RESUMEN
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.
RESUMEN
Wireless sensor networks require energy-efficient data transmission because the sensor nodes have limited power. A cluster-based routing method is more energy-efficient than a flat routing method as it can only send specific data for user requirements and aggregate similar data by dividing a network into a local cluster. However, previous clustering algorithms have some problems in that the transmission radius of sensor nodes is not realistic and multi-hop based communication is not used both inside and outside local clusters. As energy consumption based on clustering is dependent on the number of clusters, we need to know how many clusters are best. Thus, we propose an optimal number of cluster-heads based on multi-hop routing in wireless sensor networks. We observe that a local cluster made by a cluster-head influences the energy consumption of sensor nodes. We determined an equation for the number of packets to send and relay, and calculated the energy consumption of sensor networks using it. Through the process of calculating the energy consumption, we can obtain the optimal number of cluster-heads in wireless sensor networks.