{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T23:30:36Z","timestamp":1775086236574,"version":"3.50.1"},"reference-count":42,"publisher":"Public Library of Science (PLoS)","issue":"3","license":[{"start":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T00:00:00Z","timestamp":1710201600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","award":["Undergraduate Student Research Award"],"award-info":[{"award-number":["Undergraduate Student Research Award"]}],"id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","award":["RGPIN-2014-05498"],"award-info":[{"award-number":["RGPIN-2014-05498"]}],"id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","award":["RGPIN-2020-06246"],"award-info":[{"award-number":["RGPIN-2020-06246"]}],"id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:p>Neurostimulation and neural recording are crucial to develop neuroprostheses that can restore function to individuals living with disabilities. While neurostimulation has been successfully translated into clinical use for several applications, it remains challenging to robustly collect and interpret neural recordings, especially for chronic applications. Nerve cuff electrodes offer a viable option for recording nerve signals, with long-term implantation success. However, nerve cuff electrodes\u2019 signals have low signal-to-noise ratios, resulting in reduced selectivity between neural pathways. The objective of this study was to determine whether deep learning techniques, specifically networks tailored for time series applications, can increase the recording selectivity achievable using multi-contact nerve cuff electrodes. We compared several neural network architectures, the impact and trade-off of window length on classification performance, and the benefit of data augmentation. Evaluation was carried out using a previously collected dataset of 56-channel nerve cuff recordings from the sciatic nerve of Long-Evans rats, which included afferent signals evoked using three types of mechanical stimuli. Through this study, the best model achieved an accuracy of 0.936 \u00b1 0.084 and an F<jats:sub>1<\/jats:sub>-score of 0.917 \u00b1 0.103, using 50 ms windows of data and an augmented training set. These results demonstrate the effectiveness of applying CNNs designed for time-series data to peripheral nerve recordings, and provide insights into the relationship between window duration and classification performance in this application.<\/jats:p>","DOI":"10.1371\/journal.pone.0299271","type":"journal-article","created":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T17:30:39Z","timestamp":1710264639000},"page":"e0299271","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":3,"title":["Time series classification of multi-channel nerve cuff recordings using deep learning"],"prefix":"10.1371","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9525-8500","authenticated-orcid":true,"given":"Aseem Partap Singh","family":"Gill","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8842-745X","authenticated-orcid":true,"given":"Jose","family":"Zariffa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2024,3,12]]},"reference":[{"issue":"1","key":"pone.0299271.ref001","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41598-021-91954-1","article-title":"Quality of life, body image and self-esteem in patients with unilateral transtibial amputations.","volume":"11","author":"N Sarroca","year":"2021","journal-title":"Sci Rep."},{"key":"pone.0299271.ref002","article-title":"Longitudinal changes in employment, health, participation, and quality-of-life and the relationships with long-term survival after spinal cord injury.","author":"Y Cao","year":"2023","journal-title":"Spinal Cord."},{"issue":"257","key":"pone.0299271.ref003","first-page":"1","article-title":"A neural interface provides long-term stable natural touch perception.","volume":"6","author":"DW Tan","year":"2014","journal-title":"Sci Transl Med"},{"issue":"2","key":"pone.0299271.ref004","first-page":"1","article-title":"Stability and selectivity of a chronic, multi-contact cuff electrode for sensory stimulation in human amputees","volume":"12","author":"DW Tan","year":"2015","journal-title":"Journal Neural Engineering"},{"issue":"September","key":"pone.0299271.ref005","first-page":"1","article-title":"Motor Control and Sensory Feedback Enhance Prosthesis Embodiment and Reduce Phantom Pain After Long-Term Hand Amputation.","volume":"12","author":"DM Page","year":"2018","journal-title":"Front Hum Neurosci"},{"issue":"June","key":"pone.0299271.ref006","doi-asserted-by":"crossref","first-page":"327","DOI":"10.1146\/annurev.bioeng.6.040803.140103","article-title":"Functional electrical stimulation for neuromuscular applications.","volume":"7","author":"PH Peckham","year":"2005","journal-title":"Annu Rev Biomed Eng"},{"issue":"5","key":"pone.0299271.ref007","doi-asserted-by":"crossref","first-page":"934","DOI":"10.1016\/j.apmr.2015.01.013","article-title":"Functional electrical stimulation improves activity after stroke: A systematic review with meta-analysis","volume":"96","author":"OA Howlett","year":"2015","journal-title":"Arch Phys Med Rehabil"},{"issue":"1","key":"pone.0299271.ref008","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12938-020-00773-4","article-title":"Functional electrical stimulation therapy for restoration of motor function after spinal cord injury and stroke: A review","volume":"19","author":"C Marquez-Chin","year":"2020","journal-title":"Biomed Eng Online"},{"issue":"4","key":"pone.0299271.ref009","doi-asserted-by":"crossref","first-page":"539","DOI":"10.1109\/TNSRE.2012.2185065","article-title":"A comparison of closed-loop control algorithms for regulating electrically stimulated knee movements in individuals with spinal cord injury","volume":"20","author":"CL Lynch","year":"2012","journal-title":"IEEE Transactions on Neural Systems and Rehabilitation Engineering"},{"key":"pone.0299271.ref010","doi-asserted-by":"crossref","first-page":"631","DOI":"10.1016\/j.pmr.2014.05.001","article-title":"Functional electrical stimulation and Spinal Cord Injury.","volume":"25","author":"CH Ho","year":"2014","journal-title":"Physical Medicine and Rehabilitation Clinics of North America. W.B. Saunders"},{"key":"pone.0299271.ref011","first-page":"63","volume-title":"International Review of Neurobiology","author":"J del Valle","year":"2013","edition":"1"},{"issue":"June 2019","key":"pone.0299271.ref012","doi-asserted-by":"crossref","first-page":"108523","DOI":"10.1016\/j.jneumeth.2019.108523","article-title":"A review for the peripheral nerve interface designer","volume":"332","author":"CE Larson","year":"2020","journal-title":"J Neurosci Methods"},{"key":"pone.0299271.ref013","article-title":"Tutorial: A guide to techniques for analysing recordings from the peripheral nervous system.","volume":"19","author":"RGL Koh","year":"2022","journal-title":"Journal of Neural Engineering. Institute of Physics"},{"issue":"1","key":"pone.0299271.ref014","article-title":"Selective peripheral nerve recordings from nerve cuff electrodes using convolutional neural networks","volume":"17","author":"RGL Koh","year":"2020","journal-title":"J Neural Eng"},{"issue":"1","key":"pone.0299271.ref015","doi-asserted-by":"crossref","first-page":"11145","DOI":"10.1038\/s41598-019-47450-8","article-title":"Classification of naturally evoked compound action potentials in peripheral nerve spatiotemporal recordings.","volume":"9","author":"RGL Koh","year":"2019","journal-title":"Sci Rep."},{"issue":"4","key":"pone.0299271.ref016","doi-asserted-by":"crossref","first-page":"917","DOI":"10.1007\/s10618-019-00619-1","article-title":"Deep learning for time series classification: a review.","volume":"33","author":"H Ismail Fawaz","year":"2019","journal-title":"Data Min Knowl Discov.1"},{"issue":"3","key":"pone.0299271.ref017","doi-asserted-by":"crossref","first-page":"555","DOI":"10.1016\/S0306-4522(02)00093-3","article-title":"Interactions between cutaneous afferent inputs to a withdrawal reflex in the decerebrated rabbit and their control by descending and segmental systems","volume":"112","author":"RW Clarke","year":"2002","journal-title":"Neuroscience"},{"key":"pone.0299271.ref018","article-title":"Nerve Cuff Recordings of Muscle Afferent Activity from Tibial and Peroneal Nerves in Rabbit During Passive Ankle Motion.","volume":"8","author":"RR Riso","year":"2000","journal-title":"IEEE TRANSACTIONS ON REHABILITATION ENGINEERING"},{"issue":"5","key":"pone.0299271.ref019","doi-asserted-by":"crossref","first-page":"1684","DOI":"10.1152\/jn.1993.69.5.1684","article-title":"Cutaneous sensory receptors in the rat foot","volume":"69","author":"JW Leem","year":"1993","journal-title":"J Neurophysiol"},{"issue":"2","key":"pone.0299271.ref020","first-page":"1105","article-title":"Tripolar nerve cuff recording: Stimulus artifact, EMG, and the recorded nerve signal.","volume":"17","author":"JJ Struijk","year":"1995","journal-title":"Annual International Conference of the IEEE Engineering in Medicine and Biology\u2014Proceedings"},{"issue":"3","key":"pone.0299271.ref021","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1017\/S0317167100020333","article-title":"Principles Underlying New Methods for Chronic Neural Recording.","volume":"2","author":"RB Stein","year":"1975","journal-title":"Canadian Journal of Neurological Sciences \/ Journal Canadien des Sciences Neurologiques."},{"key":"pone.0299271.ref022","first-page":"2645","article-title":"Fibre-selective discrimination of physiological ENG using velocity selective recording: Report on pilot rat experiments.","author":"B Metcalfe","year":"2014","journal-title":"In: 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014. Institute of Electrical and Electronics Engineers Inc"},{"key":"pone.0299271.ref023","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1016\/j.jneumeth.2015.05.003","article-title":"A new method for spike extraction using velocity selective recording demonstrated with physiological ENG in Rat","volume":"251","author":"BW Metcalfe","year":"2015","journal-title":"J Neurosci Methods"},{"issue":"3","key":"pone.0299271.ref024","doi-asserted-by":"crossref","DOI":"10.1088\/1741-2560\/10\/3\/036016","article-title":"Fibre-selective recording from the peripheral nerves of frogs using a multi-electrode cuff","volume":"10","author":"M Schuettler","year":"2013","journal-title":"J Neural Eng"},{"key":"pone.0299271.ref025","doi-asserted-by":"crossref","first-page":"1661","DOI":"10.1162\/089976604774201631","article-title":"Communicated by Maneesh Sahani Unsupervised Spike Detection and Sorting with Wavelets and Superparamagnetic Clustering.","volume":"16","author":"R Quian Quiroga","year":"2004","journal-title":"Neural Comput"},{"key":"pone.0299271.ref026","author":"G Iglesias","year":"2022","journal-title":"Data Augmentation techniques in time series domain: A survey and taxonomy"},{"issue":"November 2021","key":"pone.0299271.ref027","doi-asserted-by":"crossref","first-page":"103496","DOI":"10.1016\/j.bspc.2022.103496","article-title":"An efficient multi-scale CNN model with intrinsic feature integration for motor imagery EEG subject classification in brain-machine interfaces.","volume":"74","author":"AM Roy","year":"2022","journal-title":"Biomed Signal Process Control."},{"issue":"6","key":"pone.0299271.ref028","doi-asserted-by":"crossref","first-page":"1936","DOI":"10.1007\/s10618-020-00710-y","article-title":"InceptionTime: Finding AlexNet for time series classification.","volume":"34","author":"H Ismail Fawaz","year":"2020","journal-title":"Data Min Knowl Discov."},{"key":"pone.0299271.ref029","doi-asserted-by":"crossref","unstructured":"Chowdhury RR, Zhang X, Shang J, Gupta RK, Hong D. TARNet: Task-Aware Reconstruction for Time-Series Transformer. In: Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery; 2022. p. 212\u201320.","DOI":"10.1145\/3534678.3539329"},{"key":"pone.0299271.ref030","author":"A Ramesh","year":"2022","journal-title":"Hierarchical Text-Conditional Image Generation with CLIP Latents"},{"key":"pone.0299271.ref031","author":"OpenA","year":"2023","journal-title":"GPT-4 Technical Report"},{"key":"pone.0299271.ref032","author":"A Goyal","year":"2020","journal-title":"Inductive Biases for Deep Learning of Higher-Level Cognition."},{"key":"pone.0299271.ref033","author":"BK Ruan","year":"2022","journal-title":"Vision Transformers: State of the Art and Research Challenges"},{"key":"pone.0299271.ref034","author":"Y Bai","year":"2021","journal-title":"Are Transformers More Robust Than CNNs?"},{"key":"pone.0299271.ref035","author":"C Szegedy","year":"2015","journal-title":"Going Deeper with Convolutions"},{"key":"pone.0299271.ref036","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v31i1.11231","article-title":"Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning","author":"C Szegedy","year":"2017"},{"key":"pone.0299271.ref037","author":"A Vaswani","year":"2017","journal-title":"Attention Is All You Need"},{"issue":"1","key":"pone.0299271.ref038","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1109\/TNSRE.2007.891391","article-title":"The optimal controller delay for myoelectric prostheses","volume":"15","author":"TR Farrell","year":"2007","journal-title":"IEEE Transactions on Neural Systems and Rehabilitation Engineering"},{"key":"pone.0299271.ref039","doi-asserted-by":"crossref","DOI":"10.5772\/intechopen.100663","article-title":"Resource-Efficient Neural Network Architectures for Classifying Nerve Cuff Recordings on Implantable Devices","author":"YCE Hwang","year":"2023","journal-title":"IEEE Trans Biomed Eng"},{"key":"pone.0299271.ref040","doi-asserted-by":"crossref","unstructured":"Koh RGL, Jabban L, Fukushi M, Adeyinka IC, Zariffa J, Metcalfe B. A comparison of extraneural approaches for selective recording in the peripheral nervous system. In: Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS. Institute of Electrical and Electronics Engineers Inc.; 2022. p. 5080\u20133.","DOI":"10.1109\/EMBC48229.2022.9871727"},{"key":"pone.0299271.ref041","author":"C Szegedy","year":"2014","journal-title":"Going Deeper with Convolutions"},{"key":"pone.0299271.ref042","author":"YE Hwang","year":"2022","journal-title":"Resource-efficient Neural Network Architectures for Classifying Nerve Cuff Recordings on Implantable Devices"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0299271","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T17:31:22Z","timestamp":1710264682000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0299271"}},"subtitle":[],"editor":[{"given":"Noman","family":"Naseer","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2024,3,12]]},"references-count":42,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2024,3,12]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0299271","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,12]]}}}