Serwis Infona wykorzystuje pliki cookies (ciasteczka). Są to wartości tekstowe, zapamiętywane przez przeglądarkę na urządzeniu użytkownika. Nasz serwis ma dostęp do tych wartości oraz wykorzystuje je do zapamiętania danych dotyczących użytkownika, takich jak np. ustawienia (typu widok ekranu, wybór języka interfejsu), zapamiętanie zalogowania. Korzystanie z serwisu Infona oznacza zgodę na zapis informacji i ich wykorzystanie dla celów korzytania z serwisu. Więcej informacji można znaleźć w Polityce prywatności oraz Regulaminie serwisu. Zamknięcie tego okienka potwierdza zapoznanie się z informacją o plikach cookies, akceptację polityki prywatności i regulaminu oraz sposobu wykorzystywania plików cookies w serwisie. Możesz zmienić ustawienia obsługi cookies w swojej przeglądarce.
With the proliferation of diversified social network services, understanding how the influence is propagated helps us better understand the network evolution mechanism and the social impact of different kinds of information. Existing models are mostly built on the static network structure. They fail to catch the temporal dynamic property of social network. In this paper, we design a new kind of latent...
Although deep neural networks (DNNs) have achieved great performance gain, the immense computational cost of DNN model training has become a major block to utilize massive speech data for DNN training. Previous research on DNN training acceleration mostly focussed on hardware-based parallelization. In this paper, node pruning and arc restructuring are proposed to explore model redundancy after a novel...
In this work, we used single electrooculogram (EOG) signal to perform automatic sleep scoring. Deep belief network (DBN) and combination of DBN and Hidden Markov Models (HMM) are employed to discriminate sleep stages. Under the leave-one-out protocol, the average accuracy of DBN and DBN-HMM are 77.7% and 83.3% for all sleep stages, respectively. On the other hand, we found the EOG signal not only...
This paper introduces a new back-end classifier for a speech recognition system that is based on artificial life (ALife). The ALife species being used for classification purposes are called wains, which were developed using the Créatúr framework. The speech recognition task used in the evaluation of the new classifier is that of isolated digit recognition. Performance of the proposed back-end classifier...
Video-based coaching systems have seen increasing adoption in various applications including dance, sports, and surgery training. Most existing systems are either passive (for data capture only) or barely active (with limited automated feedback to a trainee). In this paper, we present a video-based skill coaching system for simulation-based surgical training by exploring a newly proposed problem of...
Nowadays, more and more activity recognition algorithms begin to improve recognition performance by combining the RGB and depth information. Although, the space-time volumes (STV) algorithm and the space-time local features algorithm can combine the RGB and depth information effectively, they also have their own defects. Such as they need expensive computational cost and they are not suitable for...
With the development of sensing equipments, data from different modalities is available for gesture recognition. In this paper, we propose a novel multi-modal learning framework. A coupled hidden Markov model (CHMM) is employed to discover the correlation and complementary information across different modalities. In this framework, we use two configurations: one is multi-modal learning and multi-modal...
The actual field survey data from the Rice Department of Thailand's Ministry of Agriculture over a large area wastes a huge amount of resources. To solve this problem, this paper proposes a new approach to estimate rice phenology using SAR images derived from the RADARSAT-2 data. In this work, we divided the rice phenology into five stages, consisting of seedling, tillering, reproductive, ripening,...
This paper presents the experiments on feature selection for emotional speech classification. There are 152 features used in this experiment. The minimum redundancy maximum relevance (mRMR) feature selection is applied as the features selection. The experiments are constructed from two corpora; Interactive Emotional Dyadic Motion Capture (IEMOCAP) and Emotional Tagged Corpus on Lakorn (EMOLA) which...
Vietnamese is a syllable-based tonal language where the tone used in syllable pronunciation carries important information about the meaning. In this paper, we investigate several approaches how to incorporate the tone into an acoustic model. We propose 3 basic strategies: a) a phoneme-based, b) a vowel-based, and c) a rhyme-based one. Each can be modified so that we obtain 15 different schemes that...
Since the Chinese tone is highly related to the variation of instantaneous frequency, it is effective to use time-frequency analysis to identify the Chinese tone. In this manuscript, we find that, in addition to the change of instantaneous frequency, the variation of power, the normalized powers in the first and the second harmonics, the frequency turn, and the information of the previous tone are...
This paper presents a study aimed to assess applicability of artificial neural networks (ANNs) in human activity recognition from simple features derived from accelerometric signals. Secondary goal was to select the most descriptive signal features and sensor locations to be used as inputs to ANNs. Five triaxial accelerometers were attached to human body in the following places: one at back, two at...
Service computing is playing a more and more important role in current Internet activities, especially with the rapid adoption of electric markets, more and more individuals are engaging with commercial services. As the potential profit of service computing is becoming clear, malicious users are ramping up unfair rating attacks that can mislead honest service consumers into transacting with dishonest...
In today's IVHM system, diagnostics and prognostic play a crucial part in the system safety while reducing the operating and maintenance costs. Structural health management is a vital part of IVHM as arguably structures are the biggest and most costly part of the system, thus the failure of the structure could lead to catastrophic results. The failure of a structure is usually caused by cracks or...
This work is related to unsupervised automatic speech segmentation. An experiment was carried out on the Frame Distance Array (FDA) algorithm with a main goal of the algorithm parameter tune-up. The experiment was carried out by applying the algorithm on TIMIT corpus and by using MFCC as the speech signal features. The parameters tuned up in this work are the frame length, the frame increment, the...
Due to the challenges in automatically observing child behaviour in a social interaction, an automatic extraction of high-level features, such as head poses and hand gestures, is difficult and noisy, leading to an inaccurate model. Hence, the feasibility of using easily obtainable low-level optical flow based features is investigated in this work. A comparative study involving high-level features,...
EEG signal is one of the most important signals for diagnosing some diseases. EEG is always recorded with an amount of noise, the more noise is recorded the less quality is the EEG signal. The included noise can represent the quality of the recorded EEG signal, this paper proposes a signal quality assessment method for EEG signal. The method generates an automated measure to detect the noise level...
People who have lost their walking and moving ability need to use a wheelchair. In cases of losing complete control of the upper and lower limbs, intelligent solutions are required to ensure the autonomy and independence of those patients. The intelligent application must be designed carefully to use the available self-controlled electrical and physical activity of the patient's body like sound, Electromyogram...
Automatic sign language recognition plays an important role in communications for sign language users. Most existing sign language recognition systems use single sensor input. However, such systems may fail to recognize hand gestures correctly due to occluded regions of hand gestures. In this work, we propose a novel system for real-time recognition of the digits in American Sign Language (ASL) [1]...
Human activity recognition (HAR) is a fundamental task in smart homes. In these environments residents' data are collected via unobtrusive sensors, and human activities are inferred using machine learning mechanisms out of sensors' data. Dynamic graphical models (DGMs) have been a widely used family of machine learning mechanisms for HAR. In DGM-based HAR methods relative temporal information and...
Podaj zakres dat dla filtrowania wyświetlonych wyników. Możesz podać datę początkową, końcową lub obie daty. Daty możesz wpisać ręcznie lub wybrać za pomocą kalendarza.