Mark Embrechts

Mark Embrechts

Mark J. Embrechts is Chief Scientist at CardioMag Imaging, Inc. CardioMag developed highly accurate technology for the early detection of ischemia by measuring the magnetic field of the hearth, a technology protected by 13 patents (2 pending). Mark Embrechts is also a professor in the Department of Mechanical, Aerospace, and Nuclear Engineering (MANE) at Rensselaer. Mark is also a Full Professor of Industrial and Systems Engineering (ISE) at Rensselaer Polytechnic Institute, Troy NY. Prof. Embrechts is a frequent guest professor at the Department of Electrical Engineering / Computer Science at the University of Kassel, Deutschland. Prof. Embrechts joined the Nuclear Engineering Department at Rensselaer in 1983 and was previously an AWUDOE fellow, Staff Member and Laboratory Director's Fellow at Los Alamos National Laboratory (1981-1983). He is a pioneer in introducing neural networks, data mining, big data analytics, genetic algorithms, and computational intelligence to the Graduate Engineering Curriculum at Rensselaer and has been teaching courses related to these topics and data-driven engineering since 1988.

Contact Information: 

Phone: (518) 276-4009

Focus Area: 
Data Mining, Big Data, Neural Networks, Genetic Algorithms, Computational Intelligence, Biocomputing, Drug Design, Big Data for Renewable Energy Statistics
Selected Publications: 
  1. Embrechts, M.J., Rossi, F. Schleif, F.M., Lee, J.A., “Advances in Artificial Neural Networks, Machine Learning, and Computational Intelligence,” Neurocomputing, 141, 2014.
  2. Cortez, P. and Embrechts, M.J., “Using sensitivity analysis and visualization techniques to open black box data mining models,” 225, 2013, pp.1-17.
  3. Gatti, C.J. and Embrechts, M.J., “Reinforcement learning with neural networks: Tricks of the trade,” in Advances in Intelligent Signal Processing and Data Mining, pp.275-310, Springer, 2013.

Sample Patents

  1. Sigma tuning of gaussian kernels: detection of ischemia from magnetocardiograms L Han, M Embrechts, B Szymanski, K Sternickel, A Ross, , A Ross US Patent 8,527,435