Skip to main content
SpringerLink
Log in
Springer
Evolving Systems

An Interdisciplinary Journal for Advanced Science and Technology

Publishing model:
Hybrid

Evolving Systems - Call for Papers: Pervasive and Resource-Constrained Artificial Intelligence

Guest Editors:
Dr. Lorenzo Valerio, IIT-CNR, Italy
Dr. Franco Maria Nardini, ISTI-CNR, Italy
Prof. Mario Luca Bernardi, University of Sannio, Italy
Prof. Riccardo Pecori, eCampus University, Italy and IMEM-CNR, Italy
Dr. Paolo Dini, CTTC/CERCA, Spain

Submission status: Open   |   Submission deadline: 31 July 2024

Description
This Special Issue is dedicated to advancing the development and circulation of new ideas and research directions in pervasive and resource-constrained machine learning, suitable for constantly changing data flows. It seeks to gather high-quality contributions from researchers working on the intersection between pervasive computing and machine learning, and stimulating the cross-fertilization between the two communities.

The focus of this Special Issue is on pervasive and resource-constrained machine learning for dynamic and temporally evolving systems, emphasizing two main aspects: i) foundations and ii) applications. It specifically targets communities engaged in pervasive computing and machine learning, inviting contributions related to the foundational aspects of pervasive machine learning within mixed Cloud/Edge environments or for resource-constrained devices.

The use of advanced machine learning and deep neural networks is becoming increasingly widespread and needs to be appropriately integrated into pervasive and distributed computing architectures to foster a fully connected environment made of cooperating intelligent systems. What is still lacking regards in-depth studies focusing on the modalities and approaches to properly integrate complex learning models, architectures, and algorithms in current distributed, pervasive, and constrained systems. From this point of view, the Special Issue aims to foster the development of more advanced machine learning approaches (also based on novel models and including novel deep neural network architectures) that can be applied to all areas of computing and communication systems, as well as to increase pervasive computing performance using novel machine learning strategies.

We also aim to receive multi-disciplinary contributions related to the applications of pervasive and resource-constrained advanced machine learning in various domains where these approaches are gaining attention and importance. Examples include health, well-being, industry 4.0, environmental control/monitoring, computer vision, smart cities, smart agriculture, smart distance education, and self-driving vehicles. 

The Special Issue seeks submissions on the following topics:

Foundations: Advanced Machine Learning algorithms and methods for pervasive systems subject to resource limitations addressing the following open challenges:

  • Decentralized Machine Learning for resource-constrained devices exposed to time varying data distributions (e.g., resource-efficient federated learning)
  • Lightweight ML models for on-device continual learning in pervasive computing (e.g., GRU, ELM, Spiking NN, etc.)
  • Sustainable AI through novel, brain- and bio-inspired ML algorithms exploiting energy-efficient and adaptive hardware, e.g., FPGA, Neuromorphic HW 
  • Context-aware compression of deep learning models for real-time adaptive inference
  • Semi-supervised and self-supervised learning systems in pervasive and resource-constrained evolving scenarios;
  • Learning with imbalanced data in pervasive and resource-constrained evolving scenarios
  • Continual learning in pervasive and resource-constrained scenarios
  • Over-the-air computing for distributed/decentralized learning systems in pervasive and resource constrained scenarios

Applications: Advanced Machine Learning algorithms, methods and approaches for pervasive computing under resource limitations applied to the following adaptive application domains:

  • Health and well-being applications (e.g., activity recognition, health monitoring)
  • Anomaly/Novelty detection (e.g., Industry 4.0, predictive maintenance, condition monitoring, intrusion detection, privacy, and security)
  • Audio signal continuous processing (e.g., sound event detection, speech recognition/processing)
  • Video streams continuous processing on resource-constrained devices
  • On-the-fly Natural Language Processing and Information Retrieval (e.g., conversational applications running on resource-constrained, mobile, or edge devices)
  • Intersection between seamless mobile computing with ML/DL on resource-constrained devices
  • Any other real-world applications and case studies where the pervasiveness of resource-constrained devices is central for continuous knowledge extraction

Submission guidelines
All papers must be prepared in accordance with the Instructions for Authors at: https://www.springer.com/journal/12530/submission-guidelines (this opens in a new tab). Authors should submit through the online submission site and select article type “SI - "Pervasive and Resource-Constrained Artificial Intelligence". 

Submitted papers should present original, unpublished work, relevant to one of the topics of the special issue. All submitted papers will be evaluated on the basis of relevance, significance of contribution, technical quality, scholarship, and quality of presentation, by at least two independent reviewers. It is the policy of the journal that no submission, or substantially overlapping submission, be published or be under review at another journal or conference at any time during the review process. Final decisions on all papers are made by the Editor-in-Chief.

Accepted papers are published Online First (this opens in a new tab) until the complete Special Issue is published.

Search

Navigation