Academia.eduAcademia.edu

Figure 5 – uploaded by shavan askar

See full PDFdownloadDownload figure
Fig. 6. Comparative analysis of different evaluation methods using F1- score parameter.

Figure 6 Comparative analysis of different evaluation methods using F1- score parameter.

Related Figures (12)

Fig. 2. Demonstrates the proposed decision support system for heart disease diagnosis.
Fig. 2. Demonstrates the proposed decision support system for heart disease diagnosis.
Fig. 3. Computational procedure for computing the class of data. Both scanning and cascade structure are utilized in this work. The relevant feature for classification are chosen using scanning procedure, while classification and prediction task is conducted using cascade structure. The cascade structure contains four forest with four random tree and further, fifty trees are considered in each forest. The parameters values are taken same as presented in (Kumar, Mandal and Kumar, 2022) (Zhou and Feng, 2019). The working of cascade structure is demonstrated in Fig. 4. The features are given
Fig. 3. Computational procedure for computing the class of data. Both scanning and cascade structure are utilized in this work. The relevant feature for classification are chosen using scanning procedure, while classification and prediction task is conducted using cascade structure. The cascade structure contains four forest with four random tree and further, fifty trees are considered in each forest. The parameters values are taken same as presented in (Kumar, Mandal and Kumar, 2022) (Zhou and Feng, 2019). The working of cascade structure is demonstrated in Fig. 4. The features are given
Fig. 4. Cascade forest structure using four forest.
Fig. 4. Cascade forest structure using four forest.
THE DSS SysTEM ACCURACY SIMULATION RESULTS COMPARED TO OTHER TECHNIQUES \NN: Artificial neural network, SVM: Support vector machine, RNN: Recurrent neural network, LSTM: Long short-term memory, CNN: Convolutional neural network, DSS: Decisiot upport system TABLE II
THE DSS SysTEM ACCURACY SIMULATION RESULTS COMPARED TO OTHER TECHNIQUES \NN: Artificial neural network, SVM: Support vector machine, RNN: Recurrent neural network, LSTM: Long short-term memory, CNN: Convolutional neural network, DSS: Decisiot upport system TABLE II
SIMULATION RESULTS OF SPECIFICITY AND SENSITIVITY PROPOSED DSS AND OTHER EXITING MODELS/TECHNIQUES FOR HEART DISEASE PREDICTION ANN: Artificial neural network, SVM: Support vector machine, RNN: Recurrent neural network, LSTM: Long short-term memory, CNN: Convolutional neural network, DSS: Decisic support system TABLE IV
SIMULATION RESULTS OF SPECIFICITY AND SENSITIVITY PROPOSED DSS AND OTHER EXITING MODELS/TECHNIQUES FOR HEART DISEASE PREDICTION ANN: Artificial neural network, SVM: Support vector machine, RNN: Recurrent neural network, LSTM: Long short-term memory, CNN: Convolutional neural network, DSS: Decisic support system TABLE IV
Fig. 5. Comparative analysis of different evaluation methods using accuracy parameter.
Fig. 5. Comparative analysis of different evaluation methods using accuracy parameter.
Fig. 7. Comparative analysis of different evaluation methods using sensitivity parameter.
Fig. 7. Comparative analysis of different evaluation methods using sensitivity parameter.
Fig. 8. Comparative analysis of different evaluation methods using specificity parameter.
Fig. 8. Comparative analysis of different evaluation methods using specificity parameter.
Fig. 9. The area under the curve results proposed decision support system for prediction of heart disease.
Fig. 9. The area under the curve results proposed decision support system for prediction of heart disease.
Fig. 10. The area under the curve results proposed decision support system and other existing techniques/models.
Fig. 10. The area under the curve results proposed decision support system and other existing techniques/models.
Related topics:
Machine LearningFog ComputingInternet of Multimedia Things (IoMT)
580 California St., Suite 400
San Francisco, CA, 94104
© 2025 Academia. All rights reserved