This page has only limited features, please log in for full access.
Research on Coronavirus Disease 2019 (COVID-19) detection methods has increased in the last months as more accurate automated toolkits are required. Recent studies show that CT scan images contain useful information to detect the COVID-19 disease. However, the scarcity of large and well balanced datasets limits the possibility of using detection approaches in real diagnostic contexts as they are unable to generalize. Indeed, the performance of these models quickly becomes inadequate when applied to samples captured in different contexts (e.g., different equipment or populations) from those used in the training phase. In this paper, a novel ensemble-based approach for more accurate COVID-19 disease detection using CT scan images is proposed. This work exploits transfer learning using pre-trained deep networks (e.g., VGG, Xception, and ResNet) evolved with a genetic algorithm, combined into an ensemble architecture for the classification of clustered images of lung lobes. The study is validated on a new dataset obtained as an integration of existing ones. The results of the experimental evaluation show that the ensemble classifier ensures effective performance, also exhibiting better generalization capabilities.
Lerina Aversano; Mario Luca Bernardi; Marta Cimitile; Riccardo Pecori. Deep neural networks ensemble to detect COVID-19 from CT scans. Pattern Recognition 2021, 120, 108135 .
AMA StyleLerina Aversano, Mario Luca Bernardi, Marta Cimitile, Riccardo Pecori. Deep neural networks ensemble to detect COVID-19 from CT scans. Pattern Recognition. 2021; 120 ():108135.
Chicago/Turabian StyleLerina Aversano; Mario Luca Bernardi; Marta Cimitile; Riccardo Pecori. 2021. "Deep neural networks ensemble to detect COVID-19 from CT scans." Pattern Recognition 120, no. : 108135.
In this paper, we report the scientific experience of HELMeTO 2020, the second edition of the International Workshop on Higher Education Learning Methodologies and Technologies Online, held virtually in Bari (Italy) in September 2020 because of the COVID-19 pandemic. The call received 59 proposals from nine countries, 39 papers were accepted to the virtual workshop and 26 full papers were finally selected to be published in the proceedings. The workshop illustrated a fast-developing scenario in which the epidemic emergency accelerated the dissemination and consolidation of online learning in higher education. A specific focus of the workshop can be identified as students’ learning experience, with studies on tutoring and active learning approaches, personalized solutions supported by data analysis, virtual reality and an in-depth analysis of human–computer interactions.
Laura Agrati; Daniel Burgos; Pietro Ducange; Pierpaolo Limone; Riccardo Pecori; Loredana Perla; Pietro Picerno; Paolo Raviolo; Christian Stracke. Bridges and Mediation in Higher Distance Education: HELMeTO 2020 Report. Education Sciences 2021, 11, 334 .
AMA StyleLaura Agrati, Daniel Burgos, Pietro Ducange, Pierpaolo Limone, Riccardo Pecori, Loredana Perla, Pietro Picerno, Paolo Raviolo, Christian Stracke. Bridges and Mediation in Higher Distance Education: HELMeTO 2020 Report. Education Sciences. 2021; 11 (7):334.
Chicago/Turabian StyleLaura Agrati; Daniel Burgos; Pietro Ducange; Pierpaolo Limone; Riccardo Pecori; Loredana Perla; Pietro Picerno; Paolo Raviolo; Christian Stracke. 2021. "Bridges and Mediation in Higher Distance Education: HELMeTO 2020 Report." Education Sciences 11, no. 7: 334.
During the last years, several studies have been proposed about user identification by means of keystroke analysis. Keystroke dynamics has a lower cost when compared to other biometric-based methods since such a system does not require any additional specific sensor, apart from a traditional keyboard, and it allows the continuous identification of the users in the background as well. The research proposed in this paper concerns (i) the creation of a large integrated dataset of users typing on a traditional keyboard obtained through the integration of three real-world datasets coming from existing studies and (ii) the definition of an ensemble learning approach, made up of basic deep neural network classifiers, with the objective of distinguishing the different users of the considered dataset by exploiting a proper group of features able to capture their typing style. After an optimization phase, in order to find the best possible base classifier, we evaluated the ensemble super-classifier comparing different voting techniques, namely majority and Bayesian, as well as training allocation strategies, i.e., random and K-means. The approach we propose has been assessed using the created very large integrated dataset and the obtained results are very promising, achieving an accuracy of up to 0.997 under certain evaluation conditions.
Lerina Aversano; Mario Luca Bernardi; Marta Cimitile; Riccardo Pecori. Continuous authentication using deep neural networks ensemble on keystroke dynamics. PeerJ Computer Science 2021, 7, e525 .
AMA StyleLerina Aversano, Mario Luca Bernardi, Marta Cimitile, Riccardo Pecori. Continuous authentication using deep neural networks ensemble on keystroke dynamics. PeerJ Computer Science. 2021; 7 ():e525.
Chicago/Turabian StyleLerina Aversano; Mario Luca Bernardi; Marta Cimitile; Riccardo Pecori. 2021. "Continuous authentication using deep neural networks ensemble on keystroke dynamics." PeerJ Computer Science 7, no. : e525.
A complex system can be composed of inherent dynamical structures, i.e., relevant subsets of variables interacting tightly with one another and loosely with other subsets. In the literature, some effective methods to identify such relevant sets rely on the so-called Relevance Indexes (RIs), measuring subset relevance based on information theory principles. In this paper, we present ReSS, a collection of CUDA-based programs computing two of such RIs, either through an exhaustive search or a niching metaheuristic when the system dimension is too large. ReSS also includes a script that iteratively activates the search and identifies hierarchical relationships among the relevant subsets. The main purpose of ReSS is to establish a common and easy-to-use general RI-based platform for the analysis of complex systems and other possible applications.
Laura Sani; Michele Amoretti; Stefano Cagnoni; Monica Mordonini; Riccardo Pecori. ReSS: A tool for discovering relevant sets in complex systems. SoftwareX 2021, 14, 100693 .
AMA StyleLaura Sani, Michele Amoretti, Stefano Cagnoni, Monica Mordonini, Riccardo Pecori. ReSS: A tool for discovering relevant sets in complex systems. SoftwareX. 2021; 14 ():100693.
Chicago/Turabian StyleLaura Sani; Michele Amoretti; Stefano Cagnoni; Monica Mordonini; Riccardo Pecori. 2021. "ReSS: A tool for discovering relevant sets in complex systems." SoftwareX 14, no. : 100693.
The constant spread of smart devices in many aspects of our daily life goes hand in hand with the ever-increasing demand for appropriate mechanisms to ensure they are resistant against various types of threats and attacks in the Internet of Things (IoT) environment. In this context, Deep Learning (DL) is emerging as one of the most successful and suitable techniques to be applied to different IoT security aspects. This work aims at systematically reviewing and analyzing the research landscape about DL approaches applied to different IoT security scenarios. The contributions we reviewed are classified according to different points of view into a coherent and structured taxonomy in order to identify the gap in this pivotal research area. The research focused on articles related to the keywords ’deep learning’, ’security’ and ’Internet of Things’ or ’IoT’ in four major databases, namely IEEEXplore, ScienceDirect, SpringerLink, and the ACM Digital Library. We selected and reviewed 69 articles in the end. We have characterized these studies according to three main research questions, namely, the involved security aspects, the used DL network architectures, and the engaged datasets. A final discussion highlights the research gaps still to be investigated as well as the drawbacks and vulnerabilities of the DL approaches in the IoT security scenario.
Lerina Aversano; Mario Luca Bernardi; Marta Cimitile; Riccardo Pecori. A systematic review on Deep Learning approaches for IoT security. Computer Science Review 2021, 40, 100389 .
AMA StyleLerina Aversano, Mario Luca Bernardi, Marta Cimitile, Riccardo Pecori. A systematic review on Deep Learning approaches for IoT security. Computer Science Review. 2021; 40 ():100389.
Chicago/Turabian StyleLerina Aversano; Mario Luca Bernardi; Marta Cimitile; Riccardo Pecori. 2021. "A systematic review on Deep Learning approaches for IoT security." Computer Science Review 40, no. : 100389.
Impulsive noise is the main limiting factor for transmission over channels affected by electromagnetic interference. We study the estimation of (correlated) Gaussian signals in an impulsive noise scenario. In this work, we analyze some of the existing, as well as some novel estimation algorithms. Their performance is compared, for the first time, for different channel conditions, including the Markov–Middleton scenario, where the impulsive noise switches between different noise states. Following a modern approach in digital communications, the receiver design is based on a factor graph model and implements a message passing algorithm. The correlation among signal samples, as well as among noise states brings about a loopy factor graph, where an iterative message passing scheme should be employed. As is well known, approximate variational inference techniques are necessary in these cases. We propose and analyze different algorithms and provide a complete performance comparison among them, showing that the expectation propagation, transparent propagation, and parallel iterative schedule approaches reach a performance close to optimal, at different channel conditions.
Anoush Mirbadin; Armando Vannucci; Giulio Colavolpe; Riccardo Pecori; Luca Veltri. Iterative Receiver Design for the Estimation of Gaussian Samples in Impulsive Noise. Applied Sciences 2021, 11, 557 .
AMA StyleAnoush Mirbadin, Armando Vannucci, Giulio Colavolpe, Riccardo Pecori, Luca Veltri. Iterative Receiver Design for the Estimation of Gaussian Samples in Impulsive Noise. Applied Sciences. 2021; 11 (2):557.
Chicago/Turabian StyleAnoush Mirbadin; Armando Vannucci; Giulio Colavolpe; Riccardo Pecori; Luca Veltri. 2021. "Iterative Receiver Design for the Estimation of Gaussian Samples in Impulsive Noise." Applied Sciences 11, no. 2: 557.
Data stream mining has recently grown in popularity, thanks to an increasing number of applications which need continuous and fast analysis of streaming data. Such data are generally produced in application domains that require immediate reactions with strict temporal constraints. These particular characteristics make problematic the use of classical machine learning algorithms for mining knowledge from these fast data streams and call for appropriate techniques. In this paper, based on the well-known Hoeffding Decision Tree (HDT) for streaming data classification, we introduce FHDT, a fuzzy HDT that extends HDT with fuzziness, thus making HDT more robust to noisy and vague data. We tested FHDT on three synthetic datasets, usually adopted for analyzing concept drifts in data stream classification, and two real-world datasets, already exploited in some recent researches on fuzzy systems for streaming data. We show that FHDT outperforms HDT, especially in presence of concept drift. Furthermore, FHDT is characterized by a high level of interpretability, thanks to the linguistic rules that can be extracted from it.
Pietro Ducange; Francesco Marcelloni; Riccardo Pecori. Fuzzy Hoeffding Decision Tree for Data Stream Classification. International Journal of Computational Intelligence Systems 2021, 14, 946 -964.
AMA StylePietro Ducange, Francesco Marcelloni, Riccardo Pecori. Fuzzy Hoeffding Decision Tree for Data Stream Classification. International Journal of Computational Intelligence Systems. 2021; 14 (1):946-964.
Chicago/Turabian StylePietro Ducange; Francesco Marcelloni; Riccardo Pecori. 2021. "Fuzzy Hoeffding Decision Tree for Data Stream Classification." International Journal of Computational Intelligence Systems 14, no. 1: 946-964.
In the emerging Industrial Internet of Things (IIoT) scenario machine-to-machine communication is a key technology to set up environments wherein sensors, actuators, and controllers can exchange information autonomously. However, many current communication frameworks do not provide enough dynamic interoperability and security. Therefore, we propose a novel communication framework, based on MQTT broker bridging, which, in an Industrial IoT scenario, can foster dynamic inter-operability across different production lines or industrial sites, guaranteeing, at the same time, a higher degree of isolation and control over the information flows, thereby increasing the overall security of the whole scenario. The solution we propose does also support dynamic authentication and authorization and has been practically implemented and evaluated in a proper small-scale IIoT testbed, encompassing PLCs, IIoT gateways, as well as MQTT brokers with novel and extended capabilities.The evaluation results demonstrate a linear time complexity for all the considered implementations and bridging modes of the extended brokers. Moreover, all considered access token encapsulation techniques demonstrate a minimum overhead in comparison with standard MQTT brokers.
Michele Amoretti; Riccardo Pecori; Yanina Protskaya; Luca Veltri; Francesco Zanichelli. A Scalable and Secure Publish/Subscribe-Based Framework for Industrial IoT. IEEE Transactions on Industrial Informatics 2020, 17, 3815 -3825.
AMA StyleMichele Amoretti, Riccardo Pecori, Yanina Protskaya, Luca Veltri, Francesco Zanichelli. A Scalable and Secure Publish/Subscribe-Based Framework for Industrial IoT. IEEE Transactions on Industrial Informatics. 2020; 17 (6):3815-3825.
Chicago/Turabian StyleMichele Amoretti; Riccardo Pecori; Yanina Protskaya; Luca Veltri; Francesco Zanichelli. 2020. "A Scalable and Secure Publish/Subscribe-Based Framework for Industrial IoT." IEEE Transactions on Industrial Informatics 17, no. 6: 3815-3825.
The phenomenon of “trolling” in social networks is becoming a very serious threat to the online presence of people and companies, since it may affect ordinary people, public profiles of brands, as well as popular characters. In this paper, we present a novel method to preprocess the temporal data describing the activity of possible troll profiles on Twitter, with the aim of improving automatic troll detection. The method is based on the zI, a Relevance Index metric usually employed in the identification of relevant variable subsets in complex systems. In this case, the zI is used to group different user profiles, detecting different behavioral patterns for standard users and trolls. The comparison of the results, obtained on data preprocessed using this novel method and on the original dataset, demonstrates that the technique generally improves the classification performance of troll detection, virtually independently of the classifier that is used.
Laura Sani; Riccardo Pecori; Paolo Fornacciari; Monica Mordonini; Michele Tomaiuolo; Stefano Cagnoni. A Relevance Index-Based Method for Improved Detection of Malicious Users in Social Networks. Communications in Computer and Information Science 2020, 78 -89.
AMA StyleLaura Sani, Riccardo Pecori, Paolo Fornacciari, Monica Mordonini, Michele Tomaiuolo, Stefano Cagnoni. A Relevance Index-Based Method for Improved Detection of Malicious Users in Social Networks. Communications in Computer and Information Science. 2020; ():78-89.
Chicago/Turabian StyleLaura Sani; Riccardo Pecori; Paolo Fornacciari; Monica Mordonini; Michele Tomaiuolo; Stefano Cagnoni. 2020. "A Relevance Index-Based Method for Improved Detection of Malicious Users in Social Networks." Communications in Computer and Information Science , no. : 78-89.
In this paper, smartphones and exergame controllers are proposed as BYOD (Bring Your Own Device) solutions for carrying out the interactive learning activities of an online sport and exercise sciences university program. Such devices can be used as sources of kinematic and physiological data during the execution of some selected physical activities for providing, at the same time, a real-time feedback to the student and a ubiquitous assessment to the teacher. Some use scenarios are presented together with a conceptual framework for integrating such devices (and relevant data stream) in an e-learning platform based on a Cloud and Fog Computing architecture.
Pietro Picerno; Riccardo Pecori; Paolo Raviolo; Pietro Ducange. Smartphones and Exergame Controllers as BYOD Solutions for the e-tivities of an Online Sport and Exercise Sciences University Program. Communications in Computer and Information Science 2019, 217 -227.
AMA StylePietro Picerno, Riccardo Pecori, Paolo Raviolo, Pietro Ducange. Smartphones and Exergame Controllers as BYOD Solutions for the e-tivities of an Online Sport and Exercise Sciences University Program. Communications in Computer and Information Science. 2019; ():217-227.
Chicago/Turabian StylePietro Picerno; Riccardo Pecori; Paolo Raviolo; Pietro Ducange. 2019. "Smartphones and Exergame Controllers as BYOD Solutions for the e-tivities of an Online Sport and Exercise Sciences University Program." Communications in Computer and Information Science , no. : 217-227.
We present a model, based on Fog Computing, to access contents of a Virtual Learning Environment. This model will help bringing learning contents and applications closer to students by means of smart nodes located at the edge of the access networks used by the students themselves. It features optimized bandwidth usage that significantly reduces latency, thus improving the overall experience of distance learning. The data collected from these smart nodes, in correlation with the outcomes of the students, quantify the benefits of the proposed model. The results demonstrate that Fog Computing could make Virtual Learning Environments closer to the necessities of students and instructors.
Riccardo Pecori. Augmenting Quality of Experience in Distance Learning Using Fog Computing. IEEE Internet Computing 2019, 23, 49 -58.
AMA StyleRiccardo Pecori. Augmenting Quality of Experience in Distance Learning Using Fog Computing. IEEE Internet Computing. 2019; 23 (5):49-58.
Chicago/Turabian StyleRiccardo Pecori. 2019. "Augmenting Quality of Experience in Distance Learning Using Fog Computing." IEEE Internet Computing 23, no. 5: 49-58.
The so-called Relevance Index (RI) metrics are a set of recently-introduced indicators based on information theory principles that can be used to analyze complex systems by detecting the main interacting structures within them. Such structures can be described as subsets of the variables which describe the system status that are strongly statistically correlated with one another and mostly independent of the rest of the system. The goal of the work described in this paper is to apply the same principles to pattern recognition and check whether the RI metrics can also identify, in a high-dimensional feature space, attribute subsets from which it is possible to build new features which can be effectively used for classification. Preliminary results indicating that this is possible have been obtained using the RI metrics in a supervised way, i.e., by separately applying such metrics to homogeneous datasets comprising data instances which all belong to the same class, and iterating the procedure over all possible classes taken into consideration. In this work, we checked whether this would also be possible in a totally unsupervised way, i.e., by considering all data available at the same time, independently of the class to which they belong, under the hypothesis that the peculiarities of the variable sets that the RI metrics can identify correspond to the peculiarities by which data belonging to a certain class are distinguishable from data belonging to different classes. The results we obtained in experiments made with some publicly available real-world datasets show that, especially when coupled to tree-based classifiers, the performance of an RI metrics-based unsupervised feature extraction method can be comparable to or better than other classical supervised or unsupervised feature selection or extraction methods.
Laura Sani; Riccardo Pecori; Monica Mordonini; Stefano Cagnoni. From Complex System Analysis to Pattern Recognition: Experimental Assessment of an Unsupervised Feature Extraction Method Based on the Relevance Index Metrics. Computation 2019, 7, 39 .
AMA StyleLaura Sani, Riccardo Pecori, Monica Mordonini, Stefano Cagnoni. From Complex System Analysis to Pattern Recognition: Experimental Assessment of an Unsupervised Feature Extraction Method Based on the Relevance Index Metrics. Computation. 2019; 7 (3):39.
Chicago/Turabian StyleLaura Sani; Riccardo Pecori; Monica Mordonini; Stefano Cagnoni. 2019. "From Complex System Analysis to Pattern Recognition: Experimental Assessment of an Unsupervised Feature Extraction Method Based on the Relevance Index Metrics." Computation 7, no. 3: 39.
Evaluating novel applications and protocols in realistic scenarios has always been a very important task for all stakeholders working in the networking field. Network emulation, being a trade-off between actual deployment and simulations, represents a very powerful solution to this issue, providing a working network platform without requiring the actual deployment of all network components. We present NEMO, a flexible and scalable Java-based network emulator, which can be used to emulate either only a single link, a portion of a network, or an entire network. NEMO is able to work in both real and virtual time, depending on the tested scenarios and goals, and it can be run as either a stand-alone instance on a single machine, or distributed among different network-connected machines, leading to distributed and highly scalable emulation infrastructures. Among different features, NEMO is also capable of virtualizing the execution of third-party Java applications by running them on top of virtual nodes, possibly attached to an emulated or external network.
Luca Veltri; Luca Davoli; Riccardo Pecori; Armando Vannucci; Francesco Zanichelli. NEMO: A flexible and highly scalable network EMulatOr. SoftwareX 2019, 10, 100248 .
AMA StyleLuca Veltri, Luca Davoli, Riccardo Pecori, Armando Vannucci, Francesco Zanichelli. NEMO: A flexible and highly scalable network EMulatOr. SoftwareX. 2019; 10 ():100248.
Chicago/Turabian StyleLuca Veltri; Luca Davoli; Riccardo Pecori; Armando Vannucci; Francesco Zanichelli. 2019. "NEMO: A flexible and highly scalable network EMulatOr." SoftwareX 10, no. : 100248.
We present an improvement of a method that aims at detecting important dynamical structures in complex systems, by identifying subsets of elements that show tight and coordinated interactions among themselves, while interplaying much more loosely with the rest of the system. Such subsets are estimated by means of a Relevance Index (RI), which is normalized with respect to a homogeneous system, usually described by independent Gaussian variables, as a reference. The strategy presented herein improves the way the homogeneous system is conceived from a theoretical viewpoint. Firstly, we consider the system components as dependent and with equal pairwise correlations, which implies a non-diagonal correlation matrix of the homogeneous system. Then, we generate the components of the homogeneous system according to a multivariate Bernoulli distribution, by exploiting the NORTA method, which is able to create samples of a desired random vector, given its marginal distributions and its correlation matrix. The proposed improvement on the RI method has been applied to three different case studies, obtaining better results compared with the traditional method based on the homogeneous system with independent Gaussian variables.
Laura Sani; Alberto Bononi; Riccardo Pecori; Michele Amoretti; Monica Mordonini; Andrea Roli; Marco Villani; Stefano Cagnoni; Roberto Serra. An Improved Relevance Index Method to Search Important Structures in Complex Systems. Communications in Computer and Information Science 2019, 3 -16.
AMA StyleLaura Sani, Alberto Bononi, Riccardo Pecori, Michele Amoretti, Monica Mordonini, Andrea Roli, Marco Villani, Stefano Cagnoni, Roberto Serra. An Improved Relevance Index Method to Search Important Structures in Complex Systems. Communications in Computer and Information Science. 2019; ():3-16.
Chicago/Turabian StyleLaura Sani; Alberto Bononi; Riccardo Pecori; Michele Amoretti; Monica Mordonini; Andrea Roli; Marco Villani; Stefano Cagnoni; Roberto Serra. 2019. "An Improved Relevance Index Method to Search Important Structures in Complex Systems." Communications in Computer and Information Science , no. : 3-16.
Purpose Managing efficiently educational Big Data, produced by Virtual Learning Environments, is becoming a compelling necessity, especially for those universities providing distance learning. This paper aims to propose a possible framework to compute efficiently key performance indicators, summarizing the trends of students’ academic careers, by using educational Big Data. Design/methodology/approach The framework is designed and implemented in a distributed fashion. The parallel computation of the indicators through Map and Reduce nodes is carefully described, together with the workflow of data, from the educational sources to a NoSQL database and to the learning analytics engine. Findings This framework was tested at eCampus University, an Italian distance learning institution, and it was able to significantly reduce the amount of time needed to compute key performance indicators. Moreover, by implementing a proper data representation dashboard, it resulted in a useful help and support for educational decisions and performance analyses and for revealing possible criticalities. Originality/value The framework proposed integrates for the first time, to the best of the authors’ knowledge, a set of modules, designed and implemented in a distributed fashion, to compute key performance indicators for distance learning institutions. It can be used to analyze the dropouts and the outcomes of students and, therefore, to evaluate the performances of universities, which can, in turn, propose effective improvements toward enhancing the overall e-learning scenario.
Riccardo Pecori; Vincenzo Suraci; Pietro Ducange. Efficient computation of key performance indicators in a distance learning university. Information Discovery and Delivery 2019, 47, 96 -105.
AMA StyleRiccardo Pecori, Vincenzo Suraci, Pietro Ducange. Efficient computation of key performance indicators in a distance learning university. Information Discovery and Delivery. 2019; 47 (2):96-105.
Chicago/Turabian StyleRiccardo Pecori; Vincenzo Suraci; Pietro Ducange. 2019. "Efficient computation of key performance indicators in a distance learning university." Information Discovery and Delivery 47, no. 2: 96-105.
We consider the problem of estimating correlated Gaussian samples in (correlated) impulsive noise, through message-passing algorithms. This is a meaningful theoretical framework to model signal transmission on power-line communication systems. Due to the mixture of Gaussian variables (the samples) and Bernoulli variables (the impulsive noise switches), the complexity of messages increases exponentially with the number of samples. By adopting a Parallel Iterative Scheduling, with properly constrained messages, it turns out that each iteration of the proposed algorithm is equivalent to the parallel run of a classical Kalman Smoother and a binary sequence detection through the BCJR algorithm. Results demonstrate the effectiveness of the receiver along with its performance, in terms of mean square estimation error.
Armando Vannucci; Giulio Colavolpe; Riccardo Pecori; Luca Veltri. Estimation of a Gaussian Source with Memory in Bursty Impulsive Noise. 2019 IEEE International Symposium on Power Line Communications and its Applications (ISPLC) 2019, 1 -6.
AMA StyleArmando Vannucci, Giulio Colavolpe, Riccardo Pecori, Luca Veltri. Estimation of a Gaussian Source with Memory in Bursty Impulsive Noise. 2019 IEEE International Symposium on Power Line Communications and its Applications (ISPLC). 2019; ():1-6.
Chicago/Turabian StyleArmando Vannucci; Giulio Colavolpe; Riccardo Pecori; Luca Veltri. 2019. "Estimation of a Gaussian Source with Memory in Bursty Impulsive Noise." 2019 IEEE International Symposium on Power Line Communications and its Applications (ISPLC) , no. : 1-6.
Data stream analysis is growing in popularity in the last years since several application domains require to continuously and quickly analyse data produced by sensors with the aim of, for instance, reacting immediately when problems arise, or detecting new trends. The specificity of these domains imposes strict temporal constraints on machine learning algorithms to be used for mining useful insights. The Hoeffding Decision Tree (HDT) is a well-known classification algorithm for efficient streaming data classification. In this paper, with the aim of improving HDT accuracy and capability of handling noisy data, we exploit the learning procedure proposed in HDT for adapting a recently proposed fuzzy decision tree to cope with streaming data classification problems. We tested the fuzzy approach on a benchmark dataset for the on-line learning of data stream classification models. Results show that, during the on-line learning process, the fuzzy approach outperforms HDT in terms of accuracy.
Riccardo Pecori; Pietro Ducange; Francesco Marcelloni. Incremental Learning of Fuzzy Decision Trees for Streaming Data Classification. Proceedings of the 2019 Conference of the International Fuzzy Systems Association and the European Society for Fuzzy Logic and Technology (EUSFLAT 2019) 2019, 1 .
AMA StyleRiccardo Pecori, Pietro Ducange, Francesco Marcelloni. Incremental Learning of Fuzzy Decision Trees for Streaming Data Classification. Proceedings of the 2019 Conference of the International Fuzzy Systems Association and the European Society for Fuzzy Logic and Technology (EUSFLAT 2019). 2019; ():1.
Chicago/Turabian StyleRiccardo Pecori; Pietro Ducange; Francesco Marcelloni. 2019. "Incremental Learning of Fuzzy Decision Trees for Streaming Data Classification." Proceedings of the 2019 Conference of the International Fuzzy Systems Association and the European Society for Fuzzy Logic and Technology (EUSFLAT 2019) , no. : 1.
A Sybil attack is one of the main challenges to be addressed when securing peer-to-peer networks, especially those based on Distributed Hash Tables (DHTs). Tampering routing tables by means of multiple fake identities can make routing, storing, and retrieving operations significantly more difficult and time-consuming. Countermeasures based on trust and reputation have already proven to be effective in some contexts, but one variant of the Sybil attack, the Spartacus attack, is emerging as a new threat and its effects are even riskier and more difficult to stymie. In this paper, we first improve a well-known and deployed DHT (Chord) through a solution mixing trust with standard operations, for facing a Sybil attack affecting either routing or storage and retrieval operations. This is done by maintaining the least possible overhead for peers. Moreover, we extend the solution we propose in order for it to be resilient also against a Spartacus attack, both for an iterative and for a recursive lookup procedure. Finally, we validate our findings by showing that the proposed techniques outperform other trust-based solutions already known in the literature as well.
Riccardo Pecori; Luca Veltri. A Balanced Trust-Based Method to Counter Sybil and Spartacus Attacks in Chord. Security and Communication Networks 2018, 2018, 1 -16.
AMA StyleRiccardo Pecori, Luca Veltri. A Balanced Trust-Based Method to Counter Sybil and Spartacus Attacks in Chord. Security and Communication Networks. 2018; 2018 ():1-16.
Chicago/Turabian StyleRiccardo Pecori; Luca Veltri. 2018. "A Balanced Trust-Based Method to Counter Sybil and Spartacus Attacks in Chord." Security and Communication Networks 2018, no. : 1-16.
Systems that exhibit complex behaviours often contain inherent dynamical structures which evolve over time in a coordinated way. In this paper, we present a methodology based on the Relevance Index method aimed at revealing the dynamical structures hidden in complex systems. The method iterates two basic steps: detection of relevant variable sets based on the computation of the Relevance Index, and application of a sieving algorithm, which refines the results. This approach is able to highlight the organization of a complex system into sets of variables, which interact with one another at different hierarchical levels, detected, in turn, in the different iterations of the sieve. The method can be applied directly to systems composed of a small number of variables, whereas it requires the help of a custom metaheuristic in case of systems with larger dimensions. We have evaluated the potential of the method by applying it to three case studies: synthetic data generated by a nonlinear stochastic dynamical system, a small-sized and well-known system modelling a catalytic reaction, and a larger one, which describes the interactions within a social community, that requires the use of the metaheuristic. The experiments we made to validate the method produced interesting results, effectively uncovering hidden details of the systems to which it was applied.
Marco Villani; Laura Sani; Riccardo Pecori; Michele Amoretti; Andrea Roli; Monica Mordonini; Roberto Serra; Stefano Cagnoni. An Iterative Information-Theoretic Approach to the Detection of Structures in Complex Systems. Complexity 2018, 2018, 1 -15.
AMA StyleMarco Villani, Laura Sani, Riccardo Pecori, Michele Amoretti, Andrea Roli, Monica Mordonini, Roberto Serra, Stefano Cagnoni. An Iterative Information-Theoretic Approach to the Detection of Structures in Complex Systems. Complexity. 2018; 2018 ():1-15.
Chicago/Turabian StyleMarco Villani; Laura Sani; Riccardo Pecori; Michele Amoretti; Andrea Roli; Monica Mordonini; Roberto Serra; Stefano Cagnoni. 2018. "An Iterative Information-Theoretic Approach to the Detection of Structures in Complex Systems." Complexity 2018, no. : 1-15.
Methods based on information theory, such as the Relevance Index (RI), have been employed to study complex systems for their ability to detect significant groups of variables, well integrated among one another and well separated from the others, which provide a functional block description of the system under analysis. The integration (or zI in its standardized form) is a metric that can express the significance of a group of variables for the system under consideration: the higher the zI, the more significant the group. In this paper, we use this metric for an unusual application to a pattern clustering and classification problem. The results show that the centroids of the clusters of patterns identified by the method are effective for distance-based classification algorithms. We compare such a method with other conventional classification approaches to highlight its main features and to address future research towards the refinement of its accuracy and computational efficiency.
Laura Sani; Gianluca D’Addese; Riccardo Pecori; Monica Mordonini; Marco Villani; Stefano Cagnoni. An Integration-Based Approach to Pattern Clustering and Classification. Computer Vision 2018, 362 -374.
AMA StyleLaura Sani, Gianluca D’Addese, Riccardo Pecori, Monica Mordonini, Marco Villani, Stefano Cagnoni. An Integration-Based Approach to Pattern Clustering and Classification. Computer Vision. 2018; ():362-374.
Chicago/Turabian StyleLaura Sani; Gianluca D’Addese; Riccardo Pecori; Monica Mordonini; Marco Villani; Stefano Cagnoni. 2018. "An Integration-Based Approach to Pattern Clustering and Classification." Computer Vision , no. : 362-374.