Anna Kuznetsova

Mikhail Kulyabin, Aleksei Zhdanov, Anastasia Nikiforova et al.

Optical coherence tomography (OCT) is a non-invasive imaging technique with extensive clinical applications in ophthalmology. OCT enables the visualization of the retinal layers, playing a vital role in the early detection and monitoring of retinal diseases. OCT uses the principle of light wave interference to create detailed images of the retinal microstructures, making it a valuable tool for diagnosing ocular conditions. This work presents an open-access OCT dataset (OCTDL) comprising over 2000 OCT images labeled according to disease group and retinal pathology. The dataset consists of OCT records of patients with Age-related Macular Degeneration (AMD), Diabetic Macular Edema (DME), Epiretinal Membrane (ERM), Retinal Artery Occlusion (RAO), Retinal Vein Occlusion (RVO), and Vitreomacular Interface Disease (VID). The images were acquired with an Optovue Avanti RTVue XR using raster scanning protocols with dynamic scan length and image resolution. Each retinal b-scan was acquired by centering on the fovea and interpreted and cataloged by an experienced retinal specialist. In this work, we applied Deep Learning classification techniques to this new open-access dataset.

Anna Kuznetsova

Discrete mathematics and probability theory contain foundational material for computer scientists. Despite their importance, instructors often worry that students will find these courses to be too abstract and seemingly disconnected from their future careers. For this research project, we introduced homework questions throughout our introductory theory courses based on real world applications of the course content. Areas of application included a court case, code correctness, and machine learning ethics. We surveyed students at the beginning and end of the term on their attitudes toward the relevance of the course material. Our results, surprisingly, indicate that a small minority of students (less than 7%) expected the material to be irrelevant to them at the start of the term, and a similarly small number believed that at the end of the term. Our surveys and qualitative feedback also indicate students enjoyed having the problems and wanted them to continue being offered in future iterations of the courses.

Anna Kuznetsova, Vadim Kimmelman

Advances in Deep Learning have made possible reliable landmark tracking of human bodies and faces that can be used for a variety of tasks. We test a recent Computer Vision solution, MediaPipe Holistic (MPH), to find out if its tracking of the facial features is reliable enough for a linguistic analysis of data from sign languages, and compare it to an older solution (OpenFace, OF). We use an existing data set of sentences in Kazakh-Russian Sign Language and a newly created small data set of videos with head tilts and eyebrow movements. We find that MPH does not perform well enough for linguistic analysis of eyebrow movement - but in a different way from OF, which is also performing poorly without correction. We reiterate a previous proposal to train additional correction models to overcome these limitations.

Yuri Monakhov, Oleg Nikitin, Anna Kuznetsova et al.

In the authors' opinion, anomaly detection systems, or ADS, seem to be the most perspective direction in the subject of attack detection, because these systems can detect, among others, the unknown (zero-day) attacks. To detect anomalies, the authors propose to use machine synesthesia. In this case, machine synesthesia is understood as an interface that allows using image classification algorithms in the problem of detecting network anomalies, making it possible to use non-specialized image detection methods that have recently been widely and actively developed. The proposed approach is that the network traffic data is "projected" into the image. It can be seen from the experimental results that the proposed method for detecting anomalies shows high results in the detection of attacks. On a large sample, the value of the complex efficiency indicator reaches 97%.

Yuri Monakhov, Anna Kuznetsova

Development of optimal control procedures for congested networks is a key factor in maintaining efficient network utilization. The absence of congestion control mechanism or its failure can lead to the lack of availability for certain network segments, and in severe cases -- for the entire network. The paper presents an analytical model describing the operation of the TCP Reno congestion control algorithm in terms of differential calculus and queuing systems. The purpose of this research is to explore the possibilities and ways of increasing the virtual channel capacity utilization efficiency in a lossy environment.