scholarly journals Unscented Kalman Filter-Aided Long Short-Term Memory Approach for Wind Nowcasting

Aerospace ◽  
2021 ◽  
Vol 8 (9) ◽  
pp. 236
Author(s):  
Junghyun Kim ◽  
Kyuman Lee
Keyword(s):  
Machine Learning ◽  
Short Term Memory ◽  
Unscented Kalman Filter ◽  
Aviation Industry ◽  
Learning Models ◽  
Short Term ◽  
Machine Learning Model ◽  
Long Short Term Memory ◽  
Lstm Network ◽  
Machine Learning Models

Obtaining reliable wind information is critical for efficiently managing air traffic and airport operations. Wind forecasting has been considered one of the most challenging tasks in the aviation industry. Recently, with the advent of artificial intelligence, many machine learning techniques have been widely used to address a variety of complex phenomena in wind predictions. In this paper, we propose a hybrid framework that combines a machine learning model with Kalman filtering for a wind nowcasting problem in the aviation industry. More specifically, this study has three objectives as follows: (1) compare the performance of the machine learning models (i.e., Gaussian process, multi-layer perceptron, and long short-term memory (LSTM) network) to identify the most appropriate model for wind predictions, (2) combine the machine learning model selected in step (1) with an unscented Kalman filter (UKF) to improve the fidelity of the model, and (3) perform Monte Carlo simulations to quantify uncertainties arising from the modeling process. Results show that short-term time-series wind datasets are best predicted by the LSTM network compared to the other machine learning models and the UKF-aided LSTM (UKF-LSTM) approach outperforms the LSTM network only, especially when long-term wind forecasting needs to be considered.

scholarly journals Prediction of Head Movement in 360-Degree Videos Using Attention Model

Sensors ◽  
2021 ◽  
Vol 21 (11) ◽  
pp. 3678
Author(s):  
Dongwon Lee ◽  
Minji Choi ◽  
Joohyun Lee
Keyword(s):  
Machine Learning ◽  
Short Term Memory ◽  
Moving Average ◽  
The Other ◽  
Learning Models ◽  
Short Term ◽  
Term Memory ◽  
Attention Model ◽  
Long Short Term Memory ◽  
Machine Learning Models

In this paper, we propose a prediction algorithm, the combination of Long Short-Term Memory (LSTM) and attention model, based on machine learning models to predict the vision coordinates when watching 360-degree videos in a Virtual Reality (VR) or Augmented Reality (AR) system. Predicting the vision coordinates while video streaming is important when the network condition is degraded. However, the traditional prediction models such as Moving Average (MA) and Autoregression Moving Average (ARMA) are linear so they cannot consider the nonlinear relationship. Therefore, machine learning models based on deep learning are recently used for nonlinear predictions. We use the Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) neural network methods, originated in Recurrent Neural Networks (RNN), and predict the head position in the 360-degree videos. Therefore, we adopt the attention model to LSTM to make more accurate results. We also compare the performance of the proposed model with the other machine learning models such as Multi-Layer Perceptron (MLP) and RNN using the root mean squared error (RMSE) of predicted and real coordinates. We demonstrate that our model can predict the vision coordinates more accurately than the other models in various videos.

scholarly journals Sales forecasting using multivariate long short term memory network models

2019 ◽  
Author(s):  
Suleka Helmini ◽  
Nadheesh Jihan ◽  
Malith Jayasinghe ◽  
Srinath Perera
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Short Term Memory ◽  
Learning Models ◽  
Short Term ◽  
Term Memory ◽  
Forecasting Models ◽  
Non Linear ◽  
Long Short Term Memory ◽  
Machine Learning Models

In the retail domain, estimating the sales before actual sales become known plays a key role in maintaining a successful business. This is due to the fact that most crucial decisions are bound to be based on these forecasts. Statistical sales forecasting models like ARIMA (Auto-Regressive Integrated Moving Average), can be identified as one of the most traditional and commonly used forecasting methodologies. Even though these models are capable of producing satisfactory forecasts for linear time series data they are not suitable for analyzing non-linear data. Therefore, machine learning models (such as Random Forest Regression, XGBoost) have been employed frequently as they were able to achieve better results using non-linear data. The recent research shows that deep learning models (e.g. recurrent neural networks) can provide higher accuracy in predictions compared to machine learning models due to their ability to persist information and identify temporal relationships. In this paper, we adopt a special variant of Long Short Term Memory (LSTM) network called LSTM model with peephole connections for sales prediction. We first build our model using historical features for sales forecasting. We compare the results of this initial LSTM model with multiple machine learning models, namely, the Extreme Gradient Boosting model (XGB) and Random Forest Regressor model(RFR). We further improve the prediction accuracy of the initial model by incorporating features that describe the future that is known to us in the current moment, an approach that has not been explored in previous state-of-the-art LSTM based forecasting models. The initial LSTM model we develop outperforms the machine learning models achieving 12% - 14% improvement whereas the improved LSTM model achieves 11\% - 13\% improvement compared to the improved machine learning models. Furthermore, we also show that our improved LSTM model can obtain a 20% - 21% improvement compared to the initial LSTM model, achieving significant improvement.

scholarly journals Sales forecasting using multivariate long short term memory network models

2019 ◽  
Author(s):  
Suleka Helmini ◽  
Nadheesh Jihan ◽  
Malith Jayasinghe ◽  
Srinath Perera
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Short Term Memory ◽  
Learning Models ◽  
Short Term ◽  
Term Memory ◽  
Forecasting Models ◽  
Non Linear ◽  
Long Short Term Memory ◽  
Machine Learning Models

In the retail domain, estimating the sales before actual sales become known plays a key role in maintaining a successful business. This is due to the fact that most crucial decisions are bound to be based on these forecasts. Statistical sales forecasting models like ARIMA (Auto-Regressive Integrated Moving Average), can be identified as one of the most traditional and commonly used forecasting methodologies. Even though these models are capable of producing satisfactory forecasts for linear time series data they are not suitable for analyzing non-linear data. Therefore, machine learning models (such as Random Forest Regression, XGBoost) have been employed frequently as they were able to achieve better results using non-linear data. The recent research shows that deep learning models (e.g. recurrent neural networks) can provide higher accuracy in predictions compared to machine learning models due to their ability to persist information and identify temporal relationships. In this paper, we adopt a special variant of Long Short Term Memory (LSTM) network called LSTM model with peephole connections for sales prediction. We first build our model using historical features for sales forecasting. We compare the results of this initial LSTM model with multiple machine learning models, namely, the Extreme Gradient Boosting model (XGB) and Random Forest Regressor model(RFR). We further improve the prediction accuracy of the initial model by incorporating features that describe the future that is known to us in the current moment, an approach that has not been explored in previous state-of-the-art LSTM based forecasting models. The initial LSTM model we develop outperforms the machine learning models achieving 12% - 14% improvement whereas the improved LSTM model achieves 11\% - 13\% improvement compared to the improved machine learning models. Furthermore, we also show that our improved LSTM model can obtain a 20% - 21% improvement compared to the initial LSTM model, achieving significant improvement.

scholarly journals Analysis and Prediction of Unplanned Intensive Care Unit Readmission using Recurrent Neural Networks with Long Short-Term Memory

2018 ◽  
Author(s):  
Yu-Wei Lin ◽  
Yuqian Zhou ◽  
Faraz Faghri ◽  
Michael J. Shaw ◽  
Roy H. Campbell
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Recurrent Neural Networks ◽  
Short Term Memory ◽  
Unplanned Readmission ◽  
Learning Models ◽  
Short Term ◽  
Term Memory ◽  
Long Short Term Memory ◽  
Machine Learning Models

AbstractBackgroundUnplanned readmission of a hospitalized patient is an extremely undesirable outcome as the patient may have been exposed to additional risks. The rates of unplanned readmission are, therefore, regarded as an important performance indicator for the medical quality of a hospital and healthcare system. Identifying high-risk patients likely to suffer from readmission before release benefits both the patients and the medical providers. The emergence of machine learning to detect hidden patterns in complex, multi-dimensional datasets provides unparalleled opportunities to develop efficient discharge decision-making support system for physicians.Methods and FindingsWe used supervised machine learning approaches for ICU readmission prediction. We used machine learning methods on comprehensive, longitudinal clinical data from the MIMIC-III to predict the ICU readmission of patients within 30 days of their discharge. We have utilized recent machine learning techniques such as Recurrent Neural Networks (RNN) with Long Short-Term Memory (LSTM), by this we have been able incorporate the multivariate features of EHRs and capture sudden fluctuations in chart event features (e.g. glucose and heart rate) that are significant in time series with temporal dependencies, which cannot be properly captured by traditional static models, but can be captured by our proposed deep neural network based model. We incorporate multiple types of features including chart events, demographic, and ICD9 embeddings. Our machine learning models identifies ICU readmissions at a higher sensitivity rate (0.742) and an improved Area Under the Curve (0.791) compared with traditional methods. We also illustrate the importance of each portion of the features and different combinations of the models to verify the effectiveness of the proposed model.ConclusionOur manuscript highlights the ability of machine learning models to improve our ICU decision making accuracy, and is a real-world example of precision medicine in hospitals. These data-driven results enable clinicians to make assisted decisions within their patient cohorts. This knowledge could have immediate implications for hospitals by improving the detection of possible readmission. We anticipate that machine learning models will improve patient counseling, hospital administration, allocation of healthcare resources and ultimately individualized clinical care.

scholarly journals Quantum Optical Experiments Modeled by Long Short-Term Memory

Photonics ◽  
2021 ◽  
Vol 8 (12) ◽  
pp. 535
Author(s):  
Thomas Adler ◽  
Manuel Erhard ◽  
Mario Krenn ◽  
Johannes Brandstetter ◽  
Johannes Kofler ◽  
...  
Keyword(s):  
Machine Learning ◽  
Short Term Memory ◽  
Random Search ◽  
High Dimensional ◽  
Learning Models ◽  
Short Term ◽  
Term Memory ◽  
Output State ◽  
Long Short Term Memory ◽  
Machine Learning Models

We demonstrate how machine learning is able to model experiments in quantum physics. Quantum entanglement is a cornerstone for upcoming quantum technologies, such as quantum computation and quantum cryptography. Of particular interest are complex quantum states with more than two particles and a large number of entangled quantum levels. Given such a multiparticle high-dimensional quantum state, it is usually impossible to reconstruct an experimental setup that produces it. To search for interesting experiments, one thus has to randomly create millions of setups on a computer and calculate the respective output states. In this work, we show that machine learning models can provide significant improvement over random search. We demonstrate that a long short-term memory (LSTM) neural network can successfully learn to model quantum experiments by correctly predicting output state characteristics for given setups without the necessity of computing the states themselves. This approach not only allows for faster search, but is also an essential step towards the automated design of multiparticle high-dimensional quantum experiments using generative machine learning models.

scholarly journals Prediction of Corn and Sugar Prices Using Machine Learning, Econometrics, and Ensemble Models

2021 ◽  
Vol 9 (1) ◽  
pp. 31
Author(s):  
Roberto F. Silva ◽  
Bruna L. Barreira ◽  
Carlos E. Cugnasca
Keyword(s):  
Machine Learning ◽  
Short Term Memory ◽  
State Of The Art ◽  
Support Vector ◽  
Short Term ◽  
Corn Prices ◽  
Lower Variation ◽  
Test Sets ◽  
Long Short Term Memory ◽  
Machine Learning Models

This paper explores the use of several state-of-the-art machine learning models for predicting the daily prices of corn and sugar in Brazil in relation to the use of traditional econometrics models. The following models were implemented and compared: ARIMA, SARIMA, support vector regression (SVR), AdaBoost, and long short-term memory networks (LSTM). It was observed that, even though the prices time series for both products differ considerably, the models that presented the best results were obtained by: SVR, an ensemble of the SVR and LSTM models, an ensemble of the AdaBoost and SVR models, and an ensemble of the AdaBoost and LSTM models. The econometrics models presented the worst results for both products for all metrics considered. All models presented better results for predicting corn prices in relation to the sugar prices, which can be related mainly to its lower variation during the training and test sets. The methodology used can be implemented for other products.

scholarly journals Stock Market Predictor using Long short-term Memory (LSTM) Technique

2020 ◽  
Vol 9 (4) ◽  
pp. 393-396
Keyword(s):  
Machine Learning ◽  
Stock Market ◽  
Stock Price ◽  
Short Term Memory ◽  
Learning Model ◽  
Short Term ◽  
Term Memory ◽  
Stock Price Prediction ◽  
Machine Learning Model ◽  
Long Short Term Memory

In the stock market, it is important to have accurate prediction of future behavior of stock price..Because of the great chance of financial loss as well as scoring profits at the same time, it is mandatory to have a secure prediction of the values of the stocks. But when it comes to predicting the value of a stock in future we tend to follow stock market experts but as technology is progressing we may use these technologies rather than following human experts who may be biased many times. Stock price prediction has been interesting area for investors and researchers. This article proposes an approach towards prediction of stock price using machine learning model Long Short Term Memory. This is an ensemble learning method that has been an exceedingly successful model for predicting sequence of numbers and words. Long Short Term Memory is a machine learning model for prediction. This technique is used to forecast the future stock price of a specific stock by using historical data of the stock gathered from Yahoo! Finance.

Detection and Prediction of Spam Emails Using Machine Learning Models

2021 ◽  
pp. 201-218
Author(s):  
Salma P. Z ◽  
Maya Mohan
Keyword(s):  
Machine Learning ◽  
Short Term Memory ◽  
Machine Learning Techniques ◽  
Learning Models ◽  
Financial Loss ◽  
Term Memory ◽  
Learning Techniques ◽  
Important Means ◽  
Long Short Term Memory ◽  
Machine Learning Models

One of today's important means of communication is email. The extensive use of email for communication has led to many problems. Spam emails being the most crucial among them. It is one the major issues in today's internet world. Spam emails contain mostly advertisements and offensive content, which are often sent without the recipient's request and are generally annoying, time consuming, and wasting space on the communication media's resources. It creates inconveniences and financial loss to the recipients. Hence, there is always the need to filter the spam emails and separate them from the legitimate emails. There are a lot of content-based machine learning techniques that have proven to be effective in detecting and filtering spam emails. Due to a large increase in email spamming, the emails are studied and classified as spam or not spam. In this chapter, three machine learning models, Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), and Bidirectional LSTM (BLSTM), are used classify the emails as spam and benign.

scholarly journals Deepfake tweets classification using stacked Bi-LSTM and words embedding

2021 ◽  
Vol 7 ◽  
pp. e745
Author(s):  
Vaibhav Rupapara ◽  
Furqan Rustam ◽  
Aashir Amaar ◽  
Patrick Bernard Washington ◽  
Ernesto Lee ◽  
...  
Keyword(s):  
Deep Learning ◽  
Short Term Memory ◽  
Support Vector ◽  
Learning Models ◽  
Short Term ◽  
Term Memory ◽  
Tree Classifier ◽  
Long Short Term Memory ◽  
Digital Manipulation ◽  
Lstm Network

The spread of altered media in the form of fake videos, audios, and images, has been largely increased over the past few years. Advanced digital manipulation tools and techniques make it easier to generate fake content and post it on social media. In addition, tweets with deep fake content make their way to social platforms. The polarity of such tweets is significant to determine the sentiment of people about deep fakes. This paper presents a deep learning model to predict the polarity of deep fake tweets. For this purpose, a stacked bi-directional long short-term memory (SBi-LSTM) network is proposed to classify the sentiment of deep fake tweets. Several well-known machine learning classifiers are investigated as well such as support vector machine, logistic regression, Gaussian Naive Bayes, extra tree classifier, and AdaBoost classifier. These classifiers are utilized with term frequency-inverse document frequency and a bag of words feature extraction approaches. Besides, the performance of deep learning models is analyzed including long short-term memory network, gated recurrent unit, bi-direction LSTM, and convolutional neural network+LSTM. Experimental results indicate that the proposed SBi-LSTM outperforms both machine and deep learning models and achieves an accuracy of 0.92.

Sign in / Sign up

Export Citation Format

Share Document