BDTL Workshop 2017: 2nd International Workshop on Big Data Transfer Learning (BDTL) in Conjunction with IEEE BigData Conference 2017 The Westin Copley Place, Boston Boston, MA, United States, December 11, 2017 |
Conference website | http://www.cis.umassd.edu/~mshao/BDTL2017/index.html |
Submission deadline | October 10, 2017 |
Welcome to the 2nd IEEE BDTL!
Automatic Knowledge Mining and Transfer for Digital Healthcare
Although widely applied on lots of scientific research, conventional statistical machine learning revolves on a simplified assumption that the training data, from which the algorithms learn, are drawn i.i.d. from the same distribution as the test data, to which the learned models are applied. This assumption, being broken down by numerous real-world applications and practice, especially with the emergence of large-scale healthcare data (e.g., electronic medical record, medical sensors, MRI/CT/X-Ray images) from both private Intranet and public Internet/databases1, has fundamentally restricted the development of practical learning algorithms. For example, intelligent recognition systems are trained to recognize malignant tumors or predict certain disease; however, when deployed in the new environment, these algorithms may confront tumors in different shapes, textures with a different background, or patient with different demographics from different regions. Although both benign and malignant tumors and the disease being predicted have been registered in the system already, it may still fail due to enormous variations between training data and test data in terms of appearance or feature space.
With AI and machine learning algorithms being increasingly popular towards knowledge mining for health informatics, there is an urgent need to ''smooth'' the transition and deployment work from intelligent system trained in manufacturer’s lab to that operated in hospitals. On the other hand, weakly labeled or unlabeled data in relevant fields may contribute generic features and representations for healthcare data in a variety of formats, e.g., zero-shot learning, self-taught learning, which open up a new way for knowledge transfer in health informatics.
Submission Guidelines
- Short papers: 6 pages
- Long papers: 10 pages
- Latex template: latex
- Word template: word
- Paper click here to submit your paper online.
List of Topics
-
The BDTL is a serial workshop ever since 2016. The previous workshop in conjunction with IEEE BigData 2016 focused on the topic of Big Data Transfer Learning and Text Mining. This year, the one-day workshop in conjunction with IEEE BigData 2017 will provide a focused international forum to bring together researchers and research groups to review the status of transfer learning and knowledge mining, to exploit innovative knowledge transfer methodology given enormous weakly labeled/multi-source/multi-view/multimodal healthcare data for disease recognition/prediction, intelligent auxiliary diagnosis and emerging applications, and to explore future directions particularly in fields of increasing popularity such as deep learning, smart sensors and networks, wireless healthcare. The workshop will consist of one to two invited talks together with peer-reviewed regular papers (oral and poster). Original high-quality papers are solicited on a wide range of topics including:
1. New perspectives, concepts, or theories on big data transfer learning and knowledge mining
2. Big data transfer learning that works on multimodality, multi-source, latent domains, or multi-view healthcare data
3. Development of analytics tools for emerging and profound digital healthcare problems
4. Comparisons/survey of state-of-the-art analytics tools in health informatics
5. Deep learning, representation learning and convolutional neural networks for big data analytics in digital healthcare
6. Frontier label-free learning methodology for digital healthcare and health informatics, e.g., one-shot learning, self-taught learning, generative adversarial networks
7. Wireless healthcare, smart sensor networks, wearable devices in big data analytics and digital healthcare
8. New datasets, benchmarks, and open-source software for big data analytics in digital healthcare
Committees
Program Committee
- TBD
Contact
Ming Shao, mshao@umassd.edu