Predicting Ice Jams With Neural Networks

2002 ◽  
Author(s):  
Darrell D. Massie ◽  
Kathleen D. White ◽  
Steven F. Daly ◽  
Regan McDonald
Keyword(s):  
Neural Network ◽  
Prediction Models ◽  
Function Analysis ◽  
Analytical Description ◽  
Ice Jams ◽  
Variable Threshold ◽  
Ice Jam ◽  
The Neural Network ◽  
Neural Network Prediction ◽  
Neural Network Input

One of the most difficult problems facing hydraulicians is the development of a method that predicts the formation of breakup ice jams. Because of the suddenness with which breakup jams and related flooding occur, prediction methods are desirable to provide early warning and allow rapid, effective ice jam mitigation. Breakup ice jam prediction models are presently limited due to the lack of an analytical description of the complex physical processes, and range from empirical single-variable threshold-type analyses to statistical methods such as logistic regression and discriminant function analysis. In this study, a neural network method is used to predict breakup ice jams at Oil City, PA. Discussion of how the neural network input vector was determined and the methods used to appropriately account for the relatively low occurrence of jams are addressed. The neural network prediction proved to be more accurate than other methods attempted at this site.

Predicting Ice Jams With Discriminant Function Analysis

2002 ◽  
Author(s):  
Kathleen D. White ◽  
Steven F. Daly
Keyword(s):  
Discriminant Function ◽  
Discriminant Function Analysis ◽  
Prediction Models ◽  
Function Analysis ◽  
Quantitative Information ◽  
Prediction Methods ◽  
Deterministic Models ◽  
Ice Jams ◽  
Variable Threshold ◽  
Ice Jam

Breakup ice jam prediction methods are desirable to provide early warning and allow rapid, effective ice jam mitigation due to the suddenness with which breakup jams and related flooding occur. However, prediction models are limited to empirical or stochastic models rather than deterministic models because of the difficulties in using deterministic models to forecast the formation of breakup ice jams. Existing ice jam prediction methods range from empirical single-variable threshold-type analyses to statistical methods such as logistic regression and discriminant function analysis. Empirical methods are highly site-specific and tend to over predict jam occurrence. In addition, existing models do not provide quantitative information regarding the risk of errors in prediction, which limits their usefulness in emergency situations. In this paper, existing methods are reviewed and a three-step process to predict breakup ice jams is proposed.

Two Types of Neural Network Prediction Models and Time Complexity

2014 ◽  
Vol 548-549 ◽  
pp. 985-989
Author(s):  
Ji Min Zhang ◽  
Liang Zhu ◽  
Subhash Rekheja
Keyword(s):  
Neural Network ◽  
Time Complexity ◽  
Prediction Models ◽  
Lateral Acceleration ◽  
Neural Network Models ◽  
Pass Filter ◽  
Low Pass Filter ◽  
The Neural Network ◽  
Neural Network Prediction ◽  
Network Prediction

The linear adaptive neural network and RBF neural network, according to the measured low-pass filter lateral acceleration signal, was used to establish the reference lateral acceleration applied for the input of tilting train control system. This paper presents the two types of neural network models and prediction algorithms, and studies the time complexity of the two types of network algorithms. The results show that time complexity of the neural network prediction is closely related to its parameters, the neural network structure also can lead to the difference in their calculation time, and RBF prediction neural network spends the minimum time.

Location Selection of Public Transit Transfer Hubs Based on Gray NN Model Improved by GA

2013 ◽  
Vol 660 ◽  
pp. 174-178
Author(s):  
Min An Tang ◽  
Xiao Ming Wang ◽  
Shuang Yuan ◽  
Zhen Rong Sun
Keyword(s):  
Neural Network ◽  
Traffic Flow ◽  
Public Transit ◽  
Small Sample ◽  
Location Selection ◽  
Lanzhou City ◽  
Gray System Theory ◽  
The Neural Network ◽  
Public Traffic ◽  
Neural Network Prediction

The public traffic flow has the gray characteristics of “small sample and poor information”, thereby a forecast method for transfer flow based on the gray soft computing is proposed. This method utilizes the gray system theory to establish gray neural network prediction model, aiming to improve performance of the neural network as well as the accuracy of the system’s prediction by using genetic algorithm. The results show that the optimized model can more accurately predict the traffic flow, providing a more effective way of location selection for public transit transfer hubs. Finally, take the planning of public transit transfer hubs in Lanzhou City as an example to carry out empirical analysis and evaluation for the transfer hubs using this method

scholarly journals Stock Market Prediction Using Artificial Neural Networks

2012 ◽  
Vol 6-7 ◽  
pp. 1055-1060 ◽  
Author(s):  
Yang Bing ◽  
Jian Kun Hao ◽  
Si Chang Zhang
Keyword(s):  
Neural Network ◽  
Prediction Models ◽  
Learning Algorithm ◽  
Stock Exchange ◽  
Back Propagation ◽  
Composite Index ◽  
Network Models ◽  
Back Propagation Neural Network ◽  
Neural Network Models ◽  
The Neural Network

In this study we apply back propagation Neural Network models to predict the daily Shanghai Stock Exchange Composite Index. The learning algorithm and gradient search technique are constructed in the models. We evaluate the prediction models and conclude that the Shanghai Stock Exchange Composite Index is predictable in the short term. Empirical study shows that the Neural Network models is successfully applied to predict the daily highest, lowest, and closing value of the Shanghai Stock Exchange Composite Index, but it can not predict the return rate of the Shanghai Stock Exchange Composite Index in short terms.

scholarly journals UTILIZING SITE CHARACTERISTICS IN NEURAL NETWORK MODELLING OF PERCENTAGE COST-TIME OVERRUN OF BUILDING PROJECTS

2017 ◽  
Vol 8 (1) ◽  
pp. 1-15
Author(s):  
A. O. Ujene ◽  
A. A. Umoh
Keyword(s):  
Neural Network ◽  
Cost Overrun ◽  
Construction Costs ◽  
Network Modelling ◽  
Building Projects ◽  
The Neural Network ◽  
Site Characteristics ◽  
Neural Network Prediction ◽  
The Cost ◽  
Prediction Approach

This study evaluated the site characteristics influencing the time and cost delivery of building projects, determined the range of percentage cost and time overrun and developed a neural network model for predicting the percentage cost and time overrun using the site characteristics of building projects. The study evaluated twelve site characteristics and two performance indicators obtained from records of construction costs, contract documents, and valuation reports of 126 purposively sampled building projects spread across several cities in Nigeria. Analyses were with descriptive and artificial neural network. It was concluded that with fairly favourable site characteristics, cost overrun range reached 77.95% with a mean variation of 44.36%, while time overrun range reached 51.23% with a mean variation of 26.77%. It was found that the accuracy performance levels of 91.93% and 91.43% for the cost and time overrun predictions respectively were very high for the optimum models. Building projects have eight significant site characteristics which can be used to reliably predict the percentage overrun, among which the ground water level, level of available infrastructure and labour proximity around the site are the most important predictors of cost and time overrun. The study recommended that project owners, consultants, contractors and other stakeholders should always use the eight identified site characteristics in predicting percentage cost and time overrun, with more priority on the first three characteristics. The study also recommended the neural network prediction approach due to its prediction accuracy.

ANN-Based Wheat Chlorophyll Density Estimation Using Canopy Hyperspectral Vegetation Indices

2012 ◽  
Vol 500 ◽  
pp. 243-249
Author(s):  
Da Cheng Wang ◽  
Luo Rui Sen ◽  
Ji Hua Wang ◽  
Cun Jun Li ◽  
Dong Yan Zhang ◽  
...  
Keyword(s):  
Neural Network ◽  
Statistical Method ◽  
Prediction Models ◽  
Vegetation Indices ◽  
Remote Sensing Data ◽  
Leaf Chlorophyll ◽  
The Neural Network ◽  
Spectral Vegetation Indices ◽  
Artificial Neural Network Ann ◽  
Traditional Statistical Method

Canopy leaf Chlorophyll Density is a key index for evaluating crop potential photosynthetic efficiency and nutritional stress. Leaf Chlorophyll Density estimate using canopy hyperspectral vegetation indices provides a rapid and non-destructive method to evaluate yield predictions. A systematic comparison of two approaches to estimate Chlorophyll Density using 6 spectral vegetation indices (VIs) was presented in this study. In this study, the traditional statistical method based on power regression analyses was compared to the emerging computationally powerful techniques based on artificial neural network (ANN). The regression models of TCARI 、SAVI 、MSAVI and RDVIgreen were found to be more suitable for predicting Chlorophyll Density when only traditional statistical method was used especially TCARI and RDVI. ANN method was more appropriate to develop prediction models. The comparisons between these two methods were based on analysis of the statistic parameters. Results obtained using Root Mean Square Error (RMSE) for ANNs were significantly lower than the traditional method. From this analysis it is concluded that the neural network is more robust to train and estimate crop Chlorophyll Density from remote sensing data.

Prediction of Bending Beam Rheometer Test Outputs Using Artificial Neural Networks

2019 ◽  
Vol 821 ◽  
pp. 500-505
Author(s):  
Mohammad Fuad Aljarrah ◽  
Mohammad Ali Khasawneh ◽  
Aslam Ali Al-Omari ◽  
Mohammad Emad Alshorman
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Prediction Models ◽  
Time Interval ◽  
Testing Time ◽  
Bending Beam Rheometer ◽  
The Neural Network ◽  
Creep Stiffness ◽  
Artificial Neural

The major objective of this study is to investigate the possibility of using Artificial Neural Networks in creating prediction models capable of estimating Bending Beam Rheometer outputs; namely creep stiffness, and m-value based on test temperature, modifier content; in our case waste vegetable oil, and testing time interval. A feedforward backpropagation neural network with Bayesian Regulation training algorithm and an SSE performance function was implemented. It was found that the neural network model shows high predictive powers with training and testing performance of 99.8% and 99.2% respectively. Plots between laboratory obtained values and neural network predicted outputs were also considered, and a strong correlation between the two methods was concluded. Therefore, it was reasonable to state that using neural networks to build prediction models in order to find BBR test values is justified.

scholarly journals Axle Temperature Monitoring and Neural Network Prediction Analysis for High-Speed Train under Operation

Symmetry ◽  
2020 ◽  
Vol 12 (10) ◽  
pp. 1662
Author(s):  
Wei Hao ◽  
Feng Liu
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
High Speed ◽  
Prediction Method ◽  
High Speed Train ◽  
The Neural Network ◽  
Neural Network Prediction ◽  
Network Prediction ◽  
Trained Neural Network

Predicting the axle temperature states of the high-speed train under operation in advance and evaluating working states of axle bearings is important for improving the safety of train operation and reducing accident risks. The method of monitoring the axle temperature of a train under operation, combined with the neural network prediction method, was applied. A total of 36 sensors were arranged at key positions such as the axle bearings of the train gearbox and the driving end of the traction motor. The positions of the sensors were symmetrical. Axle temperature measurements over 11 days with more than 38,000 km were obtained. The law of the change of the axle temperature in each section was obtained in different environments. The resultant data from the previous 10 days were used to train the neural network model, and a total of 800 samples were randomly selected from eight typical locations for the prediction of axle temperature over the following 3 min. In addition, the results predicted by the neural network method and the GM (1,1) method were compared. The results show that the predicted temperature of the trained neural network model is in good agreement with the experimental temperature, with higher precision than that of the GM (1,1) method, indicating that the proposed method is sufficiently accurate and can be a reliable tool for predicting axle temperature.

Sign in / Sign up

Export Citation Format

Share Document