ASOCA 2018




Authors are invited to submit full papers ( with a maximum length of 12 pages, including references and appendices.) using ( Springer LNCS format). Authors must upload their paper as PDF file using the EasyChair platform.

If any problem arises when submitting your paper, please contact: FrankNSW2011@163.com

Each paper will be reviewed by at least three members of the international program committee for ensuring high quality.Paper acceptance will be based on originality, significance, technical soundness, and clarity of presentation. All accepted papers will be included in the workshop proceedings published as part of the Lecture Notes in Computer Science (LNCS) series of Springer.

At least one author of an accepted paper must register and participate in the workshop. Registration is subject to the terms, conditions and procedure of the main ICSOC conference to be found on their website: http://www.icsoc.org/



  • Full paper submission deadline : September 3, 2018
  • Notification to authors : September 30, 2018
  • Camera ready paper : October 15, 2018
  • Workshop : November 12, 2018


PC Co-Chairs
Dr Frank Jiang (University of Technology, Sydney, Australia)
Dr Haiying Xia (Guangxi Normal University, China)


The proposed duration of the workshop is one day.



While there are many important topics within the Big Data field, recent research suggested that learning models are critical for many real-world complex systems in associated with data analysis. The current i.i.d. ness-based learning methods cannot handle the coupling relations due to the increased complexity, multiple dimensionalities and heterogeneity of the data, they cannot efficiently find the inter-relationship and intra-relationship with such scale, and they do not scale well and nor do they perform well under highly unstructured, unpredictable conditions (data volume, data variety, data categories etc.). If these problems are resolved, the new learning methods can be the foundation to build up new Big Data applications, to further reduce financial and environmental costs, minimise under-utilised resources, and achieve better performance. Therefore, the new learning systems and applications have drawn growing attention in the community.

To this end, we propose this workshop entitled “Networked learning systems for secured sensing and Its Applications for Big Data Analytics”. The purpose of this workshop is to solicit papers that advance the fundamental theoretical understanding, technological design, and applications related to learning systems for Big Data analytics. The artificial neural network and machine learning methods are promising in solving the wide variety of analytical tasks that are hard to solve using ordinary rule-based programming. More importantly, we explore the new smart learning systems that are of vital importance in such complex, large, heterogeneous, and uncertain Big Data era. This special issue invites paper submissions on the most recent developments in security and learning architectures, neural network design, new data representation, tasks optimization, semi-supervised and coupled learning, and applications to real-world tasks. We also welcome survey and overview papers in these general areas pertaining to learning and neural network architectures, etc. Detailed topics of this workshop include but are not limited to:

  Cyber Security, CI/Fuzzy -based Learning and Analysis
  • Cyber Security, Intrusion Detection Systems, Malware and Botnets
  • IoT Security/Privacy preservation
  • Security of storage systems, operating systems
  • Intrusion detection, prediction, classification, and their response models for survivable, resilient, and self-healing systems
  • Actuate-sensory network security, web security, wireless security, digital forensics, security information analytics
  • Neural network-based learning, including the intelligent structures, algorithms and applications
  • Heterogeneous learning on multi-modality data, including Multi-view learning, Multitask learning, Transfer learning, Semi-supervised learning, Active learning; Reinforcement learning
  • Data-driven learning and control and goal-oriented learning, prediction, and control
  • Data-driven evolutionary neural systems; learning in neural control; Neuro-dynamics and complex systems
  • Computational intelligence-based learning
  • Combinatorial and numerical optimization approaches
  • Data-driven Type-2 fuzzy logic, fuzzy and rough data analysis
  • Data-driven lattice theory and multi-valued logics and approximate reasoning Fuzzy information processing
  • Data-driven Fuzzy control and intelligent system modeling and identification
  • Data-driven Fuzzy decision making and decision support systems and hybrid fuzzy systems (fuzzy-neuro-evolutionary)

  Learning-based System: Coupled Learning, Deep Learning
  • Complexity analysis of distribution algorithms
  • Non-iidness learning; Coupled learning and coupled relationship discovery
  • Theory and algorithms of data reduction techniques for Big Data including Online/incremental learning algorithms
  • Big Data mining, separation and integration techniques; Data Structure and Data Relationship techniques
  • Deep learning and its applications
  • Scalable domain discovery and analysis
  • Anomaly detection in social networks

  Applications
  • Novel applications of scalable learning in Neural hardware and applications in Image Processing, Healthcare, Financial, Cyber-security, Mobile computing, mobile networks, Smart cities, Biological data analysis, financial data analysis, industrial applications
  • Emerging application domains (e.g. smart grid, intelligent transportation systems, communication systems, robotics, etc)