Classification Based on both Attribute Value Weight and Tuple Weight under the Cloud Computing

Algorithm 1

Classification based on both attribute value weight and tuple weight (CATW).

Input: Training set 𝐷=𝑃∪𝑁 (𝑃 and 𝑁 are the sets of all positive and negative example, respectively)

Output: A set of rules for predicting class labels for examples

Procedure CATW

 attributeWeight←𝛼

 tupleWeight←𝛽

 tupleThreshold←𝜆

 rules ← null

 while |𝑃|>0

  𝑁^′←𝑁, 𝑃^′←𝑃

  𝑟←null

  while |𝑁|>0 and r.length<max_rule_length

   find the best attribute value av use the improved correlation measure combine tuple weight with attribute weight

   add av to 𝑟

   remove from 𝑃^′ all examples not satisfying 𝑟

   remove from 𝑁^′ all examples not satisfying 𝑟

  end

  add 𝑟 to rules

  for each attribute at that is included in antecedent of 𝑟 in 𝑃

   at.weight←attributeWeight∗at.weight

  end

  for each example 𝑡 in 𝑃 satisfying 𝑟’s body

   t.weight←tupleWeight∗t.weight

   if t.weight<tupleThreshold then remove 𝑡 from 𝑃

  end

 end

return rules