Daniel H. Stolfi

Daniel H. Stolfi
University of Luxembourg · Interdisciplinary Centre for Security, Reliability and Trust

PhD

About

40
Publications
15,710
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
268
Citations
Introduction
Daniel H. Stolfi currently works at SnT - Interdisciplinary Centre for Security, Reliability and Trust, University of Luxembourg. Daniel does research in Bio-inspired Algorithms, Artificial Intelligence and Unmanned Autonomous Vehicles.
Additional affiliations
February 2019 - present
University of Luxembourg
Position
  • Research Associate
Description
  • + Unpredictable trajectories for UAVs. + Cooperative Coevolutionary Algorithms + Evolutionary Game Theory
January 2013 - September 2018
University of Malaga
Position
  • Researcher
Description
  • + Design and evaluation of new metaheuristic techniques to solve mobility problems. + Optimization of road traffic. + Simulation of urban mobility. + Development of software prototypes.
October 2010 - January 2013
University of Malaga
Position
  • Project Researcher
Description
  • + Development of evaluation sessions using software and hardware tools. + Identification of indicators in order to validate hypotheses. + Software development and database management (Java, Hibernate, MySQL, Oracle).

Publications

Publications (40)
Article
Full-text available
This article proposes a mobility architecture, called Green Swarm, to reduce greenhouse gas emissions from road traffic in smart cities. The traffic flow optimization of four European cities: Malaga, Stockholm, Berlin, and Paris, is addressed with new case studies importing each city's actual roads and traffic lights from OpenStreetMap into the SUM...
Article
Full-text available
Finding an available parking space can be difficult in parts of most cities, especially in city centers. In this article, we address the study of parking occupancy data in Birmingham, Glasgow, Norfolk, and Nottingham in the United Kingdom. We test several prediction strategies, such as polynomial fitting, Fourier series, K-means clustering, and tim...
Article
Full-text available
In this article, we propose a new mobility model, called Attractor Based Inter-Swarm collaborationS (ABISS), for improving the surveillance of restricted areas performed by unmanned autonomous vehicles. This approach uses different types of vehicles which explore an area of interest following unpredictable trajectories based on chaotic solutions of...
Article
Full-text available
In this paper we present a surveillance system for early detection of escapers from a restricted area based on a new swarming mobility model called CROMM-MS (Chaotic Rössler Mobility Model for Multi-Swarms). CROMM-MS is designed for controlling the trajectories of heterogeneous multi-swarms of aerial, ground and marine unmanned vehicles with import...
Article
Full-text available
This article introduces CONcentric Swarm mObiLity modEl (CONSOLE), a novel mobility model for unmanned aerial vehicles (UAVs) to efficiently achieve surveillance and intruder detection missions. It permits to protect a restricted area from intruders using a concentric circles model where simulated UAVs evolve in these so-called security rings. Havi...
Article
Full-text available
In this article, we propose SuSy-EnGaD, a surveillance system enhanced by games of drones. We propose three different approaches to optimise a swarm of UAVs for improving intruder detection, two of them featuring a multi-objective optimisation approach, while the third approach relates to the evolutionary game theory where three different strategie...
Chapter
In this article we address the optimisation of pheromone communication used for the mobility management of a swarm of Unmanned Aerial Vehicles (UAVs) for surveillance applications. A genetic algorithm is proposed to optimise the exchange of pheromone maps used in the CACOC (Chaotic Ant Colony Optimisation for Coverage) mobility model which improves...
Article
In this paper we present the competitive optimisation of a swarm of Unmanned Aerial Vehicles (UAV) protecting a restricted area from a number of intruders following a Predator-Prey approach. We propose a Competitive Coevolutionary Genetic Algorithm (CompCGA) which optimises the parameters of the UAVs (i.e. predators) to maximise the detection of in...
Article
Traffic congestion is one of the main concerns of citizens living in big cities. In this article we propose a novel system, called Yellow Swarm, with the aim of improving road traffic at a low cost and easy implementation by using a set of LED panels placed throughout the city in order to spread road traffic over its streets. The system is optimall...
Article
Full-text available
Unmanned Aerial Vehicles (UAVs) have quickly become one of the promising Internet-of-Things (IoT) devices for smart cities. Thanks to their mobility, agility, and onboard sensors’ customizability, UAVs have already demonstrated immense potential for numerous commercial applications. The UAVs expansion will come at the price of a dense, high-speed a...
Preprint
Full-text available
Unmanned Aerial Vehicles (UAVs) have quickly become one of the promising Internet-of-Things (IoT) devices for smart cities thanks to their mobility, agility, and onboard sensors' customizability. UAVs are used in many applications expanding beyond the military to more commercial ones, ranging from monitoring, surveillance, mapping to parcel deliver...
Chapter
Full-text available
In this paper we present the parameterisation and optimisation of the CACOC (Chaotic Ant Colony Optimisation for Coverage) mobility model applied to Unmanned Aerial Vehicles (UAV) in order to perform surveillance tasks. The use of unpredictable routes based on the chaotic solutions of a dynamic system as well as pheromone trails improves the area c...
Conference Paper
Full-text available
This paper presents the parameterisation and optimisation of the CACOC (Chaotic Ant Colony Optimisation for Coverage) mobility model used by an Unmanned Aerial Vehicle (UAV) swarm to perform surveillance tasks. CACOC uses chaotic solutions of a dynamical system and pheromones for optimising area coverage. Consequently, several parameters of CACOC a...
Chapter
Full-text available
This study presents a new technique based on Deep Learning with Recurrent Neural Networks to address the prediction of car park occupancy rate. This is an interesting problem in smart mobility and we here approach it in an innovative way, consisting in automatically design a deep network that encapsulates the behavior of the car occupancy and then...
Article
Full-text available
In this article we present a novel approach for calculating realistic traffic flows for traffic simulators, called Flow Generator Algorithm (FGA). We start with an original map from OpenStreetMap and traffic data collected at different measurement points, published by the city’s authorities, to produce a model consisting of the simulation map and a...
Conference Paper
Full-text available
Nowadays, city streets are populated not only by private vehicles but also by public transport, distribution of goods, and deliveries. Since each vehicle class has a maximum cargo capacity, we study in this article how authorities could improve the road traffic by changing the different vehicle proportions: sedans, minivans, full-size vans, trucks,...
Article
Full-text available
This article presents a new set of ideas on how to build bio-inspired algorithms based on the new field of epigenetics. By analyzing this domain and extracting working computational ideas we want to offer a set of tools for the future creation of representations, operators, and search techniques that can competitively solve complex problems. To ill...
Conference Paper
Full-text available
GPS navigators are now present in most vehicles and smartphones. The usual goal of these navigators is to take the user in less time or distance to a destination. However, the global use of navigators in a given city could lead to traffic jams as they have a highly biased preference for some streets. From a general point of view, spreading the traf...
Conference Paper
Full-text available
In this article we address the study of parking occupancy data published by the Birmingham city council with the aim of testing several prediction strategies (polynomial fitting, Fourier series, k-means clustering, and time series) and analyzing their results. We have used cross validation to train the predictors and then tested them on unseen occu...
Conference Paper
Full-text available
In this article we work towards the desired future smart city in which IT and knowledge will hopefully provide a highly livable environment for citizens. To this end, we test a new concept based on intelligent LED panels (the Yellow Swarm) to guide drivers when moving through urban streets so as to finally get rid of traffic jams and protect the en...
Conference Paper
Road transportation is becoming a major concern in modern cities. The growth of the number of vehicles is provoking an important increment of pollution and greenhouse gas emissions generated by road traffic. In this paper, we present CTPATH, an innovative smart mobility software system that offers efficient paths to drivers in terms of travel time...
Conference Paper
Full-text available
In this article we present a strategy based on an evolutionary algorithm to calculate the real vehicle flows in cities according to data from sensors placed in the streets. We have worked with a map imported from OpenStreetMap into the SUMO traffic simulator so that the resulting scenarios can be used to perform different optimizations with the con...
Conference Paper
Full-text available
In this article we propose the Yellow Swarm architecture for reducing travel times, greenhouse gas emissions and fuel consumption of road traffic by using several LED panels to suggest changes in the direction of vehicles (detours) for different time slots. These time intervals are calculated using an evolutionary algorithm, specifically designed f...
Conference Paper
Full-text available
En este trabajo proponemos la arquitectura Yellow Swarm dedicada a la reducción de los tiempos de viaje del tráfico rodado mediante la utilización de una serie de paneles LED con el fin de sugerir diferentes cambios de dirección durante determinadas ventanas de tiempo. Estos tiempos son calculados por un algoritmo evolutivo diseñado expresamente pa...
Article
Full-text available
This article presents an innovative approach to solve one of the most relevant problems related to smart mobility: the reduction of vehicles' travel time. Our original approach, called Red Swarm, suggests a potentially customized route to each vehicle by using several spots located at traffic lights in order to avoid traffic jams by using V2I commu...
Conference Paper
Full-text available
This article proposes an innovative solution for reducing polluting gas emissions from road traffic in modern cities. It is based on our new Red Swarm architecture which is composed of a series of intelligent spots with WiFi connections that can suggest a customized route to drivers. We have tested our proposal in four different case studies corres...
Conference Paper
Full-text available
This article proposes an innovative solution for reducing polluting gas emissions from road traffic in modern cities. It is based on our new Red Swarm architecture which is composed of a series of intelligent spots with WiFi connections that can suggest a customized route to drivers. We have tested our proposal in four different case studies corres...
Conference Paper
Full-text available
This work presents an original approach to regulate traffic by using an on-line system controlled by an EA. Our proposal uses computational spots with WiFi connectivity located at traffic lights (the Red Swarm), which are used to suggest alternative individual routes to vehicles. An evolutionary algorithm is also proposed in order to find a configu...

Network

Cited By

Projects

Projects (3)
Project
The HUNTED project (Heterogeneous multi-swarms of UNmanned auTonomous systEms for mission Deployment) aims at designing a novel generation of mobility models for heterogeneous multi-swarms of Unmanned Autonomous Systems (UAS) for surveillance and tracking of imminent threats. Such swarms are composed of several vehicles moving in an autonomous and coordinated manner in the air, on the ground, and in the sea. Each of them can embed different sensors (e.g., video, infrared, radar) ensuring complementarity and resilience. While the UAS are conducting their mission in a fully autonomous manner, connectivity to one or multiple base stations is optimized which will ensure an efficient and reliable collection of data for further post processing and decision making by the ground forces. This research project is supported by the Office of Naval Research under Award Number N62909-18-1-2176.
Project
Research Objective #1 — Landscape-aware optimization algorithms One of the goal of MODŌ precisely lies in the foundation, analysis and intelligent design of enhanced general-purpose optimization algorithms, search paradigms and their design principles, as well as innovative ways of combining them. Research Objective #2 — Model-assisted optimization algorithms The goal here is to accelerate the convergence of the optimization process and to improve the quality of final solutions. More particularly, we will focus on the suitability of advanced statistical and machine learning meta-models for large-scale optimization, the choice of the output to be predicted by these meta-models, their prediction accuracy and their parameter sensibility, the uncertainties and inaccuracies occurring in their responses, the choice of the data set from which the meta-model learns from, and the integration of the learning phase within the optimization process. Research Objective #3 — Decomposition-based optimization algorithms First, we will address the definition of the set of sub-problems to be solved cooperatively, by decomposing the original problem into a set of sub-problems within a smaller region of the variable space and/or the objective space, so as to increase the efficiency of the optimization process. Second, we will design cooperative computational intelligence algorithms and mechanisms in order to solve each sub-problem, and to specify the local rules of interaction and cooperation governing the global optimization process. Research Objective #4 — Decentralized parallel optimization algorithms The purpose of this research topic is to push forward the design, study, and validation of generic approaches addressing the big nature of nowadays optimization problems, through the investigation of appropriate optimization techniques that can fit in the large-scale and distributed nature of modern compute facilities.
Project
This project makes an ambitious proposal for focused research in challenges related to intelligent transport and smart mobility. We do it from the perspective of building new applications based in solver metaheuristic engines enhanced with methodologies and theories contributed by our team so as to exhibit "holistic intelligence".