| Tier | Subsystem | MSCW | Functional Requirements | I/o | Design Paremeters | Process Variable | AI/Non AI | Estimated | Cost | Quality |
| 1.0 Presentation Tier | 1.1 Register | M | 1.1.1 Registration mail id | Input | 1.1.1.1 Component to register with User ID | PYQT5 | NON-AI | 1 | Optional |
| | | | 1.1.2 User name | Input | 1.1.1.2 Component to register with user name | PYQT5 | NON-AL | 1 | Optional |
| | | | 1.1.3 DOB | Input | 1.1.1.3 Component to enter DOB while registering | PYQT5 | NON-AI | 1 | Optional |
| | | | 1.1.4 User Registration | Output | 1.1.1.4 Component for user for registration confirmation | PYQT5 | NON-AI | 2 | Optional |
| | 1.2 Login | M | 1.1.5 user Name and Password | Input | 1.1.1.5 Component for logging with user name and password | PYQT5 | NON-AL | 1 | Optional |
| | | | 1.1.6 forgot username and Passoword | Input | 1.1.1.6 Component for reseting password and user name | PYQT5 | NON-AI | 2 | Optional |
| | | | 1.1.7 Successful user login | Output | 1.1.1.7 Component for user login | PYQT5 | NON-AI | 1 | Optional |
| | 1.3 Training Data set | M,C | 1.1.8 Dropdown field to accept .CSV file | Input | 1.1.1.8 Component to train the algorithms with given data set and transfer to logic tier | PYQT5 | NON-AL | 2 | optional |
| | 1.4 Testing Data | M | 1.1.9 Patient age | Input | 1.1.1.9 Component to display age data | PYQT5 | NON-AI | 1 | optional |
| | | | 1.1.10 Gender | Input | 1.1.1.10 Component to display Gender data and to transfer to logic tier | PYQT5 | NON-AI | 1 | optional |
| | | | 1.1.11 Cholestrol | Input | 1.1.1.11 Component to display cholestrol data to transfer to logic tier | PYQT5 | NON-AL | 1 | optional |
| | | | 1.1.12 FBS | Input | 1.1.1.12 Component to display FBS data to transfer to logic tier | PYQT5 | NON-AI | 1 | optional |
| | | | 1.1.13 ECG | Input | 1.1.1.13 Component to display ECG data to transfer to logic tier | PYQT5 | NON-AI | 1 | optional |
| | | | 1.1.14 Weight | Input | 1.1.1.14 Component to display Weight data to transfer to logic tier | PYQT5 | NON-AL | 1 | optional |
| | | | 1.1.15 Tobacco | Input | 1.1.1.15 Component to display Tobacco data to transfer to logic tier | PYQT5 | NON-AI | 1 | optional |
| | | | 1.1.16 Alcohol | Input | 1.1.1.16 Component to display Alcohol data to transfer to logic tier | PYQT5 | NON-AI | 1 | optional |
| | | | 1.1.17 Smoking | Input | 1.1.1.17 Componenet to display Smoking data to transfer to logic tier | PYQT5 | NON-AL | 1 | optional |
| | | | 1.1.18 High BP | Input | 1.1.1.18 Component to display High BP data to transfer to logic tier | PYQT5 | NON-AI | 1 | optional |
| | | | 1.1.19 Low BP | Input | 1.1.1.19 Component to display Low BP data to transfer to logic tier | PYQT5 | NON-AI | 1 | optional |
| | | | 1.1.20 Diabetes | Input | 1.1.1.20 Component to display Diabetes data to transfer to logic tier | PYQT5 | NON-AL | 1 | optional |
| | | | 1.1.21 Stress | Input | 1.1.1.21 Component to display Stress data to transfer to logic tier | PYQT5 | NON-AI | 1 | optional |
| | 1.5 Result | C | 1.1.22 Accuracy | output | 1.1.1.22 Component to predict accuracy | PYQT5 | NON-AI | 1 | optional |
| | | | 1.1.23 Prediction | output | 1.1.1.23 Component to predict the disease | PYQT5 | NON-AL | 1 | optional |
| | | | 1.1.24 Graphs | Output | 1.1.1.24 Component to display the level of accuracy of both algorithms | PYQT5 | NON-AI | 1 | optional |
| 2.0 Logic Tier | 2.1 Implemetation of SVM algorithm | M | 2.1.1 All the functional requirements for testing data in presentation Tier | Input | 2.1.1.1 Component to predict the disease and store in Database Tier(SVM) | Python | AI | 5 | Optional |
| | 2.2 Result of SVM algorithm | M | 2.1.2 Calculating accuracy and predictions of SVM algorithm | Ouput | 2.1.1.2 Component to transfer result to presentation tier(SVM) | Python | AI | 3 | Optional |
| | 2.3 Implemetation of K-NN algorithm | M | 2.1.3 All the functional requirements for testing data in presentation Tier | Input | 2.1.1.3 Component to predict the disease and Store in Database tier(KNN) | Python | AI | 5 | Optional |
| | 2.4 Result of K-NN algorithm | M | 2.1.4 Calculating accuracy and predictions of K-NN algorithm | output | 2.1.1.4 Component to transfer result to presentation tier(KNN) | Python | AI | 5 | Optional |
| 3.0 Data Tier | 3.1 Database table for Training data set | M | 3.1.1 Storing of trained data that is used to predict | Input | 3.1.1.1 Component for trained data | Mysql | NON-AI | 3 | Optional |
| | | | 3.1.2 Transfering of Training data | output | 3.1.1.2 Component to transfer all the details to logic tier for processing | Mysql | NON-AI | 3 | Optional |
| | 3.2 Database table for Testing data set | M | 3.1.3 Storing for testing data | Input | 3.1.1.3 Component for testing data | Mysql | NON-AI | 3 | Optional |
| | | | 3.1.4 Transfering of testing data | output | 3.1.1.4 Component to transfer all the details to logic tier for processing | Mysql | NON-AI | 3 | Optional |
| | 3.3 Database table to store user data | M | 3.1.5 Storing of registration details | input | 3.1.1.5 Component to store all user details | Mysql | NON-AI | 3 | Optional |
| | | | 3.1.6 Transfering of user details | Output | 3.1.1.6 Component of user details to llogic tier for user details validation | Mysql | NON-AI | 3 | Optional |
Rama
DM.xlsx
