Using deep learning to improve the capabilities of high-resolution satellite images has emerged recently as an important topic in automatic classification. Deep networks track hierarchical high-level features to identify objects; however, enhancing the classification accuracy from low-level features is often disregarded. We therefore proposed a two-stream deep-learning neural network strategy, ...

Today, e-commerce has occupied a large volume of economic exchanges. It is known as one of the most effective business practices. Predicted trust which means trusting an anonymous user is important in online communities. In this paper, the trust was predicted by combining two methods of multiplex network and community detection. In modeling the network in terms of a multiplex network, the relat...

telegram is now considered as one of the most famous platform online social networks among media university students. nowadays, the immense popularity of social networking websites such as telegram has created new opportunities for english learners. accordingly, the present study aims to investigate whether telegram would be an effective and easy learning tool of vocabulary for iranian female e...

An investigation of cascaded and parallel deep neural networks for speech synthesis is conducted. In these systems, suprasegmental linguistic features (syllable-level and above) are processed separately from segmental features (phone-level and below). The suprasegmental component of the networks learns compact distributed representations of high-level linguistic units without any segmental infl...

microgrid presents an efficient and novel solution for integrating many new energy generating resources with traditional distribution networks. having an appropriate protective scheme is a fundamental challenge in achieving microgrid plans. it is proven that traditional protective plans are not efficient for protecting microgrid, since the network is dynamic and the level of fault current chang...

spending costs in construction of road pavements has turned this subject into one of the significant points in transportation infrastructure of countries. concrete slabs consider as a paving method with ability of reducing the rehabilitation needs. therefore, to manage costs and optimize the thickness of concrete pavements, recognizing the amount of determinative factors’ influence will be requ...

A new method to identify the shots in basketball video based on Dynamic Bayesian Network (DBN) has been presented in this paper. Using the DBN, the semantic gap between low-lever features and high-lever semantic will be resolve. To identify the ball and the basketball hoop, Kalman filter and SURF (Speed up Robust Features) is applied separately. At last the DBN is employed to identify the shot ...

background : major injuries and death in accidents have roots in drowsiness. sleepiness is a main result of insufficient sleep. it is vital to explore drowsiness and its level. there are various sorts of methods in the forms of subjective and objective approaches. the goal of this study was to detect the association of subjective and interpretive drowsiness with facial dynamic changes. methods:...