Detection of Physical Activity Using Machine Learning Methods Based on Continuous Blood Glucose Monitoring and Heart Rate Signals

L Dénes-Fazakas, M Siket, L Szilágyi, L Kovács… - Sensors, 2022 - mdpi.com
Non-coordinated physical activity may lead to hypoglycemia, which is a dangerous condition
for diabetic people. Decision support systems related to type 1 diabetes mellitus (T1DM) still …

Using morphological data in language modeling for Serbian large vocabulary speech recognition

E Pakoci, B Popović, D Pekar - Computational intelligence and …, 2019 - Wiley Online Library
Serbian is in a group of highly inflective and morphologically rich languages that use a lot of
different word suffixes to express different grammatical, syntactic, or semantic features. This …

Physical Activity Detection for Diabetes Mellitus Patients Using Recurrent Neural Networks

L Dénes-Fazakas, B Simon, Á Hartvég, L Kovács… - Sensors, 2024 - mdpi.com
Diabetes mellitus (DM) is a persistent metabolic disorder associated with the hormone
insulin. The two main types of DM are type 1 (T1DM) and type 2 (T2DM). Physical activity …

Detection of physical activity using machine learning methods

L Dénes-Fazakas, L Szilágyi, J Tasic… - 2020 IEEE 20th …, 2020 - ieeexplore.ieee.org
In the case of diabetes mellitus physical activity does have a high effect on the glycemic
state of the patients. This is especially regarding the patients with Type 1 diabetes mellitus …

The impact of the cognitive effects of L1 orthographic depth and morphological complexity on L2 French morphographic processing

V Serrau, C Gunnarsson-Largy… - Language, Interaction and …, 2023 - jbe-platform.com
Orthographic depth has been shown to influence the default orthographic processing
mechanisms. However, the question of the impact of L1 orthographic depth on the …

Machine preparation for human labelling of hierarchical train sets by spectral clustering

D Papp, G Szűcs, Z Knoll - 2019 10th IEEE International …, 2019 - ieeexplore.ieee.org
Human labeling of an unknown dataset for machine learning is a tedious work for humans.
The aim of the paper was to develop a machine preparation of the data that helps human …

Modeli srpskog jezika i njihova primena u govornim i jezičkim tehnologijama

S Ostrogonac - 2018 - search.proquest.com
Statistički jezički model, u teoriji, predstavlja raspodelu verovatnoća nad skupom svih
mogućih sekvenci reči nekog jezika. U praksi, to je mehanizam kojim se estimiraju …

Methods for using class based n-gram language models in the Kaldi toolkit

E Pakoci, B Popović - International Conference on Speech and Computer, 2021 - Springer
This paper explains in detail several methods for utilization of class based n-gram language
models for automatic speech recognition, within the Kaldi speech recognition framework. It …

[PDF][PDF] A python package for text processing for serbian: nlpheart

S Ostrogonac, B Rastovic… - Scientific Technical …, 2020 - pdfs.semanticscholar.org
Within the past two decades, text processing became an important part of most state-of-the-
art advanced automation systems. However, for many under-resourced languages it is still …

Improving real-time recognition of morphologically rich speech with transformer language model

B Tarján, G Szaszák, T Fegyó… - 2020 11th IEEE …, 2020 - ieeexplore.ieee.org
Transformer models have become to state-of-the-art in natural language understanding,
their use for language modeling in Automatic Speech Recognition (ASR) is also promising …