Please use this identifier to cite or link to this item:
http://hdl.handle.net/10603/441349
Title: | Hybrid association and optimization based mining to detect and predict heart diseases |
Researcher: | Heena Farheen Ansari |
Guide(s): | Varsha Namdeo |
Keywords: | Computer Science Computer Science Interdisciplinary Applications Engineering and Technology |
University: | Sarvepalli Radhakrishnan University |
Completed Date: | 2020 |
Abstract: | ABSTRACT newlineIn this work, the case of heart disease data classification has been considered. The growth is observed to be the most dangerous for the men and women worldwide now days. The impact is turning out to be rapidly on the world. The main aim is to analyses the impact of different data mining and other related techniques for the efficient heart disease prediction. This work main focus is to efficiently classify the heart disease database. newlineThe aim is to analyses the collision of dissimilar data mining and other associated techniques for the proficient heart disease prediction. The current trends in the direction of heart disease prediction from different dataset have been explained. It focuses on the dataset used and methodological achievements. It also includes the current death rates along with the comparative study from the previous trends to show the horrible statics worldwide. The statics have been considered from world health organization (WHO). This analysis is based on the three factors, first those methods have been considered, which is used for the prediction system, second the combination of method impacts and the gap analysis based on the result discussion. Based on this problem statements have been highlighted, discussed and the future impacts have been suggested. newlineAn efficient Span-K-nearest neighbors (KNN) and ant colony optimization (ACO) algorithms have been proposed. It has been suggested for the efficient classification and categorization. It has been shown for the two cases either the disease chance is yes or the chances are no. For the case constraints a range has been considered for the categorization. It is between 100 to 250. ACO is used here as a final data classifier. In this approach the data are first uploaded in the proposed framework for pre-processing. For the experimentation three variant attributes have been considered. For the comparison 2-4 has been considered. This step is needed with the KNN approach. The ranges for the comparison have been considered from 100 to 250. ACO is |
Pagination: | |
URI: | http://hdl.handle.net/10603/441349 |
Appears in Departments: | COMPUTER SCIENCE & ENGINEERING |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
10 chapter 6.pdf | Attached File | 165.4 kB | Adobe PDF | View/Open |
12 annexures.pdf | 188.5 kB | Adobe PDF | View/Open | |
1 title.pdf | 83.83 kB | Adobe PDF | View/Open | |
2 prilim page.pdf | 281.46 kB | Adobe PDF | View/Open | |
3 contents.pdf | 78.58 kB | Adobe PDF | View/Open | |
4 abtract.pdf | 77.62 kB | Adobe PDF | View/Open | |
5 chapter 1.pdf | 219.4 kB | Adobe PDF | View/Open | |
6 chapter 2.pdf | 107.85 kB | Adobe PDF | View/Open | |
7 chapter 3.pdf | 77.68 kB | Adobe PDF | View/Open | |
80_recommendation.pdf | 128.02 kB | Adobe PDF | View/Open | |
8 chapter 4.pdf | 174.13 kB | Adobe PDF | View/Open | |
9 chapter 5.pdf | 2.96 MB | Adobe PDF | View/Open |
Items in Shodhganga are licensed under Creative Commons Licence Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0).
Altmetric Badge: