 |
Suchita Bhinge Ph.D., Electrical Engineering University of Maryland Baltimore County ITE 370, 1000 Hilltop Circle Baltimore, Maryland 21250 email: suchita1@umbc.edu LinkedIn: https://www.linkedin.com/in/suchitabhinge/ |
Reseach Interests: Machine learning and matrix decomposition techniques such as ICA, IVA, constrained ICA/ IVA, tensor decomposition, dictionary learning with applications to video processing/surveillance: object detection, and biomedical data analysis: spatio-temporal dynamic functional network connectivity analysis and data fusion of multi-task, multi-modal data.
Journal Publications:
- S. Bhinge, R. Mowakeaa, V. D. Calhoun, and T. Adali, "Extraction of time-varying spatio-temporal networks using parameter-tuned constrained IVA," IEEE Transaction on Medical Imaging, vol. 38, issue 7, pp. 1715-1725, 2018.
- Q. Long, S. Bhinge, Y. Levin-Schwartz, Z. Boukouvalas, V. D. Calhoun, and T. Adali, "The role of diversity in data-driven analysis of multisubject fMRI data: Comparison of approaches based on independence and sparsity using global performance metrics," Human Brain Mapping, vol. 40, issue 2, pp. 489-504, 2018.
- X. Song, S. Bhinge, R. Quiton, and T. Adali, "An ICA based approach for steady-state and transient analysis of task fMRI data: Application to study of thermal pain response," Journal of Neuroscience Methods, vol. 326, pp. 108356, 2019.
- M. A. B. S. Akhonda, Q. Long, S. Bhinge, V. D. Calhoun, and T. Adali, "Disjoint Subspaces for Common and Distinct Component Analysis: Application to Task FMRI Data ," in Annual Conference on Information Sciences and Systems (CISS), Baltimore, MD, 2019, pp. 1-6.
- S. Bhinge, V. D. Calhoun, and T. Adali, "IVA-Based Spatio-Temporal Dynamic Connectivity Analysis in Large-Scale fMRI Data," in International Conference on Acoustics, Speech and Signal Processing (ICASSP), Calgary, AB, 2018, pp. 965-969.
- M. A. B. S. Akhonda, Y. Levin-Schwartz, S. Bhinge, V. D. Calhoun and T. Adali, "Consecutive Independence and Correlation Transform for Multimodal Fusion: Application to EEG and fMRI Data," in International Conference on Acoustics, Speech and Signal Processing (ICASSP), Calgary, AB, 2018, pp. 2311-2315.
- X. Song, S. Bhinge, R. Quiton and T. Adali, "A two-level ICA approach reveals important differences in the female brain response to thermal pain," in 15th International Symposium on Biomedical Imaging (ISBI), Washington, DC, 2018, pp. 1377-1380.
- S. Bhinge, Q. Long, Y. Levin-Schwartz, Z. Boukouvalas, V. D. Calhoun and T. Adali, "Non-orthogonal constrained independent vector analysis: Application to data fusion," in International Conference on Acoustics, Speech and Signal Processing (ICASSP), New Orleans, LA, 2017, pp. 2666-2670.
- S. Bhinge, Y. Levin-Schwartz and T. Adali, "Data-driven fusion of multi-camera video sequences: Application to abandoned object detection," in International Conference on Acoustics, Speech and Signal Processing (ICASSP), New Orleans, LA, 2017, pp. 1697-1701.
- D. Emge, Z. Boukouvalas, Y. Levin-Schwartz, S. Bhinge, Qunfang Long and T. Adali, "Power spectra constrained IVA for enhanced detection of SSVEP content," in 51st Annual Conference on Information Sciences and Systems (CISS), Baltimore, MD, 2017, pp. 1-5.
- S. Bhinge, Y. Levin-Schwartz and T. Adali, "Estimation of common subspace order across multiple datasets: Application to multi-subject fMRI data," in 51st Annual Conference on Information Sciences and Systems (CISS), Baltimore, MD, 2017, pp. 1-5.
- Q. Long, S. Bhinge, Y. Levin-Schwartz, V. D. Calhoun and T. Adali, "A graph theoretical approach for performance comparison of ICA for fMRI analysis," in 51st Annual Conference on Information Sciences and Systems (CISS), Baltimore, MD, 2017, pp. 1-6.
- S. Bhinge, Z. Boukouvalas, Y. Levin-Schwartz and T. Adali, "IVA for abandoned object detection: Exploiting dependence across color channels," in International Conference on Acoustics, Speech and Signal Processing (ICASSP), Shanghai, 2016, pp. 2494-2498.
- S. Bhinge, Y. Levin-Schwartz, G. Fu, B. Pesquet-Popescu and T. Adali, "A data-driven solution for abandoned object detection: Advantages of multiple types of diversity," in Global Conference on Signal and Information Processing (GlobalSIP), Orlando, FL, 2015, pp. 1347-1351.
