Search

With increasing wafer sizes and diversifying die patterns, automated optical inspection (AOI) is progressively replacing traditional visual inspection (VI) for wafer defect detection. Yet, the defect classification efficacy of current AOI systems in our case company is not optimal. This limitation is due to the algorithms' reliance on expertly designed features, reducing adaptability across various product models. Additionally, the limited time available for operators to annotate defect samples restricts learning potential. Our study introduces a novel hybrid self-training algorithm, leveraging semi-supervised learning that integrates pseudo-labeling, noisy student, curriculum labeling, and the Taguchi method. This approach enables classifiers to autonomously integrate information from unlabeled data, bypassing the need for feature extraction, even with scarcely labeled data. Our experiments on a small-scale set show that with 25% and 50% labeled data, the method achieves over 92% accuracy. Remarkably, with only 10% labeled data, our hybrid method surpasses the supervised DenseNet classifier by over 20%, achieving more than 82% accuracy. On a large-scale set, the hybrid method consistently outperforms other approaches, achieving up to 88.75%, 86.31%, and 83.61% accuracy with 50%, 25%, and 10% labeled data. Further experiments confirm our method's consistent superiority, highlighting its potential for high classification accuracy in limited-data scenarios. [ABSTRACT FROM AUTHOR]

This study investigates the impact of media sentiment on firms' investment efficiency in the Chinese market during 2007–2017. We find that increased media sentiment can lead to overinvestment and thus distort investment efficiency, but it has no significant effect on underinvestment. Further, mediation analysis shows that financing constraints mediates the media sentiment effects on overinvestment. To mitigate potential endogenous problems, we employ instrumental variable approach and propensity score matching method. The main findings hold after a battery of robustness tests. Further tests show that corporate governance factors can ameliorate the adverse effect of news sentiment on corporate investment efficiency. [ABSTRACT FROM AUTHOR]

In this study, we examine the effects of lead independent directors (LIDs) on firms' earnings management. On the basis of US firms from 2000 to 2018, those with LIDs managed earnings less, as reflected by the absolute value of discretionary accruals. Specifically, we find the effect is likely to be more prominent among firms with less disclosure transparency, weaker corporate governance and higher risk. In addition, we find that firms with LIDs tend to increase R&D and capital expenditures, reduce leverages and enhance firm values. Overall, the findings indicate the monitoring of LIDs can effectively reduce firms' earnings management and enhance firm values. [ABSTRACT FROM AUTHOR]