TY - GEN
T1 - DLHAP
T2 - 9th International Conference on Innovations in Computer Science and Engineering, ICICSE 2021
AU - Pokkuluri, Kiran Sree
AU - Usha Devi, N. S.S.S.N.
AU - Mangalampalli, Sudheer
N1 - Publisher Copyright:
© 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
PY - 2022
Y1 - 2022
N2 - Heart attack prediction is pronounced as one of the dynamic and real-time problems faced by the world. The analysis of clinical data is a big challenge for predicting these types of diseases. Many machine learning algorithms and other methods are developed to predict this heart attack. Still there is a need for standardization of prediction and room for improvement. We have collected datasets from UCI machine learning repository consisting of thirteen attributes. We have applied a recurrent neural network (RNN) augmented with hybrid cellular automata (HCA) to process 76,467 thousand datasets to train and test the classifier. We have considered classifier accuracy, error, F-measure, specificity, precision, and sensitivity parameters to compare our work with various baseline methods. The DLHAP (Deep Learning for Heart Attract Prediction) model has reported accuracy of 94.73%, which is 3.79% more compared with the standard methods cited in the literature.
AB - Heart attack prediction is pronounced as one of the dynamic and real-time problems faced by the world. The analysis of clinical data is a big challenge for predicting these types of diseases. Many machine learning algorithms and other methods are developed to predict this heart attack. Still there is a need for standardization of prediction and room for improvement. We have collected datasets from UCI machine learning repository consisting of thirteen attributes. We have applied a recurrent neural network (RNN) augmented with hybrid cellular automata (HCA) to process 76,467 thousand datasets to train and test the classifier. We have considered classifier accuracy, error, F-measure, specificity, precision, and sensitivity parameters to compare our work with various baseline methods. The DLHAP (Deep Learning for Heart Attract Prediction) model has reported accuracy of 94.73%, which is 3.79% more compared with the standard methods cited in the literature.
UR - https://www.scopus.com/pages/publications/85127654572
UR - https://www.scopus.com/pages/publications/85127654572#tab=citedBy
U2 - 10.1007/978-981-16-8987-1_32
DO - 10.1007/978-981-16-8987-1_32
M3 - Conference contribution
AN - SCOPUS:85127654572
SN - 9789811689864
T3 - Lecture Notes in Networks and Systems
SP - 307
EP - 313
BT - Innovations in Computer Science and Engineering - Proceedings of the 9th ICICSE, 2021
A2 - Saini, H. S.
A2 - Sayal, Rishi
A2 - Govardhan, A.
A2 - Buyya, Rajkumar
PB - Springer Science and Business Media Deutschland GmbH
Y2 - 3 September 2021 through 4 September 2021
ER -