Filters
total: 974
filtered: 751
Search results for: GESTURE
-
Some developments in constitutive modelling of soft clays, Keynote lecture
PublicationPrzedstawiono przegląd najczęściej stosowanych modeli konstytutywnych dla naturalnych gruntów słabonośnych, takich jak: gliny, namuły lub torfy. Skupiono się przede wszystkim na takich elementach charakterystyki mechanicznej gruntów słabonośnych jak: anizotropia, zjawisko pełzania i relaksacji oraz destrukturyzacja. Artykuł jest podsumowaniem 4-letniego projektu badawczego finansowanego w ramach 5 ramowego projektu Unii Europejskiej:...
-
Chemical order and crystallographic texture of FePd:Cu thin alloy films
Publication -
Auditory-model based robust feature selection for speech recognition
Publication -
Lattice-commensurate skyrmion texture in a centrosymmetric breathing kagome magnet
PublicationSkyrmion lattices (SkL) in centrosymmetric materials typically have a magnetic period on the nanometer-scale, so that the coupling between magnetic superstructures and the underlying crystal lattice cannot be neglected. We reveal the commensurate locking of a SkL to the atomic lattice in Gd3Ru4Al12 via high-resolution resonant elastic x-ray scattering (REXS). Weak easy-plane magnetic anisotropy, demonstrated here by a combination...
-
Fast Distance Vector Field Extraction for Facial Feature Detection
PublicationPraca dotyczy metody lokalizowania cech twarzy z wykorzystaniem wektorowych pól odległości (DVF), zaproponowanej przez Asteriadisa. Zawiera skrótowy opis tej koncepcji oraz prezentuje ulepszenia wprowadzone przez autorów do oryginalnego rozwiązania. Główną zaletą wprowadzonych zmian jest znacznie zredukowana złożoność obliczeniowa algorytmu, jak również zwiększona precyzja wektorowego pola odległości wyznaczanego w wyniku jego...
-
Feature type and size selection for adaboost face detection algorithm
PublicationThe article presents different sets of Haar-like features defined for adaptive boosting (AdaBoost) algorithm for face detection. Apart from a simple set of pixel intensity differences between horizontally or vertically neighboring rectangles, the features based on rotated rectangles are considered. Additional parameter that limits the area on which the features are calculated is also introduced. The experiments carried out on...
-
IMPEDANCE MEASUREMENT MODULE FOR GAS SENSORS WITH TEMPERATURE CONDITIONING FEATURE
PublicationThe paper presents an impedance measurement module which is aimed for gas sensor. Sensor’s heater temperature conditioning and modulation feature is available in order to allow implementation of different techniques improving selectivity and sensitivity of gas sensors. The measurement module uses three-parameter sine-fitting technique for impedance measurement. To monitor sensor temperature, the resistance of the sensor’s heater...
-
Local Texture Pattern Selection for Efficient Face Recognition and Tracking
PublicationThis paper describes the research aimed at finding the optimal configuration of the face recognition algorithm based on local texture descriptors (binary and ternary patterns). Since the identification module was supposed to be a part of the face tracking system developed for interactive wearable computer, proper feature selection, allowing for real-time operation, became particularly important. Our experiments showed that it is...
-
Intrinsic asymmetry with respect to adversary: a new feature of Bell inequalities
PublicationIt is known that the local bound of a Bell inequality is sensitive to the knowledge of the external observer about the settings statistics. Here we ask how that sensitivity depends on the structure of that knowledge. It turns out that in some cases it may happen that the local bound is much more sensitive to the adversaryʼs knowledge about the settings of one party than the other. Remarkably, there are Bell inequalities which are...
-
Impact of the surface evenness and texture on tire/road rolling resistance
PublicationThis paper deals with the issue of a surface's roughness and texture impact on tire/road rolling resistance. It includes a brief description of research aims, measurements and an analysis of results. It also presents observations and conclusions regarding drum facility modernisation which allows studies concerning surface's roughness and texture impact on tire/road rolling resistance.
-
Audio Feature Analysis for Precise Vocalic Segments Classification in English
PublicationAn approach to identifying the most meaningful Mel-Frequency Cepstral Coefficients representing selected allophones and vocalic segments for their classification is presented in the paper. For this purpose, experiments were carried out using algorithms such as Principal Component Analysis, Feature Importance, and Recursive Parameter Elimination. The data used were recordings made within the ALOFON corpus containing audio signal...
-
Selected Aspects of Pavement Texture Influence on Tire Rolling Resistance
PublicationTire rolling resistance has a significant influence on fuel consumption in cars and trucks and on CO2 emissions. Rolling resistance depends on the tire construction, pavement texture and stiffness, as well as environmental and traffic conditions. This article presents a pilot study on the impact of pavement texture on the rolling resistance of passenger car tires. Reasons why Mean Profile Depth is not a good descriptor of pavement...
-
Tolerance Optimization of Antenna Structures by Means of Response Feature Surrogates
PublicationFabrication tolerances and other types of uncertainties, e.g., the lack of precise knowledge of material parameters, have detrimental effects on electrical and field performance of antenna systems. In the case of input characteristics these are particularly noticeable for narrow- and multi-band antennas where deviations of geometry parameters from their nominal values lead to frequency shifts of the operating frequency bands. Improving...
-
MP3vec: A Reusable Machine-Constructed Feature Representation for Protein Sequences
Publication—Machine Learning (ML) methods have been used with varying degrees of success on protein prediction tasks, with two inherent limitations. First, prediction performance often depends upon the features extracted from the proteins. Second, experimental data may be insufficient to construct reliable ML models. Here we introduce MP3vec, a transferable representation for protein sequences that is designed to be used specifically for sequence-to-sequence...
-
Experimental investigation into surface texture effect on journal bearings performance
PublicationThe aim of this study was to analyse the performance of journal bearings with specially created dimples on the sliding surface and operating under various conditions. The texture was created on the bearing surface that co-acted with the smooth journal; moreover, the variation of the textured surface of the journal mating with the smooth bearing was tested, and the results were compared to those obtained with the standard smooth...
-
Texture Features for the Detection of Playback Attacks: Towards a Robust Solution
PublicationThis paper describes the new version of a method that is capable of protecting automatic speaker verification (ASV) systems from playback attacks. The presented approach uses computer vision techniques, such as the texture feature extraction based on Local Ternary Patterns (LTP), to identify spoofed recordings. Our goal is to make the algorithm independent from the contents of the training set as much as possible; we look for the...
-
Data Sampling-Based Feature Selection Framework for Software Defect Prediction
Publication -
Standard hypothyroid treatment did not restore proper metabolic response to carbohydrate
Publication -
OmicSelector: automatic feature selection and deep learning modeling for omic experiments
Publication -
FPGA Implementation of the Gradient Adaptive Lattice Filter Structure for Feature Extraction
Publication -
Agent-Based RBF Network Classifier with Feature Selection in a Kernel Space
Publication -
Cluster-dependent rotation-based feature selection for the RBF networks initialization
Publication -
Feature-based generation of machining process plans for optimised parts manufacture
PublicationPrzedstawiono aktualne zagadnienia związane z integracją systemów CAD/CAM/CAPP. Opracowano model informacyjny danych dla systemu CAPP w postaci zapisu macierzowego. Zawarto algorytm tworzenia rozwiązań wariantowych i wyboru optymalnego procesu technologicznego obróbki. Proponowany algorytm działania zweryfikowano na rzeczywistym przykładzie z praktyki przemysłu.
-
Analysis of 2D Feature Spaces for Deep Learning-based Speech Recognition
Publicationconvolutional neural network (CNN) which is a class of deep, feed-forward artificial neural network. We decided to analyze audio signal feature maps, namely spectrograms, linear and Mel-scale cepstrograms, and chromagrams. The choice was made upon the fact that CNN performs well in 2D data-oriented processing contexts. Feature maps were employed in the Lithuanian word recognition task. The spectral analysis led to the highest word...
-
Family business experience and the probability of starting a venture: gender differences in Poland
PublicationThe aim of this study is to analyse whether the experience of working in a family member’s business is related differently to the assessed probabilities of men and women starting their own new venture in the future. The research is conducted on a sample of 334 Polish undergraduate students. Poland is an efficiency-driven European economy with a substantial gender gap in entrepreneurship. The results obtained indicate that the relationship...
-
Surface texture of pine wood beams after planing in industrial conditions
PublicationMeasuring the surface features of wooden components after planing is connected with the rising demands regarding to the quality of the painted window frames. In the paper the complex surface texture analysis especially identifying of surface damages using non-contact 3D measurement techniques for precise area measurement were presented.This enabled the study of irregular surface features with sufficient fidelity and resolution....
-
Comparative analysis of spectral and cepstral feature extraction techniques for phoneme modelling
PublicationPhoneme parameter extraction framework based on spectral and cepstral parameters is proposed. Using this framework, the phoneme signal is divided into frames and Hamming window is used. The performances are evaluated for recognition of Lithuanian vowel and semivowel phonemes. Different feature sets without noise as well as at different level of noise are considered. Two classical machine learning methods (Naive Bayes and Support...
-
Real-time facial feature tracking in poor quality thermal imagery
PublicationRecently, facial feature tracking systems have become more and more popular because of many possible use cases. Especially in medical applications location of the face and facial features are very useful. Many researches have presented methods to detect and track facial features in visible light. However, facial feature analysis in thermography may also be very advantageous. Some examples of using infrared imagery in medicine include...
-
3D PCB package for GaN inverter leg with low EMC feature
PublicationThis paper presents the adaptation of a 3D integration concept previously used with vertical devices to lateral GaN devices. This 3D integration allows to reduce loop inductance, to ensure more symmetrical design with especially limited Common Mode emission, thanks to a low middle point stray capacitance. This reduction has been achieved by both working on the power layout and including a specific shield between the devices and...
-
Surface Texture Analysis of Hardened Shafts after Ceramic Ball Burnishing
PublicationThis article represents the results of testing the surface condition of shafts manufactured by the burnishing process. The shafts with a hardness of approximately 62 HRC (Rockwell C). were burnished with a ceramic ball (Si3N4), where the force range was controlled by the means of a hydraulic system. The machining process consisted of hard turning shafts with cubic boron nitride (CBN) inserts, followed by burnishing with the use...
-
EFFECT OF CRICKET POWDER ADDITION ON 1H NMR MOBILITY AND TEXTURE OF PORK PÂTÉ
Publication -
Is the growing wealth the driving force for venture capital fundraising in Europe? An empirical analysis
Publication -
Foetal haemoglobin-blood cells (F-cells) as a feature of embryonic tumours (blastomas)
Publication -
Tree-based homogeneous ensemble model with feature selection for diabetic retinopathy prediction
Publication -
Multidimensional Feature Selection and Interaction Mining with Decision Tree Based Ensemble Methods
Publication -
Surface texture formation in precision machining of direct laser deposited tungsten carbide
Publication -
Surface texture generation during cylindrical milling in the aspect of cutting force variations
Publication -
Mechanical and Physicochemical Properties of Newly Formed ZnO-PMMA Nanocomposites for Denture Bases
Publication -
Preparation and Characterisation of Poly(methyl metacrylate)-Titanium Dioxide Nanocomposites for Denture Bases
Publication -
Response Feature Technology for High-Frequency Electronics. Optimization, Modeling, and Design Automation
PublicationThis book discusses response feature technology and its applications to modeling, optimization, and computer-aided design of high-frequency structures including antenna and microwave components. By exploring the specific structure of the system outputs, feature-based approaches facilitate simulation-driven design procedures, both in terms of improving their computational efficiency and reliability. These benefits are associated...
-
Venture capital w finansowaniu inwestycji podwyższonego ryzyka w warunkach kryzysu
PublicationW publikacji przedstawiono venture capitał jako źródło finansowania inwestycji podwyższonego ryzyka. Wykorzystanie venture capital odniesiono do kryzysu gospodarczego. Podjęto się również oceny funkcjonowania funduszy venture capital w warunkach gospodarki Polski.
-
Publicly available lecture webcasts - e-learning or promotion tool? case study
PublicationThis paper aims to show how universities interact with Internet users by webcasting selected courses. Paper has exploratory case-study character, presenting example of Berkeley Webcast initiative of University of California, Berkeley, webcasting undergraduate courses and on-campus events. On the base of short introduction to webcasting usage as an e-learning and promotional tool, the analysis of 3 purposely chosen different courses...
-
A High-Efficient Measurement System With Optimization Feature for Prototype CMOS Image Sensors
PublicationIn this paper, a gray-scale CMOS image sensor (CIS) characterization system with an optimization feature has been proposed. By using a very fast and precise control of light intensity, based on the pulsewidth-modulation method, it is avoided to measure the illuminance every time. These features accelerate the multicriteria CIS optimization requiring many thousands of measurements. The system throughput is 2.5 Gb/s, which allows...
-
Prediction based on integration of Decisional DNA and a feature selection algorithm Relief-F
PublicationThe paper presents prediction model based on Decisional DNA and Set of experienced integrated with Relief_F algorithm for feature selection
-
Current based Normalized Triple Covariance as a bearings diagnostic feature in induction motor
PublicationDiagnosis of induction motors, conducted remotely by measuring and analyzing the supply current is attractive with the lack of access to the engine. So far there is no solution, based on analysis of current, the credibility of which allow use in industry. Statistics of IM bearing failures of induction motors indicate, that they constitute more than 40% of IM damage, therefore bearing diagnosis is so important. The article provides...
-
A Study of Cross-Linguistic Speech Emotion Recognition Based on 2D Feature Spaces
PublicationIn this research, a study of cross-linguistic speech emotion recognition is performed. For this purpose, emotional data of different languages (English, Lithuanian, German, Spanish, Serbian, and Polish) are collected, resulting in a cross-linguistic speech emotion dataset with the size of more than 10.000 emotional utterances. Despite the bi-modal character of the databases gathered, our focus is on the acoustic representation...
-
Fast Design Closure of Compact Microwave Components by Means of Feature-Based Metamodels
PublicationPrecise tuning of geometry parameters is an important consideration in the design of modern microwave passive components. It is mandatory due to limitations of theoretical design methods unable to quantify certain phenomena that are important for the operation and performance of the devices (e.g., strong cross-coupling effects in miniaturized layouts). Consequently, the initial designs obtained using analytical or equivalent network...
-
Global Design Optimization of Microwave Circuits Using Response Feature Inverse Surrogates
PublicationModern microwave design has become heavily reliant on full-wave electromagnetic (EM) simulation tools, which are necessary for accurate evaluation of microwave components. Consequently, it is also indispensable for their development, especially the adjustment of geometry parameters, oriented towards performance improvement. However, EM-driven optimization procedures incur considerable computational expenses, which may become impractical...
-
Multi-Criterial Design of Antennas with Tolerance Analysis Using Response-Feature Predictors
PublicationImperfect manufacturing is one of the factors affecting the performance of antenna systems. It is particularly important when design specifications are strict and leave a minimum leeway for a degradation caused by geometry or material parameter deviations from their nominal values. At the same time, conventional antenna design procedures routinely neglect to take the fabrication tolerances into account, which is mainly a result...
-
Feature-Based Characterisation of Turned Surface Topography with Suppression of High-Frequency Measurement Errors
Publication