Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
5.3
2.5
Journals
Applied Sciences
Special Issues
Application of Deep Learning and Big Data Processing
applsci-logo
Submit to Special Issue Submit Abstract to Special Issue Review for Applied Sciences Propose a Special Issue

Journal Menu

► Journal Menu

Journal Browser

► Journal Browser
share announcement

Application of Deep Learning and Big Data Processing

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

Deadline for manuscript submissions: 20 September 2025 | Viewed by 5240

Special Issue Editor

Prof. Dr. Yuchong Hu

E-Mail Website
Guest Editor
School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan 430074, China
Interests: cloud storage; storage for AI; HPC; decentralized storage

Special Issue Information

Dear Colleagues,

In today's digital age, deep learning and big data processing has drawn significant attention in the scientific community. Deep learning exhibits remarkable capabilities in handling complex tasks such as image and speech recognition, natural language processing, and decision-making. Its ability to autonomously learn intricate patterns from data empowers applications in diverse domains, revolutionizing fields like healthcare, finance, and autonomous systems. Big data processing involves efficiently managing and analyzing vast datasets, unlocking valuable insights for informed decision-making and driving innovations across industries.

This Special Issue mainly focuses on the application of deep learning and big data processing techniques in various scientific fields. We welcome original papers and review papers related to the topics below. Authors are encouraged to delve into real-world case studies, offering insights into challenges in deploying deep learning models on large-scale datasets. We are also interested in papers on scalable, efficient big data processing frameworks that enable the seamless integration of deep learning technologies. The topics of interest include but are not limited to the following:

  • Computer Vision.
  • Speech, Natural Language Processing and Understanding.
  • Data Mining and Data Science.
  • Distributed Computing.
  • Big Data Infrastructure.
  • Social and Economic Aspects of Deep Learning

Prof. Dr. Yuchong Hu
Guest Editor

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

  • computer vision
  • natural language processing
  • machine learning
  • big data
  • data processing
  • AI for big data
  • data system for AI
  • distributed data management
  • large-scale systems for data analysis

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 (5 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

23 pages, 766 KiB  
Article
A Machine Learning Pipeline for Adenoma Detection in MRI: Integrating Deep Learning and Ensemble Classification
by Bernardo Gonçalves, Gonçalo Saldanha, Miguel Ramalho, Luísa Vieira and Pedro Vieira
Appl. Sci. 2025, 15(8), 4100; https://doi.org/10.3390/app15084100 - 8 Apr 2025
Viewed by 186
Abstract
Adrenal lesions are common findings in abdominal imaging, with adrenal adenomas being the most frequent type. Accurate detection of adrenal adenomas is essential to avoid unnecessary diagnostic procedures and treatments. However, conventional imaging-based evaluation relies heavily on the expertise of radiologists and can [...] Read more.
Adrenal lesions are common findings in abdominal imaging, with adrenal adenomas being the most frequent type. Accurate detection of adrenal adenomas is essential to avoid unnecessary diagnostic procedures and treatments. However, conventional imaging-based evaluation relies heavily on the expertise of radiologists and can be complicated by pseudo-lesions, overlapping imaging features, and suboptimal imaging techniques. To address these challenges, we propose an end-to-end machine learning pipeline that integrates deep learning-based lesion detection (FCOS) with an ensemble classifier for adrenal lesion classification in MRI. Our pipeline operates directly on broader regions of interest, eliminating the need for manual lesion segmentation. Our method was evaluated on a multi-sequence MRI dataset comprising 206 adenomas and 45 non-adenomas. The pipeline achieved 87.45% accuracy, 87.33% specificity, and 87.63% recall for adenoma classification, demonstrating competitive performance compared to prior studies. The results highlight strong non-adenoma identification while maintaining robust adenoma detection. Future research should focus on dataset expansion, external validation, and comparison with radiologist performance to further validate clinical applicability. Full article
(This article belongs to the Special Issue Application of Deep Learning and Big Data Processing)
►▼ Show Figures

Figure 1

17 pages, 6486 KiB  
Article
Detection of Small-Sized Electronics Endangering Facilities Involved in Recycling Processes Using Deep Learning
by Zizhen Liu, Shunki Kasugaya and Nozomu Mishima
Appl. Sci. 2025, 15(5), 2835; https://doi.org/10.3390/app15052835 - 6 Mar 2025
Viewed by 527
Abstract
In Japan, local governments implore residents to remove the batteries from small-sized electronics before recycling them, but some products still contain lithium-ion batteries. These residual batteries may cause fires, resulting in serious injuries or property damage. Explosive materials such as mobile batteries (such [...] Read more.
In Japan, local governments implore residents to remove the batteries from small-sized electronics before recycling them, but some products still contain lithium-ion batteries. These residual batteries may cause fires, resulting in serious injuries or property damage. Explosive materials such as mobile batteries (such as power banks) have been identified in fire investigations. Therefore, these fire-causing items should be detected and separated regardless of whether small-sized electronics recycling or other recycling processes are in use. This study focuses on the automatic detection of fire-causing items using deep learning in recycling small-sized electronic products. Mobile batteries were chosen as the first target of this approach. In this study, MATLAB R2024b was applied to construct the You Only Look Once version 4 deep learning algorithm. The model was trained to enable the detection of mobile batteries. The results show that the model’s average precision value reached 0.996. Then, the target was expanded to three categories of fire-causing items, including mobile batteries, heated tobacco (electronic cigarettes), and smartphones. Furthermore, real-time object detection on videos using the trained detector was carried out. The trained detector was able to detect all the target products accurately. In conclusion, deep learning technologies show significant promise as a method for safe and high-quality recycling. Full article
(This article belongs to the Special Issue Application of Deep Learning and Big Data Processing)
►▼ Show Figures

Figure 1

18 pages, 949 KiB  
Article
Coupling Secret Sharing with Decentralized Server-Aided Encryption in Encrypted Deduplication
by Chuang Gan, Weichun Wang, Yuchong Hu, Xin Zhao, Shi Dun, Qixiang Xiao, Wei Wang and Huadong Huang
Appl. Sci. 2025, 15(3), 1245; https://doi.org/10.3390/app15031245 - 26 Jan 2025
Viewed by 538
Abstract
Outsourcing storage to the cloud can save storage costs and is commonly used in businesses. It should fulfill two major goals: storage efficiency and data confidentiality. Encrypted deduplication can achieve both goals via performing deduplication to eliminate the duplicate data within encrypted data. [...] Read more.
Outsourcing storage to the cloud can save storage costs and is commonly used in businesses. It should fulfill two major goals: storage efficiency and data confidentiality. Encrypted deduplication can achieve both goals via performing deduplication to eliminate the duplicate data within encrypted data. Traditional encrypted deduplication generates the encryption key on the client side, which poses a risk of offline brute-force cracking of the outsourced data. Server-aided encryption schemes have been proposed to strengthen the confidentiality of encrypted deduplication by distributing the encryption process to dedicated servers. Existing schemes rely on expensive cryptographic primitives to provide a decentralized setting on the dedicated servers for scalability. However, this incurs substantial performance slowdown and can not be applied in practical encrypted deduplication storage systems. In this paper, we propose a new decentralized server-aided encrypted deduplication approach for outsourced storage, called ECDedup, which leverages secret sharing to achieve secure and efficient key management. We are the first to use the coding matrix as the encryption key to couple the encryption and encoding processes in encrypted deduplication. We also propose a acceleration scheme to speed up the encryption process of our ECDedup. We prototype ECDedup in cloud environments, and our experimental results based on the real-world backup datasets show that ECDedup can improve the client throughput by up to 51.9% compared to the state-of-the-art encrypted deduplication schemes. Full article
(This article belongs to the Special Issue Application of Deep Learning and Big Data Processing)
►▼ Show Figures

Figure 1

14 pages, 398 KiB  
Article
Integrating Environmental Data for Mental Health Monitoring: A Data-Driven IoT-Based Approach
by Sanaz Zamani, Minh Nguyen and Roopak Sinha
Appl. Sci. 2025, 15(2), 912; https://doi.org/10.3390/app15020912 - 17 Jan 2025
Viewed by 1346
Abstract
Mental health disorders constitute a significant global challenge, compounded by the limitations of traditional management approaches that rely heavily on subjective self-reports and infrequent professional evaluations. This study presents a groundbreaking IoT-based system that integrates big data analytics, fuzzy logic, and machine learning [...] Read more.
Mental health disorders constitute a significant global challenge, compounded by the limitations of traditional management approaches that rely heavily on subjective self-reports and infrequent professional evaluations. This study presents a groundbreaking IoT-based system that integrates big data analytics, fuzzy logic, and machine learning to revolutionise mental health monitoring. In contrast to existing solutions, the proposed system uniquely incorporates environmental factors, such as temperature and humidity in enclosed spaces—critical yet often overlooked contributors to emotional well-being. By leveraging IoT devices to collect and process large-scale ambient data, the system provides real-time classification and personalised visualisation tailored to individual sensitivity profiles. Preliminary results reveal high accuracy, scalability, and the potential to generate actionable insights, creating dynamic feedback loops for continuous improvement. This innovative approach bridges the gap between environmental conditions and mental healthcare, promoting a transformative shift from reactive to proactive care and laying the groundwork for predictive environmental health systems. Full article
(This article belongs to the Special Issue Application of Deep Learning and Big Data Processing)
►▼ Show Figures

Figure 1

23 pages, 5464 KiB  
Article
Semi-Supervised Training for (Pre-Stack) Seismic Data Analysis
by Edgar Ek-Chacón, Erik Molino-Minero-Re, Paul Erick Méndez-Monroy, Antonio Neme and Hector Ángeles-Hernández
Appl. Sci. 2024, 14(10), 4175; https://doi.org/10.3390/app14104175 - 15 May 2024
Cited by 3 | Viewed by 1759
Abstract
A lack of labeled examples is a problem in different domains, such as text and image processing, medicine, and static reservoir characterization, because supervised learning relies on vast volumes of these data to perform successfully, but this is quite expensive. However, large amounts [...] Read more.
A lack of labeled examples is a problem in different domains, such as text and image processing, medicine, and static reservoir characterization, because supervised learning relies on vast volumes of these data to perform successfully, but this is quite expensive. However, large amounts of unlabeled data exist in these domains. The deep semi-supervised learning (DSSL) approach leverages unlabeled data to improve supervised learning performance using deep neural networks. This approach has succeeded in image recognition, text classification, and speech recognition. Nevertheless, there have been few works on pre-stack seismic reservoir characterization, in which knowledge of rock and fluid properties is fundamental for oil exploration. This paper proposes a methodology to estimate acoustic impedance using pre-stack seismic data and DSSL with a recurrent neural network. The few labeled datasets for training were pre-processed from raw seismic and acoustic impedance data from five borehole logs. The results showed that the acoustic impedance estimation at the well location and outside it was better predicted by the DSSL compared to the supervised version of the same neural network. Therefore, employing a large amount of unlabeled data can be helpful in the development of seismic data interpretation systems. Full article
(This article belongs to the Special Issue Application of Deep Learning and Big Data Processing)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-5
Back to TopTop