Convolution kernels support the modeling of complex syntactic information in machinelearning tasks. However, such models are highly sensitive to the type and size of syntactic structure used. It is therefore an import...
详细信息
A variant of spiking neural P systems was recently investigated by the authors, using astrocytes that have excitatory and inhibitory influence on synapses. In this work, we consider this system in the non-synchronized...
详细信息
Deep Web databases contain more than 90% of pertinent information of the Web. Despite their importance, users don't profit of this treasury. Many deep web services are offering competitive services in term of pric...
详细信息
Privacy-Preserving Computational Geometry (PPCG) is a special Secure Multi-party Computation, which is a hot research in information security. This paper presented a special PPCG problem of secure two-party computing ...
详细信息
Deep Web databases contain more than 90% of pertinent information of the Web. Despite their importance, users don't profit of this treasury. Many deep web services are offering competitive services in term of pric...
详细信息
The paper proposes a scheme to improve the accuracy of tag estimation in the EBT algorithm in RFID system. In the proposed scheme, the mean value of the estimated tag number should be acquired before calculating the o...
详细信息
The paper proposes a scheme to improve the accuracy of tag estimation in the EBT algorithm in RFID system. In the proposed scheme, the mean value of the estimated tag number should be acquired before calculating the optimal prefix. And the circular queue is used to record the average tag number which has been acquired recently. Thought the computer simulation we proposed the optimal length of the queue and make an explanation why the circular queue should be used to store the average tag number. The proposed scheme makes a better system performance compared with the original EBT algorithm.
A flexible transparent modify dipole antenna printed on PET film is presented in this paper. The proposed antenna was designed to operate at 2.4GHz for ISM applications. The impedance characteristic and the radiation ...
详细信息
Message processing and data visualization are key technologies in a V2X system, influencing both real and perceived performance, and usability of a system. V2X safety applications require frequent exchange of position...
详细信息
Message processing and data visualization are key technologies in a V2X system, influencing both real and perceived performance, and usability of a system. V2X safety applications require frequent exchange of position information by means of so called Cooperative Awareness Messages (CAMs). These messages are generated, encoded and sent by all vehicles. Corresponding actions have to be executed on the receiving vehicles. The in-vehicle V2X system can be divided into several components to accomplish these tasks. Our approach is based on a "two-component" system, consisting of a vehicle-integrated V2X communication unit (onboard unit, OBU) and a personal portable device (PPD), such as a smartphone or tablet PC. Subject of this work is the investigation how to distribute the workload and functionality between the two components. Our goal is to find a flexible solution that maximizes the overall performance and reliability of the system. We investigate and compare several message processing approaches and try to combine the strengths of both components. To ensure comparability, tests are carried out on the same hardware platform. As a result, we present our final setup that can handle an up to 60 times higher message rate compared to other investigated solutions.
In this paper, a literature frontier evaluation method based on latent semantic analysis was proposed in terms of collection of front keywords and the surface information of literature. Firstly, to build the collectio...
详细信息
In this paper, a literature frontier evaluation method based on latent semantic analysis was proposed in terms of collection of front keywords and the surface information of literature. Firstly, to build the collection of front keywords, the frontier metric of keyword was studied for evaluating the frontier of keyword. Secondly, the collection of front literatures was achieved according to the built collection of front keywords and the latent semantic space of front literatures was built in terms of the front literatures' surface information such as title, keywords and abstract. Finally, the frontier of new literature was evaluated in terms of the frontier of each front literature, the semantic relevance with each front literature, and the impact factor of the journal which the new literature belonged to. The experimental results show that the collection of front keywords built by proposed frontier metric outperforms the academic hotspots achieved by the existing research platform of academic hotspots, and the proposed method is proved to be reasonable with the positive correlation between the frontier score of new literature and each of the impact factor of journal and the published year of literature.
Accent classification technologies directly influence the performance of automatic speech recognition (ASR) systems. In this paper, we evaluate three accent classification approaches: Phone Recognition followed by Lan...
详细信息
Accent classification technologies directly influence the performance of automatic speech recognition (ASR) systems. In this paper, we evaluate three accent classification approaches: Phone Recognition followed by Language Modeling (PRLM) as a phonotactic approach; accent modeling using Gaussian Mixture Models (GMM) then selecting the most similar model using Maximum Likelihood algorithm that is categorized in acoustic approaches a novel classifier combination method which is proposed to improve the performance of accent classification for several regional accents. In the proposed approach, we use an ensemble method in which each base classifier is a binary classifier that separates an accent from another one. We use the majority vote algorithm to combine the base classifiers. Results for five accents selected from FARSDAT speech database show that the proposed ensemble method outperforms PRLM and GMM-based approaches in the case of Farsi regional accent classifications.
暂无评论