Artificial Intelligence:
- AI Algorithms
- Intelligent System Architectures
- Hybrid Intelligent Systems
- Expert Systems
- Artificial Neural Networks
- Intelligent Networks
- Parallel Processing
- Pattern Recognition
- Pervasive Computing and Ambient Intelligence
- Programming Languages Artificial Intelligence
- Artificial Intelligence Tools & Applications
- CAD Design & Testing
- Computer Vision and Speech Recognition
- Fuzzy Logic, Systems and Learning
- Computational Theories, Learning and Intelligence
- Computational Neuroscience
- Soft Measurements and Computing
- Soft Computing Theory and Applications
- Software & Hardware Architectures
- Web Intelligence Applications & Search
- Ambient Intelligence
- Artificial Immune Systems
- Autonomous and Ubiquitous Computing
- Bayesian Models and Networks
- Data Fusion Distributed AI
- Machine Learning
- Deep Learning
- Learning and Adaptive Sensor Fusion
- Multisensor Data Fusion Based on Neural and Fuzzy Techniques
- Applied Artificial Intelligence
- Self-Organising Networks
- Virtual and Augmented Reality
- Emotion Detection
Signal Processing:
- Signal Processing Theory and Methods
- Sensor Array and Multichannel Signal Processing
- Multivariable Sensor Systems
- Digital Signal Processing
- Image and Video Processing
- Multichannel Signal Processing
- Biomedical Signal Processing
- Biometrics
- Chaotic and Fractal Systems
- Computer Vision and Pattern Recognition
- Image and Video Processing
- Information Theory and Coding
- Speech Signal Processing
- Signal Processing for Communications and Networking
- Radar and Sonar Signal Processing
- Satellite Signal Processing
- Nonlinear Signal Processing
- Statistical Signal Processing
- Signal Processing for Internet of Things
- Coding
- Wavelet Transformation
- Theory and Application of Filtering
- Spectral Analyze
- Multidimensional Signal Processing
Special Sessions:
Computational Approaches in Biomedicine: Concepts of Mathematical Modeling and Biosignal Processing
Exploration of regulatory principles in physiological processes has become a fully multidisciplinary task, using conceptual backgrounds from mathematics, physics and computer science. (Neuro) physiological data are characterized by a high degree of non-stationary processes with varying time-frequency features. Different (patho) physiological processes are characterized by alterations in complexity, nonlinearity and irregularity of biosystems. Biosignals represents the result of complex mechanisms, including multiple feedback and coupling interactions. Innovative ways in biosignal processing and modelling the systems at various level of complexity involves a wide and varied array of methodological approaches. In this special issue, we welcome contributions ranging from original research reports, reviews, technical or methodology articles.
The topic will introduce novel biomedical, physical or computational principles in understanding the complex processes of physiological regulations, including, but not limited to, time – frequency analysis, concepts of mathematical modeling, fuzzy logic, nonlinear dynamics and the chaos theory, or the artificial neuronal networks.
Topics of interest include:
• Mathematical biology and bioengineering
• Multiscale models and simulation of biological systems
• Nonlinear problems, Bifurcations, Chaos theory
• Model formulation, Methodologies for model validation
• Fitting mathematical models to real processes
• Multiscale and multiphysics modeling
• Signal and / or image processing, pattern recognition
• Brain mapping
• Integrative machine-learning and neuroscience
• Nonlinear dynamics and complex systems
• Entropy and/or wavelet and applications
• Differential equations (ODE's, PDE's,) in biomedicine, solving via ANN
• Dynamic equations on multiple time scales in biomedicine
• Machine learning, Deep learning) in biomedical engineering
• (Artificial) Neural Networks for Biomedical Data
• Medical Signal Acquisition, Analysis and Processing
• Audio and Acoustic Signal Processing
• Motion Control • Neural and Cardiovascular Signals Processing
Session Chairman:
RNDr. Ing. Juliana A. Knociková. Ph.D
Department of Mathematics, Informatics and Cybernetics
University of Chemistry and Technology
Prague, Czech Republic
e-mail: Juliana.Alexandra.Knocikova@vscht.cz
Deep Learning for Automatic Detection of Surface Defects
Automatic detection of surface defects is an important problem in different engineering applications. A typical application is the detection of concrete cracks above and below the waterline. Shadows, obscured view, shallow and deep-water effects make the problem even more challenging. Standard approaches are based on using a large dataset of typical surface photos (with and without defects) for training a deep learning network, which is later used for automatic classification of digital images captured by robotic cameras. Advancements in the architecture of deep learning networks, the augmentation of datasets of surface images, engineering applications for automatic detection of surface defects are equally welcome to this Special Session.
- Deep learning for digital image analysis
- Automatic detection of surface defects
- Identification, location, and quantification of defects
- Concrete cracks and their automatic classification
- Countermeasures against optical effects (shadows, underwater illumination, etc.)
- Augmentation of training datasets
- Novel architectures of deep learning networks
- Engineering examples and applications
Session Chairman:
Prof. Minvydas Ragulskis
Department of Mathematical Modelling
Kaunas University of Technology,
Kaunas, Lithuania
e-mail: minvydas.ragulskis@ktu.lt
Safe Planning and Control for Autonomous Driving Using AI Technology
Autonomous driving represents a revolutionary shift, promising safer roads, and enhanced mobility in transportation. Consider, for instance, an autonomous vehicle navigating through urban traffic while avoiding other agents such as human-driven vehicles, and pedestrians. These scenarios pose critical safety challenges due to the unpredictability of these agents' intentions and behaviors, necessitating the estimation and integration of their a-priori unknown trajectories into the planning algorithm. Conventional approaches involve using historical trajectories to train a deep network, which is then incorporated into the path-planning process. Advancements in deep learning networks, statistical methods for quantifying uncertain prediction results, and engineering applications for the safe path-planning and control of autonomous driving are equally welcomed in this Special Session.
Topics of interest include, but are not limited, to the following:
- Deep learning for trajectory prediction
- Quantified representation for uncertain prediction results
- Recognition and classification of human driver behaviors
- Safe and robust control of autonomous driving
- Cooperative control between autonomous vehicles and human-driven vehicles
- Machine learning methods for autonomous path-planning
- Modeling and advanced simulation of autonomous driving
- Engineering examples and applications
Session Organizers:
Jinhao Liang, Department of Civil and Environmental Engineering,
National University of Singapore, Singapore
e-mail: jh.liang@nus.edu.sg
Chaopeng Tan
Department of Civil and Environmental Engineering,
National University of Singapore, Singapore
e-mail: tancp@nus.edu.sg
Qingyun Tian
Department of Civil and Environmental Engineering,
Nanyang Technological University, Singapore
e-mail: qytian@ntu.edu.sg
Zhenwu Fang,
Department of Civil and Environmental Engineering,
National University of Singapore, Singapore
e-mail: zhenwu.fang@u.nus.edu
Contribution Types:
- Keynote presentations
- Invited talks
- Industrial presentations
- Regular papers
- Special session papers
- Posters
- Exhibition