no code implementations • 22 Feb 2024 • Eugen Šlapak, Matúš Dopiriak, Mohammad Abdullah Al Faruque, Juraj Gazda, Marco Levorato
For autonomous mobility, it enables new possibilities with edge computing and digital twins (DTs) that offer virtual prototyping, prediction, and more.
no code implementations • 22 Feb 2024 • Francesco Malandrino, Giuseppe Di Giacomo, Marco Levorato, Carla Fabiana Chiasserini
The existing work on the distributed training of machine learning (ML) models has consistently overlooked the distribution of the achieved learning quality, focusing instead on its average value.
no code implementations • 14 Dec 2023 • Seyed Amir Hossein Aqajari, Sina Labbaf, Phuc Hoang Tran, Brenda Nguyen, Milad Asgari Mehrabadi, Marco Levorato, Nikil Dutt, Amir M. Rahmani
We achieved the F1-score of 70\% with a Random Forest classifier using both PPG and contextual data, which is considered an acceptable score in models built for everyday settings.
no code implementations • 12 Oct 2023 • Niloofar Bahadori, Yoshitomo Matsubara, Marco Levorato, Francesco Restuccia
However, the size of the matrix grows with the number of antennas and subcarriers, resulting in an increasing amount of airtime overhead and computational load at the station.
no code implementations • 22 Jun 2023 • Juliano S. Assine, J. C. S. Santos Filho, Eduardo Valle, Marco Levorato
In approaches based on edge computing the execution of the models is offloaded to a compute-capable device positioned at the edge of 5G infrastructures.
no code implementations • 28 Apr 2023 • Ali Tazarv, Sina Labbaf, Amir Rahmani, Nikil Dutt, Marco Levorato
Most existing sensor-based monitoring frameworks presume that a large available labeled dataset is processed to train accurate detection models.
no code implementations • 2 Dec 2022 • Francesco Malandrino, Giuseppe Di Giacomo, Armin Karamzade, Marco Levorato, Carla Fabiana Chiasserini
To make machine learning (ML) sustainable and apt to run on the diverse devices where relevant data is, it is essential to compress ML models as needed, while still meeting the required learning quality and time performance.
1 code implementation • 16 Mar 2022 • Yoshitomo Matsubara, Ruihan Yang, Marco Levorato, Stephan Mandt
With the increasing demand for deep learning models on mobile devices, splitting neural network computation between the device and a more powerful edge server has become an attractive solution.
no code implementations • 11 Jan 2022 • Davide Callegaro, Francesco Restuccia, Marco Levorato
We extensively evaluate SmartDet on a real-world testbed composed of a JetSon Nano as mobile device and a GTX 980 Ti as edge server, connected through a Wi-Fi link.
2 code implementations • 7 Jan 2022 • Yoshitomo Matsubara, Davide Callegaro, Sameer Singh, Marco Levorato, Francesco Restuccia
We show that BottleFit decreases power consumption and latency respectively by up to 49% and 89% with respect to (w. r. t.)
1 code implementation • 7 Dec 2021 • Peyman Tehrani, Francesco Restuccia, Marco Levorato
Next Generation (NextG) networks are expected to support demanding tactile internet applications such as augmented reality and connected autonomous vehicles.
no code implementations • 15 Nov 2021 • Yoo Jeong Ha, Soyi Jung, Jae-Hyun Kim, Marco Levorato, Joongheon Kim
This paper utilizes surveillance UAVs for the purpose of detecting the presence of a fire in the streets.
2 code implementations • 21 Aug 2021 • Yoshitomo Matsubara, Ruihan Yang, Marco Levorato, Stephan Mandt
There has been much interest in deploying deep learning algorithms on low-powered devices, including smartphones, drones, and medical sensors.
no code implementations • 31 Jul 2021 • Ali Tazarv, Sina Labbaf, Stephanie M. Reich, Nikil Dutt, Amir M. Rahmani, Marco Levorato
Since stress contributes to a broad range of mental and physical health problems, the objective assessment of stress is essential for behavioral and physiological studies.
no code implementations • 30 Jul 2021 • Ali Tazarv, Marco Levorato
Based on these similarities, in recent years several methods were proposed to predict BP from the PPG signal.
19 code implementations • 8 Mar 2021 • Yoshitomo Matsubara, Marco Levorato, Francesco Restuccia
Mobile devices such as smartphones and autonomous vehicles increasingly rely on deep neural networks (DNNs) to execute complex inference tasks such as image classification and speech recognition, among others.
2 code implementations • 20 Nov 2020 • Yoshitomo Matsubara, Davide Callegaro, Sabur Baidya, Marco Levorato, Sameer Singh
In this paper, we propose to modify the structure and training process of DNN models for complex image classification tasks to achieve in-network compression in the early network layers.
no code implementations • 15 Sep 2020 • Peyman Tehrani, Marco Levorato
The prompt and accurate detection of faults and abnormalities in electric transmission lines is a critical challenge in smart grid systems.
2 code implementations • 31 Jul 2020 • Yoshitomo Matsubara, Marco Levorato
However, poor conditions of the wireless channel connecting the mobile devices to the edge servers may degrade the overall capture-to-output delay achieved by edge offloading.
2 code implementations • 27 Jul 2020 • Yoshitomo Matsubara, Marco Levorato
Following the trends of mobile and edge computing for DNN models, an intermediate option, split computing, has been attracting attentions from the research community.
2 code implementations • 1 Oct 2019 • Yoshitomo Matsubara, Sabur Baidya, Davide Callegaro, Marco Levorato, Sameer Singh
Offloading the execution of complex Deep Neural Networks (DNNs) models to compute-capable devices at the network edge, that is, edge servers, can significantly reduce capture-to-output delay.