Acceleration of FPGA based convolutional neural network for human activity classification using millimeter-wave radar
Open accessAbstract
Deep learning techniques have attracted much attention in the radar automatic target recognition. In this paper, we investigate an acceleration method of the convolutional neural network (CNN) on the field-programmable gate array (FPGA) for the embedded application of the millimeter-wave (mmW) radar-based human activity classification. Considering the micro-Doppler effect caused by a person's body movements, the spectrogram of mmW radar echoes is adopted as the CNN input. After that, according to the CNN architecture and the properties of the FPGA implementation, several parallel processing strategies are designed as well as data quantization and optimization of classification decision to accelerate the CNN execution. Finally, comparative experiments and discussions are carried out based on a measured dataset of nine individuals with four different actions by using a 77-GHz mmW radar. The results show that the proposed method not only maintains the high classification accuracy but also improves its execution speed, memory requirement, and power consumption. Specifically, compared with the implementation of the same network model on a graphics processing unit, it could achieve the speedup of about 30.42% at the cost of the classification accuracy loss of only 0.27%.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In addition, interlayer parallel computing also can be viewed as a time series structure from the overall viewpoint of the CNN model.
“In addition, interlayer parallel computing also can be viewed as a time series structure from the overall viewpoint of the CNN model.”
From Embedded Intelligence on FPGA: Survey, Applications and Challenges (2021) · cites this paper as [75]
In “Inter-Layer Parallel Computing,” the paper says the CNN model can be viewed as a time-series structure, not that interlayer parallel computing is one. It contrasts that sequential view with its parallel approach: a layer can begin before the previous layer finishes, allowing pipeline execution. (LLM, conf=0.84)
Checked by a reasoning model — may be wrong.
Experimental — accuracy not yet measuredPipelining is used as a technique for CNNrelated application as it computes all the functions in parallel.
“Pipelining is used as a technique for CNNrelated application as it computes all the functions in parallel.”
From Embedded Intelligence on FPGA: Survey, Applications and Challenges (2021) · cites this paper as [75]
The Inter-Layer Parallel Computing section says the CNN runs in a pipeline, starting some layer operations before the preceding layer finishes. It describes overlapping selected operations to reduce execution time, not computing all functions in parallel; page numbers are not available in the supplied copy. (LLM, conf=0.85)
Experimental — accuracy not yet measuredAll caches before the pooling are not required and the data cluster is transferred in parallel to save the time of operation in a single channel.
“All caches before the pooling are not required and the data cluster is transferred in parallel to save the time of operation in a single channel.”
From Embedded Intelligence on FPGA: Survey, Applications and Challenges (2021) · cites this paper as [75]
The “Convolution Group Parallel Computing” section says the cache before pooling may be unnecessary if data from a pooling region are provided in parallel, and describes optimizing caching and operation time within one channel. The claim overstates this conditional possibility as a categorical assertion that all such caches are unnecessary. (LLM, conf=0.88)
Experimental — accuracy not yet measuredThe entire CNN network and every convolution layer are accelerating on the Xilinx FPGA device.
“The entire CNN network and every convolution layer are accelerating on the Xilinx FPGA device.”
From Embedded Intelligence on FPGA: Survey, Applications and Challenges (2021) · cites this paper as [75]
By implementing both interlayer and convolutional group parallelism in the overall network perspective, more efficient usage of caches can be achieved, where no cache is needed for max pooling layers.
“By implementing both interlayer and convolutional group parallelism in the overall network perspective, more efficient usage of caches can be achieved, where no cache is needed for max pooling layers.”
From Embedded Intelligence on FPGA: Survey, Applications and Challenges (2021) · cites this paper as [75]
The execution speed is improved in forward propagation through the network by the computation procedure of CNN and the pipelining technique on FPGA.
“The execution speed is improved in forward propagation through the network by the computation procedure of CNN and the pipelining technique on FPGA.”
From Embedded Intelligence on FPGA: Survey, Applications and Challenges (2021) · cites this paper as [75]
The removal of the softmax step could benefit the computation reduction, as when the dimensionality of the last fully connected layer output is 4 × 1, the classification decision can be optimized by the logic, which clearly benefits the FPGA that consists of a lot of logic gates.
“The removal of the softmax step could benefit the computation reduction, as when the dimensionality of the last fully connected layer output is 4 × 1, the classification decision can be optimized by the logic, which clearly benefits the FPGA that consists of a lot of logic gates [75].”
From Embedded Intelligence on FPGA: Survey, Applications and Challenges (2021) · cites this paper as [75]
The computational implementation included the channels and layers of the CNN with several parallel processing schemes that would reduce the waiting time and caching time indirectly and increase the speed of the network on FPGA.
“The computational implementation included the channels and layers of the CNN with several parallel processing schemes that would reduce the waiting time and caching time indirectly and increase the speed of the network on FPGA.”
From Embedded Intelligence on FPGA: Survey, Applications and Challenges (2021) · cites this paper as [75]
In this application, the pipeline processing and multiple parallelism strategies show that there exists much runtime overlap between layers; thus, it is faster than the serial computing of the CNN execution.
“In this application, the pipeline processing and multiple parallelism strategies show that there exists much runtime overlap between layers; thus, it is faster than the serial computing of the CNN execution.”
From Embedded Intelligence on FPGA: Survey, Applications and Challenges (2021) · cites this paper as [75]
The proposed method is validated with a variety of human activities measured using mmWradar data.
“The proposed method is validated with a variety of human activities measured using mmWradar data.”
From Embedded Intelligence on FPGA: Survey, Applications and Challenges (2021) · cites this paper as [75]
When compared to the NVDIA GPU, the FPGA with the proposed acceleration method is 30.42% faster in the averaged execution time of CNN in test, and a 0.27% reduction in the classification accuracy is seen with 87.81%.
“When compared to the NVDIA GPU, the FPGA with the proposed acceleration method is 30.42% faster in the averaged execution time of CNN in test, and a 0.27% reduction in the classification accuracy is seen with 87.81% [75].”
From Embedded Intelligence on FPGA: Survey, Applications and Challenges (2021) · cites this paper as [75]
There are various parallel processing strategies that are proposed for the data flow and computation patterns in the network model.
“There are various parallel processing strategies that are proposed for the data flow and computation patterns in the network model.”
From Embedded Intelligence on FPGA: Survey, Applications and Challenges (2021) · cites this paper as [75]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
(2010) · International Conference on Machine Learning · Cited by 13,995 · see citing works
Searching for activation functions
Ramachandran, P., Zoph, B., & Le, Q. V. (2017) · arXiv · doi:10.48550/arxiv.1710.05941 · Cited by 2,335 · see citing works
Micro-doppler effect in radar: phenomenon, model, and simulation study
Chen, V. C., Li, F., Ho, S.-S., & Wechsler, H. (2006) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2006.1603402 · Cited by 1,697 · see citing works
Going Deeper with Embedded FPGA Platform for Convolutional Neural Network
Qiu, J., Wang, J., Yao, S., Guo, K., Li, B., Zhou, E., Yu, J., Tang, T., Xu, N., Song, S., et al. (2016) · ACM/SIGDA International Symposium on Field-Programmable Gate Arrays (FPGA) · doi:10.1145/2847263.2847265 · Cited by 1,268 · see citing works
Self-citationSoli: ubiquitous gesture sensing with millimeter wave radar
Lien, J., Gillian, N., Karagozler, M. E., Amihood, P., Schwesig, C., Olson, E., Raja, H., & Poupyrev, I. (2016) · ACM Transactions on Graphics · doi:10.1145/2897824.2925953 · Cited by 957 · see citing works
Human Activity Classification Based on Micro-Doppler Signatures Using a Support Vector Machine
Kim, Y., & Ling, H. (2009) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2009.2012849 · Cited by 880 · see citing works
Time-Frequency Transforms for Radar Imaging and Signal Analysis
Chen, V. C., & Ling, H. (2002) · Cited by 711 · see citing works
Kim, Y., & Moon, T. (2015) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2015.2491329 · Cited by 649 · see citing works
Book Review: Pattern Recognition and Machine Learning
Nasrabadi, N. M. (2007) · Journal of Electronic Imaging · doi:10.1117/1.2819119 · Cited by 636 · see citing works
Throughput-Optimized OpenCL-based FPGA Accelerator for Large-Scale Convolutional Neural Networks
Suda, N., Chandra, V., Dasika, G. S., Mohanty, A., Ma, Y., Vrudhula, S. B. K., Seo, J.-S., & Cao, Y. K. (2016) · ACM/SIGDA International Symposium on Field-Programmable Gate Arrays (FPGA) · doi:10.1145/2847263.2847276 · Cited by 556 · see citing works
Radar Signal Processing for Elderly Fall Detection: The future for in-home monitoring
Amin, M. G., Zhang, Y. D., Ahmad, F., & Ho, K. C. (2016) · IEEE Signal Processing Magazine · doi:10.1109/msp.2015.2502784 · Cited by 414 · see citing works
Indoor Person Identification Using a Low-Power FMCW Radar
Vandersmissen, B., Knudde, N., Jalalvand, A., Couckuyt, I., Bourdoux, A., Neve, W. D., & Dhaene, T. (2018) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2018.2816812 · Cited by 262 · see citing works
Fall Detection Using Deep Learning in Range-Doppler Radars
Jokanović, B., & Amin, M. G. (2017) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2017.2740098 · Cited by 261 · see citing works
Hardware accelerated convolutional neural networks for synthetic vision systems
Farabet, C., Martini, B., Akselrod, P., Talay, S., LeCun, Y., & Culurciello, E. (2010) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas.2010.5537908 · Cited by 233 · see citing works
Dickmann, J., Klappstein, J., Hahn, M., Appenrodt, N., Bloecher, H.-L., Werber, K., & Sailer, A. (2016) · IEEE Radar Conference (RadarConf) · doi:10.1109/radar.2016.7485214 · Cited by 220 · see citing works
Rycroft, M. J. (1998) · Journal of Atmospheric and Solar-Terrestrial Physics · doi:10.1016/s1364-6826(97)00104-1 · Cited by 150 · see citing works
Doppler signatures of radar backscattering from objects with micro motions
Chen, V. C. (2008) · IET Signal Processing · doi:10.1049/iet-spr:20070137 · Cited by 146 · see citing works
Latency-driven design for FPGA-based convolutional neural networks
Venieris, S. I., & Bouganis, C.-S. (2017) · International Conference on Field Programmable Logic and Applications (FPL) · doi:10.23919/fpl.2017.8056828 · Cited by 92 · see citing works
Nanzer, J. A., & Rogers, R. L. (2009) · IEEE Microwave and Wireless Components Letters · doi:10.1109/lmwc.2009.2017620 · Cited by 60 · see citing works
Le, H. T., Phung, S. L., Bouzerdoum, A., & Tivive, F. H. C. (2018) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2018.8461847 · Cited by 31 · see citing works
Collobert, R. (2004) · OpenGrey (Institut de l'Information Scientifique et Technique) · Cited by 24 · see citing works
Kim, Y., Choudhury, S. A., & Kong, H. (2016) · IEEE Access · doi:10.1109/access.2016.2547948 · Cited by 22 · see citing works
Multistatic radar classification of armed vs unarmed personnel using neural networks
Patel, J. S., Fioranelli, F., Ritchie, M., & Griffiths, H. (2017) · Evolving Systems · doi:10.1007/s12530-017-9208-6 · Cited by 20 · see citing works
76.5 GHz millimeter-wave radar for foreign objects debris detection on airport runways
Mazouni, K., Zeitler, A., Lanteri, J., Pichot, C., Dauvignac, J., Migliaccio, C., Yonemoto, N., Kohmura, A., & Futatsumori, S. (2012) · International Journal of Microwave and Wireless Technologies · doi:10.1017/s1759078712000451 · Cited by 18 · see citing works
A MIMO FMCW radar approach to HFSWR
Hinz, J. O., & Zölzer, U. (2011) · Advances in radio science · doi:10.5194/ars-9-159-2011 · Cited by 17 · see citing works
Flagged first, then by citations
Research works printed but not linked: 5
- M. Kishida, K. Ohguchi, and M. Shono, ''79 GHz-band high-resolution millimeter-wave radar,'' FUJITSU Sci. Tech. J., vol. 51, no. 4, pp. 55-59, Oct. 2015.
- J. Microw. Wireless Technol., vol. 4, no. 3, pp. 317-326, Jun. 2012.
- Field-Program. Gate Arrays (FPGA), Monterey, CA, USA, Feb. 2016, pp. 26-35.
- P. Ramachandran, B. Zoph, and Q. V. Le, ''Searching for activation func- tions,'' in Proc. Int. Conf. Learn. Represent., Vancouver, BC, Canada, Apr. 2018, pp. 1-13.
- C. M. Bishop, Pattern Recognition and Machine Learning. New York, NY, USA: Springer, 2006.
Cited by
Sorted by citations
Design possibilities and challenges of DNN models: a review on the perspective of end devices
Hussain, H., Tamizharasan, P. S., & Rahul, C. S. (2022) · Artificial Intelligence Review · doi:10.1007/s10462-022-10138-z · Cited by 113 · see citing works
Embedded Intelligence on FPGA: Survey, Applications and Challenges
Seng, K. P., Lee, P. J., & Ang, L. M. (2021) · Electronics · doi:10.3390/electronics10080895 · Cited by 105 · see citing works
“The human target-generated spectrogram of mmW radar mD signals is transferred and handled sequentially between layers [75].”
BackgroundMethodInfluentialFang, W.-C., Wang, K.-Y., Fahier, N., Ho, Y.-L., & Huang, Y.-D. (2019) · IEEE Journal on Emerging and Selected Topics in Circuits and Systems · doi:10.1109/jetcas.2019.2951232 · Cited by 86 · see citing works
Liu, X., Yang, J., Zou, C., Chen, Q., Yan, X., Chen, Y., & Cai, C. (2022) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2021.3059318 · Cited by 79 · see citing works
Sensor Fusion for Identification of Freezing of Gait Episodes Using Wi-Fi and Radar Imaging
Shah, S. A., Tahir, A., Ahmad, J. E., Zahid, A., Pervaiz, H., Shah, S. Y., Ashleibta, A. M., Hasanali, A., Khattak, S. K., & Abbasi, Q. H. (2020) · IEEE Sensors Journal · doi:10.1109/jsen.2020.3004767 · Cited by 63 · see citing works
Huang, Y., Li, W., Dou, Z., Zou, W., Zhang, A., & Li, Z. (2022) · Signals · doi:10.3390/signals3020017 · Cited by 40 · see citing works
Design of an Efficient CNN-Based Cough Detection System on Lightweight FPGA
Peng, P., Jiang, K., You, M., Xie, J., Zhou, H., Xu, W., Lu, J., Li, X., & Xu, Y. F. (2023) · IEEE Transactions on Biomedical Circuits and Systems · doi:10.1109/tbcas.2023.3236976 · Cited by 32 · see citing works
FPGA Accelerator for Human Activity Recognition Based on Radar
Long, K., Rao, C., Zhang, X., Ye, W., & Lou, X. (2023) · IEEE Transactions on Circuits & Systems II Express Briefs · doi:10.1109/tcsii.2023.3328422 · Cited by 20 · see citing works
FPGA-Based Implementation of Stochastic Configuration Network for Robotic Grasping Recognition
Pan, J., Luan, F., Gao, Y., & Wei, Y. (2020) · IEEE Access · doi:10.1109/access.2020.3012819 · Cited by 17 · see citing works
Guo, K., Liu, C., Zhao, S., Lu, J., Zhang, S., & Yang, H. (2021) · Sensors · doi:10.3390/s21237893 · Cited by 11 · see citing works
Lee, J., Song, T., He, J., Kandeepan, S., & Wang, K. (2021) · Optics Express · doi:10.1364/oe.427250 · Cited by 10 · see citing works
Ou, Z., Yu, B., & Ye, W. (2023) · IEEE Transactions on Circuits and Systems I Regular Papers · doi:10.1109/tcsi.2022.3232918 · Cited by 10 · see citing works
Saw, C. Y., & Wong, Y. C. (2023) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2023.108917 · Cited by 10 · see citing works
New Approach Based on Pix2Pix–YOLOv7 mmWave Radar for Target Detection and Classification
Lamane, M., Tabaa, M., & Klilou, A. (2023) · Sensors · doi:10.3390/s23239456 · Cited by 10 · see citing works
Hardware Acceleration for Real-Time Wildfire Detection Onboard Drone Networks
Briley, A. A., & Afghah, F. (2024) · IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS) · doi:10.1109/infocomwkshps61880.2024.10620877 · Cited by 10 · see citing works
Mathew, R. R., Mehbodniya, A., Ambalgi, A. P., Murali, M., Sahay, K. B., & Babu, D. V. (2021) · Sustainable Energy Technologies and Assessments · doi:10.1016/j.seta.2021.101731 · Cited by 9 · see citing works
RetractedJian, Y. (2020) · Microprocessors and Microsystems · doi:10.1016/j.micpro.2020.103656 · Cited by 9 · see citing works
RetractedChen, J., Lin, K., Yang, L., & Ye, W. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3422251 · Cited by 8 · see citing works
Wi-CAS: A Contactless Method for Continuous Indoor Human Activity Sensing Using Wi-Fi Devices
Hao, Z., Zhang, D., Dang, X., Liu, G., & Bai, Y. (2021) · Sensors · doi:10.3390/s21248404 · Cited by 8 · see citing works
Deep Learning-Based Human Activity Recognition With FMCW Radar: A Review
Dang, V. N., Hoang, N. C., Le, M. T., Nguyen, K. T., & Nguyen, Q. C. (2026) · IEEE Sensors Journal · doi:10.1109/jsen.2026.3651578 · Cited by 7 · see citing works
Zhou, X., & Wen, S. (2021) · Computational Intelligence and Neuroscience · doi:10.1155/2021/7006541 · Cited by 7 · see citing works
RetractedRichter, Y., & Balal, N. (2024) · Electronics · doi:10.3390/electronics13101961 · Cited by 6 · see citing works
Design of Neural Network Identification System Based on FPGA
Li, Z., zhengyan, W., & Jingcheng, S. (2019) · IEEE Advanced Information Technology, Electronic and Automation Control Conference (IAEAC) · doi:10.1109/iaeac47372.2019.8997779 · Cited by 6 · see citing works
Reg-Tune: A Regression-Focused Fine-Tuning Approach for Profiling Low Energy Consumption and Latency
Mazumder, A. N., Safavi, F., Rahnemoonfar, M., & Mohsenin, T. (2023) · ACM Transactions on Embedded Computing Systems · doi:10.1145/3623380 · Cited by 5 · see citing works
A Flexible and Low-Resource CNN Accelerator on FPGA for Edge Computing
Bai, H.-R. (2023) · International Conference on Neural Networks, Information and Communication Engineering (NNICE) · doi:10.1109/nnice58320.2023.10105734 · Cited by 5 · see citing works
On the Use of FPGAs to Implement CNNs: A Brief Review
Arshad, M., Shahriar, S., & Sagahyroon, A. A. (2020) · International Conference on Computing, Electronics & Communications Engineering (iCCECE) · doi:10.1109/iccece49321.2020.9231243 · Cited by 5 · see citing works
Li, F., Guan, Y., & Ye, W. (2024) · IEEE Transactions on Very Large Scale Integration (VLSI) Systems · doi:10.1109/tvlsi.2024.3409674 · Cited by 3 · see citing works
Steinmetz, N., & Balal, N. (2024) · Remote Sensing · doi:10.3390/rs17010091 · Cited by 3 · see citing works
FPGA Adaptive Neural Network Quantization for Adversarial Image Attack Defense
Lu, Y., Shi, X., Jiang, J., Deng, H., Wang, Y., Lu, J., & Wu, D. (2024) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2024.3438284 · Cited by 3 · see citing works
Lin, X.-Q., Lin, C.-J., Jhang, J., & Liang, S. (2025) · International Journal of Fuzzy Systems · doi:10.1007/s40815-025-02094-x · Cited by 2 · see citing works
A Low-Cost Energy-Efficient FFT-CNN Processor for Versatile mmWave Radar in IoT Applications
Chen, J., Fu, Z., & Ye, W. (2025) · IEEE Transactions on Circuits and Systems I Regular Papers · doi:10.1109/tcsi.2025.3599850 · Cited by 2 · see citing works
From cloud AI to embedded AI in cardiac healthcare
Costa, B., Postolache, O. A., & Araujo, J. (2023) · IEEE International Instrumentation and Measurement Technology Conference · doi:10.1109/i2mtc53148.2023.10176077 · Cited by 2 · see citing works
Chen, Z., Liu, P., Xu, B., Chen, Y., Zhan, W., Interdonato, G., & Buzzi, S. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3569551 · Cited by 1 · see citing works
Cho, G., Kim, S.-H., & Youn, C. (2021) · Transactions on computational science and computational intelligence · doi:10.1007/978-3-030-70296-0_49 · Cited by 1 · see citing works
A High-Performance Hardware Accelerator for Sparse Convolutional Neural Network on FPGA
Zhang, J., Xu, F., & Li, J. (2022) · IEEE International Conference on Computer and Communications (ICCC) · doi:10.1109/iccc56324.2022.10065907 · Cited by 1 · see citing works
Song, Q., He, Y., Chen, L., Xia, X., Wang, N., Song, Q., & Liu, A. (2024) · Frontiers in Physics · doi:10.3389/fphy.2024.1319678 · Cited by 1 · see citing works
A Survey Paper on Acceleration of Convolutional Neural Network using Field Programmable Gate Arrays
Doifode, J., Sadakale, R., & Patil, R. A. (2021) · International Conference on Computing, Communication and Networking Technologies (ICCCNT) · doi:10.1109/icccnt51525.2021.9580053 · Cited by 1 · see citing works
Overview of FPGA deep learning acceleration based on convolutional neural networkPreprint
Liu, S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.12634 · Cited by 1 · see citing works
A Design on Multilayer Perceptron (MLP) Neural Network for Digit Recognition
Westby, I., Koc, H., Lu, J., & Yang, X. (2021) · Transactions on computational science and computational intelligence · doi:10.1007/978-3-030-70296-0_53
Lam, D. K., Ngo, N. M., & Ngo, H. Q. T. (2023) · IET Science Measurement & Technology · doi:10.1049/smt2.12158
X-RAM: a novel and efficient multi-ported memory for AI accelerator
Xu, X., & Yao, L. (2025) · Integration · doi:10.1016/j.vlsi.2025.102592
A Precision-Scalable Energy-Efficient Accelerator for Radar-Based Human Activity Recognition
Lin, K., Li, Y., & Ye, W. (2025) · IEEE International Conference on Integrated Circuits, Technologies and Applications (ICTA) · doi:10.1109/icta68203.2025.11329782
FFT–MLP for Real‑Time Aircraft Signal Classification
Pan, S., He, B., & Cheng, Y. (2026) · Lecture notes in mechanical engineering · doi:10.1007/978-981-95-3019-9_52
CT-LNN: FPGA-Based Accelerator for Continuous-Time Liquid Neural Networks
Wang, L., Gong, Y., Xi, L., Wang, Y., Wang, Y., & Liu, W. (2026) · IEEE Transactions on Circuits and Systems I Regular Papers · doi:10.1109/tcsi.2026.3704401
- Authors
- Lei, P., Liang, J., Guan, Z., Wang, J., & Zheng, T.
- Affiliations
- Beihang University (CN)
- Venue
- IEEE Access
- Published
- 2019
- Volume
- 7
- Pages
- 88917-88926
- ISSN
- 2169-3536 (ISSN-L)
- OpenAlex
- W2953554277
- Cited by
- 44
- References
- 25
- Citations by year
- 2026: 3 · 2025: 5 · 2024: 7 · 2023: 9 · 2022: 3 · 2021: 10 · 2020: 5 · 2019: 2
- FWCI
- 5.09
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- IEEE Access (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- National Natural Science Foundation of China (61501011, 61671035)
- Topics
- Physical Sciences › Computer Science › Hardware and Architecture › Embedded Systems Design Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Engineering › Aerospace Engineering › Advanced SAR Imaging Techniques
- Keywords
- FPGA acceleration, convolutional neural networks, human activity classification, millimeter-wave radar, micro-Doppler spectrogram, parallel computing, data quantization, 77 GHz radar, embedded hardware, power consumption, automatic target recognition
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
