Arash Mahyari is a research scientist at Florida Institute for Human and Machine Cognition (IHMC), working on machine learning and signal processing. Arash joined IHMC from ABB Robotics R&D Center, San Jose, CA, where he worked on developing the next generation of artificial intelligence for industrial robots. He received his dual degree in electrical engineering (PhD) and Statistics (MSc) from Michigan State University and MSc in electrical engineering from Shiraz University.
Prior to joining IHMC, Arash has worked on several projects in different domains. For his MSc thesis, he developed image fusion algorithms to enhance the spatial quality of multispectral images of the LANDSAT satellite. He later developed a computer vision algorithm to detect the surface defects of the cold rolled steels. The algorithm located the defected areas using texture segmentation methods and extracted several statistical features to be classified using a trained neural network. He has worked on an image processing project and developed an embedded system based on Analog Device DSP processors for telecommunication companies. During his PhD, he used tensor analysis, compressive sensing and dictionary learning to develop algorithms for event detection and tracking of functional connectivity networks (cognitive science). Arash is currently working on different aspects of machine learning, computer vision and decision making process, mostly related to the DARPA AI Next campaign.
- SimON: Accurate and Scalable Simulation of Influence in Online Social Networks, DARPA, 2018-present
- Predictive maintenance for industrial robots, ABB, 2017-2018.
- Dynamic network analysis with applications to functional neural connectivity, NSF, 2012-2017.
- Image denoising using weighted alpha-median filters, 2011-2012 (PI).
- Embedded system for billing SS7-based-telecommunication systems, 2009-2012.
- Steel surface defect detection using computer vision algorithms, 2007-2009.
- Study and improvement of image fusion techniques for better detection in a basic image using complementary images, 2006-2009.
- Arash Mahyari, “Domain Adaptation in Robot Fault Diagnostic Systems,” arxiv 1809.08626. [pdf]
- A. G. Mahyari, S. Aviyente, “Structured dictionary learning for sparse common component and innovation model,” proceedings of 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), New Orleans, LA, 2017.[pdf]
- A. G. Mahyari, S. Aviyente, “Hierarchical Distributed Compressive Sensing for Simultaneous Sparse Approximation and Common Component Extraction,” Digital Signal Processing, vol. 60, pp. 230-241, 2017.[pdf]
- A. G. Mahyari, S. Aviyente, “A Tensor Decomposition based Approach for Detecting Dynamic Network States from EEG,” IEEE Transactions on Biomedical Engineering, vol. 64, no. 1, 2017. [pdf]
- A. G. Mahyari, S. Aviyente, “A Tucker Decomposition Based Approach for Topographic Functional Connectivity State Summarization,” proceedings of 3rd IEEE Global Conference on Signal and Information Processing (GLOBAL SIP), Orlando, FL, Dec 2015. [pdf]
- M. Yazdi, A. G. Mahyari, “SMOR: A Semantic Multi-view Object Representation System in 2D Image Sequences,” The Arabian Journal of Science and Engineering: Transaction B, vol. 39, no. 2, pp. 997-1005, 2014. [pdf]
- A. G. Mahyari, S. Aviyente, “Fourier Transform for Signals on Dynamic Graphs,” Proceedings of Asilomar Conference on Signals, Systems & Computers, California, USA, 2014. [pdf]
- A. G. Mahyari, S. Aviyente, “Identification of Dynamic Functional Brain Network States Through Tensor Decomposition,” Proceedings of 2014 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. 2099-2103, Florence, Italy, 2014. [pdf]
- A. Ozdemir, A. G. Mahyari, S. Aviyente, “Multiple Subject Analysis of Functional Brain Network Communities Through Co-regularized Spectral Clustering,” Proceedings of 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC’14), pp. 5592-5595, Chicago, USA, 2014. [pdf]
- A. G. Mahyari, S. Aviyente, “Multi-Scale Anomaly Detection in Complex Dynamic Networks,” Proceedings of 1st IEEE Global Conference on Signal and Information Processing (GLOBAL SIP), pp. 603-606, Austin, TX, USA, Dec 2013.
- A. G. Mahyari, S. Aviyente, “Two-Dimensional SVD for Event Detection in Dynamic Functional Brain Networks,” Proceedings of 1st IEEE Global Conference on Signal and Information Processing (GLOBAL SIP), pp. 37-40, Austin, TX, USA, Dec 2013.
- G. Mahyari, S. Aviyente, “A Multi-Scale Energy Detector For Anomaly Detection in Dynamic Graphs,” Proceedings of Asilomar Conference on Signals, Systems & Computers, pp. 962-965, California, USA, 2013.
- A. G. Mahyari, M. Yazdi, “Panchromatic and Multispectral images Fusion based on maximization of both Spectral and Spatial Similarities,” IEEE Transaction on Remote Sensing and Geoscience, vol. 49, no. 6, pp. 1976-1985, February 2011.
- G. Mahyari, “Spectral Estimation Using Modified Daniell Method,” International Journal of Electronics, vol. 97, no. 11, pp. 1311-1316, November 2010.
- A. G. Mahyari, M. Yazdi, “Fusion of Panchromatic and Multispectral Images Using Temporal Fourier Transform,” IET Image Processing, vol. 4, no. 4, pp. 255-260, August 2010.
- M. Yazdi, A. G. Mahyari, “A New 2-D Fractal Dimension Estimation Based on Contourlet Transform for Texture Segmentation,” The Arabian Journal of Science and Engineering: Transaction B, vol. 35, no. 1B, pp. 293-317, April 2010.
- G. Mahyari, M. Yazdi, “Landsat ETM+ Image Fusion Based on the Discrete Cosine Transform”, Accepted for Proceedings of 16th IEEE International Conference on Image Processing (ICIP2009), Egypt, 2009. NOT published.
- G. Mahyari, M. Yazdi, “A Novel Image Fusion Method Using Curvelet Transform Based on Linear Dependency Test,” Proceedings of the 1nd International Conference on Digital Image Processing (ICDIP 2009), pp. 351-354, Thailand, 2009.
- Yazdchi, M. Yazdi, A. G. Mahyari, “Steel Surface Defect Detection Using Texture Segmentation Based on Multifractal Dimension,” Proceedings of the 1nd International Conference on Digital Image Processing (ICDIP 2009), pp. 346-350, Thailand, 2009.
- Yazdchi, A. G. Mahyari, A. Nazeri, “Detection and Classification of Surface Defects of Cold Rolling Mill Steel Using Morphology and Neural Network,” Proceedings of International Conference on Computational Intelligence for Modelling, Control and Automation (CIMCA 08), pp. 1071-1076, Austria, 2008.
- Arash Mahyari, Method for Discriminating Robot Operation Change from Robot Mechanical Condition Change, filled to US Patent Office, 2018.
Software and Codes
- Phase-Synchrony [code]