Education
- Ph.D. in Electrical and Computer Engineering - Northeastern University (2020)
- M.S. in Telecommunications Engineering - University of Rome "La Sapienza", Italy (2013)
- B.S. in Telecommunications Engineering - University of Sannio, Benevento, Italy (2009)
Research Interests
Raffaele Guida earned his Ph.D. in Electrical and Computer Engineering from Northeastern University in 2020. He received his B.S. and M.S. in Telecommunications Engineering from the University of Sannio (2009) and the University of Rome “La Sapienza” (2013) respectively. His primary research focused on ultrasonic power transmission, ultrasonic energy harvesting, and intra-body wireless sensor networks. His other research interests included video delivery technologies, video streaming and HTTP streaming, multimedia wireless sensor networks, and mobile cloud computing. After graduation, he joined BioNet Sonar as a Manager.
Publications
2024
Journals and Magazines
This demo presents SeizNet, an innovative system for predicting epileptic seizures benefiting from a multi-modal sensor network and utilizing Deep Learning (DL) techniques. Epilepsy affects approximately 65 million people worldwide, many of whom experience drug-resistant seizures. SeizNet aims at providing highly accurate alerts, allowing individuals to take preventive measures without being disturbed by false alarms. SeizNet uses a combination of data collected through either invasive (intracranial electroencephalogram (iEEG)) or non-invasive (electroencephalogram (EEG) and electrocardiogram (ECG)) sensors, and processed by advanced DL algorithms that are optimized for real-time inference at the edge, ensuring privacy and minimizing data transmission. SeizNet achieves > 97% accuracy in seizure prediction while keeping the size and energy restrictions of an implantable device.
LinkConference Papers
In this paper, we introduce SeizNet, a closed-loop system for predicting epileptic seizures through the use of Deep Learning (DL) method and implantable sensor networks. While pharmacological treatment is effective for some epilepsy patients (with ~65M people affected worldwide), one out of three suffer from drug-resistant epilepsy. To alleviate the impact of seizure, predictive systems have been developed that can notify such patients of an impending seizure, allowing them to take precautionary measures. SeizNet leverages DL techniques and combines data from multiple recordings, specifically intracranial electroencephalogram (iEEG) and electrocardiogram (ECG) sensors, that can significantly improve the specificity of seizure prediction while preserving very high levels of sensitivity. SeizNet DL algorithms are designed for efficient real-time execution at the edge, minimizing data privacy concerns, data transmission overhead, and power inefficiencies associated with cloud-based solutions. Our results indicate that SeizNet outperforms traditional single-modality and non-personalized prediction systems in all metrics, achieving up to 99% accuracy in predicting seizure, offering a promising new avenue in refractory epilepsy treatment.
Link2022
Journals and Magazines
2020
Journals and Magazines
2019
Journals and Magazines
2018
Conference Papers
2017
Conference Papers
2016
Conference Papers
2015
Journals and Magazines
2013
Conference Papers
This paper studies a cloud-assisted procedure to improve the user's Quality of Experience (QoE) in HTTP Adaptive Streaming (HAS) services. HAS delivers video streaming services following a client-server architecture and requires the client to originate repeated HTTP requests to download chunks of encoded video. In state-of-the-art systems, the client selects the actual chunk to be downloaded from a finite set of differently encoded video versions available at the server site, according to a client-based buffer management procedure.In a multimedia cloud framework, HAS can leverage knowledge of the characteristics of the encoded video available at the server side. Therefore, we propose a cloud-assisted HAS procedure that exploits information on the encoded video content available at the cloud side to control the client-originated download requests.The proposed approach balances client-related quality issues, which would require intensive video chunks download to avoid playout stalls, with cloud related system constraints, which require the average download rate not to overcome the average video encoding rate. Finally, this approach procedure alleviates the computational load at the client, since the downloading strategy is computed at the cloud side.We demonstrate that significant QoE improvements are achievable through the proposed cloud-assisted buffer management procedure.
Link