Biografia 

Lucia Migliorelli è Ricercatrice Tenure Track in Sistemi di Elaborazione delle Informazioni presso il Dipartimento di Scienze Politiche dell’Università degli Studi di Teramo, dove è docente dei corsi di "Sistemi Multimediali e Web per il Turismo" e "Informatizzazione dell’Azienda Sanitaria". Ha conseguito con Lode il Dottorato Europeo in Ingegneria dell’Informazione presso l’Università Politecnica delle Marche, dove si è precedentemente laureata in Biomedical Engineering con Lode. 

Ha svolto attività di ricerca presso istituzioni di rilievo internazionale, tra cui il Karlsruhe Institute of Technology (Germania) e l’Universidade do Minho (Portogallo), e collabora con l’Istituto Italiano di Tecnologia (IIT), dove è stata ricercatrice affiliata presso il Dipartimento di Robotica Avanzata sotto la supervisione del Dott. Leonardo De Mattos. È inoltre membro dei gruppi di ricerca VRAI (Vision, Robotics and Artificial Intelligence) e BIMS (Biomedical Imaging for Modeling and Simulation).

Svolge attività di peer review per numerose riviste scientifiche internazionali, tra cui IEEE Transactions on Biomedical Engineering, Multimedia Tools and Applications, Expert Systems and Applications, Computer Methods and Programs in Biomedicine e Computers in Biology and Medicine. Partecipa inoltre come revisore e membro del Program Committee in conferenze di rilievo internazionale, quali BMVC, ICIAP, IPCAI, IROS, EMBC e MESA.

Attività di ricerca

La ricerca di Lucia Migliorelli si concentra sullo sviluppo di algoritmi di apprendimento profondo per l'analisi di dati multimediali, in particolare per la stima della posa umana da immagini RGB-D e video di profondità, con applicazioni nel monitoraggio neonatale e post-ictus. In un’evoluzione verso la Green e Trustworthy AI, Lucia ha introdotto strategie per ridurre la complessità computazionale dei modelli, come rami temporanei di super-risoluzione rimossi in fase di test, e ha sperimentato il porting su dispositivi a basso costo (es. Jetson Nano). Più recentemente, si dedica allo studio del rumore e dei bias nelle annotazioni per la stima della posa, sviluppando algoritmi robusti in grado di selezionare in modo adattivo i campioni più affidabili per l'addestramento algoritmico.

Short bio

Lucia Migliorelli is a Tenure-Track Researcher in Computer Engineering at the Department of Political Science of the University of Teramo, where she teaches the courses "Informatizzazione dell’Azienda Sanitaria" and "Informatizzazione dell’Azienda Sanitaria". She earned her European Ph.D. in Information Engineering with Honours from the Marche Polytechnic University, where she had previously graduated with Honours in Biomedical Engineering.

She has carried out research activities at leading international institutions, including the Karlsruhe Institute of Technology (Germany) and the University of Minho (Portugal), and collaborates with the Italian Institute of Technology (IIT), where she served as an Affiliated Researcher at the Department of Advanced Robotics under the supervision of Dr. Leonardo De Mattos. She is also a member of the VRAI (Vision, Robotics and Artificial Intelligence) and BIMS (Biomedical Imaging for Modeling and Simulation) research groups.

Dr. Migliorelli serves as a peer reviewer for several international journals, including IEEE Transactions on Biomedical Engineering, Multimedia Tools and Applications, Expert Systems and Applications, Computer Methods and Programs in Biomedicine, and Computers in Biology and Medicine. She also acts as a reviewer and program committee member for major international conferences such as BMVC, ICIAP, IPCAI, IROS, EMBC, and MESA.

Research activity

Lucia Migliorelli's research focuses on the development of deep learning algorithms for multimedia data analysis, in particular for estimating human pose from RGB-D images and depth videos, with applications in neonatal and post-stroke monitoring. In an evolution towards Green and Trustworthy AI, Lucia has introduced strategies to reduce the computational complexity of models, such as temporary super-resolution branches removed during testing, and has experimented with porting to low-cost devices (e.g., Jetson Nano). More recently, she started working on noise and bias in annotations for pose estimation, developing robust algorithms capable of adaptively selecting the most reliable samples during training.

Contributi su rivista

• Chiara Baldini, Lucia Migliorelli, Daniele Berardini, Muhammad Adeel Azam, Claudio Sampieri, Alessandro Ioppi, Rakesh Srivastava, Giorgio Peretti e Leonardo S Mattos. “Improving real-time detection of laryngeal lesions in endoscopic images using a decoupled super-resolution enhanced YOLO”. In: Computer Methods and Programs in Biomedicine 260 (2025), p. 108539. doi: https://doi.org/10.1016/j.cmpb.2024.108539.
• Daniele Berardini, Lucia Migliorelli, Alessandro Galdelli e Manuel J Marín-Jiménez. “Edge artificial intelligence and super-resolution for enhanced weapon detection in video surveillance”. In: Engineering Applications of Artificial Intelligence 140 (2025), p. 109684. doi: https://doi.org/10.1016/j.engappai.2024.109684.
• Alessandro Cacciatore, Daniele Berardini, Vito Scaraggi, Adriano Mancini, Sara Moccia e Lucia Migliorelli. “Online Knowledge Distillation and Deep Supervision in HRNet: Green AI for Preterm Infants’ Pose Estimation”. In: ACM Transactions on Computing for Healthcare (lug. 2025). Just Accepted. doi: 10.1145/3757067. url: https://doi.org/10.1145/3757067.
• Ciro Benito Raggio, Mathias Krohmer Zabaleta, Nils Skupien, Oliver Blanck, Francesco Cicone, Giuseppe Lucio Cascini, Paolo Zaffino, Lucia Migliorelli e Maria Francesca Spadea. “FedSynthCTBrain: A federated learning framework for multi-institutional brain MRI-to-CT synthesis”. In: Computers in Biology and Medicine 192 (2025), p. 110160. doi: https://doi.org/10.1016/j.compbiomed.2025.110160.
• Daniele Berardini, Lucia Migliorelli, Alessandro Galdelli, Emanuele Frontoni, Adriano Mancini e Sara Moccia. “A deep-learning framework running on edge devices for handgun and knife detection from indoor video-surveillance cameras”. In: Multimedia Tools and Applications 83.7 (2024), pp. 19109–19127. doi: https://doi.org/10.1007/s11042-023-16231-x.
• Leonardo Gabrielli, Lucia Migliorelli, Michela Cantarini, Adriano Mancini e Stefano Squartini. “An advanced multimodal driver-assistance prototype for emergency-vehicle detection”. In: Integrated Computer-Aided Engineering Preprint (2024), pp. 1–19. doi: 10.3233/ICA-240733.
• Davide Lillini, Carlo Aironi, Lucia Migliorelli, Leonardo Gabrielli e Stefano Squartini. “SiCRNN: A Siamese Approach for Sleep Apnea Identification via Tracheal Microphone Signals”. In: Sensors 24.23 (2024), p. 7782. doi: https://doi.org/10.3390/s24237782.
• Carolina Gonçalves, João M. Lopes, Sara Moccia, Daniele Berardini, Lucia Migliorelli e Cristina Santos. “Deep learning-based approaches for human motion decoding in smart walkers for rehabilitation”. In: Expert Systems with Applications 228 (2023), p. 120288. doi: https://doi.org/10.1016/j.eswa.2023.120288.
• Lucia Migliorelli, Daniele Berardini, Kevin Cela, Michela Coccia, Laura Villani, Emanuele Frontoni e Sara Moccia. “A store-and-forward cloud-based telemonitoring system for automatic assessing dysarthria evolution in neurological diseases from video-recording analysis”. In: Computers in Biology and Medicine 163 (2023), p. 107194. doi: https://doi.org/10.1016/j.compbiomed.2023.107194.
• Lucia Migliorelli, Alessandro Cacciatore, Valeria Ottaviani, Daniele Berardini, Raffaele L Dellaca’, Emanuele Frontoni e Sara Moccia. “TwinEDA: a sustainable deep-learning approach for limb-position estimation in preterm infants’ depth images”. In: Medical & Biological Engineering & Computing 61.2 (2023), pp. 387–397. doi: https://doi.org/10.1007/s11517-022-02696-9.
• Lucia Migliorelli, Lorenzo Scoppolini Massini, Michela Coccia, Laura Villani, Emanuele Frontoni e Stefano Squartini. “A deep learning-based telemonitoring application to automatically assess oral diadochokinesis in patients with bulbar amyotrophic lateral sclerosis”. In: Computer Methods and Programs in Biomedicine 242 (2023), p. 107840. doi: https://doi.org/10.1016/j.cmpb.2023.107840.
• Lucia Migliorelli, Simona Tiribelli, Alessandro Cacciatore, Benedetta Giovanola, Emanuele Frontoni e Sara Moccia. “Accountable deep-learning-based vision systems for preterm infant monitoring”. In: Computer 56.5 (2023), pp. 84–93. doi: 10.1109/MC.2023.3235987.
• Giuseppe Pio Cannata, Lucia Migliorelli, Adriano Mancini, Emanuele Frontoni, Rocco Pietrini e Sara Moccia. “Generating depth images of preterm infants in given poses using GANs”. In: Computer Methods and Programs in Biomedicine 225 (2022), p. 107057. doi: https://doi.org/10.1016/j.cmpb.2022.107057.
• Lucia Migliorelli, Emanuele Frontoni e Sara Moccia. “An accurate estimation of preterm infants’ limb pose from depth images using deep neural networks with densely connected atrous spatial convolutions”. In: Expert Systems with Applications 204 (2022), p. 117458. doi: https://doi.org/10.1016/j.eswa.2022.117458.
• Sara Casaccia, Riccardo Naccarelli, Sara Moccia, Lucia Migliorelli, Emanuele Frontoni e GianMarco Revel. “Development of a measurement setup to detect the level of physical activity and social distancing of ageing people in a social garden during COVID-19 pandemic”. In: Measurement 184 (2021), p. 109946. doi: https://doi.org/10.1016/j.measurement.2021.109946.
• Jonathan Montomoli, Luca Romeo, Sara Moccia, Michele Bernardini, Lucia Migliorelli, Daniele Berardini, Abele Donati, Andrea Carsetti, Maria Grazia Bocci, Pedro David Wendel Garcia et “Machine learning using the extreme gradient boosting (XGBoost) algorithm predicts 5-day delta of SOFA score at ICU admission in COVID-19 patients”. In: Journal of Intensive Medicine 1.02 (2021), pp. 110–116. doi: https://doi.org/10.1016/j.jointm.2021.09.002.
• Manuel Palermo, Sara Moccia, Lucia Migliorelli, Emanuele Frontoni e Cristina P Santos. “Realtime human pose estimation on a smart walker using convolutional neural networks”. In: Expert Systems with Applications 184 (2021), p. 115498. doi: https://doi.org/10.1016/j.eswa.2021.115498.
• Michele Salati, Lucia Migliorelli, Sara Moccia, Marco Andolfi, Alberto Roncon, Gian Marco Guiducci, Francesco Xiumè, Michela Tiberi, Emanuele Frontoni e Majed Refai. “A machine learning approach for postoperative outcome prediction: surgical data science application in a thoracic surgery setting”. In: World Journal of Surgery 45 (2021), pp. 1585–1594. doi: 10.1007/s00268-020-05948-7.
• Luca Antognoli, Sara Moccia, Lucia Migliorelli, Sara Casaccia, Lorenzo Scalise e Emanuele Frontoni. “Heartbeat detection by laser doppler vibrometry and machine learning”. In: Sensors 20.18(2020), p. 5362. doi: https://doi.org/10.3390/s20185362.
• Daniele Berardini, Sara Moccia, Lucia Migliorelli, Iacopo Pacifici, Paolo di Massimo, Marina Paolanti, Emanuele Frontoni e Adín Ramírez Rivera. “Fall detection for elderly-people monitoring using learned features and recurrent neural networks”. In: Experimental Results 1 (2020), e7. doi:10.1017/exp.2020.3.
• Emanuele Frontoni, Luca Romeo, Michele Bernardini, Sara Moccia, Lucia Migliorelli, Marina Paolanti, Alessandro Ferri, Paolo Misericordia, Adriano Mancini e Primo Zingaretti. “A decision support system for diabetes chronic care models based on general practitioner engagement and EHR data sharing”. In: IEEE Journal of Translational Engineering in Health and Medicine 8(2020), pp. 1–12. doi: 10.1109/JTEHM.2020.3031107.
• Lucia Migliorelli, Sara Moccia, Rocco Pietrini, Virgilio Paolo Carnielli e Emanuele Frontoni. “The babyPose dataset”. In: Data in brief 33 (2020), p. 106329. doi: https://doi.org/10.1016/j.dib.2020.106329.
• Chiara Calamanti, Sara Moccia, Lucia Migliorelli, Marina Paolanti e Emanuele Frontoni. “Learning based screening of endothelial dysfunction from photoplethysmographic signals”. In: Electronics 8.3 (2019), p. 271. doi: https://doi.org/10.3390/electronics8030271.
• Sara Moccia, Lucia Migliorelli, Virgilio Carnielli e Emanuele Frontoni. “Preterm infants’ pose estimation with spatio-temporal features”. In: IEEE Transactions on Biomedical Engineering 67.8 (2019), pp. 2370–2380. doi: 10.1109/TBME.2019.2961448.
• Angela Agostinelli, Micaela Morettini, Agnese Sbrollini, Elvira Maranesi, Lucia Migliorelli, Francesco Di Nardo, Sandro Fioretti e Laura Burattini. “CaRiSMA 1.0: cardiac risk self-monitoring assessment”. In: The Open Sports Sciences Journal 10.1 (2017). doi: 10.2174/1875399X01710010179.

Contributi su capitolo

• Sara Moccia, Luca Romeo, Lucia Migliorelli, Emanuele Frontoni e Primo Zingaretti. “Supervised CNN Strategies for Optical Image Segmentation and Classification in Interventional Medicine”. In: Deep Learners and Deep Learner Descriptors for Medical Applications. A cura di Loris Nanni, Sheryl Brahnam, Rick Brattin, Stefano Ghidoni e Lakhmi C. Jain. Cham: Springer International Publishing, 2020, pp. 213–236. isbn: 978-3-030-42750-4. doi: 10.1007/978-3-030-42750-4_8. url: https://doi.org/10.1007/978-3-030-42750-4_8.

Proceedings di conferenze

• Daniele Berardini, Lucia Migliorelli, Lorenzo Cardoni, Christian Parente, Alessandro Rongoni, Daniele Sergiacomi e Adriano Mancini. “Benchmark Analysis of YOLOv8 for Edge AI Video-Surveillance Applications”. In: 2024 20th IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications (MESA). 2024, pp. 1–7.
• Alessandro Galdelli, Gagan Narang, Lucia Migliorelli, Antonio Domenico Izzo, Adriano Mancini e Primo Zingaretti. “An AI-Driven Prototype for Groundwater Level Prediction: Exploring the Gorgovivo Spring Case Study”. In: International Conference on Image Analysis and Processing. Springer Nature Switzerland Cham. 2023, pp. 418–429.
• Lucia Migliorelli, Sara Moccia, Daniele Berardini, Emanuele Frontoni, Michela Coccia, Laura Villani e Andrea Bandini. “A preliminary study on self-care telemonitoring of dysarthria in spinal muscular atrophy”. In: 2023 45th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC). IEEE. 2023, pp. 1–4.
• Alessandro Cacciatore, Lucia Migliorelli, Daniele Berardini, Simona Tiribelli, Stefano Pigliapoco e Sara Moccia. “Some Ethical Remarks on Deep Learning-Based Movements Monitoring for Preterm Infants: Green AI or Red AI?” In: International Conference on Image Analysis and Processing. Springer International Publishing Cham. 2022, pp. 165–175.
• Michela Cantarini, Leonardo Gabrielli, Lucia Migliorelli, Adriano Mancini e Stefano Squartini. “Beware the Sirens: Prototyping an Emergency Vehicle Detection System for Smart Cars”. In: International Conference on Applied Intelligence and Informatics. Springer Nature Switzerland Cham. 2022, pp. 437–451.
• Matteo Carbonari, Greta Vallasciani, Lucia Migliorelli, Emanuele Frontoni e Sara Moccia. “End-to-end semantic joint detection and limb-pose estimation from depth images of preterm infants in NICUs”. In: 2021 IEEE Symposium on Computers and Communications (ISCC). 2021, 1–6.
• Lucia Migliorelli, Daniele Berardini, Francesca Rossini, Emanuele Frontoni, Virgilio Carnielli e Sara Moccia. “Asymmetric Three-dimensional Convolutions For Preterm Infants’ Pose Estimation”. In: 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC). IEEE. 2021, pp. 3021–3024.
• Lucia Migliorelli, Emanuele Frontoni, Simone Appugliese, Giuseppe Pio Cannata, Virgilio Carnielli e Sara Moccia. “Improving Preterm Infants’ Joint Detection in Depth Images Via Dense Convolutional Neural Networks”. In: 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC). 2021, pp. 3013–3016.
• Daniele Berardini, Lucia Migliorelli, Sara Moccia, Marcello Naldini, Gioia De Angelis e Emanuele Frontoni. “Evaluating the autonomy of children with autism spectrum disorder in washing hands: a deep-learning approach”. In: 2020 IEEE Symposium on Computers and Communications (ISCC). IEEE. 2020, pp. 1–7.
• Lucia Migliorelli, Sara Moccia, Giuseppe Pio Cannata, Alessia Galli, Ilaria Ercoli, Luigi Mandolini, Virgilio Carnielli, Emanuele Frontoni et al. “A 3D CNN for preterm-infants’ movement detection in NICUs from depth streams”. In: ... NATIONAL CONGRESS OF BIOENGINEERING. PROCEEDINGS. Patron Editore Srl. 2020, pp. 108–111.
• Michele Bernardini, Alessandro Ferri, Lucia Migliorelli, Sara Moccia, Luca Romeo, Sonia Silvestri, Luca Tiano e Adriano Mancini. “Augmented microscopy for DNA damage quantification: A machine learning tool for environmental, medical and health sciences”. In: International Design Engineering Technical Conferences and Computers and Information in Engineering Conference. Vol. 59292. American Society of Mechanical Engineers. 2019, V009T12A003.
• Lucia Migliorelli, Annalisa Cenci, Michele Bernardini, Luca Romeo, Sara Moccia e Primo Zingaretti. “A Cloud-Based Healthcare Infrastructure for Neonatal Intensive-Care Units”. In: International Design Engineering Technical Conferences and Computers and Information in EngineeringConference. Vol. 59292. American Society of Mechanical Engineers. 2019, V009T12A009.
• Lucia Migliorelli, Sara Moccia, Ismaela Avellino, Maria Chiara Fiorentino e Emanuele Frontoni. “MyDi application: Towards automatic activity annotation of young patients with Type 1 diabetes”. In: 2019 IEEE 23rd International Symposium on Consumer Technologies (ISCT). IEEE. 2019, pp. 220–224.
• Sara Moccia, Lucia Migliorelli, Rocco Pietrini e Emanuele Frontoni. “Preterm infants’ limb-pose estimation from depth images using convolutional neural networks”. In: 2019 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB). IEEE. 2019, pp. 1–7.