Automation and Remote Control最新文献

This paper discusses the phenomenon associated with the forced synchronization (“entrainment of a self-sustained oscillator by an external force”) in a relay system with hysteresis, which manifests itself in the occurrence of periodic motions close to the rhythmic activity of neurons, when packets of fast oscillations are interspersed with intervals of the slow dynamics. To study this phenomenon, we introduce a circle mapping, which, depending on the parameters, can be a circle diffeomorphism or discontinuous map (“gap map”). In both cases, this mapping demonstrates the so-called period-adding bifurcation structure. It is demonstrated that packets number of fast oscillations in the period of periodic motion is determined by the rotation number, and the length of the intervals between the packets may be found of the boundaries of the absorbing interval. The change in the number of pulses in the packet occurs through the border-collision bifurcation.

This paper reports of theoretical and computational results related to an original concept of consensus clustering involving what we call the projective distance between partitions. This distance is defined as the squared difference between a partition incidence matrix and its image over the orthogonal projection in the linear space spanning the other partition incidence matrix. It appears, provided that the ensemble clustering is of a sufficient size, agglomerate clustering with the semi-average within-cluster similarity criterion effectively solves the problem of consensus partition and, moreover, of the number of clusters in it.

The paper is devoted to the application of the plausible reasoning principles to symbolic machine learning. It seems for us that the applications are essential and necessary to improve the efficiency of ML algorithms. Many such algorithms produce and use rules in the form of implication. The generation of these rules with respect to the object classes is discussed. Our classification rules are specific. Their premise part, called good closed tests (GCTs), should cover as many objects as possible. One of the algorithms of GCTs generation called NIAGARA is presented. The algorithm is revisited and new procedures based on plausible reasoning are proposed. Their correctness is proved in propositions. We use the following rules: implication, interdiction, inductive rules of extending current sets of goal-oriented objects, rules of pruning the domain of searching solution. They allow to rise the effectiveness of algorithms.

The difficulty of interpreting performance of neural networks is a well-known problem, which is attracting a lot of attention. In particular, neural networks based on concept lattices present a promising direction in this area. Selection of formal concepts for building a neural network has a key effect on the quality of its performance. Criteria for selecting formal concepts can be based on interestingness indices, when concepts with the highest values of a certain index are used to build a neural network. This article studies the influence of the choice of an interestingness index on the neural network performance.

The problem of route optimization with realistic constraints is becoming extremely relevant in the face of global urban population growth. While we are aware of approaches that theoretically provide an exact optimal solution, their application becomes challenging as the problem size increases because of exponential complexity. We investigate the Capacitated Vehicle Routing Problem with Time Windows (CVRPTW) and compare solutions obtaining by exact solver SCIP [1] with heuristic algorithms such as LKH, 2-OPT, 3-OPT [2], the OR-Tools framework [3], and the deep learning model JAMPR [4]. We demonstrate that for problem of size 50 deep learning and classical heuristic solutions became close to SCIP exact solution but requires less time. Additionally for problems with size 100, SCIP exact methods ~13 times slower that neural and classical heuristics with the same route cost and on ~50% worse for the first feasible solution on the same time. To conduct experiments, we developed the Smart Routes platform for solving route optimization problems, which includes exact, heuristic, and deep learning models, and facilitates convenient integration of custom algorithms and datasets.

Digital twins reflect the state of the environment and the activities of enterprises affected by the hydrometeorological conditions. It is proposed to use models to calculate indicators for assessing impacts of natural hazards or of climate change; of forecasts of these impacts; damage estimates; of calculating the cost of actions to protect enterprises; of assessing the feasibility of carrying out preventive actions in order to optimize them. Requirements for impact assessment models working with a digital twin are given. The difficulties in using such models are presented. Proposals for the development of impact models are being considered. A diagram of the use of digital twins in modeling impacts of environmental on enterprises is shown.

Genetic Algorithms (GAs) are known for their efficiency in solving combinatorial optimization problems, thanks to their ability to explore diverse solution spaces, handle various representations, exploit parallelism, preserve good solutions, adapt to changing dynamics, handle combinatorial diversity, and provide heuristic search. However, limitations such as premature convergence, lack of problem-specific knowledge, and randomness of crossover and mutation operators make GAs generally inefficient in finding an optimal solution. To address these limitations, this paper proposes a new metaheuristic algorithm called the Genetic Engineering Algorithm (GEA) that draws inspiration from genetic engineering concepts. GEA redesigns the traditional GA while incorporating new search methods to isolate, purify, insert, and express new genes based on existing ones, leading to the emergence of desired traits and the production of specific chromosomes based on the selected genes. Comparative evaluations against state-of-the-art algorithms on benchmark instances demonstrate the superior performance of GEA, showcasing its potential as an innovative and efficient solution for combinatorial optimization problems.

The need for skilled medical support is growing in the era of digital healthcare. This research presents an innovative strategy, utilizing the RuBERT model, for categorizing user inquiries in the field of medical consultation with a focus on expert specialization. By harnessing the capabilities of transformers, we fine-tuned the pretrained RuBERT model on a varied dataset, which facilitates precise correspondence between queries and particular medical specialisms. Using a comprehensive dataset, we have demonstrated our approach’s superior performance with an Fl-score of over 91.8%, calculated through both cross-validation and the traditional split of test and train datasets. Our approach has shown excellent generalization across medical domains such as cardiology, neurology and dermatology. This methodology provides practical benefits by directing users to appropriate specialists for prompt and targeted medical advice. It also enhances healthcare system efficiency, reduces practitioner burden, and improves patient care quality. In summary, our suggested strategy facilitates the attainment of specific medical knowledge, offering prompt and precise advice within the digital healthcare field.

This research delves into the cybersecurity implications of neural network training in cloud-based services. Despite their recognition for solving IT problems, the resource-intensive nature of neural network training poses challenges, leading to increased reliance on cloud services. However, this dependence introduces new cybersecurity risks. The study focuses on a novel attack method exploiting neural network weights to discreetly distribute hidden malware. It explores seven embedding methods and four trigger types for malware activation. Additionally, the paper introduces an open-source framework automating code injection into neural network weight parameters, allowing researchers to investigate and counteract this emerging attack vector.