scholarly journals Short range SW monsoon rainfall forecasting over India using neural networks

2022 ◽  
Vol 53 (2) ◽  
pp. 225-232

Feedforward Neural Networks are used for daily precipitation forecast using several test stations all over India. The six year European Centre of Medium Range Weather Forecasting (ECMWF) data is used with the training set consisting of the four year data from 1985-1988 and validation set consisting of the data from 1989-1990. Neural networks are used to develop a concurrent relationship between precipitation and other atmospheric variables. No attempt is made to select optimal variables for this study and the inputs are chosen to be same as the ones obtained earlier at National Center for Medium Range Weather Forecasting (NCMRWF) in developing a linear regression model. Neural networks are found to yield results which are atleast as good as linear regression and in several cases yield 10 - 20 % improvement. This is encouraging since the variable selection has so far been optimized for linear regression.

2021 ◽  
Vol 8 ◽  
Yaoling Wang ◽  
Ruiyun Wang ◽  
Lijuan Bai ◽  
Yun Liu ◽  
Lihua Liu ◽  

Background: Arterial stiffness was the pathological basis and risk factor of cardiovascular diseases, with chronic inflammation as the core characteristic. We aimed to analyze the association between the arterial stiffness measured by cardio-ankle vascular index (CAVI) and indicators reflecting the inflammation degree, such as count of leukocyte subtypes, platelet, and monocyte-to-lymphocyte ratio (MLR), etc.Methods: The data of inpatients from November 2018 to November 2019 and from December 2019 to September 2020 were continuously collected as the training set (1,089 cases) and the validation set (700 cases), respectively. A retrospective analysis of gender subgroups was performed in the training set. The association between inflammatory indicators and CAVI or arterial stiffness by simple linear regression, multiple linear regression, and logistic regression was analyzed. The effectiveness of the inflammation indicators and the CAVI decision models to identify arterial stiffness by receiver operating curve (ROC) in the training and validation set was evaluated.Results: The effect weights of MLR affecting the CAVI were 12.87% in men. MLR was the highest risk factor for arterial stiffness, with the odds ratio (95% confidence interval) of 8.95 (5.04–184.79) in men after adjusting the covariates. A cutpoint MLR of 0.19 had 70% accuracy for identifying arterial stiffness in all participants. The areas under the ROC curve of the CAVI decision models for arterial stiffness were >0.80 in the training set and validation set.Conclusions: The MLR might be a high-risk factor for arterial stiffness and could be considered as a potential indicator to predict arterial stiffness.

2019 ◽  
Vol 56 (03) ◽  
pp. 32-38
S. S Sonawane ◽  
S. S More ◽  
S. S. Chhajed ◽  
S. J. Kshirsagar ◽  

Two simple, accurate, precise and economical UV spectrophotometric methods, Multiple Linear Regression (MLR) and Principal Component Regression (PCR), were developed for the simultaneous estimation of dapaglifozin (DAPA) and saxagliptin (SAXA) in tablets. Beer’s law was obeyed in the concentration ranges of 10 – 50 μg/mL for DAPA and 5 – 25 μg/mL for SAXA. Synthetic mixtures containing two drugs were prepared to build the training set and validation set in the calibration range using D-optimal mixture design in phosphate buffer pH 6.8 and were recorded at six wavelengths in the range of 230 – 215 nm at intervals of Δλ = 3 nm. Both methods were validated as per ICH guidelines with respect to the accuracy and precision and found suitable for routine analysis of tablets containing DAPA and SAXA without separation.

1995 ◽  
Vol 06 (01) ◽  
pp. 61-78 ◽  

Training set parallelism and network based parallelism are two popular paradigms for parallelizing a feedforward (artificial) neural network. Training set parallelism is particularly suited to feedforward neural networks with backpropagation learning where the size of the training set is large in relation to the size of the network. This paper analyzes training set parallelism for feedforward neural networks when implemented on a transputer array configured in a pipelined ring topology. Theoretical expressions for the time per epoch (iteration) and optimal size of a processor network are derived when the training set is equally distributed among the processing nodes. These show that the speed up is a function of the number of patterns per processor, communication overhead per epoch and the total number of processors in the topology. Further analysis of how to optimally distribute the training set on a given processor network when the number of patterns in the training set is not an integer multiple of the number of processors, is also carried out. It is shown that optimal allocation of patterns in such cases is a mixed integer programming problem. Using this analysis it is found that equal distribution of training patterns among the processors is not the optimal way to allocate the patterns even when the training set is an integer multiple of the number of processors. Extension of the analysis to processor networks comprising processors of different speeds is also carried out. Experimental results from a T805 transputer array are presented to verify all the theoretical results.

SAADI Bin Ahmad Kamaruddin ◽  
Nor AZURA MD Ghanib ◽  
Choong-Yeun Liong ◽  
Abdul AZIZ Jemain

This paper implements two layer neural networks with different feedforward backpropagation algorithms for better performance of firearm classification us-ing numerical features from the ring image. A total of 747 ring images which are extracted from centre of the firing pin impression have been captured from five different pistols of the Parabellum Vector SPI 9mm model. Then, based on finding from the previous studies, the six best geometric moments numerical fea-tures were extracted from those ring images. The elements of the dataset were further randomly divided into the training set (523 elements), testing set (112 el-ements) and validation set (112 elements) in accordance with the requirement of the supervised learning nature of the backpropagation neural network (BPNN). Empirical results show that a two layer BPNN with a 6-7-5 configura-tion and tansig/tansig transfer functions with ‘trainscg’ training algorithm has produced the best classification result of 98%. The classification result is an improvement compared to the previous studies as well as confirming that the ring image region contains useful information for firearm classification.

1990 ◽  
Vol 2 (2) ◽  
pp. 198-209 ◽  
Marcus Frean

A general method for building and training multilayer perceptrons composed of linear threshold units is proposed. A simple recursive rule is used to build the structure of the network by adding units as they are needed, while a modified perceptron algorithm is used to learn the connection strengths. Convergence to zero errors is guaranteed for any boolean classification on patterns of binary variables. Simulations suggest that this method is efficient in terms of the numbers of units constructed, and the networks it builds can generalize over patterns not in the training set.

2016 ◽  
Vol 7 (4) ◽  
pp. 149-160 ◽  
Oseni Taiwo Amoo ◽  
Bloodless Dzwairo

The growing severe damage and sustained nature of the recent drought in some parts of the globe have resulted in the need to conduct studies relating to rainfall forecasting and effective integrated water resources management. This research examines and analyzes the use and ability of artificial neural networks (ANNs) in forecasting future trends of rainfall indices for Mkomazi Basin, South Africa. The approach used the theory of back propagation neural networks, after which a model was developed to predict the future rainfall occurrence using an environmental fed variable for closing up. Once this was accomplished, the ANNs’ accuracy was compared against a traditional forecasting method called multiple linear regression. The probability of an accurate forecast was calculated using conditional probabilities for the two models. Given the accuracy of the forecast, the benefits of the ANNs as a vital tool for decision makers in mitigating drought related concerns was enunciated. Keywords: artificial neural networks, drought, rainfall case forecast, multiple linear regression. JEL Classification: C53, C45

Alan Zhang

COVID-19 has caused world-wide disturbances and the machine learning community has been finding ways to combat the disease. Applications of neural networks in image processing tasks allow COVID-19 Chest X-ray images to be meaningfully processed. In this study, the V7 Darwin COVID-19 Chest X-ray Dataset is used to train a U-Net based network that performs lung-region segmentation and a convolutional neural network that performs diagnosis on Chest X-ray images. This dataset is larger than most of the datasets used to develop existing COVID-19 related neural networks. The lung segmentation network achieved an accuracy of 0.9697 on the training set and an accuracy of 0.9575, an Intersectionover-union of 0.8666, and a dice coefficient of 0.9273 on the validation set. The diagnosis network achieved an accuracy of 0.9620 on the training set and an accuracy of 0.9666 and AUC of 0.985 on the validation set.

Sign in / Sign up

Export Citation Format

Share Document