Abstract Social sciences are increasingly recognized as significant for building a sustainable world since the social perspective can assist researchers in other fields in navigating public controversy and designing more responsible interaction mechanisms between the natural and social systems. However, the question arises: to what extent do natural sciences rely on social science research in their studies? Examining life science publications from seven PLoS journals, this paper attempts to characterize the volume and trajectory of citations from life sciences to social sciences. We explore three core questions: To what extent do life sciences cite social sciences? What actors in the life sciences are citing social sciences? Which actors in the social sciences are being cited? Our analysis estimates social sciences influence 15%–19% of life science publications, contributing to 1.1%–1.5% of references in 2018. Social science citers are found across peripheral and central topics of life science disciplines. Cited social science publications exhibit various levels of interdisciplinarity and achieve the greatest citation impact among peers. Citations to social sciences are prevalent in both theoretically and methodologically oriented sections. We show empirically the increasing impact of social sciences on the development of the life sciences.

Convolutional neural network (CNN)-based fault detection approaches based on multisource signals have attracted increasing interest from the research community and industrial practices, thanks to the powerful feature representation capability of CNN and the rapid development of sensor technology. Various strategies have been applied in existing CNN-based diagnostic models to learn features from 1-D real-valued multivariate data. However, the distribution gap and the intrinsic correlations among multisource mechanical signals during the learning process have been rarely considered, which may lead to suboptimal fault identification results. To tackle this issue, this article proposes a cross-modal fusion convolutional neural network (CMFCNN) for mechanical fault diagnosis, which performs modality-specific and cross-modal feature representation on multisource data. Specifically, CMFCNN adopts two parallel modality-specific networks and a cross-modal knowledge-sharing network to fully explore independent and shared features from the multisource mechanical signals. To achieve effective feature propagation and fusion, a cross-modal fusion module is introduced to integrate cross-modal features and pass the fused information to the next layer. Moreover, to alleviate overfitting and achieve a better diagnostic performance of the framework, an online soft-label training algorithm is adopted in the CMFCNN training phase. Extensive experimental results on the cylindrical rolling bearing dataset and the planetary gearbox dataset validate that the proposed CMFCNN outperforms seven state-of-the-art methods significantly, especially under strong noise conditions.