Cardiac activity is involved in the processes of organization of goal-directed behaviour. Each behavioural act is aimed at achieving an adaptive outcome and it is subserved by the actualization of functional systems consisting of elements distributed across the brain and the rest of the body. This paper proposes a system-evolutionary view on the activity of the heart and its variability. We have compared the irregularity of the heart rate, as measured by sample entropy (SampEn), in behaviours that are subserved by functional systems formed at different stages of individual development, which implement organism-environment interactions with different degrees of differentiation. The results have shown that SampEn of the heart rate was higher during performing tasks that included later acquired knowledge (foreign language vs. native language; mathematical vocabulary vs. general vocabulary) and decreased in the stress and alcohol conditions, as well as at the beginning of learning. These results are in line with the hypothesis that irregularity of the heart rate reflects the properties of a set of functional systems subserving current behaviour, with higher irregularity corresponding to later acquired and more complex behaviour.

The current problem of developing new kinds of decision support systems for different categories of management personnel is addressed in this study. A critical feature of such systems is their distributed and decentralized nature, which enables the construction of next-generation information systems in the form of Multi-Agent Systems, Internet of Things, or Fog Computing Architectures. Parallel models of the dynamics of artificial neural networks are produced under such realistic circumstances, demonstrating their potential for addressing a variety of issues. The purpose of this study is to conduct a critical analysis of the problem of integrating Artificial Neural Networks with decision support systems using a corpus of relevant scholarly literature. To tackle this question, the Design Science Research methodology was considered. According to this methodology, a literary search strategy was established, scientific literature was collected and analyzed, and key comparisons between different solutions were emphasized. The study resulted in the presentation of the most important findings, outstanding issues, and potential areas of fundamental and applied solutions. A consistent trend toward the development of decision support systems based on integrated neural-network methods has been observed, which is efficient and cost-effective since it enables the creation of distributed and trainable decision support systems.

В данной работе предлагается новый подход к многокритериальному принятию решений на основе лингвистической информации, полученной от группы автономных экспертов. Данный подход позволяет лучше анализировать и быстрее находить решения для слабоструктурированных проблем, характеризующихся большим количеством факторов и неопределенностью контекста. Одним из ключевых элементов предлагаемой методологии является иерархия абстракций, предложенная Дж. ван Гигом и используемая для определения различных уровней, на которых находятся альтернативные решения и критерии для их оценивания. Интеграция этой иерархии позволяет всецело проанализировать проблемную ситуацию. Поэтому данный подход был назван многоуровневым многоатрибутным лингвистическим методом принятия решений (multi-level multi-attribute linguistic decision making, ML–MA–LDM). Предлагаемый подход включает методологию, представляющую собой набор шагов, и математическую модель. Кроме того, представлен метод автоматического распределения весов экспертов в зависимости от уровня их уверенности в данной оценке. Данный оригинальный подход поддерживает работу как с качественными, так и с количественными оценками на протяжении всего процесса принятия решения по различным уровням абстракции. Наконец, демонстрируется прототип мультиагентной экспертной системы для решения слабоструктурированных проблем с учетом большого числа различных аспектов и неопределенности контекста. Данный прототип играет роль инструмента для конкурентного анализа и для целей верификации предложенной методологии. Основные свойства подхода и прототипа продемонстрированы на примере решения конфликтной ситуации в области стратегического управления. Также были выделены преимущества, недостатки и направления развития предложенной методологии.

Recent breakthroughs in the Deep Learning field have resulted in neural models surpassing human intelligence in a variety of specialized tasks. Modern neural networks have proven their effectiveness in object detection and segmentation applications. However, real-time performance is becoming more challenging for them, especially in cases when a vehicle's autonomy depends on its ability to perceive the surrounding environment within moments. As a result, model acceleration has gained extreme significance in the Deep Learning community. In this paper, we propose a simple yet effective lossy optimization that constitutes a part of the model optimization pipeline. This optimization allows to increase the model throughput by reducing the model input at the expense of an acceptable accuracy drop. For example, we demonstrate that by applying optimization pipeline including input reduction by 40%, 8-bit integer quantization and optimal inference configuration, RetinaNet throughput rocketing in 45 times with an accuracy drop of only 0.01%. We evaluated our acceleration technique on a range of object detection models and used the Intel® Distribution of OpenVINO™ toolkit Deep Learning Workbench as the optimization platform since it provides application engineers with all the required functionality to optimize and deploy the models.

Due to industrial demands to handle increasing amounts of training data, lower the cost of computing one model at a time, and lessen the ecological effects of intensive computing resource consumption, the job of speeding the training of deep neural networks becomes exceedingly challenging. Adaptive Online Importance Sampling and IDS are two brand-new methods for accelerating training that are presented in this research. On the one hand, Adaptive Online Importance Sampling accelerates neural network training by lowering the number of forward and backward steps depending on how poorly a model can identify a given data sample. On the other hand, Intellectual Data Selection accelerates training by removing semantic redundancies from the training dataset and subsequently lowering the number of training steps. The study reports average 1.9x training acceleration for ResNet50, ResNet18, MobileNet v2 and YOLO v5 on a variety of datasets: CIFAR-100, CIFAR-10, ImageNet 2012 and MS COCO 2017, where training data are reduced by up to five times. Application of Adaptive Online Importance Sampling to ResNet50 training on ImageNet 2012 results in 2.37 times quicker convergence to 71.7% top-1 accuracy, which is within 5% of the baseline. Total training time for the same number of epochs as the baseline is reduced by 1.82 times, with an accuracy drop of 2.45 p.p. The amount of time required to apply Intellectual Data Selection to ResNet50 training on ImageNet 2012 is decreased by 1.27 times with a corresponding decline in accuracy of 1.12 p.p. Applying both methods to ResNet50 training on ImageNet 2012 results in 2.31 speedup with an accuracy drop of 3.5 p.p.