The research deals with the development of an algorithm for detecting pathological formation in cystic fibrosis using the PSPNet model with focal loss. The model allows data sets to be entered in accordance to their similarities based on their pathological diagnostic signs. The simple and effective algorithm structure groups annotated images, processes them in a multi-scale CNN, and localizes areas of cystic fibrosis in the lungs with high accuracy.
The article presents an approach that compares different municipalities by their energy efficiency level. We propose a clustering of the municipalities by neuro-fuzzy methods to estimate how social, economic and climatic features affect the energy use. The energy use indicators analysis allows to create a set of membership functions in each cluster to get fuzzy measures of energy efficiency.
The article presents segmentation algorithms for cirrus clouds subtypes recognition based on MODIS satellite images using self-organizing feature maps. It gives the results of cirrus clouds recognition. The paper also discusses the accuracy of obtained outcomes for the chosen cirrus clouds subtypes.
This research investigates the internationalization of Master of Information Technology (MIT) education in National Research Tomsk Polytechnic University (TPU). Through a conducted case study about a course (also known as a subject or a unit) specially developed and delivered by a foreign researcher-teacher for the internationalized MIT program, it investigated how TPU approached internationalization of MIT education, why the approach was adopted and how TPU overcame the challenges in internationalizing their MIT programs (offered in two languages) and curricula. The research adopted a qualitative case study research method, which involved the data collection techniques such as survey, observation and documentations. Ten MIT program students were involved in the course delivery. The research team observed how the MIT program worked, how the students learnt from the specially provided course by a foreign researcher-teacher in the MIT program, the challenges and difficulties in the delivery of course learning, and how they were overcome. The results indicated that the students were highly satisfied and greatly benefited from the specially developed course in their internationalized MIT program.
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.