Information technologies and computer sciences

Using Machine Learning to Locate People Indoors

Authors

A. I. Topolskiy
Vinnytsia National Technical University ROR
Ye. A. Palamarchuk
Vinnytsia National Technical University ROR
DOI https://doi.org/10.31649/1997-9266-2025-178-1-92-103

Keywords

automated attendance systems e-learning systems machine learning classification methods regression methods indoor people localization

Abstract

The article investigates the problem of automated data processing to record the presence of students in classes. It is proposed to use machine learning methods, since they allow predicting the location of students in the premises even in the presence of anomalies in the data. The solution to this problem will help to increase the efficiency of the educational process and reduce dependence on traditional methods of recording presence, which require time and human resources.

Experiments were conducted using various machine learning methods for regression and classification tasks. Prediction accuracy was used as a measure to compare different methods.

Among the regression methods, the following were considered: SVR, LinearSVR, NuSVR, PLSRegression, KernelRidge, RidgeCV, BayesianRidge, DecisionTreeRegressor, and ExtraTreeRegressor. The best accuracy was obtained by DecisionTreeRegressor, KernelRidgeRegression and ExtraTreeRegressor methods — 92.5, 93.9 and 95.5 %, respectively. However, regression methods require continuous data, such as user coordinates, which limits their use in environments where technical means do not allow obtaining such data.

As an alternative, classification methods were considered, namely: SVC, KNeighborsClassifier, DecisionTreeClassifier and RandomForestClassifier. The initial results showed lower accuracy compared to regression methods, which was due to the lack of representativeness of the training data. To solve this problem, a step-by-step algorithm was applied, which gradually predicts the building, floor and specific room. This algorithm led to a significant improvement in accuracy, with the best result being achieved by the RandomForestClassifier method — 94.3 %.

It was concluded that the choice of a machine learning method depends on the technical means used. If they allow you to obtain continuous data, such as coordinates, it is optimal to use the ExtraTreeRegressor, DecisionTreeRegressor, or KernelRidgeRegression regression methods. If continuous data cannot be obtained, it is optimal to use the RandomForestClassifier classification method with the proposed step-by-step algorithm.

351 236

How to Cite

[1]
“Using Machine Learning to Locate People Indoors”, Вісник ВПІ, no. 1, pp. 92–103, Feb. 2025, doi: 10.31649/1997-9266-2025-178-1-92-103.

Author Biographies

A. I. Topolskiy, Vinnytsia National Technical University

Post-Graduate Student of the Chair of Automation and Intelligent Information Technologies

Ye. A. Palamarchuk, Vinnytsia National Technical University

Cand. Sc. (Eng.), Associate Professor, Professor of the Chair of Automation and Intelligent Information Technologies

References

A. Ademola, T. E. Somefun, and A. Oluwabusola, “Web based fingerprint roll call attendance management system,” International Journal of Electrical and Computer Engineering (IJECE), vol. 9, no. 5, pp. 4364-4371, Oct. 2019. https://doi.org/10.11591/ijece.v9i5.pp4364-4371 .
А. І. Топольський, і Є. А. Паламарчук, «Аналіз практичних реалізацій автоматизованих систем ідентифікації студентів в електронних навчальних системах,» Вісник Вінницького політехнічного інституту, № 2, с. 61-70, 2024. https://doi.org/10.31649/1997-9266-2024-173-2-61-70 .
Ji-Hyun Yoo, “Study on Prediction of Attendance Using Machine Learning,” Journal of IKEEE, vol. 23, no. 4, pp. 1243-1249, 2019. https://doi.org/10.7471/ikeee.2019.23.4.1243 .
UjiIndoorLoc: An indoor localization dataset. [Electronic resource]. Available: https://www.kaggle.com/datasets/giantuji/UjiIndoorLoc/data .
International Conference on Indoor Positioning and Indoor Navigation (IPIN), Banff, AB, Canada, 13-16 October 2015. https://doi.org/10.1109/ipin.2015.7346747 .
E. Hossain, “Machine learning algorithms,” in Machine Learning Crash Course for Engineers, Cham: Springer Int. Publishing, 2023, pp. 117-140. https://doi.org/10.1007/978-3-031-46990-9_3 .
K. Tewari, S. Vandita, and S. Jain, “Predictive analysis of absenteeism in MNCS using machine learning algorithm,” in Lecture Notes in Electrical Engineering, Cham: Springer Int. Publishing, 2019, pp. 3-14. https://doi.org/10.1007/978-3-030-29407-6_1 .
D. Basak, S. Pal, and D. Patranabis, “Support Vector Regression,” Neural Information Processing – Letters and Reviews, vol. 11, no. 10, pp. 203-224, 2007.
I. Ali, “Machine Learning models and feature relevance for student grade prediction,” Journal of High School Science, vol. 8, no. 1, pp. 180-197, 2024.
I. Aqeel, “Location fingerprinting for IoT systems using machine learning.” dissert. Dr. Sc. (Eng.), Glasgow, Scotland, 2020. https://doi.org/10.48730/1jdb-6258 .
C. Wu, Z. Yang, and C. Xiao, “Automatic Radio Map Adaptation for Indoor Localization Using Smartphones,” IEEE Transactions on Mobile Computing, vol. 17, no. 3, pp. 517-528, 2018. https://doi.org/10.1109/tmc.2017.2737004 .
A. Höskuldsson, “PLS regression methods,” Journal of Chemometrics, vol. 2, no. 3, pp. 211-228, 1988. https://doi.org/10.1002/cem.1180020306 .
M. Welling, Kernel ridge regression: Notes for a lecture on machine learning. Toronto: University of Toronto, Department of Computer Science, 2013, 3 p.
P. Exterkate, et al., “Nonlinear forecasting with many predictors using kernel ridge regression,” International Journal of Forecasting, vol. 32, no. 3, pp. 736-753, 2016. https://doi.org/10.1016/j.ijforecast.2015.11.017 .
V. Siahaan, Data visualization, time-series forecasting, and prediction using machine learning with tkinter, Balige: BALIGE Publishing Ltd., 2023, 266 p.
Y. Jung, “Multiple predicting K-fold cross-validation for model selection,” Journal of Nonparametric Statistics, vol. 30, no. 1, pp. 197-215, 2017. https://doi.org/10.1080/10485252.2017.1404598 .
A. Verma, and M. Jain, “Mediation Analysis of Diabetes and Heart Diseases Influenced by Obesity Using Machine Learning Classifiers,” Austrian Journal of Statistics, vol. 53, № 5, pp. 90-111, 2024.
B.-W. Chen, et al., “Efficient multiple incremental computation for Kernel Ridge Regression with Bayesian uncertainty modeling,” Future Generation Computer Systems, vol. 82, pp. 679-688, 2018. https://doi.org/10.1016/j.future.2017.08.053 .
Judit Kunné Tamás, “Classification based Symbolic Indoor Positioning.” Doctoral dissertation, Debrecen, 2021, 127 p.
T. Aziz, and K. Insoo, “Enhancing Indoor Localization Accuracy through Multiple Access Point Deployment,” Electronics, vol. 13, no. 16, pp. 3307, 2024. https://doi.org/10.3390/electronics13163307 .
Dwi Arman Prasetya, et al., “Resolving the Shortest Path Problem using the Haversine Algorithm,” Journal of Critical Review, vol. 7, no. 1, pp. 62-64, 2020.
O. Renaud, and M.-P. Victoria-Feser, “A robust coefficient of determination for regression,” Journal of Statistical Planning and Inference, vol. 140, no. 7, pp. 1852-1862, 2010. https://doi.org/10.1016/j.jspi.2010.01.008 .
N. Singh, S. Choe, and R. Punmiya, “Machine Learning Based Indoor Localization Using Wi-Fi RSSI Fingerprints: an Overview,” IEEE Access, vol. 9, pp. 127150-127174, 2021. https://doi.org/10.1109/access.2021.3111083 .
J. Uddin, “UHF RFID antenna architectures and applications,” Scientific Res. Essays, vol. 5, no. 10, pp. 1033-1051, 2010.
W. Charoenruengkit, et al., “Position Quantization Approach with Multi-class Classification for Wi-Fi Indoor Positioning System,” in 2018 International Conference on Information Technology (InCIT), Khon Kaen, 24-26 October 2018. https://doi.org/10.23919/incit.2018.8584863 .
Z. Chunhong, J. Licheng, and L. Yongzhao, “Support vector classifier based on principal component analysis,” Journal of Systems Engineering and Electronics, vol. 19, no. 1, pp. 184-190, 2008. https://doi.org/10.1016/s1004-4132(08)60065-1 .
S. Dhanabal, Dr. S. Chandramathi, “A Review of various k-Nearest Neighbor Query Processing Techniques,” International Journal of Computer Applications, vol. 31, no. 7, pp. 14-22, 2011.
S. Milinković, and M. Maksimović, “Using Decision Tree Classifier for Analyzing Students’ Activitie,” JITA, Journal of Information Technology and Applications (Banja Luka), APEIRON, vol. 6, no. 2, pp. 82-95, 2013. https://doi.org/10.7251/jit1302087m .
Y. Wang, et al., “WiFi Indoor Localization with CSI Fingerprinting-Based Random Forest,” Sensors, vol. 18, no. 9, pp. 2869, 2018. https://doi.org/10.3390/s18092869 .
M. Sokolova, N. Japkowicz, and S. Szpakowicz, “Beyond Accuracy, F-Score and ROC: A Family of Discriminant Measures for Performance Evaluation,” AI 2006: Advances in Artificial Intelligence: Australian Joint Conference on Artificial Intelligence, Hobart, 4-8 December 2006, Heidelberg, 2006, pp. 1015-1021.
E. Schat, et al., “The data representativeness criterion: Predicting the performance of supervised classification based on data set similarity,” PLOS ONE, vol. 15, no. 8, pp. 1-16, 2020. https://doi.org/10.1371/journal.pone.0237009 .

Most read articles by the same author(s)