Automated abstracts classification could significantly facilitate scientific literature screening. The classification of short texts could be based on their statistical properties. This research aimed to evaluate the quality of short medical abstracts classification primarily based on text statistical features. Twelve experiments with machine learning models over the sets of text features were performed on a dataset of 671 article abstracts. Each experiment was repeated 300 times to estimate the classification quality, ending up with 3600 tests total. We achieved the best result (F1 = 0.775) using a random forest machine learning model with keywords and three-dimensional Word2Vec embeddings. The classification of scientific abstracts might be implemented using straightforward and computationally inexpensive methods presented in this paper. The approach we described is expected to facilitate literature selection by researchers.
Presentation of the scheme of video signal online translation from cameras installed in the operation room (OR) to stationary and mobile devices. Material and Methods. The scheme of online webcast translation was implemented in the Institute of Neurosurgery on the basis of the existing system of TV broadcasting of video images from the operation room. Translation scheme using additional software and dedicated server, and translation scheme using IP-based cameras and video servers-encoders were designed. Results. Realized technical decisions allow chief of the department to get visual control of the operating room from any point worldwide using any device with internet access. Conclusion. The proposed technology has a low cost of implementation and helps to realize a project "Chief in the OR", providing the online monitoring of surgeon's activity regardless of the chief location. It may be used for remote surgery live demonstration with audio feedback (congresses, training courses, conferences, etc), and give opportunity for adjustment of the system parameters and further improvement with functional evolution.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.