Abstract-This letter adopts long short-term memory(LSTM) to predict sea surface temperature(SST), which is the first attempt, to our knowledge, to use recurrent neural network to solve the problem of SST prediction, and to make one week and one month daily prediction. We formulate the SST prediction problem as a time series regression problem. LSTM is a special kind of recurrent neural network, which introduces gate mechanism into vanilla RNN to prevent the vanished or exploding gradient problem. It has strong ability to model the temporal relationship of time series data and can handle the long-term dependency problem well. The proposed network architecture is composed of two kinds of layers: LSTM layer and fullconnected dense layer. LSTM layer is utilized to model the time series relationship. Full-connected layer is utilized to map the output of LSTM layer to a final prediction. We explore the optimal setting of this architecture by experiments and report the accuracy of coastal seas of China to confirm the effectiveness of the proposed method. In addition, we also show its online updated characteristics.
This paper presents wavelet packet decomposition (WPD) and wavelet coefficient residual analysis based methods for hydraulic pump health diagnosis. A real-time pump health diagnosis system has been created on the basis of this method. This pump diagnosis system would analyse a short sequence of pump discharge pressure signals to detect if the pump was operating under a healthy condition or not. If the pump were operating with defective conditions, a further diagnosis would be implemented to identify the possible cause(s) of the defect(s). Based on the results obtained from a series of random laboratory tests by randomly selecting one of the four testing pumps 8 times, the developed WPD-residual analysis based pump diagnosis system was missing only one out of a total 32 diagnoses, which represented a 96.9 per cent accuracy rate in health diagnosis. Out of 23 fault diagnosing tests, 21 returned a correct diagnosis, resulting in a 91.3 per cent accuracy rate. The study also found that the accuracy rate could be further improved by taking available information from more packets to support fault diagnosis. It is worth pointing out that, while this method was tested against a hydraulic pump, it can also be applied to other equipment.
We report several tools for 3DEM structure identification and model-based refinement developed by our research group and implemented in our in-house software package, VolRover. For viral density maps with icosahedral symmetry, we segment the capsid, polymeric and monomeric subunits using segmentation techniques based on symmetry detection and fast marching. For large biomolecules without symmetry information, we use a multi-seeded fast-marching method to segment meaningful substructures. In either case, we subject the resulting segmented subunit to secondary structure detection when the EM resolution is sufficiently high, and rigid-body fitting when the corresponding crystal structure is available. Secondary structure elements are identified by our volume- and boundary-based skeletonization methods as well as a new method, currently in development, based on solving the grassfire flow equation. For rigid-body fitting, we use a translational fast Fourier based scheme. We apply our segmentation, secondary structure elements identification, and rigid-body fitting techniques to the PSB 2011 cryo-EM modeling challenge data, and compare our results to those submitted from other research groups. The comparisons show that our software is capable of segmenting relatively accurate subunits from a viral or protein assembly, and that the high segmentation quality leads in turn to high-quality results of secondary structure elements identification and rigid-body fitting.
As a critical technology in both civil and military fields, specific emitter identification (SEI) can identify signal sources according to their various features. Existing methods on SEI are mostly based on the prior knowledge of emitters, which are powerless in the non-cooperative scenario. In order to realize the unsupervised identification, the mobile SEI method based on fingerprint set construction and feedback classification algorithm is proposed in this paper. The proposed method first divides signal fingerprints into static features and dynamic features, where the former describe the inherent features of emitters, and the latter represent the moving state features of emitters. Then, the feedback classification algorithm composed of dynamic curve fitting and back propagation (BP) neural network is applied in the classification of signals.The dynamic curve accomplishes the first classification and the results with high credibility are used to train the BP neural network which accomplishes the final classification. Simulation results demonstrate that the proposed method can complete the identification of mobile specific emitter sources in the unsupervised state with more than 95% identification rate.INDEX TERMS SEI, curve fitting, signal fingerprint, BP neural network.
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.