The purpose of question classification (QC) is to assign a question to an appropriate category from the set of predefined categories that constitute a question taxonomy. Selected question features are able to significantly improve the performance of QC. However, feature extraction, particularly syntax feature extraction, has a high computational cost. To maintain or enhance performance without syntax features, this study presents a hybrid approach to semantic feature extraction and lexical feature extraction. These features are generated by improved information gain and sequential pattern mining methods, respectively. Selected features are then fed into classifiers for questions classification. Benchmark testing is performed using the public UIUC data set. The results reveal that the proposed approach achieves a coarse accuracy of 96% and fine accuracy of 90.4%, which is superior to existing methods.

Smart homes based on the Internet of Things have been rapidly developed. To improve the safety, comfort, and convenience of residents' lives with minimal cost, daily activity recognition aims to know resident's daily activity in non-invasive manner. The performance of daily activity recognition heavily depends on solving strategy of activity feature. However, the current common employed solving strategy based on statistical information of individual activity does not support well the activity recognition. To improve the common employed solving strategy, an activity feature solving strategy based on TF-IDF is proposed in this paper. The proposed strategy exploits statistical information related to both individual activity and the whole of activities. Two distinct datasets have been commissioned, to mitigate against any possible effect of coupling between dataset and sensor configuration. Finally, a number of machine learning (ML) techniques and deep learning technique have been evaluated to assess their performance for residents activity recognition.

Science and technology are the primary productive forces of a country. However, in today's STEM (Science, Technology, Engineering, and Mathematics) fields, gender segregation remains an issue. Half of the world's population is female, yet women face considerable barriers and are underrepresented in STEM education and occupations. This article mainly focuses on STEM education, to explore how gender role is shaped and reinforced in high school and how it leads to gender segregation of STEM majors in Chinese universities. The findings show that gender stereotype leads female students to devalue self-cognition and self-assessment and, as a result, they often underestimate their ability in STEM disciplines. Second, the educational policy in high school causes female students to prioritize liberal art subjects at the expense of natural science subjects. Third, high school curriculum, textbooks, and other teaching materials that contain gender bias and unhealthy teacher-student interactions reinforce the stereotype of gender role. Fourth, the decisions of majors are strongly affected by traditional Chinese culture that represents the preferences and career expectations for different genders. At the end of this article, implications will be provided.

No abstract

Financial crisis forecasting (FCP) plays a crucial role in economic phenomena. An accurate forecast of the number and likelihood of failures indicates the growth and strength of a country's economy. Traditionally, several effective FCP methods have been proposed. On the other hand, classification performance, prediction accuracy, and data legitimacy are not good enough for practical applications. In addition, many developed methods perform well for some specific datasets but do not apply to different datasets. Therefore, there is a need to develop an effective prediction model to obtain better classification performance and to adapt to other datasets. In this paper, we improve the data characteristics of the existing methods, including introducing time series variables, macroeconomic indicators interaction terms, etc. Finally, this paper attempts to predict financial crises using logistic regression models. The analysis of the results ensures that the proposed FCP model outperforms other classification models based on different metrics and explores the essential factors affecting financial crises.