All issues

Accurate tree identification is essential for ecological monitoring, biodiversity assessment, and forest management. Traditional manual survey methods are labor-intensive and ineffective over large areas. Advances in remote sensing technologies including lidar and hyperspectral imaging improve automated, exact detection in many fields.

Nevertheless, these technologies typically require extensive labeled data and manual feature engineering, which restrict scalability. This research proposes a new method of Self-Supervised Learning (SSL) with the SimCLR framework to enhance the classification of tree species using unlabelled data. SSL model automatically discovers strong features by merging the spectral data from hyperspectral data with the structural data from LiDAR, eliminating the need for manual intervention.

We evaluate the performance of the SSL model against traditional classifiers, including Random Forest (RF), Support Vector Machines (SVM), and Supervised Learning methods, using a dataset from the ECODSE competition, which comprises both labeled and unlabeled samples of tree species in Florida’s Ordway-Swisher Biological Station. The SSL method has been demonstrated to be significantly more effective than traditional methods, with a validation accuracy of 97.5% compared to 95.56% for Semi-SSL and 95.03% for CNN in Supervised Learning.

Subsampling experiments showed that the SSL technique is still effective with less labeled data, with the model achieving good accuracy even with only 20% labeled data points. This conclusion demonstrates SSL’s practical applications in circumstances with insufficient labeled data, such as large-scale forest monitoring.

The traditional approach to studying inter-journal communication involves analyzing journal citation graphs. This paper proposes a method for analyzing journal networks using a new type of bibliometric graph — a journal intersection graph based on the binary operation of set intersection — employing techniques grounded in the friendship index and the disparity function. The approach is demonstrated using a relatively small example of a real journal network, with data sourced from the All-Russian portal Math-Net.Ru information system: 63 journals from 2008–2021 meeting specific criteria, containing almost 69 thousand articles authored by 54 thousand individuals. The mathematical model of this real-world network is represented as an intersection graph using the Jaccard coefficient, which exhibits specific properties: low dimensionality, high graph density, and an edge weight distribution that is not approximated by a power law function. The obtained results include the network structure of connections within the studied set of journals, accounting for their degree of interaction, and the identification of significant vertices using the friendship index. This captures the graph’s structural properties, offers an obvious substantive interpretation, and allows for ranking journals by this metric. Thus, the method implements a tool for distinguishing between vertices that are leaders in terms of the friendship index and “network integrators” (based on closeness/betweenness centrality). It also demonstrates a qualitative change in structural properties when reducing graph density while maintaining connectivity, achieved by applying the disparity function. The sequential application of the disparity function while lowering the significance threshold allows for the identification of the graph’s core, containing the most strongly connected vertices. This, in turn, enables the determination of a set of vertices (and corresponding journals) that are simultaneously part of the core and have the highest significance according to the friendship index. An analysis of the levels of this resulting journal set within the “Belyi Spisok” (“White List”) shows these journals have a high rating. The findings provide a deeper understanding of the relationship structure within scientific journal networks and define new approaches for their study.

Disassembly of stripped x86 binaries is an important yet non-trivial task. Disassembly is difficult to perform correctly without debug information, especially on x86 architecture, which has variablesized instructions interleaved with data. Moreover, the presence of indirect jumps in binary code adds another layer of complexity. Indirect jumps impede the ability of recursive traversal, a common disassembly technique, to successfully identify all instructions within the code. Consequently, disassembling such code becomes even more intricate and demanding, further highlighting the challenges faced in this field. Many tools, including commercial ones such as IDA Pro, struggle with accurate x86 disassembly. As such, there has been some interest in developing a better solution using machine learning (ML) techniques. ML can potentially capture underlying compiler-independent patterns inherent for the compiler-generated assembly. Researchers in this area have shown that it is possible for ML approaches to outperform the classical tools. They also can be less timeconsuming to develop compared to manual heuristics, shifting most of the burden onto collecting a big representative dataset of executables with debug information. Following this line of work, we propose an improvement of an existing RGCN-based architecture, which builds control and flow graph on superset disassembly. The enhancement comes from augmenting the graph with data flow information. In particular, in the embedding we add Jump Control Flow and Register Dependency edges, inspired by Probabilistic Disassembly. We also create an open-source x86 instruction identification dataset, based on a combination of ByteWeight dataset and a selection open-source Debian packages. Compared to IDA Pro, a state of the art commercial tool, our approach yields better accuracy, while maintaining great performance on our benchmarks. It also fares well against existing machine learning approaches such as DeepDi.

This study proposes a methodology for anomaly detection in educational assessment data, demonstrated on the case of the 2023–2024 Basic State Exam (BSE) in mathematics in Russia. The relevance of the study is related to the absence of mandatory video surveillance during the examination period, which creates a risk of potential rule violations both by individual students and by entire educational institutions. By analyzing the distribution of primary scores, we identify a big spike in the area between grades 2 and 3 as a specific pattern in results that may indicate cases of cheating during the exam. To determine the most suspicious results, two anomaly criteria were constructed. The first criterion relies on comparing the magnitude of the spike in empirical distribution function in school’s results with the corresponding regional average level. This criterion made it possible to identify 47 educational institutions with abnormally high values of the spike. The second (general) criterion was derived from comparing students’ scores on the examination with their performance on a diagnostic mathematics test conducted in grade 8 under video surveillance. This comparison is appropriate because almost the same group of students took part in both assessments. This approach helps reduce the number of detected anomalies by distinguishing those more likely to reflect actual protocol violations from those arising due to the specific characteristics of a particular student population and their exam preparation within a given educational institution. The application of the oneclass support vector machine method enabled the identification of 12 schools with atypical anomalous results. The proposed methodology could be useful for the detection of potential cases of cheating during exams and the development of methods for preventing such behavior. In particular, it can be used to support targeted preventive work with specific schools in order to reduce the risk of exam rule violations.

A new approach to the identification of hardly perceptible diagnostically significant changes in electrocardiograms is suggested. The approach is based on the analysis of topological transformations in wavelet spectra associated with electrocardiograms. Possible practical application of the approach developed is discussed.

The article describes a model of a human in the informational economy and demonstrates the multicriteria optimizational approach to the metric analysis of model-generated data. The traditional approach using the identification and study involves the model’s identification by time series and its further prediction. However, this is not possible when some variables are not explicitly observed and only some typical borders or population features are known, which is often the case in the social sciences, making some models pure theoretical. To avoid this problem, we propose a method of metric data analysis (MMDA) for identification and study of such models, based on the construction and analysis of the Kolmogorov – Shannon metric nets of the general population in a multidimensional space of social characteristics. Using this method, the coefficients of the model are identified and the features of its phase trajectories are studied. In this paper, we are describing human according to his role in information processing, considering his awareness and cognitive abilities. We construct two lifetime indices of human capital: creative individual (generalizing cognitive abilities) and productive (generalizing the amount of information mastered by a person) and formulate the problem of their multi-criteria (two-criteria) optimization taking into account life expectancy. This approach allows us to identify and economically justify the new requirements for the education system and the information environment of human existence. It is shown that the Pareto-frontier exists in the optimization problem, and its type depends on the mortality rates: at high life expectancy there is one dominant solution, while for lower life expectancy there are different types of Paretofrontier. In particular, the Pareto-principle applies to Russia: a significant increase in the creative human capital of an individual (summarizing his cognitive abilities) is possible due to a small decrease in the creative human capital (summarizing awareness). It is shown that the increase in life expectancy makes competence approach (focused on the development of cognitive abilities) being optimal, while for low life expectancy the knowledge approach is preferable.