CPS-IoTBench 2022 – Program

All times are Milan local time (CEST)

14:0014:15Opening Remarks
Chair: Michael Baddeley
14:1515:15Paper Session 1 (AI & DLT)
Chair: Olga Saukh 
∎ Regression Model Trees: Compact Energy Models for Complex IoT Devices
Daniel Friesel and Olaf Spinczyk
∎ Benchmarking Audio-based Deep Learning Models for Detection and Identification of Unmanned Aerial Vehicles
Sai Srinadhu Katta, Sivaprasad Nandyala, Eduardo Kugler Viegas and Abdelrahman Al Mahmoud
∎ Benchmarking Performance of Ethereum Blockchain on Resource Constrained Devices
Suhail Al Marzouqi, Michael Baddeley, and Martin Andreoni
15:1515:30Virtual coffee break
15:3016:30Keynote: MLPerf Tiny and the Landscape of AI Benchmarking
Presenter: Colby Banbury
Abstract
Advancements in ultra-low-power tiny machine learning (TinyML) systems promise to unlock an entirely new class of smart applications. However, continued progress is limited by the lack of a widely accepted and easily reproducible benchmark for these systems. To meet this need, we present MLPerf Tiny, the first industry-standard benchmark suite for ultra-low-power tiny machine learning systems. The benchmark suite is the collaborative effort of more than 50 organizations from industry and academia and reflects the needs of the community. MLPerf Tiny measures the accuracy, latency, and energy of machine learning inference to properly evaluate the tradeoffs between systems. Additionally, MLPerf Tiny implements a modular design that enables benchmark submitters to show the benefits of their product, regardless of where it falls on the ML deployment stack, in a fair and reproducible manner.
16:3016:45Virtual coffee break
16:4517:45Paper session 2 (Comms & Localization)
Chair: Ambuj Varshney
∎ Reproducing Key Results from “Restructuring Endpoint Congestion Control”
Tushar Dhoot and Joe Zhang
∎ Signal Loss in Body Coupled Communication: Guide for Accurate Measurements
Juris Ormanis, Vladislavs Medvedevs, Valters Abolins, Gatis Gaigals and Atis Elsts
∎ On the Performance of IEEE 802.15.4z-Compliant Ultra-Wideband Devices
Michael Stocker, Hannah Brunner, Maximilian Schuh, Carlo Alberto Boano and Kay Roemer
∎ First Steps in Benchmarking the Performance of Heterogeneous Ultra-Wideband Platforms
Maximilian Schuh, Hannah Brunner, Michael Stocker, Markus Schuss, Carlo Alberto Boano and Kay Roemer
17:4518:00Closing Remarks
Chair: Michael Baddeley