{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T15:38:13Z","timestamp":1780673893749,"version":"3.54.1"},"reference-count":49,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2023,4,14]],"date-time":"2023-04-14T00:00:00Z","timestamp":1681430400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>A novel analog integrated implementation of a hardware-friendly support vector machine algorithm that can be a part of a classification system is presented in this work. The utilized architecture is capable of on-chip learning, making the overall circuit completely autonomous at the cost of power and area efficiency. Nonetheless, using subthreshold region techniques and a low power supply voltage (at only 0.6 V), the overall power consumption is 72 \u03bcW. The classifier consists of two main components, the learning and the classification blocks, both of which are based on the mathematical equations of the hardware-friendly algorithm. Based on a real-world dataset, the proposed classifier achieves only 1.4% less average accuracy than a software-based implementation of the same model. Both design procedure and all post-layout simulations are conducted in the Cadence IC Suite, in a TSMC 90 nm CMOS process.<\/jats:p>","DOI":"10.3390\/s23083978","type":"journal-article","created":{"date-parts":[[2023,4,14]],"date-time":"2023-04-14T04:54:24Z","timestamp":1681448064000},"page":"3978","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":54,"title":["A Low-Power Analog Integrated Implementation of the Support Vector Machine Algorithm with On-Chip Learning Tested on a Bearing Fault Application"],"prefix":"10.3390","volume":"23","author":[{"given":"Vassilis","family":"Alimisis","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, National Technical University of Athens, 15780 Athens, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Georgios","family":"Gennis","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, National Technical University of Athens, 15780 Athens, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marios","family":"Gourdouparis","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, National Technical University of Athens, 15780 Athens, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8641-2414","authenticated-orcid":false,"given":"Christos","family":"Dimas","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, National Technical University of Athens, 15780 Athens, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paul P.","family":"Sotiriadis","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, National Technical University of Athens, 15780 Athens, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2023,4,14]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Meijer, G. (2008). Smart Sensor Systems, John Wiley & Sons.","DOI":"10.1002\/9780470866931"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"An, B.W., Shin, J.H., Kim, S.-Y., Kim, J., Ji, S., Park, J., Lee, Y., Jang, J., Park, Y.-G., and Cho, E. (2017). Smart sensor systems for wearable electronic devices. Polymers, 9.","DOI":"10.3390\/polym9080303"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Alioto, M. (2017). Enabling the Internet of Things: From Integrated Circuits to Integrated Systems, Springer.","DOI":"10.1007\/978-3-319-51482-6"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"108","DOI":"10.1109\/JPROC.2018.2871057","article-title":"The next generation of deep learning hardware: Analog computing","volume":"107","author":"Haensch","year":"2018","journal-title":"Proc. IEEE"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Mirchandani, N., Onabajo, M., and Shrivastava, A. (2020, January 12\u201314). RSSI Amplifier Design for a Feature Extraction Technique to Detect Seizures with Analog Computing. Proceedings of the 2020 IEEE International Symposium on Circuits and Systems (ISCAS), Seville, Spain.","DOI":"10.1109\/ISCAS45731.2020.9180802"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Singh, J., Dabeer, O., and Madhow, U. (2007, January 24\u201328). Communication limits with low precision analog-to-digital conversion at the receiver. Proceedings of the International Conference on Communications, Glasgow, Scotland.","DOI":"10.1109\/ICC.2007.1038"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Yip, M., Bohorquez, J.L., and Chandrakasan, A.P. (2012, January 13\u201315). A 0.6 V 2.9 \u03bcW mixed-signal front-end for ECG monitoring. Proceedings of the 2012 Symposium on VLSI Circuits (VLSIC), Honolulu, HI, USA.","DOI":"10.1109\/VLSIC.2012.6243792"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Alimisis, V., Gennis, G., Touloupas, K., Dimas, C., Uzunoglu, N., and Sotiriadis, P.P. (2022). Nanopower Integrated Gaussian Mixture Model Classifier for Epileptic Seizure Prediction. Bioengineering, 9.","DOI":"10.3390\/bioengineering9040160"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Yan, C., Shin, H., Bolton, C., Xu, W., Kim, Y., and Fu, K. (2020, January 18\u201320). Sok: A minimalist approach to formalizing analog sensor security. Proceedings of the 2020 IEEE Symposium on Security and Privacy (SP), Online.","DOI":"10.1109\/SP40000.2020.00026"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1578","DOI":"10.1109\/TCSI.2020.3047035","article-title":"An 800 nW Switched-Capacitor Feature Extraction Filterbank for Sound Classification","volume":"68","author":"Villamizar","year":"2021","journal-title":"IEEE Trans. Circuits Syst."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"3123","DOI":"10.1109\/JSSC.2021.3076344","article-title":"Nanowatt acoustic inference sensing exploiting nonlinear analog feature extraction","volume":"56","author":"Yang","year":"2021","journal-title":"IEEE J.-Solid-State Circuits"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"214","DOI":"10.1109\/JSSC.2012.2221220","article-title":"An 8-channel scalable EEG acquisition SoC with patient-specific seizure classification and recording processor","volume":"48","author":"Yoo","year":"2012","journal-title":"IEEE J.-Solid-State Circuits"},{"key":"ref_13","unstructured":"Peng, S.Y., Hasler, P.E., and Anderson, D. (2007, January 15\u201317). An analog programmable multi-dimensional radial basis function based classifier. Proceedings of the 2007 486 IFIP International Conference on Very Large Scale Integration, Atlanta, GA, USA."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1007\/s10470-022-02038-7","article-title":"An ultra low power analog integrated radial basis function classifier for smart IoT systems","volume":"112","author":"Alimisis","year":"2022","journal-title":"Analog. Integr. Circuits Signal Process."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"105510","DOI":"10.1016\/j.mejo.2022.105510","article-title":"Gaussian Mixture Model classifier analog integrated low-power implementation with applications in fault management detection","volume":"126","author":"Alimisis","year":"2022","journal-title":"Microelectron. J."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Alimisis, V., Gennis, G., Dimas, C., and Sotiriadis, P.P. (2021, January 19\u201322). An Analog Bayesian Classifier Implementation, for Thyroid Disease Detection, based on a Low-Power, Current-Mode Gaussian Function Circuit. Proceedings of the 2021 International Conference on Microelectronics (ICM), Cairo, Egypt.","DOI":"10.1109\/ICM52667.2021.9664939"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1007\/s10470-012-9980-y","article-title":"An analog on-line-learning K-means processor employing fully parallel self-converging circuitry","volume":"75","author":"Zhang","year":"2013","journal-title":"Analog. Integr. Circuits Signal Process."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Alimisis, V., Mouzakis, V., Gennis, G., Tsouvalas, E., Dimas, C., and Sotiriadis, P.P. (2022). A Hand Gesture Recognition Circuit Utilizing an Analog Voting Classifier. Electronics, 11.","DOI":"10.3390\/electronics11233915"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1109\/MM.2018.2873953","article-title":"Design of programmable analog calculation unit by implementing support vector regression for approximate computing","volume":"38","author":"Zhang","year":"2018","journal-title":"IEEE Micro"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Li, F., Chang, C.H., and Siek, L. (2009, January 24\u201327). A compact current mode neuron circuit with Gaussian taper learning capability. Proceedings of the 2009 IEEE International Symposium on Circuits and Systems, Taipei, Taiwan.","DOI":"10.1109\/ISCAS.2009.5118216"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"129","DOI":"10.5573\/JSTS.2019.19.1.129","article-title":"A low-power, mixed-mode neural network classifier for robust scene classification","volume":"19","author":"Lee","year":"2019","journal-title":"J. Semicond. Technol. Sci."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"270","DOI":"10.1109\/JSSC.2014.2356197","article-title":"A 1 tops\/w analog deep machine-learning engine with floating-gate storage in 0.13 \u03bcm CMOS","volume":"50","author":"Lu","year":"2014","journal-title":"IEEE J. Solid-State Circuits"},{"key":"ref_23","first-page":"1529","article-title":"A generic nano-watt power fully tunable 1-D gaussian kernel circuit for artificial neural network","volume":"67","author":"Mohamed","year":"2020","journal-title":"IEEE Trans. Circuits Syst. II Express Briefs"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1833","DOI":"10.1109\/TVLSI.2020.2984472","article-title":"Low power unsupervised anomaly detection by nonparametric modeling of sensor statistics","volume":"28","author":"Shylendra","year":"2020","journal-title":"IEEE Trans. Very Large Scale Integr. Vlsi Syst."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1007\/s42979-020-00128-9","article-title":"FPGA implementations of SVM classifiers: A review","volume":"1","author":"Afifi","year":"2020","journal-title":"SN Comput. Sci."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"163","DOI":"10.1016\/j.vlsi.2018.10.002","article-title":"SVM algorithm oriented for implementation in a low-cost Xilinx FPGA","volume":"64","year":"2019","journal-title":"Integration"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"67277","DOI":"10.1109\/ACCESS.2018.2870883","article-title":"Hardware design of real time epileptic seizure detection based on STFT and SVM","volume":"6","author":"Wang","year":"2018","journal-title":"IEEE Access"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"14472","DOI":"10.1109\/ACCESS.2019.2894169","article-title":"A hardware-efficient recognition accelerator using Haar-like feature and SVM classifier","volume":"7","author":"Luo","year":"2019","journal-title":"IEEE Access"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Lopes, F.F., Ferreira, J.C., and Fernandes, M.A. (2019). Parallel implementation on FPGA of support vector machines using stochastic gradient descent. Electronics, 8.","DOI":"10.3390\/electronics8060631"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"1426","DOI":"10.1109\/TNN.2003.816345","article-title":"Kerneltron: Support vector \u201cmachine\u201d in silicon","volume":"14","author":"Genov","year":"2003","journal-title":"IEEE Trans. Neural Netw."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1169","DOI":"10.1109\/JSSC.2007.894803","article-title":"Sub-microwatt analog VLSI trainable pattern classifier","volume":"42","author":"Chakrabartty","year":"2007","journal-title":"IEEE J. Solid-State Circuits"},{"key":"ref_32","unstructured":"Peng, S.Y., Minch, B.A., and Hasler, P. (2008, January 18\u201321). Analog VLSI implementation of support vector machine learning and classification. Proceedings of the 2008 IEEE International Symposium on Circuits and Systems, Seattle, WA, USA."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"1513","DOI":"10.1109\/TCSI.2009.2034234","article-title":"An on-chip-trainable Gaussian-kernel analog support vector machine","volume":"57","author":"Kang","year":"2009","journal-title":"IEEE Trans. Circuits Syst. I Regul. Pap."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"04DE10","DOI":"10.1143\/JJAP.51.04DE10","article-title":"Fully parallel self-learning analog support vector machine employing compact gaussian generation circuits","volume":"51","author":"Zhang","year":"2012","journal-title":"Jpn. J. Appl. Phys."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1109\/TIM.2006.887319","article-title":"Low-power and low-cost implementation of SVMs for smart sensors","volume":"56","author":"Boni","year":"2007","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"1011","DOI":"10.1109\/JIOT.2018.2799948","article-title":"An ultra low-power memristive neuromorphic circuit for Internet of Things smart sensors","volume":"5","author":"Fayyazi","year":"2018","journal-title":"IEEE Internet Things J."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Wang, A., Calhoun, B.H., and Chandrakasan, A.P. (2006). Sub-Threshold Design for Ultra Low-Power Systems, Springer.","DOI":"10.1145\/1165573.1165661"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Alimisis, V., Gourdouparis, M., Gennis, G., Dimas, C., and Sotiriadis, P.P. (2021). Analog gaussian function circuit: Architectures, operating principles and applications. Electronics, 10.","DOI":"10.3390\/electronics10202530"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Liu, S.C., Kramer, J., Indiveri, G., Delbra, T., and Douglas, R. (2002). Analog VLSI: Circuits and Principles, MIT Press.","DOI":"10.7551\/mitpress\/1250.001.0001"},{"key":"ref_40","unstructured":"Lazzaro, J., Ryckebusch, S., Mahowald, M.A., and Mead, C.A. (1988). Advances in Neural Information Processing Systems, Proceedings of the NIPS Conference, Denver, CO, USA, 27\u201330 November 1988, Morgan Kaufmann."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"1745","DOI":"10.1016\/j.dib.2018.11.019","article-title":"Bearing vibration data collected under time-varying rotational speed conditions","volume":"21","author":"Huang","year":"2018","journal-title":"Data Brief"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Alimisis, V., Gourdouparis, M., Dimas, C., and Sotiriadis, P.P. (2021, January 14). A 0.6 V, 3.3 nW, Adjustable Gaussian Circuit for Tunable Kernel Functions. Proceedings of the 2021 34th SBC\/SBMicro\/IEEE\/ACM Symposium on Integrated Circuits and Systems Design (SBCCI), Campinas, Brazil.","DOI":"10.1109\/SBCCI53441.2021.9529988"},{"key":"ref_43","unstructured":"Delbrueck, T., and Mead, C. (April, January 28). Bump circuits. Proceedings of the International Joint Conference on Neural Networks, San Francisco, CA, USA."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"153755","DOI":"10.1016\/j.aeue.2021.153755","article-title":"An ultra-low power, \u00b10.3 V supply, fully-tunable Gaussian function circuit architecture for radial-basis functions analog hardware implementation","volume":"136","author":"Gourdouparis","year":"2021","journal-title":"AEU-Int. J. Electron. Commun."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1023\/A:1011208127849","article-title":"A current-mode hysteretic winner-take-all network, with excitatory and inhibitory coupling","volume":"28","author":"Indiveri","year":"2001","journal-title":"Analog. Integr. Circuits Signal Process."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"685","DOI":"10.1049\/ell2.12156","article-title":"An adjustable 0.3 V current winner-take-all circuit for analogue neural networks","volume":"57","author":"Akbari","year":"2021","journal-title":"Electron. Lett."},{"key":"ref_47","unstructured":"(2022, May 23). Mendeley Data, Mendeley. Available online: https:\/\/data.mendeley.com\/."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Sharma, A.K., Madhusudan, M., Burns, S.M., Mukherjee, P., Yaldiz, S., Harjani, R., and Sapatnekar, S.S. (2021, January 1\u20135). Common-centroid layouts for analog circuits: Advantages and limitations. Proceedings of the 2021 Design, Automation & Test in Europe Conference & Exhibition, Grenoble, France.","DOI":"10.23919\/DATE51398.2021.9474244"},{"key":"ref_49","first-page":"4","article-title":"Gaussian Mixture Model Based Classification Revisited: Application to the Bearing Fault Classification","volume":"66","author":"Panic","year":"2020","journal-title":"Stroj. Vestn. J. Mech. Eng."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/8\/3978\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T19:15:44Z","timestamp":1760123744000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/8\/3978"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,14]]},"references-count":49,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2023,4]]}},"alternative-id":["s23083978"],"URL":"https:\/\/doi.org\/10.3390\/s23083978","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4,14]]}}}