Valutazione di metodologie di aggregazione di costi per algoritmi di visione stereo

Tesi riguardante le metodologie di aggregazione di costi applicate alla visione stereo, incentrata in particolare sull'algoritmo box filtering.

Valutazione sperimentale di metodologie di rettificazione e impatto su algoritmi di visione stereo

Ricavare informazioni dalla realtà circostante è un obiettivo molto importante dell'informatica moderna, in modo da poter progettare robot, veicoli a guida autonoma, sistemi di riconoscimento e tanto altro. La computer vision è la parte dell'informatica che se ne occupa e sta sempre più prendendo piede. Per raggiungere tale obiettivo si utilizza una pipeline di visione stereo i cui passi di rettificazione e generazione di mappa di disparità sono oggetto di questa tesi. In particolare visto che questi passi sono spesso affidati a dispositivi hardware dedicati (come le FPGA) allora si ha la necessità di utilizzare algoritmi che siano portabili su questo tipo di tecnologia, dove le risorse sono molto minori. Questa tesi mostra come sia possibile utilizzare tecniche di approssimazione di questi algoritmi in modo da risparmiare risorse ma che che garantiscano comunque ottimi risultati.

A spiking neural network implementation of sound localisation

The focus of this paper is the implementation of a spiking neural network to achieve sound localization; the model is based on the influential short paper by Jeffress in 1948. The SNN has a two-layer topology which can accommodate a limited number of angles in the azimuthal plane. The model accommodates multiple inter-neuron connections with associated delays, and a supervised STDP algorithm is applied to select the optimal pathway for sound localization. Also an analysis of previous relevant work in the area of auditory modelling supports this research.

Threat analysis of IoT networks using artificial neural network intrusion detection system

The Internet of things (IoT) is still in its infancy and has attracted much interest in many industrial sectors including medical fields, logistics tracking, smart cities and automobiles. However, as a paradigm, it is susceptible to a range of significant intrusion threats. This paper presents a threat analysis of the IoT and uses an Artificial Neural Network (ANN) to combat these threats. A multi-level perceptron, a type of supervised ANN, is trained using internet packet traces, then is assessed on its ability to thwart Distributed Denial of Service (DDoS/DoS) attacks. This paper focuses on the classification of normal and threat patterns on an IoT Network. The ANN procedure is validated against a simulated IoT network. The experimental results demonstrate 99.4% accuracy and can successfully detect various DDoS/DoS attacks.

The use of electronic voting systems to enhance deep learning.

The present paper introduces a technology-enhanced teaching method that promotes deep learning. Four stages that correspond to four different student cohorts were used for its development and to analyse its effectiveness. The effectiveness of the method has been assessed in terms of examination results as well as results obtained from class response system software statistics. The evidence gathered indicates that the method developed is very effective and its implementation is straightforward. Furthermore, its success in achieving results seems to be independent of the skills and/or experience of the lecturer.

Bumps, breathers, and waves in a neural network with spike frequency adaptation

In this Letter we introduce a continuum model of neural tissue that include the effects of so-called spike frequency adaptation (SFA). The basic model is an integral equation for synaptic activity that depends upon the non-local network connectivity, synaptic response, and firing rate of a single neuron. A phenomenological model of SFA is examined whereby the firing rate is taken to be a simple state-dependent threshold function. As in the case without SFA classical Mexican-Hat connectivity is shown to allow for the existence of spatially localized states (bumps). Importantly an analysis of bump stability using recent Evans function techniques shows that bumps may undergo instabilities leading to the emergence of both breathers and traveling waves. Moreover, a similar analysis for traveling pulses leads to the conditions necessary to observe a stable traveling breather. Direct numerical simulations both confirm our theoretical predictions and illustrate the rich dynamic behavior of this model, including the appearance of self-replicating bumps.

Existence and wandering of bumps in a spiking neural network model

We study spatially localized states of a spiking neuronal network populated by a pulse coupled phase oscillator known as the lighthouse model. We show that in the limit of slow synaptic interactions in the continuum limit the dynamics reduce to those of the standard Amari model. For non-slow synaptic connections we are able to go beyond the standard firing rate analysis of localized solutions allowing us to explicitly construct a family of co-existing one-bump solutions, and then track bump width and firing pattern as a function of system parameters. We also present an analysis of the model on a discrete lattice. We show that multiple width bump states can co-exist and uncover a mechanism for bump wandering linked to the speed of synaptic processing. Moreover, beyond a wandering transition point we show that the bump undergoes an effective random walk with a diffusion coefficient that scales exponentially with the rate of synaptic processing and linearly with the lattice spacing.

The neural network of saccadic foreknowledge.

Foreknowledge about upcoming events may be exploited to optimize behavioural responses. In a previous work, using an eye movement paradigm, we showed that different types of partial foreknowledge have different effects on saccadic efficiency. In the current study, we investigated the neural circuitry involved in processing of partial foreknowledge using functional magnetic resonance imaging. Fourteen subjects performed a mixed antisaccade, prosaccade paradigm with blocks of no foreknowledge, complete foreknowledge or partial foreknowledge about stimulus location, response direction or task. We found that saccadic foreknowledge is processed primarily within the well-known oculomotor network for saccades and antisaccades. Moreover, we found a consistent decrease in BOLD activity in the primary and secondary visual cortex in all foreknowledge conditions compared to the no-foreknowledge conditions. Furthermore we found that the different types of partial foreknowledge are processed in distinct brain areas: response foreknowledge is processed in the frontal eye field, while stimulus foreknowledge is processed in the frontal and parietal eye field. Task foreknowledge, however, revealed no positive BOLD correlate. Our results show different patterns of engagement in the saccade-related neural network depending upon precisely what type of information is known ahead.

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.

Investigation and prediction of sea level variations in the northern coasts of Persian Gulf using artificial neural network

Sea- level variations have a significant impact on coastal areas. Prediction of sea level variations expected from the pre most critical information needs associated with the sea environment. For this, various methods exist. In this study, on the northern coast of the Persian Gulf have been studied relation to the effectiveness of parameters such as pressure, temperature and wind speed on sea leve and associated with global parameters such as the North Atlantic Oscillation index and NAO index and present statistic models for prediction of sea level. In the next step by using artificial neural network predict sea level for first in this region. Then compared results of the models. Prediction using statistical models estimated in terms correlation coefficient R = 0.84 and root mean square error (RMS) 21.9 cm for the Bushehr station, and R = 0.85 and root mean square error (RMS) 48.4 cm for Rajai station, While neural network used to have 4 layers and each middle layer six neurons is best for prediction and produces the results reliably in terms of correlation coefficient with R = 0.90126 and the root mean square error (RMS) 13.7 cm for the Bushehr station, and R = 0.93916 and the root mean square error (RMS) 22.6 cm for Rajai station. Therefore, the proposed methodology could be successfully used in the study area.

Healthcare Computer Reasoning Addressing Chronically Ill Societies Using IoT: Deep Learning AI to the Rescue of Home-Based Healthcare

The authors present a proposal to develop intelligent assisted living environments for home based healthcare. These environments unite the chronical patient clinical history sematic representation with the ability of monitoring the living conditions and events recurring to a fully managed Semantic Web of Things (SWoT). Several levels of acquired knowledge and the case based reasoning that is possible by knowledge representation of the health-disease history and acquisition of the scientific evidence will deliver, through various voice based natural interfaces, the adequate support systems for disease auto management but prominently by activating the less differentiated caregiver for any specific need. With these capabilities at hand, home based healthcare providing becomes a viable possibility reducing the institutionalization needs. The resulting integrated healthcare framework will provide significant savings while improving the generality of health and satisfaction indicators.

Detecting social patterns within 20th century documentary photos: a deep learning based approach

The job of a historian is to understand what happened in the past, resorting in many cases to written documents as a firsthand source of information. Text, however, does not amount to the only source of knowledge. Pictorial representations, in fact, have also accompanied the main events of the historical timeline. In particular, the opportunity of visually representing circumstances has bloomed since the invention of photography, with the possibility of capturing in real-time the occurrence of a specific events. Thanks to the widespread use of digital technologies (e.g. smartphones and digital cameras), networking capabilities and consequent availability of multimedia content, the academic and industrial research communities have developed artificial intelligence (AI) paradigms with the aim of inferring, transferring and creating new layers of information from images, videos, etc. Now, while AI communities are devoting much of their attention to analyze digital images, from an historical research standpoint more interesting results may be obtained analyzing analog images representing the pre-digital era. Within the aforementioned scenario, the aim of this work is to analyze a collection of analog documentary photographs, building upon state-of-the-art deep learning techniques. In particular, the analysis carried out in this thesis aims at producing two following results: (a) produce the date of an image, and, (b) recognizing its background socio-cultural context,as defined by a group of historical-sociological researchers. Given these premises, the contribution of this work amounts to: (i) the introduction of an historical dataset including images of “Family Album” among all the twentieth century, (ii) the introduction of a new classification task regarding the identification of the socio-cultural context of an image, (iii) the exploitation of different deep learning architectures to perform the image dating and the image socio-cultural context classification.

Deep learning models for the automatic analysis of volleyball plays

Collecting and analysing data is an important element in any field of human activity and research. Even in sports, collecting and analyzing statistical data is attracting a growing interest. Some exemplar use cases are: improvement of technical/tactical aspects for team coaches, definition of game strategies based on the opposite team play or evaluation of the performance of players. Other advantages are related to taking more precise and impartial judgment in referee decisions: a wrong decision can change the outcomes of important matches. Finally, it can be useful to provide better representations and graphic effects that make the game more engaging for the audience during the match. Nowadays it is possible to delegate this type of task to automatic software systems that can use cameras or even hardware sensors to collect images or data and process them. One of the most efficient methods to collect data is to process the video images of the sporting event through mixed techniques concerning machine learning applied to computer vision. As in other domains in which computer vision can be applied, the main tasks in sports are related to object detection, player tracking, and to the pose estimation of athletes. The goal of the present thesis is to apply different models of CNNs to analyze volleyball matches. Starting from video frames of a volleyball match, we reproduce a bird's eye view of the playing court where all the players are projected, reporting also for each player the type of action she/he is performing.

Applied deep learning and data science with a human-centric and data-centric approach

The term Artificial intelligence acquired a lot of baggage since its introduction and in its current incarnation is synonymous with Deep Learning. The sudden availability of data and computing resources has opened the gates to myriads of applications. Not all are created equal though, and problems might arise especially for fields not closely related to the tasks that pertain tech companies that spearheaded DL. The perspective of practitioners seems to be changing, however. Human-Centric AI emerged in the last few years as a new way of thinking DL and AI applications from the ground up, with a special attention at their relationship with humans. The goal is designing a system that can gracefully integrate in already established workflows, as in many real-world scenarios AI may not be good enough to completely replace its humans. Often this replacement may even be unneeded or undesirable. Another important perspective comes from, Andrew Ng, a DL pioneer, who recently started shifting the focus of development from “better models” towards better, and smaller, data. He defined his approach Data-Centric AI. Without downplaying the importance of pushing the state of the art in DL, we must recognize that if the goal is creating a tool for humans to use, more raw performance may not align with more utility for the final user. A Human-Centric approach is compatible with a Data-Centric one, and we find that the two overlap nicely when human expertise is used as the driving force behind data quality. This thesis documents a series of case-studies where these approaches were employed, to different extents, to guide the design and implementation of intelligent systems. We found human expertise proved crucial in improving datasets and models. The last chapter includes a slight deviation, with studies on the pandemic, still preserving the human and data centric perspective.