Publications

@article{s20051515,

title = {Fast Approximations of Activation Functions in Deep Neural Networks when using Posit Arithmetic},

author = {Marco Cococcioni and Federico Rossi and Emanuele Ruffaldi and Sergio Saponara},

url = {https://www.mdpi.com/1424-8220/20/5/1515},

doi = {10.3390/s20051515},

issn = {1424-8220},

year  = {2020},

date = {2020-01-01},

journal = {Sensors},

volume = {20},

number = {5},

abstract = {With increasing real-time constraints being put on the use of Deep Neural Networks (DNNs) by real-time scenarios, there is the need to review information representation. A very challenging path is to employ an encoding that allows a fast processing and hardware-friendly representation of information. Among the proposed alternatives to the IEEE 754 standard regarding floating point representation of real numbers, the recently introduced Posit format has been theoretically proven to be really promising in satisfying the mentioned requirements. However, with the absence of proper hardware support for this novel type, this evaluation can be conducted only through a software emulation. While waiting for the widespread availability of the Posit Processing Units (the equivalent of the Floating Point Unit (FPU)), we can already exploit the Posit representation and the currently available Arithmetic-Logic Unit (ALU) to speed up DNNs by manipulating the low-level bit string representations of Posits. As a first step, in this paper, we present new arithmetic properties of the Posit number system with a focus on the configuration with 0 exponent bits. In particular, we propose a new class of Posit operators called L1 operators, which consists of fast and approximated versions of existing arithmetic operations or functions (e.g., hyperbolic tangent (TANH) and extended linear unit (ELU)) only using integer arithmetic. These operators introduce very interesting properties and results: (i) faster evaluation than the exact counterpart with a negligible accuracy degradation; (ii) an efficient ALU emulation of a number of Posits operations; and (iii) the possibility to vectorize operations in Posits, using existing ALU vectorized operations (such as the scalable vector extension of ARM CPUs or advanced vector extensions on Intel CPUs). As a second step, we test the proposed activation function on Posit-based DNNs, showing how 16-bit down to 10-bit Posits represent an exact replacement for 32-bit floats while 8-bit Posits could be an interesting alternative to 32-bit floats since their performances are a bit lower but their high speed and low storage properties are very appealing (leading to a lower bandwidth demand and more cache-friendly code). Finally, we point out how small Posits (i.e., up to 14 bits long) are very interesting while PPUs become widespread, since Posit operations can be tabulated in a very efficient way (see details in the text).},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{doi:10.1080/21645515.2020.1714311,

title = {Twitter as a sentinel tool to monitor public opinion on vaccination: an opinion mining analysis from September 2016 to August 2017 in Italy},

author = {Lara Tavoschi and Filippo Quattrone and Eleonora D’Andrea and Pietro Ducange and Marco Vabanesi and Francesco Marcelloni and Pier Luigi Lopalco},

url = {https://doi.org/10.1080/21645515.2020.1714311},

doi = {10.1080/21645515.2020.1714311},

year  = {2020},

date = {2020-01-01},

journal = {Human Vaccines & Immunotherapeutics},

volume = {16},

number = {5},

pages = {1062-1069},

publisher = {Taylor & Francis},

abstract = {ABSTRACTSocial media have become a common way for people to express their personal viewpoints, including sentiments about health topics. We present the results of an opinion mining analysis on vaccination performed on Twitter from September 2016 to August 2017 in Italy. Vaccine-related tweets were automatically classified as against, in favor or neutral in respect of the vaccination topic by means of supervised machine-learning techniques. During this period, we found an increasing trend in the number of tweets on this topic. According to the overall analysis by category, 60% of tweets were classified as neutral, 23% against vaccination, and 17% in favor of vaccination. Vaccine-related events appeared able to influence the number and the opinion polarity of tweets. In particular, the approval of the decree introducing mandatory immunization for selected childhood diseases produced a prominent effect in the social discussion in terms of number of tweets. Opinion mining analysis based on Twitter showed to be a potentially useful and timely sentinel system to assess the orientation of public opinion toward vaccination and, in future, it may effectively contribute to the development of appropriate communication and information strategies.},

note = {PMID: 32118519},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{10.1093/comjnl/bxz009,

title = {A System for Multi-Passenger Urban Ridesharing Recommendations with Ordered Multiple Stops},

author = {Eleonora D’Andrea and Beatrice Lazzerini and Francesco Marcelloni},

url = {https://doi.org/10.1093/comjnl/bxz009},

doi = {10.1093/comjnl/bxz009},

issn = {0010-4620},

year  = {2019},

date = {2019-01-01},

journal = {The Computer Journal},

volume = {63},

number = {5},

pages = {657-687},

abstract = {Traffic and air pollution caused by the increasing number of cars have become important issues in nowadays cities. A possible solution is to employ recommender systems for efficient ridesharing among users. These systems, however, typically do not allow specifying ordered stops, thus preventing a large amount of possible users from exploiting ridesharing, e.g. parents leaving kids at school while going to work. Indeed, if a parent desired to share a ride, he/she would need to indicate the following constraint in the path: the stop at school should precede the stop at work. In this paper, we propose a ridesharing recommender, which allows each user to specify an ordered list of stops and suggests efficient ride matches. The ride-matching criterion is based on a dissimilarity between the driver’s path and the shared path, computed as the shortest path on a directed acyclic graph with ordering constraints between the stops defined in the single paths. The dissimilarity value is the detour requested to the driver to visit also the stops of the paths involved in the ride-share, respecting the visiting order of the stops within each path. Results are presented on a case study involving the city of Pisa.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{BONDIELLI201938,

title = {A survey on fake news and rumour detection techniques},

author = {Alessandro Bondielli and Francesco Marcelloni},

url = {https://www.sciencedirect.com/science/article/pii/S0020025519304372},

doi = {https://doi.org/10.1016/j.ins.2019.05.035},

issn = {0020-0255},

year  = {2019},

date = {2019-01-01},

journal = {Information Sciences},

volume = {497},

pages = {38-55},

abstract = {False or unverified information spreads just like accurate information on the web, thus possibly going viral and influencing the public opinion and its decisions. Fake news and rumours represent the most popular forms of false and unverified information, respectively, and should be detected as soon as possible for avoiding their dramatic effects. The interest in effective detection techniques has been therefore growing very fast in the last years. In this paper we survey the different approaches to automatic detection of fake news and rumours proposed in the recent literature. In particular, we focus on five main aspects. First, we report and discuss the various definitions of fake news and rumours that have been considered in the literature. Second, we highlight how the collection of relevant data for performing fake news and rumours detection is problematic and we present the various approaches, which have been adopted to gather these data, as well as the publicly available datasets. Third, we describe the features that have been considered in fake news and rumour detection approaches. Fourth, we provide a comprehensive analysis on the various techniques used to perform rumour and fake news detection. Finally, we identify and discuss future directions.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{RENDA20191,

title = {Comparing ensemble strategies for deep learning: An application to facial expression recognition},

author = {Alessandro Renda and Marco Barsacchi and Alessio Bechini and Francesco Marcelloni},

url = {https://www.sciencedirect.com/science/article/pii/S0957417419304257},

doi = {https://doi.org/10.1016/j.eswa.2019.06.025},

issn = {0957-4174},

year  = {2019},

date = {2019-01-01},

journal = {Expert Systems with Applications},

volume = {136},

pages = {1-11},

abstract = {Recent works have shown that Convolutional Neural Networks (CNNs), because of their effectiveness in feature extraction and classification tasks, are suitable tools to address the Facial Expression Recognition (FER) problem. Further, it has been pointed out how ensembles of CNNs allow improving classification accuracy. Nevertheless, a detailed experimental analysis on how ensembles of CNNs could be effectively generated in the FER context has not been performed yet, although it would have considerable value for improving the results obtained in the FER task. This paper aims to present an extensive investigation on different aspects of the ensemble generation, focusing on the factors that influence the classification accuracy on the FER context. In particular, we evaluate several strategies for the ensemble generation, different aggregation schemes, and the dependence upon the number of base classifiers in the ensemble. The final objective is to provide some indications for building up effective ensembles of CNNs. Specifically, we observed that exploiting different sources of variability is crucial for the improvement of the overall accuracy. To this aim, pre-processing and pre-training procedures are able to provide a satisfactory variability across the base classifiers, while the use of different seeds does not appear as an effective solution. Bagging ensures a high ensemble gain, but the overall accuracy is limited by poor-performing base classifiers. The impact of increasing the ensemble size specifically depends on the adopted strategy, but also in the best case the performance gain obtained by involving additional base classifiers becomes not significant beyond a certain limit size, thus suggesting to avoid very large ensembles. Finally, the classic averaging voting proves to be an appropriate aggregation scheme, achieving accuracy values comparable to or slightly better than the other experimented operators.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Barsacchi2019367,

title = {Optimizing Partition Granularity, Membership Function Parameters, and Rule Bases of Fuzzy Classifiers for Big Data by a Multi-objective Evolutionary Approach},

author = {Marco Barsacchi and Alessio Bechini and Pietro Ducange and Francesco Marcelloni},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85059518114&doi=10.1007%2fs12559-018-9613-6&partnerID=40&md5=f5c60b61bc25cd98bc56fc4c4deccbe3},

doi = {10.1007/s12559-018-9613-6},

year  = {2019},

date = {2019-01-01},

journal = {Cognitive Computation},

volume = {11},

number = {3},

pages = {367 – 387},

abstract = {Classical data mining algorithms are considered inadequate to manage the volume, variety, velocity, and veracity aspects of big data. The advent of a number of open-source cluster-computing frameworks has opened new interesting perspectives for handling the volume and velocity features. In this context, thanks to their capability of coping with vague and imprecise information, distributed fuzzy models appear to be particularly suitable for handling the variety and veracity features of big data. Moreover, the interpretability of fuzzy models may assume a particular relevance in the context of big data mining. In this work, we propose a novel approach for generating, out of big data, a set of fuzzy rule–based classifiers characterized by different optimal trade-offs between accuracy and interpretability. We extend a state-of-the-art distributed multi-objective evolutionary learning scheme, implemented under the Apache Spark environment. In particular, we exploit a recently proposed distributed fuzzy decision tree learning approach for generating an initial rule base that serves as input to the evolutionary process. Furthermore, we integrate the evolutionary learning scheme with an ad hoc strategy for the granularity learning of the fuzzy partitions, along with the optimization of both the rule base and the fuzzy set parameters. Experimental investigations show that the proposed approach is able to generate fuzzy rule–based classifiers that are significantly less complex than the ones generated by the original multi-objective evolutionary learning scheme, while keeping the same accuracy levels. © 2019, Springer Science+Business Media, LLC, part of Springer Nature.},

note = {Cited by: 13},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{DANDREA2019209,

title = {Monitoring the public opinion about the vaccination topic from tweets analysis},

author = {Eleonora D'Andrea and Pietro Ducange and Alessio Bechini and Alessandro Renda and Francesco Marcelloni},

url = {https://www.sciencedirect.com/science/article/pii/S0957417418305803},

doi = {https://doi.org/10.1016/j.eswa.2018.09.009},

issn = {0957-4174},

year  = {2019},

date = {2019-01-01},

journal = {Expert Systems with Applications},

volume = {116},

pages = {209-226},

abstract = {The paper presents an intelligent system to automatically infer trends in the public opinion regarding the stance towards the vaccination topic: it enables the detection of significant opinion shifts, which can be possibly explained with the occurrence of specific social context-related events. The Italian setting has been taken as the reference use case. The source of information exploited by the system is represented by the collection of vaccine-related tweets, fetched from Twitter according to specific criteria; subsequently, tweets undergo a textual elaboration and a final classification to detect the expressed stance towards vaccination (i.e. in favor, not in favor, and neutral). In tuning the system, we tested multiple combinations of different text representations and classification approaches: the best accuracy was achieved by the scheme that adopts the bag-of-words, with stemmed n-grams as tokens, for text representation and the support vector machine model for the classification. By presenting the results of a monitoring campaign lasting 10 months, we show that the system may be used to track and monitor the public opinion about vaccination decision making, in a low-cost, real-time, and quick fashion. Finally, we also verified that the proposed scheme for continuous tweet classification does not seem to suffer particularly from concept drift, considering the time span of the monitoring campaign.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{8610271,

title = {Evolutionary Fuzzy Systems for Explainable Artificial Intelligence: Why, When, What for, and Where to?},

author = {Alberto Fernandez and Francisco Herrera and Oscar Cordon and Maria Jose del Jesus and Francesco Marcelloni},

doi = {10.1109/MCI.2018.2881645},

year  = {2019},

date = {2019-01-01},

journal = {IEEE Computational Intelligence Magazine},

volume = {14},

number = {1},

pages = {69-81},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Pecori201996,

title = {Efficient computation of key performance indicators in a distance learning university},

author = {Riccardo Pecori and Vincenzo Suraci and Pietro Ducange},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85062468115&doi=10.1108%2fIDD-09-2018-0050&partnerID=40&md5=8e1a448aefea0f88fe845827da6b194d},

doi = {10.1108/IDD-09-2018-0050},

year  = {2019},

date = {2019-01-01},

journal = {Information Discovery and Delivery},

volume = {47},

number = {2},

pages = {96 – 105},

abstract = {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. © 2019, Emerald Publishing Limited.},

note = {Cited by: 6},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{DUCANGE201971,

title = {An effective Decision Support System for social media listening based on cross-source sentiment analysis models},

author = {Pietro Ducange and Michela Fazzolari and Marinella Petrocchi and Massimo Vecchio},

url = {https://www.sciencedirect.com/science/article/pii/S0952197618302252},

doi = {https://doi.org/10.1016/j.engappai.2018.10.014},

issn = {0952-1976},

year  = {2019},

date = {2019-01-01},

journal = {Engineering Applications of Artificial Intelligence},

volume = {78},

pages = {71-85},

abstract = {Nowadays, companies and enterprises are more and more incline to exploit the pervasive action of on-line social media, such as Facebook, Twitter and Instagram. Indeed, several promotional and marketing campaigns are carried out by concurrently adopting several social medial channels. These campaigns reach very quickly a wide range of different categories of users, since many people spend most of their time on on-line social media during the day. In this work, a Decision Support System (DSS) is presented, which is able to efficiently support companies and enterprises in managing promotional and marketing campaigns on multiple social media channels. The proposed DSS continuously monitors multiple social channels, by collecting social media users’ comments on promotions, products, and services. Then, through the analysis of these data, the DSS estimates the reputation of brands related to specific companies and provides feedbacks about a digital marketing campaign. The core of the proposed DSS is a Sentiment Analysis Engine (SAE), which is able to estimate the users’ sentiment in terms of positive, negative or neutral polarity, expressed in a comment. The SAE is based on a machine learning text classification model, which is initially trained by using real data streams coming from different social media platforms specialized in user reviews (e.g., TripAdvisor). Then, the monitoring and the sentiment classification are carried out on the comments continuously extracted from a set of public pages and channels of publicly available social networking platforms (e.g., Facebook, Twitter, and Instagram). This approach is labeled as cross-source sentiment analysis. After some discussions on the design and the implementation of the proposed DSS, some results are shown about the experimentation of the proposed DSS on two scenarios, namely restaurants and consumer electronics online shops. Specifically, first the application of effective sentiment analysis models, created relying on user reviews is discussed: the models achieve accuracies higher than 90%. Then, such models are embedded into the proposed DSS. Finally, the results of a social listening campaign are presented. The campaign was carried out by fusing data streams coming from real social channels of popular companies belonging to the selected scenarios.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{8918400,

title = {Photonic Neural Networks: A Survey},

author = {Lorenzo De Marinis and Marco Cococcioni and Piero Castoldi and Nicola Andriolli},

doi = {10.1109/ACCESS.2019.2957245},

year  = {2019},

date = {2019-01-01},

journal = {IEEE Access},

volume = {7},

pages = {175827-175841},

keywords = {},

pubstate = {published},

tppubtype = {article}

}