Millimeter-Wave Communication with Out-of-Band Information
Open accessAbstract
Configuring the antenna arrays is the main source of overhead in mmWave communication systems. In high mobility scenarios, the problem is exacerbated, as achieving the highest rates requires frequent link reconfiguration. One solution is to exploit spatial congruence between signals in different frequency bands and extract mmWave channel parameters with the aid of side information obtained in another band. In this article we propose the concept of out-of-band information aided mmWave communication. We analyze different strategies to leverage information derived from sensors or from other communication systems operating at sub-6 GHz bands to help configure the mmWave communication link. The overhead reductions that can be obtained when exploiting out-of-band information are characterized in a preliminary study. Finally, the challenges associated with using out-of-band signals as a source of side information at mmWave are analyzed in detail.
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.
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
An Overview of Signal Processing Techniques for Millimeter Wave MIMO Systems
Heath, R. W., Prelcic, N. G., Rangan, S., Roh, W., & Sayeed, A. M. (2016) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2016.2523924 · Cited by 2,917 · cited 2× · see citing works
“Several strategies for configuring the links when using different kinds of MIMO architectures have been proposed in the previous literature [3].”
MethodSelf-citationStudy and prototyping of practically large-scale mmWave antenna systems for 5G cellular devices
Hong, W., Baek, K.-H., Lee, Y.-J., Kim, Y., & Ko, S. (2014) · IEEE Communications Magazine · doi:10.1109/mcom.2014.6894454 · Cited by 562 · cited 2× · see citing works
“[1] W.”
BackgroundMillimeter Wave Beam-Selection Using Out-of-Band Spatial Information
Ali, A., Prelcic, N. G., & Heath, R. W. (2017) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2017.2773532 · Cited by 288 · cited 2× · see citing works
“A result on beam training exploiting out-of-band information [13] formulates the beam selection as a weighted sparse recovery problem.”
BackgroundSelf-citationSteering with eyes closed: Mm-Wave beam steering without in-band measurement
Nitsche, T., Flores, A. B., Knightly, E. W., & Widmer, J. (2015) · IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infocom.2015.7218630 · Cited by 287 · cited 2× · see citing works
“Initial work that proposes the use of WiFi signals at sub-6-GHz to aid the configuration of 60 GHz WiFi links [8] reports some measurements that confirm the spatial congruence between sub6-GHz and mmWave channels.”
BackgroundRadar aided beam alignment in MmWave V2I communications supporting antenna diversity
Prelcic, N. G., Méndez-Rial, R., & Heath, R. W. (2016) · Information Theory and Applications Workshop (ITA) · doi:10.1109/ita.2016.7888145 · Cited by 257 · cited 1× · see citing works
“An initial approach [14] uses ray tracing simulation to show that most of the dominant DoAs for the mmWave communication signal also appear at the radar echo in a different mmWave band.”
MethodSelf-citationOn the Feasibility of Sharing Spectrum Licenses in mmWave Cellular Systems
Gupta, A. K., Andrews, J. G., & Heath, R. W. (2016) · IEEE Transactions on Communications · doi:10.1109/tcomm.2016.2590467 · Cited by 129 · see citing works
Self-citationBeam Switching for Millimeter Wave Communication to Support High Speed Trains
Va, V., Zhang, X., & Heath, R. W. (2015) · IEEE Vehicular Technology Conference · doi:10.1109/vtcfall.2015.7390855 · Cited by 93 · cited 2× · see citing works
“It was shown in [11] that there is a tradeoff in beam width selection: very narrow beams are sensitive to position error, while wide beams provide a low antenna gain.”
BackgroundSelf-citationDownlink beamforming avoiding DOA estimation for cellular mobile communications
Aste, T., Forster, P., Féty, L., & Mayrargue, S. (2002) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.1998.679573 · Cited by 64 · cited 3× · see citing works
“[4] T.”
BackgroundInfluentialEstimating millimeter wave channels using out-of-band measurements
Ali, A., Prelcic, N. G., & Heath, R. W. (2016) · Information Theory and Applications Workshop (ITA) · doi:10.1109/ita.2016.7888146 · Cited by 64 · cited 2× · see citing works
“[10] A.”
MethodSelf-citationConversion of the Spatio-Temporal Correlation from Uplink to Downlink in FDD Systems
Jordan, M., Gong, X., & Ascheid, G. (2009) · IEEE Wireless Communications and Networking Conference · doi:10.1109/wcnc.2009.4917640 · Cited by 15 · see citing works
Frequency dependency of channel parameters in urban LOS scenario for mmwave communications
Kyösti, P., Carton, I., Karstensen, A., Fan, W., & Pedersen, G. F. (2016) · European Conference on Antennas and Propagation · doi:10.1109/eucap.2016.7481423 · Cited by 13 · see citing works
Millimeter Wave Beam-Selection Using Out-of-Band Spatial Information
Ali, A., González-Prelcic, N., & Heath, R. W. (2017) · arXiv · doi:10.48550/arxiv.1702.08574 · cited 2×
“A result on beam training exploiting out-of-band information [13] formulates the beam selection as a weighted sparse recovery problem.”
BackgroundSelf-citation
Flagged first, then by citations
Research works printed but not linked: 1
- V. Va, J. Choi, T. Shimizu, G. Bansal, and R. W. Heath Jr., "Inverse fingerprinting for millimeter wave V2I beam alignment," 2017, preprint available at http://users.ece.utexas.edu/ rheath/papers/2017/TVT2/.
Cited by
Sorted by citations
An Overview of Signal Processing Techniques for Joint Communication and Radar Sensing
Zhang, J. A., Liu, F., Masouros, C., Heath, R. W., Feng, Z., Zheng, L., & Petropulu, A. P. (2021) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2021.3113120 · Cited by 1,206 · see citing works
“This may be conceived in different ways as for example an active radar in a different frequency band co-located with the base station [45], [51], leveraging information obtained by overhearing radar signals on a device [52], or as side benefit of”
Self-citationEnabling Joint Communication and Radar Sensing in Mobile Networks—A Survey
Zhang, J. A., Rahman, M. L., Wu, K., Huang, X., Guo, Y. J., Chen, S., & Yuan, J. (2021) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2021.3122519 · Cited by 1,145 · see citing works
“Techniques exploiting the propagation information of sub-6GHz signals have been proposed for improving beamforming speed for mmWave communications in mobile networks [219].”
BackgroundA Tutorial on Beam Management for 3GPP NR at mmWave Frequencies
Giordani, M., Polese, M., Roy, A., Castor, D., & Zorzi, M. (2018) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2018.2869411 · Cited by 741 · see citing works
“[44] illustrate how to exploit spatial congruence between signals in different frequency bands and extract mmWave channel parameters”
BackgroundQuantum Machine Learning for 6G Communication Networks: State-of-the-Art and Vision for the Future
Nawaz, S. J., Sharma, S. K., Wyne, S., Patwary, M. N., & Asaduzzaman, M. (2019) · IEEE Access · doi:10.1109/access.2019.2909490 · Cited by 658 · see citing works
“At the physical layer, the technology innovations to support these data rates include communications in the mmWave frequency band [47], wherein the large bandwidth can support high data rates; M-MIMO whereby the number of antenna elements at the Base Station (BS) is much larger in proportion to the serviced users [48]…”
BackgroundDeep Learning for mmWave Beam and Blockage Prediction Using Sub-6 GHz Channels
Alrabeiah, M., & Alkhateeb, A. (2020) · IEEE Transactions on Communications · doi:10.1109/tcomm.2020.3003670 · Cited by 347 · see citing works
“Future mmWave communication systems, however, are expected to operate in multiple bands (including sub-6GHz and mmWave bands) [6], [7].”
BackgroundThe Integrated Sensing and Communication Revolution for 6G: Vision, Techniques, and Applications
Prelcic, N. G., Keskin, M. F., Kaltiokallio, O., Valkama, M., Dardari, D., Shen, X., Shen, Y., Bayraktar, M., & Wymeersch, H. (2024) · Proceedings of the IEEE · doi:10.1109/jproc.2024.3397609 · Cited by 309 · see citing works
“A wireless network that harnesses such data can improve its adaptability to changes in the propagation environment and become more resilient to channel-dependent effects such as blockage [12], [26].”
Low Earth Orbit Satellite Security and Reliability: Issues, Solutions, and the Road Ahead
Yue, P., An, J., Zhang, J., Ye, J., Pan, G., Wang, S., Xiao, P., & Hanzo, L. (2023) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2023.3296160 · Cited by 306 · see citing works
“Recently, some researchers proposed CV-aided [353], [354], [355], [356] communication schemes for mmWave or THz transmission systems in which LoS propagation is critically important.”
Shafie, A., Yang, N., Han, C., Jornet, J. M., Juntti, M. J., & Kürner, T. (2022) · IEEE Network · doi:10.1109/mnet.118.2200057 · Cited by 285 · see citing works
“, estimating the CSI of THz channels using sub-6 GHz and/or mmWave band channel measurements [13].”
Method5G MIMO Data for Machine Learning: Application to Beam-Selection Using Deep Learning
Klautau, A., Batista, P., Prelcic, N. G., Wang, Y., & Heath, R. W. (2018) · Information Theory and Applications Workshop (ITA) · doi:10.1109/ita.2018.8503086 · Cited by 234 · see citing works
“MmWave MIMO is a means to exchange sensor data in vehicular systems [37].”
BackgroundMethodSelf-citationMillimeter-Wave Communication for Internet of Vehicles: Status, Challenges, and Perspectives
Ghafoor, K. Z., Kong, L., Zeadally, S., Sadiq, A. S., Epiphaniou, G., Hammoudeh, M. A. A., Bashir, A. K., & Mumtaz, S. (2020) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.2992449 · Cited by 210 · see citing works
“One of the most popular channel tracking techniques is beam searching [59] that was developed to address mobility.”
BackgroundLIDAR Data for Deep Learning-Based mmWave Beam-Selection
Junior, A. B. D. R. K., Prelcic, N. G., & Heath, R. W. (2019) · IEEE Wireless Communications Letters · doi:10.1109/lwc.2019.2899571 · Cited by 173 · see citing works
“Compared with prior work [1]–[5], we consider LIDAR on the vehicle as an additional sensor.”
BackgroundMethodInfluentialSelf-citationAutomotive Radar Optimization Design in a Spectrally Crowded V2I Communication Environment
Yao, Y., Shu, F., Cheng, X., Liu, H., Miao, P., & Wu, L. (2023) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2023.3264507 · Cited by 169 · see citing works
Learning Radio Resource Management in RANs: Framework, Opportunities, and Challenges
Calabrese, F. D., Wang, L., Ghadimi, E., Peters, G., Hanzo, L., & Soldati, P. (2018) · IEEE Communications Magazine · doi:10.1109/mcom.2018.1701031 · Cited by 154 · see citing works
“Categorising the observations per type of cell, bandwidth, RAT, etc, may be useful, for instance, to learn coarse estimates of the channel spatial parameters at high frequencies, where the cost for observations is high in terms of radio radio resources utilization, by using out-of-band observations at lower frequency…”
BackgroundSingle-shot link discovery for terahertz wireless networks
Ghasempour, Y., Shrestha, R., Charous, A., Knightly, E. W., & Mittleman, D. M. (2020) · Nature Communications · doi:10.1038/s41467-020-15761-4 · Cited by 141 · see citing works
MmWave Vehicular Beam Selection With Situational Awareness Using Machine Learning
Wang, Y., Junior, A. B. D. R. K., Ribero, M., Soong, A. C. K., & Heath, R. W. (2019) · IEEE Access · doi:10.1109/access.2019.2922064 · Cited by 112 · see citing works
“Recently, out-of-band information aided mmWave beam training was proposed in [2], [6], [18]–[20].”
BackgroundSelf-citationJameel, F., Wyne, S., Nawaz, S. J., & Chang, Z. (2019) · IEEE Wireless Communications · doi:10.1109/mwc.2018.1800174 · Cited by 107 · see citing works
Computer Vision Aided mmWave Beam Alignment in V2X Communications
Xu, W., Gao, F., Tao, X., Zhang, J., & Alkhateeb, A. (2022) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2022.3213541 · Cited by 102 · see citing works
“Recently, integrated sensing and communication (ISAC) has drawn great attention for its capability to assist beamforming [4]-[18].”
BackgroundMmWave Beam Prediction with Situational Awareness: A Machine Learning Approach
Wang, Y., Narasimha, M., & Heath, R. W. (2018) · IEEE International Workshop on Signal Processing Advances in Wireless Communications (SPAWC) · doi:10.1109/spawc.2018.8445969 · Cited by 100 · see citing works
Self-citationDeep Learning on Multimodal Sensor Data at the Wireless Edge for Vehicular Network
Salehi, B., Reus-Muns, G., Roy, D., Wang, Z., Jian, T., Dy, J., Ioannidis, S., & Chowdhury, K. R. (2022) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2022.3170733 · Cited by 83 · see citing works
FLASH: Federated Learning for Automated Selection of High-band mmWave Sectors
Salehi, B., Gu, J., Roy, D., & Chowdhury, K. R. (2022) · IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infocom48880.2022.9796865 · Cited by 75 · see citing works
“These sensors are present in autonomous vehicles to aid in driving [5] but can also be re-purposed to optimize communication links.”
BackgroundPosition and LIDAR-Aided mmWave Beam Selection using Deep Learning
Dias, M. V. D. O., Junior, A. B. D. R. K., Prelcic, N. G., & Heath, R. W. (2019) · IEEE International Workshop on Signal Processing Advances in Wireless Communications (SPAWC) · doi:10.1109/spawc.2019.8815569 · Cited by 74 · see citing works
“Most prior work in machine learning-based beam selection for mmWave systems has used the position information obtained from vehicles [1], [3]–[9].”
BackgroundSelf-citationSub-6GHz Assisted MAC for Millimeter Wave Vehicular Communications
Coll-Perales, B., Gozálvez, J., & Gruteser, M. (2019) · IEEE Communications Magazine · doi:10.1109/mcom.2019.1800509 · Cited by 71 · see citing works
Towards mmWave V2X in 5G and Beyond to Support Automated Driving
Sakaguchi, K., Fukatsu, R., Yu, T., Fukuda, E., Mahler, K., Heath, R. W., Fujii, T., Takahashi, K., Khoryaev, A., Nagata, S., et al. (2020) · IEICE Transactions on Communications · doi:10.1587/transcom.2020ebi0001 · Cited by 69 · see citing works
“As a result, research has targeted specific challenges related to mmWave for V2X such as position-aided beam training via machine learning [20] and sensor-aided beam training [21][22].”
BackgroundMethodSelf-citationAn Efficient Uplink Multi-Connectivity Scheme for 5G Millimeter-Wave Control Plane Applications
Giordani, M., Mezzavilla, M., Rangan, S., & Zorzi, M. (2018) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2018.2864650 · Cited by 63 · see citing works
“, [24], [25]) illustrate how to exploit spatial congruence between signals in different frequency bands to extract channel parameters in mm-waves from side information obtained in another band.”
BackgroundHaider, M. K., Ghasempour, Y., Koutsonikolas, D., & Knightly, E. W. (2018) · ACM Annual International Conference on Mobile Computing and Networking (MobiCom) · doi:10.1145/3241539.3241542 · Cited by 55 · see citing works
“, via session transfer to legacy bands [25, 31], AoA estimation in sub 6-GHz bands to eliminate exhaustive search for beam acquisition [22], and using sensors on mobile devices [5, 8, 26, 40].”
Gao, F., Lin, B., Bian, C., Zhou, T., Qian, J., & Wang, H. (2021) · IEEE Transactions on Communications · doi:10.1109/tcomm.2021.3110301 · Cited by 50 · see citing works
“Details can be found in [12] and will not be further expanded here.”
BackgroundMethodPartially Blind Handovers for mmWave New Radio Aided by Sub-6 GHz LTE Signaling
Mismar, F. B., & Evans, B. L. (2018) · IEEE International Conference on Communications workshops · doi:10.1109/iccw.2018.8403587 · Cited by 49 · see citing works
Millimeter Wave V2X Communications: Use Cases and Design Considerations of Beam Management
Shimizu, T., Va, V., Bansal, G., & Heath, R. W. (2018) · 2018 Asia-Pacific Microwave Conference (APMC) · doi:10.23919/apmc.2018.8617303 · Cited by 48 · see citing works
“We can leverage that sensor information to facilitate beam tracking and reduce the overhead of beam tracking [3], [13].”
Self-citationMmWave Vehicular Beam Training with Situational Awareness by Machine Learning
Wang, Y., Junior, A. B. D. R. K., Ribero, M., Narasimha, M., & Heath, R. W. (2018) · IEEE Globecom Workshops (GC Wkshps) · doi:10.1109/glocomw.2018.8644288 · Cited by 39 · see citing works
“Vehicles are also being equipped with sensors like satellite navigation, radar, LiDAR, and cameras which can be used to localize vehicles and sense the environment [1], [3].”
BackgroundSelf-citationGraff, A., Chen, Y., Prelcic, N. G., & Shimizu, T. (2023) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2023.3239227 · Cited by 37 · see citing works
“Out-of-band information to aid mmWave communication [2] can come from several sources, including sub-6 GHz systems [5], [6], [7], or sensors such as radar [3], [8], [9], [10], lidar [11], [12], inertial-measurement-units [13], [14], or position information [15], [16], [17].”
BackgroundEnabling Joint Communication and Radio Sensing in Mobile Networks -- A SurveyPreprint
Rahman, L., Zhang, J. A., Wu, K., Huang, X., Guo, Y. J., Chen, S., & Yuan, J. (2020) · arXiv (Cornell University) · Cited by 37 · see citing works
Augmenting mmWave localization accuracy through sub-6 GHz on off-the-shelf devices
Blanco, A., Mateo, P. J., Gringoli, F., & Widmer, J. (2022) · International Conference on Mobile Systems, Applications, and Services · doi:10.1145/3498361.3538920 · Cited by 36 · see citing works
“The most common use case is to reduce the mmWave beam-training overhead with the help of sub-6 GHz information [11, 28, 36, 41] to infer the optimal steering direction of themmWave antenna array.”
BackgroundPredicting Device-to-Device Channels From Cellular Channel Measurements: A Learning Approach
Najla, M., Bečvář, Z., Mach, P., & Gesbert, D. (2020) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2020.3008303 · Cited by 36 · see citing works
Li, Z., Yu, T., Fukatsu, R., Tran, G. K., & Sakaguchi, K. (2021) · IEEE Open Journal of Vehicular Technology · doi:10.1109/ojvt.2021.3049783 · Cited by 36 · see citing works
Vuckovic, K., Mashhadi, M. B., Hejazi, F., Rahnavard, N., & Alkhateeb, A. (2023) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2023.3324916 · Cited by 33 · see citing works
“Thus, the received signal at the UE antenna array at the l th subcarrier turns out to be [40] where is the precoder vector at the BS and n mm [ l ] ∈ N (0 , ( σ mm ) 2 ) is the noise.”
BackgroundDeep Learning Predictive Band Switching in Wireless Networks
Mismar, F. B., AlAmmouri, A., Alkhateeb, A., Andrews, J. G., & Evans, B. L. (2020) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2020.3023397 · Cited by 32 · see citing works
“ncy band to another without explicitly measuring the channel at the target frequency band falls under the genre of problems commonly referred to as: “channel estimation using out-of-band information” [6]. In the simplest form of this problem, there are forward and backward (downlink and uplink) links occupying the sam…”
MethodDeep Reinforcement Learning Based Dynamic Beam Selection in Dual-Band Communication Systems
Zhang, Z., Zhang, J., Zhang, Y., Yu, L., Gao, F., Shi, Q., Liu, G., Yuan, Z., & Fan, W. (2023) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2023.3300830 · Cited by 31 · see citing works
“The sub-6 GHz systems operating in parallel can be a good source of free OOB information to aid in establishing the mmWave link [11].”
BackgroundMethodSelf-Supervised Deep Learning for mmWave Beam Steering Exploiting Sub-6 GHz Channels
Chafaa, I., Negrel, R., Belmega, E. V., & Debbah, M. A. (2022) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2022.3170104 · Cited by 31 · see citing works
“Other approaches estimate the channel parameters, such as the propagation path gains and angles of departure, and use them to construct beam-forming vectors to steer the beams [7]–[9].”
BackgroundLiu, F., Zhu, H., Li, C., Li, J., Wang, P., & Orlik, P. V. (2020) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2020.2966003 · Cited by 29 · see citing works
“It is shown in [30] that the out-of-band information (mainly the angular information) extracted by the sub 6-GHz communication systems can provide useful channel characteristics for mmWave band channels.”
BackgroundMillimeter-Wave V2X Channels: Propagation Statistics, Beamforming, and Blockage
Anjinappa, C. K., & Güvenç, İ. (2018) · IEEE Vehicular Technology Conference · doi:10.1109/vtcfall.2018.8690733 · Cited by 28 · see citing works
Multi-Domain Cooperative SLAM: The Enabler for Integrated Sensing and Communications
Yang, J., Wen, C.-K., Yang, X., Xu, J., Du, T., & Jin, S. (2023) · IEEE Wireless Communications · doi:10.1109/mwc.006.2200217 · Cited by 28 · see citing works
“For example, mmWave/THz transceivers can observe a single specular path associated with a VA, whereas sub-6 GHz transceivers obtain a batch of clustered paths.”
BackgroundInfluentialDeep Learning on Visual and Location Data for V2I mmWave Beamforming
Reus-Muns, G., Salehi, B., Roy, D., Jian, T., Wang, Z., Dy, J., Ioannidis, S., & Chowdhury, K. R. (2021) · International Conference on Mobility, Sensing and Networking (MSN) · doi:10.1109/msn53354.2021.00087 · Cited by 27 · see citing works
“While such capabilities are widely exploited for assisted and autonomous driving, they have been under-explored in other domains that could also leverage from context-aware information, such as wireless communications [1].”
On the Feasibility of Out-of-Band Spatial Channel Information for Millimeter-Wave Beam Search
Kyösti, P., Zhang, P., Pärssinen, A., Haneda, K., Koivumäki, P., & Fan, W. (2023) · IEEE Transactions on Antennas and Propagation · doi:10.1109/tap.2023.3249837 · Cited by 26 · see citing works
“with reduced training overhead [11], [12], that is, extracting easily available coarse angular information with low-frequency antenna systems and using it to initialize beam search at the”
Angular and Temporal Correlation of V2X Channels across Sub-6 GHz and mmWave Bands
Anjinappa, C. K., & Güvenç, İ. (2018) · IEEE International Conference on Communications workshops · doi:10.1109/iccw.2018.8403779 · Cited by 25 · see citing works
Computer Vision-Aided mmWave UAV Communication Systems
Hua, Z., Lu, Y., Pan, G., Gao, K., da Costa, D. B., & Chen, S. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3251377 · Cited by 25 · see citing works
“LoS delivery can easily be offered by aerial-to-ground links, mmWave communications via aerial platforms have arisen as a major research direction to implement mmWave transmission systems in practice [3], [4], [5].”
BackgroundNear-Field Channel Estimation in Dual-Band XL-MIMO With Side Information-Assisted Compressed Sensing
Wu, H., Lu, L., & Wang, Z. (2024) · IEEE Transactions on Communications · doi:10.1109/tcomm.2024.3445282 · Cited by 24 · see citing works
“On the other hand, high-frequency systems are likely to be deployed at the same location as lower-frequency systems, giving rise to out-of-band spatial information [14], [15].”
BackgroundA Low-Cost Millimeter-Wave 5G V2X Multi-Beam Dual-Polarized Windshield Antenna
Nasr, A. M. H., & Sarabandi, K. (2022) · IEEE Open Journal of Antennas and Propagation · doi:10.1109/ojap.2022.3224807 · Cited by 24 · see citing works
“These include the use of out of band information [2] or machine learning algorithms [3].”
MethodAnalysis of Blockage Sensing by Radars in Random Cellular Networks
Park, J., & Heath, R. W. (2018) · IEEE Signal Processing Letters · doi:10.1109/lsp.2018.2869279 · Cited by 24 · see citing works
“For example, knowledge of blockages is side information for reconfiguring mmWave communications beams [1], [2].”
BackgroundSelf-citationJoint Scheduling and Precoding for mmWave and Sub-6GHz Dual-Mode Networks
Cheng, M., Wang, J.-B., Cheng, J., Wang, J., & Lin, M. (2020) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2020.3021012 · Cited by 23 · see citing works
“The current research on mmWave and μ Wave networks mainly focus on system configuration [16], [19]–[21], system-level performance evaluation [13], [14], [22]–[24] and resource allocation [15], [25], [26].”
BackgroundHarnessing Multimodal Sensing for Multi-User Beamforming in mmWave Systems
Patel, K., & Heath, R. W. (2024) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2024.3475950 · Cited by 22 · see citing works
Self-citationFast Position-Aided MIMO Beam Training via Noisy Tensor Completion
Chou, T.-H., Michelusi, N., Love, D. J., & Krogmeier, J. V. (2021) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2021.3063837 · Cited by 21 · see citing works
Site-Specific Online Compressive Beam Codebook Learning in mmWave Vehicular Communication
Wang, Y., Myers, N. J., Prelcic, N. G., & Heath, R. W. (2021) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2020.3047547 · Cited by 21 · see citing works
“Side information, ubiquitous in vehicular communication, can be exploited for efficient mmWave channel estimation or beam alignment [8]–[13].”
BackgroundSelf-citationContext-Aware Beam Tracking for 5G mmWave V2I Communications
Ding, H., & Shin, K. G. (2021) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2021.3137957 · Cited by 20 · see citing works
“Similar ideas have also been pursued in [16] and [17], where the channel information obtained from sensors or sub-6 GHz bands is used for fast beam selection.”
BackgroundMulti-Beam Transmission and Dual-Band Cooperation for Control/Data Plane Decoupled WLANs
Zhou, P., Fang, X., Wang, X., & Yan, L. (2019) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2019.2933543 · Cited by 20 · see citing works
“To alleviate this problem, intelligent beam management mechanisms [8]–[10], dense deployment strategies of mmWave base stations (BS) [10]–[14] and sub-6GHz and mmWave dual-band cooperation (also called “HF & LF cooperation” in this paper) technologies [15]–[17] have been studied.”
BackgroundMulti-User Matching and Resource Allocation in Vision Aided Communications
Xu, W., Gao, F., Zhang, Y., Pan, C., & Liu, G. (2023) · IEEE Transactions on Communications · doi:10.1109/tcomm.2023.3274162 · Cited by 19 · see citing works
“With the progressive development of intelligent business, such as intelligent transportation and autonomous driving, abundant types of sensors, including Radar, LIDAR and Depth/RGB cameras, will be mounted on the communications equipment or the infrastructures [3]-[4].”
BackgroundLearning Radio Resource Management in 5G Networks: Framework, Opportunities and ChallengesPreprint
Calabrese, F. D., Wang, L., Ghadimi, E., Peters, G., & Soldati, P. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.10253 · Cited by 19 · see citing works
“f-band observations at lower frequency bands, such as communication systems operating at sub-6GHz bands, sensors and positioning information, which are available with lower radio resource utilization [12]. E. Scalability In addition to scaling well with the large dimensionality and complexity of the RRM problems, the…”
BackgroundMulti-Camera Views Based Beam Searching and BS Selection With Reduced Training Overhead
Lin, B., Gao, F., Zhang, Y., Pan, C., & Liu, G. (2024) · IEEE Transactions on Communications · doi:10.1109/tcomm.2024.3351748 · Cited by 18 · see citing works
“To further reduce the beam searching overhead, some out-of-band information has been introduced into the communications systems [8], [9], [10].”
BackgroundCost-Efficient Millimeter Wave Base Station Deployment in Manhattan-Type Geometry
Dong, M., Kim, T., Wu, J., & Wong, E. W. M. (2019) · IEEE Access · doi:10.1109/access.2019.2947637 · Cited by 18 · see citing works
“In what follows, we focus on the computation of p((1)) Uo|Cj , j ∈ [1, J ], keeping in mind that the exactly same approach can be applied to the calculations of p Uo|Cj , i∈ [2, 4].”
BackgroundMethodYan, L., Fang, X., Wang, X., & Ai, B. (2020) · IEEE Vehicular Technology Magazine · doi:10.1109/mvt.2020.2969528 · Cited by 18 · see citing works
“[12], by leveraging the spatial congruence between sub-6-GHz and mm-wave bands in multiconnectivity systems, proposed the concept of outof-band information-aided mm-wave communication, where the channel-angular information of sub-6 GHz is referred to reduce the beam-searching space in mmwave bands.”
BackgroundLi, Z., Zhang, C., Lu, I., & Jia, X. (2020) · IEEE Access · doi:10.1109/access.2020.2979712 · Cited by 18 · see citing works
“The overhead of mmWave communication systems mainly comes from the antenna array configuration [33].”
BackgroundHu, Y., Yin, M., Xia, W., Rangan, S., & Mezzavilla, M. (2022) · Asilomar Conference on Signals, Systems and Computers (ACSSC) · doi:10.1109/ieeeconf56349.2022.10052063 · Cited by 17 · see citing works
“There has also been active research in leveraging information from lower frequencies for communication in the mmWave and THz bands for procedures such as beam search [6], [7], [8], and localization and sensing [9].”
Background$\text{Omni-CNN}$: A Modality-Agnostic Neural Network for mmWave Beam Selection
Salehi, B., Roy, D., Jian, T., Dick, C., Ioannidis, S., & Chowdhury, K. R. (2024) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2024.3351053 · Cited by 17 · see citing works
“To speed up the beam selection, vehicle mounted sensors like GPS (Global Positioning System), cameras, and LiDAR (Light Detection and Ranging) can be used to identify the optimum mmWave beam [10].”
MethodBeam-Selection for 5G/B5G Networks Using Machine Learning: A Comparative Study
Chatzoglou, E., & Goudos, S. K. (2023) · Sensors · doi:10.3390/s23062967 · Cited by 17 · see citing works
Optimization of 5G base station coverage based on self-adaptive mutation genetic algorithm
Li, J., Pang, J., & Fan, X. (2024) · Computer Communications · doi:10.1016/j.comcom.2024.07.002 · Cited by 16 · see citing works
LSTM-Based Predictive mmWave Beam Tracking via Sub-6 GHz Channels for V2I Communications
Zhao, Y., Zhang, X., Gao, X., Yang, K., Xiong, Z., & Han, Z. (2024) · IEEE Transactions on Communications · doi:10.1109/tcomm.2024.3395297 · Cited by 15 · see citing works
“…access points [28], [29], in two scenarios, i.e., (a) co-located scenario where the sub-6 GHz and mmWave transceivers are co-located on the same BS [30], and (b) Het-Net scenario where one sub-6 GHz and several mmWave BSs are deployed separately but connected through X2 backhaul links [31], [32],…”
BackgroundMmWave Codebook Selection in Rapidly-Varying Channels via Multinomial Thompson Sampling
Zhang, Y., Basu, S., Shakkottai, S., & Heath, R. W. (2021) · ACM International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing (MobiHoc) · doi:10.1145/3466772.3467044 · Cited by 15 · see citing works
“Some work exploits a priori knowledge of the channel to avoid exhausted beam search [15, 18, 29, 35, 42].”
BackgroundSelf-citationOut-of-Band Information Aided mmWave/THz Beam Search: A Spatial Channel Similarity Perspective
Zhang, P., Kyösti, P., Haneda, K., Koivumäki, P., Lyu, Y., & Fan, W. (2022) · IEEE Communications Magazine · doi:10.1109/mcom.001.2200398 · Cited by 15 · see citing works
“m ultI -b And s pAtIAl c hAnnel s ImIlArIty this section, we introduce two proposed metrics to measure the spatial similarity of multi-band radio channels.”
BackgroundSalehi, B., Roy, D., Gu, J., Dick, C., & Chowdhury, K. R. (2024) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2024.3401046 · Cited by 14 · see citing works
“Thus, the locations of the Tx, Rx, and potential obstacles play an important role in the sector selection process [6], [7].”
A Message Passing Approach to Acquire mm-Wave Channel State Information Based on Out-of-Band Data
Xiu, Y., Wang, W., & Zhang, Z. (2018) · IEEE Access · doi:10.1109/access.2018.2855688 · Cited by 14 · see citing works
“To be specific, millimeter wave (mm-wave) frequency has recently caused significant concern owing to the expansion of bandwidth [1]–[4].”
BackgroundMethodInfluentialZhang, Q., Ji, K., Feng, Z., Han, Z., & Gao, H. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3181247 · Cited by 13 · see citing works
“…order to reduce the beam search overhead, a multiband aggregation method is proposed to assist mmWave beam alignment with the weighted spatial information using dedicated short-range communication (DSRC), where the spatial consistency between mmWave and Sub-6-GHz bands is analyzed in [31] and [32].”
MethodTowards Robustness: Machine Learning for MmWave V2X with Situational Awareness
Wang, Y., Narasimha, M., & Heath, R. W. (2018) · Asilomar Conference on Signals, Systems and Computers (ACSSC) · doi:10.1109/acssc.2018.8645370 · Cited by 12 · see citing works
“Side information is valuable in reducing the overheads associated with mmWave vehicular beam training [5].”
BackgroundSelf-citationSide-information-aided Noncoherent Beam Alignment Design for Millimeter Wave Systems
Zhang, Y., Patel, K., Shakkottai, S., & Heath, R. W. (2019) · ACM International Symposium on Mobile Ad Hoc Networking and Computing (MobiHoc) · doi:10.1145/3323679.3326532 · Cited by 12 · see citing works
“To reduce the beam training overhead, one promising solution is to leverage side information from available sensors to infer the channel prior to performing any training [12].”
BackgroundSelf-citationBandit Inspired Beam Searching Scheme for mmWave High-Speed Train CommunicationsPreprint
Wang, J.-B., Cheng, M., Wang, J., Lin, M., Wu, Y., Zhu, H., & Wang, J. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1810.06150 · Cited by 11 · see citing works
“Out-of-band side information, such as data from sensors and other communications and congruency between the channels at mmWave and sub-6 GHz bands, are leveraged to assist beam training and channel estimation in [20] and [21], respectively.”
BackgroundIntegrated Sensing and Communication with Multi-Domain CooperationPreprint
Yang, J., Yang, X., Wen, C.-K., & Jin, S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.03065 · Cited by 11 · see citing works
“…example, although the mmWave massive multi-input multi-output network has high sensing resolution, its coverage is limited, sub-6 GHz can ensure reliable links to assist mmWave, wireless local area networks (WLANs) and sensor networks can also provide side information to mmWave networks [12], [13].”
BackgroundNabil, Y., ElSawy, H., Al-Dharrab, S. I., Mostafa, H., & Attia, H. (2024) · IEEE Access · doi:10.1109/access.2024.3365631 · Cited by 10 · see citing works
“This information is utilized to limit the beam search space [3], [4], [5], [6].”
BackgroundMethodInfluentialZhao, Y., Zhang, X., Gao, X., Yang, K., Xiong, Z., Han, Z., & Lu, J. (2025) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2025.3632415 · Cited by 10 · see citing works
“In this paper, we investigate dual-connectivity multi-cell multi-user MISO interference networks, where the mobile users are served by both sub-6 GHz and mmWave transceivers located at the same BS [18], [20], [28].”
Rate and Outage Probability in Dual Band Systems With Prediction-Based Band Switching
Burghal, D., & Molisch, A. F. (2018) · IEEE Wireless Communications Letters · doi:10.1109/lwc.2018.2833860 · Cited by 10 · see citing works
“Due to this reason, as well as requirements for backward compatibility, next generation wireless networks are anticipated to use both centimeter-wave (cm-wave) band and mm-wave frequency bands [1], [2].”
MethodBand Assignment in Dual Band Systems: A Learning-Based Approach
Burghal, D., Wang, R., & Molisch, A. F. (2018) · IEEE Military Communications Conference (MILCOM) · doi:10.1109/milcom.2018.8599747 · Cited by 11 · see citing works
“To gain the advantages of both bands, next-generation wireless networks are anticipated to use both frequency bands [3], [4].”
BackgroundTUNE: Transfer Learning in Unseen Environments for V2X mmWave Beam Selection
Gu, J., Salehi, B., Pimple, S., Roy, D., & Chowdhury, K. R. (2023) · International Conference on Communications · doi:10.1109/icc45041.2023.10279177 · Cited by 10 · see citing works
“Exploitation of multimodal sensing data to reduce aspects of mmWave communication has been widely researched [6], [7], [8], [9].”
BackgroundBurghal, D., Wang, R., Alghafis, A., & Molisch, A. F. (2022) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2022.3159762 · Cited by 10 · see citing works
“the system could rely on the correlation and the joint characteristics of the two bands [6], [14].”
Communication-Aware DNN Pruning
Jian, T., Roy, D., Salehi, B., Soltani, N., Chowdhury, K. R., & Ioannidis, S. (2023) · IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infocom53939.2023.10229043 · Cited by 10 · see citing works
“We also validate CaP on a publicly available real-world dataset 6 of multimodal beamforming [44], [45] in a vehicle to infrastructure (V2I) scenario, as depicted in Fig.”
MethodChannel Estimation for mmWave MIMO Using Sub-6 GHz Out-of-Band Information
Pasic, F., Hofer, M., Mussbah, M., Caban, S., Schwarz, Š., Zemen, T., & Mecklenbräuker, C. F. (2024) · International Conference on Smart Applications, Communications and Networking (SmartNets) · doi:10.1109/smartnets61466.2024.10577648 · Cited by 9 · see citing works
“The main challenge in using mmWave frequency bands is link establishment, which is done by designing the precoder and combiner [4].”
BackgroundMajid, S. I., Shah, S. W., & Marwat, S. N. K. (2020) · Electronics · doi:10.3390/electronics9040545 · Cited by 8 · see citing works
Similarity of Wireless Multiband Propagation in Urban Vehicular-to-Infrastructure Scenarios
Hofer, M., Löschenbrand, D., Pasic, F., Radovic, D., Rainer, B., Blumenstein, J., Mecklenbräuker, C. F., Sangodoyin, S., Hammoud, H., Matz, G., et al. (2024) · IEEE International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC) · doi:10.1109/pimrc59610.2024.10817364 · Cited by 7 · see citing works
Attitude Information Aided Digital Beamforming in Millimeter-Wave MIMO Systems
Zhou, S., Chen, L., & Wang, W. (2021) · IEEE Systems Journal · doi:10.1109/jsyst.2021.3092430 · Cited by 7 · see citing works
“In order to reduce the training overhead, some studies utilize out-of-band information from sensors or other communication systemsoperatingatsub-6-GHzfrequenciestoaidmmWavelink establishmentandbeamforming[14],[15].”
BackgroundDeep Learning and Gaussian Process based Band Assignment in Dual Band Systems.Preprint
Burghal, D., Wang, R., & Molisch, A. F. (2019) · arXiv (Cornell University) · Cited by 6 · see citing works
Positioning-Aided Channel Estimation for Multi-LEO Satellite Cooperative Beamforming
Zhang, Y., Zheng, P., Ma, J., Wymeersch, H., & Al-Naffouri, T. Y. (2026) · IEEE Transactions on Communications · doi:10.1109/tcomm.2026.3658404 · Cited by 6 · see citing works
“The role of position information in terrestrial networks has been widely recognized for enhancing communication performance [25], [26], [27], [28], [29].”
A Comprehensive Study of Low Frequency and High Frequency Channel Correlation
Mateo, P. J., Blanco, A., Ludant, N., Borelli, M. M., García-García, A., Loch, A., Shi, Z., Wang, Y., & Widmer, J. (2019) · 2012 International Conference on Computing, Networking and Communications (ICNC) · doi:10.1109/iccnc.2019.8685565 · Cited by 6 · see citing works
“Going one step further, the authors in [6], [7] propose inferring spatial correlation matrices in mmWave channels from the LF Channel State Information (CSI).”
BackgroundGeometric Tracking of Vehicular mmWave Channels to Enable Machine Learning of Onboard Sensors
Zöchmann, E., Va, V., Rupp, M., & Heath, R. W. (2018) · IEEE Globecom Workshops (GC Wkshps) · doi:10.1109/glocomw.2018.8644440 · Cited by 6 · see citing works
“The concept of using external information for improved channel estimation was recently re-introduced, see [26], [27] and the reference therein.”
BackgroundSelf-citationSimulation of machine learning-based 6G systems in virtual worlds
Oliveira, A., Bastos, F., Trindade, I., Frazão, W., Nascimento, A., Gomes, D. D. A., M�ller, F., & Junior, A. B. D. R. K. (2021) · ITU Journal on Future and Evolving Technologies · doi:10.52953/sjas4492 · Cited by 6 · see citing works
“Beam selection is a classical application of AI/ML to communications [20, 21, 22].”
BackgroundSensing-Aided Precoding With High-Dynamic Moving Scatterers
Lin, L., Zhou, C., Zheng, H., Shi, Z., Vorobyov, S. A., & Heath, R. W. (2025) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2025.3587089 · Cited by 5 · see citing works
“Additionally, the spatial correlation can also be used to facilitate beam configuration [25].”
Self-citationMillimeter Wave MIMO Channel Estimation Using Sub-6 GHz Out-of-Band Information
Pasic, F., Hofer, M., Mussbah, M., Sangodoyin, S., Caban, S., Schwarz, S., Zemen, T., Rupp, M., Molisch, A. F., & Mecklenbräuker, C. F. (2025) · IEEE Transactions on Communications · doi:10.1109/tcomm.2025.3588591 · Cited by 5 · see citing works
“However, the main challenge in utilizing antenna arrays is link establishment, which is achieved through either beam selection or channel estimation [25].”
FineAP: Fine-Grained Access Point Deployment Strategy for 60 GHz Millimeter-Wave Wireless Networks
Yang, Y., Zhou, A., & Ma, H. (2022) · IEEE Communications Letters · doi:10.1109/lcomm.2022.3213578 · Cited by 5 · see citing works
“There are typically three methods in mmWave local area network (LAN) to get over obstructions and maintain the LOS path open: (i) Using WiFi with several bands [1], [2].”
MethodNerini, M., & Clerckx, B. (2023) · IEEE Wireless Communications Letters · doi:10.1109/lwc.2023.3235154 · Cited by 5 · see citing works
“To select the optimal precoder in mmWave, sub-6GHz band signaling has been used in [3], [4].”
MethodLiang, J., Li, K., Zhang, Q., & Qi, Z. (2022) · Applied Sciences · doi:10.3390/app12094779 · Cited by 5 · see citing works
Machine Learning Enhanced CSI Acquisition and Training Strategy for FDD Massive MIMO
Song, N., & Yang, T. (2021) · IEEE Wireless Communications and Networking Conference · doi:10.1109/wcnc49053.2021.9417500 · Cited by 5 · see citing works
“The channel is generated according to [17], [18] at 2.15 GHz.”
BackgroundInfluentialHigh‐Capacity Millimeter Wave UAV Communications
Prelcic, N. G., Heath, R. W., Rusu, C., & Junior, A. B. D. R. K. (2020) · doi:10.1002/9781119575795.ch8 · Cited by 5 · see citing works
Self-citationBeam Training in mmWave Vehicular Systems: Machine Learning for Decoupling Beam Selection
Kilinç, İ., Dreifuerst, R. M., Kim, J.-H., & Heath, R. W. (2024) · IEEE International Black Sea Conference on Communications and Networking · doi:10.1109/blackseacom61746.2024.10646235 · Cited by 4 · see citing works
“Codebook-based beam training is one approach for con-figuring mmWave MIMO links by transmitting and receiving with each beamforming codeword-pair in highly dynamic vehicular environments [2], [3].”
BackgroundSelf-citationLearning-based blockage prediction for robust links in dynamic millimeter wave networks
Zarifneshat, M., Xiao, L., Tang, J., & Zhang, X. (2021) · Wireless Networks · doi:10.1007/s11276-021-02759-z · Cited by 4 · see citing works
Zhou, Z., Zhang, L., Wang, C., Huang, J., & Xin, L. (2024) · IEEE/CIC International Conference on Communications in China (ICCC) · doi:10.1109/iccc62479.2024.10681962 · Cited by 3 · see citing works
“In light of this, some researchers proposed a multi-frequency collaboration approach, wherein the out-of-band CSI is employed to assist in beam searching at the target frequency band, thereby reducing pilot overhead and enhancing spectral efficiency [8], [9].”
- Authors
- Gonzalez-Prelcic, N., Ali, A., Va, V., & Heath, R. W.
- Affiliations
- The University of Texas at Austin (US)
- Venue
- IEEE Communications Magazine
- Published
- 2017-12
- Volume
- 55
- Issue
- 12
- Pages
- 140-146
- ISSN
- 0163-6804 (ISSN-L)
- OpenAlex
- W2605150011
- Cited by
- 137
- References
- 11
- Citations by year
- 2026: 7 · 2025: 10 · 2024: 20 · 2023: 17 · 2022: 16 · 2021: 15 · 2020: 16 · 2019: 11 · 2018: 23 · 2017: 1 · 2016: 1
- FWCI
- 5.79
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE Communications Magazine (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Science Foundation (1319556)
- U.S. Department of Transportation
- European Regional Development Fund (TEC2016- 75103-C2-2-R)
- Topics
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Millimeter-Wave Propagation and Modeling
- Physical Sciences › Engineering › Aerospace Engineering › Radar Systems and Signal Processing
- Physical Sciences › Engineering › Aerospace Engineering › Antenna Design and Analysis
- Keywords
- millimeter-wave communication, antenna array configuration, high mobility, spatial congruence, side information, channel parameter estimation, sub-6 GHz, overhead reduction
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
