{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T22:58:59Z","timestamp":1775084339796,"version":"3.50.1"},"reference-count":23,"publisher":"MDPI AG","issue":"23","license":[{"start":{"date-parts":[[2023,12,4]],"date-time":"2023-12-04T00:00:00Z","timestamp":1701648000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Korean government (MSIT)","award":["2022R1A5A8026986"],"award-info":[{"award-number":["2022R1A5A8026986"]}]},{"name":"Korean government (MSIT)","award":["2020-0-01304"],"award-info":[{"award-number":["2020-0-01304"]}]},{"name":"Korean government (MSIT)","award":["2021R1F1A1061314"],"award-info":[{"award-number":["2021R1F1A1061314"]}]},{"name":"Korean government (MSIT)","award":["2020-0-01077"],"award-info":[{"award-number":["2020-0-01077"]}]},{"name":"Korean government (MSIT)","award":["IITP-2023-2020-0-01462"],"award-info":[{"award-number":["IITP-2023-2020-0-01462"]}]},{"name":"Korean government (MSIT)","award":["2020M3H2A1076786"],"award-info":[{"award-number":["2020M3H2A1076786"]}]},{"name":"MSIT (Ministry of Science and ICT), Korea","award":["2022R1A5A8026986"],"award-info":[{"award-number":["2022R1A5A8026986"]}]},{"name":"MSIT (Ministry of Science and ICT), Korea","award":["2020-0-01304"],"award-info":[{"award-number":["2020-0-01304"]}]},{"name":"MSIT (Ministry of Science and ICT), Korea","award":["2021R1F1A1061314"],"award-info":[{"award-number":["2021R1F1A1061314"]}]},{"name":"MSIT (Ministry of Science and ICT), Korea","award":["2020-0-01077"],"award-info":[{"award-number":["2020-0-01077"]}]},{"name":"MSIT (Ministry of Science and ICT), Korea","award":["IITP-2023-2020-0-01462"],"award-info":[{"award-number":["IITP-2023-2020-0-01462"]}]},{"name":"MSIT (Ministry of Science and ICT), Korea","award":["2020M3H2A1076786"],"award-info":[{"award-number":["2020M3H2A1076786"]}]},{"name":"Ministry of Science and ICT","award":["2022R1A5A8026986"],"award-info":[{"award-number":["2022R1A5A8026986"]}]},{"name":"Ministry of Science and ICT","award":["2020-0-01304"],"award-info":[{"award-number":["2020-0-01304"]}]},{"name":"Ministry of Science and ICT","award":["2021R1F1A1061314"],"award-info":[{"award-number":["2021R1F1A1061314"]}]},{"name":"Ministry of Science and ICT","award":["2020-0-01077"],"award-info":[{"award-number":["2020-0-01077"]}]},{"name":"Ministry of Science and ICT","award":["IITP-2023-2020-0-01462"],"award-info":[{"award-number":["IITP-2023-2020-0-01462"]}]},{"name":"Ministry of Science and ICT","award":["2020M3H2A1076786"],"award-info":[{"award-number":["2020M3H2A1076786"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>In this paper, we propose a compact and low-power mixed-signal approach to implementing convolutional operators that are often responsible for most of the chip area and power consumption of Convolutional Neural Network (CNN) processing chips. The convolutional operators consist of several multiply-and-accumulate (MAC) units. MAC units are the primary components that process convolutional layers and fully connected layers of CNN models. Analog implementation of MAC units opens a new paradigm for realizing low-power CNN processing chips, benefiting from less power and area consumption. The proposed mixed-signal convolutional operator comprises low-power binary-weighted current steering digital-to-analog conversion (DAC) circuits and accumulation capacitors. Compared with a conventional binary-weighted DAC, the proposed circuit benefits from optimum accuracy, smaller area, and lower power consumption due to its symmetric design. The proposed convolutional operator takes as input a set of 9-bit digital input feature data and weight parameters of the convolutional filter. It then calculates the convolutional filter\u2019s result and accumulates the resulting voltage on capacitors. In addition, the convolutional operator employs a novel charge-sharing technique to process negative MAC results. We propose an analog max-pooling circuit that instantly selects the maximum input voltage. To demonstrate the performance of the proposed mixed-signal convolutional operator, we implemented a CNN processing chip consisting of 3 analog convolutional operators, with each operator processing a 3 \u00d7 3 kernel. This chip contains 27 MAC circuits, an analog max-pooling, and an analog-to-digital conversion (ADC) circuit. The mixed-signal CNN processing chip is implemented using a CMOS 55 nm process, which occupies a silicon area of 0.0559 mm2 and consumes an average power of 540.6 \u03bcW. The proposed mixed-signal CNN processing chip offers an area reduction of 84.21% and an energy reduction of 91.85% compared with a conventional digital CNN processing chip. Moreover, another CNN processing chip is implemented with more analog convolutional operators to demonstrate the operation and structure of an example convolutional layer of a CNN model. Therefore, the proposed analog convolutional operator can be adapted in various CNN models as an alternative to digital counterparts.<\/jats:p>","DOI":"10.3390\/s23239612","type":"journal-article","created":{"date-parts":[[2023,12,4]],"date-time":"2023-12-04T12:15:14Z","timestamp":1701692114000},"page":"9612","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Analog Convolutional Operator Circuit for Low-Power Mixed-Signal CNN Processing Chip"],"prefix":"10.3390","volume":"23","author":[{"given":"Malik Summair","family":"Asghar","sequence":"first","affiliation":[{"name":"Department of Electronics, College of Electrical and Computer Engineering, Chungbuk National University, Cheongju 28644, Republic of Korea"},{"name":"Department of Electrical and Computer Engineering, COMSATS University Islamabad, Abbottabad Campus, University Road, Tobe Camp, Abbottabad 22044, Pakistan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4038-462X","authenticated-orcid":false,"given":"Saad","family":"Arslan","sequence":"additional","affiliation":[{"name":"TSY Design (Pvt.) Ltd., Islamabad 44000, Pakistan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2602-2075","authenticated-orcid":false,"given":"HyungWon","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Electronics, College of Electrical and Computer Engineering, Chungbuk National University, Cheongju 28644, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2023,12,4]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"304","DOI":"10.1016\/j.giq.2019.02.003","article-title":"IoT and AI for smart government: A research agenda","volume":"36","author":"Kankanhalli","year":"2019","journal-title":"Gov. Inf. Q."},{"key":"ref_2","unstructured":"Gupta, S. (2023, February 06). Neuromorphic Hardware: Trying to Put Brain into Chips. 30 June 2019. Available online: https:\/\/towardsdatascience.com\/neuromorphic-hardware-trying-to-put-brain-into-chips-222132f7e4de."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"630","DOI":"10.1109\/LED.2018.2809661","article-title":"Spiking Neural Network Using Synaptic Transistors and Neuron Circuits for Pattern Recognition with Noisy Images","volume":"39","author":"Kim","year":"2018","journal-title":"IEEE Electron Device Lett."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1664","DOI":"10.1109\/TBCAS.2019.2945406","article-title":"Spike Counts Based Low Complexity SNN Architecture with Binary Synapse","volume":"13","author":"Tang","year":"2019","journal-title":"IEEE Trans. Biomed. Circuits Syst."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"992","DOI":"10.1109\/JSSC.2018.2884901","article-title":"A 4096-Neuron 1M-Synapse 3.8-pJ\/SOP Spiking Neural Network with On-Chip STDP Learning and Sparse Weights in 10-nm FinFET CMOS","volume":"54","author":"Chen","year":"2019","journal-title":"IEEE J. Solid-State Circuits"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Asghar, M.S., Arslan, S., Al-Hamid, A.A., and Kim, H. (2023). A Compact and Low-Power SoC Design for Spiking Neural Network Based on Current Multiplier Charge Injector Synapse. Sensors, 23.","DOI":"10.3390\/s23146275"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Bachtiar, Y.A., and Adiono, T. (2019, January 8\u20139). Convolutional Neural Network and Maxpooling Architecture on Zynq SoC FPGA. Proceedings of the International Symposium on Electronics and Smart Devices (ISESD), Badung-Bali, Indonesia.","DOI":"10.1109\/ISESD.2019.8909510"},{"key":"ref_8","unstructured":"Sabogal, S., George, A., and Crum, G. (August, January 30). ReCoN: A Reconfigurable CNN Acceleration Framework for Hybrid Semantic Segmentation on Hybrid SoCs for Space Applications. Proceedings of the IEEE Space Computing Conference (SCC), Pasadena, CA, USA."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"388","DOI":"10.1109\/JETCAS.2019.2909317","article-title":"ReRAM-Based In-Memory Computing for Search Engine and Neural Network Applications","volume":"9","author":"Halawani","year":"2019","journal-title":"IEEE J. Emerg. Sel. Top. Circuits Syst."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Park, S.-S., and Chung, K.-S. (2020). CENNA: Cost-Effective Neural Network Accelerator. Electronics, 9.","DOI":"10.3390\/electronics9010134"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"461","DOI":"10.1145\/3296957.3173176","article-title":"MAERI: Enabling Flexible Dataflow Mapping over DNN Accelerators via Reconfigurable Interconnects","volume":"53","author":"Kwon","year":"2018","journal-title":"SIGPLAN Not."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Zhu, J., Huang, Y., Yang, Z., Tang, X., and Ye, T.T. (2019, January 11\u201314). Analog Implementation of Reconfigurable Convolutional Neural Network Kernels. Proceedings of the 2019 IEEE Asia Pacific Conference on Circuits and Systems (APCCAS), Bangkok, Thailand.","DOI":"10.1109\/APCCAS47518.2019.8953177"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Choi, J., Lee, S., Son, Y., and Kim, S.Y. (2020). Design of an Always-On Image Sensor Using an Analog Lightweight Convolutional Neural Network. Sensors, 20.","DOI":"10.3390\/s20113101"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1145\/3304110","article-title":"A Mixed Signal Architecture for Convolutional Neural Networks","volume":"15","author":"Lou","year":"2019","journal-title":"ACM J. Emerg. Technol. Comput. Syst."},{"key":"ref_15","unstructured":"Wong, M.Z., Guillard, B., Murai, R., Saeedi, S., and Kelly, P.H.J. (2020). AnalogNet: Convolutional Neural Network Inference on Analog Focal Plane Sensor Processors. arXiv, Available online: http:\/\/arxiv.org\/abs\/2006.01765."},{"key":"ref_16","first-page":"7","article-title":"A Low Power Mixed Signal Convolutional Neural Network for Deep Learning SoC","volume":"9","author":"Asghar","year":"2023","journal-title":"IDEC J. Integr. Circuits Syst."},{"key":"ref_17","first-page":"4357","article-title":"Low power 12-bit SAR ADC for Analog Convolutional Kernel of Mixed-Signal CNN Accelerator","volume":"75","author":"Lee","year":"2023","journal-title":"CMC-Comput. Mater. Contin. (CMC)"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1142\/S0218126607003642","article-title":"High Speed High Precision Voltage-Mode MAX and MIN Circuits","volume":"16","author":"Khoei","year":"2007","journal-title":"J. Circuits Syst. Comput. (JCSC)"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Soleimani, M., Khoei, A., Hadidi, K., and Nia, S.K. (2009, January 23\u201327). Design of high-speed high-precision voltage-mode MAX-MIN circuits with low area and low power consumption. Proceedings of the 2009 European Conference on Circuit Theory and Design, Antalya, Turkey.","DOI":"10.1109\/ECCTD.2009.5274998"},{"key":"ref_20","first-page":"1665","article-title":"Cnn accelerator using proposed diagonal cyclic array for minimizing memory accesses","volume":"76","author":"Son","year":"2023","journal-title":"Comput. Mater. Contin."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"\u00c5leskog, C., Grahn, H., and Borg, A. (2022). Recent Developments in Low-Power AI Accelerators: A Survey. Algorithms, 15.","DOI":"10.3390\/a15110419"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Kim, J.-H., Kim, C., Kim, K., and Yoo, H.-J. (2019, January 26\u201329). An Ultra-Low-Power Analog-Digital Hybrid CNN Face Recognition Processor Integrated with a CIS for Always-on Mobile Devices. Proceedings of the 2019 IEEE International Symposium on Circuits and Systems (ISCAS), Sapporo, Japan.","DOI":"10.1109\/ISCAS.2019.8702698"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Zhang, B., Saikia, J., Meng, J., Wang, D., Kwon, S., Myung, S., Kim, H., Kim, S.J., Seo, J.-S., and Seok, M. (2022, January 24\u201327). A 177 TOPS\/W, Capacitor-based In-Memory Computing SRAM Macro with Stepwise-Charging\/Discharging DACs and Sparsity-Optimized Bitcells for 4-Bit Deep Convolutional Neural Networks. Proceedings of the 2022 IEEE Custom Integrated Circuits Conference (CICC), Newport Beach, CA, USA.","DOI":"10.1109\/CICC53496.2022.9772781"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/23\/9612\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T21:37:46Z","timestamp":1760132266000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/23\/9612"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,4]]},"references-count":23,"journal-issue":{"issue":"23","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["s23239612"],"URL":"https:\/\/doi.org\/10.3390\/s23239612","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,4]]}}}