Advanced Time Series and Computational Methods in Biological Signal Processing

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

Deadline for manuscript submissions: 30 September 2025 | Viewed by 649

Special Issue Editor


E-Mail Website
Guest Editor
Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China
Interests: time series data mining; machine learning; deep learning; biological signal processing; affective computing

Special Issue Information

Dear Colleagues,

The Special Issue “Advanced Time Series and Computational Methods in Biological Signal Processing” aims to address the growing intersection of time series analysis, deep learning, and their transformative applications in biological signal processing and affective computing. With the increasing prevalence of wearable devices, biosensors, and healthcare technologies, vast amounts of physiological and behavioral data are being collected in real time. These data provide unprecedented opportunities to analyze and gain a deeper understanding of human states and emotions, offering transformative potential in areas such as mental health monitoring, personalized medicine, adaptive learning, and human–computer interaction.

Despite the rapid progress in this field, significant challenges remain. Biological signals, such as EEG, ECG, and PPG, are often noisy, complex, and non-stationary, requiring robust analytical methods capable of capturing temporal dependencies and underlying patterns. Traditional time series models often struggle with such complexities, while deep learning models, though powerful, are often computationally intensive and lack interpretability. Furthermore, the fusion of multimodal signals, essential for comprehensive understanding, presents additional challenges related to feature alignment, missing data, and modality-specific noise. Addressing these issues requires innovative models, efficient algorithms, and a collaborative approach that connects theoretical advancements with real-world applications.

This Special Issue provides a platform for researchers and practitioners to share innovative contributions that push the boundaries of time series analysis and deep learning for biological signal processing and affective computing. We invite high-quality submissions that address areas of research, including but not limited to, the following:

1.  Advanced Time Series Models:

  • Innovative methodologies for modeling and analyzing complex physiological signals.
  • Temporal feature extraction and representation learning in biological data.
  • Novel frameworks for real-time signal forecasting and anomaly detection.

2.  Deep Learning for Biological Signal Processing:

  • Interpretable deep learning architectures for EEG, ECG, and multimodal data.
  • Multi-scale and hybrid models combining classical techniques with neural networks.
  • Applications of attention mechanisms, graph neural networks, and transformers.

3.  Affective Computing and Emotion Recognition:

  • Algorithms for emotion recognition and regulation based on physiological data.
  • Personalized models for tracking and predicting affective states in real time.
  • Use of deep learning for non-invasive monitoring and intervention in mental health.

4.  Efficient and Scalable Solutions:

  • Lightweight models for resource-constrained environments (e.g., mobile devices).
  • Compression techniques like low-rank approximations, pruning, and quantization.
  • Privacy-preserving and federated learning methods for sensitive health data.

5.  Real-world Applications and Emerging Topics:

  • Cross-disciplinary case studies demonstrating practical applications in healthcare, education, and smart environments.
  • Synthetic data generation for training models in data-scarce settings.
  • Creation of new benchmarks, datasets, and tools to facilitate future research.

Through this Special Issue, we aim to advance the theoretical foundations and practical applications of time series models and deep learning in biological signal processing and affective computing. By fostering collaboration among experts in artificial intelligence, neuroscience, medicine, and psychology, we hope to address pressing societal challenges and improve human well-being through innovative technological solutions.

Dr. Ziyu Jia
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

  • time series analysis
  • deep learning algorithms
  • biological signal processing
  • affective computing
  • physiological data modeling
  • multimodal data fusion
  • emotion recognition
  • computational neuroscience
  • mathematical modeling
  • real-time signal processing

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.
  • Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.

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

33 pages, 2654 KiB  
Article
A Portable and Affordable Four-Channel EEG System for Emotion Recognition with Self-Supervised Feature Learning
by Hao Luo, Haobo Li, Wei Tao, Yi Yang, Chio-In Ieong and Feng Wan
Mathematics 2025, 13(10), 1608; https://doi.org/10.3390/math13101608 - 14 May 2025
Viewed by 405
Abstract
Emotions play a pivotal role in shaping human decision-making, behavior, and physiological well-being. Electroencephalography (EEG)-based emotion recognition offers promising avenues for real-time self-monitoring and affective computing applications. However, existing commercial solutions are often hindered by high costs, complicated deployment processes, and limited reliability [...] Read more.
Emotions play a pivotal role in shaping human decision-making, behavior, and physiological well-being. Electroencephalography (EEG)-based emotion recognition offers promising avenues for real-time self-monitoring and affective computing applications. However, existing commercial solutions are often hindered by high costs, complicated deployment processes, and limited reliability in practical settings. To address these challenges, we propose a low-cost, self-adaptive wearable EEG system for emotion recognition through a hardware–algorithm co-design approach. The proposed system is a four-channel wireless EEG acquisition device supporting both dry and wet electrodes, with a component cost below USD 35. It features over 7 h of continuous operation, plug-and-play functionality, and modular expandability. At the algorithmic level, we introduce a self-supervised feature extraction framework that combines contrastive learning and masked prediction tasks, enabling robust emotional feature learning from a limited number of EEG channels with constrained signal quality. Our approach attains the highest performance of 60.2% accuracy and 59.4% Macro-F1 score on our proposed platform. Compared to conventional feature-based approaches, it demonstrates a maximum accuracy improvement of up to 20.4% using a multilayer perceptron classifier in our experiment. Full article
Show Figures

Figure 1

Back to TopTop