[go: up one dir, main page]

 
 
applsci-logo

Journal Browser

Journal Browser

Recent Research on Big Data Mining for Social Networks

A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Computing and Artificial Intelligence".

Deadline for manuscript submissions: 30 April 2025 | Viewed by 3198

Special Issue Editors


E-Mail Website
Guest Editor
Department of Computer Engineering in School of Software, College of Engineering, Jeju National University, Jeju 63243, Republic of Korea
Interests: big data computing; intelligent computing & Artificial Intelligence; cloud computing

E-Mail Website
Guest Editor
Department of Computer Software and Engineering, Soonchunhyang University, Asan 31538, Republic of Korea
Interests: social network analysis; data mining; big data; distribute system
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

A social network is a digital platform for creating and maintaining relationships between individuals or businesses, allowing users to share information and interact with each other. These platforms take many forms and have many purposes, and they typically offer features such as user profiles, friend connections, content sharing, group participation, and message sending. The platforms for these social networks have hundreds of millions of active users worldwide, and the development of social media has significantly changed the paradigm of communication and information sharing. In particular, the analysis of big data generated by social networks is very important and is becoming more valuable through machine learning, deep learning, etc. This Special Issue aims to provide an overview of the latest technologies and trends in the ever-changing world of social networks and big data processing.

The main topics include, but are not limited to:

  • Analyzing graph data to identify patterns and connections in networks;
  • Real-time analytics and decision making using big data mining techniques;
  • Social influence and opinion analysis;
  • Text and sentiment analysis using large amounts of text data;
  • Privacy and security with large-scale data collection and analysis;
  • Applications of machine learning and deep learning;
  • Fake news and information reliability;
  • Extended reality experiences utilizing social media, AR, and VR;
  • Applied technologies related to social networks and big data.

Dr. Jisu Park
Prof. Dr. Joon-Min Gil
Prof. Dr. Doo-Soon Park
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. Applied Sciences 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.

Keywords

  • social network
  • big data
  • machine learning
  • deep learning
  • data mining
  • large-scale data

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue policies can be found here.

Published Papers (1 paper)

Order results
Result details
Select all
Export citation of selected articles as:

Research

18 pages, 10575 KiB  
Article
Synthetic Image Generation Using Conditional GAN-Provided Single-Sample Face Image
by Muhammad Ali Iqbal, Waqas Jadoon and Soo Kyun Kim
Appl. Sci. 2024, 14(12), 5049; https://doi.org/10.3390/app14125049 - 10 Jun 2024
Cited by 1 | Viewed by 2416
Abstract
The performance of facial recognition systems significantly decreases when faced with a lack of training images. This issue is exacerbated when there is only one image per subject available. Probe images may contain variations such as illumination, expression, and disguise, which are difficult [...] Read more.
The performance of facial recognition systems significantly decreases when faced with a lack of training images. This issue is exacerbated when there is only one image per subject available. Probe images may contain variations such as illumination, expression, and disguise, which are difficult to recognize accurately. In this work, we present a model that generates six facial variations from a single neutral face image. Our model is based on a CGAN, designed to produce six highly realistic facial expressions from one neutral face image. To evaluate the accuracy of our approach comprehensively, we employed several pre-trained models (VGG-Face, ResNet-50, FaceNet, and DeepFace) along with a custom CNN model. Initially, these models achieved only about 76% accuracy on single-sample neutral images, highlighting the SSPP challenge. However, after fine-tuning on the synthetic expressions generated by our CGAN from these single images, their accuracy increased significantly to around 99%. Our method has proven highly effective in addressing SSPP issues, as evidenced by the significant improvement achieved. Full article
(This article belongs to the Special Issue Recent Research on Big Data Mining for Social Networks)
Show Figures

Figure 1

Figure 1
<p>Proposed CGAN architecture for synthetic image generation.</p>
Full article ">Figure 2
<p>Proposed discriminator architecture.</p>
Full article ">Figure 3
<p>Proposed generator architecture.</p>
Full article ">Figure 4
<p>Image pairs for training CGAN. Here, we paired each neutral face image with six different expression images, respectively. In (<b>A</b>), we paired the neutral face image with illumination change image. In (<b>B</b>), we paired the neutral face image with anger image. In (<b>C</b>), we paired the neutral face image with the glasses image. In (<b>D</b>), we paired the neutral face image with the disguise image. In (<b>E</b>), we paired the neutral face with the stare image. In (<b>F</b>), we paired the neutral face with the smile image.</p>
Full article ">Figure 5
<p>Containing set of paired images for CGAN testing. A neutral image of a person is paired with the expressions of different individuals for testing each CGAN performance. In (<b>A</b>), we paired the neutral face image with the stare image of a different individual. In (<b>B</b>), we paired the neutral face image with the smile image of a female individual. In (<b>C</b>), we paired neutral face image with the anger image of a different individual. In (<b>D</b>), we paired the neutral face image with the glasses image of a different individual. In (<b>E</b>), we paired the neutral face with the illumination change image of a different individual. In (<b>F</b>), we paired the neutral face with a disguised image of a female individual. Here, the reference paired images are identity-independent.</p>
Full article ">Figure 6
<p>Six generated variations provided from a single neutral face image. The variations are generated glasses, generated illumination, generated anger, generated stare, generated smile, and generated glasses. All these expressions were generated from a single neutral face image.</p>
Full article ">Figure 7
<p>One-on-one comparison of the generated and real image/original of the same person.</p>
Full article ">Figure 8
<p>Six generated facial variations for a female individual with darker skin tone.</p>
Full article ">Figure 9
<p>Six generated facial variations for a male individual with darker skin tone.</p>
Full article ">Figure 10
<p>Illustration of training and validation accuracies, along with training loss and validation loss of the Convolutional Neural Network (CNN).</p>
Full article ">Figure 11
<p>Original images of the person used for testing the performance of the CNN model.</p>
Full article ">Figure 12
<p>Accuracy comparison with state-of-the-art SSPP methods [<a href="#B17-applsci-14-05049" class="html-bibr">17</a>,<a href="#B19-applsci-14-05049" class="html-bibr">19</a>,<a href="#B20-applsci-14-05049" class="html-bibr">20</a>,<a href="#B26-applsci-14-05049" class="html-bibr">26</a>].</p>
Full article ">Figure 13
<p>Smile expression generation on randomly sampled images outside the dataset.</p>
Full article ">Figure 14
<p>Stare expression generation on randomly sampled images outside the dataset.</p>
Full article ">
Back to TopTop