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 20 of 48 for “"Constrained Platforms"”.
-
Analog Signal Processing Elements for Energy-Constrained Platforms
Energy constrained processing poses a number of challenges that have resulted in tremendous innovations over the past decade. Shrinking supply voltages and limited clock speeds have placed an emphasis on processing efficiency over the raw throughput of a processor. One of the approaches to increase …
-
High performance deep learning on resource constrained platforms
… of complex and better performing models on constrained devices?</p> <p>This thesis studies this challenging problem from three different perspectives: first, by identifying a new paradigm for compression frameworks where model parameters are generated on-the-fly, enabling inference …
-
Power, Communication and Sensing Solutions for Energy Constrained Platforms
We live in a world where mobile devices such as smartphones, smart watches and tablets are commonplace. With rapid strides in technology, we have come a long way from the first main frame computer ENIAC, which occupied 167 m2 and consumed 150 kW of electricity. But, we cannot stand still. We are …
-
Compressed MobileNet V3: An efficient CNN for resource constrained platforms
Computer Vision is a mathematical tool formulated to extend human vision to machines. This tool can perform various tasks such as object classification, object tracking, motion estimation, and image segmentation. These tasks find their use in many applications, namely robotics, self-driving cars, …
-
Efficient Simulation and Implementation of Neural Networks on Resource-Constrained Platforms
… capabilities associated with embedded processing platforms, such platforms are of increasing interest for deploying signal processing systems with neural networks. However, unlike high-performance computing platforms, which are suitable for computationally-intensive neural-network-equipped …
-
Efficient visual place recognition in changing environments for resource-constrained platforms
Visual Place Recognition (VPR) enables autonomous systems to localize themselves within their environment using image information, a crucial component of robotic navigation. The affordability, availability, and versatility of current camera sensors makes VPR an attractive option for many mobile …
-
Edge Computing for Deep Learning-Based Distributed Real-time Object Detection on IoT Constrained Platforms at Low Frame Rate
… for efficient object detection on a distributed constrained platform system. In this thesis, a scalable and adaptable network for fast and easy convolutional neural network prototyping on the Xilinx PYNQ cluster has been proposed. We employed PYNQ Z1 AP-SoC (All Programmable System-on-Chip) as …
-
Designing security primitives using digital and analog discrete-time chaotic systems
… for efficient implementation on resource-constrained platforms while maintaining strong statistical and security properties.
-
Efficient querying for analytics on Internet of Things databases and streams
… streaming time-series data, possibly on resource-constrained platforms, without significant delay. Obtaining good performance is complicated by the complexity of the data model.<br/><br/>In the first part of the thesis, a graph data model is shown to support the representation of metadata and data …
-
ENERGY EFFICIENT SPIKING NEURAL NETWORKS AND THEIR APPLICATIONS
… Neural Networks (SNNs) are promising for energy-constrained platforms, but training remains challenging due to discrete activations. This thesis introduces three CNN-to-SNN conversion methods: CQ, CQ+, and VR-encoding, which minimize accuracy loss and reduce time window requirements. Our approach …
-
Nonlinear Adaptive Dynamic Inversion Control for Variable Stability Small Unmanned Aircraft Systems
… control systems on size, weight, and power constrained platforms such as small uninhabited aerial systems used by universities and research organizations. This thesis aims to develop a flight control system that brings in-flight simulation capability to these platforms. Two control systems …
-
Real-Time Recognition of Planar Targets on Mobile Devices. A Framework for Fast and Robust Homography Estimation
… demand for fast and robust estimation on power-constrained platforms. For robust recognition of targets at very low computational costs, we employ feature based methods which are based on local binary descriptors allowing fast feature matching at run-time. The matching set is then fed to a …
-
Toward Integrating Intelligence Into Everything Around Us
… intelligent systems can do and what resource-constrained platforms can support, this work establishes a foundation for truly pervasive intelligence that operates sustainably at large scale.
-
Machine Learning for the Internet of Things: Applications, Implementation, and Security
… in deep learning, sensor systems, and computing platforms by providing improved network latency and bandwidth. While tremendous progress has been made in the Internet of Things, current work has largely focused on building robust applications that leverage the data collected through ubiquitous …
-
Lightweight Cryptographic Hardware Architectures for Secure IoT Systems
… devices is therefore critical. However, resource-constrained platforms cannot always accommodate the hardware, memory, power, and computational costs of conventional security mechanisms. This dissertation investigates how the National Institute of Standards and Technology (NIST)-standardized Ascon …
-
Object Tracking Using Local Binary Descriptors
… which hinders their application to resource constrained platforms such as mobile devices. Under these conditions, the implementation of Augmented Reality (AR) or complex multi-part systems is not possible. In this thesis, we explore a variety of interest point descriptors for generic object …
-
Advancements in ML via Efficient Generative Modeling, Robust Domain Adaptation, and Explainable Multimodal Retrieval
… shifts, enable deployment on resource-constrained platforms, and enhance interpretability. For classification, the Iterative Maximum Likelihood Classifier (IMLC) recasts regularized maximum likelihood training as a fixed-point contraction with convergence guarantees, enabling faster and …
-
Design, Development and Flight Testing of a Tube-launched, Rotary-wing, Micro Air Vehicle
… when scaled down. By launching these energy-constrained platforms to a target area, the mission range could be significantly improved. The vehicle design features coaxial rotors with foldable blades, and a thrust-vectoring mechanism for pitch and roll control. Yaw control was accomplished …
-
Hardware-aware deep learning and signal processing for low-power RF modulation classification
… challenges for deployment on energy and resource-constrained platforms like embedded systems and edge devices. To overcome these limitations, this dissertation introduces a set of Piecewise Linear Approximation (PLA) techniques that replace standard nonlinear activations with segmented linear …
-
MiniVO: A Lightweight Visual Odometry Model for Resource-Constrained Systems
… model tailored for deployment on resource-constrained platforms, such as the ESP32-S3 Sense. MiniVO was designed to balance predictive accuracy with computational efficiency, using architectural simplifications and lightweight preprocessing to enable on-device inference using grayscale …
Page 1 of 3