no code implementations • 31 Oct 2024 • Daniel May, Alessandro Tundo, Shashikant Ilager, Ivona Brandic
While split computing enables the decomposition of large neural networks (NNs) and allows partial computation on both edge and cloud devices, identifying the most suitable split layer and hardware configurations is a non-trivial task.
1 code implementation • 13 May 2024 • Shashikant Ilager, Jakob Fahringer, Alessandro Tundo, Ivona Brandić
However, traditional monitoring systems have a centralized architecture for both data plane and control plane, which increases latency, creates a failure bottleneck, and faces challenges in providing quick and trustworthy data in volatile edge environments, especially where infrastructures are often built upon failure-prone, unsophisticated computing and network resources.
1 code implementation • 31 Aug 2023 • Alessandro Tundo, Marco Mobilio, Shashikant Ilager, Ivona Brandić, Ezio Bartocci, Leonardo Mariani
In this paper, we present an energy-aware approach for the design and deployment of self-adaptive AI-based applications that can balance application objectives (e. g., accuracy in object detection and frames processing rate) with energy consumption.
no code implementations • 9 May 2022 • Vera Colombo, Alessandro Tundo, Michele Ciavotta, Leonardo Mariani
In such environments, monitoring solutions have to cope with the heterogeneity of the devices and platforms present in the Fog, the limited resources available at the edge of the network, and the high dynamism of the whole Cloud-to-Thing continuum.
1 code implementation • 6 Oct 2021 • Oliviero Riganelli, Paolo Saltarel, Alessandro Tundo, Marco Mobilio, Leonardo Mariani
Hierarchical Temporal Memory (HTM) is an unsupervised learning algorithm inspired by the features of the neocortex that can be used to continuously process stream data and detect anomalies, without requiring a large amount of data for training nor requiring labeled data.