| (i) | Input: decision table. |
| (ii) | Output: A relative attribute reduction of decision table. |
| (iii) | Stage 1:Find core attribute in parallel |
| (iv) | Step 1: Each process assigns attributes as according to label and drawer principle, and meets. |
| (v) | Step 2: Each process computes the core attribute in. |
| (vi) | Step 3: Each process exchanges the core attribute with each other, and obtains the final core attribute.. |
| (vii) | Stage 2: Prejudge whether the core attribute is the result of reduction |
| (viii) | |
| (ix) | Stage 3. Step 1 |
| (x) | Stage 3: Attribute expansion stage |
| (xi) | Step 1: Calculate the attributes to be added,. |
| (xii) | Step 2: Each process assigns attributes as according to label and drawer principle, and meets the following condition . |
| (xiii) | Step 3: Each process computes the best attributes to be added . |
| (xiv) | Step 4: Each process sends the results of the calculations in Step3 to the main process.. |
| (xv) | Step 5: The main process receives calculation results of each process and calculates the attribute that is best to be added.. |
| (xvi) | Then main process distributes the results,. |
| (xvii) | Step 6: Each process accepts the calculation results of the main process and updates the reduction results. ,; |
| (xviii) | Step 7: If goto Stage4 |
| (xix) | else goto Stage 3. Step 2; |
| (xx) | Stage 4:Attribute compression stage |
| (xxi)Step 1: Calculate the properties needed to be checked, . |
| (xxii)Step 2: Each process checks whether can be removed according to its. , send to main process |
| (xxiii)else Send -1 to main process. |
| (xxiv)Step 3: The main process receives the calculation result of the sub process, select one attribute to compress and distribute the results. |
| (xxv)Step 4: Each process updates the compression results ; ; |
| (xxvi)Step 5: return |
| (xxvii)else goto Stage 4.Step 2. |
