DeepComp: A Hybrid Framework for Data Compression Using Attention Coupled Autoencoder

被引:9
|
作者
Sriram, S. [1 ]
Dwivedi, Arun K. [2 ]
Chitra, P. [1 ]
Sankar, V. Vijay [1 ]
Abirami, S. [1 ]
Durai, S. J. Rethina [1 ]
Pandey, Divya [2 ]
Khare, Manoj K. [2 ]
机构
[1] Thiagarajar Coll Engn, Dept Comp Sci & Engn, Madurai, Tamil Nadu, India
[2] C DAC, HPC S&EA Grp, Pune 411008, Maharashtra, India
关键词
Deep learning; Multilayer autoencoder; Compression ratio; Attention; Reconstruction loss; EFFICIENT; ALGORITHM;
D O I
10.1007/s13369-022-06587-x
中图分类号
O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];
学科分类号
07 ; 0710 ; 09 ;
摘要
Due to the evolution of new media formats, emphasis on appropriate compression of data becomes paramount. Compression algorithms employed in real-time streaming applications must provide high compression ratio with acceptable loss. For such applications, the compression ratio of traditional compression algorithms used in Windows remains a challenge. Integrating deep learning algorithms with traditional Windows archivers can help the research objective in overcoming the challenges encountered by traditional Windows archivers. In this study, we propose a hybrid and robust compression framework named DeepComp that employs an attention-based autoencoder along with traditional Windows WinRAR archiver to compress both numerical and image data formats. Autoencoders- a well-known deep learning architecture widely used for data compression, outperform traditional archivers in terms of compression ratio but fall short in terms of reconstruction error. To minimize the reconstruction error, an attention layer is proposed in the autoencoder used in DeepComp. The attention layer accomplishes this by impeding the transition of spatial locality of the input data points during its processing in the compression and decompression phase. DeepComp is evaluated using numerical and image-type atmospheric and oceanic data obtained from the National Centers for Environmental Prediction (NCEP), which operates under National Oceanic and Atmospheric Administration (NOAA), USA. The performance analysis illustrates the robustness of DeepComp in compressing both numeric and image datatypes. In terms of compression ratio, it outperforms Windows archivers by an average of 69% and multilayer autoencoders by 48%. DeepComp also outperforms the reconstruction performance of the multilayer autoencoder.
引用
收藏
页码:10395 / 10410
页数:16
相关论文
共 50 条
  • [1] DeepComp: A Hybrid Framework for Data Compression Using Attention Coupled Autoencoder
    S. Sriram
    Arun K. Dwivedi
    P. Chitra
    V. Vijay Sankar
    S. Abirami
    S. J. Rethina Durai
    Divya Pandey
    Manoj K. Khare
    Arabian Journal for Science and Engineering, 2022, 47 : 10395 - 10410
  • [2] Low-loss data compression using deep learning framework with attention-based autoencoder
    Sriram, S.
    Chitra, P.
    Sankar, V. Vijay
    Abirami, S.
    Durai, S. J. Rethina
    INTERNATIONAL JOURNAL OF COMPUTATIONAL SCIENCE AND ENGINEERING, 2023, 26 (01) : 90 - 100
  • [3] scAAGA: Single cell data analysis framework using asymmetric autoencoder with gene attention
    Meng, Rui
    Yin, Shuaidong
    Sun, Jianqiang
    Hu, Huan
    Zhao, Qi
    COMPUTERS IN BIOLOGY AND MEDICINE, 2023, 165
  • [4] Efficient Lossy Satellite Image Compression using Hybrid Autoencoder Model
    Badr, Mohamed A.
    Elrewainy, Ahmed F.
    Elshafey, Mohamed A.
    2024 14TH INTERNATIONAL CONFERENCE ON ELECTRICAL ENGINEERING, ICEENG 2024, 2024, : 78 - 83
  • [5] Spatial-Temporal Autoencoder with Attention Network for Video Compression
    Sigger, Neetu
    Al-Jawed, Naseer
    Nguyen, Tuan
    IMAGE ANALYSIS AND PROCESSING, ICIAP 2022, PT III, 2022, 13233 : 290 - 300
  • [6] An Approach to Near-lossless Hyperspectral Data Compression using Deep Autoencoder
    Kuester, Jannick
    Gross, Wolfgang
    Middelmann, Wolfgang
    IMAGE AND SIGNAL PROCESSING FOR REMOTE SENSING XXVI, 2020, 11533
  • [7] Dual Autoencoder-based Framework for Image Compression and Decompression
    Patel, Bhargav
    FIFTEENTH INTERNATIONAL CONFERENCE ON MACHINE VISION, ICMV 2022, 2023, 12701
  • [8] An Autoencoder Framework With Attention Mechanism for Cross-Domain Recommendation
    Zhong, Shi-Ting
    Huang, Ling
    Wang, Chang-Dong
    Lai, Jian-Huang
    Yu, Philip S.
    IEEE TRANSACTIONS ON CYBERNETICS, 2022, 52 (06) : 5229 - 5241
  • [9] A hybrid autoencoder and index modulation framework for OTFS modulation
    Tek, Yusuf Islam
    Dogukan, Ali Tugberk
    Gevez, Yarkin
    Pihtili, Mehmet Ertug
    Basar, Ertugrul
    SIGNAL IMAGE AND VIDEO PROCESSING, 2025, 19 (01)
  • [10] Signal Enhancement for Downhole Microseismic Data Using Improved Attention Mechanism Based on Autoencoder Network
    Ge, Wenxuan
    Mao, Qinghui
    Zhou, Wei
    Gui, Zhixian
    Wang, Peng
    IEEE ACCESS, 2024, 12 : 156390 - 156400