Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
3.5
2.4
Journals
Mathematics
Special Issues
Applications of Artificial Intelligence and Pattern Recognition
share announcement

Applications of Artificial Intelligence and Pattern Recognition

A special issue of Mathematics (ISSN 2227-7390). This special issue belongs to the section "Mathematics and Computer Science".

Deadline for manuscript submissions: closed (31 March 2024) | Viewed by 3785

Special Issue Editors

Prof. Dr. Yen-Lin Chen

E-Mail Website
Guest Editor
Department of Computer Science and Information Engineering, National Taipei University of Technology, 1, Sec. 3, Chung-hsiao E. Rd., Taipei 10608, Taiwan
Interests: intelligent image analytics; embedded-vision systems; artificial intelligence applications; pattern recognition; intelligent vehicles; intelligent transportation system
Special Issues, Collections and Topics in MDPI journals
Dr. Wai-Khuen Cheng

E-Mail Website
Guest Editor
Faculty of Information and Communication Technology, Department of Computer Science, Universiti Tunku Abdul Rahman, Jalan Universiti Bandar Barat. 31900 Kampar, Perak, Malaysia.
Interests: artificial intelligence; cloud computing; distributed and high-performance computing; Internet of Things (IoT); recommender systems; intelligent agent systems; financial technology
Special Issues, Collections and Topics in MDPI journals
Prof. Dr. Hsin-Hui Hu

E-Mail Website
Guest Editor
Department of Electronic Engineering, National Taipei University of Technology, 1, Sec. 3, Chung-hsiao E. Rd., Taipei 10608, Taiwan
Interests: RF device design and manufacture; semiconductor device simulation and modeling; machine learning in area of semiconductor manufacturing

Special Issue Information

Dear Colleagues,

Recently, Artificial Intelligent (AI) emerged as a game-changing technology that penetrated a wide range of applications such as smart healthcare, intelligent manufacturing, smart transportation, financial technology, etc. The integration of AI and the Internet of Things (IoT) is becoming a research trend to improve the user experience while boosting productivity. For instance, smart systems have enabled the continuously collection of environmental data while accordingly performing various analyses. Despite the methodological breakthrough across computer vision and natural language processing outperforming human beings, the development of intelligent applications is still facing various challenges in response to different domains. The possible challenges range from data processing, computer modeling, domain adaptation, intelligent optimization, control theory, network technology, etc.

In the context of this special issue, researchers are encouraged to explore how mathematical modelling and analysis techniques can be applied to improve AI algorithms and systems. Optimization methods may be employed to develop efficient algorithms capable of handling large datasets in real-time. Numerical methods can be used to analyze and solve complex mathematical models that arise in AI applications. Control theory methods may be developed to ensure that AI systems operate safely and effectively in various environments. Additionally, network technology can be leveraged to enhance the scalability and performance of distributed AI systems. By utilizing these mathematical approaches, researchers can improve the theoretical foundations of AI and devise practical solutions to real-world problems.

This Special Issue will concentrate on both the theoretical and practical of Artificial Intelligence in the application of Industry Internet of Things, Intelligent Transportation, and intelligence systems across different environments and semiconductor process modeling. Thus, we offer the opportunity for researchers to continuously explore new promising research directions while contributing to the research area. Topics include but are not limited to:

  • Computer vision;
  • Pattern recognition;
  • Optimization methods;
  • Numerical methods for intelligent systems;
  • Financial technology;
  • Smart Manufacturing.

Prof. Dr. Yen-Lin Chen
Dr. Wai-Khuen Cheng
Prof. Dr. Hsin-Hui Hu
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. Mathematics 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 2600 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
  • pattern recognition
  • machine learning
  • deep learning
  • industry Internet of Things (IIOT)
  • intelligent agents
  • intelligent transportation
  • intelligent vehicles
  • intelligent vision-embedded systems
  • financial technology
  • smart manufacturing
  • machine learning in area of semiconductor manufacturing

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

27 pages, 8078 KiB  
Article
Deep-Learning-Based Classification of Bangladeshi Medicinal Plants Using Neural Ensemble Models
by A. Hasib Uddin, Yen-Lin Chen, Bijly Borkatullah, Mst. Sathi Khatun, Jannatul Ferdous, Prince Mahmud, Jing Yang, Chin Soon Ku and Lip Yee Por
Mathematics 2023, 11(16), 3504; https://doi.org/10.3390/math11163504 - 14 Aug 2023
Cited by 3 | Viewed by 1534
Abstract
This research addresses the lack of publicly available datasets for Bangladeshi medicinal plants by presenting a comprehensive dataset comprising 5000 images of ten species collected under controlled conditions. To improve performance, several preprocessing techniques were employed, such as image selection, background removal, unsharp [...] Read more.
This research addresses the lack of publicly available datasets for Bangladeshi medicinal plants by presenting a comprehensive dataset comprising 5000 images of ten species collected under controlled conditions. To improve performance, several preprocessing techniques were employed, such as image selection, background removal, unsharp masking, contrast-limited adaptive histogram equalization, and morphological gradient. Then, we applied five state-of-the-art deep learning models to achieve benchmark performance on the dataset: VGG16, ResNet50, DenseNet201, InceptionV3, and Xception. Among these models, DenseNet201 demonstrated the highest accuracy of 85.28%. In addition to benchmarking the deep learning models, three novel neural network architectures were developed: dense-residual–dense (DRD), dense-residual–ConvLSTM-dense (DRCD), and inception-residual–ConvLSTM-dense (IRCD). The DRCD model achieved the highest accuracy of 97%, surpassing the benchmark performances of individual models. This highlights the effectiveness of the proposed architectures in capturing complex patterns and dependencies within the data. To further enhance classification accuracy, an ensemble approach was adopted, employing both hard ensemble and soft ensemble techniques. The hard ensemble achieved an accuracy of 98%, while the soft ensemble achieved the highest accuracy of 99%. These results demonstrate the effectiveness of ensembling techniques in boosting overall classification performance. The outcomes of this study have significant implications for the accurate identification and classification of Bangladeshi medicinal plants. This research provides valuable resources for traditional medicine, drug discovery, and biodiversity conservation efforts. The developed models and ensemble techniques can aid researchers, botanists, and practitioners in accurately identifying medicinal plant species, thereby facilitating the utilization of their therapeutic potential and contributing to the preservation of biodiversity. Full article
(This article belongs to the Special Issue Applications of Artificial Intelligence and Pattern Recognition)
►▼ Show Figures

Figure 1

12 pages, 2379 KiB  
Article
Rewarding Developers by Storing Applications on Non-Fungible Tokens
by Ayesha Kalhoro, Asif Ali Wagan, Abdullah Ayub Khan, Jim-Min Lin, Chin Soon Ku, Lip Yee Por and Jing Yang
Mathematics 2023, 11(11), 2519; https://doi.org/10.3390/math11112519 - 30 May 2023
Cited by 2 | Viewed by 1492
Abstract
Non-fungible tokens (NFTs) are individual tokens with valuable information stored inside them over blockchain technology. They can be purchased and sold like other physical and virtual art pieces because their worth is mostly determined by the market and demand. The unique data of [...] Read more.
Non-fungible tokens (NFTs) are individual tokens with valuable information stored inside them over blockchain technology. They can be purchased and sold like other physical and virtual art pieces because their worth is mostly determined by the market and demand. The unique data of NFTs render it simple to verify and authenticate their ownership and transfer of tokens between owners. However, in Pakistan, developers cannot acquire different licences to accomplish their projects not because they cannot afford it, but because they cannot invest in every piece of software to accomplish each new sensitive task. Rather, they can render the product platform independent. Considering this technology, this paper provides IT professionals with a new NFT approach and business policies that solely belong to the information technology domain. In addition, this paper also introduces how NFT tokens can hold software applications. Since we can store files, we can let NFTs also store complete applications to help developers in further utilising virtuality and having the metaverse at their fingertips. Whenever they succeed in a project, they never receive rewards, and their skills only pay the bills. In a nutshell, this paper presents a prototype of NFTs that would be further polished to save and utilise applications in a decentralised manner while rewarding the developers. Full article
(This article belongs to the Special Issue Applications of Artificial Intelligence and Pattern Recognition)
►▼ 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