Title: A brief survey of machine learning methods and their sensor and IoT applications.
Authors: Uday Shankar Shanthamallu, Andreas Spanias, Cihan Tepedelenlioglu, Mike Stanley.
About the paper: The paper provides a brief survey of the basic concepts and algorithms used for Machine Learning and its applications in supervised and unsupervised paradigms.
Published in: 8th IEE International Conference on Information, Intelligence, Systems & Applications (IISA), Larnaca, 2017
Citation: U. S. Shanthamallu, A. Spanias, C. Tepedelenlioglu and M. Stanley, “A brief survey of machine learning methods and their sensor and IoT applications,” 2017 8th International Conference on Information, Intelligence, Systems & Applications (IISA), Larnaca, 2017, pp. 1-8.
Title: Positive and Unlabeled Learning Algorithms and Applications
Authors: Kristen Jaskie and Andreas Spanias
About the paper: Survey paper of the positive and unlabeled learning problem, a type of semi-supervised learning that has extensive practical applications in medicine, signal processing, and many other areas.
Published in: IEEE IISA 2019 (International Conference on Information, Intelligence, Systems and Applications)
Citation: K. Jaskie and A. Spanias, “Positive And Unlabeled Learning Algorithms And Applications: A Survey,” 2019 10th International Conference on Information, Intelligence, Systems and Applications (IISA), Patras, Greece, July 2019.
Title: GrAMME: Semisupervised Learning Using Multilayered Graph Attention Models
Authors: Uday Shankar Shanthamallu, Jayaraman J. Thiagarajan, Huan Song, Andreas Spanias
About the paper: We proposed novel fusion techniques to learn effective graph embeddings for multi-layer graphs and we evaluate the proposed approaches and demonstrate significant performance improvements in comparison with the state-of-the-art network embedding strategies.
Published in: One of the top IEEE neural networks journals, transactions on neural networks and learning systems
Citation: U. S. Shanthamallu, J. J. Thiagarajan, H. Song, and A. Spanias, “GrAMME: Semisupervised Learning Using Multilayered Graph Attention Models,” in IEEE Transactions on Neural Networks and Learning Systems.
Title: Modeling Human Brain Connectomes Using Structured Neural Networks
Authors: Uday Shankar Shanthamallu, Qunwei Li, Jayaraman J. Thiagarajan, Rushil Anirudh, Alan Kaplan, and Timo Bremer.
About the paper: In this paper, we employ relational graph neural networks to model a human brain connectome, which is a complete functional and structural mapping of human brain. We train the machine learning model to predict meta-information such as Gender, Age, Cortical Volumes and Areas of brain regions.
Published in: 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, Canada.
Citation: U. S. Shanthamallu., et al. Modeling Human Brain Connectomes using Structured Neural Networks, Graph Representation Learning workshop, 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, Canada.
Title: Solar Array Fault Detection using Neural Networks.
Authors: Sunil Rao, Andreas Spanias, and Cihan Tepedelenlioglu
About the paper: A custom neural network for detection and classification of commonly occurring faults in utility scale PV arrays.
Published in: IEEE International Conference on Industrial Cyber-Physical Systems, Taiwan 2019.
Citation: Sunil Rao, Andreas Spanias, and Cihan Tepedelenlioglu. “Solar array fault detection using neural networks.” 2019 IEEE International Conference on Industrial Cyber Physical Systems (ICPS). IEEE, 2019.
Title: A Modified Logistic Regression for Positive and Unlabeled Learning
Authors: Kristen Jaskie, Charles Elkan, and Andreas Spanias
About the paper: This paper describes a novel algorithm to effectively and efficiently solve the positive and unlabeled learning problem.
Published in: IEEE Asilomar Conference on Signals, Systems, and Computers 2019
Citation: K. Jaskie, C. Elkan, and A. Spanias, “A Modified Logistic Regression for Positive and Unlabeled Learning,” in IEEE Asilomar, Pacific Grove, California, Nov. 2019.
Title: Graph Filtering with Multiple Shift Matrices
Authors: Jie Fan, Cihan Tepedelenlioglu, Andreas Spanias
Citation: J. Fan, C. Tepedelenlioglu and A. Spanias, “Graph Filtering with Multiple Shift Matrices,” ICASSP 2019 – 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, United Kingdom, 2019, pp. 3557-3561.
Fan, Jie & Tepedelenlioglu, Cihan & Spanias, Andreas. (2019). Graph Filtering with Multiple Shift Matrices. 3557-3561. 10.1109/ICASSP.2019.8682807.
Title: Designing an effective metric learning pipeline for speaker diarization
Authors: Vivek Sivaraman Narayanaswamy, Jayaraman J. Thiagarajan, Huan Song, Andreas Spanias
Citation: Narayanaswamy, V. S., Thiagarajan, J. J., Song, H., Spanias, A., “Designing an Effective Metric Learning Pipeline for Speaker Diarization”, In 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) , Brighton, UK, pp. 5806-5810.
Title: Audio Source Separation via Multi-Scale Learning with Dilated Dense U-Nets
Authors: Vivek Sivaraman Narayanaswamy, Sameeksha Katoch, Jayaraman J. Thiagarajan, Huan Song, Andreas Spanias
Citation: Narayanaswamy, V. S., Katoch, S., Thiagarajan, J. J., Song, H., Spanias, A, “Audio Source Separation via Multi-Scale Learning with Dilated Dense U-Nets”, arXiv preprint arXiv:1904.04161.
Title: Designing Deep Inverse Models for History Matching in Reservoir Simulations
Authors: Vivek Sivaraman Narayanaswamy, Jayaraman J. Thiagarajan, Rushil Anirudh, Fahim Forouzanfar, Peer-Timo Bremer, Xiao-Hui Wu
Citation: Narayanaswamy, V.S., Thiagarajan, J.J., Anirudh, R., Forouzanfar, F., Bremer, P.T. and Wu, X.H., “Designing Deep Inverse Models for History Matching in Reservoir Simulations”, Machine Learning for Physical Sciences workshop, 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, Canada.
Title: Connection Topology Optimization in Photovoltaic Array Systems using Neural Networks
Authors: Vivek Sivaraman Narayanaswamy, Raja Ayyanar, Andreas Spanias, Cihan Tepedelenlioglu, Devarajan Srinivasan
Citation: Narayanaswamy, V. S., Ayyanar, R., Spanias, A., Tepedelenlioglu, C., Srinivasan, D. “Connection Topology Optimization in Photovoltaic Arrays using Neural Networks” In IEEE International Conference on Industrial Cyber Physical Systems (ICPS), Taipei, May 2019 ,pp. 167-172
Title: Temporal Transformer Networks: Joint Learning of Invariant and Discriminative Time Warping
Authors: Suhas Lohit, Qiao Wang, Pavan K. Turaga
Citation: Lohit, Suhas, Qiao Wang and Pavan K. Turaga. “Temporal Transformer Networks: Joint Learning of Invariant and Discriminative Time Warping.” 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019): 12418-12427.
Title: Non-Parametric Priors For Generative Adversarial Networks
Authors: Rajhans Singh, Pavan K. Turaga, Suren Jayasuriya, Ravi Garg, Martin W. Braun
Citation: Singh, Rajhans, Pavan Turaga, Suren Jayasuriya, Ravi Garg, and Martin W. Braun. “Non-Parametric Priors For Generative Adversarial Networks.” arXiv preprint arXiv:1905.07061 (2019).
Title: Temporal Alignment Improves Feature Quality
Authors:
Citation: H. Choi, Q. Wang, M. Toledo, P. Turaga, M. Buman and A. Srivastava, “Temporal Alignment Improves Feature Quality: An Experiment on Activity Recognition with Accelerometer Data,” 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Salt Lake City, UT, 2018, pp. 462-4628.
Title: Designing an effective metric learning pipeline for speaker diarization
Link: https://arxiv.org/abs/1811.00183
Title: Audio Source Separation via Multi-Scale Learning with Dilated Dense U-Nets
Link: https://arxiv.org/abs/1904.04161
Title: Connection Topology Optimization in Photovoltaic Array Systems using Neural Networks
Link: https://ieeexplore.ieee.org/document/8780242
Title: Invenio: Discovering Hidden Relationships Between Tasks/Domains Using Structured Meta Learning
Link: https://arxiv.org/abs/1911.10600
Title: V. Berisha, A. Wisler, A. Hero, A. Spanias, “Data-driven estimation of density functionals using a polynomial basis ” IEEE Transactions on Signal Processing, pp. 558-572, Vol. 66, January 2018.
Title: V. Berisha, A. Wisler, A. Hero, A. Spanias, “Empirically Estimable Classification Bounds Based on a Nonparametric Divergence Measure,” IEEE Transactions on Signal Processing, vol. 64, no. 3, pp.580-591, Feb. 2016.
Title: H. Braun, S. T. Buddha, V. Krishnan, C. Tepedelenlioglu, A. Spanias, M. Banavar, and D. Srinivansan, “Topology reconfiguration for optimization of photovoltaic array output,” Elsevier Sustainable Energy, Grids and Networks (SEGAN), pp. 58-69, Vol. 6, June 2016.
Title: M. Shah, C. Chakrabarti and A. Spanias, “Within and cross-corpus speech emotion recognition using latent topic model-based features”, EURASIP Journal on Audio, Speech, and Music Processing, 2015:4, January 2015.
Title: M. Shah, M. Tu, V. Berisha, C. Chakrabarti, A. Spanias, “Articulation Constrained Learning with Application to Speech Emotion Recognition,”Computer Speech and Language, Elsevier, 2019.
Title: H. Song, J. Thiagarajan, P. Sattigeri, A. Spanias, “Optimizing Kernel Machines using Deep Learning” IEEE Transactions on Neural Networks and Learning Systems, NLS-2017-P-8053.R1, pp. 5528–5540, Feb. 2018.
Title: Spanias, Andreas.“A brief survey of time-and frequency-domain adaptive filters.”In 2016 IEEE 7th International Conference on Information, Intelligence, Systems & Applications (IEEE IISA 2016), pp. 1-7, July 2016.
About the paper:The paper describes adaptive and learning systems and more specifically time and frequency domain adaptive filters.