HRAESN-IoT: A Hybrid Residual Attention and Echo State Network Approach for IoT-Enabled Heart Disease Prediction
Venkatesh BhandageDepartment of Computer Science and Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, Karnataka India. venkatesh.bhandage@manipal.edu0000-0002-9503-8196
Manjunath GDepartment of Electronics and Communication Engineering, B. N. M Institute of Technology, Bengaluru, Karnataka, India manjunathasuti@bnmit.in0000-0001-6577-7396
Nijaguna Gollara SiddappaDepartment of Information Science and Engineering, S.E.A College of Engineering and Technology, Bangalore, Karnataka, India. nijagunags@seaedu.ac.in0000-0002-9899-2161
Praveenkumar S ChallagidadDepartment of CSE (Data Science), Nagarjuna College of Engineering & Technology, Devanahalli, Bengaluru, Karnataka, India. praveenchallagidad@gmail.com0000-0003-4165-1822
Nirmalkumar S. BenniDepartment of Information Science and Engineering, RNS Institute of Technology, Channasandra, Bengaluru, Karnataka, India. nirmalkumarsbenni@rnsit.ac.in0000-0002-5164-8160
Cenitta D. Department of Computer Science and Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, Karnataka, India. cenitta.d@manipal.edu0000-0003-3715-6941
R. Vijaya ArjunanDepartment of Computer Science and Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, Karnataka, India. vijay.arjun@manipal.edu0000-0002-1402-6573
Keywords: IoT, Heart Disease Prediction, Ischemic Heart Disease (IHD), Deep Learning, Attention Residual Learning, Echo State Network (ESN), Cardiovascular Disease, Real-Time Monitoring, Medical Diagnosis, Wearable Sensors.
Abstract
Detection of Ischemic Heart Disease needs immediate accurate identifications since incorrect medical assessments lead to serious outcomes. A perfect heart disease prediction model must combine deep learning techniques with the Internet of Things (IoT) for achieving diagnoses of high accuracy. The authors present HRAESN-IoT as a real-time IHD severity prediction method that retrieves patient data from wearable sensors enabled by Internet of Things technology. Using attention residual learning together with Echo State Network (ESN) the model discovers significant medical patterns along with maintaining stable learning for time-dependent predictions. HRAESN-IoT incorporates IoT technology to continuously monitor patients which leads to real-time detection of IHD severity especially for early diagnosis. The model achieves 97.2% accuracy when tested on the Kaggle cardiovascular illness dataset that contains 70,000 cases. This method delivers better results compared to existing models implying its capability to develop customized therapeutic plans and rapid cardiac disease detection in real-time. Keywords: IoT, Heart Disease Prediction, Ischemic Heart Disease (IHD), Deep Learning, Attention Residual Learning, Echo State Network (ESN), Cardiovascular Disease, Real-Time Monitoring, Medical Diagnosis, Wearable Sensors.