Several artificial neural network (ANN) models with a feed-forward, back-propagation network structure and various training algorithms, are developed to forecast daily and monthly river flow discharges in Manwan Reservoir. In order to test the applicability of these models, they are compared with a conventional time series flow prediction model. Results indicate that the ANN models provide better accuracy in forecasting river flow than does the auto-regression time series model. In particular, the scaled conjugate gradient algorithm furnishes the highest correlation coefficient and the smallest root mean square error. This ANN model is finally employed in the advanced water resource project of Yunnan Power Group.
In this paper, we analyze the theory of the Julia set (J set) of Newton's method, construct the Julia sets of Newton's method of function F (z) = ze z w (w ∈ C) through iteration method, and analyze the attracting region of the two fixed points 0 and ∞ when w are different values. Consequently, we draw the following conclusions: (1) When the judge conditions for the iterative algorithm are changed to |N(z n ) − z n | ≤ EOF, the properties of the figures in our experiments are contrary to the conclusions in (Wegner and Peter son, Fractal Creations, pp. 168-231, 1991); (2) The attracting regions of the fixed points 0 and ∞ for w = 2n (n = 0, ±2, ±4, . . .) are symmetrical about x-axis and y-axis; select the main argument to be in [−π, π), for arbitrary w = α (α ∈ C), the attracting regions of the fixed points 0 and ∞ are symmetrical about the x-axis;(3) The attracting regions of the two fixed points 0 and ∞ of J set for w = ±η have rotational symmetry of η times; (4) If w = −4.7, k = 0.8, then the attracting regions of different magnifications display a startling similarity, J set holds infinite self-similar structures; (5) When w is a complex number, because the selection of main argument θ z in the negative x-axis is not continuous, the fault and rupture of the attracting regions of the two fixed points 0 and ∞ appear only in the negative x-axis.
Forecasting reservoir inflow is important to hydropower reservoir management and scheduling. An Adaptive-Network-based Fuzzy Inference System (ANFIS) is successfully developed to forecast the long-term discharges in Manwan Hydropower. Using the long-term observations of discharges of monthly river flow discharges during 1953-2003, different types of membership functions and antecedent input flows associated with ANFIS model are tested. When compared to the ANN model, the ANFIS model has shown a significant forecast improvement. The training and validation results show that the ANFIS model is an effective algorithm to forecast the long-term discharges in Manwan Hydropower. The ANFIS model is finally employed in the advanced water resource project of Yunnan Power Group (http://202.118.74.192:7001/YNProject/index.jsp).
The skins of most mature apple fruits are incompletely red and also include green and pale yellow color, which increases the difficulty of fruit detection by machine vision. A detection method based on color and shape features is proposed for this kind of apple fruits. Simple linear iterative clustering (SLIC) is adapted to segment images taken in orchards into super-pixel blocks. The color feature extracted from blocks is used to determine candidate regions, which can filter a large proportion of non-fruit blocks and improve detection precision. Next, the histogram of oriented gradient (HOG) is adopted to describe the shape of fruits, which is applied to detect fruits in candidate regions and locate the position of fruits further. The proposed method was tested by images taken under different illuminations. The average values of recall, precision, and F 1 reach 89.80%, 95.12%, and 92.38% respectively. The performance of detecting fruits covered at different levels is also tested. The values of the recall are all more than 85%, which indicates that proposed method can detect a great part of covered fruits. Compared with pedestrian detection method and faster region-based convolutional neural network (RCNN), the proposed method has the best performance and higher than faster RCNN slightly. However, the proposed method is not robust to noise and its elapsed time of one image is 1.94 s and less than faster RCNN.
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.