Proceeding IEEE Xplore - Combining Integreted Sampling Technique with Feature Selection for Software Defect Prediction

Good quality software is a supporting factor that is important in any line of work in of society. But the software component defective or damaged resulting in reduced performance of the work, and can increase the cost of development and maintenance. An accurate prediction on software module prone defects as part of efforts to reduce the increasing cost of development and maintenance of software. An accurate prediction on software module prone defects as part of efforts to reduce the increasing cost of development and maintenance of software. From the results of these studies are known, there are two problems that can decrease performance prediction of classifiers such imbalances in the distribution of the class and irrelevant of the attributes that exist in the dataset. So as to handle both of these issues, we conducted this research using integrated a sample technique with feature selection method. Based on research done previously, there are two methods of samples including random under sampling and SMOTE for random over sampling. While on feature selection method such as chi square, information gain and relief methods. After doing the research process, integration SMOTE technique with relief method used on Naïve Bayes classifiers, the result of the predicted value better than any other method that is 82%.

If you want to know more details from this research please visit the IEEE Xplore website as follows:
Combining Integreted Sampling Technique with Feature Selection for Software Defect Prediction

Read more...

Agustus 2017 - CITSM 2017

Pada tanggal 8-10 Agustus 2017 bertempat di STIKOM Bali saya berkesempatan hadir di The 5th International Conference on Information Technology for Cyber and IT Services Management (CITSM 2017).

Pada rangkaian CITSM 2017 saya tidak hanya mengikuti rangkaian seminar yang disampaikan oleh keynote speech yang membahas mengenai gelombang suhu manusia yang dapat dimanfaat sebagai kemudahan penggunaan teknologi. Seperti, lampu akan otomatis menyala atau mati ketika keberdaan suhu panas tubuh orang terdeteksi oleh sensor. Selain itu, saya pun mendapat materi mengenai berbagai macam tips dan trik untuk mengetahui jenis-jenis jurnal internsional yang predator dan bukan.

Selain itu, dihari selanjutnya saya berkesempatan untuk mempresentasikan hasil penelitian saya yang berjudul Combining Integrated Samling Technique with Feature Selection for Software Defect Prediction. Makalah ini merupakan penelitian pertama saya yang di peresentasikan dan di publikasikan di Conference International maupun Proceeding International. 

Saya berharap, ini merupakan langkah awal membuka jalan saya untuk berkarya pada tingkat internasional. Masih panjang jalannya saya untuk menjadi dosen sekaligus sebagai peneliti secara profesional. 

Read more...