Enhancing predictive models for assessing 5G exposure effects on human health and cognition through supervised machine learning: a multi-stage feature selection approach

• Autorzy: Sofri Tasneem , Andrew Allan Melvin , Rahim Hasliza A. , Nishizaki Hiromitsu , Kamarudin Latifah Munirah , Wong Peng Wen , Soh Ping Jack

Identyfikatory

DOI

10.15199/48.2024.06.23

Warianty tytułu

PL

Udoskonalanie modeli predykcyjnych do oceny wpływu narażenia na sieć 5G na zdrowie ludzkie i funkcje poznawcze poprzez nadzorowane uczenie maszynowe: wieloetapowe podejście do wyboru funkcji

• Języki publikacji: EN

Abstrakty

EN

No prior reviews have focused on any comprehensively examine the effects of 5G exposure (700 MHz to 30 GHz) on human health and cognition using supervised Machine Learning (ML). This novel research combined the Multi-Stage Feature Selection (MSFS) and hybrid features for classification machine learning model. The approach which includes the use of MSFS, yielded better results in terms of accuracy, precision, F1 score, sensitivity, and specificity when contrasted with the approach that did not incorporate MSFS with accuracy more than 0.95 for both datasets.

PL

adne wcześniejsze przeglądy nie skupiały się na kompleksowym badaniu wpływu narażenia na sieć 5G (700 MHz do 30 GHz) na zdrowie ludzkie i funkcje poznawcze przy użyciu nadzorowanego uczenia maszynowego (ML). W tym nowatorskim badaniu połączono wieloetapowy wybór cech (MSFS) i funkcje hybrydowe na potrzeby modelu uczenia maszynowego klasyfikującego. Podejście obejmujące wykorzystanie MSFS dało lepsze wyniki pod względem dokładności, precyzji, współczynnika f1, czułości i specyficzności w porównaniu z podejściem, które nie obejmowało MSFS z dokładnością większą niż 0,95 dla obu zbiorów danych.

Słowa kluczowe

EN

antenna; propagation; bioelectromagnetic; probabilistic neural network; supervised machine learning

PL

antena; propagacja; bioelektromagnetyczny; probabilistyczna sieć neuronowa; nadzorowane uczenie maszynowe

• Wydawca: Wydawnictwo SIGMA-NOT
• Czasopismo: Przegląd Elektrotechniczny
• Rocznik: 2024
• Tom: R. 100, nr 6
• Strony: 122--128
• Opis fizyczny: Bibliogr. 33 poz., rys., tab.

Twórcy

autor

Sofri Tasneem

• aculty of Electronic Engineering & Technology, Universiti Malaysia Perlis, Perlis, Malaysia
• Advanced Communication Engineering, Centre of Excellence (ACE), Universiti Malaysia Perlis, Perlis, Malaysia
• Integrated Graduate School of Medicine, Engineering, and Agricultural Sciences, University of Yamanashi, Yamanashi, Japan

• https://orcid.org/0000-0003-0218-2584

autor

Andrew Allan Melvin

• Advanced Communication Engineering, Centre of Excellence (ACE), Universiti Malaysia Perlis, Perlis, Malaysia
• Faculty of Electrical Engineering & Technology, Universiti Malaysia Perlis, Perlis, Malaysia

• https://orcid.org/0000-0002-0377-0006

autor

Rahim Hasliza A.

• Faculty of Electronic Engineering & Technology, Universiti Malaysia Perlis, Perlis, Malaysia
• Advanced Communication Engineering, Centre of Excellence (ACE), Universiti Malaysia Perlis, Perlis, Malaysia
• Faculty of Graduate Studies (FGS), Daffodil International University, Dhaka, Bangladesh

• https://orcid.org/0000-0002-5662-7158

autor

Nishizaki Hiromitsu

• Faculty of Electrical Engineering & Technology, Universiti Malaysia Perlis, Perlis, Malaysia

• https://orcid.org/0000-0002-7717-8312

autor

Kamarudin Latifah Munirah

• Faculty of Electronic Engineering & Technology, Universiti Malaysia Perlis, Perlis, Malaysia
• Universiti Malaysia Perlis, Perlis, Malaysia

• https://orcid.org/0000-0002-2547-3934

autor

Wong Peng Wen

• Filpal (M) Sdn Bhd, Sains@Universiti Sains Malaysia, Penang, Malaysia

• https://orcid.org/0009-0005-5550-6521

autor

Soh Ping Jack

• University of Oulu, Oulu, Finland

• https://orcid.org/0000-0002-6394-5330

Bibliografia

• [1] WHO, “Radiation: 5G mobile networks and health,” World Health Orgnization (WHO), 2020.
• [2] C. L. Russell, “5 G wireless telecommunications expansion: Public health and environmental implications,” Environ. Res., vol. 165, no. April, pp. 484–495, 2018, doi: 10.1016/j.envres.2018.01.016.
• [3] WHO, “IARC Classifies Radiofrequency Electromagnetic Fields as Possibly Carcinogenic to Humans,” Press Release; World Heal. Organ., 2011, [Online]. Available: https://www.iarc.who.int/wpcontent/uploads/2018/07/pr208_E.pdf.
• [4] L. Redazione, “International Appeal: Scientists call for protection from non-ionizing electromagnetic field exposure,” Eur. J. Oncol., vol. 20, no. 3/4 SE-Specific topics, pp. 180–182, Dec. 2015, [Online]. Available: https://www.mattioli1885journals.com/index.php/EJOEH/article/view/4971.
• [5] R. Nyberg and L. Hardell, “EU 5G Appeal – Scientists warn of potential serious health effects of 5G,” Jrs Eco Wirel., pp. 1–11, 2017.
• [6] R. N. Kostoff, P. Heroux, M. Aschner, and A. Tsatsakis, “Adverse health effects of 5G mobile networking technology under real-life conditions,” Toxicol. Lett., vol. 323, no. January, pp. 35–40, 2020, doi: 10.1016/j.toxlet.2020.01.020.
• [7] J. Kaur, M. A. Khan, M. Iftikhar, M. Imran, and Q. Haq, “Machine Learning Techniques for 5G and Beyond,” IEEE Access, vol. PP, p. 1, 2021, doi: 10.1109/ACCESS.2021.3051557.
• [8] A. Haidine, F. Z. Salmam, A. Aqqal, and A. Dahbi, “Artificial Intelligence and Machine Learning in 5G and beyond: A Survey and Perspectives,” in Moving Broadband Mobile Communications Forward, A. Haidine, Ed. Rijeka: IntechOpen, 2021.
• [9] S. Khan et al., “5G Vehicular Network Resource Management for Improving Radio Access Through Machine Learning,” IEEE Access, vol. 7, pp. 1–9, Jan. 2020, doi: 10.1109/ACCESS.2020.2964697.
• [10] S. Stanczak, S. Limmer, and L. Miretti, “Machine Learning for 5G and Beyond,” IEEE Access, 2021, [Online]. Available: www.scopus.com.
• [11] V. P. Rekkas, S. Sotiroudis, P. Sarigiannidis, S. Wan, G. K. Karagiannidis, and S. K. Goudos, “Machine Learning in Beyond 5G/6G Networks—State-of-the-Art and Future Trends,” Electronics, vol. 10, no. 22, 2021, doi: 10.3390/electronics10222786.
• [12] S. J. Regel et al., “UMTS base station-like exposure, wellbeing, and cognitive performance.,” Environ. Health Perspect., vol. 114, no. 8, pp. 1270–1275, Aug. 2006, doi: 10.1289/ehp.8934.
• [13] S. Andrianome, J. Gobert, L. Hugueville, E. StéphanBlanchard, F. Telliez, and B. Selmaoui, “An assessment of the autonomic nervous system in the electrohypersensitive population: a heart rate variability and skin conductance study.,” J. Appl. Physiol., vol. 123, no. 5, pp. 1055–1062, Nov. 2017, doi: 10.1152/japplphysiol.00229.2017.
• [14] G. Curcio, E. Valentini, F. Moroni, M. Ferrara, L. De Gennaro, and M. Bertini, “Psychomotor performance is not influenced by brief repeated exposures to mobile phones.,” Bioelectromagnetics, vol. 29, no. 3, pp. 237–241, Apr. 2008, doi: 10.1002/bem.20393.
• [15] M. Koivisto, C. M. Krause, A. Revonsuo, M. Laine, and H. Hämäläinen, “The effects of electromagnetic field emitted by GSM phones on working memory.,” Neuroreport, vol. 11, no. 8, pp. 1641–1643, Jun. 2000, doi: 10.1097/00001756-20000605000009.
• [16] C. Cinel, A. Boldini, E. Fox, and R. Russo, “Does the Use of Mobile Phones Affect Human Short-Term Memory or Attention?,” Appl. Cogn. Psychol., vol. 22, pp. 1113–1125, Dec. 2008, doi: 10.1002/acp.1425.
• [17] A. Trunk et al., “Effects of concurrent caffeine and mobile phone exposure on local target probability processing in the human brain,” Sci. Rep., vol. 5, p. 14434, Sep. 2015, doi: 10.1038/srep14434.
• [18] H. Kleinlogel, T. Dierks, T. Koenig, H. Lehmann, A. Minder, and R. Berz, “Effects of weak mobile phone - Electromagnetic fields (GSM, UMTS) on well-being and resting EEG,” Bioelectromagnetics, vol. 29, no. 6, pp. 479–487, 2008, doi: 10.1002/bem.20419.
• [19] Z. Vecsei, B. Knakker, P. Juhász, G. Thuróczy, A. Trunk, and I. Hernádi, “Short-term radiofrequency exposure from new generation mobile phones reduces EEG alpha power with no effects on cognitive performance,” Sci. Rep., vol. 8, no. 1, p. 18010, 2018, doi: 10.1038/s41598-018-36353-9.
• [20] S. Eltiti et al., “Does short-term exposure to mobile phone base station signals increase symptoms in individuals who report sensitivity to electromagnetic fields? A double-blind randomized provocation study.,” Environ. Health Perspect., vol. 115, no. 11, pp. 1603–1608, Nov. 2007, doi: 10.1289/ehp.10286.
• [21] J. Wallace, S. Andrianome, R. Ghosn, E. S. Blanchard, F. Telliez, and B. Selmaoui, “Heart rate variability in healthy young adults exposed to global system for mobile communication (GSM) 900-MHz radiofrequency signal from mobile phones,” Environ. Res., vol. 191, p. 110097, 2020, doi: https://doi.org/10.1016/j.envres.2020.110097.
• [22] G. Oftedal, A. Straume, A. Johnsson, and L. J. Stovner, “Mobile phone headache: a double blind, sham-controlled provocation study.,” Cephalalgia, vol. 27, no. 5, pp. 447–455, May 2007, doi: 10.1111/j.1468-2982.2007.01336.x.
• [23] I. van Moorselaar et al., “Effects of personalised exposure on self-rated electromagnetic hypersensitivity and sensibility – A double-blind randomised controlled trial,” Environ. Int., vol. 99, pp. 255–262, 2017, doi: 10.1016/j.envint.2016.11.031.
• [24] G. Curcio, M. Ferrara, L. De Gennaro, R. Cristiani, G. D’Inzeo, and M. Bertini, “Time-course of electromagnetic field effects on human performance and tympanic temperature.,” Neuroreport, vol. 15, no. 1, pp. 161–164, Jan. 2004, doi: 10.1097/00001756200401190-00031.
• [25] F. Malek, K. A. Rani, H. A. Rahim, and M. H. Omar, “Effect of Short-Term Mobile Phone Base Station Exposure on Cognitive Performance, Body Temperature, Heart Rate and Blood Pressure of Malaysians,” Sci. Rep., vol. 5, no. 1, p. 13206, 2015, doi: 10.1038/srep13206.
• [26] S. Eltiti et al., “Short-Term Exposure to Mobile Phone Base Station Signals Does Not Affect Cognitive Functioning or Physiological Measures in Individuals Who Report Sensitivity to Electromagnetic Fields and Controls,” Bioelectromagnetics, vol. 30, pp. 556–563, Oct. 2009, doi: 10.1002/bem.20504.
• [27] M. N. Halgamuge, “Supervised machine learning algorithms for bioelectromagnetics: Prediction models and feature selection techniques using data from weak radiofrequency radiation effect on human and animals cells,” Int. J. Environ. Res. Public Health, vol. 17, no. 12, pp. 1–27, 2020, doi: 10.3390/ijerph17124595.
• [28] A. A. A. Halim et al., “Optimized Intelligent Classifier for Early Breast Cancer Detection Using Ultra-Wide Band Transceiver,” Diagnostics, vol. 12, no. 11, 2022, doi: 10.3390/diagnostics12112870.
• [29] A. Elkhouly, A. M. Andrew, H. A. Rahim, N. Abdulaziz, M. F. A. Malek, and S. Siddique, “Data-driven audiogram classifier using data normalization and multi-stage feature selection,” Sci. Rep., vol. 13, no. 1, pp. 1–14, 2023, doi: 10.1038/s41598-02225411-y.
• [30] J. T. Hancock and T. M. Khoshgoftaar, “Survey on categorical data for neural networks,” J. Big Data, vol. 7, no. 1, p. 28, 2020, doi: 10.1186/s40537-020-00305-w.
• [31] G. A. Ismaeel, “Machine Learning to Diagnose Breast Cancer,” Prz. Elektrotechniczny, vol. 99, no. 1, pp. 10–12, 2023, doi: 10.15199/48.2023.01.02.
• [32] H. Huang, A. Y. Chang, and C. Ho, “Using Artificial Neural Networks to Establish a Customer-cancellation Prediction Model,” Prz. Elektrotechniczny, vol. 89, no. 1b, pp. 178–180, 2013.
• [33] ICNIRP, “Guidelines for Limiting Exposure to Electromagnetic Fields (100 kHz to 300 GHz).,” Health Phys., vol. 118, no. 5, pp. 483–524, May 2020, doi: 10.1097/HP.0000000000001210.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki i promocja sportu (2025).