This study aimed at testing the feasibility of neurosurgical procedures classification into 100+ classes using natural language processing and machine learning. A catboost algorithm and bidirectional recurrent neural network with a gated recurrent unit showed almost the same accuracy of ∼81%, with suggestions of correct class in top 2-3 scored classes up to 98.9%. The classification of neurosurgical procedures via machine learning appears to be a technically solvable task which can be additionally improved considering data enhancement and classes verification.

In our recent study, the attempt to classify neurosurgical operative reports into routinely used expert-derived classes exhibited an F-score not exceeding 0.74. This study aimed to test how improving the classifier (target variable) affected the short text classification with deep learning on real-world data. We redesigned the target variable based on three strict principles when applicable: pathology, localization, and manipulation type. The deep learning significantly improved with the best result of operative report classification into 13 classes (accuracy = 0.995, F1 = 0.990). Reasonable text classification with machine learning should be a two-way process: the model performance must be ensured by the unambiguous textual representation reflected in corresponding target variables. At the same time, the validity of human-generated codification can be inspected via machine learning.

The article proposes a technology for controlling access through a Web application. In the first part, the implementation of the electromechanical part of the ACS, the key feature of which is the preservation of the last state when the power is turned off and the presence of an anti-panic mode. This feature is obtained by installing a geared motor on the lock cylinder. This solution allows you to abandon the need for certification of the lock, use both electronic control, for example, by means of a telephone or proximity cards, and classical control using a regular standard key, as well as finding the lock in any state for an arbitrarily long time, regardless of the presence of power. In the second part, the implementation of network interaction between the user and the directly controlled object is proposed.

The article discusses the structure of the hardware and internetworking of automated room heat loss identification system on example of the Ugra State University classroom. The temperature controller has been developed taking into account the specifics of the room. A heat meter with telemetry capability has been selected.