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 14 of 14 for “"embedded machine learning"”.
-
Improving training and inference for embedded machine learning
… development of Artificial Intelligence (AI) for embedded systems that require AI models to operate in resource constrained environments. Desirable characteristics of these models are reduced memory, computation and power requirements, that still deliver powerful performance. Deep learning has …
-
CANLP: Intrusion Detection for Controller Area Networks using Natural Language Processing and Embedded Machine Learning
… features associated with CAN data and trains machine learning models to identify three types of attacks- fuzzing, spoofing, and masquerade. When an attack is detected, CANLP identifies the compromised transmitter ECU and malicious CAN frame, which is important for developing resilient systems. …
-
An industrial analytics methodology and fog computing cyber-physical system for Industry 4.0 embedded machine learning applications
… internet-of-things, artificial intelligence, and machine learning), to derive self-aware and self-configuring factories capable of delivering major production innovations. However, the technologies and architectures needed to connect and extend physical factory operations to the cyber world have …
-
Towards Better Interpretability of Machine Learning-Based Decision Support Systems
… In recent years, researchers have applied machine learning for the purpose of supporting decision making in a wide range of domains. Yet, how to communicate the system recommendations to human decision makers, and how human decision makers would use and trust the machine learning …
-
Analytical guarantees for reduced precision fixed-point margin hyperplane classifiers
… hyperplane classifiers such as support vector machines are strong predictive models having gained considerable success in various classification tasks. Their conceptual simplicity makes them suitable candidates for the design of embedded machine learning systems. Their accuracy and resource …
-
A Full System Co-Simulation Platform for Evaluating Edge Machine Learning Inference Using Compute-in-Memory
… co-simulation platform for evaluating embedded machine learning (ML) inference using compute-in-memory (CIM). CIM architectures aim to reduce data movement overhead by performing matrix operations in memory, but end-to-end benefits depend on system-level integration costs that are …
-
Analysis of Closed-Loop Digital Twin
… was developed which made use of live data with embedded machine learning to improve predictions. This model had live data updated directly to the DES model without user interaction, creating an adaptive and dynamic model. It was found that this DES with machine learning capabilities typically …
-
Medidor inteligente para predição mensal de consumo de energia elétrica com Aprendizado de Máquina embarcado sob restrições de hardware
… and monthly energy consumption forecasting using embedded machine learning techniques. Electrical measurements are performed by dedicated energy metering integrated circuits, while data processing, predictive inference, and system management are executed on an ESP32-S3 microcontroller under strict …
-
Cyber Resilience Analytics For Cyber-Physical Systems
… merging from different scientific fields such as embedded systems, control systems, operational technology, information technology systems (ITS), and cybernetics. Today critical infrastructures (CIs) (e.g., energy systems, electric grids, etc.) and other CPSs (e.g., manufacturing industries, …
-
The Legitimacy and Accountability for the Deployment of Autonomous Weapon Systems under International Humanitarian Law
… systems’, looking at the structure of the embedded machine learning algorithms. The second endeavour was to prove that there are no reasons to proclaim a ‘responsibility gap’. AWS will require not only a higher level of responsibility from commanders, designers, programmers and technicians …
-
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 …
-
Hardware-in-the-Loop Evaluation of Sensor-Source Selection for Prosthetic Locomotion Intent Recognition
… may be unsuitable for resource-constrained embedded hardware. Existing sensor-selection methods generally prioritize classification accuracy without directly accounting for processing latency, memory usage, or other hardware-dependent requirements. To address this limitation, this thesis …
-
Anomaly detection in IoT devices using side-channel power consumption
… the work transitions to self-supervised learning trained exclusively on normal behaviour. A Convolutional Autoencoder (CAE) and a dropout-enhanced variant establish that reconstruction-based anomaly detection can identify unseen attacks while remaining interpretable through …
-
Resource optimization methods for Machine Learning model execution on resource constrained embedded systems
… dissertation investigates the optimization of machine learning (ML) workloads for execution on resource-constrained microcontroller units (MCUs), addressing both algorithmic and architectural challenges. The rapid emergence of edge Artificial Intelligence (AI) applications necessitates …