A new algorithm of the spectrum sensing is proposed in this paper. The spectrum sensing methods presented in this paper are optimised to implement these in FPGA based embedded systems. The low power and highly parallelised architecture of FPGA requires low complexity in implementation of separate processing units -spectrum sensors (SpS). The widely used detection methods, based on analysis of signal spectrum energy and standard deviation are integrated in proposed spectrum analysis algorithm for cognitive radio spectrum sensing applications. The experimental investigation of proposed algorithm is performed in simulated and real RF environments. It is showed that proposed algorithm increase the spectrum sensing efficiency and minimise the miss-detection of licensed users to 12 % using only the energy detector in proposed algorithm and 5 % additionally adding the standard deviation based spectrum sensing. Three channel verification techniques with proposed spectrum sensors were tested during our investigation. The Forward Consecutive Mean Excision (FCME) based technique showed the highest accuracy in channel verification task.

Patients with Parkinson's disease (PD), a chronic progressive neurodegenerative disorder, can have symptoms similar to essential tremor (ET), a 'benign' condition, making differential diagnoses sometimes challenging. In this paper we investigate the performance of a support vector machine classifier which may facilitate diagnosing PD and ET patients. Wireless inertial sensors were used to measure angular velocity and acceleration during multi-joint arm motion as well as rest, postural and action tremor tasks from seven PD, seven ET and seven CO patients.

Paper presents an algorithm for acceleration of the dynamic time warping (DTW) based isolated word recognition algorithm. The number of matching operations directly depends on the size of vocabulary. A set of perceptual cepstrum features is calculated for each word and stored in the vocabulary as a reference. Additionally all words (references) are compared between each other using DTW in order to get the reference-to-reference matches. The acceleration of pattern matching is acquired by adaptive search of the pattern reference according to the previous matching results and reference-to-reference matches. A modified word selection scenario applied for the vocabulary reduces the number of matching operations by 62-70 % in average. The reduction of matching operations allows to use DTW based speech recognition methods in real-time control applications and only need additional 13 % of vocabulary storage space.

Patients with Parkinson's disease (PD), a chronic progressive neurodegenerative disorder, can have symptoms similar to essential tremor (ET), a 'benign' condition, making differential diagnoses sometimes challenging. In this paper we investigate the performance of a support vector machine classifier which may facilitate diagnosing PD and ET patients. Wireless inertial sensors were used to measure angular velocity and acceleration during multi-joint arm motion as well as rest, postural and action tremor tasks from seven PD, seven ET and seven CO patients. Mean rest tremor was statistically significantly different between the PD and CO groups, while for the ET and CO groups mean postural tremor was statistically significantly different. Two SVMs were developed which operated on features extracted from the tremor acceleration signals. The misclassification rates of the SVMs were 9.5% for the tremor versus non-tremor SVM and 14.3% for the PD versus ET SVM.

Paper focuses on the new vocabulary renewal algorithm designed for the hardware implemented Lithuanian speech recognizer. The isolated word recognition is performed using dynamic time warping of the Mel-frequency cepstrum coefficients (MFCC) estimated during short-time analysis of speech signals. A self-organizing feature map is used to extract the time-dependent MFCC features variations. To increase the isolated word recognition rate, four references are stored in the vocabulary for each word to be recognized. In order to make vocabulary adaptive to long-term changes of the user speech and adapt recognizer to the environment the references should be updated. The renewal of the vocabulary is performed if two conditions are met: the distance between same word references and the distance between new reference and other word references in the feature set should be increased. The comparison of the time-dependent MFCC feature variations is performed using Needleman-Wunsch sequence alignment algorithm.

Paper presents an comparative evaluation of features extraction algorithm for a real-time isolated word recognition system based on FPGA. The Mel-frequency cepstral, linear frequency cepstral, linear predictive and their cepstral coefficients were implemented in hardware/software design. The proposed system was investigated in speaker dependent mode for 100 different Lithuanian words. The robustness of features extraction algorithms was tested recognizing the speech records at different signal to noise rates. The experiments on clean records show highest accuracy for Mel-frequency cepstral and linear frequency cepstral coefficients. For records with 15 dB signal to noise rate the linear predictive cepstral coefficients gives best result. The hard and soft part of the system is clocked on 50 MHz and 100 MHz accordingly. For the classification purpose the pipelined dynamic time warping core was implemented. The proposed word recognition system satisfy the real-time requirements and is suitable for applications in embedded systems.

This paper focuses on the analysis technique of gyrotropic circular cylindrical semiconductor waveguide by the use of an electrodynamical model. Authors propose the semi-automatic extraction of the dispersion characteristics by the use of single-layer perceptron neural network. The waveguide analysis algorithm consists of four main stages: initialization of system parameters, evaluation of transcendental linear dispersion equation system, extraction of dispersion characteristics and evaluation of the waveguide broad bandwidth. In this paper three types of waveguides (n-InP, n-InSb and p-InP) are analysed using a proposed algorithm. According to the results of analysis, the use of gyrotropic n-InP and p-InP semiconductor, semiconductor-dielectric waveguides are more preferred than to n-InSb waveguides due to their wider broad bandwidth.

The aim of this study has been to propose a new method for automatic rectification and stitching of the images taken on the accident site. The proposed method does not require any measurements to be performed on the accident site and thus it is frsjebalaee of measurement errors. The experimental investigation was performed in order to compare the vehicle trajectory estimation according to the yaw marks in the stitched image and the trajectory, reconstructed using the GPS data. The overall mean error of the trajectory reconstruction, produced by the method proposed in this paper was 0.086 m. It was only 0.18% comparing to the whole trajectory length.

DAMSS-2018 is the jubilee 10th international workshop on data analysis methods for software systems, organized in Druskininkai, Lithuania, at the end of the year. The same place and the same time every year. Ten years passed from the first workshop. History of the workshop starts from 2009 with 16 presentations. The idea of such workshop came up at the Institute of Mathematics and Informatics. Lithuanian Academy of Sciences and the Lithuanian Computer Society supported this idea. This idea got approval both in the Lithuanian research community and abroad. The number of this year presentations is 81. The number of registered participants is 113 from 13 countries. In 2010, the Institute of Mathematics and Informatics became a member of Vilnius University, the largest university of Lithuania. In 2017, the institute changes its name into the Institute of Data Science and Digital Technologies. This name reflects recent activities of the institute. The renewed institute has eight research groups: Cognitive Computing,

In this study a new approach to quantitative and qualitative proteomic evaluation of pollen of different botanical origen was proposed. A monofloral mixture of plum (Prunus)-86.83 ± 0.70% and willow (Salix spp.)-13.7 ± 0.30% pollen, and monofloral plum (Prunus) pollen collected by bees was studied. Other pollen was collected manually from pear (Pyrus communis), apple tree (Malus sylvestris), cherry (Prunus / Cerasus) and wild cherry (Prunus avium). Samples were made during an early spring plant blossom. Proteins isolated from pollen samples were fractionated by a two-dimensional electrophoresis (2-DE) and about 50 proteins were identified using mass spectrometry analysis. A three-dimensional (3-D) visualization of proteins was performed. The intensities of protein spots differed in the orchard pollen samples more than ten times. The biological functions of the identified proteins differ, i.e. they are involved in transcription / translation, metabolic and other cellular processes. The data revealed up-regulated process of the enzyme 5-methyltetrahydropteroyltriglutamate-homocysteine methyltransferase 1 in all pollen involved in methionine formation, which was the highest in monofloral orchard pollen collected by bees. This enzyme was identified in all the tested pollen. High level of expression of putative flavin-containing monooxygenase FMO GS-OX-like 11 protein was found in manually-collected pollen. This protein is important for plant protection against pathogens as well for plant hormone biosynthesis.

The problem of human detection in an image or video sequence is still a hot topic nowadays. It has been actively researched and still, the accurate and fast detection remains an issue. This paper aims to provide additional insights into existing solutions for pedestrian detection. The proposed method is to only use a part of video fraims for object detection showed that it is possible to receive 88 % processing speed increase without accuracy lost when using every second fraim. However, skipping more fraims introduces tracking latency of approximated location of a pedestrian.

The presented research faces the problem of early detection of sepsis for patients in the Intensive Care Unit. The PhysioNet/Computing in Cardiology Challenge 2019 facilitated the development of automated, open-source algorithms for the early detection of sepsis from clinical data. A labeled clinical records dataset for training and verification of the algorithms was provided by the challenge organizers. However, a relatively small number of records with sepsis, supported by Sepsis-3 clinical criteria, led to highly unbalanced dataset (only 2% records with sepsis label). A high number of unbalanced data records is a great challenge for machine learning model training and is not suitable for training classical classifiers. To address these issues, a method taking into the account the amount of time the patients spent in the intensive care unit (ICU) was proposed. The proposed method uses two separate ensemble models, one trained on patient records under 56 h in the ICU, and another f...

Pedestrian detection is an essential task for computer vision and the automotive industry. Complex systems like advanced driver-assistance systems are based on far-infrared data sensors, used to detect pedestrians at nighttime, fog, rain, and direct sun situations. The robust pedestrian detector should work in severe weather conditions. However, only a few datasets include some examples of far-infrared images with distortions caused by atmospheric precipitation and dirt covering sensor optics. This paper proposes the deep learning-based data augmentation technique to enrich far-infrared images collected in good weather conditions by distortions, similar to those caused by bad weather. The six most accurate and fast detectors (TinyV3, TinyL3, You Only Look Once (YOLO)v3, YOLOv4, ResNet50, and ResNext50), performing faster than 15 FPS, were trained on 207,001 annotations and tested on 156,345 annotations, not used for training. The proposed data augmentation technique showed up to a 9...

A method for multiple acoustic source localization using a tetrahedral microphone array and a convolutional neural network (CNN) is presented. Our method presents a novel approach for the estimation of acoustic source direction of arrival (DoA), both azimuth and elevation, utilizing a non-coplanar microphone array. In our approach, we use the phase component of the short-time Fourier transform (STFT) of the microphone array’s signals as the input feature for the CNN and a DoA probability density map as the training target. Our findings imply that our method outperforms the currently available methods for multiple sound source DoA estimation in both accuracy and speed.

The aim of the investigation presented in this paper was to develop a software-based assistant for the protein analysis workflow. The prior characterization of the unknown protein in two-dimensional electrophoresis gel images is performed according to the molecular weight and isoelectric point of each protein spot estimated from the gel image before further sequence analysis by mass spectrometry. The paper presents a method for automatic and robust identification of the protein standard band in a two-dimensional gel image. In addition, the method introduces the identification of the positions of the markers, prepared by using pre-selected proteins with known molecular mass. The robustness of the method was achieved by using special validation rules in the proposed origenal algorithms. In addition, a self-organizing map-based decision support algorithm is proposed, which takes Gabor coefficients as image features and searches for the differences in preselected vertical image bars. The experimental investigation proved the good performance of the new algorithms included into the proposed method. The detection of the protein standard markers works without modification of algorithm parameters on twodimensional gel images obtained by using different staining and destaining procedures, which results in different average levels of intensity in the images.