The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Research on activity recognition provides a wide range of ubiquitous computing applications. Once activities are recognized, computers can use this information to provide people with suitable services. In the past decade, many classification algorithms have been applied to activity recognition. However, most of them were based on the use of inertial measurement sensors, such as tri-axial accelerometers...
Cross-domain learning text classification aims to train an accurate model for a target domain by using labeled text data from a source domain with different but related data distributions. To narrow the data distribution gap between different domains, most of the previous approaches utilize the bag-of-words model to obtain latent features representation of the text. However, this kind of model loses...
In recent years, the IoT application and the biometric-based authorization become popular. This paper proposes a face recognition system with high accuracy rate based on extended Local Binary Pattern, and applies it as an access control system on an IoT device which is always low-cost, low-power and small-footprint. The proposed face recognition system includes three parts, face detection, feature...
Recently, various 3-D talking heads have been applied to computer-aided language learning as a novel mode. However, there is a lack of objective evaluation of learners' perception of the talking head when learning Mandarin as a second language. This study used eye-tracking methodology to evaluate a multimodal 3-D Mandarin pronunciation tutor, in comparison with real human instructor. The pronunciation...
By taking advantage of VC++, this paper has realized one kind of speaker-independent speech recognition system with small vocabulary and isolated words. By adopting the method of pre-emphasis endpoint detection, this system can eliminate effects of low-frequency noise. Moreover, it invokes HTK speech processing toolbox in VC to complete the feature extraction and pattern matching. According to the...
With the development of Internet based services, the requirement of keeping keep their vitality and the user viscosity has become an important challenge. Better understanding of users behaviour is an effective way to improve the services lifecycle management. As such analysis of users experience from web log, questionnaire and some other ways have been attached much importance. From previous studies...
This paper presents a method for voice conversion using deep neural networks (DNNs) trained with multiple source speakers. The proposed DNNs can be used in two ways for different scenarios: 1) in the absence of training data for source speaker, the DNNs can be treated as source-speaker-independent models and perform conversions directly from arbitrary source speakers to certain target speaker; 2)...
This paper presents a new spectral envelope conversion method using deep neural networks (DNNs). The conventional joint density Gaussian mixture model (JDGMM) based spectral conversion methods perform stably and effectively. However, the speech generated by these methods suffer severe quality degradation due to the following two factors: 1) inadequacy of JDGMM in modeling the distribution of spectral...
Properly designed context models can increase the compression gain. In this paper, we propose a new lossless image coding scheme with two proposed algorithms: nonlocal context modeling and adaptive prediction (NCMAP). Since structural self-similarity often exists in natural images, we use the probability to measure the similarity between the powers of prediction errors for the pixels to be coded....
This study analyzed the problems on the “Mechanical Innovation Design” teaching in higher vocational institutions, proposed to reform the teaching materials and teaching methods of Mechanical Innovation Design with CDIO Engineering education initiative. And the reform has been tested in the experimental class. The teaching reform has made some achievements, improved the innovation capability of the...
In our work, a virtual reality-based surgical simulator for the mandibular angle reduction was designed and implemented on CUDA-based platform. High-fidelity visual and haptic feedbacks between the surgical instruments and the bone material are provided to enhance the perception in a realistic virtual surgical environment. Impulse-based dynamics haptic model was employed to simulate the contact forces...
Swimmer tracking in swimming pools is a challenging vision task due to its varying complex background. Most moving object detection methods are developed for static or partial static backgrounds, and thus can not be applied in swimmer detection problems. This work presents an approach combining mean-shift clustering and cascaded boosting learning algorithm for swimmer detection. There are three main...
Epilepsy is one of the most common brain disorders in the world. The spontaneous seizure onset influences the daily life of epilepsy patients. The studies on feature extraction and feature classification from Electroencephalography(EEG) signal in seizure prediction methods have shown great improvement these years. However, the variation issue of EEG signal (being awake, being asleep, severity of epilepsy,...
Professional development of foreign languages teachers rely heavily on cultivating and improving the awareness of reflecting on their own teaching. This paper investigates reflective teaching of secondary school English teachers in the ethnic and remote regions of Guangxi in China. The result shows that few teachers there have much knowledge about reflective teaching and none of them have practiced...
Analysis of noisy data gathered from measurement devices is challenging in the power grid. In this study, an effective noisy data regression approach based on general regression neural networks (GRNN) is employed to deal with the problem for remote terminal units (RTU) in power SCADA systems. Experimental results show the proposed model is able to handle noisy data for practical applications, and...
This paper proposes synchronized robust control for an active gait trainer. We design an active gait trainer, which composes of linkage mechanism and motors, to produce preferred gait traces for people with walking disability. The goal of this work is to simultaneously control the motors to mimic normal gaits. By finding the transfer functions of the mechanism and motors, we design robust controllers...
This paper presents a non-parallel training algorithm for voice conversion based on feature transform Gaussian mixture model (FTGMM), which is a mixture model of joint density space of source speaker and target speaker with explicit feature transform modeling. In FT-GMM, the correlations between the distributions of two speakers in each component of the mixture model are not directly modeled, but...
In this paper, we propose a Gaussian mixture model (GMM) based voice conversion method using explicit feature transform models. A piecewise linear transform with stochastic bias is adopted to present the relationship between the spectral features of source and target speakers. This explicit transformations are integrated into the training of GMM for the joint probability density of source and target...
BP network has a memory function of historical data due to adding local self-feedback on some nodes of it. The improved local self-feedback BP network can solve dynamic mapping and process historical data. The multi-information fusion algorithm can be achieved by using this local self-feedback BP network, which can also be applied to detect the battery power. The embedded microprocessor and the corresponding...
Most visual-based gesture control systems are bound to specific applications. They used predefined postures for users to control devices. Users need to learn and be familiar with those predefined postures to issue a command. This makes it difficult to transfer one gesture control interface into different applications. This study presented a generic framework for the design of a human machine interface...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.