Preferencje help
Widoczny [Schowaj] Abstrakt
Liczba wyników

Znaleziono wyników: 17

Liczba wyników na stronie
first rewind previous Strona / 1 next fast forward last
Wyniki wyszukiwania
Wyszukiwano:
w słowach kluczowych:  dynamic time warping
help Sortuj według:

help Ogranicz wyniki do:
first rewind previous Strona / 1 next fast forward last
EN
In this paper effects of COVID–19 pandemic on stock market network are analyzed by an application of operational research with a mathematical approach. For this purpose two minimum spanning trees for each time period namely before and during COVID–19 pandemic are constructed. Dynamic time warping algorithm is used to measure the similarity between each time series of the investigated stock markets. Then, clusters of investigated stock markets are constructed. Numerical values of the topology evaluation for each cluster and time period is computed.
EN
Seismic sparse spike deconvolution is commonly used to invert for subsurface refectivity series and is usually implemented as an inversion scheme. Conventional sparse spike deconvolution method does not utilize the relationships among adjacent traces resulting in instability and poor lateral continuity of the inverted result. We propose a multichannel sparse spike deconvolution method with a sparsity-promoting constraint and an extra lateral constraint exploiting the spatial relationships among adjacent seismic traces. Firstly, the dynamic time warping (DTW) is performed between any two adjoining seismic traces to obtain the warping path (a series of estimated time shifts of one seismic trace relative to the other). Based on the assumption that if the inverted refectivity series is convolved with the same wavelet used for inversion, the newly constructed adjoining seismic traces shall also be conformable to the relationships exploited among the original seismic traces by DTW. A diference operator is constructed with the estimated time shifts to guarantee the diference operation is performed between corresponding time samples on adjoining seismic traces and the inversion is regularized with this diference operator as the lateral constraint. Synthetic and real data case studies confrm that inverted result obtained by the proposed method is superior to those obtained by single-channel sparse spike deconvolution method and another multichannel deconvolution method based on horizontal frst-order derivative constraint in both signal-to-noise ratio and lateral continuity.
3
Content available remote Computer – aided method for lower limbs kinematic analysis
EN
The aim of this paper is to propose a novel method that enables kinematic analysis of motion capture (MoCap) data of lower limbs activities by comparison of body joints trajectories to the reference template. We propose an appropriate human body kinematic model, MoCap aligning procedure and heuristic evaluation with Dynamic Time Warping (DTW) - based approach. In contrast to other state-of-the-art papers, where analysis is performed on the single joint on the selected two-dimensional plane, we performed three-dimensional evaluation of human body by analyzing the whole kinematic chain jointly. This approach allows us to find which body joints affected the difference between the input and reference recordings the most. This is valuable information that a person who evaluates MoCap data expects to find. We have also performed kinematic analysis applying commonly used kinematic parameters proposed in state-of-the-art researches in order to show that in our case, when there is no restriction on speed or dynamic of action to be analyzed, those parameters cannot be used to draw valuable conclusions. We have tested our method on a dataset consisting recordings of four karate athletes with various experience in Shorin Ryu karate school. While comparing our algorithm’s results to experts evaluation the true positive rate equals 0.93 while negative rate 0.96.
PL
W pracy zaproponowano nową metodę analizy kinematyki kończyn dolnych przy pomocy nagrań motion capture (MoCap). Zaproponowane rozwiązanie pozwala na kompleksową analize całosci łańcucha kinematycznego. Przetestowaliśmy zaproponowany algorytm na zbiorze danych zawierającym nagrania czterech zawodników Shorin Ryu karate uzyskując zadawalające wyniki w porównaniu do analogicznej ewaluacji przeprowadzonej przez eksperta.
EN
The paper describes an evaluation of the application of selected similarity functions in the task of keyword spotting. Experiments were carried out in the Polish language. The research results can be used to improve already existing keyword spotting methods, or to develop new ones.
PL
W pracy przedstawiono ocenę zastosowania wybranych funkcji podobieństwa w zadaniu wykrywania słów kluczowych. Przeprowadzono eksperymenty dla języka polskiego. Wyniki badań można wykorzystać do ulepszenia już istniejących metod wykrywania słów kluczowych lub do opracowania nowych.
EN
In the light of regularized dynamic time warping kernels, this paper re-considers the concept of a time elastic centroid for a set of time series. We derive a new algorithm based on a probabilistic interpretation of kernel alignment matrices. This algorithm expresses the averaging process in terms of stochastic alignment automata. It uses an iterative agglomerative heuristic method for averaging the aligned samples, while also averaging the times of their occurrence. By comparing classification accuracies for 45 heterogeneous time series data sets obtained by first nearest centroid/medoid classifiers, we show that (i) centroid-based approaches significantly outperform medoid-based ones, (ii) for the data sets considered, our algorithm, which combines averaging in the sample space and along the time axes, emerges as the most significantly robust model for time-elastic averaging with a promising noise reduction capability. We also demonstrate its benefit in an isolated gesture recognition experiment and its ability to significantly reduce the size of training instance sets. Finally, we highlight its denoising capability using demonstrative synthetic data. Specifically, we show that it is possible to retrieve, from few noisy instances, a signal whose components are scattered in a wide spectral band.
EN
This paper presents experimental results on whispered speech recognition based on Teager Energy Operator for linear and mel cepstral coefficients including the Cepstral Mean Subtraction normalization technique. The feature vectors taken into consideration are Linear Frequency Cepstral Coefficients, Teager Energy based Linear Frequency Cepstral Coefficients, Mel Frequency Cepstral Coefficients and Teager Energy based Mel Frequency Cepstral Coefficients. A speaker dependent scenario is used. For the recognition process, Dynamic Time Warping and Hidden Markov Models methods are applied. Results show a respectable improvement in whispered speech recognition as achieved by using the Teager Energy Operator with Cepstral Mean Subtraction.
EN
One of the crucial aspects of the environmental protection is continuous monitoring of environment. Specific aspect is estimation of the bird species population. It is particularly important for bird species being in danger of extinction. Avian monitoring programs are time and money consuming actions which usually base on terrain expeditions. Certain remedy for this can be automatic acoustical avian monitoring system, described in the paper. Main components of the designed system are: digital audio recorder for bird voices acquisition, computer program automatically recognizing bird species by its signals emitted (voices or others) and object-relational database accessed via the Internet. Optional system components can be: digital camera and camcorder, bird attracting device, wireless data transmission module, power supply with solar panel, portable weather station. The system records bird voices and sends the recordings to the database. Recorded bird voices can be also provoked by the attracting device. Application of wireless data transmission module and power supply with solar panel allows long term operation of digital sound recorder in a hard accessible terrain. Recorded bird voices are analysed by the computer program and labelled with the automatically recognized bird species. Recognition accuracy of the program can be optionally enhanced by an expert system. Besides of labelled sound recordings, database can store also many other information like: photos and films accompanying recorded bird voices/ sounds, information about localization of observation/ recordings (GPS position, description of a place of an observation), information about bird features and behaviour, meteorological information, etc. Database on the base of geographical/ geological digital maps can generate actual maps of bird population (presence, number of individuals of each species). Moreover data-base can trigger alerts in case of rapidly decreasing bird population. It is also possible to obtain new knowledge about bird species with data mining methods. The paper presents collected data on observed bird species (audio recordings, photos and films) as well as results of experiments testing particular components of the automatic acoustical avian monitoring system.
EN
A signature verification system based on static features and time-domain functions of signals obtained using a tablet has been presented in the paper. The signature verification method, based mainly on dynamic time warping coupled with some signature image features, has been described. The FRR measures reflecting the method’s efficiency have been evaluated for verification attempts performed directly after obtaining model signatures and for delayed attempts made after two days. The FAR measures have been assessed both: for simple and for skilled forgeries. The dynamic time warping-based verification has been also examined after applying it to the signals obtained using the developed biometric pen. Obtained results are presented and discussed in the paper.
PL
W artykule przedstawiono system weryfikacji autentyczności podpisu oparty na cechach statycznych i funkcjach czasowych sygnałów pozyskanych na tablecie. Opisano metodę weryfikacji autentyczności podpisu, opartą głównie na metodzie dynamicznego marszczenia czasu i wykorzystującą cechy statyczne wizerunku podpisu. Wyznaczono miary FRR określające skuteczność metody, dla prób weryfikacji następujących bezpośrednio po pozyskaniu modeli podpisów i dla prób odłożonych w czasie o 2 dni. Miary FAR wyznaczono zarówno dla fałszerstw prostych, jak i szkolonych. Weryfikacja oparta na metodzie dynamicznego marszczenia czasu została również zbadana po zastosowaniu jej do sygnałów pozyskanych z wykorzystaniem opracowanego pióra biometrycznego. W artykule przedstawiono i poddano dyskusji otrzymane wyniki.
EN
The availability of cheap and widely applicable person identification techniques is essential due to a wide-spread usage of online services. The dynamics of typing is characteristic to particular users, and users are hardly able to mimic the dynamics of typing of others. State-of-the-art solutions for person identification from the dynamics of typing are based on machine learning. The presence of hubs, i.e., few instances that appear as nearest neighbours of surprisingly many other instances, have been observed in various domains recently and hubness-aware machine learning approaches have been shown to work well in those domains. However, hubness has not been studied in the context of person identification yet, and hubnessaware techniques have not been applied to this task. In this paper, we examine hubness in typing data and propose to use ECkNN, a recent hubness-aware regression technique together with dynamic time warping for person identification. We collected time-series data describing the dynamics of typing and used it to evaluate our approach. Experimental results show that hubness-aware techniques outperform state-of-the-art time-series classifiers.
PL
W referacie przedstawiono system statycznej i dynamicznej weryfikacji autentyczności podpisu odręcznego, składanego piórem biometrycznym, wyposażonym w 2 akcelerometry, 2 żyroskopy i 3 czujniki ścisku, na rezystancyjnej powierzchni dotykowej, łączącym się bezprzewodowo z urządzeniami komputerowymi. We wstępie przedstawiono architekturę sieciową wielomodalnego systemu biometrii. Przedstawiono warstwę sprzętową systemu weryfikacji autentyczności podpisu, przyjętą metodykę weryfikacji oraz wyniki oceny miar FRR i FAR.
EN
The static and dynamic signature verification method employing a biometric pen equipped with 2 accelerometers, 2 gyroscopes and 3 pressure sensors, used with resistive surface, connecting wireless with computerized devices, has been presented in the paper. In the introduction the network architecture of the multimodal biometric system has been described. The software of the signature verification system and the utilized methodology of verification have been presented along with the results of FRR and FAR measures assessment.
PL
W artykule przedstawiony został system do rozpoznawania komend głosowych zbudowany w oparciu o 32-bitowy mikrokontroler rodziny ARM7. Zadaniem systemu jest rozpoznanie komendy w oparciu o zadany słownik komend, a następnie wysterowanie odpowiedniego wyjścia. Wypowiedziana komenda zostaje zamieniona na wektor cech wypracowany w oparciu o analizę cepstralną. Ten wektor cech jest porównywany z wektorami cech komend wzorcowych. Porównywanie wykonywane jest metodą nieliniowej transformacji czasowej (ang. Dynamic Time Warping, DTW), w celu eliminacji problemu różnej szybkości wypowiadanych komend.
EN
The article presents a voice recognition system implemented on a 32-bit microcontroller of ARM7 core. The system recognizes a spoken commend from a prepared dictionary and drives the corresponding output. A spoken command is recorded and then converted into a representative vector of cepstrum features. This vector is compared against feature vectors of the commands from the dictonary. The comparison is carried out by means of Dynamic Time Warping algorithm (DTW) which remedies the problem of different duration of spoken commands.
EN
Dynamic Time Warping is a standard algorithm used for matching time series irrespective of local tempo variations. Its application in the context of Query-by-Humming interface to multimedia databases requires providing the transposition independence, which involves some additional, sometimes computa- tionally expensive processing and may not guarantee the success, e.g., in the presence of a pitch trend or accidental key changes. The method of tune following, proposed in this paper, enables solving the pitch alignment problem in an adaptive way inspired by the human ability of ignoring typical errors occurring in sung melodies. The experimental validation performed on the database containing 4431 queries and over 5000 templates confirmed the enhancement introduced by the proposed algorithm in terms of the global recognition rate.
13
Content available remote Wyszukiwanie podciągu w ciągu z zastosowaniem obiektów CRL
PL
Celem niniejszej pracy jest zaprezentowanie możliwości zastosowania mapowanych na elementy proceduralne Transact SQL klas obiektowych CLR tworzonych na platformie .NET w złożonych algorytmach przetwarzania. Przedstawione zostały podstawy teoretyczne algorytmów dopasowania łańcuchów dla alfabetów skończonych. Dla wprowadzonych alfabetów nieskończonych rozwiązania te nie mogą być w sposób prosty zmodyfikowane, dlatego zaproponowany został algorytm DTW (Dynamic Time Warping), który został oprogramowany z zastosowaniem reguł mapowania do obiektów rozszerzenia proceduralnego SQL. Przedstawiono elementy praktycznej realizacji praktycznej oraz dokonano omówienia wyników eksperymentu numerycznego dopasowującego gesty.
EN
The purpose of this work is to present the possibility to use mapped to the procedural elements Transact SQL CLR object classes that are created on the NET platform in a complex processing algorithms. There are presented theoretical algorithms for matching chains for finite symbol set alphabets. For introduced infinite symbol set alphabets solutions may not be easily modified, so it was proposed the algorithm DTW (Dynamic Time Warping), which was programmed using the mapping rules for procedural extension to SQL. There where shown elements of the practical implementation and the experimental results of matching gestures were discuss.
EN
Traditional use of dynamic time warping for signature verification consists of forming some dissimilarity measure between the signature in question and a set of "template signatures". In this paper, we propose to replace this set with the hidden signature and use it to calculate the normalized errors of signature under verification. The approach was tested on the MCYT database, using both genuine signatures and skilled forgeries. Moreover, we present the real-world application of the proposed algorithm, namely the complete biometric system for authorizing payment transactions. The authorization is performed directly at a point of sale by the automatic signature verification system based on the hidden signature.
15
Content available State-space averaging for maternal ECG suppression
EN
In this paper a new method of maternal electrocardiogram suppression for fetal component extraction from one-channel maternal abdominal bioelectric signals is proposed. The method performs maternal ECG estimation by application of state-space averaging. The estimated signal is subtracted from the original one and this way suppressed. The method parameters allow us to balance between the precision of maternal ECG suppression and the necessity not to attenuate the fetal QRS complexes. A small database of the maternal abdominal bioelectric signals is used to investigate the developed system for fetal heart rate determination. The final assessment is based on the detection performance index. It is shown that by proper choice of the parameters we can tune the system so that it is more effective than the classical approach based on template subtraction.
EN
Authentication based on handwritten signature is one of the most accepted authentication systems based on biometry. In this paper a method for the automatic verification of on-line handwritten signatures using three similarity measures is described. The proposed approach, is based on extreme values and dynamic features of the signature. In investigations proposed coefficients together with the factor [R2] were connected and new signature recognition quality has been achieved.
EN
Results from preliminary research on recognition of Polish birds' species are presented in the paper. Bird voices were recorded in a highly noised municipal environment. High 96 kHz sampling frequency has been used. As a feature set standard mel-frequency cepstral coefficients (MFCC) and recently proposed human-factor cepstral coefficients (HFCC) parameters were selected. Superior performance of the HFCC features over MFCC ones has been observed. Proper limiting of the maximal frequency during HFCC feature extraction results in increasing accuracy of birds' species recognition. Good initial results are very promising for practical application of the methods described in the paper in monitoring of protected birds' area.
PL
W artykule zaprezentowano wyniki wstępnych badań dotyczących rozpoznawania głosów ptaków. Nagrania cyfrowe ptaków dokonano z częstotliwością próbkowania 96 kHz w zaszumionym środowisku miejskim. Jako cech użyto współczynników mel-cepstralnych (MFCC) oraz ostatnio zaproponowanych współczynników human-cepstralnych (HFCC). Zaobserwowano większą skuteczność rozpoznawania, prowadzonego z użyciem tych drugich. Pokazano, że odpowiednie ograniczenie maksymalnej częstotliwości podczas wyznaczania współczynników HFCC prowadzi do podniesienia efektywności rozpoznawania. Uzyskane obiecujące wyniki są dobrym prognostykiem do planowanego, praktycznego zastosowania opisanych metod do monitorowania ostoi ptaków.
first rewind previous Strona / 1 next fast forward last
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.