Resource-constrained project scheduling problem (RCPSP) is one of the most challenging combinatorial optimization problems. This task contains different variations and is the object of attention of many researchers. However, the existing formulation of practical optimization tasks in industrial production processes significantly exceeds the limits of classical RSPCP formulation, academic frameworks like PSPLib and datasets like RG300. It is expressed in the presence of additional parameters (degrees of freedom), uncertainty in the actual data of parameters of the solving task and the dimensionality of the problems themselves. A striking example of such production processes is the capital construction of complex facilities, such as capital projects (construction of capital assets) or airport operation, where activities can exceed tens of thousands, have fuzzy connections, form sub-sets of tasks, and be performed by complex teams that have different types of resources in their disposal. The formulation of such problems not only opens up the opportunities to develop new modifications of existing algorithms but also allows us to evaluate the practical feasibility of using such algorithms on dimensions orders of times higher than the generally accepted test sets. In the current research, we introduce problem extension MLRCPSP - multi-resource-constrained project scheduling problem and a new generalized algorithm that can take into account the features of actual production processes and demonstrates how effective it could be in application to synthetically generated data from real practical applications, using an extended state-of-the-art implementation of the genetic algorithm.

Resource-intensive computations are a major factor that limits the effectiveness of automated machine learning solutions. In the paper, we propose a modular approach that can be used to increase the quality of evolutionary optimization for modelling pipelines with a graph-based structure. It consists of several stages - parallelization, caching, and evaluation. Heterogeneous and remote resources can be involved in the evaluation stage. The conducted experiments confirm the correctness and effectiveness of the proposed approach. The implemented algorithms are available as a part of the open-source framework FEDOT.

Today, the city is full of digital information, which can be extremely useful in various applications. Instagram, Facebook, VKontakte, and other popular social networks contain a vast amount of valuable data. This information reflects individual stories of people and the background of the city, its events, and current activities in different areas and places of attraction. City events have essential attributes like the time of occurrence, geographical coverage, audience, and often expressed interests or topics. Owning the subject of events, you can solve a whole range of tasks - from individual recommendation systems for leisure activities for citizens and tourists to providing services in the field of food (food trucks) and transport (taxis). To determine the topic (subject) of events, it is necessary to solve two crucial tasks: to identify the events themselves from a variety of city posts and to develop an approach based on modern natural language processing methods for identifying events topics. To determine the events, we suggest an improved algorithm that we had previously developed that integrates time window and area coverage strategy. However, the focus of the work is on the analysis of different approaches to identifying topics, considering the heterogeneity of posts, both in semantic meaning and in size and structure. The focus of this paper is the importance of using post hashtags in various variations to set up more accurate models. In addition, the analysis of features for different language groups was carried out.

Online advertising is one of the most widespread ways to reach and increase a target audience for those selling products. Usually having a form of a banner, advertising engages users into visiting a corresponding webpage. Professional generation of banners requires creative and writing skills and a basic understanding of target products. The great variety of goods presented in the online market enforce professionals to spend more and more time creating new advertisements different from existing ones. In this paper, we propose a neural network-based approach for the automatic generation of online advertising using texts from given webpages as sources. The important part of the approach is training on open data available online, which allows avoiding costly procedures of manual labeling. Collected open data consist of multiple subdomains with high data heterogeneity. The subdomains belong to different topics and vary in used vocabularies, phrases, styles that lead to reduced quality in adverts generation. We try to solve the problem of identifying existed subdomains and proposing a new ensemble approach based on exploiting multiple instances of a seq2seq model. Our experimental study on a dataset in the Russian language shows that our approach can significantly improve the quality of adverts generation.

In the modern world, with the growth of the volume of processed data arrays, the logic of solving problems also becomes more complex. This leads more and more often to the need to use high-performance computational clusters, such as supercomputers. Created multi-agent simulation applications require not only significant resources but often perform time-consuming complex scenarios, which significantly affects the efficiency of the executed process. However, there are various mechanisms for optimizing application execution for different needs. Unfortunately, the specificity of multi-agent simulation does not allow the use of traditional and modern algorithms due to the iteratively variable workload and limitations of a system software installed on the supercomputers. In this paper, we propose a four-level scheme for organizing the symbiotic execution (co-design) of multi-agent applications on supercomputers, as well as an effective two-level algorithm for optimizing the flow of the execution of an urban mobility simulation application. The algorithm is based on evolutionary approach and machine learning techniques.