[go: up one dir, main page]
 
 
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
Exploring AI: Methods and Applications for Data Mining
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

Exploring AI: Methods and Applications for Data Mining

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

Deadline for manuscript submissions: 31 August 2025 | Viewed by 5224

Special Issue Editors

Dr. Sukjun Lee

E-Mail Website
Guest Editor
Department, Business School, Kwangwoon University, 20 Kwangwoon-ro, Nowon-gu, Seoul 01897, Republic of Korea
Interests: data mining; machine/deep learning; big data analysis in healthcare
Special Issues, Collections and Topics in MDPI journals
Dr. Jae Joon Ahn

E-Mail Website
Guest Editor
Division of Data Science, Yonsei University, 1 Yonseidae-gil, Wonju, Gangwon-do 26493, Republic of Korea
Interests: deep learning; big data; artificial intelligence; image recognition; financial statistics
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

With the advancement of ICT technology introducing new technologies, such as mobile technology, IoT, and sensors, organizations are now faced with an environment where they generate and utilize vast and diverse types of big data. While traditional data analysis has focused on hypothesis verification based on correlations between structured data, the big data era increasingly involves the discovery and verification of hypotheses considering both structured and unstructured data.

Artificial intelligence (AI) technology, particularly methods derived from machine learning and the rapidly developing area of deep learning, is gaining attention as a powerful tool for such big data analyses. These new AI technologies are being applied across various fields, offering solutions to problems previously unsolvable by humans, and have become significant both academically and industrially.

As a result, AI has become a crucial element in maintaining sustainable competitiveness for various stakeholders and is an area of keen interest to many researchers.

This Special Issue will explore creative analytical models and generate innovative results using big data analysis and a data mining approach grounded in new AI technologies.

Topics of interest for this Special Issue include (but are not limited to) the following:

  • AI systems for business applications;
  • Big data analytics in customer behavior;
  • Data mining in healthcare and forensic science;
  • AI-based image reconstruction and recognition technology;
  • Machine learning applications for financial market predictions;
  • Novel methods in big data analytics;
  • Text mining applications.

Dr. Sukjun Lee
Dr. Jae Joon Ahn
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

  • AI systems
  • customer behavior analytics
  • healthcare and forensic data mining
  • AI-based image reconstruction and recognition
  • machine learning for predictions

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 (4 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

24 pages, 23269 KiB  
Article
Improving Medical Image Quality Using a Super-Resolution Technique with Attention Mechanism
by Dong Yun Lee, Jang Yeop Kim and Soo Young Cho
Appl. Sci. 2025, 15(2), 867; https://doi.org/10.3390/app15020867 - 17 Jan 2025
Viewed by 951
Abstract
Image quality plays a critical role in medical image analysis, significantly impacting diagnostic outcomes. Sharp and detailed images are essential for accurate diagnoses, but acquiring high-resolution medical images often demands sophisticated and costly equipment. To address this challenge, this study proposes a convolutional [...] Read more.
Image quality plays a critical role in medical image analysis, significantly impacting diagnostic outcomes. Sharp and detailed images are essential for accurate diagnoses, but acquiring high-resolution medical images often demands sophisticated and costly equipment. To address this challenge, this study proposes a convolutional neural network (CNN)-based super-resolution architecture, utilizing a melanoma dataset to enhance image resolution through deep learning techniques. The proposed model incorporates a convolutional self-attention block that combines channel and spatial attention to emphasize important image features. Channel attention uses global average pooling and fully connected layers to enhance high-frequency features within channels. Meanwhile, spatial attention applies a single-channel convolution to emphasize high-frequency features in the spatial domain. By integrating various attention blocks, feature extraction is optimized and further expanded through subpixel convolution to produce high-quality super-resolution images. The model uses L1 loss to generate realistic and smooth outputs, outperforming existing deep learning methods in capturing contours and textures. Evaluations with the ISIC 2020 dataset—containing 33126 training and 10982 test images for skin lesion analysis—showed a 1–2% improvement in peak signal-to-noise ratio (PSNR) compared to very deep super-resolution (VDSR) and enhanced deep super-resolution (EDSR) architectures. Full article
(This article belongs to the Special Issue Exploring AI: Methods and Applications for Data Mining)
►▼ Show Figures

Figure 1

Figure 1
<p>ISIC 2020 Challenge dataset.</p> Full article ">Figure 2
<p>ResNet architecture.</p> Full article ">Figure 3
<p>Network model: (<b>a</b>) existing CNN; (<b>b</b>) CNN-based ResNet residual block.</p> Full article ">Figure 4
<p>Convolutional block attention module.</p> Full article ">Figure 5
<p>Channel attention module of the convolutional block attention module.</p> Full article ">Figure 6
<p>Spatial attention module.</p> Full article ">Figure 7
<p>Architecture of the proposed super-resolution method.</p> Full article ">Figure 8
<p>Attention block structure.</p> Full article ">Figure 9
<p>Channel spatial block.</p> Full article ">Figure 10
<p>Channel attention structure.</p> Full article ">Figure 11
<p>Spatial attention structure.</p> Full article ">Figure 12
<p>Integrated architecture of the CSBlock with channel and spatial attention.</p> Full article ">Figure 13
<p>Upsampling.</p> Full article ">Figure 14
<p>ISIC_3371618 result: (<b>a</b>) original image, (<b>b</b>) bicubic interpolation image, (<b>c</b>) VDSR, (<b>d</b>) EDSR, and (<b>e</b>) the proposed method.</p> Full article ">Figure 15
<p>ISIC_4382016 results: (<b>a</b>) original image, (<b>b</b>) bicubic interpolation image, (<b>c</b>) VDSR, (<b>d</b>) EDSR, and (<b>e</b>) the proposed method.</p> Full article ">Figure 16
<p>Training loss and validation PSNR comparison across models and scales.</p> Full article ">
21 pages, 3591 KiB  
Article
Unbiased Isotonic Regression Tree for Discovering Hidden Heterogeneity in Monotonicity Constraints
by Doowon Choi
Appl. Sci. 2025, 15(2), 818; https://doi.org/10.3390/app15020818 - 15 Jan 2025
Viewed by 638
Abstract
Integrating domain knowledge is increasingly recognized as vital for improving the relevance and reliability of machine learning models. This integration is often implemented through specific types of constraints that reflect real-world conditions or theoretical insights. Within the family of regression trees, the isotonic [...] Read more.
Integrating domain knowledge is increasingly recognized as vital for improving the relevance and reliability of machine learning models. This integration is often implemented through specific types of constraints that reflect real-world conditions or theoretical insights. Within the family of regression trees, the isotonic regression tree is used to incorporate a monotonicity constraint between a predictor and a response variable. However, the isotonic regression tree could be susceptible to split selection bias, as it selects both its split variable and cutpoint simultaneously. This study first explores the possibility of selection bias on split variables in the isotonic regression tree and proposes an unbiased isotonic regression tree that mitigates the issue of the selection bias problem. The results of the simulation and case study demonstrate the effectiveness of the proposed approach and the ability to discover hidden heterogeneous monotonic constraints. Full article
(This article belongs to the Special Issue Exploring AI: Methods and Applications for Data Mining)
►▼ Show Figures

Figure 1

Figure 1
<p>An example of isotonic regression trees.</p> Full article ">Figure 2
<p>Partitioning at each node in the proposed unbiased isotonic regression tree.</p> Full article ">Figure 3
<p>The framework for constructing the proposed unbiased isotonic regression tree.</p> Full article ">Figure 4
<p>A comparison of the selection rates of all split covariates between IRT and UIRT in the simulation.</p> Full article ">Figure 5
<p>A comparison of the selection rates of all split covariates between IRT and UIRT in the real dataset.</p> Full article ">Figure 6
<p>(<b>a</b>) The schematic representation of the main components of a wind turbine, and (<b>b</b>) an example of a real wind turbine.</p> Full article ">Figure 7
<p>The six subgroups identified by the proposed isotonic regression tree.</p> Full article ">Figure 8
<p>The different monotonic increasing patterns associated with wind turbine 1.</p> Full article ">Figure 9
<p>The different monotonic increasing patterns associated with wind turbine 2.</p> Full article ">Figure 10
<p>Results of prediction performance of the four methods.</p> Full article ">
22 pages, 5532 KiB  
Article
Analysing Online Reviews Consumers’ Experiences of Mobile Travel Applications with Sentiment Analysis and Topic Modelling: The Example of Booking and Expedia
by Pınar Çelik Çaylak, Mehmet Kayakuş, Nisa Eksili, Fatma Yiğit Açikgöz, Artuğ Eren Coşkun, Mirona Ana Maria Ichimov and Georgiana Moiceanu
Appl. Sci. 2024, 14(24), 11800; https://doi.org/10.3390/app142411800 - 17 Dec 2024
Viewed by 1146
Abstract
This study aims to analyse consumer experiences, purchase behaviours, and emotional responses through Booking and Expedia’s mobile applications. The 2000 user reviews collected from Google Play were subjected to a comprehensive sentiment analysis, text mining, and topic modelling process to identify the key [...] Read more.
This study aims to analyse consumer experiences, purchase behaviours, and emotional responses through Booking and Expedia’s mobile applications. The 2000 user reviews collected from Google Play were subjected to a comprehensive sentiment analysis, text mining, and topic modelling process to identify the key elements that shape consumers’ emotional experiences and purchase decisions. According to the results of text mining and sentiment analysis performed with Python’s WordNet library, 81.9% of Booking.com reviews are positive, 8.4% are negative, and 11.3% are neutral, whereas 55.8% of Expedia reviews are positive, 37.8% are negative, and 8.0% are neutral. In the topic modelling analysis, Booking.com emphasised ease of booking, while Expedia emphasised difficulties in cancellation and refund processes. These findings provide valuable insights into how consumers’ emotional states and purchasing behaviours are reflected in their experiences with mobile applications. The study enables the development of strategic recommendations for marketing management to better analyse consumers’ expectations and experiences. Full article
(This article belongs to the Special Issue Exploring AI: Methods and Applications for Data Mining)
►▼ Show Figures

Figure 1

Figure 1
<p>Graphical representation of user comments.</p> Full article ">Figure 2
<p>Booking.com, and Expedia positive review word clouds.</p> Full article ">Figure 3
<p>Booking.com, and Expedia negative review word clouds.</p> Full article ">Figure 4
<p>Booking.com, and Expedia neutral review word clouds.</p> Full article ">Figure 5
<p>LDA terms (Booking). (<b>a</b>) Topic 1; (<b>b</b>) Topic 2; (<b>c</b>) Topic 3; (<b>d</b>) Topic 4; (<b>e</b>) Topic 5.</p> Full article ">Figure 5 Cont.
<p>LDA terms (Booking). (<b>a</b>) Topic 1; (<b>b</b>) Topic 2; (<b>c</b>) Topic 3; (<b>d</b>) Topic 4; (<b>e</b>) Topic 5.</p> Full article ">Figure 6
<p>LDA terms (Expedia). (<b>a</b>) Topic 1; (<b>b</b>) Topic 2; (<b>c</b>) Topic 3; (<b>d</b>) Topic 4; (<b>e</b>) Topic 5.</p> Full article ">Figure 6 Cont.
<p>LDA terms (Expedia). (<b>a</b>) Topic 1; (<b>b</b>) Topic 2; (<b>c</b>) Topic 3; (<b>d</b>) Topic 4; (<b>e</b>) Topic 5.</p> Full article ">
20 pages, 2935 KiB  
Article
Developing a Dynamic Feature Selection System (DFSS) for Stock Market Prediction: Application to the Korean Industry Sectors
by Woojung Kim, Jiyoung Jeon, Minwoo Jang, Sanghoe Kim, Heesoo Lee, Sanghyuk Yoo and Jaejoon Ahn
Appl. Sci. 2024, 14(16), 7314; https://doi.org/10.3390/app14167314 - 20 Aug 2024
Viewed by 1849
Abstract
For several years, a growing interest among numerous researchers and investors in predicting stock price movements has spurred extensive exploration into employing advanced deep learning models. These models aim to develop systems capable of comprehending the stock market’s complex nature. Despite the immense [...] Read more.
For several years, a growing interest among numerous researchers and investors in predicting stock price movements has spurred extensive exploration into employing advanced deep learning models. These models aim to develop systems capable of comprehending the stock market’s complex nature. Despite the immense challenge posed by the diverse factors influencing stock price forecasting, there remains a notable lack of research focused on identifying the essential feature set for accurate predictions. In this study, we propose a Dynamic Feature Selection System (DFSS) to predict stock prices across the 10 major industries, as classified by the FnGuide Industry Classification Standard (FICS) in South Korea. We apply 16 feature selection algorithms from filter, wrapper, embedded, and ensemble categories. Subsequently, we adjust the settings of industry-specific index data to evaluate the model’s performance and robustness over time. Our comprehensive results identify the optimal feature sets that significantly impact stock prices within each sector at specific points in time. By analyzing the inclusion ratios and significance of the optimal feature set by category, we gain insights into the proportion of feature classes and their importance. This analysis ensures the interpretability and reliability of our model. The proposed methodology complements existing methods that do not consider changes in the types of variables significantly affecting stock prices over time by dynamically adjusting the input variables used for learning. The primary goal of this study is to enhance active investment strategies by facilitating the creation of diversified portfolios for individual stocks across various sectors, offering robust models and feature sets that consistently demonstrate high performance across industries over time. Full article
(This article belongs to the Special Issue Exploring AI: Methods and Applications for Data Mining)
►▼ Show Figures

Figure 1

Figure 1
<p>DFSS Process.</p> Full article ">Figure 2
<p>Average results across all sectors in DFSS (red box is a feature selection algorithm with a high friedman rank compared to a low standard deviation).</p> Full article ">Figure 3
<p>Results for each of ten sectors in DFSS (red box is a feature selection algorithm with a high friedman rank compared to a low standard deviation).</p> Full article ">Figure 4
<p>Dynamic adjustment of the percentage of feature classes across timeline.</p> Full article ">Figure 5
<p>Dynamic adjustment of the important features across timeline.</p> Full article ">
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-4
Back to TopTop