Aims and scope

Discover Computing (formerly Information Retrieval Journal) is a fully open access, peer-reviewed journal that supports multidisciplinary research and policy developments across all fields relevant to computer science. The journal aims to be a resource for researchers, policy makers and the general public for recent advances in computer science, and its uses in research development and society. As a fully open access journal, we ensure that our research is highly discoverable and instantly available globally to everyone. The journal particularly welcomes work that aims to address the United Nations Sustainable Development Goals, especially, Industry, Innovation and Infrastructure.

Topics 

Topics welcomed at Discover Computing include but are not limited to the following:

Foundational computing theories:

    Algorithms, data structures, computational complexity
    Automata theory, graph theory, formal languages
    Turing machines, P vs NP problem, lambda calculus

Modern computing architectures and systems:

    Quantum computing, distributed systems, parallel computing
    Microarchitecture, multicore processors, memory hierarchies
    Cloud computing, edge computing, serverless architectures

Human-computer interaction:

    User experience (UX), user interface (UI), accessibility
    Cognitive ergonomics, adaptive systems, virtual reality
    User-centered design, haptic feedback, gesture recognition

Artificial intelligence and machine learning:

    Neural networks, deep learning, reinforcement learning
    Natural language processing, computer vision, robotics
    Generative adversarial networks (GANs), transfer learning, explainable AI

Cybersecurity and privacy:

    Cryptography, firewall, intrusion detection systems
    Digital forensics, malware analysis, blockchain security
    Data anonymization, end-to-end encryption, zero trust architectures

Emergent technologies:

    Augmented reality (AR), virtual reality (VR), mixed reality (MR)
    Internet of Things (IoT), 5G, smart cities
    Drones, autonomous vehicles, wearable tech

Societal impacts of computing:

    Digital ethics, algorithmic bias, technological unemployment
    Digital divide, accessibility, information equity
    Digital literacy, e-governance, surveillance capitalism

Content types

Discover Computing welcomes a variety of article types – please see our submission guidelines for details. The journal also publishes guest-edited Topical Collections of relevance to all aspects of computer science and its applications. For more information, please follow up with our journal publishing contact.

Special Issue on Enhancing Smart Grid Security, Efficiency and Resilience: The Role of AI and Blockchain in EV Charging
提出日: 2026-01-31

The convergence of electric vehicles (EVs), renewable energy, and smart grids signals a pivotal evolution in energy management. Central to this shift is the creation of secure and efficient EV charging infrastructures resilient to cyber threats and capable of managing increased load demands. This collection delves into pioneering research and innovative practices that harness Artificial Intelligence (AI), Machine Learning (ML), and Blockchain technologies to enhance the security and efficiency of EV charging within smart grids. The objective is to compile cutting-edge research, impactful applications, and informed discussions on deploying AI/ML and Blockchain to enhance EV charging infrastructure's performance and security. Contributions will cover a broad range of topics, including AI/ML-driven anomaly detection, robust Blockchain frameworks for secure transactions, predictive maintenance strategies using data analytics, interoperability and standardization of Blockchain across smart grids, intelligent demand response and load balancing, and cybersecurity risk assessment models. The collection will also explore AI-enhanced grid cybersecurity architectures, user privacy and daspecuata security, resource allocation optimization, and real-world implementations of integrated AI/ML and Blockchain in smart charging. By offering this compendium, we aim to inspire future advancements in EV charging security, stimulate innovative smart grid solutions, and contribute to sustainable energy practices. We welcome dynamic and impactful submissions that push the boundaries of current research and practice in this emerging field. 

Special Issue on Graph-Based Approaches for Data Mining
提出日: 2026-01-31

Graph-based approaches are revolutionizing the field of data mining, offering powerful methods to model and analyze complex, interconnected data. This Collection invites contributions that explore innovative uses of graph theory and graph algorithms in the context of data mining. As data becomes increasingly relational, graph-based models provide unique advantages for uncovering hidden patterns, detecting communities, and predicting relationships in a variety of domains. We are particularly interested in topics such as social network analysis, graph-based recommendation systems, science network (e.g., scientific collaboration networks, citation networks, and other networks commonly found in science of science), fake news detection, and cybersecurity. Additionally, we encourage work that addresses the computational challenges associated with mining large-scale graphs and explores novel applications of graph analytics. This collection seeks to highlight both theoretical advancements and practical applications, fostering collaboration across disciplines to push the boundaries of graph-based data mining.

Keywords: Graph-based approaches, social network analysis, recommendation systems, science network, fake news detection

Special Issue on Artificial Intelligence for Multimedia Applications
提出日: 2026-01-31

Artificial Intelligence (AI) is revolutionizing the field of multimedia, introducing new ways to create, process, analyze, and interact with various forms of content, such as images, videos, audio, and text. This multidisciplinary field focuses on leveraging AI to enhance multimedia systems and applications, offering innovative solutions to address the growing demand for intelligent, scalable, and user-centric technologies.

AI in multimedia covers a wide range of topics, from advanced machine learning algorithms for content analysis to real-time processing systems and augmented/virtual reality experiences. These advancements have brought innovations in personalization, interactive interfaces, and multimedia analytics, creating new opportunities and challenges across diverse domains, such as entertainment, healthcare, education and communication.

This Collection welcomes original research papers, as well as review articles, that address theoretical, technical, and applied aspects of AI in multimedia applications, such as image and video analysis, audio and speech recognition, natural language processing for multimedia, augmented and virtual reality, and cross-modal data integration. Contributions focusing on emerging trends, interdisciplinary approaches, and innovative methodologies are particularly encouraged.

Topics of interest include, but are not limited to:

- Generative AI for multimedia content creation
- Deep learning for multimedia analytics
- Natural language processing for multimedia systems
- AI-driven augmented and virtual reality applications
- Personalized and adaptive multimedia systems
- Multimedia recommender systems
- AI in multimedia learning
- AI Healthcare Systems
- Human-Computer Interaction in multimedia applications
- Security, privacy, and ethics in AI multimedia applications

This Collection supports and amplifies research related to SDG 9.

Keywords: AI-Driven Content Creation, Multimedia Analytics, Personalized Multimedia Systems, Real-Time Multimedia Processing, Virtual and Augmented Reality

Special Issue on Forgery Detection and Its Applications
提出日: 2026-01-31

Forgery detection is an increasingly critical area of research, particularly in the age of digital transformation where the authenticity of documents, images, videos, and other forms of media is frequently challenged. This Topical Collection aims to explore the latest advancements, methodologies, and technologies in the field of forgery detection, encompassing a wide range of applications from document verification to digital multimedia authentication and beyond. The goal of this Collection is to bring together researchers, practitioners, and industry professionals to share their insights, innovative approaches, and practical solutions in combating forgery across various domains.

Topics of interest include, but are not limited to:

- Advanced techniques in document forgery detection, including handwriting analysis and digital document verification.
- Image and video forgery detection, including deepfake detection, image splicing, and copy-move forgery identification.
- Applications of machine learning and deep learning in forgery detection.
- Cryptographic methods and watermarking for content authentication and protection.
- Forensic analysis and investigative methodologies for uncovering forgeries.
- Legal and ethical considerations in forgery detection.
- Case studies and real-world applications of forgery detection in sectors such as finance, legal, art, and historical document preservation.

Keywords: forgery detection, forgery identification, forgery localization, deep learning, content authentication

Special Issue on        Computational Sustainability Technologies: AI for Energy Economy, Carbon Neutrality, and ESG
提出日: 2026-01-31

This Collection focuses on advancing computational sustainability technologies that leverage artificial intelligence (AI) and digitalization to address global challenges in energy transition, carbon neutrality, and ESG implementation. Modern industries and cities are shifting toward more sustainable and intelligent energy operations. Accordingly, there is a growing need for computational frameworks to optimize energy use, reduce greenhouse gas (GHG) emissions, and support environmentally responsible decision-making.

We invite submissions that address the intersection of AI, data-driven modelling, and cyber-physical systems (CPS) applied to energy and environmental domains for a sustainable future. Relevant topics include but are not limited to AI-based energy management systems, digital twins for sustainable infrastructure, IoT-enabled monitoring and control, and GHG emission prediction and mitigation algorithms. Research on applicable platforms that enable traceable ESG performance, energy economic analysis for dynamic demand control, and optimal models for the integration of distributed energy resources is also encouraged. In particular, we are interested in innovative approaches that integrate emerging AI paradigms—such as Agentic AI, multi-agent coordination, and reinforcement learning. Submissions may include theoretical methodologies, applied research, reviews, or case studies across smart cities, smart buildings, smart farms, manufacturing, and other specific industries.

The goal of this Collection is to foster computational strategies that not only enhance technical performance but also contribute meaningfully to long-term ecological and societal goals.

This Collection supports and amplifies research related to SDG 7, SDG 11, and SDG 13.

Keywords: Computational Sustainability, Artificial Intelligence (AI), Energy Economic Analysis, AI-Based Energy Management, Carbon Neutrality, GHG Emission Mitigation, ESG Platforms, Digital Twins, Distributed Energy Resources Integration

Special Issue on Advanced Technologies and Intelligent Applications for Unmanned Swarm Systems
提出日: 2026-01-31

Most recently, unmanned swarm systems have played an increasingly important role in the national economy and human social life across many fields, such as traffic monitoring, disaster relief, anti-terrorism operations and target acquisition, and are considered one of the most exciting and innovative technologies in the field of artificial intelligence. Unmanned swarm systems can share their detected information (e.g., physical surroundings, collision events, threat messages) with others via various communication systems (e.g., aircraft addressing and reporting systems, vehicular ad hoc networks, long-term evolution, and 4G/5G mobile networks) for cooperation and coordination. Compared with manned vehicles, unmanned swarm systems can relieve humans from dull, dirty, and dangerous tasks and perform operations more efficiently. With the advances in various computing models and control strategies, a growing number of researchers and practitioners have begun actively focusing on the key technologies and intelligent applications of unmanned swarm systems. Meanwhile, with the integration of artificial intelligence, machine learning, data mining, signal processing and other technologies, many intelligent applications of unmanned swarm systems are rapidly evolving and being widely adopted. Advances in unmanned swarm systems affect every part of life, business, industry, and education, and have become an important driver of innovation and value for many companies and organizations.

This collection aims to bring together world-class researchers to present state-of-the-art research achievements and advances in unmanned swarm systems in terms of advanced technologies and intelligent applications for self-driving cars, unmanned surface vehicles, unmanned aerial vehicles, and more. Review articles are also encouraged.

Topics of interest may include (but are not limited to):

- Knowledge-based AI for vehicle perception, control, and decision-making
- Artificial intelligence applications in unmanned aerial vehicles
- Data science approaches for autonomous vehicle systems
- Localization, mapping, and semantic segmentation for unmanned aerial vehicles
- Collaborative perception and control of vehicle swarms
- Highly Safe and Reliable Communication Networks
- Simulation and verification of autonomous vehicle systems
- Task allocation and resource scheduling for multi-agent systems
- Fault detection and diagnosis for unmanned aerial vehicles
- Human-robot interaction for autonomous robots
- Motion drive and teleoperation control for unmanned aerial vehicles

This Collection supports and amplifies research related to SDG 9.

Special Issue on Generative AI Models for Time Series Forecasting and Applications
提出日: 2026-02-28

This Topical Collection focuses on cutting-edge research in AI-based generative models for predictive applications. It aims to explore innovative approaches in developing and applying generative AI models to forecast future trends, behaviors, and outcomes across various domains. The collection welcomes studies on novel architectures, training methodologies, and real-world applications of generative models in predictive tasks. Key areas of interest include, but are not limited to, time series forecasting, risk assessment, scenario planning, and decision support systems powered by generative AI. This collection seeks to highlight advancements that bridge the gap between generative AI’s creative capabilities and its potential for accurate, robust predictions.

Keywords: Generative AI, Predictive Modeling, Machine Learning, Forecasting, Time Series Analysis, Deep Learning, Neural Networks, Decision Support Systems, Risk Assessment, Scenario Generation

This Collection supports and amplifies research related to SDG 3, SDG 6, SDG 7, SDG 9, SDG 11, SDG 12, and SDG 13.

Special Issue on AI Advancements in Computing for Large Scale IoT Networks
提出日: 2026-02-28

The Internet of Things (IoT) plays a crucial role in transforming the way we live and work, connecting physical devices, vehicles, and infrastructure to the digital world. By enabling real-time data exchange and analytics, IoT improves efficiency, productivity, and decision-making across various sectors. From smart homes and cities to healthcare and industrial automation, IoT enhances convenience, safety, and innovation. Its impact is felt in increased energy efficiency, reduced costs, and enhanced customer experiences. IoT’s seamless integration of technology with massive computing capabilities promises a more connected and sustainable future, but the challenges are significant, and the research community is working hard to provide solutions. Computing, a major area of focus for large-scale IoT networks, plays a pivotal role in enabling real-time data processing, analysis, and decision-making. By analyzing vast amounts of sensor data, computing transforms IoT devices into intelligent systems. Edge computing and cloud computing integrated with Artificial Intelligence (AI) facilitate smart solutions for efficient data processing, reducing latency and improving IoT device performance. Based on the advancements in computing for futuristic intelligent IoT networks, this Collection mainly targets the challenges and solutions in enhancing computing capabilities in large-scale IoT networks. We welcome original contributions from the research community and the topics of interest for this Collection include but are not limited to AI advancements in the following areas:

- Mobile edge computing for IoT networks
- Scheduling schemes in cloud for IoT networks
- Advanced IoT architectures for intelligent systems
- Cross layer design issues in IoT networks
- Adaptive algorithms for IoT networks
- Communication schemes for IoT networks
- Real-time data analytics for IoT networks
- Quality of service/performance enhancement in IoT networks
- Middleware platforms for IoT networks
- Machine learning and deep learning methodologies for IoT networks
- Security and privacy issues for IoT networks
- Computing algorithms for IoT Applications (smart home/smart cities/smart transportation/smart devices/healthcare)

This Collection supports and amplifies research related to SDG 9.

Keywords: Internet of Things (IoT), Edge Computing, Intelligent Systems, Artificial Intelligence (AI), Machine Learning (ML), Deep Learning (DL), Security

Special Issue on Intelligent Control Systems and Their Applications
提出日: 2026-02-28

The Collection “Intelligent Control Systems and Their Applications” aims to showcase cutting-edge research and advancements in the development and deployment of intelligent control strategies across diverse fields. As modern systems grow increasingly complex, conventional control methods often fall short in handling nonlinearities, uncertainties, and real-time decision-making challenges. This collection emphasizes innovative approaches that integrate neural networks, fuzzy logic, and hybrid neuro-fuzzy models, including Type-2 fuzzy systems, to address these issues.

We invite contributions that explore theoretical advancements, algorithm design, and practical implementations of intelligent control systems. Specific areas of interest include, but are not limited to, adaptive and learning-based control, optimization techniques, robust control strategies, and applications in robotics, autonomous vehicles, smart grids, and industrial automation. By bringing together interdisciplinary insights, this collection seeks to highlight the transformative impact of intelligent control systems on improving performance, efficiency, and reliability across various domains.

We encourage researchers and practitioners to submit original research, review articles, and case studies that demonstrate novel solutions, emerging trends, and future directions in this exciting and rapidly evolving field.

This Collection supports and amplifies research related to SDG 7 and SDG 9.

Keywords: Intelligent control systems, Neural networks, Fuzzy systems, Type-2 fuzzy systems, Neuro-fuzzy systems.

Special Issue on        Graph Representation Learning for Biomedical Applications
提出日: 2026-03-31

Graphs are a powerful abstraction of the structure and dynamics of complex systems, providing a solid theoretical framework for developing methods tackling relevant biomedical problems, for example, the modeling of 3D protein structures, enrichment of incomplete protein-protein interaction networks, protein automatic function prediction, construction of accurate disease classification models, drug discovery and repurposing, medical images analysis.

Biomedical data involves the use of complex multimodal and possibly heterogeneous graphs that have been leveraged to effectively model a wide range of different entities (e.g. atoms in molecular structures, protein-protein interactions, gene co-expression networks, regulatory networks, drug-target networks, cellular networks, healthcare knowledge, clinical, genetic and functional similarities among patients).

From this standpoint, Graph Representation Learning is attracting increasing interest from the biomedical network research community. This area has been further fueled by the emergence of Graph Neural Networks, specifically designed for the analysis of graphs using neural network tools and paving the way for the development of novel techniques.

This topical collection focuses on the research on graph representation methods, exploring both its theoretical and practical dimensions in addressing biomedical problems. We aim at gathering innovative research inspired by various biomedical problems featuring novel techniques for the development and application of Graph Representation Learning methods in biology and medicine.

We particularly welcome (but are not limited to) submissions on advancements in network representation and learning that target biomedical challenges, such as:

- Theoretical aspects of Graph Representation Learning (e.g. Foundations in knowledge representation, Structural Network analysis)
- Graph Representation Learning algorithms (e.g. Graph Embedding Techniques, Heterogeneous network representations, Multimodal/Multiview graphs, Generative graph models)
- Learning task on Graphs (e.g. node/link/graph property prediction, graph explainability and visualization techniques, graph generation)
- Deep Learning on Graphs (e.g. Graph Neural Networks)
- Applications of Graph Representation Learning (e.g. Drug discovery and re-purposing and response, Biomarker discovery, Functional genomics, Molecular interaction, Molecular structure, Biomedical image analysis, Analysis on single-cell and multi-omics data, Patient similarity networks, EHR and clinical data analysis, patients prognosis/diagnosis/recurrence prediction, general applications in Precision Medicine)
- Representation and algorithm on dynamical/temporal Graphs
- Network datasets and benchmarks
- Generative models for biomedical entities (e.g. generative LLM models)
- Evolutionary networks (e.g. phylogenetic, pangenomic)

This Collection supports and amplifies research related to SDG 9.

Keywords: graph representation learning, biomedicine, artificial intelligence, network medicine, heterogeneous network, multimodal data, node prediction, link prediction, graph visualization, precision medicine

Special Issue on Explainable AI and NLP Innovations for Understanding Online Social Media via Large Language Models
提出日: 2026-03-31

This collection explores the growing convergence of Natural Language Processing (NLP), Explainable Artificial Intelligence (XAI), and Large Language Models (LLMs) and how these technologies are revolutionizing online social media analytics. As LLMs such as GPT, BERT, and domain-specific transformers are increasingly deployed in real-world applications, the need for transparency, interpretability, and trust in AI systems has become paramount. This is especially true in high-stakes domains like digital communication platforms.

By integrating XAI and NLP approaches, it is possible to extract meaningful and interpretable insights from vast amounts of user-generated content on social media. Content moderation, sentiment and emotion analysis, behavioral profiling, and misinformation identification are some examples of applications.

We invite high-quality submissions that present novel approaches, models, algorithms, frameworks, or case studies demonstrating the use of explainable LLMs and NLP in social media contexts. Contributions that emphasize ethical deployment, interpretability, and the reliability of AI technologies in these sensitive and impactful settings are especially encouraged.

This Collection supports and amplifies research related to SDG 9.

Keywords: Explainable Artificial Intelligence, Large Language Models, Natural Language Processing, Social Media Analytics

Special Issue on Software Quality Assurance and Optimization in an Age of Intelligence
提出日: 2026-03-31

This collection aims to advance research and practice in Software Quality Assurance and Optimization (SQAP) to address the growing complexity and criticality of modern software systems. As software underpins industries such as healthcare, finance, aerospace, and smart infrastructure, ensuring reliability, security, and efficiency is paramount. This topic is timely, as industries increasingly demand systems that balance robustness with efficiency—highlighting the need for interdisciplinary approaches that address these challenges and explore emerging solutions across theory, methodology, and application.

The collection seeks innovative methodologies that integrate rigorous quality assurance with optimization techniques to enhance system quality and performance, and to mitigate risks. Specific areas of interest include software testing, defect modeling, AI-driven software tools, dynamic monitoring systems, performance engineering, and search-based software engineering. Additionally, the collection emphasizes both traditional and emerging optimization strategies, such as learning-based optimization, evolutionary computation, performance tuning, resource allocation, and DevOps-driven continuous integration pipelines.

By bridging software quality assurance and optimization, this collection aims to foster solutions that ensure software not only meets functional requirements but also operates sustainably under real-world constraints. Submissions are encouraged to address challenges in scalable quality assurance for distributed systems, AI/ML-based optimization, and the interplay between security and performance in complex software systems.

This Collection supports and amplifies research related to SDG 9.

Keywords: Software Quality Assurance, Software Optimization, Software Testing, Software Performance, Software Verification and Validation, Performance Engineering, Search-Based Software Engineering

Special Issue on 5G-Enabled IoT for Smart Cities
提出日: 2026-04-30

This collection examines the pivotal role of 5G-enabled IoT technologies in transforming urban infrastructure and enhancing city management through advanced civil engineering practices. It highlights how these technologies contribute to smarter, more sustainable cities by improving connectivity, data management, and automation across various urban systems. Contributions will explore the integration of 5G and IoT to optimize resource management, increase the efficiency of public services, and enhance the sustainability and resilience of urban environments. The collection aims to provide a comprehensive analysis of the challenges and opportunities presented by these technologies in urban planning and civil engineering, offering insights into innovative solutions and future advancements.

This Collection supports and amplifies research related to SDG 9, SDG 11, and SDG 13.

Keywords: 5G Communications, Internet of Things, Smart Cities, Urban Infrastructure, Civil Engineering, Sustainable Development, Connectivity, Data Management, Urban Automation, Technological Integration

Special Issue on Intelligent Decision and Optimization for Resilient Supply Chains
提出日: 2026-04-30

The collection “Intelligent Decision and Optimization for Resilient Supply Chains” highlights recent advancements in applying artificial intelligence and advanced optimization techniques to modern supply chain systems. As global supply chains encounter increasing uncertainty, disruptions, and sustainability pressures, intelligent, data-driven solutions have become essential for enhancing resilience, adaptability, and efficiency.

This collection focuses on innovative methodologies that integrate AI-driven decision-making, reliability analysis, and optimization strategies, including metaheuristic algorithms. Topics of interest include AI-based decision support systems, supply chain network optimization, reliability and risk assessment under uncertainty, and real-time adaptive strategies empowered by technologies such as machine learning, IoT, and digital twins.

We welcome original research that addresses emerging challenges in supply chain management, offering novel approaches to improving performance, resilience, and long-term sustainability.

This Collection supports and amplifies research related to SDG 9 and SDG 12.

Keywords: Intelligent Supply Chains, AI-Driven Decision-Making, Supply Chain Optimization, Reliability Analysis, Metaheuristics

Special Issue on Beyond Generative Models: Emerging Frameworks in Computational Protein Design
提出日: 2026-05-31

Recent advances in generative models—particularly diffusion-based, autoregressive, and transformer-based architectures—have propelled computational protein design into a new era of data-driven creativity. However, their success comes at a cost: high computational training demands and limited flexibility to incorporate or modify design constraints without significant retraining overhead.

This collection aims to highlight emerging computational frameworks that complement or extend beyond generative models in protein design. We invite contributions that explore function-guided optimization techniques, symbolic regression for developing novel scoring functions, evolutionary algorithms, reinforcement learning strategies, and energy-based modeling. We also welcome work on structure prediction-guided optimization, and hybrid pipelines that integrate generative models with constraint-aware modules using transfer learning, modular neural architectures, or post hoc fine-tuning—enabling adaptation to new design objectives without the need for full retraining.

This collection seeks to broaden the design landscape by encouraging methodological diversity, theoretical understanding, and practical design strategies. We particularly welcome studies that benchmark alternatives to generative models, highlight underexplored protein classes or functional goals, and demonstrate in silico and/or experimental validation.

This Collection supports and amplifies research related to SDG 9.

Keywords: Computational Protein Design, Computational Biology, Machine Learning, Artificial Intelligence, Bioinformatics, Cancer Biology, Metaheuristics

Special Issue on Augmenting Edge AI with Collaborative Edge Computing: From Trusted Nodes to Ubiquitous Personal Devices
提出日: 2026-05-31

Edge AI enables intelligent data processing at the closest edge and hence the execution of smart, novel latency-sensitive and data-intensive applications in numerous domains. A key aspect of Edge AI is the ability to execute complex artificial intelligence algorithms on resource-limited devices. However, the potential of Edge AI lies not only in the capabilities of individual devices to run AI tasks, but also in the enhanced performance that can be achieved when groups of co-located, trusted devices operate collaboratively, which might further improve results quality and energy consumption for AI inference and training tasks, paving the way for Collaborative Edge AI. Collaboration typically involves dedicated and trusted edge devices such as single-board computers, UAVs, FPGAs, and edge nodes, while personal devices like wearables and smartphones are less frequently considered. Year to year, societies all over the world invest in renewing or acquiring personal devices with improved computing capabilities that remain underutilized for long periods. Together with traditional edge computing devices, these personal devices represent a massively deployed distributed infrastructure, with computing resources at the closest edge whose integration to collaborative Edge AI has been scarcely explored.

This collection solicits state-of-the-art research addressing a broad spectrum of challenges and opportunities, including novel collaborative edge AI applications, edge AI-specific programming frameworks and languages, improved edge AI offloading frameworks, and mechanisms/protocols to implement scalable, robust, fault-tolerant, secure, and private middleware services that include dedicated edge and/or consumer devices as computing resource providers in such settings. Literature surveys and benchmarking studies are also welcome. We also welcome in-depth discussions and empirical studies of the sociological aspects (e.g., ethical issues, incentive mechanisms, societal consequences) and implications (e.g. environmental benefits) of collaborative edge AI.

This Collection supports and amplifies research related to SDG 9 and SDG 11.

Keywords: Edge AI, Collaborative Edge applications, Edge infrastructure, Machine Learning, Energy-aware Edge Collaboration, Social-Aware Edge Computing

Special Issue on Bio-Inspired Adaptive Systems for Collective Behaviors and Intelligent Optimization
提出日: 2026-05-31

This Collection aims to explore cutting-edge research in bio-inspired algorithms and adaptive systems, focusing on their applications in collective behavior, intelligent optimization, and decision-making processes. We invite submissions that investigate the theoretical development, practical implementation, and interdisciplinary approach, emphasizing the role of bio-inspired algorithms in modeling and solving complex real-world problems. The Collection will also highlight how these systems contribute to understanding and modeling social behaviors, improving multi-agent coordination, and solving optimization problems in domains such as transportation systems, crowd management, and resource allocation.

This Collection supports and amplifies research related to SDG 9.

Keywords: Bio-inspired algorithms, Adaptive systems, Collective behaviors, Ant Colony Optimization (ACO), Multi-agent systems, Self-organization, Artificial Intelligence, Agent-based Models and Intelligent optimization

Special Issue on AI-Empowered Smart Manufacturing: Paradigm, Systems, and Processes
提出日: 2026-05-31

Deep learning, large language models and other AI technologies, when applied in manufacturing industries, have attracted much attention from both scholars and practitioners. With the empowerment of AI technologies, production control and management in smart manufacturing systems will change significantly. This collection focuses on the cutting-edge research in AI-empowered smart manufacturing systems to solve the sophisticated production control and management issues in smart shop floors and factories. It aims to explore the potential of deep learning, large language models, and other emerging AI technologies to reorganize the production structure paradigm, reform the smart manufacturing system, and reshape the autonomous production control and management processes, especially in the area of collaborative design, process planning, production scheduling, human-robot collaboration, assembly sequencing, logistics monitoring, and other production control and management issues.

This Collection supports and amplifies research related to SDG 9.

Keywords: Artificial Intelligence, Smart Manufacturing System, Large Language Models, Production Control, Production Management, Prediction and Optimization

Special Issue on Hybrid Deep Learning and Computational Intelligence: Models, Optimization, and Applications
提出日: 2026-05-31

As AI systems become increasingly complex and application-driven, the need for interpretable, optimized, and domain-specific solutions is more critical than ever. This collection aims to highlight innovative research at the intersection of deep learning, fuzzy logic, and evolutionary computation, with a particular focus on hybrid neural-fuzzy models and metaheuristic-based optimization techniques.

It seeks to explore the synergy between deep learning and computational intelligence approaches—particularly those combining convolutional neural networks (CNNs), type-2 fuzzy systems, and metaheuristic algorithms such as particle swarm optimization (PSO), fuzzy gravitational search algorithm (FGSA), and the fireworks algorithm (FWA).

We welcome contributions that present novel hybrid architectures and optimization strategies applied to real-world challenges, especially in healthcare domains such as neurodegenerative disease diagnosis, medical image analysis, assistive technologies, and intelligent control systems. Research addressing critical issues such as explainability, fairness, data efficiency, and the ethical deployment of AI is especially encouraged.

Topics of interest may include, but are not limited to, the following areas:

- Hybrid neuro-fuzzy models integrating CNNs, type-2 fuzzy systems, and metaheuristic optimization
- Deep learning optimization using PSO, FGSA, FWA, and other swarm intelligence algorithms
- Type-2 fuzzy preprocessing for medical image enhancement, edge detection, and classification
- Deep learning and fuzzy logic integration in neurodegenerative disease research (e.g., Alzheimer’s detection)
- Large language models (LLMs) and fuzzy reasoning in medical knowledge extraction
- Hybrid AI systems for pattern recognition and real-time intelligent control
- Explainable and interpretable AI in biomedical and assistive applications
- Ethical and societal implications of AI in healthcare, accessibility, and sensitive environments

This Collection supports and amplifies research related to SDG 9.

Keywords: Hybrid Intelligence, Deep Learning Optimization, Type-2 Fuzzy Systems, CNNs, Computational Intelligence, Biomedical AI, Assistive Technologies, Metaheuristic Algorithms, Explainable AI, Intelligent Control Systems, Neurodegenerative Disease Classification, PSO, FGSA, FWA, Fuzzy Image Processing

Special Issue on Exploring the Collaboration Between Large and Small AI Models
提出日: 2026-05-31

The Collection “Exploring the Collaboration Between Large and Small AI Models” aims to showcase cutting-edge research and advancements in the synergistic integration of large and small models across diverse domains and applications.

As AI systems become increasingly ubiquitous, relying solely on large models presents challenges in computational efficiency, deployment costs, and real-time responsiveness, while small models alone may lack the generalized knowledge and processing power required for complex tasks. This collection emphasizes innovative approaches that leverage the complementary strengths of both paradigms through knowledge distillation, model ensembles, and other collaborative strategies.

We invite contributions that explore the theoretical foundations, architectural innovations, and practical implementations of large–small model collaboration. Topics of interest include, but are not limited to:

- Federated learning approaches combining large and small AI models
- Efficient knowledge transfer mechanisms
- Dynamic model selection strategies
- Applications of large models in edge computing, mobile intelligence, distributed systems, and resource-constrained environments

We welcome original research articles, reviews, and case studies that present novel collaboration frameworks, emerging methodologies, and future directions in this rapidly evolving field of AI model integration.

This Collection supports and amplifies research related to SDG 9 and SDG 11.

Keywords: Large–Small AI model collaboration, efficient knowledge transfer, model ensemble, hierarchical collaboration frameworks, federated learning with large-small models

Special Issue on Interoperability in Data and Security
提出日: 2026-06-30

In an era where digital transformation is rapidly reshaping industries and systems, the seamless integration and interaction of diverse technologies have become crucial. Data and security interoperability—ensuring that different systems can exchange and process data effectively while maintaining robust security measures—is at the forefront of these challenges. As organizations increasingly operate within complex ecosystems characterized by a variety of technologies, platforms, and data formats, achieving interoperability is crucial not only for operational efficiency but also for safeguarding sensitive information. This topical collection seeks to explore and elucidate the techniques and methodologies for enhancing data and security interoperability across different domains. We invite contributions encompassing theoretical research, experimental studies, comprehensive reviews, and survey papers. Areas of primary interest include, but are not limited to:

- Theoretical and practical approaches to data/security interoperability
- Designing interoperability with security and privacy requirements
- Solutions to compatibility issues across various data formats and standards
- Data interoperability in cloud computing and distributed systems
- Security and data interoperability in Internet of Things (IoT) environments
- Managing data interoperability in compliance with privacy regulations
- New technological approaches and frameworks for interoperability
- Data interoperability and security policy regulation and standardization

This Collection supports and amplifies research related to SDG 9 and SDG 11.

Keywords: interoperability, data interoperability, security interoperability, network interoperability, platform interoperability artificial intelligence, Internet of Things, standards

Special Issue on Cloud Services in the Era of Data Spaces, High-Performance and Edge Computing
提出日: 2026-06-30

Cloud computing has transformed computing, storage, and network management by offering centralized platforms, but the rise of mobile applications and IoT has revealed limitations in traditional architectures. Edge computing addresses these issues by decentralizing data collection, processing, and storage, placing them closer to the data source. This approach reduces latency, enhances responsiveness, scalability, and privacy, and cuts costs by lowering data traffic and cloud computing expenses. However, deploying AI on edge systems is challenging due to limited resources and the need for optimized architecture design.

Technologies like distributed logs (DLTs), such as blockchain and directed acyclic graphs (DAGs), offer secure, cost-effective solutions for digital asset exchange and traceability. Federated Machine Learning, which allows decentralized AI model training on local devices, promises improved privacy without sacrificing functionality.

Middleware solutions are critical for abstracting hardware and OS complexities, especially in edge computing, but optimizing resource usage in edge environments remains a challenge. Additionally, integrating quantum computing with high-performance computing (HPC) systems presents technical hurdles. Ongoing research in energy-efficient HPC-cloud architectures, HPC-quantum computing integration, and edge computing architecture is essential for addressing these issues.

This Collection supports and amplifies research related to SDG 9 and SDG 11.

Keywords: Cloud & AI; Large Scale Cloud Applications; Cloud Management and Operations; Cloud Security and Distributed Ledger Technologies; Cloud-base Quantum Technologies

Special Issue on        Intelligent Wireless Communications
提出日: 2026-06-30

In the era of ubiquitous interconnectivity, the requirements for wireless communication systems are continuously escalating. With its capabilities for dynamic optimization and adaptability, intelligent wireless communication is increasingly emerging as a pivotal direction in the evolution of wireless technologies. This collection aims to explore the latest advancements, methodologies, and technologies in the field of intelligent wireless communication, with a focus on novel solutions emphasizing low latency and high reliability. Emerging technologies such as reconfigurable intelligent surface (RIS), integrated sensing and communications (ISAC), and other innovations have attracted significant attention and demonstrate broad application prospects. By bringing together researchers, practitioners, and industry experts, this compilation seeks to share insights, innovative solutions, and practical approaches to advance cutting-edge developments in intelligent wireless communication systems.

This Collection supports and amplifies research related to SDG 9.

Keywords: reconfigurable intelligent surfaces (RIS), integrated sensing and communications (ISAC), channel estimation, intelligent communication, beamforming, semantic communication, communication performance, multiple-input multiple-output (MIMO), secure UAV communication.

Special Issue on Advances in Intelligent Information Fusion: Applications to Safety and Reliability Analysis of Complex Systems
提出日: 2026-06-30

This Collection explores cutting-edge advancements in intelligent information fusion (IIF) and their transformative applications in enhancing the safety and reliability of complex systems. As modern infrastructure, industrial processes, and cyber-physical systems grow in scale and interdependence, ensuring their robustness against failures, uncertainties, and dynamic operational conditions becomes critical. Traditional methods often struggle to handle the multidimensional, heterogeneous data streams inherent in such systems. This Collection aims to highlight innovative IIF methodologies—integrating machine learning, probabilistic reasoning, multi-sensor data fusion, and AI-driven analytics—to address these challenges. Contributions are sought in areas such as adaptive decision-making under uncertainty, real-time anomaly detection, predictive maintenance, risk assessment frameworks, and resilience optimization for systems in aerospace, energy, transportation, healthcare, and smart cities. By bridging gaps between theoretical advancements and practical implementations, this Collection will showcase how IIF enables proactive safety management, reduces operational risks, and improves system longevity. Submissions emphasizing interdisciplinary approaches, case studies, or validation in high-stakes environments are particularly encouraged. The Collection seeks to foster dialogue among researchers in computer science, systems engineering, reliability analysis, and applied mathematics, ultimately driving the evolution of intelligent, self-aware systems capable of thriving in complex, data-rich ecosystems.

This Collection supports and amplifies research related to SDG 7 and SDG 9.

Keywords: Intelligent Information Fusion; Complex System Reliability; Safety Analysis; Multi-Sensor Data Fusion; Machine Learning for Risk Assessment; Predictive Maintenance; Uncertainty Quantification; Resilience Engineering; Decision Support Systems; Cyber-Physical Systems

Special Issue on Embedded AI for Real-World Edge Applications
提出日: 2026-07-31

The integration of embedded systems, low-power hardware, and artificial intelligence (AI) has enabled significant advances in real-time, on-device computing, widely known as Edge AI. These advances enable intelligent data processing and decision-making directly at the network edge, reducing latency, conserving bandwidth, and enhancing reliability in resource-constrained or remote environments.

This Collection aims to explore the technical foundations, design methodologies, and applied deployments of embedded AI systems across a broad range of real-world domains, including healthcare, smart environments, industrial monitoring, mobility, autonomous guide, smart agriculture, energy harvesting, and environmental sensing.

We welcome contributions on Embedded AI, Edge Computing, and TinyML with a focus on systems and solutions that are field-deployable, resource-efficient, and practically validated.

Topics of interest include, but are not limited to:

- TinyML and lightweight deep learning architectures for edge inference
- Hardware–software co-design for embedded AI systems
- Signal and image processing on microcontrollers or low-power devices
- Edge-based biosignal analysis (e.g., EEG, EMG, PPG) and wearable health monitoring
- Embedded vision systems for object detection, semantic segmentation, or classification
- On-device machine learning for monitoring and actuation in real-world settings
- Sensor fusion in edge nodes for environmental or health monitoring
- Distributed edge architectures and federated or collaborative learning
- Energy harvesting and power management for AIoT applications
- Security, privacy, and robustness of embedded intelligence in the field
- Benchmark datasets, reproducible experiments, and validated field deployments

This Collection supports and amplifies research related to SDG 9.

Keywords: Edge AI; Embedded Systems; Embedded Intelligence; Edge Computing; TinyML; Hardware-software Co-design; Embedded Vision; On-Device Machine Learning; Sensor Fusion; Federated Learning; Signal Processing; Wearable AI; AIoT

Special Issue on Large Language Models as Evaluators in Computing: Opportunities, Challenges, and Future Directions
提出日: 2026-07-31

Large Language Models (LLMs) are rapidly reshaping the AI landscape, and their use as automated “judges” or evaluators has the potential to revolutionize how we assess a wide range of outputs, from document relevance in information retrieval to the quality of machine-generated text. Crucially, their benefits extend far beyond traditional, well-resourced tasks where human judgments are costly to obtain. LLMs open the door to generating labels and evaluations in niche or emerging domains where no strong annotation tradition exists and data are scarce, so-called “low-resource” areas. Examples range from specialized biomedical subfields, environmental and climate-change–related text analysis, and underrepresented languages, to emerging areas such as online behavioral research or misinformation detection. In these contexts, LLMs can help create high-quality labels, accelerate dataset development, and enable reliable system evaluation where traditional human annotation would be prohibitively difficult or expensive.

This collection aims to bring together cutting-edge research that addresses the significant opportunities and inherent challenges of this paradigm. We welcome contributions on topics such as: foundational methods, novel prompting strategies, fine-tuning techniques, and frameworks for improving LLM evaluation capabilities.

Topics of interest include but are not limited to:

- Reliability and Bias: Studies on understanding, quantifying, and mitigating the inherent biases (e.g., position bias, self-preference) and ensuring the reliability of LLM-based judgments.
- Novel Applications: Papers exploring the use of LLM evaluators in diverse domains, including information retrieval, NLP, recommender systems, healthcare, computational social science, and education.
- Human-LLM Collaboration: Research on hybrid systems that combine human expertise with the scalability of LLMs to create more robust and efficient evaluation pipelines.
- Efficiency and Scalability: Techniques to make LLM-based evaluation more cost-effective and computationally efficient.

This Collection supports and amplifies research related to SDG 9.

Keywords: Large Language Models (LLMs), LLM-based Evaluation, Automated Evaluation, Bias in AI Evaluation, Human-LLM Collaboration, Prompting Strategies, Fine-Tuning Techniques, Information Retrieval, Scalable Evaluation Methods

Special Issue on Imaging for Human Recognition: Advances, Challenges, and Social Impact
提出日: 2026-08-25

The integration of imaging technologies, artificial intelligence, and identity systems is rapidly reshaping how human identity is established, verified, and protected across sectors, including healthcare, public safety, digital governance, and border control. Imaging-based biometric systems – from fingerprints and face to palm, iris, vascular patterns, gait, and neonatal biometrics – hold tremendous potential to enhance identity assurance, enable secure access to public services, and strengthen protection for vulnerable populations. Yet fundamental challenges remain. Imaging under real-world conditions often faces limitations related to physiological variation (e.g., aging and growth in infants and children), data scarcity, sensor constraints, spoofing and security threats, demographic biases, and privacy and ethical considerations. Addressing these challenges demands a multidisciplinary approach combining advanced imaging techniques, AI-driven modeling, clinical and field validation, human-centric design, ethical framework,s and public-policy alignment. This collection aims to gather cutting-edge research advancing biometric imaging in its technical, ethical, and societal dimensions. We invite contributions that explore innovations in biometric image acquisition, enhancement, and recognition; develop trustworthiness, fairness, security, and explainability in biometric imaging systems; and bridge laboratory advances with deployment in real-world social, health, and security settings.

This Collection supports and amplifies research related to SDG 16.

Keywords: Biometric Imaging; Infant Biometrics; Longitudinal Human Identification; AI for Identification and Security; Social and Public-Policy Applications of Biometrics; Security; Vulnerable Populations; Real-world Deployment

Special Issue on Hypergraph Learning and Its Applications to Science
提出日: 2026-08-31

This collection is dedicated to advancing and highlighting the potential of hypergraph models in scientific discovery. Moving beyond the limitations of conventional graph-based methods, hypergraphs provide a native and powerful framework for capturing complex high-order interactions inherent in modern scientific data, from polypharmaceutical interactions in biomedicine to multi-component reactions in chemistry and functional networks in neuroscience. This collection aims to bridge the gap between theoretical innovation and practical application, soliciting cutting-edge research on hypergraph neural networks, hypergraph representation learning, hypergraph matching, and so on. We welcome contributions that either push the methodological frontiers of hypergraph learning or demonstrate its pivotal role in unlocking new insights and solving previously intractable problems across diverse scientific domains, including but not limited to AI for science, complex systems, bioinformatics, robotics, and brain-computer interfaces.

This Collection supports and amplifies research related to SDG 9.

Keywords: Hypergraph Learning; Hypergraph Neural Networks; High-Order Interactions; Representation Learning; AI for Science; Scientific Discovery; Biomedicine; Neuroscience; Brain-Computer Interfaces; Complex Systems

Special Issue on Intelligent Assistants for Industry 5.0
提出日: 2026-08-31

Industry 5.0 aims to reach beyond efficiency and productivity as the sole goals and emphasizes the role and contribution of industry to society. It focuses on the wellbeing of the worker and on the limitations of the planet. Industry 5.0 applies advanced technological solutions to increase prosperity. Hence, it complements Industry 4.0 by directing research and innovation efforts towards human-centric paradigm and sustainability. In order to enhance human capabilities and enrich the workplaces, Industry 5.0 introduces Intelligent Assistants, systems capable of understanding, reasoning, and learning from interactions.

This collection aims to bring together world-class researchers to present state-of-the-art research achievements and innovations in Intelligent Assistants applied to Industry 5.0. We invite submissions that investigate theoretical developments, practical implementations, and interdisciplinary approaches, with an emphasis on the role of Intelligent Assistants in modern manufacturing.

This collection explores the potential of Intelligent Assistants in providing instant access to critical data, enabling faster decision-making, improving troubleshooting, enhancing efficiency in modern factories, and more. We welcome a wide range of human–Intelligent Assistant communication designs, such as chatbots, voice assistants, and related systems. Meta-analyses of various Intelligent Assistants, or Intelligent Assistants used in various settings, are also encouraged.

This Collection supports and amplifies research related to SDG 8 and SDG 9.

Keywords: Artificial Intelligence; Natural Language Processing; Large Language Models; Human-Computer Interaction; Chatbot; Voice-Enabled Assistant; Industry 5.0; Smart Manufacturing; Production Planning and Control; Human-Centric Manufacturing

Special Issue on Recent Advances in Media Computing
提出日: 2026-08-31

The landscape of Media Computing is undergoing a fundamental shift. While recent deep learning breakthroughs, such as diffusion models, large multimodal foundation models, and adversarial generative techniques, have significantly enhanced media creation and manipulation, they still face critical limitations. These include high computational demands, shallow semantic reasoning, limited controllability, perceptual inconsistencies, and challenges related to trust, safety, and authenticity.

This collection focuses on next-generation Media Computing methodologies that bridge intelligent media understanding with efficient representation, perceptual modeling, and multimodal interaction. Our goal is to advance media systems that are resource-efficient, perceptually aligned, semantically grounded, and suitable for real-world deployment across visual, haptic, audio, 3D, immersive, and cross-modal scenarios.

We particularly seek contributions that advance:

- Perception- and semantics-aware media analysis, including models that integrate high-level reasoning with human visual, auditory, or haptic perception
- Efficient and scalable media representations, including AI-enhanced video, 3D/360°, and point-cloud compression, as well as rate-distortion-complexity-optimized, edge-aware coding
- Explainable, robust, and trustworthy media computing, covering interpretability, safety, integrity verification, and deepfake or media forensic analysis
- Cross-modal and embodied media intelligence, involving alignment and fusion across visual, linguistic, auditory, tactile, or 3D signals, and multimodal sensing for embodied or interactive systems
- Human-in-the-loop and controllable media systems, including adaptive interfaces, interactive perceptual feedback, and cognition- and memory-aware quality modeling
- Immersive and spatial media computing, such as VR/AR, light-field, volumetric, and 6DoF media processing, transmission, and perceptual quality evaluation
- Benchmarks, datasets, and evaluation methodologies addressing perceptual consistency, QoE, efficiency, reliability, and deployment under real-world constraints (e.g., bandwidth, device limits, environmental noise, underwater or degraded conditions)
- Efficient and on-device model architectures designed for mobile, edge, and resource-constrained environments
- Neuro-symbolic and hybrid learning approaches that combine structured reasoning with statistical or data-driven models
- Ethical, societal, and policy considerations associated with emerging media technologies and intelligent media systems

This collection aims to chart the future trajectory of Media Computing by highlighting research that unifies intelligence, perception, efficiency, and cross-modal interaction. Submissions demonstrating real-world validation in applications such as virtual and augmented reality, intelligent robotics and embodied AI, next-generation communication systems, healthcare imaging, environmental and underwater sensing, and digital forensics are especially encouraged.

This Collection supports and amplifies research related to SDG 9.

Keywords: Media Computing; Computer Vision; Multimodal Learning; Diffusion Models; Perception-Aware Models; Semantics-Aware Analysis; Cross-Modal Intelligence; Neuro-Symbolic Learning; Video and 3D Compression; Point Cloud Processing; Immersive Media (VR/AR/6DoF); Multimodal Interaction; Human-in-the-Loop Systems

Special Issue on Hardware Accelerated AI/ML Applications
提出日: 2026-09-16

Modern Artificial Intelligence (AI) and Machine Learning (ML) models require advanced hardware platforms that allow task parallelism both for the training and the deployment of these models in real time. Generative AI, for example, that is used to create new audio and video content or Large Language Models (LLM) such as ChatGPT have been trained and run on expensive supercomputers that can provide the hardware resources for the fast execution of these large deep learning models. Common AI/ML models for object detection, classification, tracking, tilt/orientation classification, etc, do not require the hardware resources of Generative AI or LLMs but still, cannot be executed on ordinary computing machines (desktops, laptops, smart phones). Lightweight versions of these models (e.g., pruning can be applied to reduce the stored parameters) are often offered for faster operation on platforms with lower computational power such as microcontrollers or other devices operating at the edge of an Internet of Things (IoT) infrastructure. These lightweight models offer lower inference latency but with a slight precision degradation. Graphic Processing Unit (GPU) powered computers are often employed for training, testing and using in real time AI/ML models. In embedded applications reconfigurable hardware is also an option to execute fast these models e.g., at the IoT edge.

In this Topical Collection we are interested in AI/ML models and applications that are based on hardware acceleration for efficient training, testing and real time operation. Hardware acceleration techniques can exploit data pipelining, loop unrolling, use of redundant resources and wide ports/buses to satisfy different Neural Network (NN) architectures that require a high degree of parallelism. The operations that need to be executed fast include NN weight transfer/update, multiply/accumulate, vector operations, etc. The efficient use of the hardware resources in order to achieve the highest operating speed with low cost platforms and a reasonable power consumption is very important for many AI/ML applications.

This Collection of Discover Computing, provides a forum for presenting novel approaches for hardware accelerated AI/ML applications. Therefore, papers that do not focus on hardware acceleration cannot be accepted.

This Collection supports and amplifies research related to SDG 9, SDG 11 and SDG 12.

Keywords: Artificial Intelligence; Machine Learning; Hardware Acceleration; Neural Networks; Hardware resources; Data pipelining; Loop Unrolling; High Speed Inference; Low Power

Special Issue on Bridging Computational Intelligence with Control Theory
提出日: 2026-09-20

The modeling, analysis, and control of complex dynamical systems are increasingly critical for solving real-world problems as computing, automation, and intelligent technologies advance. The high dimensionality, nonlinearity, and uncertainty inherent in these systems often make traditional control methods insufficient.

This collection explores how integrating computational intelligence techniques (e.g., reinforcement learning, neural networks) with control theory methodologies (e.g., model predictive control, stability analysis, event-triggered control) can address challenges such as real-time control, multi-agent collaboration, and decision-making in dynamic, high-dimensional, and uncertain environments.

Topics of Interest include, but are not limited to:

- Hybrid Control Strategies: Integrating reinforcement learning, neural networks, fuzzy logic, and classical control methods for improved performance in large-scale, nonlinear systems like autonomous vehicles, drones, and robots. Emphasis on event-triggered control for adaptive, real-time decision-making with reduced communication and computation.

- Deep Reinforcement Learning (DRL) and Model Predictive Control (MPC): Combining DRL with MPC to enable real-time optimization and adaptive decision-making in dynamic, uncertain environments, particularly for autonomous and multi-agent systems. Enhances MPC with computational intelligence to handle uncertainty and improve stability.

- Network Control and Event-Triggered Mechanisms: Optimizing distributed systems with event-triggered strategies to reduce communication and computation while ensuring robust performance under uncertainty. Focus on delayed feedback and fault tolerance to maintain stability in large-scale systems.

- Multi-Agent Collaboration and Distributed Control: Improving decision-making in multi-agent systems by incorporating neural network-based or fuzzy logic models for real-time collaboration, synchronization, and robust handling of uncertainties and delays.

- High-Dimensional Nonlinear Control and Optimization: Using computational intelligence techniques like neural networks and reinforcement learning to enhance optimization and decision-making in complex, high-dimensional systems such as robotics, smart grids, and industrial automation.

- Modeling and Simulation with Differential Equations: Leveraging differential and difference equations to model complex dynamical systems, with a focus on delays and uncertainties, key aspects of robust control and event-triggered mechanisms.

- Hybrid Models in Control: Combining classical control theory with neural networks and data-driven models for adaptive, intelligent control, ensuring both stability and performance guarantees.

This Collection supports and amplifies research related to SDG 9.

Keywords: Hybrid Control; Computational Intelligence; Event-triggered Control; Reinforcement Learning; Model Predictive Control; Distributed Control Systems; Multi-agent Systems; Neural Networks; Nonlinear Control; High-Dimensional Systems; Complex Dynamical Systems; Differential Equations and Simulation

Special Issue on Sensor-Driven Intelligence and Embodied Interactive Systems
提出日: 2026-09-30

Modern intelligent systems increasingly rely on rich, heterogeneous sensor data from cameras, depth sensors, wearable devices, robots, drones, and IoT platforms. These environments present challenges such as noisy or incomplete data, dynamic conditions, and real-time constraints, requiring integrated approaches in machine learning, computer vision, robotics, and computational intelligence.

This collection focuses on AI methods that transform sensor data into meaningful perception, enable intelligent decision-making, and support embodied interaction or real-world deployment. By framing research along this sensor-to-action pipeline, the collection provides a cohesive venue for contributions that bridge machine learning, sensing technologies, robotics, and AIoT systems, emphasizing practical, robust, and human-centered AI across healthcare monitoring, underwater sensing, assistive technologies, smart environments, educational robotics, and AIoT applications.

Topics of interest include, but are not limited to:

Sensor Acquisition and Perception

- Depth, stereo, fisheye, ultrasonic, and multimodal sensor fusion
- Visual perception in constrained environments (underwater, occlusion, low light)
- Medical and biological imaging with deep learning (CT, MRI, biomarkers)

Computational Intelligence & Decision-Making

- Swarm intelligence, PSO, evolutionary methods, and reinforcement learning
- Learning-based rule extraction for medical or behavioral prediction
- Scheduling, prediction, and optimization in sensor-rich environments

Embodied Interaction & Real-World Deployment

- Human–robot interaction and socially assistive robotics
- Sensor-based interactive systems (Kinect, gesture recognition, VR/AR)
- Edge and AIoT-based monitoring and assistive devices for health, safety, and environmental applications

This Collection supports and amplifies research related to SDG 9.

Keywords: Sensor Fusion; Artificial Intelligence (AI); Machine Learning; Computer Vision; Multimodal Sensor Data; Robotics; Embodied Systems; Human-Robot Interaction; AIoT (Artificial Intelligence of Things); Assistive Technologies; Healthcare Monitoring; Smart Environments

Special Issue on AI-Driven Remote Sensing and Sustainable Development
提出日: 2026-10-05

The amount of imagery collected from satellites, aircraft, UAVs, ground sensors, and mobile mapping systems is growing quickly. As these datasets become larger and more detailed, photogrammetry and remote sensing are increasingly working together with modern artificial intelligence and machine learning methods. This combination is opening new possibilities in Earth observation, 3D modelling, environmental monitoring, and the planning of sustainable infrastructure. With this Topical Collection, we hope to bring together studies that show how advanced imaging technologies can be combined with intelligent computational approaches in geospatial applications. We are interested in work that uses machine learning on optical, multispectral, hyperspectral, or SAR images, as well as research focused on processing point clouds from LiDAR, UAVs, or photogrammetric surveys. Topics such as interpretable AI for geographic decision making, optimization techniques for improving image quality or calibrating sensors, and the creation of digital twins of both natural and urban environments are also welcome. We also encourage studies in which AI and GIS are used together to support areas like renewable energy, disaster management, climate adaptation, or cultural heritage preservation. Our aim is to highlight methods that make geospatial imaging more accurate, more efficient, and easier to understand. By encouraging dialogue between researchers in photogrammetry, remote sensing, computer vision, GIS, environmental sciences, and engineering, we hope to support work that responds to real-world needs and global sustainability goals. Through this effort, we aim to contribute to the development of the next generation of responsible and effective geoimaging technologies.

Discover Imaging welcomes submissions that focus on on advanced imaging technologies, data acquisition (optical, multispectral, hyperspectral, SAR, LiDAR), image processing, and geospatial applications such as Earth observation, 3D modeling, and GIS integration for sustainability.

Discover Computing welcomes submissions that emphasize algorithmic innovation: machine learning and AI for image analysis, optimization techniques, interpretable AI frameworks, data fusion, and scalable computational models for large geospatial datasets.

This Collection supports and amplifies research related to SDG 7, SDG 11 and SDG 13.

Keywords: GeoAI; Explainable AI in Remote Sensin; Geospatial Machine Learning; Metaheuristic Optimization in Imaging; Sustainable Site Selection; Geospatial imaging; Remote Sensing; Environmental monitoring

Special Issue on AI-Enhanced Cyber-Physical and Societal Systems
提出日: 2026-10-05

This Topical Collection focuses on cutting-edge research that integrates artificial intelligence with cyber-physical systems (CPS), intelligent infrastructure, and societal-scale technologies. As digital and physical worlds converge, AI is increasingly essential for enabling autonomy, resilience, and sustainability in complex engineered systems such as smart grids, intelligent transportation networks, healthcare technologies, and urban infrastructures. The collection invites contributions on AI-driven modeling, control, optimization, sensing, decision-making, and system intelligence within CPS and societal applications. Topics may include machine learning for smart cities, AI-based energy management, autonomous and connected mobility, intelligent environmental monitoring, resilient infrastructures, and socio-technical systems that leverage AI for large-scale impact. Emphasis will be placed on work supporting the United Nations Sustainable Development Goals through innovations that promote clean energy, industrial modernization, sustainable communities, and improved societal well-being. Both theoretical advances and real-world deployments are welcome.

This Collection supports and amplifies research related to SDG 7, SDG 9 and SDG 11.

Keywords: Cyber-Physical Systems (CPS); Smart Cities; Resilient Infrastructures; Artificial Intelligence; Computational Biology; Machine Learning; Human-machine Interactions; Big Data

Special Issue on Intelligent Medicine: Machine Learning and Explainable AI for Next-Generation Healthcare
提出日: 2026-10-05

The healthcare sector is undergoing a profound digital transformation driven by Machine Learning (ML) and Artificial Intelligence (AI). As these technologies increasingly support diagnosis, prognosis, and clinical decision-making, the challenge is to balance predictive performance with interpretability, fairness, and trust. This Collection invites high-quality research that advances ML theory, methods, and applications specifically designed for clinical, epidemiological, and public-health contexts.

A central emphasis of the Collection is explainability as both a transparency requirement and an educational aid: model explanations that support clinicians in understanding complex patient dynamics, uncovering novel relationships, and enhancing causal reasoning. Contributions that integrate structured electronic health records with imaging, signals, or clinical text, as well as studies addressing fairness, uncertainty quantification, and human-centered design, are particularly encouraged. Likewise, approaches that enable federated, privacy-preserving, and regulation-compliant collaboration across healthcare institutions are welcome.

Topics of Interest

- Predictive Modeling for Diagnosis and Prognosis: Advanced ML architectures for risk stratification, early detection, treatment-response prediction, postoperative outcome modeling, and survival analysis.
- Comorbidity Analysis and Longitudinal Patient Trajectories: Representation learning and temporal modeling for disease interactions, multimorbidity networks, state-transition modeling, and dynamic patient phenotyping based on multivariate or multimodal time-series data.
- Multimodal Data Integration: Techniques merging structured EHRs with imaging (MRI, CT, X-ray), physiological signals (ECG, EEG, wearable data), genomics, and clinical narratives through attention mechanisms, graph-based learning, transformers, and foundation-model adaptation.
- Federated, Distributed, and Privacy-Preserving Learning: Federated optimization, secure aggregation, differential privacy, and decentralized architectures enabling cross-institutional collaboration while safeguarding patient confidentiality and ensuring regulatory compliance.
- Fairness, Causality, Robustness, and Trustworthy ML: Approaches addressing algorithmic bias, causal inference and counterfactual reasoning, calibration and uncertainty quantification, out-of-distribution robustness, and explainability techniques designed for clinical auditability.
- Ethical, Educational, and Human-Centered AI: Interpretable ML systems that enhance clinical training, support explainable decision pathways, improve AI literacy, and facilitate responsible deployment of AI-enabled healthcare tools.
- Human–Robot Interaction and Intelligent Interfaces in Healthcare: Adaptive clinical interfaces, affective computing for patient engagement, assistive robotics, and cognitive-support systems for medical staff and learners.

We warmly welcome submissions that advance explainable and trustworthy AI in healthcare, with a focus on methodological innovation and clinically relevant applications. To keep the Collection aligned with this focus, studies primarily centered on sentiment analysis or opinion mining of AI adoption fall outside the intended scope.

This Collection supports and amplifies research related to SDG 9.

Keywords: Machine Learning; Explainable AI; Healthcare; Comorbidity; Multimodal Learning; Time Series; Federated Learning; Causal Inference; Trustworthy AI; Medical Education; HCI for Personal Healthcare Assistant

Special Issue on Advances in Geovisualization Evaluation: Methods and Applications
提出日: 2026-10-09

Maps are abstract representations that aim to effectively and efficiently communicate spatiotemporal information to the users. Different geovisualization methods, including simple or more sophisticated ones, are utilized to represent such information. Nowadays, maps can be static, animated, mobile, and/or interactive, while they are primarily distributed through the internet. At the same time, modern geovisualization also incorporates extended reality (XR) technologies. Undoubtedly, geovisualization may be characterized by a high level of visual and perceived complexity. Hence, it is crucial to establish robust methods towards the evaluation of their usability. Examining how well, how and why different types of geovisualization work mainly involves the implementation of experimental studies that employ behavioral and neuroimaging methods and techniques to measure visual perception and cognition.

This collection aims to collect high-quality original research articles and systematic literature review studies in the field of geovisualization evaluation. We welcome new theories, methods, research frameworks, softwares, scientific datasets, and innovative applications.

Potential topics include, but are not limited to, the following:

-Cartographic design variables evaluation
-Experimental data analysis for geovisualization evaluation
-Mixed methods in geovisualization evaluation
-New methods in geovisualization evaluation
-Geovisualization and Human-Computer Interaction (HCI)
-Geovisualization software tools
-Geovisualization of Big Geospatial Data
-Geovisualization and Artificial Intelligence (AI) applications
-Map usability studies
-Extended Reality (XR) applications

For submissions to Discover Imaging, we welcome papers that focus on topics such as cartographic design variable evaluation, map usability studies, experimental and mixed-method approaches (including behavioral, eye-tracking, and neuroimaging), extended reality (XR) visualization for geospatial data, and human-computer interaction aspects centered on visual cognition and design.

For Discover Computing, we welcome submissions that emphasize geovisualization software tools and frameworks, handling big geospatial data through scalable architectures and GPU/edge acceleration, computational methods for real-time rendering and uncertainty encoding, XR integration from a systems perspective, and AI-driven applications for adaptive visualization and usability prediction.

This Collection supports and amplifies research related to SDG 4, SDG 9 and SDG 11.

Keywords: Eye-Tracking; Geovisualization; Geovisualization Applications; Map Evaluation; Map Usability; Map Interaction; Methods; Tools & Datasets; Neuroimaging. 

Special Issue on Theoretical and Methodological Integration of High-Performance Computing and Machine Learning
提出日: 2026-10-31

This collection focuses on the theoretical foundations, methodological innovations, and computational strategies that underpin the integration of High-Performance Computing (HPC) and Machine Learning (ML). It aims to provide insights into how HPC accelerates ML model training, scaling, and optimization, while ML techniques enhance HPC computational efficiency and performance. The collection explores how novel algorithms, frameworks, and system architectures enable scalable, efficient, and robust integration of ML and HPC.

Potential topics of interest include, but are not limited to:

- Theoretical models and frameworks for HPC-ML integration
- Architectures and design principles for scalable ML on HPC systems
- Energy-optimized GPU scheduling
- Trends in HPC-enabled ML frameworks and libraries (e.g., PyTorch, Horovod)
- Distributed training and parallelization of deep learning models using HPC infrastructure
- Deep Learning and Reinforcement Learning on HPC systems
- Techniques for parallelizing ML algorithms across heterogeneous computing environments
- Optimization of resource allocation, memory management, and scheduling for large-scale ML tasks
- Co-design of HPC hardware and ML software, including AI accelerators and exascale computing platforms
- Methodologies for integrating quantum, neuromorphic, and edge computing into HPC–ML workflows
- Generative AI and large language models at HPC scale
- Leveraging HPC to enhance cybersecurity with AI-driven threat detection, anomaly detection, and real-time attack analysis
- Demonstrating the practical integration of HPC with ML through mini-labs or live demos (e.g., setting up distributed training environments, optimizing model performance on HPC clusters)

This Collection supports and amplifies research related to SDG 9.

Keywords: High-Performance Computing (HPC); Machine Learning (ML); HPC-Accelerated Machine Learning; Distributed Deep Learning; Scalable Machine Learning; Parallel Computing for AI; Edge-to-Cloud AI Systems; AI Model Optimization on HPC; Resource Optimization in HPC-ML Systems; Exascale Computing for AI

Special Issue on Trustworthy Visual Intelligence and Adaptive Learning for Safety-Critical Systems
提出日: 2026-12-31

This Collection focuses on advancing trustworthy and adaptive visual intelligence for safety-critical systems. With deep learning increasingly deployed in industrial inspection, environmental monitoring, and predictive maintenance, ensuring reliability, interpretability, and adaptability is essential. We welcome original research and reviews on vision-based defect inspection, anomaly detection, predictive maintenance, and intelligent surveillance, emphasizing explainable, uncertainty-aware, and domain-adaptive learning. Topics of interest include diffusion and self-training models, uncertainty-aware perception, edge-AI for real-time monitoring, and human-in-the-loop decision systems. Works validated in manufacturing, energy, or public-safety environments are especially encouraged. By integrating trustworthy AI principles with visual intelligence and adaptive learning, this Collection aims to advance reliable, transparent, and resilient intelligent systems that enhance safety, operational efficiency, and confidence in next-generation AI applications.

This Collection supports and amplifies research related to SDG 9.

Keywords: Trustworthy AI; Visual Intelligence; Adaptive Learning; Safety-Critical Systems; Deep Learning; Vision-Based Defect Inspection; Predictive Maintenance; Anomaly Detection; Intelligent Surveillance; Uncertainty-Aware Learning