IP Library › Granted Patent US 12,578,415
Granted Patent B2
US 12,578,415 · App. 18/040,330 · Granted Mar 17, 2026

LOS training dataset imbalance detection

Inventors: Oana-Elena Barbu (Aalborg, DK); Zexian Li (Espoo, FI); István Zsolt Kovács (Aalborg, DK)
Assignee: Nokia Technologies Oy
G01S5/0218G06N20/00
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,578,415
App. No.
18/040,330
Granted
Mar 17, 2026
Kind
B2
Abstract

There is provided a method for a UE of a wireless communication system, the method comprising: detecting an imbalance in a line-of-sight, LOS, training dataset for training a LOS detector; determining a minority class of the LOS training dataset associated with the detected imbalance; transmitting, to a network element of the wireless communication system, a request message indicating the determined minority class and requesting measurement activation to perform one or more measurements, by the UE, to obtain one or more additional signal samples for the minority class; and receiving, from the network element, an activation message causing the UE to perform the one or more measurements during a configured observation window.

Claims (54)

1 . An apparatus comprising:

at least one processor; and

at least one memory including computer program code, the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus to:

detect an imbalance in a line-of-sight, LOS, training dataset for training a LOS detector;

determine a minority class of the LOS training dataset associated with the detected imbalance;

transmit, to a network element of a wireless communication system, a request message indicating the determined minority class and requesting measurement activation to perform one or more measurements to obtain one or more additional signal samples for the minority class; and

receive, from the network element, an activation message causing the apparatus to perform the one or more measurements during a configured observation window,

wherein the at least one memory and the computer program code are further configured to, with the at least one processor, cause the apparatus to:

obtain the one or more additional signal samples for the minority class; and after obtaining the one or more additional signal samples, retraining the LOS detector with the LOS training set,

wherein the activation message comprises observation window configuration information,

wherein the observation window configuration information indicates a duration of the observation window and a start time of the observation window relative to an index of a subframe carrying a predetermined message or relative to a system frame number,

wherein the predetermined message is the request message and the subframe is an uplink subframe, or the predetermined message is the activation message and the subframe is a downlink subframe.

2 . The apparatus of claim 1 , wherein the at least one memory and the computer program code are further configured to, with the at least one processor, cause the apparatus to:

detect class imbalance if the following conditions are fulfilled:

the size of any class in the training dataset is less than a percentage of the size of a majority class,

the size of any class is less than a percentage of the size of the majority class, after untrustworthy signal samples have been discarded or removed,

untrustworthy measurements comprise signal samples having SNR exceeding a threshold, signal samples having RL exceeding a RL threshold, and signal samples having Doppler shift exceeding a threshold, and

the size of any class is less than a given percentage of the size of the majority class and Δt has passed since the latest signal sample has been collected.

3 . The apparatus of claim 1 , wherein the at least one memory and the computer program code are further configured to, with the at least one processor, cause the apparatus to:

after a class imbalance is detected, send to the network a reconfiguration request for obtaining new channel signal samples belonging to the minority class;

report, to the network element, the severity of the class imbalance comprising an imbalance ratio, an indicator of the imbalance and of the relative sizes of the different class signal samples;

determine the severity of the imbalance by determining how many additional signal samples for the minority class is required to at least reduce the imbalance to an acceptable level, the acceptable level being network configured or preconfigured, or determined by the LOS detector).

4 . The apparatus of claim 1 , wherein the at least one memory and the computer program code are further configured to, with the at least one processor, cause the apparatus to:

receiving, from the network element, a configuration message comprising observation window configuration information.

5 . The apparatus of claim 4 , wherein the signal samples may directly indicate and comprise parameters and indicators that include at least signal power, received signal strength indicator (RSSI), signal-to-noise-plus-interference-ratio (SINR), signal-to-noise-ratio (SNR), Doppler shift, channel impulse response and power delay power.

6 . The apparatus of claim 5 , wherein the at least one memory and the computer program code are further configured to, with the at least one processor cause the apparatus to:

collect the signal samples by performing measurements in the configured observation window;

tag the signal samples with a corresponding class label;

timestamps the signal samples; and

buffer the signal samples internally.

7 . The apparatus of claim 1 , wherein the request message further comprises a severity indicator being indicative of a severity of the imbalance.

8 . The apparatus of claim 1 , wherein the at least one memory and the computer program code are further configured to, with the at least one processor, cause the apparatus to:

receive, from the network element, an imbalance threshold value; determine whether the imbalance satisfies the imbalance threshold value; and

based on determining that the imbalance satisfies the imbalance threshold, transmit the request message to the network element, otherwise prevent transmitting the request message.

9 . The apparatus of claim 1 , wherein the activation message indicates acknowledgement, ACK, or non-acknowledgement, NACK, wherein an indication of ACK causes the apparatus to perform the one or more measurements during the configured observation window, and wherein an indication of NACK causes the apparatus to prevent performing the one or more measurements.

10 . The apparatus of claim 1 , wherein the at least one memory and the computer program code are further configured to, with the at least one processor, cause the apparatus to:

receive, from the network element, a reference symbol configuration to be used for retraining the LOS detector; and

utilize the reference symbol configuration in retraining the LOS detector by initiating reception of training signals according to the reference symbol configuration.

11 . An apparatus comprising: at least one processor; and at least one memory including computer program code, the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus to:

receive a request message from a user equipment, UE, of a wireless communication system, the request message indicating a minority class associated with an imbalance in a line-of-sight, LOS, training dataset for training a LOS detector and requesting measurement activation to perform one or more measurements, by the UE, to obtain one or more additional signal samples for the minority class; and

transmit, to the UE, an activation message causing the UE to perform the one or more measurements during a configured observation window,

wherein the at least one memory and the computer program code are further configured to, with the at least one processor, cause the apparatus to:

obtain a location estimation about at least one future location of the UE;

estimate radio condition at said at least one future location; determine, based on the estimated radio condition at said at least one future location, a time for transmitting the activation message;

and transmit the activation message at said time.

12 . A method for a user equipment, UE, of a wireless communication system, the method comprising:

detecting an imbalance in a line-of-sight, LOS, training dataset for training a LOS detector;

determining a minority class of the LOS training dataset associated with the detected imbalance; transmitting, to a network element of the wireless communication system, a request message indicating the determined minority class and requesting measurement activation to perform one or more measurements, by the UE, to obtain one or more additional signal samples for the minority class; and

receiving, from the network element, an activation message causing the UE to perform the one or more measurements during a configured observation window,

wherein the method further comprises:

obtaining the one or more additional signal samples for the minority class; and after obtaining the one or more additional signal samples, retraining the LOS detector with the LOS training set,

wherein the activation message comprises observation window configuration information,

wherein the observation window configuration information indicates a duration of the observation window and a start time of the observation window relative to an index of a subframe carrying a predetermined message or relative to a system frame number,

wherein the predetermined message is the request message and the subframe is an uplink subframe, or the predetermined message is the activation message and the subframe is a downlink subframe.

Assignments (4)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 13, 2023
From: BARBU, OANA-ELENA; Z. KOVÁCS, ISTVÁN
To: NOKIA DENMARK A/S
Reel/Frame 063308/0762 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 13, 2023
From: LI, ZEXIAN
To: NOKIA SOLUTIONS AND NETWORKS OY
Reel/Frame 063308/0765 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 13, 2023
From: NOKIA DENMARK A/S
To: NOKIA TECHNOLOGIES OY
Reel/Frame 063308/0768 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 13, 2023
From: NOKIA SOLUTIONS AND NETWORKS OY
To: NOKIA TECHNOLOGIES OY
Reel/Frame 063308/0810 →
Priority Claims (1)
EP 20191241 · Aug 17, 2020 · regional
Continuity (1)
Related Publication 20230266426A1 · Aug 24, 2023
References Cited (45)
US 9720069B2 · Lim et al. · 2017 [cited by applicant]
US 11451260B2 · Scholand · 2022 [cited by examiner]
US 12279120B2 · Da Silva · 2025 [cited by examiner]
US 20130271324A1 · Sendonaris et al. · 2013 [cited by applicant]
US 20150055459A1 · Wong · 2015 [cited by examiner]
US 20150356464A1 · Lin · 2015 [cited by examiner]
US 20170170940A1 · Lee · 2017 [cited by examiner]
US 20180123837A1 · Barbu · 2018 [cited by examiner]
US 20180210944A1 · Sukhanov et al. · 2018 [cited by applicant]
US 20200097690A1 · Wan et al. · 2020 [cited by applicant]
US 20200120482A1 · Parkvall et al. · 2020 [cited by applicant]
US 20200177259A1 · Zu et al. · 2020 [cited by applicant]
US 20200177266A1 · Kang et al. · 2020 [cited by applicant]
US 20200275291A1 · Moisio · 2020 [cited by examiner]
US 20210001981A1 · Ihalainen · 2021 [cited by examiner]
US 20210073671A1 · Puri · 2021 [cited by examiner]
US 20220038931A1 · Kuru · 2022 [cited by examiner]
US 20220312354A1 · Teyeb · 2022 [cited by examiner]
US 20230156658A1 · Barbu · 2023 [cited by examiner]
CN 108769969A · 2018 [cited by applicant]
CN 110261818A · 2019 [cited by applicant]
EP 2015103A1 · 2009 [cited by applicant]
JP 2010534423A · 2010 [cited by applicant]
JP 2015523545A · 2015 [cited by applicant]
WO 2021204351A1 · 2021 [cited by applicant]
WO 2021213685A1 · 2021 [cited by applicant]
WO 2021249634A1 · 2021 [cited by applicant]
Office Action received for corresponding Japanese Patent Application No. 2023-512069, dated May 23, 2024, 3 pages of Office Action and 4 pages of summary and translation available. [cited by applicant]
“3rd Generation Partnership Project; Technical Specification Group Radio Access Network; NR; Physical layer procedures for data (Release 16)”, 3GPP TS 38.214, V16.1.0, Mar. 2020, pp. 1-151. [cited by applicant]
“3rd Generation Partnership Project; Technical Specification Group Radio Access Network; Study on channel model for frequencies from 0.5 to 100 GHz (Release 16)”, 3GPP TR 38.901, V16.1.0, Dec. 2019, pp. 1-101. [cited by applicant]
“Initial views on potential positioning enhancements”, 3GPP TSG RAN WG1 #101-e, R1-2003721, Agenda: 8.2.3, Nokia, May 2020, 4 pages. [cited by applicant]
“Why it is important to work with a balanced classification dataset”, amsantac.co, Retrieved on Mar. 1, 2023, Webpage available at : http://amsantac.co/blog/en/2016/09/20/balanced-image-classification-r.html. [cited by applicant]
Huang et al., “Machine Learning-Enabled LOS/NLOS Identification for MIMO Systems in Dynamic Environments”, IEEE Transactions on Wireless Communications, vol. 19, No. 6, Jun. 2020, pp. 3643-3657. [cited by applicant]
Bombino et al., “Machine Learning-Aided Classification Of LoS/NLoS Radio Links In Industrial IoT”, 16th IEEE International Conference on Factory Communication Systems (WFCS), Apr. 27-29, 2020, 8 pages. [cited by applicant]
Extended European Search Report received for corresponding European Patent Application No. 20191241.7, dated Feb. 2, 2021, 9 pages. [cited by applicant]
Hsu, “GNSS multipath detection using a machine learning approach”, IEEE 20th International Conference on Intelligent Transportation Systems (ITSC), Oct. 16-19, 2017, 6 pages. [cited by applicant]
Tallo et al., “The Implementation of Genetic Algorithm in Smote (Synthetic Minority Oversampling Technique) for Handling Imbalanced Dataset Problem”, 4th International Conference on Science and Technology (ICST), Aug. 7… [cited by applicant]
International Search Report and Written Opinion received for corresponding Patent Cooperation Treaty Application No. PCT/EP2021/071757, dated Nov. 24, 2021, 12 pages. [cited by applicant]
“Other aspects on AI/ML for positioning accuracy enhancement”, 3GPP TSG RAN WG1 #109, R1-2204576, Agenda: 9.2.4.2, Nokia, May 9-20, 2022, 7 pages. [cited by applicant]
Notice of Allowance received for corresponding European Patent Application No. 20191241.7, dated Apr. 19, 2024, 8 pages. [cited by applicant]
Office action received for corresponding Indian Patent Application No. 202347016548, dated Jul. 21, 2023, 5 pages. [cited by applicant]
Office Action received for corresponding Chinese Patent Application No. 202180050649.2, dated Jun. 29, 2025, 10 pages of Office Action and no page of translation available. [cited by applicant]
Miao et al., “Class Imbalance Learning for Identifying NLOS in UWB Positioning”, Journal of Signal Processing, vol. 32, No. 01, Jan. 2016, pp. 8-13. [cited by applicant]
Song et al., “NLOS Identification Approach in UWB Positioning Based on Class—Imbalance Classification”, Journal of Information Engineering University, vol. 20, No. 02, Apr. 2019, pp. 147-153. [cited by applicant]
Miao et al., “Application of One-Class Classification in NLOS Identification of UWB Positioning”, International Conference on Information System and Artificial Intelligence, Jun. 24-26, 2016, pp. 318-322. [cited by applicant]