Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 18 of 18 for “"Tiny Machine Learning"”.
-
EdgeCube -- An IoT Edge-Sensor Node for Tiny Machine Learning Applications
This thesis presents a novel internet-of-things (IoT) edge device, EdgeCube, a compact embedded system that combines a microcontroller unit (MCU) and a field-programmable gate array (FPGA). The proposed platform explores a trade-off between the performance gains achievable through FPGA-based …
-
Efficient Operation of Edge AI and Tiny Machine Learning on Heterogeneous Resource-Constrained Devices
Tiny Machine Learning (TinyML) brings data-driven intelligence directly onto microcontroller-based Internet of Things (IoT) devices, thereby lowering communication overhead, improving real-time responsiveness, and enabling energy-efficiency at the network edge. However, widespread adoption is still …
-
Validación de un sistema IoT con aprendizaje federado y TinyML para el monitoreo postural en un entorno de cuidado simulado
… based on the Internet of Things (IoT), Federated Learning (FL), and Tiny Machine Learning (TinyML), aimed at healthcare environments in simulated conditions. The system was designed to support continuous monitoring of body posture in care settings, prioritizing data privacy, computational …
-
Avaliação de modelos otimizados de TinyML para detecção de anomalias em IoT
… apresenta uma avaliação de modelos otimizados de Tiny Machine Learning (TinyML), onde são investigados os benefícios de se ter em um dispositivo sensor, um algoritmo otimizado onde a inferência dos dados é realizada localmente. O desempenho de cada uma das técnicas é avaliado, bem como a …
-
Otimização de modelos de aprendizado de máquina em dispositivos de borda: Random Forest e XGBoost
… impulsionado o desenvolvimento de técnicas de Tiny Machine Learning (TinyML), que visam executar algoritmos de aprendizado de máquina em plataformas com severas restrições de energia, memória e capacidade computacional. Neste contexto, os Field-Programmable Gate Arrays (FPGAs) emergem como uma …
-
MMCloud: um algoritmo de clustering não supervisionado online para análise do comportamento do motorista
… real-time driver behavior diagnosis, leveraging Tiny Machine Learning (TinyML) and soft sensors. It introduces the MMCloud algorithm, an incremental clustering model designed to manage continuous data streams. The algorithm eliminates the need for retraining and is capable of adapting to concept …
-
An evolving multivariate time series compression algorithm for IoT applications
… substantial energy consumption. In this context, Tiny Machine Learning (TinyML) emerges as a promising solution, enabling the execution of machine-learning models on resource-constrained embedded devices. This paper aims to develop two online multivariate time series compression approaches …
-
Lightweight Cryptographic Hardware Architectures for Secure IoT Systems
… a secure-boot architecture for FPGA-based Tiny Machine Learning (TinyML) systems that authenticates firmware, model parameters, and boot metadata before application execution is enabled. Collectively, these works provide a layered approach to lightweight FPGA security spanning …
-
Prediktivní údržba vestavných systémů založená na strojovém učení
… neplánovaných odstávek. S nástupem technologie Tiny Machine Learning (TinyML) je nyní možné provozovat lehké prediktivní modely přímo na vestavěných mikrokontrolérech, což umožňuje decentralizovanou a okamžitou detekci poruch na okraji sítě. Tato práce zkoumá proveditelnost a efektivitu použití …
-
TinyML for Real-Time Crop Disease Detection in Precision Agriculture: A Proof-of-Concept Study on Maize Leaf Disease Detection
Traditional machine learning approaches for crop disease detection often require substantial computational resources, energy consumption, and net-work connectivity. Tiny Machine Learning (TinyML) addresses these limita-tions by enabling machine learning inference directly on resource-constrained …
-
An unsupervised tinyML incremental learning approach for outlier processing and forecasting
… processing enables the development of optimized machine learning algorithms, known as Tiny Machine Learning (TinyML). By employing lightweight and optimized algorithms, TinyML offers advantages such as reduced latency, improved energy efficiency, and increased autonomy for devices operating in …
-
Techniques and Applications for Efficient Low-power TinyML
Tiny machine learning (tinyML) is becoming popular in Internet of Things (IoT) systems to add intelligence to end nodes with limited resources. Nowadays, there are tens of billions of connected devices that exchange data wirelessly, making dense IoT networks. However, the data involved in …
-
On the Design of Efficient Deep Learning Methods for Human Activity Recognition in Resource Constrained Devices
… wearable and ambient sensors. Advances in deep learning, especially Convolutional Neural Networks (CNN) have revolutionized intelligent frameworks such as HAR systems by effectively and efficiently inferring human activity from various modalities of data. However, the training and inference of …
-
Robust Edge Machine-Learning For The Real-Time Processing And Prediction of Geomagnetic Anomalies and Geomagnetically Induced Currents (GICs)
… charged particles from the Sun) \cite{camporeale_machine_2018} \cite{geosciences12010027}. These induced currents considerably threaten vital technological systems, notably the electrical power grids. This research addresses the critical challenges of robust, real-time forecasting and monitoring …
-
Towards Securing Quantized Deep Learning
The impressive capabilities of Machine Learning (ML) technology, driven largely by the rapid emergence of Deep Learning (DL), have facilitated a wide array of practical applications, spanning from image recognition, autonomous driving, to speech processing. The significance of DL is further …
-
The development of EdgeML applications using TinyML
… of the thesis is to investigate the new field of Tiny Machine Learning, also known as TinyML. Machine Learning is an expanding field that is actively researched in both academic and industrial settings. The technology is employed in diverse domains, such as Internet of Things and Data Science. …
-
ENHANCING PRIVACY WHILE REVEALING VULNERABILITIES: STRATEGIES FOR ADAPTATION, OPTIMIZATION, AND MODEL EXTRACTION
In the evolving landscape of machine learning and artificial intelligence, this dissertation presents a series of innovative contributions spanning several critical areas: embracing semi-supervised domain adaptation for secure knowledge transfer, enhancing the model performance of tiny models, and …
-
Využití strojového učení k rozpoznání pohybu feederového prutu
Cílem této diplomové práce je vytvořit zařízení, které využívá metody strojového učení k rozpoznávání pohybů feederového rybářského prutu na základě dat z inerciální měřící jednotky. Úvodní část je věnována rybolovné technice feeder, výběru důležitých pohybů a možnostem upevnění detekčního zařízení …