IMPROVING THE QUALITY OF MULTI-MODAL DATA BASED ON THE HYBRIDIZATION OF PREPROCESSING AND MULTISENSORY FUSION METHODS
Abstract
The article explores the methods of data preprocessing and merging of multi-modal data. The data collected from multi-sensor devices contains noise, anomalies, and includes sensor failures. The use of raw data inevitably leads to false patterns when using machine learning models in which this data is used. To improve the quality of data, it is necessary to use special methods for preliminary processing and merging. The aim of the work is to create a hybrid preprocessing and multisensory data fusion controller operating at the peripheral computing level. To achieve this, the tasks of removing the consequences of technical failures and noise from the data, time synchronization, scaling of features and combining duplicate sources, considering their dynamic weight, have been solved. The following methods were applied: inter-quartile scale to detect outliers, linear interpolation to replace them, high-pass filter to suppress noise, and weighed multisensory fusion with dynamic weight calculation. In addition, methods for processing visual, sensory, and acoustic data within a hybrid pipeline are presented that can be adapted for implementation at the peripheral computing level. The experimental verification of the developed pipeline was carried out on a simulated set of climatic data with artificially introduced noises and anomalies. The proposed approach has demonstrated high efficiency of data recovery. For air temperature, the coefficient of determination (R2) increased from 0.9807 to 0.9964 with a slight change in the mean absolute percentage error (MAPE) from 10.11% to 10.48%. For relative humidity, the R2 metric increased from 0.9248 to 0.9675, and the MAPE error decreased from 2.87% to 2.57%. The most significant improvement has been achieved for atmospheric pressure. The R2 metric increased from a negative value of -0.124 to 0.974, and the MAPE error decreased from 0.12% to 0.06%. The results confirm that the proposed pipeline reduces the error and improves the quality of multisensory data, minimizes the amount of data being transferred. The practical value lies in creating a continuous cycle of local filtering and merging of data without accumulation of errors.
References
1. Gryaznov S.A., Kuznetsov M.I. Faktory, vliyayushchie na vosproizvodimost' nauchnykh issledovaniy [Factors affecting the reproducibility of scientific research], Mezhdunarodnyy zhurnal gumanitarnykh i estestvennykh nauk [International Journal of Humanities and Natural Sciences], 2024, No. 8-1 (95), pp. 69-71.
2. Jesus G. Casimiro A., Oliveira A. A Survey on Data Quality for Dependable Monitoring in Wireless Sensor Networks, Sensors, 2017, Vol. 17, No. 9, 2010 p.
3. Zhang L. Jeong D., Lee S. Data Quality Management in the Internet of Things, Sensors, 2021, Vol. 21, No. 17, 5834 p.
4. Borovskaya V.G., Gomon Yu.M. Otsenka kachestva dannykh real'noy klinicheskoy praktiki [Quality assessment of real-world data], Real'naya klinicheskaya praktika: dannye i dokazatel'stva [Real-World Data & Evidence], 2022, Vol. 2, No. 4, pp. 10-16.
5. Papavasileiou A., Michalos G., Makris S. Quality control in manufacturing – review and challenges on robotic applications, International Journal of Computer Integrated Manufacturing, 2025, Vol. 38,
No. 1, pp. 79-115.
6. Alexakis T., Adamopoulou E., Peppes N. [et al.]. Evaluating Data Quality: Comparative Insights on Standards, Methodologies, and Modern Software Tools, Electronics, 2025, Vol. 14, No. 15, 3038 p.
7. Bogani R., Theodorou A., Arnaboldi L., Wortham R.H. Garbage in, toxic data out: a proposal for ethical artificial intelligence sustainability impact statements, AI and Ethics, 2023, Vol. 3, No. 4, pp. 1135-1142.
8. Kilkenny M.F., Robinson K.M. Data quality: “Garbage in – garbage out”, Health Information Manage-ment Journal, 2018, Vol. 47, No. 3, ppp. 103-105.
9. Liu C., Ye F. A review of multimodal medical data fusion techniques for personalized medicine, Associa-tion for Computing Machinery. New York: ACM, 2025, pp. 338-347.
10. Duan J., Xiong J., Li Y., Ding W. Deep learning based multimodal biomedical data fusion: An overview and comparative review, Information Fusion, 2024, Vol. 112, 102536 p.
11. Azcarate S.M., Ríos-Reina R., Amigo J.M., Goicoechea H.C. Data handling in data fusion: Methodolo-gies and applications, TrAC Trends in Analytical Chemistry, 2021, Vol. 143, 116355 p.
12. Mourad A., Bertrand-Krajewski J.L., El-Youssef A. Edge Computing for Data Anomaly Detection of Multi-Sensors in IoT Environmental Monitoring, Electronics, 2021, Vol. 10, No. 3, 302 p.
13. Zraunig M., Susto G.A., Cenedese A. Detecting Faults at the Edge via Sensor Data Fusion Echo State Networks, Sensors, 2022, Vol. 22, No. 8, 2858 p.
14. Li L., Wang J., Zheng Y. Hybrid Machine Learning-Based Fault-Tolerant Sensor Data Fusion and Anomaly Detection for Fire Risk Mitigation in IIoT Environment, Sensors, 2025, Vol. 25, No. 7, 2146 p.
15. Chauhan D., Shukla K., Desai D. [et al.]. A Comprehensive Review of IoT-Enabled Microgrids: Archi-tectures, Challenges, and Future Prospects to achieve Sustainability, Next Research, 2026, 102156 p.
16. Bikakis N., Maroulis S., Papastefanatos G., Vassiliadis P. In-situ visual exploration over big raw data, Information Systems, 2021, Vol. 95, 101616 p.
17. Maia A., Boutouchent A., Kardjadja Y., Gherari M., Soyak E.G., Saqib M., Boussekar K., Cilbir I., Habibi S., Ali S.O., Ajib W. A survey on integrated computing, caching, and communication in the cloud-to-edge continuum, Computer Communications, 2024, Vol. 219, pp. 128-152.
18. Sergeev M.B., Solov'ev N.V., Stadnik A.I. Metody povysheniya kontrastnosti rastrovykh izobrazheniy dlya sistem tsifrovoy obrabotki videoinformatsii [Methods for increasing the contrast of raster images for digital video processing systems], Informatsionno-upravlyayushchie sistemy [Information and Con-trol Systems], 2007, No. 1, pp. 2-7.
19. Li D., Wang Y., Wang J., Wang C., Duan Y. Recent advances in sensor fault diagnosis: A review, Sensors and Actuators A: Physical, 2020, Vol. 309, 111990 p.
20. Gasparyan L., Gasparyan F., Simonyan V. Internal Electrical Noises of BioFET Sensors Based on Vari-ous Architectures, OJBIPHY, 2021, Vol. 11, No. 02, pp. 177-204.
21. Jadhav S.P., Srinivas A., Dipak R.P., Ramkumar P.M., Suryawanshi J., Haldorai A. Deep learning ap-proaches for multi-modal sensor data analysis and abnormality detection, Measurement: Sensors, 2024, Vol. 33, 101157 p.
22. Tang Q., Liang J., Zhu F. A comparative review on multi-modal sensors fusion based on deep learning, Signal Processing, 2023, Vol. 213, 109165 p.
23. Mitsis K., Zarkogianni K., Kalafatis E., Dalakleidi K., Jaafar A., Mourkousis G., Nikita K.S. A Multi-modal Approach for Real Time Recognition of Engagement towards Adaptive Serious Games for Health, Sensors, 2022, Vol. 22, No. 7, 2472 p.
24. Chernov A.V., Savvas I.K., Alexandrov A.A., Kartashov O.O., Polyanichenko D.S., Butakova M.A., Soldatov A.V. Integrated Video and Acoustic Emission Data Fusion for Intelligent Decision Making in Material Surface Inspection System, Sensors, 2022, Vol. 22, No. 21, 8554 p.
25. Wang Q.-G., Li X., Qin Q. Feature Selection for Time Series Modeling, JILSA, 2013, Vol. 05, No. 03, pp. 152-164.
