There are 8 (eight) finalized special sessions as listed below. All special session papers go through the same rigorous review process. Special sessions with only a small number of accepted papers will be canceled, and the accepted papers moved to the regular/main session.
List of Special Sessions
| Session |
Artificial Neural Networks and Pattern Recognition in Geosciences
|
| Organizers |
- Sid-Ali Ouadfeul. Algerian Petroleum Institute, IAP, Algeria
- Leila Aliouane. LABOPHYT, FHC, UMBB, Boumerdes, Algeria
|
| Scopes/Topics |
Artificial Neural Networks and Pattern Recognition in the following area and other relevant research:
- Petrophysics/Well-logs data.
- Seismic method.
- Gravity/Magnetic (Potential field) methods.
- Electromagnetism/Magneto-telluric.
- Geology/Geophysics.
- Climatology.
- Geography
- Geodesy/Topography.
- Oceanography.
- Hydrology/Hydrogeology.
- Fractal Analysis combined with Neural Network.
- Wavelet Transform approaches combined with Neural Network.
- New Learning techniques in geosciences.
|
| Session |
Randomization-Based Deep and Shallow Learning Algorithms
|
| Organizers |
|
| Scopes/Topics |
Topics of the special session include (with randomization-based methods), but are not limited to:
- Randomized convolutional neural networks
- Randomized internal representation learning
- Regression, classification, and time series analysis by randomization-based methods
- Kernel methods such as kernel ridge regression, kernel adaptive filters, etc. with randomization
- Feedforward, recurrent, multilayer, deep, and other structures with randomization
- Ensemble learning with randomization l Moore-Penrose pseudoinverse, SVD, and other solution procedures.
- Gaussian process regression
- Randomization-based methods for large-scale problems with and without kernels
- Theoretical analysis of randomization-based methods
- Comparative studies with competing methods without randomization
- Applications of randomized methods in domains such as power systems, biomedical, finance, signal processing, big data, and all other relevant areas.
|
| Session |
Advances in deep and shallow machine learning algorithms for biomedical data and imaging
|
| Organizers |
|
| Scopes/Topics |
The topics relevant to the special issue include (but are not limited to) the following topics:
- Computer-aided detection and diagnosis
- Machine learning methods applied to biomedical data
- Computational intelligence techniques for neuroimaging data
- Deep learning (DL) for neuroimaging
- Applications of DL algorithms in biomedical data processing, pathological detection, and diagnosis
- Adversarial learning, meta-learning, and few-shot learning in image segmentation
- Biomedical image classification Evolutionary computing in bioinformatics
- Pattern recognition for imaging and genomics
- Computational intelligence for large scale imbalanced data
- Improved algorithms for multimodality neuroimaging data fusion systems
- Clustering and classification algorithms for Healthcare
- Real-world applications of computational intelligence for biomedical data and imaging
|
| Session |
Smart Home Technologies & Services for the Wellbeing and Sustainability of Society
|
| Organizers |
|
| Scopes/Topics |
Articles focusing on the following topics (but not limited to) are invited for this special session.
- Technology convergence and middleware standardization protocols for smart homes;
- Energy management systems solutions for smart homes;
- Network management solutions (etc: Edge Computing) for smart homes
- Cloud infrastructure services and management for smart homes
- Smart environment monitoring and control;
- Ambient Intelligences with IoT-enabled Smart Homes
- Situational aware services for IoT-enabled Smart Home
- Integration of Smart Home Big Data ( Audio, Video, text) management
- Innovative home automation applications and services ( sensors, wearable, RFID) for smart appliances
- Machine learning methods applied to smart homes;
- Artificial Intelligences based smart home automation and predictive living;
- Privacy-preserving Smart home solutions and services for user and system data
- Data integrity, authentication, and access control solutions and services for smart homes.
Some important topics that fit in the scope of the special session may not be listed above; therefore, if you are unsure whether your work would fit, we encourage you to get in touch with any organizer. All papers must comply with the basic requirements of ICONIP 2021. The review process will comply with the standard review process of the ICONIP. Each paper will receive at least three reviews from experts in the field. |
| Session |
Theory and Applications of Natural Computing Paradigms
|
| Organizers |
|
| Scopes/Topics |
The topics relevant to this special session include the following, but are not limited to:
- Physical reservoir computing
- Probabilistic computing
- Stochastic computing
- Reversible computing
- Molecule Computing, DNA computing
- Biological Cell Computing (amoeba, membrane)
- Optical/Photonic Computing
- Quantum Computing
- Any other topics related to natural computing
|
| Session |
Uncertainty-aware Imitation Learning
|
| Organizers |
|
| Scopes/Topics |
Topics of interest include, but are not limited to:
- Distribution shifts in imitation learning
- Noise injection in imitation learning
- Uncertainty quantification for imitation learning approaches
- Bayesian methods for mitigating uncertainties in imitation learning
- Direct methods for uncertainty quantification in deep imitation learning
- Applications (1D/2D/3D, supervised and unsupervised)
|
| Session |
Intelligent Transportation Analytics
|
| Organizers |
- R. Uday Kiran (The University of Aizu, Fukushima, Japan)
- Sonali Agarwal (Indian Institute of Information Technology, Allahabad, India)
- Koji Zettsu (National Institute of Information and Communications Technology, Japan)
- Ismail Khalil (IInstitute of Telecooperation, Johannes Kepler University, Linz, Austria)
|
| Scopes/Topics |
Topics of interest include but are not limited to:
- Visionary papers on Intelligent transportation systems related to Society 5.0/Industry 4.0 applications
- Models to predict traffic congestion
- Distributed and parallel frameworks to process and discover knowledge from very large transportation data
- Mining transportation data streams
- Mining uncertain transportation data
- Machine learning/Deep learning/Data Mining/Statistical analysis of transportation data
- Optimizing machine learning algorithms to predict traffic congestion effectively
- User interfaces to visualize transportation systems
- Multimodal analytics on transportation data
- Case studies
|
| Session |
Reliable, Robust, and Secure Machine Learning Algorithms
|
| Organizers |
- Dr. Xuan-Son Vu, Umeå University, Sweden
- Dr. Harry Nguyen, University of Glasgow, Singapore
- Dr. Monowar Bhuyan, Umeå University, Sweden
|
| Scopes/Topics |
Topics of the special session include (with reliable/robustness/secure learning methods), including but not limited to:
- Robustness of machine learning/deep learning/reinforcement learning algorithms and trustworthy systems in general.
- Confidence, consistency, and uncertainty in model predictions for reliability beyond robustness.
- Transparent AI concepts in data collection, model development, deployment, and reporting.
- Adversarial attacks – evasion, poisoning, extraction, and inference.
- New solutions to make a system robust to novel or potentially adversarial inputs; to handle model mis-specification, corrupted training data, addressing concept drifts, or dataset shifts.
- Theoretical and empirical analysis of reliable/robust/secure ML methods.
- Comparative studies with competing methods without reliable/robust certified properties.
- Applications of reliable/robust machine learning algorithms in domains such as biomedical, finance, computer vision, natural language processing, big data, and all other relevant areas.
- Unique societal and legal challenges facing reliability for trustworthy AI systems.
|
| Homepage |
https://www.reliableml.cs.umu.se/
|
