Quantization and Deployment of Deep Neural Networks on Microcontrollers [PDF]
Sensors, 2021 Embedding Artificial Intelligence onto low-power devices is a challenging task that has been partly overcome with recent advances in machine learning and hardware design.
Pierre-Emmanuel Novac +4 more
doaj +2 more sources
Influence of Control System Architecture on Mobile Robot Stability and Performance [PDF]
SensorsThis paper presents an analysis of the impact of the control architecture in a mobile robot on the quality of regulation in real systems. Comparative studies were conducted for successive stages of the implementation of architectural improvements, such ...
Maciej Salwa, Izabela Krzysztofik
doaj +2 more sources
Implementation of a Universal Framework Using Design Patterns for Application Development on Microcontrollers [PDF]
SensorsThis article focuses on the area of software development for microcontrollers and details the implementation of modern programming practices and principles in embedded systems and IoT applications.
Marek Babiuch, Petr Foltynek
doaj +2 more sources
TinyOL: TinyML with Online-Learning on Microcontrollers [PDF]
IEEE International Joint Conference on Neural Network, 2021 Tiny machine learning (TinyML) is a fast-growing research area committed to democratizing deep learning for all-pervasive microcontrollers (MCUs).
Haoyu Ren, Darko Anicic, T. Runkler
semanticscholar +1 more source
TinyissimoYOLO: A Quantized, Low-Memory Footprint, TinyML Object Detection Network for Low Power Microcontrollers [PDF]
International Conference on Artificial Intelligence Circuits and Systems, 2023 This paper introduces a highly flexible, quantized, memory-efficient, and ultra-lightweight object detection network, called TinyissimoYOLO. It aims to enable object detection on microcontrollers in the power domain of milliwatts, with less than 0.5 MB ...
Julian Moosmann +3 more
semanticscholar +1 more source
Human Activity Recognition on Microcontrollers with Quantized and Adaptive Deep Neural Networks [PDF]
ACM Transactions on Embedded Computing Systems, 2022 Human Activity Recognition (HAR) based on inertial data is an increasingly diffused task on embedded devices, from smartphones to ultra low-power sensors.
Francesco Daghero +8 more
semanticscholar +1 more source
Femto-containers: lightweight virtualization and fault isolation for small software functions on low-power IoT microcontrollers [PDF]
International Middleware Conference, 2022 Low-power operating system runtimes used on IoT microcontrollers typically provide rudimentary APIs, basic connectivity and, sometimes, a (secure) firmware update mechanism.
K. Zandberg +4 more
semanticscholar +1 more source
WORKSHOP ROBOTIK DAN MIKROCONTROLLER PADA SISWA SMK BINA INSAN SIAK HULU
Jurnal Pengabdian dan Edukasi Sekolah, 2022 This community service activity is carried out as a form of devotion from AMIK Tri Dharma Pekanbaru lecturers to the community, as for the materials chosen in this activity are robotics and microcontrollers, the target is students majoring in computer ...
Zulafwan Zulafwan +3 more
doaj +1 more source
Fire Detection System At Labuhanbatu University Based On Internet Of Things (IoT)
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), 2023 Fire accidents are disasters that often occur compared to other fire disasters such as floods, landslides, earthquakes or tsunamis. Fires can occur at any time, and no one knows for sure when a fire accident will occur.
Iwan Purnama +4 more
doaj +1 more source
Keyword Spotting System and Evaluation of Pruning and Quantization Methods on Low-power Edge Microcontrollers [PDF]
arXiv.org, 2022 Keyword spotting (KWS) is beneficial for voice-based user inter-actions with low-power devices at the edge. The edge devices are usually always-on, so edge computing brings bandwidth savings and privacy protection.
Jingyi Wang, Shengchen Li
semanticscholar +1 more source