Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
4.0
2.3
Journals
Mathematics
Special Issues
Deep Neural Network: Theory, Algorithms and Applications
share announcement

Deep Neural Network: Theory, Algorithms and Applications

A special issue of Mathematics (ISSN 2227-7390). This special issue belongs to the section "E1: Mathematics and Computer Science".

Deadline for manuscript submissions: 15 September 2025 | Viewed by 653

Special Issue Editor

Dr. Cheng Tang

E-Mail Website
Guest Editor
Faculty of Engineering, Kyushu University, Fukuoka-shi 819-0395, Japan
Interests: neural networks; evolutionary computation; learning analytics; bioinformatics; artificial intelligence in medical big data
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

In recent years, the rapid advancements in artificial intelligence and its integration into diverse domains have underscored the transformative potential of deep neural networks (DNNs). These networks have demonstrated remarkable performance in solving complex problems across various applications, including computer vision, natural language processing, and autonomous systems. However, the development and deployment of DNNs present unique challenges, such as optimizing algorithms, improving interpretability, and ensuring robust performance in real-world scenarios. This Special Issue aims to highlight innovative research on the theoretical underpinnings, algorithmic advancements, and diverse applications of DNNs, emphasizing state-of-the-art methodologies and solutions to address these challenges.

Within this context, the topics covered in the Special Issue encompass various aspects of DNNs, including emerging architectures, optimization techniques, interpretability frameworks, and interdisciplinary applications across multiple domains.

We look forward to receiving your valuable submissions.

Topics include, but are not limited to, the following:

  • Theoretical advancements in deep neural networks;
  • Novel architectures for efficient and scalable DNNs;
  • Optimization algorithms and training methodologies for DNNs;
  • Interpretability and explainability techniques for deep learning models;
  • Applications of DNNs in computer vision, NLP, and autonomous systems;
  • Integration of DNNs with emerging technologies like IoT, edge computing, and quantum computing;
  • Privacy-preserving and secure deep learning frameworks;
  • Robustness and generalization techniques in deep neural networks;
  • Real-world case studies of DNN deployment in healthcare, finance, and other industries;
  • Hybrid models combining deep learning with traditional approaches or domain-specific knowledge.

Dr. Cheng Tang
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. 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

  • deep neural networks
  • computer vision
  • natural language processing
  • autonomous systems
  • optimization algorithm
  • XAI
  • application

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 (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

19 pages, 1789 KiB  
Article
Optimization of Temporal Feature Attribution and Sequential Dependency Modeling for High-Precision Multi-Step Resource Forecasting: A Methodological Framework and Empirical Evaluation
by Jiaqi Shen, Peiwen Qin, Rui Zhong and Peiyao Han
Mathematics 2025, 13(8), 1339; https://doi.org/10.3390/math13081339 - 19 Apr 2025
Viewed by 102
Abstract
This paper presents a comprehensive time-series analysis framework leveraging the Temporal Fusion Transformer (TFT) architecture to address the challenge of multi-horizon forecasting in complex ecological systems, specifically focusing on global fishery resources. Using global fishery data spanning 70 years (1950–2020), enhanced with key [...] Read more.
This paper presents a comprehensive time-series analysis framework leveraging the Temporal Fusion Transformer (TFT) architecture to address the challenge of multi-horizon forecasting in complex ecological systems, specifically focusing on global fishery resources. Using global fishery data spanning 70 years (1950–2020), enhanced with key climate indicators, we develop a methodology for predicting time-dependent patterns across three-year, five-year, and extended seven-year horizons. Our approach integrates static metadata with temporal features, including historical catch and climate data, through a specialized architecture incorporating variable selection networks, multi-head attention mechanisms, and bidirectional encoding layers. A comparative analysis demonstrates the TFT model’s robust performance against traditional methods (ARIMA), standard deep learning models (MLP, LSTM), and contemporary architectures (TCN, XGBoost). While competitive across different horizons, TFT excels in the 7-year forecast, achieving a mean absolute percentage error (MAPE) of 13.7%, outperforming the next best model (LSTM, 15.1%). Through a sensitivity analysis, we identify the optimal temporal granularity and historical context length for maximizing prediction accuracy. The variable selection component reveals differential weighting, with recent market observations (past 1-year catch: 31%) and climate signals (ONI index: 15%, SST anomaly: 10%) playing significant roles. A species-specific analysis uncovers variations in predictability patterns. Ablation experiments quantify the contributions of the architectural components. The proposed methodology offers practical applications for resource management and theoretical insights into modeling temporal dependencies in complex ecological data. Full article
(This article belongs to the Special Issue Deep Neural Network: Theory, Algorithms and Applications)
►▼ Show Figures

Figure 1

22 pages, 892 KiB  
Article
Next Point of Interest (POI) Recommendation System Driven by User Probabilistic Preferences and Temporal Regularities
by Fengyu Liu, Jinhe Chen, Jun Yu and Rui Zhong
Mathematics 2025, 13(8), 1232; https://doi.org/10.3390/math13081232 - 9 Apr 2025
Viewed by 345
Abstract
The Point of Interest (POI) recommendation system is a critical tool for enhancing user experience by analyzing historical behaviors, social network data, and real-time location information with the increasing demand for personalized and intelligent services. However, existing POI recommendation systems face three major [...] Read more.
The Point of Interest (POI) recommendation system is a critical tool for enhancing user experience by analyzing historical behaviors, social network data, and real-time location information with the increasing demand for personalized and intelligent services. However, existing POI recommendation systems face three major challenges: (1) oversimplification of user preference modeling, limiting adaptability to dynamic user needs, (2) lack of explicit arrival time modeling, leading to reduced accuracy in time-sensitive scenarios, and (3) complexity in trajectory representation and spatiotemporal mining, posing difficulties in handling large-scale geographic data. This paper proposes NextMove, a novel POI recommendation model that integrates four key modules to address these issues. Specifically, the Probabilistic User Preference Generation Module first employs Latent Dirichlet Allocation (LDA) and a user preference network to model user personalized interests dynamically by capturing latent geographical topics. Secondly, the Self-Attention-based Arrival Time Prediction Module utilizes a Multi-Head Attention Mechanism to extract time-varying features, improving the precision of arrival time estimation. Thirdly, the Transformer-based Trajectory Representation Module encodes sequential dependencies in user behavior, effectively capturing contextual relationships and long-range dependencies for accurate future location forecasting. Finally, the Next Location Feature-Aggregation Module integrates the extracted representation features through an FC-based nonlinear fusion mechanism to generate the final POI recommendation. Extensive experiments conducted on real-world datasets demonstrate the superiority of the proposed NextMove over state-of-the-art methods. These results validate the effectiveness of NextMove in modeling dynamic user preferences, enhancing arrival time prediction, and improving POI recommendation accuracy. Full article
(This article belongs to the Special Issue Deep Neural Network: Theory, Algorithms and Applications)
►▼ 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