READ ME File: 
Dataset for PhD thesis "Runtime Algorithm and Hardware Management for Efficient DNN Inference on Mobile and Embedded Platforms"

Dataset DOI: 
https://doi.org/10.5258/SOTON/D3575

Date that the file was created: 
June 2025

-------------------
GENERAL INFORMATION
-------------------

ReadMe Author: 
Lei Xun, University of Southampton 

ORCID ID:
https://orcid.org/0000-0003-0765-6726

This dataset supports the thesis entitled "Runtime Algorithm and Hardware Management for Efficient DNN Inference on Mobile and Embedded Platforms"
AWARDED BY: Univeristy of Southampton
DATE OF AWARD: 2025

DESCRIPTION OF THE DATA:
This dataset supports the PhD thesis: Lei Xun (2025), "Runtime Algorithm and Hardware Management for Efficient DNN Inference on Mobile and Embedded Platforms", University of Southampton, Faculty of Engineering and Physical Sciences, School of Electronics and Computer Science, PhD Thesis, 150pp.

The data were generated during my PhD experiments and are provided as a Microsoft Excel (.xlsx) file.

This dataset contains:
Raw experiment data for Fig 3.4, 3.9, 3.10, 3.11, 3.12, 3.13, 3.14, 3.15, 4.1, 4.4, 4.5, 4.6, 4.7, 4.8, 4.9, 4.10, 4.11, 4.12, 4.13, 4.14, 5.2, and 5.3.

Date of data collection: March 2018 to March 2023

Information about geographic location of data collection: 
University of Southampton, United Kingdom.

Related projects/Funders:
Engineering and Physical Sciences Research Council (EPSRC) Spatial ML Centre (Grant EP/S030069/1)

--------------------------
SHARING/ACCESS INFORMATION
--------------------------

Licence:
CC BY

Recommended citation for the data:
Lei Xun (2025), Dataset for PhD thesis "Runtime Algorithm and Hardware Management for Efficient DNN Inference on Mobile and Embedded Platforms", University of Southampton, Faculty of Engineering and Physical Sciences, School of Electronics and Computer Science, PhD Thesis Dataset, 150pp.


This dataset supports the thesis:
Lei Xun (2025), "Runtime Algorithm and Hardware Management for Efficient DNN Inference on Mobile and Embedded Platforms", University of Southampton, Faculty of Engineering and Physical Sciences, School of Electronics and Computer Science, PhD Thesis, 150pp.


Related publication:
1. Wei Lou*, Lei Xun*, Amin Sabet, Jia Bi, Jonathon Hare, and Geoff V. Merrett. Dynamic-OFA: Runtime DNN Architecture Switching for Performance Scaling on Heterogeneous Embedded Platforms. Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2021.
-Paper: https://arxiv.org/abs/2105.03596
-Data: https://eprints.soton.ac.uk/448421/

2. Lei Xun, Long Tran-Thanh, Bashir M. Al-Hashimi, and Geoff V. Merrett. Optimising Resource Management for Embedded Machine Learning. Design, Automation and Test in Europe Conference (DATE), 2020.
-Paper: https://arxiv.org/abs/2105.03608
-Data: https://eprints.soton.ac.uk/436356/

3. Lei Xun, Long Tran-Thanh, Bashir M. Al-Hashimi, and Geoff V. Merrett. Incremental Training and Group Convolution Pruning for Runtime DNN Performance Scaling on Heterogeneous Embedded Platforms. Workshop on Machine Learning for CAD (MLCAD), 2019.
-Paper: https://arxiv.org/abs/2105.03600
-Data: https://eprints.soton.ac.uk/437753/