Open Access Open Access  Restricted Access Subscription Access

Smart Radio-Based Spectrum Monitoring System for Hospital Wireless Safety

Shrishail Hiremath, Siddaling Bharatnoor, Sharangouda Patil, Veeresh K, Dr. Sharanbasappa Sali, Ashok Kumbar

Abstract


This work creates a smart spectrum monitoring system built with Python to identify wireless signal outages in medical settings. To train machine learning classifiers, synthetic signals were created by mimicking zone-specific radiofrequency circumstances (ICU, OT, Radiology, Lobby, and General Ward) with clinically relevant SNR levels (-10dB to 15dB). From 1,000 signal samples, five statistical characteristics were extracted: energy, mean, variance, skewness, and kurtosis. In the classification of active/idle states, Random Forest outperformed the other four evaluated models (SVM, KNN, Naïve Bayes, and Random Forest) with 96% accuracy and 0.98 AUC. In crucial zones such as ICU/OT, the system showed 97% recall, demonstrating its effectiveness in detecting interference. Three significant advancements are offered by this hardware-free method: (1) ML-driven signal monitoring with an error rate of less than 4%, (2) realistic simulation of hospital electromagnetic risks, and (3) an approachable methodology for environments with limited resources. Real-time SDR implementations will be the focus of future research.


Full Text:

PDF

References


Latré, B., Braem, B., Moerman, I., Blondia, C., & Demeester, P. (2011). A survey on wireless body area networks. Wireless Networks, 17(1), 1–18.

Alemdar, H., & Ersoy, C. (2010). Wireless sensor networks for healthcare: A survey. Computer Networks, 54(15), 2688–2710.

Chatterjee, S., Ghosh, S. K., & Sarker, R. (2020). Internet of Medical Things (IoMT): Applications, challenges, and prospects in healthcare. Journal of Network and Computer Applications, 148, 102444.

Yucek, T., & Arslan, H. (2009). A survey of spectrum sensing algorithms for cognitive radio applications. IEEE Communications Surveys & Tutorials, 11(1), 116–130.

Haykin, S. (2005). Cognitive radio: Brain-empowered wireless communications. IEEE Journal on Selected Areas in Communications, 23(2), 201–220.

Bazzi, A., Zanella, A., & Pasolini, G. (2016). Cooperative adaptive energy detection for dynamic spectrum sensing. EURASIP Journal on Wireless Communications and Networking, 2016(1), 1–14.

Adeel, A., Rana, M., & Hussain, M. (2020). Machine learning-based signal classification in LTE and Wi-Fi coexistence environment. Wireless Personal Communications, 110(4), 1827–1842.

Rajendran, S., & Mishra, D. (2022). Intelligent classification of wireless IoT signals using ensemble learning. International Journal of Electronics and Communications, 139, 153900.

Sharma, V., Thakur, A., & Singh, S. (2021). Real-time radar signal detection using Naive Bayes classifier in congested spectrum. IEEE Access, 9, 76648–76657.

van Lieshout, E. J., et al. (2013). Clinical risk of Wi-Fi interference with telemetry devices: A hospital case study. BMJ Open, 3(6), e002992.


Refbacks

  • There are currently no refbacks.