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 6 of 6 for “"Low-Power Edge Devices"”.

  1. Towards a Green Future: Energy Efficient Conversational AI on the Edge

    … can be executed in an energy efficient way on low-power edge devices. To this end, I set up a cloud compute cluster consisting of three Raspberry Pis based on the ARM architecture. I then built a conversational AI app, a simple chatbot, to run on this cluster. My proposed framework reduces the …

    texas-state Repository record for Towards a Green Future: Energy Efficient Conversational AI on the Edge (opens in a new tab)

  2. Efficient Processing of Convolutional Neural Networks on the Edge: A Hybrid Approach Using Hardware Acceleration and Dual-Teacher Compression

    … Convolutional Neural Networks (CNNs) for edge computing in computer vision applications by developing specialized hardware solutions that maintain high accuracy and perform real-time inference. Driven by open-source hardware design frameworks such as FINN and HLS4ML, this research focuses …

    ucf Repository record for Efficient Processing of Convolutional Neural Networks on the Edge: A Hybrid Approach Using Hardware Acceleration and Dual-Teacher Compression (opens in a new tab)

  3. Towards real-time object detection on edge with deep neural networks

    … inter-frame information fusing, model knowledge distillation, advanced model flow control for progressive inference, and hardware oriented model design and optimization. More specifically, we proposed a novel cross-frame verification scheme for spatial temporal fused object detection model …

    missouri Repository record for Towards real-time object detection on edge with deep neural networks (opens in a new tab)

  4. Efficient Neural Network Accelerators for Low-Cost Edge Systems

    … algorithms are challenging to be executed on low-cost and low-power edge systems due to the lack of sufficient computational capability in low-cost, battery-powered edge devices. Therefore, low-cost and low-power edge devices require a highly optimized hardware accelerator to achieve better …

    umn Repository record for Efficient Neural Network Accelerators for Low-Cost Edge Systems (opens in a new tab)

  5. Designing Right-Provisioned System Architectures for Edge Computing

    … various industry sectors. Millions of smart devices, sensors, and actuators collaborate to monitor and manage the physical environment and human systems in the IoT paradigm. The traditional IoT is designed as a distributed system, with low-power edge devices collecting data and transmitting …

    arizona-thes Repository record for Designing Right-Provisioned System Architectures for Edge Computing (opens in a new tab)

  6. Energy-Efficient Semi-Supervised Optimization for PAPR Reduction in OTSM for High-Mobility 6G Wireless Communications

    … in high-mobility doubly dispersive channels and lower computational complexity compared to OFDM and OTFS. However, OTSM suffers from a high PAPR, which reduces power amplifier efficiency, increases energy consumption, and degrades transmission reliability. Classical PAPR reduction techniques such …

    calgary Repository record for Energy-Efficient Semi-Supervised Optimization for PAPR Reduction in OTSM for High-Mobility 6G Wireless Communications (opens in a new tab)