Leveraging Probabilistic Neural Networks For Early Detection Of Respiratory Viral Infection
Keywords:
Breathing issue, Human respiratory system, Equalization, Fuzzy logic and PNN
Abstract
The Respiratory Detection System (RDS) contributes to global mortality and necessitates suitable medical intervention. Therefore, this paper aims to classify lung MRI images into abnormal or normal categories. Our latest proposed approach involves the utilization of Probabilistic Neural Networks (PNN), incorporating both image fusion and PNN techniques. Initially, we applied several preprocessing operations, including multi-focus image fusion, to improve the exactness of MRI pictures to classify RDS. We conducted two separate experiments using distinct databases to evaluate the reliability of our PNN approach. In the first attempt, the MRI image dataset is partitioned into a 20% research set and an 80% training set, whereas in the second attempt, we employed a 10-fold cross-validation approach for the image dataset. In the first test, our methodology achieved a classification accuracy of 98.33% on dataset 1, and in the second test, it reached an accuracy of 98.77%. For dataset 2, the accuracy obtained in the first test was 92.22%, and in the second test, it was 93.33%. Hence, this control chart exhibits the potential to serve as an effective tool for the early detection of respiratory virus outbreaks, thereby facilitating prompt outbreak investigation and mitigation efforts.
References
[1] J. C. Bezdek, “Objective Function Clustering,” in Pattern Recognition with Fuzzy Objective Function Algorithms, Springer US, 1981, pp. 43–93. doi: 10.1007/978-1-4757-0450-1_3.
[2] S.-D. Chen, “A new image quality measure for assessment of histogram equalization-based contrast enhancement techniques,” Digit Signal Process, vol. 22, no. 4, pp. 640–647, Jul. 2012, doi: 10.1016/j.dsp.2012.04.002.
[3] C. Piewbang, A. Rungsipipat, Y. Poovorawan, and S. Techangamsuwan, “Cross-sectional investigation and risk factor analysis of community-acquired and hospital-associated canine viral infectious respiratory disease complex,” Heliyon, vol. 5, no. 11, p. e02726, Nov. 2019, doi: 10.1016/j.heliyon.2019.e02726.
[4] V. S. Nallanthighal, Z. Mostaani, A. Härmä, H. Strik, and M. Magimai-Doss, “Deep learning architectures for estimating breathing signal and respiratory parameters from speech recordings,” Neural Networks, vol. 141, pp. 211–224, Sep. 2021, doi: 10.1016/j.neunet.2021.03.029.
[5] J. J. Feddema and E. Claassen, “Prevalence of viral respiratory infections amongst asthmatics: Results of a meta-regression analysis,” Respir Med, vol. 173, p. 106020, Nov. 2020, doi: 10.1016/j.rmed.2020.106020.
[6] Y. Zhang et al., “A novel point-of-care test of respiratory syncytial viral RNA based on cellulose-based purification and convective PCR,” Clinica Chimica Acta, vol. 511, pp. 154–159, Dec. 2020, doi: 10.1016/j.cca.2020.10.012.
[7] J. R. Machado Fernández and L. Anishchenko, “Mental stress detection using bioradar respiratory signals,” Biomed Signal Process Control, vol. 43, pp. 244–249, May 2018, doi: 10.1016/j.bspc.2018.03.006.
[8] S. S. Sai Koushik and K. G. Srinivasa, “Detection of respiratory diseases from chest X rays using Nesterov accelerated adaptive moment estimation,” Measurement, vol. 176, p. 109153, May 2021, doi: 10.1016/j.measurement.2021.109153.
[9] M. Abreu, A. Fred, J. Valente, C. Wang, and H. da Silva, “Morphological autoencoders for apnea detection in respiratory gating radiotherapy,” Comput Methods Programs Biomed, vol. 195, p. 105675, Oct. 2020, doi: 10.1016/j.cmpb.2020.105675.
[10] C. Bi et al., “Simultaneous detection and mutation surveillance of SARS-CoV-2 and multiple respiratory viruses by rapid field-deployable sequencing,” Med, vol. 2, no. 6, pp. 689-700.e4, Jun. 2021, doi: 10.1016/j.medj.2021.03.015.
[11] B. Jin, Y. Zhao, and Y. Liang, “RETRACTED: Internet of things medical image detection and pediatric renal failure dialysis complicated with respiratory tract infection,” Microprocess Microsyst, vol. 83, p. 104016, Jun. 2021, doi: 10.1016/j.micpro.2021.104016.
[12] C. Adrover-Jaume et al., “Paper biosensors for detecting elevated IL-6 levels in blood and respiratory samples from COVID-19 patients,” Sens Actuators B Chem, vol. 330, p. 129333, Mar. 2021, doi: 10.1016/j.snb.2020.129333.
[13] J. Zhang, Z. Yang, Q. Liu, and H. Liang, “Electrochemical biotoxicity detection on a microfluidic paper-based analytical device via cellular respiratory inhibition,” Talanta, vol. 202, pp. 384–391, Sep. 2019, doi: 10.1016/j.talanta.2019.05.031.
[14] S. Haridy, A. Maged, A. W. Baker, M. Shamsuzzaman, H. Bashir, and M. Xie, “Monitoring scheme for early detection of coronavirus and other respiratory virus outbreaks,” Computers & Industrial Engineering, vol. 156, p. 107235, Jun. 2021, doi: 10.1016/j.cie.2021.107235.
[15] B. V. Ribeiro, T. A. R. Cordeiro, G. R. e Freitas, L. F. Ferreira, and D. L. Franco, “Biosensors for the detection of respiratory viruses: A review,” Talanta Open, vol. 2, p. 100007, Dec. 2020, doi: 10.1016/j.talo.2020.100007.
[16] H. G. Lee et al., “PCR-coupled Paper-based Surface-enhanced Raman Scattering (SERS) Sensor for Rapid and Sensitive Detection of Respiratory Bacterial DNA,” Sens Actuators B Chem, vol. 326, p. 128802, Jan. 2021, doi: 10.1016/j.snb.2020.128802.
[17] Z. Zhao et al., “Advancements in electrochemical biosensing for respiratory virus detection: A review,” TrAC Trends in Analytical Chemistry, vol. 139, p. 116253, Jun. 2021, doi: 10.1016/j.trac.2021.116253.
[18] E. F. Greneker III, “<title>Radar sensing of heartbeat and respiration at a distance with security applications</title>,” in Radar Sensor Technology II, R. Trebits and J. L. Kurtz, Eds., SPIE, Jun. 1997, pp. 22–27. doi: 10.1117/12.276106.
[19] M. Cao, Q. Sun, X. Zhang, Y. Ma, and J. Wang, “Detection and differentiation of respiratory syncytial virus subgroups A and B with colorimetric toehold switch sensors in a paper-based cell-free system,” Biosens Bioelectron, vol. 182, p. 113173, Jun. 2021, doi: 10.1016/j.bios.2021.113173.
[20] L. Chen, M. Hu, N. Liu, G. Zhai, and S. X. Yang, “Collaborative use of RGB and thermal imaging for remote breathing rate measurement under realistic conditions,” Infrared Physics & Technology, vol. 111, p. 103504, Dec. 2020, doi: 10.1016/j.infrared.2020.103504.
[21] P. Viola and M. Jones, “Rapid object detection using a boosted cascade of simple features,” in Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001, in CVPR-01, vol. 1. IEEE Comput. Soc, pp. I-511–I–518. doi: 10.1109/cvpr.2001.990517.
[2] S.-D. Chen, “A new image quality measure for assessment of histogram equalization-based contrast enhancement techniques,” Digit Signal Process, vol. 22, no. 4, pp. 640–647, Jul. 2012, doi: 10.1016/j.dsp.2012.04.002.
[3] C. Piewbang, A. Rungsipipat, Y. Poovorawan, and S. Techangamsuwan, “Cross-sectional investigation and risk factor analysis of community-acquired and hospital-associated canine viral infectious respiratory disease complex,” Heliyon, vol. 5, no. 11, p. e02726, Nov. 2019, doi: 10.1016/j.heliyon.2019.e02726.
[4] V. S. Nallanthighal, Z. Mostaani, A. Härmä, H. Strik, and M. Magimai-Doss, “Deep learning architectures for estimating breathing signal and respiratory parameters from speech recordings,” Neural Networks, vol. 141, pp. 211–224, Sep. 2021, doi: 10.1016/j.neunet.2021.03.029.
[5] J. J. Feddema and E. Claassen, “Prevalence of viral respiratory infections amongst asthmatics: Results of a meta-regression analysis,” Respir Med, vol. 173, p. 106020, Nov. 2020, doi: 10.1016/j.rmed.2020.106020.
[6] Y. Zhang et al., “A novel point-of-care test of respiratory syncytial viral RNA based on cellulose-based purification and convective PCR,” Clinica Chimica Acta, vol. 511, pp. 154–159, Dec. 2020, doi: 10.1016/j.cca.2020.10.012.
[7] J. R. Machado Fernández and L. Anishchenko, “Mental stress detection using bioradar respiratory signals,” Biomed Signal Process Control, vol. 43, pp. 244–249, May 2018, doi: 10.1016/j.bspc.2018.03.006.
[8] S. S. Sai Koushik and K. G. Srinivasa, “Detection of respiratory diseases from chest X rays using Nesterov accelerated adaptive moment estimation,” Measurement, vol. 176, p. 109153, May 2021, doi: 10.1016/j.measurement.2021.109153.
[9] M. Abreu, A. Fred, J. Valente, C. Wang, and H. da Silva, “Morphological autoencoders for apnea detection in respiratory gating radiotherapy,” Comput Methods Programs Biomed, vol. 195, p. 105675, Oct. 2020, doi: 10.1016/j.cmpb.2020.105675.
[10] C. Bi et al., “Simultaneous detection and mutation surveillance of SARS-CoV-2 and multiple respiratory viruses by rapid field-deployable sequencing,” Med, vol. 2, no. 6, pp. 689-700.e4, Jun. 2021, doi: 10.1016/j.medj.2021.03.015.
[11] B. Jin, Y. Zhao, and Y. Liang, “RETRACTED: Internet of things medical image detection and pediatric renal failure dialysis complicated with respiratory tract infection,” Microprocess Microsyst, vol. 83, p. 104016, Jun. 2021, doi: 10.1016/j.micpro.2021.104016.
[12] C. Adrover-Jaume et al., “Paper biosensors for detecting elevated IL-6 levels in blood and respiratory samples from COVID-19 patients,” Sens Actuators B Chem, vol. 330, p. 129333, Mar. 2021, doi: 10.1016/j.snb.2020.129333.
[13] J. Zhang, Z. Yang, Q. Liu, and H. Liang, “Electrochemical biotoxicity detection on a microfluidic paper-based analytical device via cellular respiratory inhibition,” Talanta, vol. 202, pp. 384–391, Sep. 2019, doi: 10.1016/j.talanta.2019.05.031.
[14] S. Haridy, A. Maged, A. W. Baker, M. Shamsuzzaman, H. Bashir, and M. Xie, “Monitoring scheme for early detection of coronavirus and other respiratory virus outbreaks,” Computers & Industrial Engineering, vol. 156, p. 107235, Jun. 2021, doi: 10.1016/j.cie.2021.107235.
[15] B. V. Ribeiro, T. A. R. Cordeiro, G. R. e Freitas, L. F. Ferreira, and D. L. Franco, “Biosensors for the detection of respiratory viruses: A review,” Talanta Open, vol. 2, p. 100007, Dec. 2020, doi: 10.1016/j.talo.2020.100007.
[16] H. G. Lee et al., “PCR-coupled Paper-based Surface-enhanced Raman Scattering (SERS) Sensor for Rapid and Sensitive Detection of Respiratory Bacterial DNA,” Sens Actuators B Chem, vol. 326, p. 128802, Jan. 2021, doi: 10.1016/j.snb.2020.128802.
[17] Z. Zhao et al., “Advancements in electrochemical biosensing for respiratory virus detection: A review,” TrAC Trends in Analytical Chemistry, vol. 139, p. 116253, Jun. 2021, doi: 10.1016/j.trac.2021.116253.
[18] E. F. Greneker III, “<title>Radar sensing of heartbeat and respiration at a distance with security applications</title>,” in Radar Sensor Technology II, R. Trebits and J. L. Kurtz, Eds., SPIE, Jun. 1997, pp. 22–27. doi: 10.1117/12.276106.
[19] M. Cao, Q. Sun, X. Zhang, Y. Ma, and J. Wang, “Detection and differentiation of respiratory syncytial virus subgroups A and B with colorimetric toehold switch sensors in a paper-based cell-free system,” Biosens Bioelectron, vol. 182, p. 113173, Jun. 2021, doi: 10.1016/j.bios.2021.113173.
[20] L. Chen, M. Hu, N. Liu, G. Zhai, and S. X. Yang, “Collaborative use of RGB and thermal imaging for remote breathing rate measurement under realistic conditions,” Infrared Physics & Technology, vol. 111, p. 103504, Dec. 2020, doi: 10.1016/j.infrared.2020.103504.
[21] P. Viola and M. Jones, “Rapid object detection using a boosted cascade of simple features,” in Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001, in CVPR-01, vol. 1. IEEE Comput. Soc, pp. I-511–I–518. doi: 10.1109/cvpr.2001.990517.
Published
2025-01-29
How to Cite
Hasan Hussein, A. (2025). Leveraging Probabilistic Neural Networks For Early Detection Of Respiratory Viral Infection. CENTRAL ASIAN JOURNAL OF MATHEMATICAL THEORY AND COMPUTER SCIENCES, 6(1), 44-56. Retrieved from https://cajmtcs.centralasianstudies.org/index.php/CAJMTCS/article/view/717
Section
Articles
