s conceptual framework is based on four interrelated elements: location, interaction, knowledge, and advantage, together with the concept of networks which is employed as an operationally and theoretically unifying concept. The research questions are developed in four successive categories: Policy, Theory, Networks, and Method. The questions are approached using a study of two contrasting groups of rural small businesses in West Cork, Ireland: (a) Speciality Foods, and (b) firms in Digital Products and Services. The study combines Social Network Analysis (SNA) with Qualitative Thematic Analysis, using data collected from semi-structured interviews with 58 owners or managers of these businesses. Data comprise relational network data on the firms’ connections to suppliers, customers, allies and competitors, together with linked qualitative data on how the firms established connections, and how tacit and codified knowledge was sourced and utilised. The research finds that the key characteristics identified in the cluster literature are evident in the sample of Speciality Food businesses, in relation to flows of tacit knowledge, social embedding, and the development of forms of social capital. In particular the research identified the presence of two distinct forms of collective social capital in this network, termed “community” and “reputation”. By contrast the sample of Digital Products and Services businesses does not have the form of a cluster, but matches more closely to dispersive models, or “chain” structures. Much of the economic and social structure of this set of firms is best explained in terms of “project organisation”, and by the operation of an individual rather than collective form of “reputation”. The rural setting in which these firms are located has resulted in their being service-centric, and consequently they rely on ICT-mediated communication in order to exchange tacit knowledge “at a distance”. It is this factor, rather than inputs of codified knowledge, that most strongly influences their operation and their need for availability and adoption of high quality communication technologies. Thus the findings have applicability in relation to theory in Economic Geography and to policy and practice in Rural Development. In addition the research contributes to methodological questions in SNA, and to methodological questions about the combination or mixing of quantitative and qualitative methods.

Pseudoneglect and visual attention networks

Pseudoneglect represents the tendency for healthy individuals to show a slight but consistent bias in favour of stimuli appearing in the left visual field. The bias is often measured using variants of the line bisection task. An accurate model of the functional architecture of the visuospatial attention system must account for this widely observed phenomenon, as well as for modulation of the direction and magnitude of the bias within individuals by a variety of factors relating to the state of the participant and/or stimulus characteristics. To date, the neural correlates of pseudoneglect remain relatively unmapped. In the current thesis, I employed a combination of psychophysical measurements, electroencephalography (EEG) recording and transcranial direct current stimulation (tDCS) in an attempt to probe the neural generator(s) of pseudoneglect. In particular, I wished to utilise and investigate some of the factors known to modulate the bias (including age, time-on-task and the length of the to-be-bisected line) in order to identify neural processes and activity that are necessary and sufficient for the lateralized bias to arise. Across four experiments utilising a computerized version of a perceptual line bisection task, pseudoneglect was consistently observed at baseline in healthy young participants. However, decreased line length (experiments 1, 2 and 3), time-on-task (experiment 1) and healthy aging (experiment 3) were all found to modulate the bias. Specifically, all three modulations induced a rightward shift in subjective midpoint estimation. Additionally, the line length and time-on-task effects (experiment 1) and the line length and aging effects (experiment 3) were found to have additive relationships. In experiment 2, EEG measurements revealed the line length effect to be reflected in neural activity 100 – 200ms post-stimulus onset over source estimated posterior regions of the right hemisphere (RH: temporo-parietal junction (TPJ)). Long lines induced a hemispheric asymmetry in processing (in favour of the RH) during this period that was absent in short lines. In experiment 4, bi-parietal tDCS (Left Anodal/Right Cathodal) induced a polarity-specific rightward shift in bias, highlighting the crucial role played by parietal cortex in the genesis of pseudoneglect. The opposite polarity (Left Cathodal/Right Anodal) did not induce a change in bias. The combined results from the four experiments of the current thesis provide converging evidence as to the crucial role played by the RH in the genesis of pseudoneglect and in the processing of visual input more generally. The reduction in pseudoneglect with decreased line length, increased time-on-task and healthy aging may be explained by a reduction in RH function, and hence contribution to task processing, induced by each of these modulations. I discuss how behavioural and neuroimaging studies of pseudoneglect (and its various modulators) can provide empirical data upon which accurate formal models of visuospatial attention networks may be based and further tested.

A contribution to semantic description of images and videos: an application of soft biometrics

Humans have a high ability to extract visual data information acquired by sight. Trought a learning process, which starts at birth and continues throughout life, image interpretation becomes almost instinctively. At a glance, one can easily describe a scene with reasonable precision, naming its main components. Usually, this is done by extracting low-level features such as edges, shapes and textures, and associanting them to high level meanings. In this way, a semantic description of the scene is done. An example of this, is the human capacity to recognize and describe other people physical and behavioral characteristics, or biometrics. Soft-biometrics also represents inherent characteristics of human body and behaviour, but do not allow unique person identification. Computer vision area aims to develop methods capable of performing visual interpretation with performance similar to humans. This thesis aims to propose computer vison methods which allows high level information extraction from images in the form of soft biometrics. This problem is approached in two ways, unsupervised and supervised learning methods. The first seeks to group images via an automatic feature extraction learning , using both convolution techniques, evolutionary computing and clustering. In this approach employed images contains faces and people. Second approach employs convolutional neural networks, which have the ability to operate on raw images, learning both feature extraction and classification processes. Here, images are classified according to gender and clothes, divided into upper and lower parts of human body. First approach, when tested with different image datasets obtained an accuracy of approximately 80% for faces and non-faces and 70% for people and non-person. The second tested using images and videos, obtained an accuracy of about 70% for gender, 80% to the upper clothes and 90% to lower clothes. The results of these case studies, show that proposed methods are promising, allowing the realization of automatic high level information image annotation. This opens possibilities for development of applications in diverse areas such as content-based image and video search and automatica video survaillance, reducing human effort in the task of manual annotation and monitoring.

Tourism demand modelling and forecasting with artificial neural network models: the Mozambique case study

This study is aimed to model and forecast the tourism demand for Mozambique for the period from January 2004 to December 2013 using artificial neural networks models. The number of overnight stays in Hotels was used as representative of the tourism demand. A set of independent variables were experimented in the input of the model, namely: Consumer Price Index, Gross Domestic Product and Exchange Rates, of the outbound tourism markets, South Africa, United State of America, Mozambique, Portugal and the United Kingdom. The best model achieved has 6.5% for Mean Absolute Percentage Error and 0.696 for Pearson correlation coefficient. A model like this with high accuracy of forecast is important for the economic agents to know the future growth of this activity sector, as it is important for stakeholders to provide products, services and infrastructures and for the hotels establishments to adequate its level of capacity to the tourism demand.

Functional, clustered, feedforward, and mesoscale brain networks

The brain is a network spanning multiple scales from subcellular to macroscopic. In this thesis I present four projects studying brain networks at different levels of abstraction. The first involves determining a functional connectivity network based on neural spike trains and using a graph theoretical method to cluster groups of neurons into putative cell assemblies. In the second project I model neural networks at a microscopic level. Using diferent clustered wiring schemes, I show that almost identical spatiotemporal activity patterns can be observed, demonstrating that there is a broad neuro-architectural basis to attain structured spatiotemporal dynamics. Remarkably, irrespective of the precise topological mechanism, this behavior can be predicted by examining the spectral properties of the synaptic weight matrix. The third project introduces, via two circuit architectures, a new paradigm for feedforward processing in which inhibitory neurons have the complex and pivotal role in governing information flow in cortical network models. Finally, I analyze axonal projections in sleep deprived mice using data collected as part of the Allen Institute's Mesoscopic Connectivity Atlas. After normalizing for experimental variability, the results indicate there is no single explanatory difference in the mesoscale network between control and sleep deprived mice. Using machine learning techniques, however, animal classification could be done at levels significantly above chance. This reveals that intricate changes in connectivity do occur due to chronic sleep deprivation.

Computational Models Development and Demand Response Application for Smart Grids

This paper focuses on computational models development and its applications on demand response, within smart grid scope. A prosumer model is presented and the corresponding economic dispatch problem solution is analyzed. The prosumer solar radiation production and energy consumption are forecasted by artificial neural networks. The existing demand response models are studied and a computational tool based on fuzzy clustering algorithm is developed and the results discussed. Consumer energy management applications within the InovGrid pilot project are presented. Computation systems are developed for the acquisition, monitoring, control and supervision of consumption data provided by smart meters, allowing the incorporation of consumer actions on their electrical energy management. An energy management system with integration of smart meters for energy consumers in a smart grid is developed.

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.

Deploying and processing neural representations of signals

Neural representations (NR) have emerged in the last few years as a powerful tool to represent signals from several domains, such as images, 3D shapes, or audio. Indeed, deep neural networks have been shown capable of approximating continuous functions that describe a given signal with theoretical infinite resolution. This finding allows obtaining representations whose memory footprint is fixed and decoupled from the resolution at which the underlying signal can be sampled, something that is not possible with traditional discrete representations, e.g., grids of pixels for images or voxels for 3D shapes. During the last two years, many techniques have been proposed to improve the capability of NR to approximate high-frequency details and to make the optimization procedures required to obtain NR less demanding both in terms of time and data requirements, motivating many researchers to deploy NR as the main form of data representation for complex pipelines. Following this line of research, we first show that NR can approximate precisely Unsigned Distance Functions, providing an effective way to represent garments that feature open 3D surfaces and unknown topology. Then, we present a pipeline to obtain in a few minutes a compact Neural Twin® for a given object, by exploiting the recent advances in modeling neural radiance fields. Furthermore, we move a step in the direction of adopting NR as a standalone representation, by considering the possibility of performing downstream tasks by processing directly the NR weights. We first show that deep neural networks can be compressed into compact latent codes. Then, we show how this technique can be exploited to perform deep learning on implicit neural representations (INR) of 3D shapes, by only looking at the weights of the networks.

Uncovering the encoding and transmission of behaviourally relevant information in neural activity

Most cognitive functions require the encoding and routing of information across distributed networks of brain regions. Information propagation is typically attributed to physical connections existing between brain regions, and contributes to the formation of spatially correlated activity patterns, known as functional connectivity. While structural connectivity provides the anatomical foundation for neural interactions, the exact manner in which it shapes functional connectivity is complex and not yet fully understood. Additionally, traditional measures of directed functional connectivity only capture the overall correlation between neural activity, and provide no insight on the content of transmitted information, limiting their ability in understanding neural computations underlying the distributed processing of behaviorally-relevant variables. In this work, we first study the relationship between structural and functional connectivity in simulated recurrent spiking neural networks with spike timing dependent plasticity. We use established measures of time-lagged correlation and overall information propagation to infer the temporal evolution of synaptic weights, showing that measures of dynamic functional connectivity can be used to reliably reconstruct the evolution of structural properties of the network. Then, we extend current methods of directed causal communication between brain areas, by deriving an information-theoretic measure of Feature-specific Information Transfer (FIT) quantifying the amount, content and direction of information flow. We test FIT on simulated data, showing its key properties and advantages over traditional measures of overall propagated information. We show applications of FIT to several neural datasets obtained with different recording methods (magneto and electro-encephalography, spiking activity, local field potentials) during various cognitive functions, ranging from sensory perception to decision making and motor learning. Overall, these analyses demonstrate the ability of FIT to advance the investigation of communication between brain regions, uncovering the previously unaddressed content of directed information flow.

Finding Quasi-Optimal Network Topologies for Information Transmission in Active Networks

This work clarifies the relation between network circuit (topology) and behaviour (information transmission and synchronization) in active networks, e.g. neural networks. As an application, we show how one can find network topologies that are able to transmit a large amount of information, possess a large number of communication channels, and are robust under large variations of the network coupling configuration. This theoretical approach is general and does not depend on the particular dynamic of the elements forming the network, since the network topology can be determined by finding a Laplacian matrix (the matrix that describes the connections and the coupling strengths among the elements) whose eigenvalues satisfy some special conditions. To illustrate our ideas and theoretical approaches, we use neural networks of electrically connected chaotic Hindmarsh-Rose neurons.

Construct and Compare Gene Coexpression Networks with DAPfinder and DAPview

Background: DAPfinder and DAPview are novel BRB-ArrayTools plug-ins to construct gene coexpression networks and identify significant differences in pairwise gene-gene coexpression between two phenotypes. Results: Each significant difference in gene-gene association represents a Differentially Associated Pair (DAP). Our tools include several choices of filtering methods, gene-gene association metrics, statistical testing methods and multiple comparison adjustments. Network results are easily displayed in Cytoscape. Analyses of glioma experiments and microarray simulations demonstrate the utility of these tools. Conclusions: DAPfinder is a new friendly-user tool for reconstruction and comparison of biological networks.

Embedded DSP-Based Compact Fuzzy System and Its Application for Induction-Motor V/f Speed Control

This paper presents a compact embedded fuzzy system for three-phase induction-motor scalar speed control. The control strategy consists in keeping constant the voltage-frequency ratio of the induction-motor supply source. A fuzzy-control system is built on a digital signal processor, which uses speed error and speed-error variation to change both the fundamental voltage amplitude and frequency of a sinusoidal pulsewidth modulation inverter. An alternative optimized method for embedded fuzzy-system design is also proposed. The controller performance, in relation to reference and load-torque variations, is evaluated by experimental results. A comparative analysis with conventional proportional-integral controller is also achieved.

Neural network model for designing automotive devices using SMD LED

The advantages offered by the electronic component LED (Light Emitting Diode) have resulted in a quick and extensive application of this device in the replacement of incandescent lights. In this combined application, however, the relationship between the design variables and the desired effect or result is very complex and renders it difficult to model using conventional techniques. This paper consists of the development of a technique using artificial neural networks that makes it possible to obtain the luminous intensity values of brake lights using SMD (Surface Mounted Device) LEDs from design data. This technique can be utilized to design any automotive device that uses groups of SMD LEDs. The results of industrial applications using SMD LED are presented to validate the proposed technique.

Evaluation of Adaptive Genetic Algorithm to Environmental Modeling of Peponapis and Cucurbita

This paper presents a free software tool that supports the next-generation Mobile Communications, through the automatic generation of models of components and electronic devices based on neural networks. This tool enables the creation, training, validation and simulation of the model directly from measurements made on devices of interest, using an interface totally oriented to non-experts in neural models. The resulting model can be exported automatically to a traditional circuit simulator to test different scenarios.