-A problem of improving the performance of convolutional neural networks is considered. A parameter of the training set is investigated. The parameter is the batch size. The goal is to find an impact of training set batch size on the performance. To get consistent results, diverse datasets are used. They are MNIST and CIFAR-10. Simplicity of the MNIST dataset stands against complexity of the CIFAR-10 dataset, although the simpler dataset has 10 classes as well as the more complicated one. To achieve acceptable testing results, various convolutional neural network architectures are selected for the MNIST and CIFAR-10 datasets, with two and five convolutional layers, respectively. The assumption about the dependence of the recognition accuracy on the batch size value is confirmed: the larger the batch size value, the higher the recognition accuracy. Another assumption about the impact of the type of the batch size value on the CNN performance is not confirmed.

The achievement of high-precision segmentation in medical image analysis has been an active direction of research over the past decade. Significant success in medical imaging tasks has been feasible due to the employment of deep learning methods, including convolutional neural networks (CNNs). Convolutional architectures have been mostly applied to homogeneous medical datasets with separate organs. Nevertheless, the segmentation of volumetric medical images of several organs remains an open question. In this paper, we investigate fully convolutional neural networks (FCNs) and propose a modified 3D U-Net architecture devoted to the processing of computed tomography (CT) volumetric images in the automatic semantic segmentation tasks. To benchmark the architecture, we utilised the differentiable Sørensen-Dice similarity coefficient (SDSC) as a validation metric and optimised it on the training data by minimising the loss function. Our hand-crafted architecture was trained and tested on the manually compiled dataset of CT scans. The improved 3D UNet architecture achieved the average SDSC score of 84.8 % on testing subset among multiple abdominal organs. We also compared our architecture with recognised state-of-the-art results and demonstrated that 3D U-Net based architectures could achieve competitive performance and efficiency in the multi-organ segmentation task.

The presented work addresses the issue of semantic alignment of ontology components with a generalized structured corpus. The field of research refers to the sphere of determining the features of trust in artificial intelligence. An alignment method is proposed at the level of semantic components of the general alignment system. The method is a component of a broader alignment system and compares entities at the level of meaningful correspondence. Moreover, only the alignment entities’ descriptive content is considered within the proposed technique. Descriptive contents can be represented by variously named id and semantic relations. The method defines a fundamental ontol- ogy and a specific alignment structure. Semantic correspondence in the form of information scope is formed from the alignment structure. In this way, an entity is formed on the side of the alignment structure, which would correspond in the best meaningful way to the entity from the ontology in terms of meaningful descriptiveness. Meaningful descriptiveness is the filling of information scope. Information scopes are formed as a final form of generalization and can consist of entities, a set of entities, and their partial union. In turn, entities are a generalization of properties that are located at a lower level of the hierarchy and, in turn, are a combination of descriptors. Descriptors are a fundamental element of generalization that represent principal content. Descriptors can define atomic content within a knowledge base and represent only a particular aspect of the content. Thus, the element of meaningfulness is not self-sufficient and can manifest as separate meaningfulness in the form of a property, as a minimal representation of the meaningfulness of an alignment. Descriptors can also supplement the content at the level of information frameworks, entities, and properties. The essence of the alignment in the form of information scope cannot be represented as a descriptor or their combination. It happens because the descriptive descriptor does not represent the content in the completed form of the correspondence unit. The minimum structure of representation of information scope is in the form of properties. This form of organization of establishing the correspondence of the semantic level of alignment allows you to structure and formalize the information content for areas with a complex form of semantic mapping. The hierarchical representation of the generalization not only allows simplifying the formalization of semantic alignment but also enables the formation of information entities with the possibility of discretization of content at the level of descriptors. In turn, descriptors can expand meaningfulness at an arbitrary level of the generalization hierarchy. This provides quantization of informational content and flexibility of the alignment system with discretization at the level of descriptors. The proposed method is used to formalize the semantic alignment of ontology entities and areas of structured representation of information.

No abstract

There have been rapid development and application of computer methods and information systems in digital medical diagnosis in recent years. However, although computer methods of medical imaging have proven helpful in diagnosing lung disease, for detecting early pneumonia on chest X-rays, the problem of cooperation between professional radiologists and specialists in computer science remains urgent. Thus, to address this issue, we propose information technology that medical professionals can employ to detect pneumonia on chest X-rays and interpret the results of the digital diagnosis. The technology is presented as a web-oriented system with an available and intuitive user interface. The information system contains three primary components: a module for disease prediction based on a classification model, a module responsible for hyperparameter tuning of the model, and a module for interpreting the diagnosis results. In combination, these three modules form a feasible tool to facilitate medical research in radiology. Moreover, a web-based system with a local server allows storing personal patient data on the user's computing device, as all calculations are performed locally.