ارائه روشی ترکیبی جهت تشخیص بیماری قلبی با بهره گیری از رویکردهای انتخاب ویژگی تلفیقی و طبقه بندی بهینه

چکیده مقاله :

بیماری‌های قلبی یکی از مهم‌ترین عوامل مرگ‌ومیر در جهان محسوب می‌شوند و تشخیص زودهنگام آنها از اهمیت بالایی برخوردار است. روش‌های موجود در انتخاب ویژگی برای تشخیص بیماری قلبی معمولاً محدود به استفاده از یک الگوریتم واحد بوده و ممکن است منجر به انتخاب ویژگی‌های زائد یا حذف ویژگی‌های مهم شوند که این امر دقت طبقه‌بندی را کاهش می‌دهد. در این مقاله، روش ترکیبی جدیدی برای انتخاب ویژگی ارائه شده که با بهره‌گیری از تلفیق نرم نتایج چند الگوریتم انتخاب ویژگی، ویژگی‌های کارآمدتر و مرتبط‌تر شناسایی می‌شوند. همچنین برای افزایش دقت و سرعت تشخیص، از طبقه‌بندی ماشین یادگیری حداکثری با کرنل موجک استفاده شده که پارامترهای آن توسط نسخه اصلاح‌شده الگوریتم فراابتکاری قورباغه بهینه می‌شوند. این الگوریتم اصلاح‌شده شامل مکانیزم وزن‌دهی پویا و ترکیب با الگوریتم ژنتیک می‌باشد که به بهبود دقت و سرعت طبقه‌بندی کمک می‌کند. برای اثبات توانمندی و تعمیم‌پذیری روش، آن بر روی سه مجموعه داده معتبر UCI آزمایش شده که نتایج ارزیابی نشان می‌دهند دقت مدل پیشنهادی به 3_/93% رسیده است. نتایج بیانگر توانمندی و تعمیم‌پذیری بالای روش پیشنهادی در تشخیص بیماری قلبی می‌باشد.

چکیده انگلیسی :

Heart disease is one of the leading causes of mortality worldwide, and its early diagnosis is of great importance. Existing feature selection methods for heart disease diagnosis are typically limited to using a single algorithm, which may lead to the selection of redundant features or the omission of important ones, consequently reducing classification accuracy. In this paper, a novel hybrid method for feature selection is proposed, which identifies more efficient and relevant features by employing a soft integration of the results from multiple feature selection algorithms. To enhance the accuracy and speed of diagnosis, an Extreme Learning Machine (ELM) classifier with a wavelet kernel is utilized, where its parameters are optimized using a modified version of the Shuffled Frog-Leaping Algorithm (SFLA). The improved algorithm incorporates a dynamic weighting mechanism and is combined with a Genetic Algorithm (GA), contributing to improved classification accuracy and speed. To demonstrate the robustness and generalizability of the proposed method, it is tested on three well-known UCI datasets. Evaluation results show that the proposed model achieves an accuracy of 93.3%. These findings highlight the high capability and generalization power of the proposed method in heart disease diagnosis.

منابع و مأخذ:

[1] E. J. Nelwan, E. Widjajanto, S. Andarini, and M. S. Djati, "Modified risk factors for coronary heart disease (CHD) in Minahasa ethnic group from Manado city Indonesia," J. of Experimental Life Science, vol. 6, no. 2, pp. 88-94, Apr. 2017.
[2] C. J. Taylor and J. Moore, "NICE chronic heart failure update guideline 2018," Primary Care Cardiovascular J., vol. 3, no. 9, pp. 1-3, Apr. 2019.
[3] S. Citlik-Saritas, S. Saritas, R. Cevik-Akyil, and K. Isik, "The effects of Turkish classical music on physiological parameters, pain and analgesic use in patients with myocardial infarction: a non-randomized controlled study," Eur. J. of Integrative Medicine, vol. 22, pp. 50-53, Sept. 2018.
[4] M. Adam, et al., "Automated characterization of cardiovascular diseases using relative wavelet nonlinear features extracted from ECG signals," Comput. Methods and Programs in Biomedicine, vol. 161, pp. 133-143, Jul. 2018.
[5] M. Kolahkaj, A. Harounabadi, and M. Sadeghzade, "A recommender system for web mining using neural network and fuzzy algorithm," Int. J. of Computer Applications, vol. 78, no. 8, pp. 20-24, Sept. 2013.
[6] م. کلاه¬کج، "ارائه سیستم بازیابی تصاویر مبتنی بر محتوا با بهره‌گیری از یادگیری نیمه¬نظارت‌شده و کاوش الگوهای مکرر انجمنی،" نشریه مهندسی برق و مهندسی کامپیوتر ایران، ب- مهندسی کامپیوتر، سال 20، شماره 3، صص. 252-245، پاییز 1401.
[7] K. Oh, Z. Li, B. S. Oh, and K. A. Toh, "Optimizing between data transformation and parametric weighting for stable binary classification," J. of the Franklin Institute, vol. 355, no. 4, pp. 1614-1637, Mar. 2018.
[8] M. Kolahkaj, "An image retrieval approach based on feature extraction and self-supervised learning," in Proc. 2nd Int. Conf. on Distributed Computing and High-Performance Computing, pp. 46-51, Qom, Iran, 2-3 Mar. 2022.
[9] C. Berry, D. R. Murdoch, and J. J. McMurray, "Economics of chronic heart failure," Eur. J. of Heart Failure, vol. 3, no. 3, pp. 283-291, Jun. 2001.
[10] J. C. de la Torre, "Hemodynamic instability in heart failure intensifies age-dependent cognitive decline," J. of Alzheimer's Disease, vol. 76, no. 1, pp. 63–84, May 2020.
[11] H. Linusson, U. Johansson, H. Boström, and T. Löfström, "Classification with reject option using conformal prediction," in Proc. Pacific-Asia Conf. on Knowledge Discovery and Data Mining, pp. 94-105, Melbourne, Australia, 3-6 Jun. 2018.
[12] J. Qiu, J. Xie, D. Zhang, and R. Zhang, "A robust twin support vector machine based on fuzzy systems," Int. J. of Intelligent Computing and Cybernetics, vol. 17, no. 1, pp. 101-125, Feb. 2024.
[13] B. Sahmadi and D. Boughaci, "Hybrid genetic algorithm with SVM for medical data classification," in Proc. Int. Conf. on Applied Smart Systems, 6 pp., Medea, Algeria, 24-25 Nov. 2018.
[14] S. Chen, J. Cao, F. Chen, and B. Liu, "Entropy-based fuzzy least squares twin support vector machine for pattern classification," Neural Processing Letters, vol. 51, no. 1, pp. 41-66, Feb. 2020.
[15] Z. Zainuddin, K. H. Lai, and P. Ong, "An enhanced harmony searches-based algorithm for feature selection: applications in epileptic seizure detection and prediction," Computers & Electrical Engineering, vol. 53, pp. 143-162, Jul. 2016.
[16] M. Nekkaa and D. Boughaci, "Hybrid harmony search combined with stochastic local search for feature selection," Neural Processing Letters, vol. 44, no. 1, pp. 199-220, Aug. 2016.
[17] D. Karaboga and C. Ozturk, "A novel clustering approach: artificial bee colony (ABC) algorithm," Appl. Soft Computing, vol. 11, no. 1, pp. 652-657, Jan. 2011.
[18] P. Tapkan, L. Özbakır, S. Kulluk, and A. Baykasoğlu, "A cost-sensitive classification algorithm: BEE-Miner," Knowledge-Based Systems, vol. 95, pp. 99-113, Mar. 2016.
[19] X. Lai, Z. Zhang, H. Chen, L. Zhang, Z. Li, and W. Lu, "Tracking-removed neural network with graph information for classification of incomplete data," Appl. Intelligence, vol. 55, no. 3, pp. 1-20, Feb. 2025.
[20] J. Wu, S. Pan, X. Zhu, P. Zhang, and C. Zhang, "Sode: self-adaptive one-dependence estimators for classification," Pattern Recognition, vol. 51, pp. 358-377, Mar. 2016.
[21] X. Zhu, et al., "Confidence guided semi-supervised cross-modality person re-identification," Pattern Recognition, vol. 165, Article ID: 111669, Sept. 2025.
[22] X. Wang, G. Wu, G. Hao, and Z. Zhang, "A novel fuzzy twin support vector machine using mass-based dissimilarity measure," Knowledge and Information Systems, vol. 55, no. 5, pp. 4233-4300, Jan. 2025.
[23] B. Aydïlek, "Examining effects of the support vector machines kernel types on biomedical data classification," in Proc. Int. Conf. on Artificial Intelligence and Data Processing, 4 pp., Maltaya, Turkey, 28-30 Sept. 2018.
[24] S. Chen, J. Cao, and Z. Huang, "Weighted linear loss projection twin support vector machine for pattern classification," IEEE Access, vol. 7, pp. 57349-57360, 2019.
[25] S. Lee and C. H. Jun, "Fast incremental learning of logistic model tree using least angle regression," Expert Systems with Applications, vol. 97, pp. 137-145, May 2018.
[26] H. Wang, P. Li, Y. Zheng, K. Jiang, and Y. Xu, "Sparse pinball universum nonparallel support vector machine and its safe screening rule," Appl. Intelligence, vol. 55, no. 6, pp. 563-580, Apr. 2025.
[27] C. T. Tran, M. Zhang, P. Andreae, B. Xue, and L. T. Bui, "An effective and efficient approach to classification with incomplete data," Knowledge-Based Systems, vol. 154, pp. 1-16, Aug. 2018.
[28] A. K. Jović, K. Brkić, and N. Bogunović, "A review of feature selection methods with applications," in Proc. 38th Int. Convention on Information and Communication Technology, Electronics and Microelectronics, pp. 1200-1205, Opatija, Croatia, 25-29 May 2015.
[29] J. Hamidzadeh, Z. Mehravaran, and A. Harati, "Feature selection by utilizing kernel-based fuzzy rough set and entropy-based non-dominated sorting genetic algorithm in multi-label data," Knowledge and Information Systems, vol. 67, no. 4, pp. 3789–3819, Apr. 2025.
[30] S. Narayanamoorthy, S. Geetha, R. Rakkiyappan, and Y. H. Joo, "Interval-valued intuitionistic hesitant fuzzy entropy based VIKOR method for industrial robots' selection," Expert Systems with Applications, vol. 121, pp. 28-37, May 2019.
[31] I. Kadhim Ajlan, H. Murad, A. A. Salim, and A. Fadhil Bin Yousif, "Extreme learning machine algorithm for breast cancer diagnosis," Multimedia Tools and Applications, vol. 84, pp. 14739-14758, 2024.
[32] X. Zhang, X. Hu, G. Cui, Y. Wang, and Y. Niu, "An improved shuffled frog leaping algorithm with cognitive behavior," in Proc. 7th World Congress on Intelligent Control and Automation, pp. 6197-6202, Chongqing, China, 25-27, Jun. 2008.
[33] UCI Machine Learning Repository, Heart Disease, 1988, available at https://www.archive.ics.uci.edu/ml/datasets/Heart+Disease
[34] G. Moody and R. Mark, MIT-BIH Arrhythmia Database, 2025, available at https://physionet.org/content/mitdb/1.0.0/
[35] J. Wu, S. Pan, X. Zhu, Z. Cai, P. Zhang, and C. Zhang, "Self-adaptive attribute weighting for Naive Bayes classification," Expert Systems with Applications, vol. 42, no. 3, pp. 1487-1502, Feb. 2015.
[36] P. Shunmugapriya and S. Kanmani, "A hybrid algorithm using ant and bee colony optimization for feature selection and classification (AC-ABC Hybrid)," Swarm and Evolutionary Computation, vol. 36, pp. 27-36, Oct. 2017.
[37] X. J. Shen, Y. Dong, J. P. Gou, Y. Z. Zhan, and J. Fan, "Least squares kernel ensemble regression in reproducing kernel Hilbert space," Neurocomputing, vol. 311, pp. 235-244, Oct. 2018.
[38] C. Yang and X. C. Yin, "Diversity-based random forests with sample weight learning," Cognitive Computation, vol. 11, no. 5, pp. 685-696, Oct. 2019.