Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
5.3
2.6
Journals
Electronics
Special Issues
Data Compression and Its Application in AI
share announcement

Data Compression and Its Application in AI

A special issue of Electronics (ISSN 2079-9292). This special issue belongs to the section "Computer Science & Engineering".

Deadline for manuscript submissions: closed (31 January 2022) | Viewed by 6010

Special Issue Editors

Prof. Dr. Hiroshi Sakamoto

E-Mail Website
Guest Editor
Graduate School of Computer Science and Systems Engineering, Kyushu Institute of Technology, 680-4 Kawazu, Iizuka-shi, Fukuoka 820-8502, Japan
Interests: lossless and lossy data compression algorithm and its application to compressed information processing, e.g., information retrieval, data mining, and machine learning on compressed data
Dr. Shinichi Yamagiwa

E-Mail Website
Guest Editor
1. Faculty of Engineering, Information and Systems, University of Tsukuba, 1-1-1 Tennodai, Tsukuba, Ibaraki 305-8573, Japan
2. JST, PRESTO, 4-1-8 Honcho, Kawaguchi, Saitama 332-0012, Japan
Interests: lossless and lossy data compression; IoT systems and applications; computer architecture; embedded system; parallel and distributed system

Special Issue Information

Dear Colleagues,

Research in the past decade has shown that data compression and AI are deeply related to each another. Data compression aims to obtain a succinct representation of redundant data, while AI aims to abstract complex data. Here, it is important to note that algorithms in one field might expand the other. In image/video compression, for example, predicting pixel values is one of the most important tasks that can be improved using deep learning for image recognition. In contrast, deep learning for image recognition can be accelerated by using compressed images as the training data. Such are applications of lossy compression to AI. Moreover, we can also find a close relation between lossless compression and AI, e.g., in language processing. As part of machine translation, pairs of sentences in the target and source languages are given as the training data. In fact, it is known that the translation accuracy can be improved by directly learning from the compressed training data. In this way, data compression and AI are developing while interacting with each other. Addressing this Special Issue, we invite a wide range of theoretical/empirical research on both AI for data compression and compression for AI. We welcome papers including but not limited to the following:

Theoretical research of data compression

            Coding methods and expression of compressed information;

            Algorithms for making compact data structures;

            Analytical study of data compression;

            Data compression mechanisms based on machine learning approaches;

            Data processing from compressed data structures.

Applications of artificial intelligence with data compression

            Lossy and lossless data compression in AI；

            Cognitive applications with data compression；

            Image and visual applications with data compression；

            Human and healthcare applications with data compression；

            Medical and biological applications with data compression；

            Bigdata processing and data mining with data compression.

Systems with data compression

            IoT systems with data compression；

            Mobile and ubiquitous computing with data compression；

            Processors and accelerators for machine learning with data compression.

Implementation and benchmarks

            Software/hardware implementation of machine learning with data compression；

            Case studies of LSI and FPGA design for artificial intelligence with data compression；

            System-wide usage of data compression in AI applications.

Research survey

            Studies from wide areas of scientific research with data compression；

            Algorithm surveys of data compression with AI；

            Studies of Bigdata processing applying AI with data compression.

Open data and its processing methods by machine learning approaches with data compression

            Application of social open data with data compression;

            Sensory data and image databases with data compression;

            Applications of open data with data compression.

Prof. Dr. Hiroshi Sakamoto
Dr. Shinichi Yamagiwa
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Electronics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Published Papers (2 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

13 pages, 932 KiB  
Article
A Compression-Based Multiple Subword Segmentation for Neural Machine Translation
by Keita Nonaka, Kazutaka Yamanouchi, Tomohiro I, Tsuyoshi Okita, Kazutaka Shimada and Hiroshi Sakamoto
Electronics 2022, 11(7), 1014; https://doi.org/10.3390/electronics11071014 - 24 Mar 2022
Cited by 9 | Viewed by 1819
Abstract
In this study, we propose a simple and effective preprocessing method for subword segmentation based on a data compression algorithm. Compression-based subword segmentation has recently attracted significant attention as a preprocessing method for training data in neural machine translation. Among them, BPE/BPE-dropout is [...] Read more.
In this study, we propose a simple and effective preprocessing method for subword segmentation based on a data compression algorithm. Compression-based subword segmentation has recently attracted significant attention as a preprocessing method for training data in neural machine translation. Among them, BPE/BPE-dropout is one of the fastest and most effective methods compared to conventional approaches; however, compression-based approaches have a drawback in that generating multiple segmentations is difficult due to the determinism. To overcome this difficulty, we focus on a stochastic string algorithm, called locally consistent parsing (LCP), that has been applied to achieve optimum compression. Employing the stochastic parsing mechanism of LCP, we propose LCP-dropout for multiple subword segmentation that improves BPE/BPE-dropout, and we show that it outperforms various baselines in learning from especially small training data. Full article
(This article belongs to the Special Issue Data Compression and Its Application in AI)
►▼ Show Figures

Figure 1

13 pages, 4396 KiB  
Article
Adaptive Lossless Image Data Compression Method Inferring Data Entropy by Applying Deep Neural Network
by Shinichi Yamagiwa, Wenjia Yang and Koichi Wada
Electronics 2022, 11(4), 504; https://doi.org/10.3390/electronics11040504 - 9 Feb 2022
Cited by 8 | Viewed by 2591
Abstract
When we compress a large amount of data, we face the problem of the time it takes to compress it. Moreover, we cannot predict how effective the compression performance will be. Therefore, we are not able to choose the best algorithm to compress [...] Read more.
When we compress a large amount of data, we face the problem of the time it takes to compress it. Moreover, we cannot predict how effective the compression performance will be. Therefore, we are not able to choose the best algorithm to compress the data to its minimum size. According to the Kolmogorov complexity, the compression performances of the algorithms implemented in the available compression programs in the system differ. Thus, it is impossible to deliberately select the best compression program before we try the compression operation. From this background, this paper proposes a method with a principal component analysis (PCA) and a deep neural network (DNN) to predict the entropy of data to be compressed. The method infers an appropriate compression program in the system for each data block of the input data and achieves a good compression ratio without trying to compress the entire amount of data at once. This paper especially focuses on lossless compression for image data, focusing on the image blocks. Through experimental evaluation, this paper shows the reasonable compression performance when the proposed method is applied rather than when a compression program randomly selected is applied to the entire dataset. Full article
(This article belongs to the Special Issue Data Compression and Its Application in AI)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-2
Back to TopTop