Neural decoding on imbalanced calcium imaging data with a network of support vector machines

Abstract

We present a novel neural decoding system for calcium imaging data. Miniature calcium imaging is of great utility for examining population neural activity of animals. Our neural decoding system is developed using a carefully designed support vector machine subsystem together with dataflow-based techniques for system design, which capture the high-level structure of the application and enable powerful system-level analysis and optimization. Also, we introduce a framework for handling imbalanced data. This addresses a problem of imbalanced datasets, which arises commonly in neural decoding applications, as well as in a wide variety of other applications in biomedical engineering and advanced robotics. We developed an ensemble learning-based method to tackle this problem. The proposed framework systemically incorporates two heterogeneous model characteristics into a combined model. Through extensive experiments, we evaluate the proposed system using calcium imaging datasets in which neural activities of D1 medium spiny neurons in the dorsal striatum were recorded. The results show that the $F_1$ score of the proposed system is significantly better than those of previously developed neural decoding systems for calcium imaging.

GRAPHICAL ABSTRACT

Keywords:

• Neural decoding
• Dataflow
• Imbalanced data
• Support vector machine

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Funding

This work was supported in part by the NIH NINDS (R01NS110421) and the BRAIN Initiative.

Notes on contributors

Kyunghun Lee

Kyunghun Lee has researched machine learning, software/hardware optimization, and automatic detection and classification system development. Dr Lee has a Ph.D. degree in Electrical and Computer Engineering from the University of Maryland, College Park. After his Ph. D. study, Dr Lee worked as a postdoctoral fellow in the Diagnostic Radiology and Nuclear Medicine Department at the University of Maryland School of Medicine and focused on leveraging machine learning and computational modeling to understand the relationship between brain and behavior, leading to novel therapeutic concepts for brain disorders and brain-inspired A.I. Now, he is a scientist (Computational Analyst) at the National Institute of Mental Health (NIMH) and helping NIMH researchers in every phase of the automated software workflow to use neuroscience to identify treatment targets, and Dr Lee is working on software/algorithm development based on real-time information from wearable devices.

Xiaomin Wu

Xiaomin Wu joined the Department of Electrical and Computer Engineering at the University of Maryland, College Park (UMD) as a Ph.D. Student in 2018. He received the bachelor's degree in Biomedical Engineering with minor in Electrical Engineering from State University of New York at Stony Brook. His research interests include machine learning and deep learning, software/algorithm development.

Yaesop Lee

Yaesop Lee received the bachelor's degree in Electrical Engineering from Sogang University, South Korea, and master's degree in Telecommunications from the University of Maryland, College Park. She joined the Department of Electrical and Computer Engineering at the University of Maryland, College Park as a Ph.D. student in 2018. Her research interests include Embedded Machine Learning.

Da-Ting Lin

Da-Ting Lin is a Senior Investigator and the Chief of Neural Engineering Section at the Intramural Research Program, National Institute on Drug Abuse, National Institutes of Health. Dr Lin received his B.S. degree in Biology from University of Science and Technology of China and his Ph.D. degree in Cell Biology from University of Texas Health Science Center at San Antonio. Dr Lin's current research program focuses on developing and applying in vivo optical imaging methods, as well as computational methods for data analysis, to study neuronal circuit dysfunction leading to the development of long-term drug addiction and relapse.

Shuvra S. Bhattacharyya

Shuvra S. Bhattacharyya is a Professor in the Department of Electrical and Computer Engineering at the University of Maryland, College Park. He holds a joint appointment in the University of Maryland Institute for Advanced Computer Studies (UMIACS). He also holds a part-time position as International Research Chair, joint with INSA/IETR, and INRIA in Rennes, France. His research interests include signal processing, embedded systems, electronic design automation, machine learning, wireless communication, and wireless sensor networks. He received the Ph.D. degree from the University of California at Berkeley. He has held industrial positions as a Researcher at the Hitachi America Semiconductor Research Laboratory (San Jose, California), and Compiler Developer at Kuck & Associates (Champaign, Illinois). He has held a visiting summer research position at AFRL in Rome, New York. From 2015 through 2018, he was a part-time visiting professor in the Department of Pervasive Computing at the Tampere University of Technology, Finland, as part of the Finland Distinguished Professor Programme (FiDiPro). He is a Fellow of the IEEE.

Rong Chen

Rong Chen is an Associate Professor and Associate Vice Chair of AI in the Department of Diagnostic Radiology and Nuclear Medicine at the University of Maryland School of Medicine. He has been conducting interdisciplinary research integrating neuroscience and computer science. Dr Chen has degrees in Biomedical Engineering (BS), Electrical Engineering (MS), Electrical and Computer Engineering (Ph.D.), and Translational Medicine (MTR). Dr Chen's research focuses on leveraging machine learning, theory, and computational methods to understand the relationship between brain and behavior across scales, leading to next-generation AI, a deeper understanding of mechanisms of cognition, emotion, and decision making, and novel therapeutic concepts for brain disease such as Alzheimer's disease, Parkinson's disease, substance use disorder, autism, sickle cell disease, and HIV.