Selected Publications

Note: this page considers publications from 2008 onwards. For a list of previous selected publications, please consult our older website.

Authors: Type:

2016

  • [PDF] [DOI] S. Scardapane, D. Comminiello, M. Scarpiniti, and A. Uncini, "A Semi-supervised Random Vector Functional-Link Network based on the Transductive Framework," Information Sciences, vol. 364-365, pp. 156-166, 2016.
    [Bibtex]
    @Article{scardapane2016semisupervised,
    Title = {{A} {S}emi-Supervised {R}andom {V}ector {F}unctional-{L}ink {N}etwork Based on the {T}ransductive {F}ramework},
    Author = {Scardapane, S. and Comminiello, D. and Scarpiniti, M. and Uncini, A.},
    Journal = {{I}nformation {S}ciences},
    Year = {2016},
    Month = {October},
    Pages = {156--166},
    Volume = {364-365},
    Abstract = {Semi-supervised learning (SSL) is the problem of learning a function with only a partially labeled training set. It has considerable practical interest in applications where labeled data is costly to obtain, while unlabeled data is abundant. One approach to SSL in the case of binary classification is inspired by work on transductive learning (TL) by Vapnik. It has been applied prevalently using support vector machines (SVM) as the base learning algorithm, giving rise to the so-called transductive SVM (TR-SVM). The resulting optimization problem, however, is highly non-convex and complex to solve. In this paper, we propose an alternative semi-supervised training algorithm based on the TL theory, namely semi-supervised random vector functional-link (RVFL) network, which is able to obtain state-of-the-art performance, while resulting in a standard convex optimization problem. In particular we show that, thanks to the characteristics of RVFLs networks, the resulting optimization problem can be safely approximated with a standard quadratic programming problem solvable in polynomial time. A wide range of experiments validate our proposal. As a comparison, we also propose a semi-supervised algorithm for RVFLs based on the theory of manifold regularization.},
    Doi = {10.1016/j.ins.2015.07.060},
    }
  • [PDF] [DOI] M. Scarpiniti, D. Comminiello, G. Scarano, R. Parisi, and A. Uncini, "Steady-State Performance of Spline Adaptive Filters," IEEE Transactions on Signal Processing, vol. 64, iss. 4, pp. 816-828, 2016.
    [Bibtex]
    @Article{scarpiniti2016steadystate,
    Title = {{S}teady-{S}tate {P}erformance of {S}pline {A}daptive {F}ilters},
    Author = {Scarpiniti, M. and Comminiello, D. and Scarano, G. and Parisi, R. and Uncini, A.},
    Journal = {{IEEE} {T}ransactions on {S}ignal {P}rocessing},
    Year = {2016},
    Month = {February},
    Number = {4},
    Pages = {816--828},
    Volume = {64},
    Abstract = {Recently, a novel class of nonlinear adaptive filters, called spline adaptive filters (SAFs), has been introduced and demonstrated to be very effective in many practical applications. The learning rules of these architectures are based on the least mean square (LMS) algorithm. In order to provide theoretical foundation to the SAF, in this paper we provide a steady-state performance evaluation. In particular, after the stochastic analysis of the mean behavior of the SAF approach under the Gaussian assumption, the analytical derivation of the theoretical excess mean square error (EMSE) and the normalized misadjustment are derived and discussed. The proposed analysis of EMSE and misadjustment is based on the energy conservation approach that has been extended to SAF architecture. The derived theoretical analysis allows to accurately predict the steady-state performance. Therefore, some properties for the correct choice of filter parameters are also provided. Experimental results demonstrate the effectiveness of the analysis results.},
    Doi = {10.1109/TSP.2015.2493986},
    }
  • [PDF] [DOI] S. Scardapane, M. Panella, D. Comminiello, A. Hussain, and A. Uncini, "Distributed reservoir computing with sparse readouts [research frontier]," IEEE Computational Intelligence Magazine, vol. 11, iss. 4, pp. 59-70, 2016.
    [Bibtex]
    @article{scardapane2016distributed,
    title={Distributed Reservoir Computing with Sparse Readouts [Research Frontier]},
    author={Scardapane, Simone and Panella, Massimo and Comminiello, Danilo and Hussain, Amir and Uncini, Aurelio},
    journal={{IEEE} {C}omputational {I}ntelligence {M}agazine},
    volume={11},
    number={4},
    pages={59--70},
    year={2016},
    publisher={IEEE},
    doi={http://dx.doi.org/10.1109/MCI.2016.2601759}
    }
  • [PDF] [DOI] S. Scardapane, D. Wang, and M. Panella, "A decentralized training algorithm for echo state networks in distributed big data applications," Neural Networks, vol. 78, pp. 65-74, 2016.
    [Bibtex]
    @article{scardapane2016decentralized,
    title={A decentralized training algorithm for echo state networks in distributed big data applications},
    author={Scardapane, Simone and Wang, Dianhui and Panella, Massimo},
    journal={{N}eural {N}etworks},
    volume={78},
    pages={65--74},
    year={2016},
    publisher={Elsevier},
    doi={http://dx.doi.org/10.1016/j.neunet.2015.07.006}
    }
  • [PDF] [DOI] S. Scardapane, R. Fierimonte, P. Di Lorenzo, M. Panella, and A. Uncini, "Distributed semi-supervised support vector machines," Neural Networks, vol. 80, pp. 43-52, 2016.
    [Bibtex]
    @article{scardapane2016distributedsemi,
    title={Distributed semi-supervised support vector machines},
    author={Scardapane, Simone and Fierimonte, Roberto and Di Lorenzo, Paolo and Panella, Massimo and Uncini, Aurelio},
    journal={{N}eural {N}etworks},
    volume={80},
    pages={43--52},
    year={2016},
    publisher={Elsevier},
    doi={http://dx.doi.org/10.1016/j.neunet.2016.04.007}
    }
  • [PDF] [DOI] R. Fierimonte, S. Scardapane, A. Uncini, and M. Panella, "Fully decentralized semi-supervised learning via privacy-preserving matrix completion," IEEE Transactions on Neural Networks and Learning Systems, 2016.
    [Bibtex]
    @article{fierimonte2016fully,
    title={Fully decentralized semi-supervised learning via privacy-preserving matrix completion},
    author={Fierimonte, Roberto and Scardapane, Simone and Uncini, Aurelio and Panella, Massimo},
    journal={{IEEE} {T}ransactions on {N}eural {N}etworks and {L}earning {S}ystems},
    year={2016},
    publisher={IEEE},
    doi={http://dx.doi.org/10.1109/TNNLS.2016.2597444}
    }

2015

  • [PDF] [DOI] D. Comminiello, S. Cecchi, M. Scarpiniti, M. Gasparini, L. Romoli, F. Piazza, and A. Uncini, "Intelligent Acoustic Interfaces with Multisensor Acquisition for Immersive Reproduction," IEEE Transactions on Multimedia, vol. 17, iss. 8, pp. 1262-1272, 2015.
    [Bibtex]
    @Article{comminiello2015intelligent,
    Title = {{I}ntelligent {A}coustic {I}nterfaces with {M}ultisensor {A}cquisition for {I}mmersive {R}eproduction},
    Author = {Comminiello, D. and Cecchi, S. and Scarpiniti, M. and Gasparini, M. and Romoli, L. and Piazza, F. and Uncini, A.},
    Journal = {{IEEE} {T}ransactions on {M}ultimedia},
    Year = {2015},
    Month = {August},
    Number = {8},
    Pages = {1262--1272},
    Volume = {17},
    Abstract = {Immersive speech communication systems have been gaining increasing attention due to their ability to reproduce enhanced acoustic images, and thus achieving good performance in terms of sound quality and accuracy. In this context, a fundamental role is played by intelligent acoustic interfaces (IAIs), which aim at acquiring and/or reproducing desired acoustic information with enhanced perception. The recent widespread availability of multimedia devices, equipped with different kind of sensors, has broadened the range of data processing methods, thus giving a chance for developing advanced IAIs. In this paper, we propose an immersive communication system composed of two IAIs: the first one exploits microphones and cameras, together with a signal processing system, to reduce unwanted noise and enhance the speech quality of the desired information in the transmitting room; the second one is an advanced reproduction system based on a loudspeaker array and on an effective wave field synthesis technique capable of reproducing the spatial perception of the desired speech source in the receiving room. The whole system has been assessed in simulated and real immersive communication scenarios: objective and subjective evaluations have been shown the effectiveness of the proposed system.},
    Doi = {10.1109/TMM.2015.2442151},
    }
  • [PDF] [DOI] D. Comminiello, M. Scarpiniti, S. Scardapane, R. Parisi, and A. Uncini, "Improving Nonlinear Modeling Capabilities of Functional Link Adaptive Filters," Neural Networks, vol. 69, pp. 51-59, 2015.
    [Bibtex]
    @Article{comminiello2015improving,
    Title = {{I}mproving {N}onlinear {M}odeling {C}apabilities of {F}unctional {L}ink {A}daptive {F}ilters},
    Author = {Comminiello, D. and Scarpiniti, M. and Scardapane, S. and Parisi, R. and Uncini, A.},
    Journal = {{N}eural {N}etworks},
    Year = {2015},
    Month = {September},
    Pages = {51--59},
    Volume = {69},
    Abstract = {The functional link adaptive filter (FLAF) represents an effective solution for online nonlinear modeling problems. In this paper, we take into account a FLAF-based architecture, which separates the adaptation of linear and nonlinear elements, and we focus on the nonlinear branch to improve the modeling performance. In particular, we propose a new model that involves an adaptive combination of filters downstream of the nonlinear expansion. Such combination leads to a cooperative behavior of the whole architecture, thus yielding a performance improvement, particularly in the presence of strong nonlinearities. An advanced architecture is also proposed involving the adaptive combination of multiple filters on the nonlinear branch. The proposed models are assessed in different nonlinear modeling problems, in which their effectiveness and capabilities are shown.},
    Doi = {10.1016/j.neunet.2015.05.002},
    }
  • [PDF] [DOI] S. Scardapane, D. Comminiello, M. Scarpiniti, and A. Uncini, "Online sequential extreme learning machine with kernels," IEEE Transactions on Neural Networks and Learning Systems, vol. 26, iss. 9, pp. 2214-2220, 2015.
    [Bibtex]
    @article{scardapane2015online,
    title={Online sequential extreme learning machine with kernels},
    author={Scardapane, Simone and Comminiello, Danilo and Scarpiniti, Michele and Uncini, Aurelio},
    journal={{IEEE} {T}ransactions on {N}eural {N}etworks and {L}earning {S}ystems},
    volume={26},
    number={9},
    pages={2214--2220},
    year={2015},
    publisher={IEEE},
    doi={http://dx.doi.org/10.1109/TNNLS.2016.2597444}
    }
  • [PDF] [DOI] S. Scardapane, M. Scarpiniti, M. Bucciarelli, F. Colone, M. V. Mansueto, and R. Parisi, "Microphone Array Based Classification for Security Monitoring in Unstructured Environments," AEĂś International Journal of Electronics and Communications, vol. 69, iss. 11, pp. 1715-1723, 2015.
    [Bibtex]
    @Article{scardapane2015microphone,
    Title = {{M}icrophone {A}rray {B}ased {C}lassification for {S}ecurity {M}onitoring in {U}nstructured {E}nvironments},
    Author = {Scardapane, S. and Scarpiniti, M. and Bucciarelli, M. and Colone, F. and Mansueto, M. V. and Parisi, R.},
    Journal = {{AE\"U} – {I}nternational {J}ournal of {E}lectronics and {C}ommunications},
    Year = {2015},
    Month = {November},
    Number = {11},
    Pages = {1715--1723},
    Volume = {69},
    Abstract = {The aim of this paper is to describe a novel security system able to localize and classify audio sources in an outdoor environment. Its primary intended use is for security monitoring in severe scenarios, and it has been designed to cope with a large set of heterogeneous objects, including weapons, human speakers and vehicles. The system is the result of a research project sponsored by the Italian Ministry of Defense. It is composed of a large squared array of 864 microphones arranged in a rectangular lattice, whose input is processed using a classical delay-and-sum beamformer. The result of this localization process is elaborated by a complex multi-level classification system designed in a modular fashion. In this paper, after presenting the details of the system's design, with a particular emphasis on the innovative aspects that are introduced with respect to the state-of-the-art, we provide an extensive set of simulations showing the effectiveness of the proposed architecture. We conclude by describing the current limits of the system, and the projected further developments.},
    Doi = {10.1016/j.aeue.2015.08.007},
    }
  • [PDF] [DOI] S. Scardapane, D. Wang, M. Panella, and A. Uncini, "Distributed Learning for Random Vector Functional-Link Networks," Information Sciences, vol. 301, pp. 271-284, 2015.
    [Bibtex]
    @Article{scardapane2015distributed,
    Title = {{D}istributed {L}earning for {R}andom {V}ector {F}unctional-{L}ink {N}etworks},
    Author = {Scardapane, Simone and Wang, Dianhui and Panella, Massimo and Uncini, Aurelio},
    Journal = {{I}nformation {S}ciences},
    Year = {2015},
    Pages = {271--284},
    Volume = {301},
    Doi = {10.1016/j.ins.2015.01.007},
    Publisher = {Elsevier}
    }
  • [PDF] [DOI] M. Scarpiniti, D. Comminiello, R. Parisi, and A. Uncini, "Nonlinear system identification using IIR Spline Adaptive Filters," Signal Processing, vol. 108, pp. 30-35, 2015.
    [Bibtex]
    @Article{scarpiniti2015nonlinear,
    Title = {{N}onlinear system identification using {IIR} {S}pline {A}daptive {F}ilters},
    Author = {Michele Scarpiniti and Danilo Comminiello and Raffaele Parisi and Aurelio Uncini},
    Journal = {{S}ignal {P}rocessing},
    Year = {2015},
    Number = {0},
    Pages = {30 - 35},
    Volume = {108},
    Doi = {http://dx.doi.org/10.1016/j.sigpro.2014.08.045},
    }
  • [PDF] [DOI] M. Scarpiniti, D. Comminiello, R. Parisi, and A. Uncini, "Novel Cascade Spline Architectures for the Identification of Nonlinear Systems," IEEE Transactions on Circuits and Systems---I: Regular Papers, vol. 62, iss. 7, pp. 1825-1835, 2015.
    [Bibtex]
    @Article{scarpiniti2015novel,
    Title = {{N}ovel {C}ascade {S}pline {A}rchitectures for the {I}dentification of {N}onlinear {S}ystems},
    Author = {Scarpiniti, M. and Comminiello, D. and Parisi, R. and Uncini, A.},
    Journal = {{IEEE} {T}ransactions on {C}ircuits and {S}ystems---{I}: {R}egular {P}apers},
    Year = {2015},
    Month = {July},
    Number = {7},
    Pages = {1825--1835},
    Volume = {62},
    Abstract = {In this paper two novel nonlinear cascade adaptive architectures, here called sandwich models, suitable for the identification of general nonlinear systems are presented. The proposed architectures rely on the combination of structural blocks, each one implementing a linear filter or a memoryless nonlinear function. All the nonlinear functions involved in the adaptation process are based on spline functions and can be easily modified during learning using gradient-based techniques.
    In particular, a simple form of the on-line adaptation algorithms for the two architectures is derived. In addition, we analytically obtain a bound for the selection of the learning rates involved in the learning algorithms, in order to guarantee a convergence towards a minimum of the cost function. Finally, some experimental results demonstrate the effectiveness of the proposed method.},
    Doi = {10.1109/TCSI.2015.2423791},
    }

2014

  • [PDF] [DOI] E. Baccarelli, F. Chiti, N. Cordeschi, R. Fantacci, D. Marabissi, R. Parisi, and A. Uncini, "Green multimedia wireless sensor networks: distributed intelligent data fusion, in-network processing, and optimized resource management," IEEE Wireless Communications, vol. 21, iss. 4, pp. 20-26, 2014.
    [Bibtex]
    @Article{baccarelli2014green,
    Title = {{G}reen multimedia wireless sensor networks: distributed intelligent data fusion, in-network processing, and optimized resource management},
    Author = {Baccarelli, E. and Chiti, F. and Cordeschi, N. and Fantacci, R. and Marabissi, D. and Parisi, R. and Uncini, A.},
    Journal = {{IEEE} {W}ireless {C}ommunications},
    Year = {2014},
    Month = {August},
    Number = {4},
    Pages = {20-26},
    Volume = {21},
    Doi = {10.1109/MWC.2014.6882292},
    ISSN = {1536-1284}
    }
  • [PDF] [DOI] D. Comminiello, M. Scarpiniti, L. A. Azpicueta-Ruiz, J. Arenas-GarcĂ­a, and A. Uncini, "Nonlinear Acoustic Echo Cancellation Based on Sparse Functional Link Representations," IEEE/ACM Transactions on Audio, Speech and Language Processing, vol. 22, iss. 7, pp. 1172-1183, 2014.
    [Bibtex]
    @Article{comminiello2014nonlinear,
    Title = {{N}onlinear {A}coustic {E}cho {C}ancellation {B}ased on {S}parse {F}unctional {L}ink {R}epresentations},
    Author = {Comminiello, Danilo and Scarpiniti, Michele and Azpicueta-Ruiz, Luis A. and Arenas-Garc\'{\i}a, Jer\'{o}nimo and Uncini, Aurelio},
    Journal = {{IEEE}/{ACM} {T}ransactions on {A}udio, {S}peech and {L}anguage {P}rocessing},
    Year = {2014},
    Month = jul,
    Number = {7},
    Pages = {1172--1183},
    Volume = {22},
    Doi = {10.1109/TASLP.2014.2324175},
    Issue_date = {July 2014},
    Numpages = {12},
    Publisher = {IEEE Press}
    }
  • [PDF] [DOI] M. Scarpiniti, D. Comminiello, R. Parisi, and A. Uncini, "Hammerstein uniform cubic spline adaptive filters: Learning and convergence properties," Signal Processing, vol. 100, pp. 112-123, 2014.
    [Bibtex]
    @Article{scarpiniti2014hammerstein,
    Title = {{H}ammerstein uniform cubic spline adaptive filters: {L}earning and convergence properties },
    Author = {Michele Scarpiniti and Danilo Comminiello and Raffaele Parisi and Aurelio Uncini},
    Journal = {{S}ignal {P}rocessing },
    Year = {2014},
    Number = {0},
    Pages = {112 - 123},
    Volume = {100},
    Doi = {http://dx.doi.org/10.1016/j.sigpro.2014.01.019},
    }

2013

  • [PDF] [DOI] D. Comminiello, M. Scarpiniti, L. A. Azpicueta-Ruiz, J. Arenas-Garcia, and A. Uncini, "Functional Link Adaptive Filters for Nonlinear Acoustic Echo Cancellation," IEEE Transactions on Audio, Speech, and Language Processing, vol. 21, iss. 7, pp. 1502-1512, 2013.
    [Bibtex]
    @Article{comminiello2013functional,
    Title = {{F}unctional {L}ink {A}daptive {F}ilters for {N}onlinear {A}coustic {E}cho {C}ancellation},
    Author = {Comminiello, D. and Scarpiniti, M. and Azpicueta-Ruiz, L.A. and Arenas-Garcia, J. and Uncini, A.},
    Journal = {{IEEE} {T}ransactions on {A}udio, {S}peech, and {L}anguage {P}rocessing},
    Year = {2013},
    Month = {July},
    Number = {7},
    Pages = {1502-1512},
    Volume = {21},
    Doi = {10.1109/TASL.2013.2255276},
    ISSN = {1558-7916}
    }
  • [PDF] [DOI] D. Comminiello, M. Scarpiniti, R. Parisi, and A. Uncini, "Combined adaptive beamforming schemes for nonstationary interfering noise reduction," Signal Processing, vol. 93, iss. 12, pp. 3306-3318, 2013.
    [Bibtex]
    @Article{comminiello2013combined,
    Title = {{C}ombined adaptive beamforming schemes for nonstationary interfering noise reduction },
    Author = {Danilo Comminiello and Michele Scarpiniti and Raffaele Parisi and Aurelio Uncini},
    Journal = {{S}ignal {P}rocessing },
    Year = {2013},
    Note = {Special Issue on Advances in Sensor Array Processing in Memory of Alex B. Gershman},
    Number = {12},
    Pages = {3306 - 3318},
    Volume = {93},
    Doi = {http://dx.doi.org/10.1016/j.sigpro.2013.05.014},
    }
  • [PDF] D. Comminiello, M. Scarpiniti, R. Parisi, and A. Uncini, "Convergence properties of nonlinear functional link adaptive filters," Electronics Letters, vol. 49, p. 873-875(2), 2013.
    [Bibtex]
    @Article{comminiello2013convergence,
    Title = {{C}onvergence properties of nonlinear functional link adaptive filters},
    Author = {Comminiello, D. and Scarpiniti, M. and Parisi, R. and Uncini, A.},
    Journal = {{E}lectronics {L}etters},
    Year = {2013},
    Month = {July},
    Pages = {873-875(2)},
    Volume = {49},
    Issue = {14},
    }
  • [PDF] D. Comminiello, M. Scarpiniti, R. Parisi, and A. Uncini, "Intelligent Acoustic Interfaces for Immersive Audio," in Audio engineering society convention 134, 2013.
    [Bibtex]
    @Conference{comminiello2013intelligent,
    Title = {{I}ntelligent {A}coustic {I}nterfaces for {I}mmersive {A}udio},
    Author = {Comminiello, Danilo and Scarpiniti, Michele and Parisi, Raffaele and Uncini, Aurelio},
    Booktitle = {Audio Engineering Society Convention 134},
    Year = {2013},
    Month = {May},
    Url = {http://www.aes.org/e-lib/browse.cfm?elib=16798}
    }
  • [PDF] M. Scarpiniti, D. Comminiello, R. Parisi, and A. Uncini, "Nonlinear spline adaptive filtering," Signal Processing, vol. 93, iss. 4, pp. 772-783, 2013.
    [Bibtex]
    @Article{scarpiniti2013nonlinear,
    Title = {{N}onlinear spline adaptive filtering},
    Author = {Scarpiniti, Michele and Comminiello, Danilo and Parisi, Raffaele and Uncini, Aurelio},
    Journal = {{S}ignal {P}rocessing},
    Year = {2013},
    Number = {4},
    Pages = {772--783},
    Volume = {93},
    Publisher = {Elsevier}
    }

2012

  • [PDF] A. Maesa, F. Garzia, M. Scarpiniti, and R. Cusani, "Text Independent Automatic Speaker Recognition System Using Mel-Frequency Cepstrum Coefficient and Gaussian Mixture Models," Journal of Information Security, vol. 3, iss. 04, p. 335, 2012.
    [Bibtex]
    @Article{maesa2012text,
    Title = {{T}ext {I}ndependent {A}utomatic {S}peaker {R}ecognition {S}ystem {U}sing {M}el-{F}requency {C}epstrum {C}oefficient and {G}aussian {M}ixture {M}odels},
    Author = {Maesa, Alfredo and Garzia, Fabio and Scarpiniti, Michele and Cusani, Roberto},
    Journal = {{J}ournal of {I}nformation {S}ecurity},
    Year = {2012},
    Number = {04},
    Pages = {335},
    Volume = {3},
    Publisher = {Scientific Research Publishing}
    }
  • [PDF] [DOI] R. Parisi, F. Camoes, M. Scarpiniti, and A. Uncini, "Cepstrum Prefiltering for Binaural Source Localization in Reverberant Environments," IEEE Signal Processing Letters, vol. 19, iss. 2, pp. 99-102, 2012.
    [Bibtex]
    @Article{parisi2012cepstrum,
    Title = {{C}epstrum {P}refiltering for {B}inaural {S}ource {L}ocalization in {R}everberant {E}nvironments},
    Author = {Parisi, R. and Camoes, F. and Scarpiniti, M. and Uncini, A.},
    Journal = {{IEEE} {S}ignal {P}rocessing {L}etters},
    Year = {2012},
    Month = {Feb},
    Number = {2},
    Pages = {99-102},
    Volume = {19},
    Doi = {10.1109/LSP.2011.2180376},
    }

2010

  • [PDF] M. Scarpiniti, R. Parisi, and A. Uncini, "Flexible estimation of joint probability and joint cumulative density functions," Electronics Letters, vol. 46, iss. 2, pp. 1084-1086, 2010.
    [Bibtex]
    @Article{scarpiniti2010flexible,
    Title = {{F}lexible estimation of joint probability and joint cumulative density functions},
    Author = {Scarpiniti, M. and Parisi, R. and Uncini, A.},
    Journal = {{E}lectronics {L}etters},
    Year = {2010},
    Month = {July},
    Number = {2},
    Pages = {1084--1086},
    Volume = {46},
    Issue = {15},
    }

2009

  • [PDF] [DOI] M. Scarpiniti, R. Parisi, and A. Uncini, "Flexible Estimation of Probability and Cumulative Density Functions," Electronics Letters, vol. 45, iss. 21, pp. 1095-1096, 2009.
    [Bibtex]
    @Article{scarpiniti2009flexible,
    Title = {{F}lexible {E}stimation of {P}robability and {C}umulative {D}ensity {F}unctions},
    Author = {Scarpiniti, M. and Parisi, R. and Uncini, A.},
    Journal = {{E}lectronics {L}etters},
    Year = {2009},
    Month = {October},
    Number = {21},
    Pages = {1095--1096},
    Volume = {45},
    Abstract = {A novel, simple and effective algorithm for the estimation of the probability density function and cumulative density function is presented. The algorithm is based on an information maximisation approach. The nonlinear function involved in the algorithm is adaptively modified during learning and is implemented by using a spline function.},
    Doi = {10.1049/el.2009.1274}
    }

2008

  • [PDF] [DOI] M. Scarpiniti, D. Vigliano, R. Parisi, and A. Uncini, "Generalized Splitting Functions for Blind Separation of Complex Signals," Neurocomputing, vol. 71, iss. 10-12, pp. 2245-2270, 2008.
    [Bibtex]
    @Article{scarpiniti2008generalized,
    Title = {{G}eneralized {S}plitting {F}unctions for {B}lind {S}eparation of {C}omplex {S}ignals},
    Author = {M. Scarpiniti and D. Vigliano and R. Parisi and A. Uncini},
    Journal = {{N}eurocomputing},
    Year = {2008},
    Month = {June},
    Number = {10-12},
    Pages = {2245--2270},
    Volume = {71},
    Abstract = {This paper proposes the Blind Separation of complex signals using a novel neural network architecture based on an adaptive non-linear bi-dimensional activation function; the separation is obtained maximizing the output joint entropy. Avoiding the restriction due to the Louiville’s theorem, the activation function is composed by a couple of bi-dimensional spline functions, one for the real and one for the imaginary part of the signal. The surface of this function is flexible and it is adaptively modified according to the learning process performed by a gradient-based technique.
    The use of the bi-dimensional spline defines a new class of flexible activation functions which are bounded and locally analytic. This paper aims at demonstrate that this novel bi-dimentional complex activation function outperforms the separation in every environment in which the real and the imaginary part of the complex signal are not decorrelated. This situation is realistic in a large number of cases.},
    Doi = {10.1016/j.neucom.2007.07.037},
    }
  • [PDF] [DOI] D. Vigliano, M. Scarpiniti, R. Parisi, and A. Uncini, "Flexible Nonlinear Blind Signal Separation in the Complex Domain," International Journal of Neural Systems, vol. 18, iss. 2, pp. 105-122, 2008.
    [Bibtex]
    @Article{vigliano2008flexible,
    Title = {{F}lexible {N}onlinear {B}lind {S}ignal {S}eparation in the {C}omplex {D}omain},
    Author = {Vigliano, D. and Scarpiniti, M. and Parisi, R. and Uncini, A.},
    Journal = {{I}nternational {J}ournal of {N}eural {S}ystems},
    Year = {2008},
    Month = {April},
    Number = {2},
    Pages = {105--122},
    Volume = {18},
    Abstract = {This paper introduces an Independent Component Analysis (ICA) approach to the separation of nonlinear mixtures in the complex domain. Source separation is performed by a complex INFOMAX approach. The neural network which realizes the separation employs the so called “Mirror Model” and is based on an adaptive activation function, whose shape is properly modified during learning. Nonlinear functions involved in the processing of complex signals are realized by pairs of spline neurons called “splitting functions”, working on the real and the imaginary part of the signal respectively. Theoretical proof of existence and uniqueness of the solution under proper assumptions is also provided. In particular a simple adaptation algorithm is derived and some experimental results that demonstrate the effectiveness of the proposed method are shown.},
    Doi = {10.1142/S0129065708001427},
    }