?
Coniferest: A complete active anomaly detection framework
Astronomy and Computing. 2025. Vol. 52. Article 100960.
M.V. Kornilov, Korolev V., Malanchev K., Lavrukhina A., Russeil E., Semenikhin T. A., Gangler E., Ishida E. O., Pruzhinskaya M., Volnova A. A., Sreejith S.
We present coniferest, an open source generic purpose active anomaly detection framework written in Python. The package design and implemented algorithms are described. Currently, static outlier detection analysis is supported via the Isolation forest algorithm. Moreover, Active Anomaly Discovery (AAD) and Pineforest algorithms are available to tackle active anomaly detection problems. The algorithms and package performance are evaluated on a series of synthetic datasets. We also describe a few success cases which resulted from applying the package to real astronomical data in active anomaly detection tasks within the SNAD project.
Springer, 2026.
Two volumes of the SPECOM 2026 proceedings contain a collection of submitted papers presented at SPECOM 2026, which were thoroughly reviewed by members of the Program Committee and additional reviewers consisting of almost 80 experts in the conference topic areas. In total, 65 regular full papers out of 99 submissions made via the EasyChair electronic ...
Added: September 20, 2026
Aleksei Samarin, Alexander Savelev, Aleksei Toropov et al., Pattern Recognition and Image Analysis 2026 Vol. 36 No. 2 P. 323–334
In this paper, an improved approach for automatic wildlife detection in natural environments based on the integration of a neural network architecture with a two-stream attention mechanism and a novel preclassification step based on infrared data has been presented. The proposed method addresses one of the key challenges in environmental monitoring: the need for scalable ...
Added: September 19, 2026
Aleksei Samarin, Nazarenko A., Kotenko E. et al., Proceedings of the ACM on Management of Data, USA 2026 Vol. 4 No. 1 P. 1–28
Modern knowledge and large volumes of data are increasingly encoded within neural networks, making the task of simplifying their structures and reducing the number of parameters especially relevant, both to improve efficiency and to facilitate deployment in resource-constrained environments. This paper presents a novel approach to neural network compression that addresses redundancy at both the ...
Added: September 19, 2026
Aleksei Samarin, Alexander Savelev, Aleksei Toropov et al., Pattern Recognition and Image Analysis 2025 Vol. 35 No. 2 P. 148–158
This paper describes our research on creating classifiers for microbial images (micrococci microscopy images) obtained from pictures of unfixed microscopic scenes. In our work, we propose an AutoML approach based on the automatic generation and analysis of the feature space for constructing the most optimal descriptors of microorganism images for subsequent classification. This makes it ...
Added: September 19, 2026
Aleksei Samarin, Alexander Savelev, Aleksei Toropov et al., Pattern Recognition and Image Analysis 2026 Vol. 36 No. 2 P. 302–312
The lack of annotated microscopic datasets remains a major obstacle to training robust deep learning models for microbial classification. In this paper, a novel data augmentation pipeline that uses visual–linguistic large-scale models to generate synthetic microscopic images of six different bacterial and nonbacterial classes has been proposed. Synthetic samples have gradually been added to the ...
Added: September 19, 2026
Springer, Cham, 2026.
computer vision ...
Added: September 19, 2026
Springer, Cham, 2026.
Added: September 19, 2026
FRUCT Oy, 2024.
Added: September 19, 2026
FRUCT Oy, 2024.
Added: September 19, 2026
FRUCT Oy, 2025.
Added: September 19, 2026
FRUCT Oy, 2026.
Added: September 19, 2026
Aleksei Samarin, Nazarenko A., Kotenko E. et al., Machine Learning and Knowledge Extraction 2026 Vol. 8 No. 8 P. 1–26
This paper presents a novel method for pruning deep neural networks based on the concept of flow, derived from the continuous modeling of signal propagation across layers. We derive flow functions for fully connected, convolutional, and self-attention architectures, and we propose a new iterative pruning algorithm, Iterative Flow-Aware Pruning (IFAP), that leverages these measures to ...
Added: September 19, 2026
Myachin A. L., Procedia Computer Science 2026 Vol. 287 P. 193–200
We extend the static pattern analysis method to the temporal dimension by introducing a six-type trajectory taxonomy that classifies objects according to the frequency and structure of pattern switches over an observation window of T > 8 periods. For each object, a reference pattern is designated as the most frequently occupied group over the observation ...
Added: September 18, 2026
Копьев А., JETP Letters 2026 Vol. 123 No. 5 P. 310–316
The incompressible three-dimensional Euler equations develop very thin pancake-like regions of exponen tially increasing vorticity. The characteristic thickness of such regions decreases exponentially with time, while the other two dimensions do not change considerably, making the flow near each pancake strongly anisotropic. The pancakes emerge in increasing number with time, which may enhance the anisotropy ...
Added: September 18, 2026
Громов Р. С., Нестеров Р.А., Proceedings of the Institute for System Programming of the RAS 2026 Vol. 38 No. 4 P. 23–44
This paper explores the performance criteria of the newest algorithm for solving the problem of finding shortest paths on a graph from a given vertex – Bounded Multi-Source Shortest Path Algorithm
(BM-SSP). The algorithm was published in 2025 and, as its creators claim, it is asymptotically superior to Dijkstra’s deterministic algorithm. However, in the publication devoted ...
Added: September 18, 2026
Захаров А. В., Düven H., Capar M. I., Physics Letters A 2026 No. 576 Article 131388
Molecular dynamics simulations were carried out to study the structural properties of nematic pentyl
cyanobiphenyl (5CB) and pentyloxy cyanobiphenyl (5OCB) liquid crystals (LCs) doped with gold nanoparti
cles (GNPs) of different numbers, shapes and sizes. The spherical GNPs of two different radii and rod-like have
been doped in 5CB and 5OCB cyanobiphenyl liquid crystals. In order to describe ...
Added: September 17, 2026
Кузнецов М. Е., Полякова М., Лукьянович В. et al., ФАНУ "Востокгосплан", 2026.
Обзор международных практик развития робототехники и искусственного интеллекта и оценка возможностей их применения в условиях России, в первую очередь для Дальнего Востока и Арктической зоны РФ ...
Added: September 16, 2026
Andreev D. V., Kornev S. A., Bondarenko G.G. et al., Inorganic Materials: Applied Research 2026 Vol. 17 No. 5 P. 1226–1230
Comparative studies are carried out to investigate high-field charge degradation effects in the gate
dielectric of metal—insulator—semiconductor (MIS) structures with aluminum and polysilicon gates.
Charging phenomena in MIS structures are explored using high-field electron injection into the dielectric
under conditions of gradually increasing voltage current density, with periodic short-term switching to a measurement
mode at a constant low injection ...
Added: September 15, 2026
Poddiakov A., / Series Social Science Research Network "Social Science Research Network". 2026. No. 7437658.
Clarity of knowledge and reasoning is necessary in many cases. Yet vagueness in scientific thinking related to surprise, curiosity, "ability to engage with not-knowing" (de Freitas) and abductive reasoning is also a crucially important source of scientific creativity which supplements combinatorial logic when dealing with the already known. Starting from studies by C. S. Peirce ...
Added: September 15, 2026
Maghsoohi A., Pavlov V., Rouse P. et al., Health Care Management Science 2026 Vol. 29 Article 37
As the numbers of older people (65 +) rise globally, the pressure on acute hospitals to provide efficient and effective care while addressing resource inequities increases. In this study we introduce Recognising Episodes of Acute Complexity in Health (REACH), a novel Automatic Machine Learning (AutoML)-based predictive model that prioritises older patients and assigns them to complex ...
Added: July 30, 2026
Izyumov P., Ivchenko A., , in: 2024 26th International Conference on Digital Signal Processing and its Applications (DSPA).: IEEE, 2024. P. 1–5.
The paper describes the issues of setting up an experiment, limitations, and features of the platform, primarily focusing on the influence of hardware and software versions of probes, network types, and cross-traffic. The impact of new versions of software and hardware requires analysis and con-sideration in further data work. Additionally, the nature of the global ...
Added: June 28, 2026
Interpretable Machine Learning in Guided Synthesis of Stable Sols Based on Nanosized Titanium Oxides
Glushko A., Neznanov A., Kuz'micheva G. et al., , in: 2026 International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA), 5-7 Feb. 2026.: IEEE, 2026. P. 1–6.
This report discusses the guided synthesis of sols containing nanosized titanium(IV) oxides for use in biological and medical applications. These sols vary in size (from ∼2 up to 2000nm) and different stability (from 0 up to 90 days). They are synthesized under changing fabrication conditions (temperature, hydrolysis duration, titanium-containing precursors composition and concentration) without surfactants. ...
Added: April 29, 2026
NY: Association for Computing Machinery (ACM), 2026.
It is our great pleasure to welcome you to the 35th edition of the Web Conference to be held on June 29 – July 3, 2026, in Dubai, United Arab Emirates.
Following discussions with our partners and key stakeholders, we have taken the decision to postpone the ACM Web Conference 2026, initially planned for April 2026. ...
Added: April 17, 2026
Ali S., Khizhik A., Ryzhikov A. et al., , in: 2025 IEEE Ural-Siberian Conference on Biomedical Engineering, Radioelectronics and Information Technology (USBEREIT), 12-13 May 2025.: IEEE, 2025. P. 357–360.
Three-phase induction motors play a crucial role in industrial applications due to their efficiency, durability, and reliability. However, effective fault detection remains challenging, primarily due to the scarcity of labeled failure data, which limits the performance of traditional machine learning (ML)-based diagnostic models and increases the risk of overfitting and poor generalization. Conventional methods, such ...
Added: July 3, 2025