Recent advances in the wireless technology and sensor networks have given both new opportunities and new challenges to data networking and mining. Large amounts of sensory data are being gathered and transmitted for various applications and these need to be analyzed and utilized effectively. On these other hand, the sensory and networking data exchanged between sensing devices can be explored for smart and efficient in-network and application designs. The nature of the sensing environment, however, has a number of constraints that differentiate it from conventional machine learning settings. Sensory data are generated in continuous streams from a dynamic environment, and stored in a distributed manner. Meanwhile, sensing devices are subject to limitation of power, memory, and communication bandwidth. To address these challenges there is a wide range of machine learning techniques that need to be adapted and utilized. Following the successful MLSDA events in Dunedin (2013), Gold Coast (2014), MLSDA joins the PAKDD in 2016 to provide a golden opportunity for researchers working in relevant fields to share their research progress, and establish potential collaboration for the future.

We call for papers of relevant topics as follows:

  • Time series analysis
  • Motif detection
  • Anomaly detection
  • Online data stream mining
  • Concept drift detection and handling
  • Feature extraction and dimension reduction
  • Ensemble learning
  • Compressed sensing
  • Sensory data modeling and prediction
  • Smart environment
  • Self-organization
  • Distributed signal processing
  • Resource management and task scheduling
  • Energy efficiency and cloud offloading
  • Reinforcement learning in WSNs
  • Privacy-preserving data mining
  • Multimodal signal processing
  • Activity detection and behaviour classification
  • Intrusion detection

All submissions will go through a rigorous double-blind peer review process conducted by the program committee. Accepted papers are expected to be published by the Springer LNCS series.