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.
Real time traffic crash risk prediction is very important for proactive safety management systems. In this paper, a new model is developed to predict real time traffic crash risk based on some elaborately selected characteristics of traffic flow. Compared with the dominant conventional matched case-control logistic regression model which is based on the assumption that all the traffic crashes share...
Understanding the actions of other people is a key component of social interaction. This paper used an electroencephalography and functional near infrared spectroscopy (EEG-fNIRS) bimodal system to investigate the temporal-spatial features of action intention understanding. We measured brain activation while participants observed three actions: 1) grasping a cup for drinking; 2) grasping a cup for...
As the multivariate extension of empirical mode decomposition, multivariate empirical mode decomposition still suffers the problem of mode mixing. A noise-assisted method has been proposed to reduce mode mixing in multivariate empirical mode decomposition by using the dyadic filter bank property of multivariate empirical mode decomposition when applied to white Gaussian noise. However, the noise-assisted...
Traditional electroencephalographic (EEG)-based steady-state visual evoked potentials (SSVEPs) have been studied for decades. However, classification accuracy is still limited. One reason for this is the existence of false positives when subjects are not focusing on a stimulus or target. In this study, we used fNIRS signals to identify the time at which subject really focusing on the stimulus and...
This paper proposes a speech/music classification system based on i-vector. An analysis of two classification methods, namely cosine distance score (CDS) and support vector machine (SVM) is performed. Two session compensation methods, within-class covariance normalization (WCCN) and linear discriminant analysis (LDA) are also discussed. The performance of proposed systems yields better results compared...
The National Digital Switching System Engineering and Technological R&D Center (NDSC) speech-to-text transcription system for the 2016 multi-genre broadcast challenge is described. Various acoustic models based on deep neural network (DNN), such as hybrid DNN, long short term memory recurrent neural network (LSTM RNN), and time delay neural network (TDNN), are trained. The system also makes use...
A complex dielectric lens in slab shape which is made of electromagnetic-induction materials (cage-shaped granules of conductor materials) and polymethyl methacrylate materials is proposed. Active millimeter wave imaging on focal plane with compound lens which consists of two complex dielectric lenses is investigated. The imaging system is introduced. The parameters of the millimeter wave source,...
Novel compound lens based on the new material of CGC (cage-shaped granule of conductor) was applied to the millimeter wave focal plane imaging. Millimeter wave imaging test circuit and the signal receiving system were designed and constructed. Active millimeter wave focal plane imaging was built, and the sharp image which proved that compound lens was feasible for millimeter wave focal plane imaging...
The focusing device comprising two element focusing lenses made of electromagnetic-induction materials has been used in the active millimeter-wave (AMMW) imaging system. The electromagnetic-induction materials exhibit a refractive index of 1.502 at 35 GHz. The AMMW imaging system presented in this paper consists of an illumination source, a focusing device, a one dimensional receiver and a signal...
In this paper, we describe the THUEE (Department of Electronic Engineering, Tsinghua University) team's method of building language models (LMs) for the OpenKWS 2015 Evaluation held by the National Institute of Standards and Technology (NIST). Due to the very limited in-domain data provided by NIST, it takes most of our time and efforts to make good use of the out-of-domain data. There are three main...
Cost aggregation is the most important step in a local stereo matching algorithm. In this paper, a novel cost aggregation method based on Adaptive Shape Support Window (ASSW) is proposed. There are two main parts: At first we construct a local support skeleton anchored each pixel with four varying arm lengths decided on color similarity, as a result, the support window integral of multiple horizontal...
This paper presents an ASIC design of ultra-low power SAR ADC. To achieve ultra-low power, the proposed ADC operates at ultra-low voltage, deploying a single-ended structure and top plate sampling technique. In order to improve sampling circuit linearity at ultra-low supply voltage, a bootstrapped switch is developed. A non-binary redundant algorithm is applied to correct the inevitable decision errors...
Currently the research in binocular stereo vision area mainly focuses on camera calibration and stereo matching. For camera calibration, to estimate the camera's parameters is of vital very importance for acquiring better three-dimensional positioning reconstruction accuracy. This research investigates camera calibration parameters for a binocular stereo vision system and their effects on system reconstruction...
In this paper, a hierarchical segmentation algorithm using object-oriented strategy is proposed to partition polarimetric SAR data into homogeneous regions efficiently. After the multi-looked and de-speckled processing, the scheme uses a homogeneity definition to achieve an optimal result in local and global through a hierarchical stepwise process. Since PolSAR data contains plenty of polarimetry...
Service semantic annotation is advancing quickly in recent years. However, the task of yielding semantics knowledge becomes a bottleneck of semantic annotation. In this paper, we present a new method for extracting tags from WSDL files and mining semantic relationships between tags. It is foundation of building ontology, which can be used to annotate web service. Core tags of domain are extracted,...
In this paper, the vehicle equipped with electromechanical brake system is taken as the research objective, and the simulation and research on the control strategy of anti-lock brake system is done. Firstly, the force of the wheels is analyzed in cornering with braking, and the control strategy of anti-lock brake system is proposed based on the slip rate and BP neural network PID control. Then, the...
In this paper, the license plate recognition, in the case of the character's local information missing and the license plate partially obstructed, is taken as the research objective. According to the visual identification features that the overall message can be inferred from local information, the characters whose local information missing in the license plate can be deduced from the local evidence...
During the mapping task using high-resolution airborne SAR images, the effective using of DGPS data has important influence on the final accuracy and efficiency of surveying and mapping. This paper analyzed the imaging geometric characteristics of airborne SAR system, and, under the condition of space-constant PRF imaging technique, it put forward to a kind of flight track processing method for radar...
A cross layer scheme of resource allocation is proposed for the delay sensitive service in OFDMA wireless system. The minimal and maximal rates of users are given according to the delay threshold of the service and queue state info at MAC. The minimal rate guarantees the quality of service and fairness of users, whereas the maximal rate increases the resource usage efficiency. With these rate constraints,...
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.