Background: A rapid growth in private dentistry in China has been observed during recent years. Promoting the entrepreneurship of dentists has increasingly received attention in both dentistry and dental education worldwide. However, understanding about the unique features of entrepreneurial behaviors of dentists remains inadequate. Methods: This study examines dentist’s entrepreneurial intention (EI), which was represented by his/her intention of leaving the public hospital system to be engaged in the private sector. Through a snowball sampling method, a total of 336 questionnaires from public hospitals in five major cities in Guangdong Province (China) were collected. The association between the dentists’ EI and their individual characteristics were analyzed using a logistic regression model. Results: In the sample studied, 35.7% of the respondents reported to have EI. Female dentists are less likely to report EI (OR = 0.365, p = 0.001). Dentists in the age group of 36 to 45 years (OR = 14.205, p = 0.012) and those aged over 45 years (OR = 8.45, p = 0.066) reported respectively a much stronger EI than those in their 20s. Compared with intern dentists, attending dentists (OR = 7.812, p = 0.016) and associate/chief dentists (OR = 9.857, p = 0.021) were significantly more likely to report EI. Those with master level (OR = 0.221, p = 0.021) or doctorate degrees (OR = 0.118, p = 0.005) are much less likely to report EI. Meanwhile, those in mid-large hospitals (with 101–200 employees) (OR = 3.554, p = 0.036) and small hospitals (with < 50 employees) (OR = 2.398, p = 0.044) reported a stronger EI than those in large hospitals. Additionally, dentists’ entrepreneurial behaviors, risk aversion attitudes and their family background all have significant associations. Conclusions: Since dentistry is a knowledge-intensive industry, dentists’ entrepreneurial behaviors have their own features. The findings by this study suggest that, accumulation of practical skills in a dental career, as implied by age, professional qualifications and leadership skills, help to promote EI, whereas an academic oriented education degree per se does not. Dentists in mid-large and small hospitals, rather than in top large hospitals in China, have higher EI. Additionally, female dentists may need more social supports to develop a higher EI. These findings have practical implications for the promotion of EI among dentists.

With the vigorous development of integrated circuit (IC) manufacturing, the harmfulness of defects and hardware Trojans is also rising. Therefore, chip verification becomes more and more important. At present, the accuracy of most existing chip verification methods depends on high-precision sample data of ICs. Paradoxically, it is more challenging to invent an efficient algorithm for high-precision noiseless data. Thus, we recently proposed a fusion clustering framework based on low-quality chip images named High-Frequency Low-Rank Subspace Clustering (HFLRSC), which can provide the data foundation for the verification task by effectively clustering those noisy and low-resolution partial images of multiple target ICs into the correct categories. The first step of the framework is to extract high-frequency texture components. Subsequently, the extracted texture components will be integrated into subspace learning so that the algorithm can not only learn the low-rank space but also retain high-frequency information with texture characteristics. In comparison with the benchmark and state-of-the-art method, the presented approach can more effectively process simulation low-quality IC images and achieve better performance.

As China's economic level continues to grow, people's standard of living is improving along with their awareness of oral health. The increased demand for high-quality dental services provides good opportunities for dentists to start their own businesses. Despite the rapid growth of private dental practices in China, more research is still needed to gain insight into the distinctive characteristics and influencing factors of dentists' entrepreneurial behavior. In this study, the entrepreneurial intention of dentists (the person's intention to leave the public hospital system and enter the private institution) was analyzed by collecting relevant questionnaires from public hospitals in five major cities of Guangdong Province, and the relationship between the entrepreneurial intention of dentists and their personal characteristics was analyzed using XGBoost method and binary logistic regression method. A total of 505 dentists' survey data were included in this study, and the top 5 influencing factors of importance were obtained based on the research analysis. Experiments showed that the importance-related features obtained in this study can play a high predictive role and have favorable stability, with an accuracy of more than 82% in XGBoost, decision tree and random forest classification algorithms. The prediction model of dentists' entrepreneurial intention based on machine learning algorithm is of high practical significance and can be incorporated into the screening and decision-making of dentists' entrepreneurial intention status. Based on this method, the entrepreneurial intention of relevant individuals can be accurately grasped, so that appropriate measures can be taken to promote the development and management of the industry.