Abstract: The invention discloses an energy-efficient sample selection method based on sample complexity, which performs sample selection on the raw data sets through two stages of inter-class sampling and intra-class sampling, the object is to select representative samples from large-scale data sets, thereby reducing the number of samples used for model training and achieving the object of lightweight training. Compared with the prior art, the invention has the following advantages: the invention proposes an energy-efficient sample selection method based on complexity, selects representative samples from large-scale datasets for efficient model training, and proves that sample complexity and model training strategies have a very important impact on the efficient training of deep neural networks.

Abstract: A layout method of large-flux algae control wells based on a sluice-pump hub area includes: defining positions of a sluice-pump hub and a river diversion channel as a sluice-pump hub area, arranging at least two sets of pumping station units at the water outlet end of the river diversion channel, using a water flow model to guide streamline and flow velocity distribution of water flow in the river diversion channel, and determining whether it is necessary to adopt rectification measures based on water flow streamline and flow velocity distribution; and obtaining hydraulic characteristic values of the pumping station units, determining whether the currently arranged algae control wells and the adopted rectifying measures simultaneously meet the algae control requirements and subsequent running requirements of the pumping station units based on the hydraulic characteristic values.