Deep-learning applicato all'identificazione automatica di frutta in immagini

Analisi delle fasi per la realizzazione di uno strumento di supporto gli agricoltori, dalla creazione di un dataset, all'addestramento e test di una rete neurale artificiale, con obiettivo la localizzazione del prodotto agricolo all'interno delle immagini.

A Computer-Aided Decision Support System for Making Locational Decisions, 1990

This report is the product of a first-year research project in the University Transportation Centers Program. This project was carried out by an interdisciplinary research team at The University of Iowa's Public Policy Center. The project developed a computerized system to support decisions on locating facilities that serve rural areas while minimizing transportation costs. The system integrates transportation databases with algorithms that specify efficient locations and allocate demand efficiently to service regions; the results of these algorithms are used interactively by decision makers. The authors developed documentation for the system so that others could apply it to estimate the transportation and route requirements of alternative locations and identify locations that meet certain criteria with the least cost. The system was developed and tested on two transportation-related problems in Iowa, and this report uses these applications to illustrate how the system can be used.

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.

The design and Evaluation of 'CAP Tools' - A computer aided parallelisation tool-kit

Abstract not available

Computer aided parallelisation of unstructured mesh codes

Abstract not available

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.

Computer Aided Design Algorithmic Technique for Very Large Scale Integrated Circuit Design and Smart Home Embedded System Design

To tackle the challenges at circuit level and system level VLSI and embedded system design, this dissertation proposes various novel algorithms to explore the efficient solutions. At the circuit level, a new reliability-driven minimum cost Steiner routing and layer assignment scheme is proposed, and the first transceiver insertion algorithmic framework for the optical interconnect is proposed. At the system level, a reliability-driven task scheduling scheme for multiprocessor real-time embedded systems, which optimizes system energy consumption under stochastic fault occurrences, is proposed. The embedded system design is also widely used in the smart home area for improving health, wellbeing and quality of life. The proposed scheduling scheme for multiprocessor embedded systems is hence extended to handle the energy consumption scheduling issues for smart homes. The extended scheme can arrange the household appliances for operation to minimize monetary expense of a customer based on the time-varying pricing model.

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.

Dynamic Human Robot Interaction Framework Using Deep Learning and Robot Operating System (ROS): a practical approach

Trying to explain to a robot what to do is a difficult undertaking, and only specific types of people have been able to do so far, such as programmers or operators who have learned how to use controllers to communicate with a robot. My internship's goal was to create and develop a framework that would make that easier. The system uses deep learning techniques to recognize a set of hand gestures, both static and dynamic. Then, based on the gesture, it sends a command to a robot. To be as generic as feasible, the communication is implemented using Robot Operating System (ROS). Furthermore, users can add new recognizable gestures and link them to new robot actions; a finite state automaton enforces the users' input verification and correct action sequence. Finally, the users can create and utilize a macro to describe a sequence of actions performable by a robot.