The recent advances of deep learning in both computer vision (CV) and natural language processing (NLP) provide us a new way of understanding semantics, by which we can deal with more challenging tasks such as automatic description generation from natural images. In this challenge, the encoder-decoder framework has achieved promising performance when a convolutional neural network (CNN) is used as image encoder and a recurrent neural network (RNN) as decoder. In this paper, we introduce a sequential guiding network that guides the decoder during word generation. The new model is an extension of the encoder-decoder framework with attention that has an additional guiding long short-term memory (LSTM) and can be trained in an end-to-end manner by using image/descriptions pairs. We validate our approach by conducting extensive experiments on a benchmark dataset, i.e., MS COCO Captions. The proposed model achieves significant improvement comparing to the other state-ofthe-art deep learning models.
This paper aims to improve the model of the hydro-turbine system under the effect of water-hammer for frequency-domain studies. It brings out a novel way to overcome the accuracy limitation linked to the simple first and second-order approximations of the gate-turbine transfer function. The proposed study is based on the detailed model of the hydraulic system considering the effects of water compressibility and pipe elasticity. The improved system is controlled using particle-swarm optimization algorithm, which is shown to be very efficient in controlling the overshoot and stability of the system connected to a single machine single load test system. Step response and load disturbance are simulated. Results from our example prove that covering accurately a frequency range from 0 to over 30Hz is easily made when using this method for frequency-domain simulations of hydropower plant load-frequency control.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.