Sensors · 2024 · 15 citations · 18 references
ComputingData ScienceManufacturing EngineeringFeature EngineeringMachine LearningManufacturing ProcessesClassificationData PreparationData PreprocessingDefect ClassificationKernel MethodsSupport Vector MachinesBenchmark DatasetsClass Imbalance HandlingData LeakageData Leakage PreventionImbalanced ClassificationMachine Learning ClassificationMachine Learning-based Defect DetectionManufacturing
Various data types generated in the semiconductor manufacturing process can be used to increase product yield and reduce manufacturing costs. On the other hand, the data generated during the process are collected from various sensors, resulting in diverse units and an imbalanced dataset with a bias towards the majority class. This study evaluated analysis and preprocessing methods for predicting good and defective products using machine learning to increase yield and reduce costs in semiconductor manufacturing processes. The SECOM dataset is used to achieve this, and preprocessing steps are performed, such as missing value handling, dimensionality reduction, resampling to address class imbalances, and scaling. Finally, six machine learning models were evaluated and compared using the geometric mean (GM) and other metrics to assess the combinations of preprocessing methods on imbalanced data. Unlike previous studies, this research proposes methods to reduce the number of features used in machine learning to shorten the training and prediction times. Furthermore, this study prevents data leakage during preprocessing by separating the training and test datasets before analysis and preprocessing. The results showed that applying oversampling methods, excluding KM SMOTE, achieves a more balanced class classification. The combination of SVM, ADASYN, and MaxAbs scaling showed the best performance with an accuracy and GM of 85.14% and 72.95%, respectively, outperforming all other combinations.
18
A survey on missing data in machine learning
Tlamelo Emmanuel, Thabiso Maupong, Dimane Mpoeleng et al. · Journal Of Big Data · 2021 · 975 citations · Full text
Effect of Data Scaling Methods on Machine Learning Algorithms and Model Performance
Md Manjurul Ahsan, M. A. Parvez Mahmud, Pritom Saha et al. · Technologies · 2021 · 696 citations · Full text
Computing, Cardiology, Data Science +17
Boosting methods for multi-class imbalanced data classification: an experimental review
Jafar Tanha, Yousef Abdi, Negin Samadi et al. · Journal Of Big Data · 2020 · 429 citations · Full text
A Comparative Performance Analysis of Data Resampling Methods on Imbalance Medical Data
Matloob Khushi, Kamran Shaukat, Talha Mahboob Alam et al. · IEEE Access · 2021 · 320 citations · Full text
Computing, Biostatistics, Oncology +17