The International Journal of eScience

Computing infrastructures and systems are rapidly developing and so are novel ways to map, control and execute scientific applications which become more and more complex and collaborative.
Computational and storage capabilities, databases, sensors, and people need true collaborative tools. Over the last years there has been a real explosion of new theory and technological progress supporting a better understanding of these wide-area, fully distributed sensing and computing systems. Big Data in all its guises require novel methods and infrastructures to register, analyze and distill meaning.

FGCS aims to lead the way in advances in distributed systems, collaborative environments, high performance and high performance computing, Big Data on such infrastructures as grids, clouds and the Internet of Things (IoT).

The Aims and Scope of FGCS cover new developments in:

[1] Applications and application support:

    Novel applications for novel e-infrastructures
    Complex workflow applications
    Big Data registration, processing and analyses
    Problem solving environments and virtual laboratories
    Semantic and knowledge based systems
    Collaborative infrastructures and virtual organizations
    Methods for high performance and high throughput computing
    Urgent computing
    Scientific, industrial, social and educational implications
    Education

[2] Methods and tools:

    Tools for infrastructure development and monitoring
    Distributed dynamic resource management and scheduling
    Information management
    Protocols and emerging standards
    Methods and tools for internet computing
    Security aspects

[3] Theory:

    Process specification;
    Program and algorithm design
    Theoretical aspects of large scale communication and computation
    Scaling and performance theory
    Protocols and their verification

Special Issue on Explainable Artificial Intelligence in Drug Discovery and Development
Día de Entrega: 2024-12-15

Motivation and Scope

'Artificial Intelligence' (AI) has recently revolutionized the field of drug discovery and development, achieving breakthroughs in areas such as molecular design, chemical synthesis planning, protein structure prediction, and macromolecular target identification. Despite various computational methods proposed to address practical challenges, the complexity of these algorithms often results in limited explainability of the models, hindering our ability to understand and explain their underlying mechanisms. Given the rapid advancement of AI in drug discovery and related fields, there is an increasing demand for methods that help us understand and interpret the underlying models. Consequently, proposing 'Explainable Artificial Intelligence' (XAI) methods to address the challenge posed by the lack of explainability in deep learning models and enhancing human reasoning and decision-making capabilities have become imperative.

This special issue aims to gather papers that focus on integrating and applying advanced XAI algorithms to address the most fundamental questions in drug discovery and development, including drug repositioning, potential drug target identification, and small drug molecule target interaction and binding affinity prediction, etc. We expect the articles covering this special issue can effectively promote the drug discovery in methodology and meanwhile provide interesting insights or new biological observations.

The topics of this special issue include but not limited to:

Prediction of drug properties with XAI
Explaining drug-drug/target interaction through XAI
Development of explainable large language models for drug discovery
XAI for drug and target feature representation
XAI for ab initio drug design
XAI for virtual screening drugs

Guest Editors

Leyi WeiShandong University, Chinaweileyi@sdu.edu.cn 
Balachandran ManavalanSungkyunkwan University, South Koreabala2022@skku.edu 
Xiucai YeUniversity of Tsukuba, Japan yexiucai@cs.tsukuba.ac.jp 
Dariusz MrozekSilesian University of Technology, PolandDariusz.Mrozek@polsl.pl 

Important Dates
Submission portal opens: March 20, 2024
Deadline for paper submission: Dec. 15, 2024
Latest acceptance deadline for all papers: March 1, 2025 

Special Issue on Approximate Computing: the need for efficient and sustainable computing
Día de Entrega: 2025-01-31

Motivation and Scope

Today, computing systems face unprecedented computational demands. They serve as bridges between the digital and physical world, processing vast data from diverse sources. Our digital world is constantly producing an immense volume of data. According to recent estimates, millions of terabytes of data are created each day. To handle this immense volume of data, increasingly sophisticated and resource-constrained devices are deployed at the edge, where energy and power efficiency takes center stage. Additionally, the growth of modern AI models, particularly neural networks, has led to boundless computational and power demands. For example, GPT-3 featuring 175 billion parameters, BERT large equipped with 340 million parameters, require high energy costs for training and inferencing data. Approximate Computing (AxC) provides a promising solution: by intentionally allowing slight inaccuracies in computations, AxC significantly reduces overhead (including energy, area, and latency) while preserving practical accuracy levels. These paradigms find applications across several domains. With the intent of navigating the intricate balance between accuracy, reliability, and energy efficiency, exploring Approximate Computing (AxC) techniques becomes crucial.

The proposed Special Issue (SI) investigates the intersection of energy-efficient computing and accuracy of state-of-the-art workloads, shedding light on innovative approaches and practical implementations.

The potential areas of interest for the proposed SI include, but are not limited to, the following topics:

    Approximation for Deep Learning applications, including Large Language Models (LLMs)
    Approximation techniques for emerging processor and memory technologies
    Approximation-induced error modeling and propagation
    Approximation in edge computing applications
    Approximation in HPC and embedded systems
    Approximation in Foundation Models
    Approximation in reconfigurable computing
    Architectural support for approximation
    Cross-layer approximate computing
    Hardware/software co-design of approximate systems
    Dependability of approximate circuits and systems
    Design automation of approximate architectures
    Design of approximate reconfigurable architectures
    Error resilient Near-Threshold Computing
    Methods for monitoring and controlling approximation quality
    Modeling, specification, and verification of approximate circuits, and systems
    Safety and reliability applications of approximate computing
    Security in the context of approximation
    Software-based fault-tolerant technique for approximate computing
    Test and fault tolerance of approximate systems

Guest Editors

Annachiara Ruospo
Politecnico di Torino, Italy
annachiara.ruospo@polito.it

Salvatore Barone
University of Naples Federico II, Italy
salvatore.barone@unina.it

Jorge Castro-Godinez
School of Electronics Engineering
Instituto Tecnologico de Costa Rica, Costa Rica
jocastro@itcr.ac.cr

Important Dates

Submission portal opens: November 1st, 2024
Deadline for paper submission: January 31st, 2025
Latest acceptance deadline for all papers: May 31st, 2025

Special Issue on On-device Artificial Intelligence solutions with applications on Smart Environments
Día de Entrega: 2025-02-25

Motivation and Scope

The recent advancements in Artificial Intelligence (AI) and the increasing computational power acted as catalyzer for the widespread diffusion of Intelligent Cyber Physical Systems (ICPSs) as a novel way to run smart applications with a “reasoning” component. Unfortunately, the limited hardware capabilities of these devices pose significant limitations on the complexity of the tasks and Deep Learning models that can be run effectively. During the years, solutions like weights compression or quantization have been proposed to address this issue, but they usually require a careful tuning and most of the time they consist in a post-training operation. From the very beginning, the training of complex Deep Learning models has always been reserved to powerful machines with large computing capabilities (typically identified in the Cloud), limiting the Edge only to the inference. However, these solutions do not work especially when latency, security, and high customization aspects become key prerequisites. In such a context emerges the need of novel methods to deliver the intelligence into an embedded system without the data leaving the device. Originally born as a complementary technology, On-device AI is expected to become a hot topic in the next years as a new paradigm where both training and inference processes are performed on the same device. If on the one hand, the possibility to run intelligent algorithms on these systems is a challenging task, on the other the benefits in terms of response time and energy efficiency derived from this technology are going to be the foundations for a novel type of “reasoning” systems. To this aim novel architectures and frameworks should be explored to enable the access to AI based tailored services. Considering a scenario where the Edge would potentially store sensitive data (that should never travers the Internet), it is evident that these devices could become the target of attacks by malicious users. In this sense, privacy and security aspects represent another key elements to be carefully considered and implemented.

This special issue has the goal to promote original, unpublished, high-quality research about On-device AI solutions applied to the Smart Environments and Industry 4.0 contexts.

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

    On-device training solutions
    On-device AI applications
    Federated Learning training and inference strategies on Edge devices
    AI Intelligent Systems
    AI for Microcontrollers
    AI applications at the Edge
    AI methods for Industrial applications
    AI based services at the Edge
    Hardware efficient Deep Learning applications
    Energy efficient Deep Learning algorithms
    Privacy and Security for Deep Learning
    Comparative analysis of on-device AI frameworks
    Implementation case studies
    Low-power AI applications and methods
    Lightweight AI algorithms for Edge devices
    Edge architectures and frameworks for AI

Important Dates

Submission portal opens: July 25, 2024
Deadline for paper submission: February 25, 2025
Latest acceptance deadline for all papers: June 30, 2025

Special Issue on Advances in Quantum Computing: Methods, Algorithms, and Systems Vol II
Día de Entrega: 2025-02-28

Motivation and Scope

Quantum computing (QC) is an emerging, potentially disruptive computational model gaining strong momentum in the scientific community. QC research covers multiple intertwined aspects, ranging from potential hardware design and different implementations and technologies to the quantum software stack, including compilers, high-level programming abstraction, tools, and quantum algorithms and applications. With the advent of the QC systems openly available to the scientific community and the first promising benchmarks showing quantum advantage, the effort towards practical, yet daunting, issues such as the hardware and software integration of QC systems into the HPC infrastructure, the QC acceleration of classical scientific and industrial applications and workflows (e.g., quantum chemistry and quantum simulations, drug discovery, computational fluid dynamics) intensified in the last few years, leading to several proposed approaches to harness the QC power.

From a high-level point of view, the Quantum Processing Unit (QPU) can be seen as a specialized device to accelerate certain applications that exploit algorithmic formulations to use quantum state superposition, entanglement, quantum tunneling, or interference. QPUs can be deployed today as an accelerator for the first time in HPC systems. While extensive experience has been gained to operate and exploit other accelerators, such as GPUs that today provide the backbone of HPC systems, we face challenges fundamentally different from the past. These challenges include the usage of technologies, often requiring exceedingly low temperature and shielding, the need for interfacing the classical and quantum systems, the development of error correction algorithms, and quantum computer simulators to test the results of QC systems and QC real-world use cases and applications still in their infancy.

This special issue aims to collect influential contributions to address these challenges of quantum computing (QC). This special collection invites papers targeting the following topics:

    Integration of QC systems into HPC software and hardware infrastructure
    Large-scale HPC quantum computer simulators
    Tools for quantum applications, including compilers, runtimes, workflow managers, schedulers, and orchestrators
    Quantum algorithms and applications for solving scientific and engineering applications
    Quantum machine learning algorithms and applications
    Quantum data and quantum memories
    Quantum error correction codes
    Hybrid QC-HPC algorithms, applications, and workflows
    Performance modeling, analysis, and characterization of QC systems
    Quantum computer and cloud computing
    Quantum technologies for computation
    Characterization of quantum speed-up and supremacy
    Benchmarking of quantum systems
    Quantum Annealers: algorithms and applications

Guest Editors

Stefano Markidis
KTH Royal Institute of Technology, Sweden
markidis@kth.se 

Michela Taufer
University of Tennessee Knoxville, USA
taufer@utk.edu 

Lucio Grandinetti
Università della Calabria, Italy
lucio.grandinetti@unical.it 

Important Dates

Submission portal opens: August 15, 2024
Deadline for paper submission: February 28, 2025
Latest acceptance deadline for all papers: April 30, 2025

Special Issue on Large-scale HPC Approaches and Applications on Highly Distributed Platforms
Día de Entrega: 2025-03-15

Motivation and Scope

The ever-increasing complexity of scientific and industrial challenges due to the enormous amount of data available nowadays requires advanced high-performance computing (HPC) solutions capable of processing and analyzing data efficiently on highly distributed platforms. Traditional centralized HPC systems frequently fall short of the demands of contemporary large-scale applications (e.g., large language models), prompting a move towards more flexible and scalable distributed computing environments. Furthermore, the growing emphasis on the environmental impact of large-scale computing has highlighted the need for sustainable computing practices that minimize energy consumption and carbon footprint.

This Special Issue targets innovative solutions that investigate and tackle the challenges and opportunities of deploying HPC applications on distributed platforms, such as cloud, edge, and hybrid systems, focusing on promoting sustainable computing practices. The aim is to bring together pioneering research and practical insights highlighting advancements in scalable algorithms, efficient data management, robust performance optimization techniques, and sustainable computing strategies. By providing a platform for disseminating innovative solutions and best practices, this Special Issue aspires to support the development of resilient, efficient, and sustainable HPC applications that can meet the demands of future scientific and industrial challenges.

The topics of this special issue include (but are not limited to):

    High-performance computing architectures and systems for big data
    Parallel and distributed algorithms for big data processing
    HPC-enabled data analytics
    High-performance data storage and retrieval systems
    Performance modeling and evaluation of HPC systems in distributed platforms
    HPC in machine learning and artificial intelligence
    HPC for scientific computing and simulations
    HPC in the Cloud for big data processing
    Energy-efficient and green HPC

Guest Editors

Alessia Antelmi
University of Turin, Italy
alessia.antelmi@unito.it

Emanuele Carlini
National Research Council of Italy, Italy 
emanuele.carlini@isti.cnr.it

Important Dates

Submission portal opens: Sep 15, 2024
Deadline for paper submission: March 15, 2025
Latest acceptance deadline for all papers: June 15, 2025

Special Issue on Generative AI in Cybersecurity
Día de Entrega: 2025-05-15

Motivation and Scope

The world of cybersecurity is changing very rapidly, and the integration of Generative Artificial Intelligence (GenAI) represents a major transition in defense systems as well as attack tactics. Over the last decade, AI developments, especially through chatbots such as ChatGPT, Gemini, and DALL-E, have permeated several sectors, enhancing efficiency in operations and availing innovative approaches. This transformative technology is now at the center stage of cybersecurity by offering unprecedented possibilities and new challenges. Generative AI’s power transcends traditional use cases, fortifying defenses but also creating fresh angles for cyber threats. This special issue intends to examine the multifaceted influence of GenAI on cybersecurity by providing a comprehensive understanding of its potential to transform threat detection, mitigation, and response strategies. In particular, we are looking for ground-breaking studies that address topics including vulnerability assessment, automated hacking, ransomware and malware generation, as well as automation in cyber-defense mechanisms. There is also a need for papers examining the ethical concerns surrounding the use of GenAI within the cybersecurity landscape, hence promoting a balanced approach toward this potent tool.

The topics of Interest Include, but are not limited to:

    Vulnerability Assessment: Enhancing detection and assessment methodologies with GenAI.
    Social Engineering and Phishing Attacks: Crafting sophisticated social engineering attacks and developing prevention strategies.
    Automated Hacking and Attack Payload Generation: Automating hacking processes and generating complex attack payloads.
    Ransomware and Malware Code Generation: Creating and detecting advanced malicious software.
    Polymorphic Malware Generation: Generating and neutralizing dynamic, AI-generated threats.
    Cyberdefense Automation: Automating and enhancing defense mechanisms through AI integration.
    Cybersecurity Reporting and Threat Intelligence: Leveraging AI for advanced threat intelligence and proactive defense.
    Secure Code Generation and Detection: Employing AI for secure code generation and vulnerability detection.
    Identification of Cyber Attacks: Real-time attack identification and response using AI.
    Developing Ethical Guidelines: Establishing ethical norms for AI deployment in cybersecurity.
    Enhancing Cybersecurity Technologies: Augmenting existing tools and methodologies with AI.
    Incident Response Guidance: Utilizing AI in incident response and management.
    Malware Detection: Advancing detection techniques with AI.
    Social, Legal, and Ethical Implications of Generative AI: Comprehensive analysis of societal impacts and ethical considerations.

Guest Editors

S. Leili Mirtaheri
University of Calabria, Italy
leili.mirtaheri@dimes.unical.it

Andrea Pugliese
University of Calabria, Italy
andrea.pugliese@unical.it

Valerio Pascucci
University of Utah, United States of America
pascucci@acm.org

Important Dates

Submission portal opens: November 1, 2024
Deadline for paper submission: May 15, 2025
Latest acceptance deadline for all papers: September 15, 2025

Special Issue on High-performance Computing Heterogeneous Systems and Subsystems
Día de Entrega: 2025-05-30

Motivation and Scope

High-performance computing (HPC) is at a pivotal juncture, characterized by significant advancements in computing technologies and architectural features. This special issue explores this dynamic field's latest advancements, challenges, and innovations. Heterogeneous HPC systems integrate diverse computational resources, including CPUs, GPUs, FPGAs, and other specialized accelerators, to deliver superior performance for various applications. To harness their potential fully, these systems require novel resource management, scheduling, programming models, and performance optimization approaches. Combining cutting-edge research and practical insights, this special issue provides a comprehensive overview of heterogeneous HPC systems' current state and future directions. It is a valuable resource for researchers, practitioners, and policymakers interested in leveraging heterogeneous computing to solve complex scientific, engineering, and data-intensive problems more efficiently and effectively.

The topics include but are not limited to:

1. Heterogeneous Programming Models and Runtime Systems:

    Models, parallel resource management, and automated parallelization
    Algorithms, libraries, and frameworks for heterogeneous systems

2. Heterogeneous Architectures:

    Power/energy management, reliability, and non-von Neuman architectures
    Memory and interconnection designs
    Data allocation, caching, and disaggregated memory
    Consistency models, persistency, and failure-atomicity

3. Heterogeneous Resource Management:

    System and software designs for dynamic resources
    High-level programming, run-time techniques, and resource frameworks
    Scheduling algorithms, resource management, and I/O provisioning

4. Heterogeneity in Artificial Intelligence:

    AI/ML/DL predictive models and optimized systems for heterogeneous workflows and applications
    Tools and workflows for AI/ML/DL in scientific applications

Guest Editors

Sergio Iserte
Barcelona Supercomputing Center, Spain
sergio.iserte@bsc.es  

Pedro Valero-Lara
Oak Ridge National Laboratory, USA
valerolarap@ornl.gov 

Kevin A. Brown
Argonne National Laboratory, USA
kabrown@anl.gov 

Important Dates

Submission portal opens: October 01, 2024
Deadline for paper submission: May 30, 2025
Latest acceptance deadline for all papers: July 31, 2025

Special Issue on Cloud Continuum
Día de Entrega: 2025-08-30

Motivation and Scope

Cloud computing has become a common commodity with many different providers and solutions. Several new architectural models are being developed and applied to ensure scalability, quality of service, and resilience. The models focus both on the providers, optimizing the use of their infrastructure, and on the users' side, optimizing the response times and/or costs. This scenario is becoming more complex with the possibility of having computing power close to the users on edge/fog models. All this scenario can be seen as the Cloud Continuum.

There are already some conferences that have the Cloud Continuum in their call-for-papers. However, only some of them have explicitly focused on the applications. We aim to attract a broader range of papers, from software engineering to High-Performance Computing applications. All of them will be discussed in the Cloud Continuum scenario.

The following list includes some of the major topics for this special issue:

    Energy Efficiency
    AI-powered Services
    Security
    IoT Applications
    Architectural Models
    Serverless Computing
    Elasticity
    Storage Virtualization
    Sustainable Models
    Programming Models
    QoS for Applications
    Optimization and Performance Issues
    Communication Protocols
    Big Data
    High-Performance Computing Applications
    Innovative Cloud Applications and Experiences
    Availability and Reliability
    Microservices
    New Models (e.g., spot instances)
    Frameworks and APIs
    HPC as a Service

Guest Editors

Alfredo Goldman
University of São Paulo, Brazil
gold@ime.usp.br

Eduardo Guerra
University of Bolzano, Italy
eduardo.guerra@unibz.it

Jean Luca Bez
Lawrence Berkeley National Laboratory, USA
jlbez@lbl.gov

Important Dates;

Submission Portal Opens: April, 15th, 2025;
Deadline for paper submission: August, 30th 2025;
Latest acceptance deadline for all papers: February 15th, 2026.