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 144 for “"On-device"”.
-
On-device mobile speech recognition
Despite many years of research, Speech Recognition remains an active area of research in Artificial Intelligence. Currently, the most common commercial application of this technology on mobile devices uses a wireless client – server approach to meet the computational and memory demands of the …
-
Towards On-Device Detection of Sharks with Drones
… seen several projects across the globe using drones to detect sharks, including several high profile projects around alerting beach authorities to keep people safe. However, so far many of these attempts have used cloud-based machine learning solutions for the detection component, which …
-
Cognify: An On-Device, AI-powered Learning Assistant
… where the capabilities of massive, multi-billion parameter models can be realistically replicated on consumer-grade devices. This thesis builds upon that foundation by developing an AI-powered note-taking application that runs entirely offline, using only the compute resources available on a …
-
Dependence of typing speed and accuracy on device type and familiarity
… in modem lives through its uses in laptops, phones, tablets, and other consumer electronics. Current computers encourage high typing speeds by implementing mistake corrections such as "backspace" or "delete" keys, functions that were previously done by cross-outs or complete rewrites of the …
-
Efficient Continual Learning and On-Device Training for Mobile and IoT Devices
The surge in mobile phones, wearables, and Internet of Things (IoT) devices has resulted in an abundance of sensor data. This played a pivotal role in the widespread adoption of deep neural networks (DNN) to support various real-world scenarios in mobile computing, including personalising user …
-
On-device Learning and Inference Optimization for Lightweight Neural Networks and Transformers on Microcontrollers
L'abstract è presente nell'allegato / the abstract is in the attachment
-
Enabling Hardware-efficient On-Device Learning on Microcontroller-powered Ultra-low-power IoT Nodes
L'abstract è presente nell'allegato / the abstract is in the attachment
-
On-device Classification of Human-induced Non-Line-of-Sight on Chest-Worn Ultra-wideband Wearables
Accurate indoor localization has become increasingly essential across domains that play a crucial role in modern daily life, such as IoT smart buildings, healthcare and safety, industrial operations, and emergency response, where real-time information about a person’s location or movement is …
-
Low-Cost and High-Throughput Optofluidic Add-on Device for Light Sheet Imaging of Larval and Adult C. Elegans
In this research, we have made modifications to our low-cost light sheet platform, allowing us to capture high-content cross-sectional images of nematodes' nervous systems at earlier stages of development and with higher throughputs. Our platform was put to the test in imaging larval and adult pan …
-
Democratizing interaction mining
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2024-03-01 without embargo terms
-
Integrable and Integrated Optoelectronic Devices Grown by Metalorganic Chemical Vapor Deposition
… several integrable and integrated optoelectronic devices grown by metalorganic chemical vapor deposition (MOCVD) crystal growth. The emphasis is on device design and fabrication using crystal growth techniques to minimize post-growth processing and add design flexibility.
-
Energy-efficient Neuromorphic Computing for Resource-constrained Internet of Things Devices
Due to the limited computation and storage resources of Internet of Things (IoT) devices, many emerging intelligent applications based on deep learning techniques heavily depend on cloud computing for computation and storage. However, cloud computing faces technical issues with long latency, poor …
-
Imperfection-Aware Design of CNFET Digital VLSI Circuits
<p>Carbon nanotube field-effect transistor (CNFET) is one of the promising candidates as extensions to silicon CMOS devices. The CNFET, which is a 1-D structure with a near-ballistic transport capability, can potentially offer excellent device characteristics and order-of-magnitude better …
-
Development of inversion-mode and junctionless Indium-Gallium-Arsenide MOSFETs
This PhD covers the development of planar inversion-mode and junctionless Al2O3/In0.53Ga0.47As metal-oxidesemiconductor field-effect transistors (MOSFETs). An implant activation anneal was developed for the formation of the source and drain (S/D) of the inversionmode MOSFET. Fabricated …
-
Process Development for Aluminum Gallium Nitride-Based Enhancement- and Depletion -Mode HEMTs
This dissertation documents the development of high-performance gate-recessed HEMTs in the AlGaN-GaN material system. The primary goal of the dissertation research is the development of processes that are suitable for fabrication of AlGaN/GaN HEMTs with precise threshold voltage control for both …
-
Systems of Nonlinear Algebraic Equations Arising in Simulation of Semiconductor Devices
In this thesis we present several formulations of the system of elliptic partial differential equations that model a semiconductor device. We use standard finite difference methods to discretize these equations and derive systems of nonlinear equations. Due to the extremely large number of unknowns …
-
Efficient Deep Learning Systems for Visual Perception on the Edge
Deep learning for visual perception on edge devices has become increasingly critical, driven by emerging applications in autonomous driving and AR/VR. Typically, sparse convolution on 3D point clouds and Visual Language Models (VLMs) for image processing are two important methods for visual …
-
Enable Intelligence on Billion Devices with Deep Learning
<p>With the proliferation of edge computing and Internet of Things (IoT), billions of edge devices (e.g., smartphone, AR/VR headset, autonomous car, etc) are deployed in our daily life and constantly generating the gigantic amount of data at the network edge. Bringing deep learning to such huge …
-
Device-type Profiling using Packet Inter-Arrival Time for Network Access Control
Network Access Control (NAC) systems are technologies and defined policies typically established to control the access of devices attempting to connect to enterprise networks. However, NAC limitations have led to security threats that can lead to illegal and unauthorised access to networks as well …
-
Learning to Adapt to Diverse Data and Systems Heterogeneity
Deep learning has revolutionized the field of artificial intelligence (AI), leading to significant advancements in various industries and seamlessly integrating into our everyday lives. From playing a crucial role in autonomous vehicles to aiding in disease diagnosis, deep learning has enabled …
Page 1 of 8