Difference between revisions of "Track: DMM"

(Created page with "<html> <!-- <div class="langx is-pulled-right"><a class="button is-small" href="/index.php?title=Konferansın_Yeri">Turkish</a></div> --> <section class="section tot">...")
(No difference)

Revision as of 19:43, 9 June 2018

Track

Data Mining and Machine/Deep Learning


Track Chair

Dr. H. Dağ
Kadir Has University

Call for Papers

Data science expresses that previous data processing applications are not sufficient to process larger and more complex data sets. The relatively recent concepts of data mining, machine learning, and deep learning offer a new set of techniques and methods. Today, researchers and companies are dealing with and experimenting with various methods of deriving value, such as machine learning, data mining, artificial intelligence, and deep learning. Data Mining and Machine / Deep Learning track aims to contribute to fields that are related to analytics of data that based on different data types. New approaches, applications, models or methods related to the topic of this track are encouraged to apply to the track.

Dr. Hasan Dağ, Kadir Has University

hasan.dag@khas.edu.tr


Biography of the Chair

Dr. Dağ obtained his bachelor degree in electrical engineering from Istanbul Technical University, Istanbul, Turkey and obtained both his master and PhD degrees both in University of Wisconsin-Madison in electrical and Computer Engineering. His area of interest in general is computational science, data science and smart grid. His recent research areas are Data Science, Big Data, Cyber Security, and their application to Smart Grid. He holds the directorate position of research resources, while at the same time holding the position of the head of Management Information System at Kadir Has University, Istanbul, Turkey. He has also been appointed the directorate position of Research Center for Cyber Security and Critical Infrastructures.

Key Topics

We welcome papers related to the following topics (but not limited to):

  • Demand forecasting
  • Process optimization
  • Predictive maintenance or condition monitoring
  • Recommendation engines
  • Market segmentation and targeting
  • Disease identification and risk stratification
  • Dynamic pricing
  • Social media-consumer feedback and interaction analysis
  • Traffic patterns and congestion management
  • Power usage analytics
  • Energy demand and supply optimization
  • Customer behavior prediction
  • Sentiment analysis
  • Convolutional neural networks
  • Recurrent neural networks
  • Recursive neural networks