Wyniki wyszukiwania dla: MPEG 7 LOW-LEVEL AUDIO DESCRIPTORS
-
Formaty zapisu cyfrowych dokumentów muzycznych
PublikacjaW pracy zwrócono uwagę na problem przechowywania różnych postaci muzyki występujących w cyfrowych dokumentach muzycznych. Przedstawiono ogólną charakterystykę istniejących formatów zapisu danych muzycznych oraz wybrane cyfrowe formaty muzyczne. Przedstawiono również propozycję stworzenia uniwersalnego formatu opisu danych muzycznych w oparciu o istniejący standard MPEG-7.
-
Online sound restoration system for digital library applications.
PublikacjaAudio signal processing algorithms were introduced to the new online non-commercial service for audio restoration intended to enhance the content of digitized audio repositories. Missing or distorted audio samples are predicted using neural networks and a specific implementation of the Jannsen interpolation method based on the autoregressive model (AR) combined with the iterative restoring of missing signal samples. Since the distortion...
-
Dangerous sound event recognition using Support Vector Machine classifiers
PublikacjaA method of recognizing events connected to danger based on their acoustic representation through Support Vector Machine classification is presented. The method proposed is particularly useful in an automatic surveillance system. The set of 28 parameters used in the classifier consists of dedicated parameters and MPEG-7 features. Methods for parameter calculation are presented, as well as a design of SVM model used for classification....
-
Percentage of the population over 65 in selected EU countries in 2006 and 2017
Dane BadawczeUntil the mid-1980s, Poland belonged to the group of countries with a high dynamics of population growth, reaching 0.9% annually. The average value of the population growth dynamics in the 1980s was 0.66%. From the beginning of this century, the growth rate has taken negative values and in the years 2000-2014 it amounted to an annual average of -0.03%.
-
Skuteczność klasyfikacji gatunków muzycznych za pomocą sieci neuronowej w zależności od typu danych wejściowych
PublikacjaRozpoznawanie gatunku muzycznego jest jednym z podstawowych elementów inteligentnych systemów tworzenia automatycznych list muzyki. Platformy strumieniowe oferujące taką usługę wymagają rozwiązań, które umożliwią jak najdokładniej określić przynależność utworu do gatunku muzycznego. Zgodnie z aktualnym stanem wiedzy – najskuteczniejszym klasyfikatorem są sztuczne sieci neuronowe (w tym w wersji uczenia głębokiego), dla których...
-
Further Developments of the Online Sound Restoration System for Digital Library Applications
PublikacjaNew signal processing algorithms were introduced to the online service for audio restoration available at the web address: www.youarchive.net. Missing or distorted audio samples are estimated using a specific implementation of the Jannsen interpolation method. The algorithm is based on the autoregressive model (AR) combined with the iterative complementation of signal samples. Since the interpolation algorithm is computationally...
-
Marek Wójcikowski dr hab. inż.
OsobyMarek Wójcikowski ukończył w 1993 r. Wydział Elektroniki Politechniki Gdańskiej, specjalność układy elektroniczne. W 2002 r. uzyskał stopień doktora w dziedzinie elektroniki, a w 2016 r. uzyskał stopień doktora habilitowanego na Wydziale Elektroniki Telekomunikacji i Informatyki Politechniki Gdańskiej. Od początku kariery jest związany z Politechniką Gdańską: najpierw jako asystent (lata 1994–2002), a następnie jako adiunkt (od...
-
Exploiting audio-visual correlation by means of gaze tracking
PublikacjaThis paper presents a novel means for increasing audio-visual correlation analysis reliability. This is done based on gaze tracking technology engineered at the Multimedia Systems Department of the Gdansk University of Technology, Poland. In the paper, the past history and current research in the area of audio-visual perception analysis are shortly reviewed. Then the methodology employing gaze tracking is presented along with the...
-
The data exchange between smart glasses and healthcare information systems using the HL7 FHIR standard
PublikacjaIn this study we evaluated system architecture for the use of smart glasses as a viewer of information, as a source of medical data (vital sign measurements: temperature, pulse rate, and respiration rate), and as a filter of healthcare information. All activities were based on patient/device identification procedures using graphical markers or features based on visual appearance. The architecture and particular use cases were implemented...
-
Multibeam sonar data processing for seafloor characterisation
PublikacjaThe approach to seafloor characterisation was investigated. It relies on calculation of several descriptors (parameters) related to seabed type using three types of multibeam sonar data obtained during seafloor sensing: 1) the grey-level sonar images of seabed, 2) the 3D model of the seabed surface which consist of (x, y, z) points, 3) the set of time domain echo envelopes corresponding to several beams. The proposed method has...
-
Combined method of multibeam sonar signal processing and image analysis for seafloor classification
PublikacjaThe combined approach to seafloor characterisation was investigated. It relies on calculation of several descriptors (parameters) related to seabed type using three types of multibeam sonar data obtained during seafloor sensing: 1) the grey-level sonar images (echograms) of seabed, 2) the 3D model of the seabed surface which consists of bathymetric data, 3) the set of time domain bottom echo envelopes received in the consecutive...
-
Detection of Lexical Stress Errors in Non-Native (L2) English with Data Augmentation and Attention
PublikacjaThis paper describes two novel complementary techniques that improve the detection of lexical stress errors in non-native (L2) English speech: attention-based feature extraction and data augmentation based on Neural Text-To-Speech (TTS). In a classical approach, audio features are usually extracted from fixed regions of speech such as the syllable nucleus. We propose an attention-based deep learning model that automatically de...
-
Visual Features for Improving Endoscopic Bleeding Detection Using Convolutional Neural Networks
PublikacjaThe presented paper investigates the problem of endoscopic bleeding detection in endoscopic videos in the form of a binary image classification task. A set of definitions of high-level visual features of endoscopic bleeding is introduced, which incorporates domain knowledge from the field. The high-level features are coupled with respective feature descriptors, enabling automatic capture of the features using image processing methods....
-
Content-Based Approach to Automatic Recommendation of Music
PublikacjaThis paper presents a content-based approach to music recommendation. For this purpose, a database which contains more than 50000 music excerpts acquired from public repositories was built. Datasets contain tracks of distinct performers within several music genres. All music pieces were converted to mp3 format and then parameterized based on MPEG-7, mel-cepstral and time-related dedicated parameters. All feature vectors are stored...
-
Fitting the mobile device characteristics to the user's hearing preferences
PublikacjaA method for fitting the mobile computer audio characteristics to the user's hearing preferences is proposed. The process consists of two stages: calibration and dynamics processing. During the calibration phase the user performs a loudness scaling test giving their response regarding the perceived loudness. The dynamics processing made on above basis sets the loudness to the most comfortable level. The processing accounts both...
-
Detailed results of shaping personnel risk factors in enterprise C
Dane BadawczeThe data presents the shape of all the researched personnel risk factors in the C enterprise (which was tested by the author). Further considerations should be started with the presentation of the synthesis of the obtained results, which is presented in this research data.
-
Wykorzystanie xml do reprezentacji cyfrowych dokumentów muzycznych
PublikacjaW bibliotekach cyfrowych dokumentów muzycznych potrzebny jest format pozwalający na wymianę danych różnego typu związanych z dokumentem muzycznym. Otwarty format XML posiada wiele zalet, które pozwalają na zastosowanie go w tej bibliotece. W rozdziale zwrócono uwagę na możliwość wykorzystania formatów MPEG-7, MARCXML oraz MusicXML do opisania różnorodnych aspektów muzyki. Połączenie wszystkich informacji związanych z dokumentem...
-
A concept of Signal Equalization Method Based on Music Genre and the Listener's Room Characteristics
PublikacjaA research study that investigates the influence of the room acoustics environment on the frequency characteristic of the audio signal playback is presented. First, a novel spectral equalization method of the room acoustic conditions is introduced. On the basis of the frequency response of the room, a system for room acoustics compensation based on eight-band equalizer is proposed. The system settings depend on music genre. In...
-
Multi-Stage Video Analysis Framework
PublikacjaThe chapter is organized as follows. Section 2 presents the general structure of the proposed framework and a method of data exchange between system elements. Section 3 is describing the low-level analysis modules for detection and tracking of moving objects. In Section 4 we present the object classification module. Sections 5 and 6 describe specialized modules for detection and recognition of faces and license plates, respectively....
-
Predicting Value of Binding Constants of Organic Ligands to Beta-Cyclodextrin: Application of MARSplines and Descriptors Encoded in SMILES String
PublikacjaThe quantitative structure–activity relationship (QSPR) model was formulated to quantify values of the binding constant (lnK) of a series of ligands to beta–cyclodextrin (β-CD). For this purpose, the multivariate adaptive regression splines (MARSplines) methodology was adopted with molecular descriptors derived from the simplified molecular input line entry specification (SMILES) strings. This approach allows discovery of regression...
-
Synthesis, Molecular Structure, Metabolic Stability and QSAR Studies of a Novel Series of Anticancer N-Acylbenzenesulfonamides
PublikacjaA series of novel N-acyl-4-chloro-5-methyl-2-(R1-methylthio)benzenesulfonamides 18–47 have been synthesized by the reaction of N-[4-chloro-5-methyl-2-(R1-methylthio) benzenesulfonyl]cyanamide potassium salts with appropriate carboxylic acids. Some of them showed anticancer activity toward the human cancer cell lines MCF-7, HCT-116 and HeLa, with the growth percentages (GPs) in the range from 7% to 46%. Quantitative structure-activity relationship...
-
Synthesis, Molecular Structure, Anticancer Activity, and QSAR Study of N-(aryl/heteroaryl)-4-(1H-pyrrol-1-yl)Benzenesulfonamide Derivatives
PublikacjaA series of N-(aryl/heteroaryl)-4-(1H-pyrrol-1-yl)benzenesulfonamides were synthesized from 4-amino-N-(aryl/heteroaryl)benzenesulfonamides and 2,5-dimethoxytetrahydrofuran. All the synthesized compounds were evaluated for their anticancer activity on HeLa, HCT-116, and MCF-7 human tumor cell lines. Compound 28, bearing 8-quinolinyl moiety, exhibited the most potent anticancer activity against the HCT-116, MCF-7, and HeLa cell lines,...
-
Paremetrization of sounds for recognizing hazarodus events
PublikacjaNowoczesne systemy monitoringu działają na zasadzie automatycznego wykrywania niebezpiecznych zdarzeń na podstawie analizy obrazu z kamer i dźwięku z mikrofonów. W niniejszej publikacji skupiono się na pierwszym etapie rozpoznawania zdarzeń dźwiękowych, jakim jest parametryzacja dźwięku. Podstawą do skutecznego działania systemu jest znalezienie parametrów, których zmienność najlepiej odzwierciedla cechy charakterystyczne dźwięku...
-
Badanie wektora parametrów do automatycznego rozpoznawania stylów muzycznych.
PublikacjaW referacie przedstawiono badania nad doborem parametrów w wektorze cech, służącego do automatycznego rozpoznawania stylu utworów muzycznych. W celu przeprowadzenia eksperymentów zbudowano bazę danych muzycznych zawierającą fragmenty utworów z kilkuset płyt kompaktowych. Zgromadzone utwory przydzielono do odpowiednich stylów muzycznych, wykorzystując w tym celu format danych zawarty na płytach kompaktowych, służący do opisu płyt...
-
Investigating Noise Interference on Speech Towards Applying the Lombard Effect Automatically
PublikacjaThe aim of this study is two-fold. First, we perform a series of experiments to examine the interference of different noises on speech processing. For that purpose, we concentrate on the Lombard effect, an involuntary tendency to raise speech level in the presence of background noise. Then, we apply this knowledge to detecting speech with the Lombard effect. This is for preparing a dataset for training a machine learning-based...
-
Marek Czachor prof. dr hab.
Osoby -
Andrzej Czyżewski prof. dr hab. inż.
OsobyProf. zw. dr hab. inż. Andrzej Czyżewski jest absolwentem Wydziału Elektroniki PG (studia magisterskie ukończył w 1982 r.). Pracę doktorską na temat związany z dźwiękiem cyfrowym obronił z wyróżnieniem na Wydziale Elektroniki PG w roku 1987. W 1992 r. przedstawił rozprawę habilitacyjną pt.: „Cyfrowe operacje na sygnałach fonicznych”. Jego kolokwium habilitacyjne zostało przyjęte jednomyślnie w czerwcu 1992 r. w Akademii Górniczo-Hutniczej...
-
Machine learning applied to acoustic-based road traffic monitoring
PublikacjaThe motivation behind this study lies in adapting acoustic noise monitoring systems for road traffic monitoring for driver’s safety. Such a system should recognize a vehicle type and weather-related pavement conditions based on the audio level measurement. The study presents the effectiveness of the selected machine learning algorithms in acoustic-based road traffic monitoring. Bases of the operation of the acoustic road traffic...
-
Machine learning applied to acoustic-based road traffic monitoring
PublikacjaThe motivation behind this study lies in adapting acoustic noise monitoring systems for road traffic monitoring for driver’s safety. Such a system should recognize a vehicle type and weather-related pavement conditions based on the audio level measurement. The study presents the effectiveness of the selected machine learning algorithms in acoustic-based road traffic monitoring. Bases of the operation of the acoustic road traffic...
-
Traffic Noise Analysis Applied to Automatic Vehicle Counting and Classification
PublikacjaProblems related to determining traffic noise characteristics are discussed in the context of automatic dynamic noise analysis based on noise level measurements and traffic prediction models. The obtained analytical results provide the second goal of the study, namely automatic vehicle counting and classification. Several traffic prediction models are presented and compared to the results of in-situ noise level measurements. Synchronized...
-
Audio Feature Analysis for Precise Vocalic Segments Classification in English
PublikacjaAn 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...
-
Experimental Study of the Influence of Noise Level on the Uncertainty Value in a Measurement System Containing an Analog-to-Digital Converter
Dane BadawczeFor newly developed measuring systems it is easy to estimate type B uncertainties based on the technical data of the measuring modules applied. However, it is difficult to estimate A type un-certainties due to the unknown type and level of interferences infiltrating into the measuring sys-tem. This is a particularly important problem for measurements...
-
seafloor characterisation combined approach using multibeam sonar echo signal processing and image analysis
PublikacjaThe authors propose the approach to seafloor characterisation which relies on the combined, concurrent use of two different techniques: (i) multibeam sonar image analysis and (ii) multibeam seabed echoes processing. The first technique is based on constructing the grey-level sonar images of the seabed extracted from the echoes received in the consecutive soundings. Then, the set of parameters describing the local region of sonar...
-
Results of implementation of Feed Forward Neural Networks for modeling of heat transfer coefficient during flow condensation for low and high values of saturation temperature
Dane BadawczeThis database present results of implementation of Feed Forward Neural Networks for modeling of heat transfer coefficient during flow condensation for low and high values of saturation temperature. Databse contain one table and 7 figures.
-
Analysis of the Usefulness of Cheap Audio Recorders for Spectral Measurement of Environmental Noise
PublikacjaEnvironmental noise pollution is nowadays one of the most serious health threats. The impact of noise on the human body depends not only on the sound level but also on its spectral distribution. Reliable measurements of the environmental noise spectrum are often hampered by the very high price of top quality measuring devices. This paper explores the possibility of using much cheaper audio recorders for the frequency analysis....
-
Accidents, victims and risk levels on regional roads in pomorskie voivodeship, 2017-2019 - Medium to High and high road sections
Dane BadawczeData contain road sections with the highest number of accidents and victims on regional roads (voivodeship roads) in pomorskie voivodeship in 2017-2019. Measures used to assess the level of risk is: minimum 4 accidents or 4 seriously injured or fatalities per one kilometer (5 classes: low, low to medium, medium, medium to high, high):
-
Evaluation of aspiration problems in L2 English pronunciation employing machine learning
PublikacjaThe approach proposed in this study includes methods specifically dedicated to the detection of allophonic variation in English. This study aims to find an efficient method for automatic evaluation of aspiration in the case of Polish second-language (L2) English speakers’ pronunciation when whole words are analyzed instead of particular allophones extracted from words. Sample words including aspirated and unaspirated allophones...
-
Zmiany w systemach jakości BRC dedykowanych producentom żywności
PublikacjaW artykule przedstawiono zmiany wprowadzone w najnowszych wersjach standardu BRC Food wersja 7 i BRC/IoP wersja 5. Na podstawie danych zamieszczonych w ogólnodostępnym katalogu „BRC Global Standards Directory” dokonano oceny stopnia certyfikacji polskich przedsiębiorstw wg standardu BRC Food. Przeprowadzono analizę liczby akredytowanych jednostek certyfikujących w Polsce z uwzględnieniem stopnia ich wydajności.
-
Power electronic transformer based on cascaded H-bridge converter
PublikacjaIn this paper the control strategy of power electronic transformer (PET) is proposed. The analyzed structure of PET uses two seven-level cascaded H-bridge (CHB) rectifiers. The electrical power of PET is transferred between DC-links of CHB converters using dual-active-bridges (DABs) and low voltage high frequency transformers. The roposed solution allows for controlling the active and reactive power with a low level of harmonic...
-
Electron Scattering from Methyl Formate (HCOOCH3): A Joint Theoretical and Experimental Study
PublikacjaElastic low-energy electron collisions with methyl formate have been studied theoretically at the level of various theories. The elastic integral cross section was calculated using Schwinger multichannel and R-matrix methods, in the static-exchange and static-exchange plus polarization levels of approximations for energies up to 15 eV. The absolute total cross section for electron scattering from methyl formate has been measured...
-
Seafloor characterisation using multibeam data: sonar image properties, seabed surface properties and echo properties
PublikacjaIn the paper, the approach to seafloor characterisation is presented. The multibeam sonars, besides their well verified and widely used applications like high resolution bathymetry and underwater object detection and imaging, are also the promising tool in seafloor characterization and classification, having several advantages over conventional single beam echosounders. The proposed approach relies on the combined, concurrent use...
-
APPLICATION OF THE HIGH FREQUENCY LINEARIZATION OF THE EAR IN PATIENTS WITH TINNITUS . Metoda linearyzacji narządu słuchu u osób cierpiących z szumami usznymi
PublikacjaThis paper summarises the problem of tinnitus, hypotheses on its causes and the treatment methods. Moreover, a hypothesis on tinnitus origins is explained, based on the mechanisms of the analog-to-digital conversion and quantization. In addition, this paper describes methods of determining the acoustic intensity and spectra of low- level ultrasonic signals, as well as impedance characteristics of an ultrasound transducer. Furthermore,...
-
System for characterisation and multidimensional imaging of seafloor using multibeam sonar data
PublikacjaMultibeam sonars are widely used in applications like high resolution bathymetry measurements, underwater object detection and imaging, etc. Also, they are the promising tool in seafloor characterisation and classification, having several advantages over conventional single beam echosounders. The proposed approach to seafloor classification relies on the combined use of three different techniques. In each of them, a set of descriptors...
-
Pounding between high-rise buildings with different structural arrangements
PublikacjaEarthquake-induced structural pounding has led to significant damages during previous earthquakes. This paper investigates the effect of pounding on the dynamic response of colliding high-rise buildings with different structural arrangements. Three 3-D buildings are considered in the study, including 5-storey building, 7-storey building and 9-storey building. Three pounding scenarios are also taken into account, i.e. pounding between...
-
THREE-LEVEL F-TYPE INVERTER
PublikacjaGiven the recent available IGBT switch modules up to 6.5 kV, 1200 A rating, the prospect of the diode-free variant topology of the three-level neutral-point-clamped (3-level, T-type) inverter in certain medium voltage applications is bright; due to its small part count and low conduction losses compared to the diode-clamped NPC inverter. However, within this voltage range, the input dc voltage rating of 50% of the switches per...
-
Low-energy interactions related to atmospheric and extreme conditions
PublikacjaThis Topical Issue, entitled “Low-Energy Interactions Related to Atmospheric and Extreme Conditions”, showcases a collection of eighteen articles that reported recent theoretical and experimental findings pertaining to the following topics: – low-energy interactions of charged particles (electrons [1–7], protons [8], positrons [9]), and photons [10] with atoms and molecules of biological [1–4,7,8], astrochemical [10], industrial,...
-
Multi-core processing system for real-time image processing in embedded computer vision applications
PublikacjaW artykule opisano architekturę wielordzeniowego programowalnego systemu do przetwarzania obrazów w czasie rzeczywistym. Dane obrazu są przetwarzane równocześnie przez wszystkie procesory. System umożliwia niskopoziomowe przetwarzanie obrazów,np. odejmowanie tła, wykrywanie obiektów ruchomych, transformacje geometryczne, indeksowanie wykrytych obiektów, ocena ich kształtu oraz podstawowa analiza trajektorii ruchu. Ang:This paper...
-
Accidents, victims and risk levels on regional roads in pomorskie voivodeship, 2017-2019 - All accidents
Dane BadawczeData contain risk classification on regional roads (voivodeship roads) in pomorskie voivodeship in 2017-2019. Measures used to assess the level of risk are (5 classes low, low to medium, medium, medium to high, high):
-
Skin Conductance Level (SCL) data collected during mental training of group of 30 athletes
Dane BadawczeThe dataset contain raw Skin Conductance Level (SCL) data, collected at a frequency of 40 Hz and expressed in units of microsiemens (μS), during mental training of group of 30 athletes, under the project "Psychophysiology of guided and self-produced imagery in sport".
-
Assessing groundwater vulnerability to sea water intrusion in the coastline of the inner Puck Bay using GALDIT method
PublikacjaIn this research, GALDIT method was used to assess seawater intrusion in the coastal aquifer of the inner Puck Bay (Southern Baltic Sea). The impact of potential sea-level rise on groundwater vulnerability for years 2081-2100 was also considered. The study area was categorized into three classes of vulnerability: low, moderate and high. The most vulnerable area is the Hel Peninsula with northern part of the Kashubian Coastland....