Browsing by Author "AL-OBAIDI, ANMAR SADEQ JASIM"
Now showing 1 - 1 of 1
Results Per Page
Sort Options
Item NOVEL SOFTWARE DEFECT PREDICTION METHOD BASED ON PCA AND OPTIMIZED LSTM(2022-01-10) AL-OBAIDI, ANMAR SADEQ JASIM; MISHRA, Alok; YAZICI, AliIn this thesis, new approach presented for software defect prediction applying PCA based LSTM. This study consists from two parts feature selection executed by PCA and classification part executed by LSTM. The aim applying PCA as feature selection is to reduce the size of input features to decrease the computation time by removing unaffected features. Then, the output of PCA wired to the LSTM that is time series classifier which classify the input software defect features to the two classes (defect and normal). The PSO applied to optimize the performance of the LSTM by updating the weight and basis of the LSTM to obtain best accuracy. The obtained results compared with common studies presented in this field.