Raffaella Folli

Prof. Dr. Raffaella Folli

orcid

Research Focus & Metrics

Academic Career Length

21Years (2006-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
17 August 2020 in Sensors
Verified
Journal Article
Open access
PDF file
CCCiaran Cooney
Ciaran Cooney
AKAttila Korik
Attila Korik
RFRaffaella Folli
Raffaella Folli
DCDamien Coyle
Damien Coyle
Classification of electroencephalography (EEG) signals corresponding to imagined speech production is important for the development of a direct-speech brain–computer interface (DS-BCI). Deep learning (DL) has been utilized with great success across several domains. However, it remains an open question whether DL methods provide significant advances over traditional machine learning (ML) approaches for classification of imagined speech. Furthermore, hyperparameter (HP) optimization has been neglected in DL-EEG studies, resulting in the significance of its effects remaining uncertain. In this study, we aim to improve classification of imagined speech EEG by employing DL methods while also statistically evaluating the impact of HP optimization on classifier performance. We trained three distinct convolutional neural networks (CNN) on imagined speech EEG using a nested cross-validation approach to HP optimization. Each of the CNNs evaluated was designed specifically for EEG decoding. An imagined speech EEG dataset consisting of both words and vowels facilitated training on both sets independently. CNN results were compared with three benchmark ML methods: Support Vector Machine, Random Forest and regularized Linear Discriminant Analysis. Intra- and inter-subject methods of HP optimization were tested and the effects of HPs statistically analyzed. Accuracies obtained by the CNNs were significantly greater than the benchmark methods when trained on both datasets (words: 24.97%, p < 1 × 10–7, chance: 16.67%; vowels: 30.00%, p < 1 × 10–7, chance: 20%). The effects of varying HP values, and interactions between HPs and the CNNs were both statistically significant. The results of HP optimization demonstrate how critical it is for training CNNs to decode imagined speech.

30 March 2012 in Journal of Linguistics
Verified
Journal Article
Closed access
PDF file
RFRaffaella Folli
Raffaella Folli
HHHeidi Harley
Heidi Harley
This paper provides an analysis of Italian complex predicates formed by combining a feminine nominalization in -ataand one of three light verbs:fare‘make’,dare‘give’ andprendere‘take’. We show that the constraints governing the choice of light verb follow from a syntactic approach to argument structure, and that several interpretive differences between complex and simplex predicates formed from the same verb root can be accounted for in a compositional, bottom–up approach. These differences include variation in creation vs. affected interpretations of Theme objects, implications concerning the size of the event described, the (un)availability of a passive alternant, and the agentivity or lack thereof of the subject argument.

7 December 2021 in IEEE Transactions on Biomedical Engineering
Verified
Journal Article
Open access
CCCiaran Cooney
Ciaran Cooney
RFRaffaella Folli
Raffaella Folli
DCDamien Coyle
Damien Coyle
Objective: Brain-computer interfaces (BCI) studies are increasingly leveraging different attributes of multiple signal modalities simultaneously. Bimodal data acquisition protocols combining the temporal resolution of electroencephalography (EEG) with the spatial resolution of functional near-infrared spectroscopy (fNIRS) require novel approaches to decoding. Methods: We present an EEG-fNIRS Hybrid BCI that employs a new bimodal deep neural network architecture consisting of two convolutional sub-networks (subnets) to decode overt and imagined speech. Features from each subnet are fused before further feature extraction and classification. Nineteen participants performed overt and imagined speech in a novel cue-based paradigm enabling investigation of stimulus and linguistic effects on decoding. Results: Using the hybrid approach, classification accuracies (46.31% and 34.29% for overt and imagined speech, respectively (chance: 25%)) indicated a significant improvement on EEG used independently for imagined speech ( p = 0.020) while tending towards significance for overt speech ( p = 0.098). In comparison with fNIRS, significant improvements for both speech-types were achieved with bimodal decoding ( p <0.001). There was a mean difference of ∼12.02% between overt and imagined speech with accuracies as high as 87.18% and 53%. Deeper subnets enhanced performance while stimulus effected overt and imagined speech in significantly different ways. Conclusion: The bimodal approach was a significant improvement on unimodal results for several tasks. Results indicate the potential of multi-modal deep learning for enhancing neural signal decoding. Significance: This novel architecture can be used to enhance speech decoding from bimodal neural signals.

28 June 2006 in Studia Linguistica
Verified
Journal Article
Closed access
PDF file
RFRaffaella Folli
Raffaella Folli
HHHeidi Harley
Heidi Harley

1 July 2020 in Linguistic Inquiry
Verified
Journal Article
Closed access
RFRaffaella Folli
Raffaella Folli
HHHeidi Harley
Heidi Harley
We propose that the well-known verb-framed/satellite-framed variation observed by Talmy ( 1975 , 1985 , 2000 ) is a true syntactic parameter of a well-understood type: a head movement parameter. We claim that it depends on an uninterpretable feature bundled with the particular v head used in change-of-state constructions that forces the head of the Res(ult)P complement of v to undergo head movement to v in Italian. The technical apparatus employed is a feature-driven head movement parameter, of the same kind that accounts for the familiar V-to-T or T-to-C movement variation crosslinguistically. We argue that in Talmy’s class of verb-framed languages, head movement of the embedded Res head to change-of-state v is mandatory, just as head movement of v to finite T is mandatory in V-to-T movement languages. Unlike previous proposals, this approach does not ascribe a deficiency to verb-framed languages, either in their semantic composition inventory or in their inventory of structural operations, both deficiencies being prima facie implausible from a biolinguistic/Minimalist perspective.

1 March 2006 in Trends in Cognitive Sciences
Verified
Journal Article
Closed access
RFRaffaella Folli
Raffaella Folli
HHHeidi Harley
Heidi Harley