Dataset for sparse data reconstruction with AI
- Citation Author(s):
-
Mingqiang Zhang (Shandong University)Haixia Zhang (Shandong University)Dongfeng Yuan (Shandong University)
- Submitted by:
- Mingqiang Zhang
- Last updated:
- DOI:
- 10.21227/xssz-sx65
- Data Format:
- Links:
311 views
- Categories:
- Keywords:
Abstract
A dataset asscociated with paper “Learning-based Sparse Data Reconstruction for Compressed Data Aggregation in IoT Networks” in IEEE Internet of Things Journal. Five different structured sparse models (SSMs) are considered in the synthesized dataset, including random sparse (Sparse Model A), row sparse (Sparse Model B), row-sparse with embedded element-sparse (Sparse Model C), row-sparse plus element-spares (Sparse Model D) and block diagonal sparse (Block Sparse or group sparse).
Baidu：https://pan.baidu.com/s/1pMvrcQ3-MT_riIxnsbQDbw Code：fgoe
GoogleDrive：https://drive.google.com/drive/folders/10VP49rftNlN4ezKXtvt8fZIQtZEi4q68?usp=sharing
If you have any questions or suggestions, do not hesitate to contact the corresponding author: mqzhang@mail.sdu.edu.cn
Instructions:
Please refer to the paper“Learning-based Sparse Data Reconstruction for Compressed Data Aggregation in IoT Networks”on IEEE Xplore.
https://ieeexplore.ieee.org/abstract/document/9354846
The results for Fig.7 in the paper are as follows:
MSE=[0.0079473, 0.03834, 0.00010, 0.02004, 0.00141, 0.00350;//CR=1/4
0.0084604, 0.08905, 0.00018, 0.03870, 0.00556, 0.00483;//CR=1/8
0.0080209, 0.12295, 0.00044, 0.05009, 0.00618, 0.02195];//CR=1/16
SSIM=[0.9999415, 0.84560, 0.99955, 0.89072, 0.99406, 0.98824 ;//CR=1/4
0.9999427, 0.63513, 0.99918, 0.76592, 0.97515, 0.98379 ; //CR=1/8
0.9999425, 0.34732, 0.99807, 0.67469, 0.97246, 0.92214 ];//CR=1/16
PSNR=[25.6037168, 23.38230, 43.61214, 22.26013, 32.33393, 30.98234; //CR=1/4
25.3328179, 19.63983, 41.36600, 19.34246, 25.92045, 29.56332;//CR=1/8
25.5474088, 18.17754, 38.41058, 18.21483, 25.24101, 22.77923];//CR=1/16
