{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T12:40:04Z","timestamp":1761396004202,"version":"3.41.0"},"reference-count":43,"publisher":"Association for Computing Machinery (ACM)","issue":"2","license":[{"start":{"date-parts":[[2021,4,15]],"date-time":"2021-04-15T00:00:00Z","timestamp":1618444800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Army Research Laboratory and was accomplished under Cooperative","award":["W911NF-10-2-0022"],"award-info":[{"award-number":["W911NF-10-2-0022"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["J. Emerg. Technol. Comput. Syst."],"published-print":{"date-parts":[[2021,4,30]]},"abstract":"<jats:p>\n            This article presents an energy-efficient and flexible multichannel Electroencephalogram (EEG) artifact identification network and its hardware using depthwise and separable convolutional neural networks. EEG signals are recordings of the brain activities. EEG recordings that are not originated from cerebral activities are termed\n            <jats:italic>artifacts<\/jats:italic>\n            . Our proposed model does not need expert knowledge for feature extraction or pre-processing of EEG data and has a very efficient architecture implementable on mobile devices. The proposed network can be reconfigured for any number of EEG channel and artifact classes. Experiments were done with the proposed model with the goal of maximizing the identification accuracy while minimizing the weight parameters and required number of operations. Our proposed network achieves 93.14% classification accuracy using an EEG dataset collected by 64-channel BioSemi ActiveTwo headsets, averaged across 17 patients and 10 artifact classes. Our hardware architecture is fully parameterized with number of input channels, filters, depth, and data bit-width. The number of processing engines (PE) in the proposed hardware can vary between 1 to 16, providing different latency, throughput, power, and energy efficiency measurements. We implement our custom hardware architecture on Xilinx FPGA (Artix-7), which on average consumes 1.4 to 4.7 mJ dynamic energy with different PE configurations. Energy consumption is further reduced by 16.7\u00d7 implementing on application-specified integrated circuit at the post layout level in 65-nm CMOS technology. Our FPGA implementation is 1.7 \u00d7 to 5.15 \u00d7 higher in energy efficiency than some previous works. Moreover, our Application-Specified Integrated Circuit implementation is also 8.47 \u00d7 to 25.79 \u00d7 higher in energy efficiency compared to previous works. We also demonstrated that the proposed network is reconfigurable to detect artifacts from another EEG dataset collected in our lab by a 14-channel Emotiv EPOC+ headset and achieved 93.5% accuracy for eye blink artifact detection.\n          <\/jats:p>","DOI":"10.1145\/3427471","type":"journal-article","created":{"date-parts":[[2021,4,15]],"date-time":"2021-04-15T11:04:42Z","timestamp":1618484682000},"page":"1-21","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":17,"title":["A Flexible Multichannel EEG Artifact Identification Processor using Depthwise-Separable Convolutional Neural Networks"],"prefix":"10.1145","volume":"17","author":[{"given":"Mohit","family":"Khatwani","sequence":"first","affiliation":[{"name":"University of Maryland, Baltimore County, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hasib-Al","family":"Rashid","sequence":"additional","affiliation":[{"name":"University of Maryland, Baltimore County, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hirenkumar","family":"Paneliya","sequence":"additional","affiliation":[{"name":"University of Maryland, Baltimore County, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mark","family":"Horton","sequence":"additional","affiliation":[{"name":"University of Maryland, Baltimore County, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nicholas","family":"Waytowich","sequence":"additional","affiliation":[{"name":"Human Research and Engineering Directorate, US Army Research Lab, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"W. David","family":"Hairston","sequence":"additional","affiliation":[{"name":"Human Research and Engineering Directorate, US Army Research Lab, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tinoosh","family":"Mohsenin","sequence":"additional","affiliation":[{"name":"University of Maryland, Baltimore County, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,4,15]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/NEWCAS.2018.8585542"},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.5555\/1929142.1929234"},{"volume-title":"Proceedings of the 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC\u201915)","author":"Bhardwaj Swati","key":"e_1_2_1_3_1","unstructured":"Swati Bhardwaj , Pranit Jadhav , Bhagyaraja Adapa , Amit Acharyya , and Ganesh R. Naik . 2015. Online and automated reliable system design to remove blink and muscle artefact in EEG . In Proceedings of the 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC\u201915) . IEEE, 6784--6787. Swati Bhardwaj, Pranit Jadhav, Bhagyaraja Adapa, Amit Acharyya, and Ganesh R. Naik. 2015. Online and automated reliable system design to remove blink and muscle artefact in EEG. In Proceedings of the 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC\u201915). IEEE, 6784--6787."},{"key":"e_1_2_1_4_1","volume-title":"Proceedings of the IEEE Biomedical Circuits and Systems Conference (Biocas\u201911)","author":"Chander James","year":"2011","unstructured":"James Chander , Jordan Bisasky , and Tinoosh Mohsenin . 2011 . Real-time multi-channel seizure detection and analysis hardware . In Proceedings of the IEEE Biomedical Circuits and Systems Conference (Biocas\u201911) (Nov. 2011). James Chander, Jordan Bisasky, and Tinoosh Mohsenin. 2011. Real-time multi-channel seizure detection and analysis hardware. In Proceedings of the IEEE Biomedical Circuits and Systems Conference (Biocas\u201911) (Nov. 2011)."},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/BioCAS.2016.7833772"},{"volume-title":"Proceedings of the 2018 2nd International Conference on Intelligent Computing and Control Systems (ICICCS\u201918)","author":"Dutande Prasad Vilas","key":"e_1_2_1_7_1","unstructured":"Prasad Vilas Dutande , Sanjay L. Nalbalwar , and Sanjay V. Khobragade . 2018. FPGA implementation of filters for removing muscle artefacts from EEG signals . In Proceedings of the 2018 2nd International Conference on Intelligent Computing and Control Systems (ICICCS\u201918) . IEEE, 728--732. Prasad Vilas Dutande, Sanjay L. Nalbalwar, and Sanjay V. Khobragade. 2018. FPGA implementation of filters for removing muscle artefacts from EEG signals. In Proceedings of the 2018 2nd International Conference on Intelligent Computing and Control Systems (ICICCS\u201918). IEEE, 728--732."},{"key":"e_1_2_1_8_1","first-page":"00","volume-title":"Proceedings of the 2019 IEEE 30th International Conference on Application-specific Systems, Architectures and Processors (ASAP\u201919)","volume":"8","author":"Fan H.","year":"2019","unstructured":"H. Fan , C. Luo , C. Zeng , M. Ferianc , Z. Que , S. Liu , X. Niu , and W. Luk . 2019. F-E3D: FPGA-based acceleration of an efficient 3D convolutional neural network for human action recognition . In Proceedings of the 2019 IEEE 30th International Conference on Application-specific Systems, Architectures and Processors (ASAP\u201919) , Vol. 2160-052X. 1-- 8 . DOI:https:\/\/doi.org\/10.1109\/ASAP. 2019 . 00 - 44 10.1109\/ASAP.2019.00-44 H. Fan, C. Luo, C. Zeng, M. Ferianc, Z. Que, S. Liu, X. Niu, and W. Luk. 2019. F-E3D: FPGA-based acceleration of an efficient 3D convolutional neural network for human action recognition. In Proceedings of the 2019 IEEE 30th International Conference on Application-specific Systems, Architectures and Processors (ASAP\u201919), Vol. 2160-052X. 1--8. DOI:https:\/\/doi.org\/10.1109\/ASAP.2019.00-44"},{"key":"e_1_2_1_9_1","doi-asserted-by":"crossref","unstructured":"Morteza Hosseini and Tinoosh Mohsenin. 2020. Binary precision neural network manycore accelerator. ACM J. Emerg. Technol. Comput. Syst. (2020).  Morteza Hosseini and Tinoosh Mohsenin. 2020. Binary precision neural network manycore accelerator. ACM J. Emerg. Technol. Comput. Syst. (2020).","DOI":"10.1145\/3423136"},{"key":"e_1_2_1_10_1","volume-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv:1704.04861.","author":"Howard Andrew G.","year":"2017","unstructured":"Andrew G. Howard , Menglong Zhu , Bo Chen , Dmitry Kalenichenko , Weijun Wang , Tobias Weyand , Marco Andreetto , and Hartwig Adam . 2017 . Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv:1704.04861. Retrieved from https:\/\/arxiv.org\/abs\/1704.04861. Andrew G. Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, and Hartwig Adam. 2017. Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv:1704.04861. Retrieved from https:\/\/arxiv.org\/abs\/1704.04861."},{"key":"e_1_2_1_11_1","volume-title":"Proceedings of the 2020 IEEE 33rd International System-on-Chip Conference (SOCC\u201920)","author":"\u00a0al H. Ren","year":"2020","unstructured":"H. Ren et \u00a0al . 2020 . End-to-end scalable and low power multi-modal CNN for respiratory-related symptoms detection . In Proceedings of the 2020 IEEE 33rd International System-on-Chip Conference (SOCC\u201920) . H. Ren et\u00a0al. 2020. End-to-end scalable and low power multi-modal CNN for respiratory-related symptoms detection. In Proceedings of the 2020 IEEE 33rd International System-on-Chip Conference (SOCC\u201920)."},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1097\/00004691-200307000-00004"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucli.2016.07.002"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/SPMB.2017.8257049"},{"volume-title":"IEEE Signal Processing in Medicine and Biology Symposium (SPMB'17)","author":"Islam R.","key":"e_1_2_1_15_1","unstructured":"R. Islam , W. D. Hairston , T. Oates , and T. Mohsenin . 2017. An EEG artifact detection and removal technique for embedded processors . In IEEE Signal Processing in Medicine and Biology Symposium (SPMB'17) . 1--3. DOI:10.1109\/SPMB.2017.8257049 10.1109\/SPMB.2017.8257049 R. Islam, W. D. Hairston, T. Oates, and T. Mohsenin. 2017. An EEG artifact detection and removal technique for embedded processors. In IEEE Signal Processing in Medicine and Biology Symposium (SPMB'17). 1--3. DOI:10.1109\/SPMB.2017.8257049"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/IEEECONF44664.2019.9049048"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CISS.2019.8693023"},{"key":"e_1_2_1_18_1","first-page":"1","article-title":"SensorNet: A scalable and low-power deep convolutional neural network for multimodal data classification","volume":"66","author":"\u00a0al A. Jafari","year":"2019","unstructured":"A. Jafari et \u00a0al . 2019 . SensorNet: A scalable and low-power deep convolutional neural network for multimodal data classification . IEEE Trans. Circ. Syst. I: Regul. Pap. 66 , 1 (Jan. 2019), 274--287. DOI:https:\/\/doi.org\/10.1109\/TCSI.2018.2848647 10.1109\/TCSI.2018.2848647 A. Jafari et\u00a0al. 2019. SensorNet: A scalable and low-power deep convolutional neural network for multimodal data classification. IEEE Trans. Circ. Syst. I: Regul. Pap. 66, 1 (Jan. 2019), 274--287. DOI:https:\/\/doi.org\/10.1109\/TCSI.2018.2848647","journal-title":"IEEE Trans. Circ. Syst. I: Regul. Pap."},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.2017.8050346"},{"key":"e_1_2_1_20_1","volume-title":"Sejnowski","author":"Jung Tzyy-Ping","year":"1998","unstructured":"Tzyy-Ping Jung , Colin Humphries , Te-Won Lee , Scott Makeig , Martin J McKeown , Vicente Iragui , and Terrence J . Sejnowski . 1998 . Extended ICA removes artifacts from electroencephalographic recordings. In Advances in Neural Information Processing Systems . 894--900. Tzyy-Ping Jung, Colin Humphries, Te-Won Lee, Scott Makeig, Martin J McKeown, Vicente Iragui, and Terrence J. Sejnowski. 1998. Extended ICA removes artifacts from electroencephalographic recordings. In Advances in Neural Information Processing Systems. 894--900."},{"key":"e_1_2_1_21_1","unstructured":"Lukasz Kaiser Aidan N. Gomez and Francois Chollet. 2017. Depthwise separable convolutions for neural machine translation. arXiv:1706.03059. Retrieved from https:\/\/arxiv.org\/abs\/1706.03059.  Lukasz Kaiser Aidan N. Gomez and Francois Chollet. 2017. Depthwise separable convolutions for neural machine translation. arXiv:1706.03059. Retrieved from https:\/\/arxiv.org\/abs\/1706.03059."},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/BIOCAS.2018.8584791"},{"key":"e_1_2_1_23_1","unstructured":"Raghuraman Krishnamoorthi. 2018. Quantizing deep convolutional networks for efficient inference: A whitepaper. arXiv:1806.08342. Retrieved from https:\/\/arxiv.org\/abs\/1806.08342.  Raghuraman Krishnamoorthi. 2018. Quantizing deep convolutional networks for efficient inference: A whitepaper. arXiv:1806.08342. Retrieved from https:\/\/arxiv.org\/abs\/1806.08342."},{"key":"e_1_2_1_24_1","volume-title":"Hinton","author":"Krizhevsky Alex","year":"2012","unstructured":"Alex Krizhevsky , Ilya Sutskever , and Geoffrey E . Hinton . 2012 . Imagenet classification with deep convolutional neural networks. In Advances in Neural Information Processing Systems . 1097--1105. Alex Krizhevsky, Ilya Sutskever, and Geoffrey E. Hinton. 2012. Imagenet classification with deep convolutional neural networks. In Advances in Neural Information Processing Systems. 1097--1105."},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jneumeth.2012.05.017"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1088\/1741-2552\/aace8c"},{"key":"e_1_2_1_27_1","article-title":"Design and implementation of a novel complete filter for EEG application on FPGA","volume":"10","author":"Mahabub Atik","year":"2018","unstructured":"Atik Mahabub . 2018 . Design and implementation of a novel complete filter for EEG application on FPGA . Int. J. Image Graph. Sign. Process. 10 , 6 (2018). Atik Mahabub. 2018. Design and implementation of a novel complete filter for EEG application on FPGA. Int. J. Image Graph. Sign. Process. 10, 6 (2018).","journal-title":"Int. J. Image Graph. Sign. Process."},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.3390\/s19071736"},{"volume-title":"Proceedings of the 3rd ACM SIGKDD International Workshop on Epidemiology meets Data Mining and Knowledge Discovery (epiDAMIK\u201920)","author":"Hosseini M.","key":"e_1_2_1_29_1","unstructured":"M. Hosseini , H. Ren , H. Rashid , A. Mazumder , B. Prakash , and T. Mohsenin . 2020. Neural networks for pulmonary disease diagnosis using auditory and demographic information . In Proceedings of the 3rd ACM SIGKDD International Workshop on Epidemiology meets Data Mining and Knowledge Discovery (epiDAMIK\u201920) . ACM, 1--5. M. Hosseini, H. Ren, H. Rashid, A. Mazumder, B. Prakash, and T. Mohsenin. 2020. Neural networks for pulmonary disease diagnosis using auditory and demographic information. In Proceedings of the 3rd ACM SIGKDD International Workshop on Epidemiology meets Data Mining and Knowledge Discovery (epiDAMIK\u201920). ACM, 1--5."},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1097\/00004691-198801000-00001"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC.2015.7320031"},{"key":"e_1_2_1_32_1","first-page":"109","article-title":"A flexible multichannel EEG feature extractor and classifier for seizure detection","volume":"62","author":"Page Adam","year":"2015","unstructured":"Adam Page , Chris Sagedy , et\u00a0al. 2015 . A flexible multichannel EEG feature extractor and classifier for seizure detection . IEEE Trans. Circ. Syst. II: Express Briefs 62 , 2 (2015), 109 -- 113 . Adam Page, Chris Sagedy, et\u00a0al. 2015. A flexible multichannel EEG feature extractor and classifier for seizure detection. IEEE Trans. Circ. Syst. II: Express Briefs 62, 2 (2015), 109--113.","journal-title":"IEEE Trans. Circ. Syst. II: Express Briefs"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISQED48828.2020.9137013"},{"key":"e_1_2_1_34_1","volume-title":"Proceedings of the SafeAI Workshop of the 34th AAAI Conference on Artificial Intelligence. AAAI.","author":"\u00a0al Bharat Prakash","year":"2020","unstructured":"Bharat Prakash et \u00a0al . 2020 . Guiding safe reinforcement learning policies using structured language constraints . In Proceedings of the SafeAI Workshop of the 34th AAAI Conference on Artificial Intelligence. AAAI. Bharat Prakash et\u00a0al. 2020. Guiding safe reinforcement learning policies using structured language constraints. In Proceedings of the SafeAI Workshop of the 34th AAAI Conference on Artificial Intelligence. AAAI."},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISQED48828.2020.9137056"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITB.2004.824735"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3386263.3407652"},{"key":"e_1_2_1_38_1","volume-title":"Proceedings of the 2016 Second International Conference on Science Technology Engineering and Management (ICONSTEM\u201916)","author":"\u00a0al Kalyana Sundaram","year":"2016","unstructured":"Kalyana Sundaram et \u00a0al . 2016 . FPGA based filters for EEG pre-processing . In Proceedings of the 2016 Second International Conference on Science Technology Engineering and Management (ICONSTEM\u201916) . IEEE, 572--576. Kalyana Sundaram et\u00a0al. 2016. FPGA based filters for EEG pre-processing. In Proceedings of the 2016 Second International Conference on Science Technology Engineering and Management (ICONSTEM\u201916). IEEE, 572--576."},{"volume-title":"Proceedings of the 31st AAAI Conference on Artificial Intelligence.","author":"Szegedy Christian","key":"e_1_2_1_39_1","unstructured":"Christian Szegedy , Sergey Ioffe , Vincent Vanhoucke , and Alexander A. Alemi . 2017. Inception-v4, inception-resnet and the impact of residual connections on learning . In Proceedings of the 31st AAAI Conference on Artificial Intelligence. Christian Szegedy, Sergey Ioffe, Vincent Vanhoucke, and Alexander A. Alemi. 2017. Inception-v4, inception-resnet and the impact of residual connections on learning. In Proceedings of the 31st AAAI Conference on Artificial Intelligence."},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNSRE.2018.2876129"},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1186\/1744-9081-7-30"},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/2684746.2689060"},{"volume-title":"Proceedings of the International Conference on Web-Age Information Management. Springer, 298--310","author":"Zheng Yi","key":"e_1_2_1_43_1","unstructured":"Yi Zheng , Qi Liu , Enhong Chen , Yong Ge , and J. Leon Zhao . 2014. Time series classification using multi-channels deep convolutional neural networks . In Proceedings of the International Conference on Web-Age Information Management. Springer, 298--310 . Yi Zheng, Qi Liu, Enhong Chen, Yong Ge, and J. Leon Zhao. 2014. Time series classification using multi-channels deep convolutional neural networks. In Proceedings of the International Conference on Web-Age Information Management. Springer, 298--310."}],"container-title":["ACM Journal on Emerging Technologies in Computing Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3427471","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3427471","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T21:24:39Z","timestamp":1750195479000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3427471"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,15]]},"references-count":43,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2021,4,30]]}},"alternative-id":["10.1145\/3427471"],"URL":"https:\/\/doi.org\/10.1145\/3427471","relation":{},"ISSN":["1550-4832","1550-4840"],"issn-type":[{"type":"print","value":"1550-4832"},{"type":"electronic","value":"1550-4840"}],"subject":[],"published":{"date-parts":[[2021,4,15]]},"assertion":[{"value":"2020-05-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2020-09-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-04-15","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}