Related papers: Usability and Performance Analysis of Embedded Dev…
Although Federated Learning (FL) is promising to enable collaborative learning among Artificial Intelligence of Things (AIoT) devices, it suffers from the problem of low classification performance due to various heterogeneity factors (e.g.,…
This working paper explores the integration of neural networks onto resource-constrained embedded systems like a Raspberry Pi Pico / Raspberry Pi Pico 2. A TinyML aproach transfers neural networks directly on these microcontrollers,…
Nowadays, billions of phones, IoT and edge devices around the world generate data continuously, enabling many Machine Learning (ML)-based products and applications. However, due to increasing privacy concerns and regulations, these data…
IoT applications usually rely on cloud computing services to perform data analysis such as filtering, aggregation, classification, pattern detection, and prediction. When applied to specific domains, the IoT needs to deal with unique…
The pervasive integration of Artificial Intelligence models into contemporary mobile computing is notable across numerous use cases, from virtual assistants to advanced image processing. Optimizing the mobile user experience involves…
In Federated Learning (FL), devices that participate in the training usually have heterogeneous resources, i.e., energy availability. In current deployments of FL, devices that do not fulfill certain hardware requirements are often dropped…
The integration of artificial intelligence (AI) into embedded devices, a paradigm known as embedded artificial intelligence (eAI) or tiny machine learning (TinyML), is transforming industries by enabling intelligent data processing at the…
We explore how to improve the energy performance of battery-less Internet of Things (IoT) devices at the cost of a reduction in the quality of the output. Battery-less IoT devices are extremely resource-constrained energy-harvesting…
The use of Dynamic Random Access Memory (DRAM) for storing Machine Learning (ML) models plays a critical role in accelerating ML inference tasks in the next generation of communication systems. However, periodic refreshment of DRAM results…
This dissertation explores the area of real-time IP networking for embedded devices, especially those with limited computational resources. With the increasing convergence of information and operational technologies in various industries,…
Dynamic Voltage and Frequency Scaling is essential for enhancing energy efficiency in mobile platforms. However, traditional heuristic-based governors are increasingly inadequate for managing the complexity of heterogeneous System-on-Chip…
One of the challenges for Tiny Machine Learning (tinyML) is keeping up with the evolution of Machine Learning models from Convolutional Neural Networks to Transformers. We address this by leveraging a heterogeneous architectural template…
Autonomous nano-drones, powered by vision-based tiny machine learning (TinyML) models, are a novel technology gaining momentum thanks to their broad applicability and pushing scientific advancement on resource-limited embedded systems.…
Earth observation (EO) missions traditionally rely on transmitting raw or minimally processed imagery from satellites to ground stations for computationally intensive analysis. This paradigm is infeasible for CubeSat systems due to…
Embedded machine learning (ML) systems have now become the dominant platform for deploying ML serving tasks and are projected to become of equal importance for training ML models. With this comes the challenge of overall efficient…
The use of virtualization technologies in different contexts - such as Cloud Environments, Internet of Things (IoT), Software Defined Networking (SDN) - has rapidly increased during the last years. Among these technologies, container-based…
Deep learning recommendation models (DLRM) rely on large embedding tables to manage categorical sparse features. Expanding such embedding tables can significantly enhance model performance, but at the cost of increased GPU/CPU/memory usage.…
Transformers have revolutionized the machine learning landscape, gradually making their way into everyday tasks and equipping our computers with "sparks of intelligence". However, their runtime requirements have prevented them from being…
On-device training has become an increasingly popular approach to machine learning, enabling models to be trained directly on mobile and edge devices. However, a major challenge in this area is the limited memory available on these devices,…
With the recent advancement of technologies over the past year, IoT has become a paradigm in which devices communicate with each other and the cloud to achieve various applications in multidisciplinary fields. However, developing,…