Closed-Loop Neural Interfaces with Embedded Machine Learning

Zhu, Bingzhao; Shin, Uisub; Shoaran, Mahsa

doi:10.1109/icecs49266.2020.9294844

Cited by 11 publications

(8 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, a major question regarding Paradigm C is whether an edge DL model can achieve desired inference performance. Although machine learning-enabled processors for neural implants have been reported [14,15], DL models have only rarely been implemented [11,16,17]. Therefore, the objective of the present work was to evaluate the inference performance limitations and resource constraints of edge DL designs through a case study.…”

Section: Introductionmentioning

confidence: 99%

Edge deep learning for neural implants: a case study of seizure detection and prediction

Liu

Richardson

2021

J. Neural Eng.

View full text Add to dashboard Cite

Objective. Implanted devices providing real-time neural activity classification and control are increasingly used to treat neurological disorders, such as epilepsy and Parkinson’s disease. Classification performance is critical to identifying brain states appropriate for the therapeutic action (e.g. neural stimulation). However, advanced algorithms that have shown promise in offline studies, in particular deep learning (DL) methods, have not been deployed on resource-restrained neural implants. Here, we designed and optimized three DL models or edge deployment and evaluated their inference performance in a case study of seizure detection. Approach. A deep neural network (DNN), a convolutional neural network (CNN), and a long short-term memory (LSTM) network were designed and trained with TensorFlow to classify ictal, preictal, and interictal phases from the CHB-MIT scalp EEG database. A sliding window based weighted majority voting algorithm was developed to detect seizure events based on each DL model’s classification results. After iterative model compression and coefficient quantization, the algorithms were deployed on a general-purpose, off-the-shelf microcontroller for real-time testing. Inference sensitivity, false positive rate (FPR), execution time, memory size, and power consumption were quantified. Main results. For seizure event detection, the sensitivity and FPR for the DNN, CNN, and LSTM models were 87.36%/0.169 h−1, 96.70%/0.102 h−1, and 97.61%/0.071 h−1, respectively. Predicting seizures for early warnings was also feasible. The LSTM model achieved the best overall performance at the expense of the highest power. The DNN model achieved the shortest execution time. The CNN model showed advantages in balanced performance and power with minimum memory requirement. The implemented model compression and quantization achieved a significant saving of power and memory with an accuracy degradation of less than 0.5%. Significance. Inference with embedded DL models achieved performance comparable to many prior implementations that had no time or computational resource limitations. Generic microcontrollers can provide the required memory and computational resources, while model designs can be migrated to application-specific integrated circuits for further optimization and power saving. The results suggest that edge DL inference is a feasible option for future neural implants to improve classification performance and therapeutic outcomes.

show abstract

Section: Introductionmentioning

confidence: 99%

Edge deep learning for neural implants: a case study of seizure detection and prediction

Liu

Richardson

2021

J. Neural Eng.

View full text Add to dashboard Cite

show abstract

“…This fully implantable wireless BCI is capable of providing LFP data, multiunit activities as well as cortical and white matter stimulation on different specified electrodes with simultaneous recording of the real-time responses. Some of the main features of the presented device in comparison to other recently published BCIs are noted in Table 1 (Rouse et al, 2011;Bagheri et al, 2013;Yin et al, 2014;Musk, 2019;Zhou et al, 2019;NeuroPace, 2020;Zhu et al, 2020). Rather than the possibility of wireless inductive charging, other specificities such as high sample rate, ADC resolution, and width bandwidth range can be mentioned as improvements in this study.…”

Section: Discussionmentioning

confidence: 99%

Brain-Computer Interfaces for Perception, Learning, and Motor Control

2021

Frontiers Research Topics

View full text Add to dashboard Cite

About FrontiersFrontiers is more than just an open-access publisher of scholarly articles: it is a pioneering approach to the world of academia, radically improving the way scholarly research is managed. The grand vision of Frontiers is a world where all people have an equal opportunity to seek, share and generate knowledge. Frontiers provides immediate and permanent online open access to all its publications, but this alone is not enough to realize our grand goals. Frontiers Journal SeriesThe Frontiers Journal Series is a multi-tier and interdisciplinary set of open-access, online journals, promising a paradigm shift from the current review, selection and dissemination processes in academic publishing. All Frontiers journals are driven by researchers for researchers; therefore, they constitute a service to the scholarly community. At the same time, the Frontiers Journal Series operates on a revolutionary invention, the tiered publishing system, initially addressing specific communities of scholars, and gradually climbing up to broader public understanding, thus serving the interests of the lay society, too. Dedication to QualityEach Frontiers article is a landmark of the highest quality, thanks to genuinely collaborative interactions between authors and review editors, who include some of the world's best academicians. Research must be certified by peers before entering a stream of knowledge that may eventually reach the public -and shape society; therefore, Frontiers only applies the most rigorous and unbiased reviews. Frontiers revolutionizes research publishing by freely delivering the most outstanding research, evaluated with no bias from both the academic and social point of view. By applying the most advanced information technologies, Frontiers is catapulting scholarly publishing into a new generation.

show abstract

“…Second, we will not address dynamical MML systems here. By dynamica MML systems, we refer to both continuously learning MML systems as well as ML-based closed-loop control of physiological systems (without any human decision-making in the loop), such as automatic insulin delivery systems [34], [35] and closed-loop neural interfaces [36]. Third, we will not address the social implications of developing and deploying an MML system, the question of whether such a system should be built at all, questions of data governance, nor the implementation of inclusive and participatory development processes.…”

Section: B Scope and Purpose Of This Documentmentioning

confidence: 99%

Responsible and Regulatory Conform Machine Learning for Medicine: A Survey of Challenges and Solutions

Petersen

Potdevin

Mohammadi³

et al. 2022

IEEE Access

View full text Add to dashboard Cite

project, see www.ki-sigs.de, which is funded by the German Federal Ministry for Economic Affairs and Climate Action (BMWK) and involves several universities, research institutions and private companies in northern Germany. Researchers YP, SB and LP are employed through funding from the KI-SIGS project. Neither the funding agency nor the involved private companies have had any influence on the planning and design of this survey, the writing of the manuscript, or the publication process. This research was conducted while EP was at Universität zu Lübeck.

show abstract

Closed-Loop Neural Interfaces with Embedded Machine Learning

Cited by 11 publications

References 22 publications

Edge deep learning for neural implants: a case study of seizure detection and prediction

Edge deep learning for neural implants: a case study of seizure detection and prediction

Brain-Computer Interfaces for Perception, Learning, and Motor Control

Responsible and Regulatory Conform Machine Learning for Medicine: A Survey of Challenges and Solutions

Contact Info

Product

Resources

About