Sidebar[Skip]

Special Session 1:
Deep Learning and Applications

---

Deep learning techniques have achieved tremendous success in a variety of applications. Unlike other machine learning techniques, deep learning is able to generate hierarchical high-level representations from massive volumes of raw data automatically. This ability, in conjunction with the increased availability of large amounts of data and processing power, has enabled deep learning techniques to push the state-of-the-art in almost every domain it has been applied to, including computer vision, speech recognition, natural language processing, and machine translation. Deep learning-based systems that achieve, and even exceed human performance, are rapidly being deployed in the real world, most widely in the industrial domain, health, financial institutions, and e-commerce. As deep learning-based agents become pervasive, their impact on society and the economy at large becomes ever more profound.

This special session aims to bring together professionals, researchers, and practitioners to discuss new advancements of deep learning in applications from industry, healthcare, transportation, agriculture, logistics, and commerce, including and not restricted to medical image processing, medical diagnosis using wearables, smart cities, autonomous vehicles, robotics, industrial control, and fault diagnosis, quality control, manufacturing, satellite image processing, environmental monitoring, communication systems, Internet of Things, security, natural language processing, etc.

Scope and topics:

This special session invites submissions with new developments from those working in areas of deep learning algorithms, systems, and applications. Topics covered by this special session include but are not limited to:

• Supervised Deep Learning Architectures
• Convolutional Neural Networks
• Capsule Networks
• Deep Reinforcement Learning
• Unsupervised Deep Learning Architectures
• Deep Belief Networks
• Deep Autoencoders
• Generative Adversarial Networks
• Explainability and Deep Learning
• Adversarial Attacks and Defence Strategies
• Deep Learning for Text Generation
• Transfer Learning
• Deep Learning for Multi-Class Classification
• Deep Learning for Pattern Recognition
• Deep Learning for Image Segmentation and Object Detection
• Deep Learning for real-world applications such as:
• Modelling and System Identification for Prediction and Forecasting
• Quality control, condition monitoring, and fault diagnosis
• Big Data, Web applications, Decision Support Systems
• Medical Applications and Cloud Computing
• Robotics, Advanced Manufacturing
• Smart Cities, autonomous driving
• Advanced Communications and Multi-media Applications
• Environmental applications and satellite image processing
• Social Networks and Natural Language Processing, etc.

Special Session contact e-mail: muzafarrasool@gmail.com

• Chairs:

Muzafar Rasool, IUST-Kashmir, India
Uche Onyekpe, Ofcom, UK
M. Arif Wani, University of Kashmir, India
Vasile Palade, Coventry University, UK


• Chair Biographies

Muzafar Rasool: Details are available here.

Uche Onyekpe is a Machine Learning expert at the Office of Communications, UK, and Director of the African institute for Artificial Intelligence, with a focus on practical applications that benefit society. With a Ph.D. in Applied Machine Learning to Autonomous Vehicles, his work extends beyond the theoretical, impacting real-world technology and policy. Dr. Onyekpe's approach is characterised by a collaborative spirit and a commitment to ethical standards, fostering innovation and knowledge-sharing in the AI community. He has a proven track record in leading teams to develop innovative AI solutions. His work has not only enhanced operational efficiencies but also shaped regulatory policies and ethical AI standards.

M. Arif Wani: Details are available here.

Vasile Palade: Details are available here.

Technical Committee

• Edwin Lughofer, Johannes Kepler University Linz, Austria
• Slawomir Nowaczyk, Halmstad University, Sweden
• Sepideh Pashami, Halmstad University, Sweden
• Grzegorz Nalepa, Jagiellonian University, Kraków, Poland
• Bruno Veloso, University of Porto, Portugal
• Szymon Bobek, Jagiellonian University, Kraków, Poland
• Vaibhavi Chavan, Ravensbourne University, UK
• Joao Gama, University of Porto, Portugal
• Ariel Ruiz-Garcia, SeeChange.ai, UK
• Roozbeh Razavi-Far, University of Windsor, Canada
• Sara Sharifzadeh, Swansea University, UK
• Ibukun Oduntan, African Institute for Artificial Intelligence, Ghana
• Abdulrahman Altaahhan, Leeds Becket University, UK
• Ibrahim Almakky, MBZUAI University, United Arab Emirates
• Khan Muhammad, Sejong University, South-Korea
• Douglas Vieira, ENACOM, Brazil Wannous, IMT Nord Europe, France

Paper Submission Instructions

All papers will be double-blind reviewed and must present original work.

• CMT Submission Site
• Select the track: Special Session 1: Deep Learning and Applications

Papers submitted for reviewing should conform to IEEE specifications. Manuscript templates can be downloaded from:

• IEEE website

Keydates

• Submission Deadline: June 20, 2026
• Notification of Acceptance: July 10, 2026
• Camera-Ready Papers: July 20, 2026
• Pre-Registration: July 20, 2026

Registration

In order for your paper to be published in the proceedings you must register to the conference.

Paper Presentation Instructions

The papers submitted to this track will be presented in person as part of the conference. There is no virtual presentation for this session.