Investigation of Applicability of Impact Factors to Estimate Solar Irradiance: Comparative Analysis Using Machine Learning Algorithms

This study explores investigation of applicability of impact factors to estimate solar irradiance by four machine learning algorithms using climatic elements as comparative analysis: linear regression, support vector machines (SVM), a multi-layer neural network (MLNN), and a long short-term memory (LSTM) neural network. The methods show how actual climate factors impact on solar irradiation, and the possibility of estimating one year local solar irradiance using machine learning methodologies with four different algorithms. This study conducted readily accessible local weather data including temperature, wind velocity and direction, air pressure, the amount of total cloud cover, the amount of middle and low-layer cloud cover, and humidity. The results show that the artificial neural network (ANN) models provided more close information on solar irradiance than the conventional techniques (linear regression and SVM). Between the two ANN models, the LSTM model achieved better performance, improving accuracy by 31.7% compared to the MLNN model. Impact factor analysis also revealed that temperature and the amount of total cloud cover are the dominant factors affecting solar irradiance, and the amount of middle and low-layer cloud cover is also an important factor. The results from this work demonstrate that ANN models, especially ones based on LSTM, can provide accurate information of local solar irradiance using weather data without installing and maintaining on-site solar irradiance sensors.

Download Full-text

ARPEGE cloud cover forecast post-processing with convolutional neural network

10.5194/egusphere-egu2020-18325 ◽

2020 ◽

Author(s):

Florian Dupuy ◽

Olivier Mestre ◽

Léo Pfitzner

Keyword(s):

Neural Network ◽

Machine Learning ◽

Convolutional Neural Network ◽

Random Forests ◽

Cloud Cover ◽

Spatial Information ◽

Weather Prediction ◽

Excellent Result ◽

Machine Learning Algorithms ◽

Post Processing

Cloud cover is a crucial information for many applications such as planning land observation missions from space. However, cloud cover remains a challenging variable to forecast, and Numerical Weather Prediction (NWP) models suffer from significant biases, hence justifying the use of statistical post-processing techniques. In our application, the ground truth is a gridded cloud cover product derived from satellite observations over Europe, and predictors are spatial fields of various variables produced by ARPEGE (M&#233;t&#233;o-France global NWP) at the corresponding lead time.In this study, ARPEGE cloud cover is post-processed using a convolutional neural network (CNN). CNN is the most popular machine learning tool to deal with images. In our case, CNN allows to integrate spatial information contained in NWP outputs. We show that a simple U-Net architecture produces significant improvements over Europe. Compared to the raw ARPEGE forecasts, MAE drops from 25.1 % to 17.8 % and RMSE decreases from 37.0 % to 31.6 %. Considering specific needs for earth observation, special interest was put on forecasts with low cloud cover conditions (< 10 %). For this particular nebulosity class, we show that hit rate jumps from 40.6 to 70.7 (which is the order of magnitude of what can be achieved using classical machine learning algorithms such as random forests) while false alarm decreases from 38.2 to 29.9. This is an excellent result, since improving hit rates by means of random forests usually also results in a slight increase of false alarms.

Download Full-text

Automatic genome segmentation with HMM-ANN hybrid models

10.1101/034579 ◽

2015 ◽

Author(s):

Li Shen

Keyword(s):

Neural Network ◽

Machine Learning ◽

Artificial Neural Network ◽

Markov Model ◽

State Of The Art ◽

Hidden Markov ◽

Machine Learning Algorithms ◽

Ann Models ◽

Artificial Neural Network Ann ◽

Genomic Regions

AbstractWe consider the problem of automatic genome segmentation (AGS) that aims to assign discrete labels to all genomic regions based on multiple ChIP-seq samples. We propose to use a hybrid model that combines a hidden Markov model (HMM) with an artificial neural network (ANN) to overcome the weaknesses of a standard HMM. Our contributions are threefold: first, we benchmark two approaches to generate targets for ANN training on an example dataset; second, we investigate many different ANN models to identify the ones with best predictions on chromatin states; third, we test different hyper-parameters and discuss how they affect the machine learning algorithms’ performance. We find our best performing models to beat two pervious state-of-the-art methods for AGS by large margins.

Download Full-text

Prediction of aircraft estimated time of arrival using machine learning methods

The Aeronautical Journal ◽

10.1017/aer.2021.13 ◽

2021 ◽

pp. 1-15

Author(s):

O. Basturk ◽

C. Cetek

Keyword(s):

Machine Learning ◽

Web Application ◽

Absolute Error ◽

Machine Learning Algorithms ◽

Weather Data ◽

Time Of Arrival ◽

Learning Models ◽

Trajectory Data ◽

Different Sources ◽

Machine Learning Models

ABSTRACT In this study, prediction of aircraft Estimated Time of Arrival (ETA) is proposed using machine learning algorithms. Accurate prediction of ETA is important for management of delay and air traffic flow, runway assignment, gate assignment, collaborative decision making (CDM), coordination of ground personnel and equipment, and optimisation of arrival sequence etc. Machine learning is able to learn from experience and make predictions with weak assumptions or no assumptions at all. In the proposed approach, general flight information, trajectory data and weather data were obtained from different sources in various formats. Raw data were converted to tidy data and inserted into a relational database. To obtain the features for training the machine learning models, the data were explored, cleaned and transformed into convenient features. New features were also derived from the available data. Random forests and deep neural networks were used to train the machine learning models. Both models can predict the ETA with a mean absolute error (MAE) less than 6min after departure, and less than 3min after terminal manoeuvring area (TMA) entrance. Additionally, a web application was developed to dynamically predict the ETA using proposed models.

Download Full-text

Internet financial supervision based on machine learning and improved neural network

Journal of Intelligent & Fuzzy Systems ◽

10.3233/jifs-189555 ◽

2020 ◽

pp. 1-12

Author(s):

Cao Yanli

Keyword(s):

Neural Network ◽

Machine Learning ◽

Credit Risk ◽

Machine Learning Algorithms ◽

Financial Supervision ◽

Loan Pricing ◽

Comprehensive Management ◽

Risk Pricing ◽

Basel Agreement ◽

Relevant Factors

The research on the risk pricing of Internet finance online loans not only enriches the theory and methods of online loan pricing, but also helps to improve the level of online loan risk pricing. In order to improve the efficiency of Internet financial supervision, this article builds an Internet financial supervision system based on machine learning algorithms and improved neural network algorithms. Moreover, on the basis of factor analysis and discretization of loan data, this paper selects the relatively mature Logistic regression model to evaluate the credit risk of the borrower and considers the comprehensive management of credit risk and the matching with income. In addition, according to the relevant provisions of the New Basel Agreement on expected losses and economic capital, starting from the relevant factors, this article combines the credit risk assessment results to obtain relevant factors through regional research and conduct empirical analysis. The research results show that the model constructed in this paper has certain reliability.

Download Full-text

EMOTIONS RECOGNITION IN HUMAN SPEECH USING DEEP NEURAL NETWORKS

Vestnik komp iuternykh i informatsionnykh tekhnologii ◽

10.14489/vkit.2021.01.pp.044-051 ◽

2021 ◽

pp. 44-51

Author(s):

E. Yu. Shchetinin

Keyword(s):

Neural Network ◽

Machine Learning ◽

Neural Networks ◽

Convolutional Neural Network ◽

Recurrent Neural Network ◽

Deep Neural Networks ◽

Learning Algorithms ◽

Machine Learning Algorithms ◽

Audio Recordings ◽

Computer Studies

The recognition of human emotions is one of the most relevant and dynamically developing areas of modern speech technologies, and the recognition of emotions in speech (RER) is the most demanded part of them. In this paper, we propose a computer model of emotion recognition based on an ensemble of bidirectional recurrent neural network with LSTM memory cell and deep convolutional neural network ResNet18. In this paper, computer studies of the RAVDESS database containing emotional speech of a person are carried out. RAVDESS-a data set containing 7356 files. Entries contain the following emotions: 0 – neutral, 1 – calm, 2 – happiness, 3 – sadness, 4 – anger, 5 – fear, 6 – disgust, 7 – surprise. In total, the database contains 16 classes (8 emotions divided into male and female) for a total of 1440 samples (speech only). To train machine learning algorithms and deep neural networks to recognize emotions, existing audio recordings must be pre-processed in such a way as to extract the main characteristic features of certain emotions. This was done using Mel-frequency cepstral coefficients, chroma coefficients, as well as the characteristics of the frequency spectrum of audio recordings. In this paper, computer studies of various models of neural networks for emotion recognition are carried out on the example of the data described above. In addition, machine learning algorithms were used for comparative analysis. Thus, the following models were trained during the experiments: logistic regression (LR), classifier based on the support vector machine (SVM), decision tree (DT), random forest (RF), gradient boosting over trees – XGBoost, convolutional neural network CNN, recurrent neural network RNN (ResNet18), as well as an ensemble of convolutional and recurrent networks Stacked CNN-RNN. The results show that neural networks showed much higher accuracy in recognizing and classifying emotions than the machine learning algorithms used. Of the three neural network models presented, the CNN + BLSTM ensemble showed higher accuracy.

Download Full-text

Detection of Spoofing Attack using Machine Learning based on Multi-Layer Neural Network in Single-Frequency GPS Receivers

Journal of Navigation ◽

10.1017/s0373463317000558 ◽

2017 ◽

Vol 71 (1) ◽

pp. 169-188 ◽

Cited By ~ 12

Author(s):

E. Shafiee ◽

M. R. Mosavi ◽

M. Moazedi

Keyword(s):

Neural Network ◽

Machine Learning ◽

Late Phase ◽

Machine Learning Algorithms ◽

Computational Method ◽

Single Frequency ◽

Detection Accuracy ◽

Gps Receiver ◽

Navigation Data ◽

Spoofing Detection

The importance of the Global Positioning System (GPS) and related electronic systems continues to increase in a range of environmental, engineering and navigation applications. However, civilian GPS signals are vulnerable to Radio Frequency (RF) interference. Spoofing is an intentional intervention that aims to force a GPS receiver to acquire and track invalid navigation data. Analysis of spoofing and authentic signal patterns represents the differences as phase, energy and imaginary components of the signal. In this paper, early-late phase, delta, and signal level as the three main features are extracted from the correlation output of the tracking loop. Using these features, spoofing detection can be performed by exploiting conventional machine learning algorithms such as K-Nearest Neighbourhood (KNN) and naive Bayesian classifier. A Neural Network (NN) as a learning machine is a modern computational method for collecting the required knowledge and predicting the output values in complicated systems. This paper presents a new approach for GPS spoofing detection based on multi-layer NN whose inputs are indices of features. Simulation results on a software GPS receiver showed adequate detection accuracy was obtained from NN with a short detection time.

Download Full-text

A Bayesian neural network predicts the dissolution of compact planetary systems

Proceedings of the National Academy of Sciences ◽

10.1073/pnas.2026053118 ◽

2021 ◽

Vol 118 (40) ◽

pp. e2026053118

Author(s):

Miles Cranmer ◽

Daniel Tamayo ◽

Hanno Rein ◽

Peter Battaglia ◽

Samuel Hadden ◽

...

Keyword(s):

Neural Network ◽

Machine Learning ◽

Time Series ◽

Planetary System ◽

Machine Learning Algorithms ◽

Orbital Elements ◽

Bayesian Neural Network ◽

Inference Model ◽

Link Type ◽

Numerical Integrator

We introduce a Bayesian neural network model that can accurately predict not only if, but also when a compact planetary system with three or more planets will go unstable. Our model, trained directly from short N-body time series of raw orbital elements, is more than two orders of magnitude more accurate at predicting instability times than analytical estimators, while also reducing the bias of existing machine learning algorithms by nearly a factor of three. Despite being trained on compact resonant and near-resonant three-planet configurations, the model demonstrates robust generalization to both nonresonant and higher multiplicity configurations, in the latter case outperforming models fit to that specific set of integrations. The model computes instability estimates up to 105 times faster than a numerical integrator, and unlike previous efforts provides confidence intervals on its predictions. Our inference model is publicly available in the SPOCK (https://github.com/dtamayo/spock) package, with training code open sourced (https://github.com/MilesCranmer/bnn_chaos_model).

Download Full-text

Near-Optimal Sparse Neural Trees for Supervised Learning

10.20944/preprints202105.0117.v2 ◽

2021 ◽

Author(s):

Tanujit Chakraborty

Keyword(s):

Neural Network ◽

Machine Learning ◽

Decision Tree ◽

Classification Tree ◽

Mathematical Formulation ◽

Machine Learning Algorithms ◽

Optimal Decision ◽

Feed Forward ◽

Feed Forward Network ◽

Tree Algorithms

Decision tree algorithms have been among the most popular algorithms for interpretable (transparent) machine learning since the early 1980s. On the other hand, deep learning methods have boosted the capacity of machine learning algorithms and are now being used for non-trivial applications in various applied domains. But training a fully-connected deep feed-forward network by gradient-descent backpropagation is slow and requires arbitrary choices regarding the number of hidden units and layers. In this paper, we propose near-optimal neural regression trees, intending to make it much faster than deep feed-forward networks and for which it is not essential to specify the number of hidden units in the hidden layers of the neural network in advance. The key idea is to construct a decision tree and then simulate the decision tree with a neural network. This work aims to build a mathematical formulation of neural trees and gain the complementary benefits of both sparse optimal decision trees and neural trees. We propose near-optimal sparse neural trees (NSNT) that is shown to be asymptotically consistent and robust in nature. Additionally, the proposed NSNT model obtain a fast rate of convergence which is near-optimal up to some logarithmic factor. We comprehensively benchmark the proposed method on a sample of 80 datasets (40 classification datasets and 40 regression datasets) from the UCI machine learning repository. We establish that the proposed method is likely to outperform the current state-of-the-art methods (random forest, XGBoost, optimal classification tree, and near-optimal nonlinear trees) for the majority of the datasets.

Download Full-text

Deep Convolutional Neural Network Feed Forward and Back Prop a gation (DCNN F BP) Algorithm f or Predicting Heart Disease u sing Internet o f Things

International Journal of Engineering and Advanced Technology - Regular Issue ◽

10.35940/ijeat.a3212.1011121 ◽

2021 ◽

Vol 11 (1) ◽

pp. 283-287

Author(s):

Saranya N ◽

◽

Kavi Priya S ◽

Keyword(s):

Neural Network ◽

Machine Learning ◽

Heart Disease ◽

Convolutional Neural Network ◽

Back Propagation ◽

High Volume ◽

Deep Convolutional Neural Network ◽

Machine Learning Algorithms ◽

Batch Size ◽

Feed Forward

In recent years, due to the increasing amounts of data gathered from the medical area, the Internet of Things are majorly developed. But the data gathered are of high volume, velocity, and variety. In the proposed work the heart disease is predicted using wearable devices. To analyze the data efficiently and effectively, Deep Canonical Neural Network Feed-Forward and Back Propagation (DCNN-FBP) algorithm is used. The data are gathered from wearable gadgets and preprocessed by employing normalization. The processed features are analyzed using a deep convolutional neural network. The DCNN-FBP algorithm is exercised by applying forward and backward propagation algorithm. Batch size, epochs, learning rate, activation function, and optimizer are the parameters used in DCNN-FBP. The datasets are taken from the UCI machine learning repository. The performance measures such as accuracy, specificity, sensitivity, and precision are used to validate the performance. From the results, the model attains 89% accuracy. Finally, the outcomes are juxtaposed with the traditional machine learning algorithms to illustrate that the DCNN-FBP model attained higher accuracy.

Download Full-text

Cereal yield forecasting combining satellite drought-based indices, regional climate and weather data using machine learning approaches in Morocco

10.5194/egusphere-egu21-14590 ◽

2021 ◽

Author(s):

El houssaine Bouras ◽

Lionel Jarlan ◽

Salah Er-Raki ◽

Riad Balaghi ◽

Abdelhakim Amazirh ◽

...

Keyword(s):

Machine Learning ◽

Regional Climate ◽

Model Development ◽

Machine Learning Algorithms ◽

Weather Data ◽

Drought Indices ◽

Support Vector ◽

Learning Approaches ◽

Climate Data ◽

Yield Forecasting

Cereals are the main crop in Morocco. Its production exhibits a high inter-annual due to uncertain rainfall and recurrent drought periods. Considering the importance of this resource to the country's economy, it is thus important for decision makers to have reliable forecasts of the annual cereal production in order to pre-empt importation needs. In this study, we assessed the joint use of satellite-based drought indices, weather (precipitation and temperature) and climate data (pseudo-oscillation indices including NAO and the leading modes of sea surface temperature -SST- in the mid-latitude and in the tropical area) to predict cereal yields at the level of the agricultural province using machine learning algorithms (Support Vector Machine -SVM-, Random forest -FR- and eXtreme Gradient Boost -XGBoost-) in addition to Multiple Linear Regression (MLR). Also, we evaluate the models for different lead times along the growing season from January (about 5 months before harvest) to March (2 months before harvest). The results show the combination of data from the different sources outperformed the use of a single dataset; the highest accuracy being obtained when the three data sources were all considered in the model development. In addition, the results show that the models can accurately predict yields in January (5 months before harvesting) with an R&#178; = 0.90 and RMSE about 3.4 Qt.ha-1. &#160;When comparing the model&#8217;s performance, XGBoost represents the best one for predicting yields. Also, considering specific models for each province separately improves the statistical metrics by approximately 10-50% depending on the province with regards to one global model applied to all the provinces. The results of this study pointed out that machine learning is a promising tool for cereal yield forecasting. Also, the proposed methodology can be extended to different crops and different regions for crop yield forecasting.

Download Full-text