1,721,049 research outputs found
Novel neural network-based algorithms for urban classification and change detection from satellite imagery
Get PDFL`attività umana sta cambiando radicalmente l`ecosistema ambientale, unito anche alla rapida espansione demografica dei sistemi urbani. Benche` queste aree rappresentano solo una minima frazione della Terra, il loro impatto sulla richiesta di energia, cibo, acqua e materiali primi, e` enorme. Per cui, una informazione accurata e tempestiva risulta essere essenziale per gli enti di protezione civile in caso, ad esempio, di catastrofi ambientali.
Negli ultimi anni il forte sviluppo di sistemi satellitari, sia dal punto di vista della risoluzione spaziale che di quella radiometrica e temporale, ha permesso una sempre piu` accurato monitoraggio della Terra, sia con sistemi ottici che con quelli RADAR.
Ad ogni modo, una piu` alta risoluzione (sia spaziale, che spettrale o temporale) presenta tanti vantaggi e miglioramenti quanti svantaggi e limitazioni.
In questa tesi sono discussi in dettaglio i diversi aspetti e tecniche per la classificazione e monitoraggio dei cambiamenti di aree urbane, utilizzando sia sistemi ottici che RADAR. Particolare enfasi e` data alla teoria ed all`uso di reti neurali.Human activity dominates the Earth's ecosystems with structural modifications. The rapid population growth over recent decades and the concentration of this population in and around urban areas have significantly impacted the environment. Although urban areas represent a small fraction of the land surface, they affect large areas due to the magnitude of the associated energy, food, water, and raw material demands. Reliable information in populated areas is essential for urban planning and strategic decision making, such as civil protection departments in cases of emergency.
Remote sensing is increasingly being used as a timely and cost-effective source of information in a wide number of applications, from environment monitoring to location-aware systems. However, mapping human settlements represents one of the most challenging areas for the remote sensing community due to its high spatial and spectral diversity. From the physical composition point of view, several different materials can be used for the same man-made element (for example, building roofs can be made of clay tiles, metal, asphalt, concrete, plastic, grass or stones). On the other hand, the same material can be used for different purposes (for example, concrete can be found in paved roads or building roofs). Moreover, urban areas are often made up of materials present in the surrounding region, making them indistinguishable from the natural or agricultural areas (examples can be unpaved roads and bare soil, clay tiles and bare soil, or parks and vegetated open spaces) [1].
During the last two decades, significant progress has been made in developing and launching satellites with instruments, in both the optical/infrared and microwave regions of the spectra, well suited for Earth observation with an increasingly finer spatial, spectral and temporal resolution. Fine spatial sensors with metric or sub-metric resolution allow the detection of small-scale objects, such as elements of residential housing, commercial buildings, transportation systems and utilities. Multi-spectral and hyper-spectral remote sensing systems provide additional discriminative features for classes that are spectrally similar, due to their higher spectral resolution. The temporal component, integrated with the spectral and spatial dimensions, provides essential information, for example on vegetation dynamics. Moreover, the delineation of temporal homogeneous patches reduces the effect of local spatial heterogeneity that often masks larger spatial patterns.
Nevertheless, higher resolution (spatial, spectral or temporal) imagery comes with limits and challenges that equal the advantages and improvements, and this is valid for both optical and synthetic aperture radar data [2].
This thesis addresses the different aspects of mapping and change detection of human settlements, discussing the main issues related to the use of optical and synthetic aperture radar data. Novel approaches and techniques are proposed and critically discussed to cope with the challenges of urban areas, including data fusion, image information mining, and active learning. The chapters are subdivided into three main parts. Part I addresses the theoretical aspects of neural networks, including their different architectures, design, and training. The proposed neural networks-based algorithms, their applications to classification and change detection problems, and the experimental results are described in Part II and Part III
Model predictive control of cyber-physical systems
No full textCyber-Physical Systems (CPS) represent a groundbreaking technological advancement that integrates physical processes with computational resources and networking capabilities, heralding a significant leap in efficiency, functionality, and adaptability across various applications. From revolutionizing transportation through self-driving cars to enhancing energy distribution via smart grids, CPS are poised to be pivotal in the fourth industrial revolution, fundamentally altering daily life and work in a manner akin to the transformative impacts of the internet and the World Wide Web.
Originating from the concept of merging digital and physical realms, CPS aim to create systems that are inherently intelligent, adaptive, and resilient, extending beyond traditional embedded systems by leveraging advancements in computing, communication, and control.
These systems are characterized by a core architecture comprising physical components (sensors and actuators), cyber elements (computational and communication infrastructure), and control mechanisms (algorithms and software), working in unison through a feedback loop to dynamically interact with and respond to their environment. In this respect, the work done in this thesis is the application of Model Predictive Control (MPC) framework to CPS with the aim to an increase in operational efficiency, an increase in optimality with respect to resource allocation, and an increase in general responsiveness and adaptability of such systems to ambient variability. This thesis attempts to manifest the future implications in applying MPC to transform the management and control of these sophisticated cyber-physical systems within their crucial sectors via theoretical development and practical implementation of case studies.
The control methodology discussed in this thesis regards the application of MPC in three case studies: in the frame of Power Systems, Smart Cities and Industry 4.0 in the space sector.
The first work deals with the emerging complexities in modern transmission and distribution grids that arise through integration with distributed energy resources such as electric energy storage systems, renewable energy plants, and plug-in electric vehicles. The new issues are the intermittency in power generation from renewable sources and in the demand from electric vehicles present a new challenge to grids requiring advancement in grid control and optimization. Considering these challenges, in this work the candidate proposes a novel reconfiguration algorithm based on MPC for the dynamic configuration and re-configuration (topology) of the grid to minimize losses and to improve operational resilience in the presence of adverse events like faults or (cyber-)attacks. The algorithm progresses over the existing methods by removing the necessity of constantly connected grids to let autonomous grid islands be formed that can dynamically get connected and disconnected from the main grid. This research provides a critical review of existing network reconfiguration strategies, spanning between classic optimization-based methods, heuristics ((meta)heuristics), and machine learning-based solutions with their respective advantages and limits. It is hence observed that while the classic optimization methods actually give optimum solutions, they are afflicted by high computational costs. (Meta)heuristics are computationally efficient, though void of guarantees about the optimality of solutions. Machine learning based approaches, in particular Reinforcement Learning, promise policies that are near optimal but come at an enormously high demand for computational resources during training and also offer serious concerns about safety. In such a way, the proposed MPC-based solution combines the features of optimal control at a lower computational cost and adaptability for real-time applications. This means to be the breakthrough approach in network reconfiguration, bridging the gaps that exist within today's available methodologies and thereby offering a powerful, robust, efficient, flexible solution to meet challenges posed by today's modern, dynamic grid environment.
The second work addresses a crucial challenge that urban greenhouse gases (GHG), primarily produced by buildings and transportation, with a focus on optimization of the intelligent traffic light (TL) control systems in mitigating road congestion. Given the global climate change efforts like the 2016 Paris Agreement and the EU 2019 Green Deal, the study would emphasize the need for viable urban traffic management strategies that could lead to significant GHG emission reductions, as a majority of such emissions originate from urban settings. Although an extensive literature on Intelligent TL controls is available today, it is found that there is a gap in adaptability and efficiency, mainly in real-time traffic conditions. A novel model predictive control strategy based on mixed-integer optimization has been proposed in this thesis to enhance the timings of TLs at intersections by an original approach different from classical fixed-timing strategies without any real-time reaction. The main contribution of this thesis lies in proposing an integrated MPC controller which determines both the optimal signal timing for the TLs and optimal trajectories for Automatically Driven Vehicles (ADVs), while modelling also Manually Driven Vehicles (MDVs) dynamics, leading to significant reduction of queue length and waiting times. In these terms the controller is adaptive, allowing it to operate in mixed scenarios. In addition, several innovative constraints that have been introduced within the MPC formulation allow recursive feasibility to be ensured in constraint-activating events, for instance, when a vehicle approaching the TL during red signal could bring the problem towards infeasibility because some constraints cannot be violated.
About Industry 4.0, the most important challenge this thesis tackles is the optimization of task scheduling and controlling in the spaceport within the dynamically changing space industry, which previously limited to governmental entities is now expanding to include private companies. This research was carried out within the framework of the H2020 SESAME project--partnership led by ArianeGroup--that aims to enhance the schedule of assembly operations of space vehicles to maximize the launch throughput at the Guiana space center in Kourou. In the literature they are referred to as Assembly Line Balancing Problems (ALBP) and the key contribution of this work is the development of a scalable MPC algorithm, integrated with a Mixed-Integer Linear Program (MILP) model, to optimize campaign planning in real-time leverages both static and dynamic data, addressing scalability, flexibility and the ability to manage complex constraints, and real-time disturbances. Simulation results confirm the merit of proposed efficient task scheduling algorithm which retains the characteristics of standard MPC and outperforms state-of-the-art optimal scheduling heuristics maintaining similar speed which makes it suitable for real-time implementation
Recommended from our members
Nature can still be the strongest help against aging and neurodegeneration: The sirtuins way
No full textAutomatic Change Detection in Very High Resolution Images with Pulse-Coupled Neural Networks
No full textA novel approach based on pulse-coupled neural networks(PCNNs) for image change detection is presented. PCNNs are based on the implementation of the mechanisms underlying the visual cortex of small mammals, and, with respect to more traditional NNs architectures, such as multilayer perceptron, own interesting advantages. In particular, they are unsupervised and context sensitive. This latter property may be particularly useful
when very high resolution images are considered as, in this case, an object analysis might be more suitable than a pixel-based one. The qualitative and more quantitative results are reported.
The performance of the algorithm has been evaluated on a pair of QuickBird images taken over the test area of Tor Vergata
University, Rome
Going Beyond Counting First Authors in Author Co-citation Analysis
Get PDFThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Analysis of lecitin in pharmaceutical products and diet integrators using a new biosensor operating directly in non aqueous solvent
No full textVariations on the Author
Get PDF“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
Appropriate Similarity Measures for Author Cocitation Analysis
Get PDFWe provide a number of new insights into the methodological discussion about author cocitation analysis. We first argue that the use of the Pearson correlation for measuring the similarity between authors’ cocitation profiles is not very satisfactory. We then discuss what kind of similarity measures may be used as an alternative to the Pearson correlation. We consider three similarity measures in particular. One is the well-known cosine. The other two similarity measures have not been used before in the bibliometric literature. Finally, we show by means of an example that our findings have a high practical relevance.information science;Pearson correlation;cosine;similarity measure;author cocitation analysis
- …
