عنوان انگلیسی مقاله:
Data mining algorithm for pre-processing biopharmaceutical drug product manufacturing records
ترجمه فارسی عنوان مقاله:
الگوریتم داده کاوی برای سوابق تولید دارویی بیوشیمیایی قبل از پردازش
Sciencedirect - Elsevier - Computers and Chemical Engineering, 124 (2019) 253-269: doi:10:1016/j:compchemeng:2018:12:001
Gioele Casola a , Christian Siegmund b , Markus Mattern b , Hirokazu Sugiyama a , ∗
The quality of data plays a crucial role in providing a reliable decision-making process when improving processes and operations under uncertainty. We present a data mining-based algorithm for robustly pre- processing the manufacturing records of biopharmaceutical batch processes. The algorithm can identify the time intervals in which the process is in commercial operation, and can characterize process fail- ures automatically. An approximate string-matching algorithm, a decision tree classifier and a constrained clustering is applied to sequence the raw data, to classify the noise and identify each single batches; fi- nally process failure are characterized. The algorithm was applied to the records of the process named as “cleaning- and sterilizing-in-place”, which is an essential process in manufacturing environment, in a case study. The algorithm was training on state of the art manual pre-processing outcome and was ap- plied reducing the execution time of the activity down to 11.7% while maintaining high data quality and integrity.
Keywords: GMP | Noise Filtering | Language recognition | Supervised machine learning | Semi-supervised machine learning | Ishikawa fishbone diagram