Integrated Circuit Test Data Division Based on Clustering Algorithm

With the increase in scale and complexity of integrated circuits, the amount of test data volume has also grown. Due to the simple structure, low computational cost, and capability to handle large-scale data of clustering algorithms, they offer a new solution for processing test data of integrated circuits. This paper defines two characteristics based on the features of test data: frequency_rate and co unt_of_ones, and incorporates them into the K-MEANS, DBSCAN, and OPTICS algorithms, respectively, to achieve segmentation of circuit test data with the silhouette coefficient as the evaluation criterion. Based on extensive data experiments, the results indicate that the OPTICS algorithm achieves the best clustering effect and is suitable for subsequent data processing.