Anas Osman

Anas Osman, Usman Abid, Luca Gemma et al.

Recent advances in state-of-the-art ultra-low power embedded devices for machine learning (ML) have permitted a new class of products whose key features enable ML capabilities on microcontrollers with less than 1 mW power consumption (TinyML). TinyML provides a unique solution by aggregating and analyzing data at the edge on low-power embedded devices. However, we have only recently been able to run ML on microcontrollers, and the field is still in its infancy, which means that hardware, software, and research are changing extremely rapidly. Consequently, many TinyML frameworks have been developed for different platforms to facilitate the deployment of ML models and standardize the process. Therefore, in this paper, we focus on bench-marking two popular frameworks: Tensorflow Lite Micro (TFLM) on the Arduino Nano BLE and CUBE AI on the STM32-NucleoF401RE to provide a standardized framework selection criterion for specific applications.

Wamiq Raza, Anas Osman, Francesco Ferrini et al.

In recent years, the proliferation of unmanned aerial vehicles (UAVs) has increased dramatically. UAVs can accomplish complex or dangerous tasks in a reliable and cost-effective way but are still limited by power consumption problems, which pose serious constraints on the flight duration and completion of energy-demanding tasks. The possibility of providing UAVs with advanced decision-making capabilities in an energy-effective way would be extremely beneficial. In this paper, we propose a practical solution to this problem that exploits deep learning on the edge. The developed system integrates an OpenMV microcontroller into a DJI Tello Micro Aerial Vehicle (MAV). The microcontroller hosts a set of machine learning-enabled inference tools that cooperate to control the navigation of the drone and complete a given mission objective. The goal of this approach is to leverage the new opportunistic features of TinyML through OpenMV including offline inference, low latency, energy efficiency, and data security. The approach is successfully validated on a practical application consisting of the onboard detection of people wearing protection masks in a crowded environment.

Anas Osman, Morteza Alijani

Unmanned Aerial Vehicles (UAVs), which are at the forefront of cutting-edge technology, have unmatched potential for pioneering applications in a wide range of disciplines. In particular, in the field of cognitive radio (CR), which is a key aspect in the implementation of the new 5G telecommunication technology. The integration between the drone and CR consolidates the drone's capabilities at the heart of the remarkably promising Internet-of-Things (IoT) technology supported by CR. The highly dynamic network topologies, weakly networked communication links, reliable line-of-sight (LOS) communication links, and orbital or flight paths are characteristic features of UAV communication compared to terrestrial wireless networks. Nevertheless, the implementation of this system is constrained by several severe challenges, such as energy efficiency, battery power limitation, spectrum handover, propagation channel modeling, routing protocols, security policy, and delay setbacks. In this paper, we consider the impact of energy scarcity faced by the UAV in various CR applications. We also analyze the impact of energy scarcity on communication-based applications and present the general problem of battery limitation. Finally, we give an overview and comparison between recent solutions proposed by researchers both in the field of communication and based on batteries and consider possible future directions according to the state of the art, such as novel Graph Signal Processing (GSP) and machine learning (ML).