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 133 for “"Edge-AI"”.
-
MODEL ADAPTATION FOR EDGE AI
Deployment of Deep Neural Networks (DNNs) on edge devices presents significant challenges due to their computational demands. Existing model compression techniques often fall short by being oblivious to downstream user-specific tasks. This thesis addresses the challenge of adapting DNN models …
-
Deep Learning Anomaly Detection Using Edge AI
… is possible to distribute anomaly detection to edge devices without sacrificing accuracy, and the runtime can be improved with further research.
-
Exploiting compression techniques for efficient edge AI
… for achieving Artificial Intelligence on edge devices (edge AI). There are three major categories of DNN model compression techniques: a) pruning, methods that remove weights from DNN models; b) quantization, methods that reduce the bit length of weight and/or activation values of DNN …
-
Benchmark pro Edge AI aplikace v UWB IIoT
… (MCU) z hlediska jejich vhodnosti pro Edge AI aplikace v IIoT prostředí. Práce definuje soubor evaluačních metrik a vytváří komplexní benchmark pro testování výkonnosti a efektivity mikrokontrolerů při zpracování úloh umělé inteligence. V rámci výzkumu bylo otestováno deset různých …
-
Advancing Edge AI through Integrated Neuromorphic Algorithms and Hardware
… many applications operate under strict constraints on latency, bandwidth, privacy, and power availability. Meeting these demands increasingly requires deploying machine learning at the edge to process data locally rather than relying on remote cloud infrastructure. These limitations highlight …
-
Real-Time Facial Expression Recognition Using Edge AI Accelerators
… problem for computer vision systems, especially edge computing systems. Current Deep Learning (DL) methods rely on large-scale Convolutional Neural Networks (CNN) which require millions of floating point operations (FLOPS) to accomplish similar image classification tasks. However, on edge and IoT …
-
Near-Memory Computing Architectures for Scalable Edge AI Applications
Artificial intelligence (AI) and machine learning (ML) are rapidly permeating nearly every aspect of modern life, frompersonal devices and autonomous systems to industrial automation and environmental monitoring. The growing demandfor intelligence at the network edge is reshaping how computing …
-
An Edge AI Test Bench for Unsupervised Anomaly Detection
… that are compact enough to run on edge hardware, stable enough to generalize across production runs, and informative enough to support downstream anomaly detection without labeled fault examples. This thesis addresses all three requirements on a purpose-built, low-cost CNC-inspired …
-
Dora: QoE-aware hybrid parallelism for distributed edge AI
Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2027-12-01
-
3D Integration Technology and Near-Memory Computing for Edge AI
In the era of artificial intelligence of things (AIoT), distributed processing on local devices is growing in popularity. This stems from the need to reduce data transfer to and from central servers, with concerns about privacy and latency encouraging the processing of AI applications on edge …
-
Lightweight edge AI vision models for IoT-based insect monitoring
… With recent advances in Artificial Intelligence (AI) and Information and Communications Technology (ICT), there is an opportunity to automate the insect monitoring process effectively and directly in the field. However, key challenges persist, such as limited energy availability, unreliable …
-
Federated learning for edge AI : realistic hardware-software system co-design
Federated learning (FL) has revolutionized edge artificial intelligence by enabling decentralized, privacy-preserving model training. However, real-world edge scenarios pose challenges stemming from mobility, heterogeneous resources, and limited connectivity. This dissertation addresses these gaps …
-
Resource efficient distributed inference of deep neural networks for Edge AI
… However, executing these models efficiently on edge devices remains a major challenge due to their high computational, energy, and bandwidth demands. This dissertation presents a unified framework for resource-efficient distributed inference of DNNs in Edge AI, built upon three tightly coupled …
-
Exploring Simplified Reservoir Computing Systems for Resource-constrained Edge AI Hardware
… in which only the output weights require training, while the recurrent internal reservoir remains fixed. This characteristic significantly reduces training complexity and computation time, making ESNs particularly attractive for real-time processing and resource-constrained, low-power …
-
ON-CHIP ARCHITECTURES FOR ENERGY-EFFICIENT EDGE AI COMPUTING AND HARDWARE SECURITY
… on-chip architectures for energy-efficient edge AI computing and hardware security. As AI inference moves from cloud to resource-constrained edge systems, edge-system design is limited not only by arithmetic cost, but also by the system bandwidth and data-movement cost. Meanwhile, edge …
-
Design of Next-Generation Hardware-Accelerated Edge AI Engines for Privacy Preservation}
Artificial Intelligence (AI) has become ubiquitous across domains such as healthcare, finance, and autonomous systems, where it routinely processes sensitive personal and organizational data. This widespread adoption raises urgent concerns about model leakage, inference attacks, and the …
-
Efficient, secure, and intelligent wireless systems: From edge AI to network management
In one sentence: this thesis makes AI efficient, secure, and explainable enough for real-time wireless systems. The vision of AI-native 6G networks is blocked by three barriers. First, state-of-the-art deep learning models are too large and power-hungry for battery-powered edge receivers, where …
Page 1 of 7