Workshop Sessions

Intelligent sensor technology is widely used in healthcare. One goal is to assist patients with chronical diseases, e.g. by monitoring activity, recognizing emergencies and raising alerts. Before any use in healthcare, sensor technology is first tested in medical research, where the goals are to contribute to better diagnostics, to assess the effectiveness of some treatment or to design prevention measures. In this talk, I discuss examples of sensor mining for diagnostics and prevention.

The first example is on analyzing tumor enhancement kinetics in Dynamic Contrast-Enhanced Magnetic Resonance Images. Here, the goal of sensor mining is to distinguish between benign and malignant breast tumors. The relative enhancement curves differ, depending on whether a voxel belongs to a malignant region or not. However, the curve of any single voxel is not adequate to decide on malignancy. Signals from proximal voxels are evidently correlated, and this fact can (and should) be exploited to identify regions that exhibit similar enhancement curves.

The second example is on understanding how patients with diabetic foot syndrome apply plantar pressure. Medical research has shown that the likelihood of foot amputation among patients with diabetic foot syndrom is up to 40 times higher than among non-diabetics, that increased foot temperature may indicate the onset of an ulceration, and that plantar pressure modulates temperature. Intelligent wearables thus monitor pressure in different regions of the feet. Here, a goal of sensor mining is to derive pressure profiles, exploiting the correlation among proximal sensors, and to optimize the number and placement of sensors in the wearable.

• Predicting Phone Usage Behaviors with Sensory Data using Hierarchical Generative Model, by Chuankai An and Dan Rockmore

• Learning Multi-faceted Activities from Heterogeneous Data with the Product Space Hierarchical Dirichlet Processes, by Thanh Binh Nguyen, Vu Nguyen, Svetha Venkatesh and Dinh Phungy

• Image Segmentation With Superpixel Based Covariance Descriptor, by Xianbin Gu and Martin Purvis

• Phishing Detection on Twitter Streams using Unsupervised Learning, by Se Yeong Jeong, Yun Sing Koh and Gill Dobbie

• Rigidly Self-Expressive Sparse Subspace Clustering, by Linbo Qiao, Bo-Feng Zhang, Shiqian Ma and Jinshu Su

• A Comparative Evaluation of Action Recognition Methods via Riemannian Manifolds, Fisher Vectors and GMMs: Ideal and Challenging Conditions, by Johanna Carvajal, Arnold Wiliem, Chris McCool, Brian Lovell and Conrad Sanderson

• Joint Recognition and Segmentation of Actions via Probabilistic Integration of Spatio-Temporal Fisher Vectors, by Johanna Carvajal, Chris McCool, Brian Lovell and Conrad Sanderson

Professor Jim Warren, Chair in Health Informatics, Department of Computer Science, University of Auckland

• Normalized Cross-Match: Pattern Discovery Algorithm from Biofeedback Signals
• Event Prediction in Healthcare Analytics: Beyond Prediction Accuracy
• Clinical Decision Support for Stroke using Multi-View Learning based Models for NIHSS Scores

Topic: Use of medical domain knowledge for predictive analytics – Issues and Challenges

Distinguished Panel Members:

• Professor Naren Ramakrishnan, Virginia Tech, USA
• Professor Myra Spiliopoulou, Otto-von-Guericke-University Magdeburg, Germany
• Professor Pedro Pereira Rodrigues, University of Porto, Portugal
• Professor Ernestina Menasalvas, Universidad Politecnica de Madrid, Spain

• The Use of Reference Graphs in the Entity Resolution of Criminal Networks
  David Robinson
• Heterogeneous Information Networks Bi-Clustering with Similarity Regularization*
  Haixin Li, Xianchao Zhang, Wenxin Liang, Linlin Zong, and Xinyue Liu

• A Profile-Based Authorship Attribution Approach to Forensic Identification in Chinese Online Messages
  Jianbin Ma, Bing Xu, and Mengjie Zhang
• Multilevel Syntactic Parsing based on Recursive Restricted Boltzmann Machines and Learning to Rank*
  Jungang Xu, Hong Chen, Shilong Zhou, and Ben He
• Stratified Over-Sampling Bagging Method for Random Forests on Imbalanced Data*
  He Zhao, Xiaojun Chen, Tung Nguyen, Joshua Huang, Graham Williams, and Hui Chen
• Revisiting Attribute Independence Assumption in Probabilistic Unsupervised Anomaly Detection*
  Sunil Aryal, Kai Ming Ting, and Gholamreza Haffari

• Incremental Privacy-Preserving Association Rule Mining Using Negative Border
  Duc H. Tran, Wee Keong Ng, Yiik Diew Wong, and Vinh V. Thai
• Differentially Private Multi-Task Learning
  Sunil Gupta, Santu Rana, and Svetha Venkatesh
• Intelligent Recognition of Spontaneous Expression Using Motion Magnification of Spatio-Temporal Data
  B. M. S. Bahar Talukder, Brinta Chowdhury, Tamanna Howlader, and S. M. Mahbubur Rahman

• k-NN Classification of Malware in HTTPS Traffic Using the Metric Space Approach
  Jakub Lokoč, Jan Kohout, Přemysl Čech, Tomáš Skopal, and Tomáš Pevný
• A Syntactic Approach for Detecting Viral Polymorphic Malware Variants
  Vijay Naidu and Ajit Narayanan
• Small State Acquisition of Offensive Cyberwarfare Capabilities: Towards Building an Analytical Framework*
  Daniel Hughes and Andrew Colarik
• Data-Driven Stealthy Injection Attacks on Smart Grid with Incomplete Measurements*
  Adnan Anwar, Abdun Mahmood, and Mark Pickering
• Information Security in Software Engineering, Analysis of Developers Communications about Security in Social Q&A Website*
  Shahab Bayati and Marzieh Heidary