Fusion-Based Deep Learning Framework Detection Using an Optimized for Cardiovascular Disease Squeeze Net Model
محورهای موضوعی : Pattern Recognition
1 - Department of Computer Science and Engineering, BVRIT HYDERABAD College of Engineering for Women, Hyderabad, India
کلید واژه: Electrocardiogram (ECG), Data Mining, Pattern Mining, Optimization Search Algorithm (OSA), Squeeze Net (OSA-SN),
چکیده مقاله :
The electrocardiogram (ECG), which measures the electrical activity of the heart, is frequently used to identify heart conditions because it is simple and non-invasive. The primary focus of the analysis is on the fusion of action impulse patterns produced by the heart’s specialized cardiac tissues. It is possible to detect any irregularities in the heart by closely examining the electrical signal generated with each heartbeat. Since the application of data mining technology in healthcare has greatly increased knowledge, data mining is becoming a more and more popular option in the medical field. This study uses a hybridized algorithm for pattern mining in order to categorize heartbeats. First, the input data from the ECG signal is pre- processed using a median filter, and then the features are extracted. Both statistical and medical aspects are included in these extracted features. Activity pattern mining using the Optimization Search Algorithm (OSA), a hybridized optimization algorithm, is the next step. Lastly, the rule matrix produced by the mining of activity patterns is used to categorize heartbeats. This research proposes a deep learning-based framework for the classification of cardiovascular diseases using electrocardiogram (ECG) signals. A hybrid optimization technique, integrating the Taylor series and Ebola Optimization Search Algorithm (OSA), termed OSA-SN, is introduced to enhance the performance of a lightweight convolutional neural network model, SqueezeNet. The ECG signals undergo preprocessing and feature extraction, followed by sequential pattern mining using the proposed optimization strategy. The optimized model achieves superior performance metrics, with a precision of 0.93, sensitivity of 0.94, and specificity of 0.91. These results demonstrate the potential of the OSA-SN-enhanced SqueezeNet model in accurate, real-time heartbeat classification for clinical applications.
The electrocardiogram (ECG), which measures the electrical activity of the heart, is frequently used to identify heart conditions because it is simple and non-invasive. The primary focus of the analysis is on the fusion of action impulse patterns produced by the heart’s specialized cardiac tissues. It is possible to detect any irregularities in the heart by closely examining the electrical signal generated with each heartbeat. Since the application of data mining technology in healthcare has greatly increased knowledge, data mining is becoming a more and more popular option in the medical field. This study uses a hybridized algorithm for pattern mining in order to categorize heartbeats. First, the input data from the ECG signal is pre- processed using a median filter, and then the features are extracted. Both statistical and medical aspects are included in these extracted features. Activity pattern mining using the Optimization Search Algorithm (OSA), a hybridized optimization algorithm, is the next step. Lastly, the rule matrix produced by the mining of activity patterns is used to categorize heartbeats. This research proposes a deep learning-based framework for the classification of cardiovascular diseases using electrocardiogram (ECG) signals. A hybrid optimization technique, integrating the Taylor series and Ebola Optimization Search Algorithm (OSA), termed OSA-SN, is introduced to enhance the performance of a lightweight convolutional neural network model, SqueezeNet. The ECG signals undergo preprocessing and feature extraction, followed by sequential pattern mining using the proposed optimization strategy. The optimized model achieves superior performance metrics, with a precision of 0.93, sensitivity of 0.94, and specificity of 0.91. These results demonstrate the potential of the OSA-SN-enhanced SqueezeNet model in accurate, real-time heartbeat classification for clinical applications.
[1] M. Sornalakshmi, S. Balamurali, M. Venkatesulu, M. N. Krishnan, L. K. Ramasamy, S. Kadry, and S. Lim, “An efficient apriori algorithm for frequent pattern mining using mapreduce in healthcare data,” Bulletin of Electrical Engineering and Informatics, vol. 10, no. 1, pp. 390–403, 2021.
[2] X. Chang, C. Zhou, Z. Wang, and P. Hu, “A novel method for mining sequential patterns in datasets,” in Sixth International Conference on Intelligent Systems Design and Applications, vol. 1. IEEE, 2006, pp. 611–615.
[3] H. Estiri, S. Vasey, and S. N. Murphy, “Transitive sequential pattern mining for discrete clinical data,” in Artificial Intelligence in Medicine: 18th International Conference on Artificial Intelligence in Medicine, AIME 2020, Minneapolis, MN, USA, August 25–28, 2020, Proceedings 18. Springer, 2020, pp. 414–424.
[4] S. B. Golas, T. Shibahara, S. Agboola, H. Otaki, J. Sato, T. Nakae, T. Hisamitsu, G. Kojima, J. Felsted, S. Kakarmath et al., “A machine learning model to predict the risk of 30-day readmissions in patients with heart failure: a retrospective analysis of electronic medical records data,” BMC medical informatics and decision making, vol. 18, no. 1, pp. 1–17, 2018.
[5] N. Bala, S. N. Price, C. M. Horan, M. W. Gerber, and E. M. Taveras, “Use of telehealth to enhance care in a family-centered childhood obesity intervention,” Clinical Pediatrics, vol. 58, no. 7, pp. 789– 797, 2019.
[6] F. N. Iandola, S. Han, M. W. Moskewicz, K. Ashraf, W. J. Dally, and K. Keutzer, “Squeezenet: Alexnet-level accuracy with 50x fewer parameters and¡ 0.5 mb model size,” arXiv preprint arXiv:1602.07360, 2016.
[7] H. Yoo, S. Han, and K. Chung, “A frequency pattern mining model based on deep neural network for real-time classification of heart conditions,” in Healthcare, vol. 8, no. 3. MDPI, 2020, p. 234.
[8] J. Jin, W. Sun, F. Al-Turjman, M. B. Khan, and X. Yang, “Activity pattern mining for healthcare,” Ieee Access, vol. 8, pp. 56730– 56738, 2020.
[9] S. A. Mangai, B. R. Sankar, and K. Alagarsamy, “Taylor series prediction of time series data with error propagated by artificial neural network,” International Journal of Computer Applications, vol. 89, no. 1, 2014.
[10]M. Shanmuga Sundari and V. C. Jadala, “Neurological disease prediction using impaired gait analysis for foot position in cerebellar ataxia by ensemble approach,” Automatika, vol. 64, no. 3, pp. 541– 550, 2023.
[11]S. Zhou, J. He, H. Yang, D. Chen, and R. Zhang, “Big data-driven abnormal behavior detection in healthcare based on association rules,” IEEE Access, vol. 8, pp. 129002–129011, 2020.
[12]Iandola, F. N., Han, S., Moskewicz, M. W., Ashraf, K., Dally, W. J., & Keutzer, K. (2016). SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and< 0.5 MB model size. arXiv preprint arXiv:1602.07360.
[13]Sornalakshmi, M., Balamurali, S., Venkatesulu, M., Krishnan, M. N., Ramasamy, L. K., Kadry, S., & Lim, S. (2021). An efficient Apriori algorithm for frequent pattern mining using MapReduce in healthcare data. Bulletin of Electrical Engineering and Informatics, 10(1), 390–403.
[14]Yoo, H., Han, S., & Chung, K. (2020). A frequency pattern mining model based on deep neural network for real-time classification of heart conditions. Healthcare, 8(3), 234.
[15]Estiri, H., Vasey, S., & Murphy, S. N. (2020). Transitive sequential pattern mining for discrete clinical data. In Artificial Intelligence in Medicine: 18th International Conference on Artificial Intelligence in Medicine, AIME 2020, Minneapolis, MN, USA, August 25–28, 2020, Proceedings (pp. 414–424). Springer.
[16]Jin, J., Sun, W., Al-Turjman, F., Khan, M. B., & Yang, X. (2020). Activity pattern mining for healthcare. IEEE Access, 8, 56730–56738.
[17]Ahmed, S. A., & Nath, B. (2020). Adverse disease agent identification using FP-Growth algorithm in healthcare data mining. Journal of King Saud University-Computer and Information Sciences. Advance online publication.
[18]L. Penninga, A. K. Lorentzen, and C. Davis, “A telemedicine case series for acute medical emergencies in greenland: a model for austere environments,” Telemedicine and e-Health, vol. 26, no. 8, pp. 1066–1070, 2020.
[19]O. N. Oyelade and A. E. Ezugwu, “Ebola optimization search algorithm (eosa): A new metaheuristic algorithm based on the propagation model of ebola virus disease,” arXiv preprint arXiv:2106.01416, 2021.
[20]V. C. Jadala et al., “Real-time neurological disease prediction with 3d single pose estimation using mediapipe,” International Journal of Intelligent Systems and Applications in Engineering, vol. 12, no. 4s, pp. 595–607, 2024.
[21]V. C. Jadala, S. K. Pasupuleti, P. Yellamma et al., “Deep learning analysis using resnet for early detection of cerebellar ataxia disease,” in 2022 International Conference on Advancements in Smart, Secure and Intelligent Computing (ASSIC). IEEE, 2022, pp.
[22]Bindu, V., Sundari, M. S., Pasupuleti, P., Shaik, R., & Pochareddy, J. (2024, November). Revolutionizing Skin Disease Diagnosis: Advanced Image Analysis and Precision Healthcare using EfficientNet. In 2024 8th International Conference on Electronics, Communication and Aerospace Technology (ICECA) (pp. 604-608). IEEE.–6.
[23]J.-S. Kang, D.-H. Shin, J.-W. Baek, and K. Chung, “Activity recommendation model using rank correlation for chronic stress management,” Applied Sciences, vol. 9, no. 20, p. 4284, 2019.
[24]J.-S. Kang, J.-W. Baek, and K. Chung, “Prefixspan based pattern mining using time sliding weight from streaming data,” IEEE Access, vol. 8, pp. 124833–124844, 2020.
[25]K. K. Mohbey and S. Kumar, “A parallel approach for high utilitybased frequent pattern mining in a big data environment,” Iran Journal of Computer Science, vol. 4, no. 3, pp. 195–200, 2021.
[26] Mariyappan, S. S., Penthala, H. R., Nagaram, A., & Arisham, D. (2024, July). Retina fundus disease gray scale image perception using semantic segmentation model. In AIP Conference Proceedings (Vol. 3028, No. 1). AIP Publishing.
