https://etalpykla.vilniustech.lt/handle/123456789/159394 2026-04-11T21:29:06Z https://etalpykla.vilniustech.lt/handle/123456789/159556 Deep Learning Model for Sensor based Swimming Style Recognition Tarasevičius, Deividas; Serackis, Artūras This paper aim is to present deep learning based approach for swimming style recognition performed on publicly available data collected with a smartwatch. The proposed method is a Bi-LSTM (Bidirectional Long-Short Term Memory) network, which was constructed using MATLAB neural network toolbox. Data for the system was prepared by segmenting it into fixed-size windows and extracting pure signal features such as mean, standard deviation, median absolute deviation (MAD), signal magnitude area (SMA), interquartile range (IQR) as well as features from normalized signal spectrum such as entropy, energy, kurtosis, skewness and index of spectrum maximum (ISM) from each window. The Bi-LSTM method was able to perform with average F1 score of 91.39%. 2020-01-01T00:00:00Z https://etalpykla.vilniustech.lt/handle/123456789/159555 Analysis of Deep Neural Network Architectures and Similarity Metrics for Low-Dose CT Reconstruction Brusokas, Jonas; Petkevičius, Linas Computed tomography (CT) is a widely used imaging technique in the medical field. During CT procedures patients are exposed to high amounts of radiation, posing a tangible threat to their health. Developed low-dose procedures lower exposure but produce noise and artifacts in images. To improve diagnostic accuracy, deep learning techniques are proposed to remove noises and artifacts from low-dose images. In this paper, the performance of several neural network architectures and similarity metrics as loss functions for low-dose CT image reconstruction are analyzed. Experimental results showed that selection of loss function can have significant impact on model performance, with the GSSIM metric outperforming other contemporary metrics SSIM, MSSSIM and MSE. Experiments were conducted using open-access and local cancer research institution data. 2020-01-01T00:00:00Z https://etalpykla.vilniustech.lt/handle/123456789/159554 Naming and Routing Scheme for Data Content Objects in Information-Centric Network Jaber, Ghassan; Pastei, Natallia; Rahal, Fatima; Abboud, Ahmad The subject of this article is devoted to the problems of naming and routing scheme for data content object in information-centric networks (ICN). The relevance of the work is determined by the idea of an information-content networks as a future promising technology for the Internet. The article introduces a new naming strategy for ICN – named Semantic Information-Centric Network (SINC). SINC uses three addresses: Geographical, Semantic and Publisher ID address. It was done the classifying data into the four types and classifying subscriber request into four classes where the SICN can cope with these different types and classes. Briefly discussed routing tables structure Geo-ID, Geo-Sematic, ID-Semantic and some algorithms for updating, removing, merging and matching records. The results of two scenarios modeling evaluation by comparing the SICN with different schemes and projects including IP, DONA, PURSUIT, CBCB, KBN according to following metrics: time delay, flooding or traffic, and efficiency reuse factor for data are presented. In terms of flooding and time delay SICN outperforms the other ICN projects. In terms of efficiency SICN shows a good results compared with other schemes. 2020-01-01T00:00:00Z https://etalpykla.vilniustech.lt/handle/123456789/159553 Search by Image Engine using Local Feature Detectors Smelyakov, Kirill; Chupryna, Anastasiya; Ponomarenko, Oleksandr; Kolisnyk, Maksym Nowadays, modern big data warehouses require the development of effective management algorithms. For large image storages first of all it's important to develop effective algorithms for comparing and searching a similar image from an image, taking into account their possible geometric transformations. In this regard, one of the most promising is the approach based on the use of invariant Local Feature Detectors. The work is carried out experimental research of such detectors’ effectiveness for Search by Image Engine in large image storages. 2020-01-01T00:00:00Z