Analysis and Applications of Location-Aware Big Complex Network Data
1The University of Western Australia, Crawley, Australia
2RMIT University, Melbourne, Australia
3The Hong Kong Baptist University, Kowloon, Hong Kong
4Soochow University, Suzhou, China
Analysis and Applications of Location-Aware Big Complex Network Data
Description
In response to the ever-increasing challenges of location-aware network data like spatiosocial network and traffic network data, the network data processing technology is experiencing revolutionary changes in each stage including data collecting, cleaning, organizing, interpreting, analyzing, utilizing, and visualization. Those changes lead to a globally noticeable development trend of the convergence with big data frameworks, network analytical modeling, link or route prediction, and recommendation systems. This special issue aims at providing a forum to present recent advancements in the convergent research about big complex network data. Challenges include real-time event detection in a city, congestion discovery in a traffic network, location prediction of social users, social users’ behavior recognition in physical world, and unified systems of processing multidimensional complex network data. The robust solutions call for highly innovative techniques in the fields including, but not limited to, machine learning, genetic algorithms, chaos, genetic algorithms, cellular automata, neural networks, and evolutionary game theory. The special issue will attract high-quality submissions of location-aware big complex network data from world-wide researchers in the areas of the machine learning, artificial intelligence, data mining, natural language processing, data and web mining, and big data management to utilize their expertise and match up to develop more efficient and practical algorithms or models to obtain smart knowledge from daily generated invaluable social network data and traffic network data.
Potential topics include but are not limited to the following:
- Novel genetic algorithms to handle the problem complexity in location-aware social network
- Sophisticated neural network structure predicting complex events in location-aware social network
- Machine learning or deep learning in deriving social activities and behavioral metrics
- Fuzzy modeling and control of chaotic systems to cope with data uncertainty
- Spatial social influence learning modeling techniques
- Parallel big data processing infrastructure to achieve real-time response to data analysis requests
- Dynamic network data modeling using evolutionary game theory
- Learning methods for social link prediction and revisit prediction in traffic network
- Applications of any of the above methods and technologies