A Long Short-Term Memory Model for Global Rapid Intensification Prediction

ABSTRACTRapid intensification (RI) is an outstanding source of error in tropical cyclone (TC) intensity predictions. RI is generally defined as a 24-h increase in TC maximum sustained surface wind speed greater than some threshold, typically 25, 30, or 35 kt (1 kt ≈ 0.51 m s−1). Here, a long short-term memory (LSTM) model for probabilistic RI predictions is developed and evaluated. The variables (features) of the model include storm characteristics (e.g., storm intensity) and environmental variables (e.g., vertical shear) over the previous 48 h. A basin-aware RI prediction model is trained (1981–2009), validated (2010–13), and tested (2014–17) on global data. Models are trained on overlapping 48-h data, which allows multiple training examples for each storm. A challenge is that the data are highly unbalanced in the sense that there are many more non-RI cases than RI cases. To cope with this data imbalance, the synthetic minority-oversampling technique (SMOTE) is used to balance the training data by generating artificial RI cases. Model ensembling is also applied to improve prediction skill further. The model’s Brier skill scores in the Atlantic and eastern North Pacific are higher than those of operational predictions for RI thresholds of 25 and 30 kt and comparable for 35 kt on the independent test data. Composites of the features associated with RI and non-RI situations provide physical insights for how the model discriminates between RI and non-RI cases. Prediction case studies are presented for some recent storms.

Download Full-text

Long Short-Term Memory with Dynamic Skip Connections

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v33i01.33016481 ◽

2019 ◽

Vol 33 ◽

pp. 6481-6488 ◽

Cited By ~ 3

Author(s):

Tao Gui ◽

Qi Zhang ◽

Lujun Zhao ◽

Yaosong Lin ◽

Minlong Peng ◽

...

Keyword(s):

Language Processing ◽

Short Term Memory ◽

Training Data ◽

Sequential Data ◽

Short Term ◽

Term Memory ◽

Transition Functions ◽

Proposed Model ◽

Long Short Term Memory

In recent years, long short-term memory (LSTM) has been successfully used to model sequential data of variable length. However, LSTM can still experience difficulty in capturing long-term dependencies. In this work, we tried to alleviate this problem by introducing a dynamic skip connection, which can learn to directly connect two dependent words. Since there is no dependency information in the training data, we propose a novel reinforcement learning-based method to model the dependency relationship and connect dependent words. The proposed model computes the recurrent transition functions based on the skip connections, which provides a dynamic skipping advantage over RNNs that always tackle entire sentences sequentially. Our experimental results on three natural language processing tasks demonstrate that the proposed method can achieve better performance than existing methods. In the number prediction experiment, the proposed model outperformed LSTM with respect to accuracy by nearly 20%.

Download Full-text

Electric Load Forecasting with Deep Machine Learning

Journal of Computational and Theoretical Nanoscience ◽

10.1166/jctn.2019.8300 ◽

2019 ◽

Vol 16 (8) ◽

pp. 3404-3409

Author(s):

Ala Adin Baha Eldin Mustafa Abdelaziz ◽

Ka Fei Thang ◽

Jacqueline Lukose

Keyword(s):

Mobile Application ◽

Energy Demand ◽

Short Term Memory ◽

Historical Data ◽

Electrical Energy ◽

Training Data ◽

Short Term ◽

Feed Forward Neural Network ◽

Term Memory ◽

Long Short Term Memory

The most commonly used form of energy in houses, factories, buildings and agriculture is the electrical energy, however, in recent years, there has been an increase in electrical energy demand due to technology advancements and rise in population, therefore an appropriated forecasting system must be developed to predict these demands as accurately as possible. For this purpose, five models were selected, they are Bidirectional-Long Short Term Memory (Bi-LSTM), Feed Forward Neural Network (FFNN), Long Short Term Memory (LSTM), Nonlinear Auto Regressive network with eXogenous inputs (NARX) and Multiple Linear Regression (MLR). This paper will demonstrate the development of these selected models using MATLAB and an android mobile application, which is used to visualize and interact with the data. The performance of the selected models was evaluated by performing the Mean Absolute Percent Error (MAPE), the selected historical data used to perform the MAPE was obtained from Toronto, Canada and Tasmania, Australia, where the year 2006 until 2016 was used as training data and the year 2017 was used to test the MAPE of the historical data with the models’ data. It is observed that the NARX model had the least MAPE for both the regions resulting in 1.9% for Toronto, Canada and 2.9% for Tasmania, Australia. Google cloud is used as the IoT (Internet of Things) platform for NARX data model, the 2017 datasets is converted to JavaScript Object Notation (JSON) file using JavaScript programming language, for data visualization and analysis for the android mobile application.

Download Full-text

Implementasi Recurrent Neural Network dalam Memprediksi Kepadatan Restoran Berbasis LSTM

JURNAL MEDIA INFORMATIKA BUDIDARMA ◽

10.30865/mib.v5i2.2916 ◽

2021 ◽

Vol 5 (2) ◽

pp. 524

Author(s):

Annisa Farhah ◽

Anggunmeka Luhur Prasasti ◽

Marisa W Paryasto

Keyword(s):

Neural Network ◽

Recurrent Neural Network ◽

Short Term Memory ◽

Training Data ◽

Accurate Information ◽

Rate Parameter ◽

Short Term ◽

Term Memory ◽

Long Short Term Memory ◽

Modern Era

In this modern era, restaurants are becoming very popular, especially in big cities. However, this can lead to density or queues of visitors at a restaurant, which should be avoided during the current Covid-19 pandemic. So that accurate information that can predict the density of restaurant will be very useful. In predicting the density of restaurants, data processing on the number of visitors obtained from one of the restaurants is carried out using artificial intelligence in the form of LSTM (Long Short Term Memory) RNN (Recurrent Neural Network). The results of the research on Recurrent Neural Network based on LSTM (Long Short Term Memory) at the best learning rate parameter of 0.001 and a maximum epoch of 2000 resulted in an MSE value of 0.00000278 on the training data and 0.0069 on the test data

Download Full-text

Automatic generation of learning outcomes based on long short–term memory artificial neural network1

Journal of Intelligent & Fuzzy Systems ◽

10.3233/jifs-219234 ◽

2021 ◽

pp. 1-13

Author(s):

Joel Suárez-Cansino ◽

Virgilio López-Morales ◽

Julio César Ramos-Fernández

Keyword(s):

Instructional Design ◽

Learning Outcomes ◽

Short Term Memory ◽

Automatic Generation ◽

Training Data ◽

Educational Activity ◽

Short Term ◽

Term Memory ◽

Long Short Term Memory ◽

Artificial Neural

Building a good instructional design requires a sound organization management to program and articulate several tasks based for instance on the time availability, process follow-up, social and educational context. Furthermore, learning outcomes are the basis involving every educational activity. Thus, based on a predefined ontology, including the instructional educative model and its characteristics, we propose the use of a Long Short–Term Memory Artificial Neural Network (LSTM) to organize the structure and automatize the obtention of learning outcomes for a focused instructional design. We present encouraging results in this direction through the use of a LSTM using as the training data, a small learning outcomes set predefined by the user, focused on the characteristics of an educative model previously defined.

Download Full-text

Inter-Sentence Segmentation of YouTube Subtitles Using Long-Short Term Memory (LSTM)

Applied Sciences ◽

10.3390/app9071504 ◽

2019 ◽

Vol 9 (7) ◽

pp. 1504 ◽

Cited By ~ 1

Author(s):

Hye-Jeong Song ◽

Hong-Ki Kim ◽

Jong-Dae Kim ◽

Chan-Young Park ◽

Yu-Seop Kim

Keyword(s):

Online Education ◽

Short Term Memory ◽

Training Data ◽

Short Term ◽

Term Memory ◽

Video Sharing ◽

Video Lectures ◽

Sentence Segmentation ◽

Long Short Term Memory ◽

Voice Data

Recently, with the development of Speech to Text, which converts voice to text, and machine translation, technologies for simultaneously translating the captions of video into other languages have been developed. Using this, YouTube, a video-sharing site, provides captions in many languages. Currently, the automatic caption system extracts voice data when uploading a video and provides a subtitle file converted into text. This method creates subtitles suitable for the running time. However, when extracting subtitles from video using Speech to Text, it is impossible to accurately translate the sentence because all sentences are generated without periods. Since the generated subtitles are separated by time units rather than sentence units, and are translated, it is very difficult to understand the translation result as a whole. In this paper, we propose a method to divide text into sentences and generate period marks to improve the accuracy of automatic translation of English subtitles. For this study, we use the 27,826 sentence subtitles provided by Stanford University’s courses as data. Since this lecture video provides complete sentence caption data, it can be used as training data by transforming the subtitles into general YouTube-like caption data. We build a model with the training data using the LSTM-RNN (Long-Short Term Memory – Recurrent Neural Networks) and predict the position of the period mark, resulting in prediction accuracy of 70.84%. Our research will provide people with more accurate translations of subtitles. In addition, we expect that language barriers in online education will be more easily broken by achieving more accurate translations of numerous video lectures in English.

Download Full-text

Outpatient Text Classification Using Attention-Based Bidirectional LSTM for Robot-Assisted Servicing in Hospital

Information ◽

10.3390/info11020106 ◽

2020 ◽

Vol 11 (2) ◽

pp. 106 ◽

Cited By ~ 4

Author(s):

Che-Wen Chen ◽

Shih-Pang Tseng ◽

Ta-Wen Kuan ◽

Jhing-Fa Wang

Keyword(s):

Text Classification ◽

Short Term Memory ◽

Family Doctor ◽

Training Data ◽

Service Robots ◽

Service Robot ◽

Short Term ◽

Data Set ◽

Term Memory ◽

Long Short Term Memory

In general, patients who are unwell do not know with which outpatient department they should register, and can only get advice after they are diagnosed by a family doctor. This may cause a waste of time and medical resources. In this paper, we propose an attention-based bidirectional long short-term memory (Att-BiLSTM) model for service robots, which has the ability to classify outpatient categories according to textual content. With the outpatient text classification system, users can talk about their situation to a service robot and the robot can tell them which clinic they should register with. In the implementation of the proposed method, dialog text of users in the Taiwan E Hospital were collected as the training data set. Through natural language processing (NLP), the information in the dialog text was extracted, sorted, and converted to train the long-short term memory (LSTM) deep learning model. Experimental results verify the ability of the robot to respond to questions autonomously through acquired casual knowledge.

Download Full-text

Near-Real-Time Forecast of Satellite-Based Soil Moisture Using Long Short-Term Memory with an Adaptive Data Integration Kernel

Journal of Hydrometeorology ◽

10.1175/jhm-d-19-0169.1 ◽

2020 ◽

Vol 21 (3) ◽

pp. 399-413 ◽

Cited By ~ 2

Author(s):

Kuai Fang ◽

Chaopeng Shen

Keyword(s):

Soil Moisture ◽

Data Integration ◽

Real Time ◽

Short Term Memory ◽

Training Data ◽

Random Component ◽

Short Term ◽

Projection Model ◽

Term Memory ◽

Long Short Term Memory

AbstractNowcasts, or near-real-time (NRT) forecasts, of soil moisture based on the Soil Moisture Active and Passive (SMAP) mission could provide substantial value for a range of applications including hazards monitoring and agricultural planning. To provide such a NRT forecast with high fidelity, we enhanced a time series deep learning architecture, long short-term memory (LSTM), with a novel data integration (DI) kernel to assimilate the most recent SMAP observations as soon as they become available. The kernel is adaptive in that it can accommodate irregular observational schedules. Testing over the CONUS, this NRT forecast product showcases predictions with unprecedented accuracy when evaluated against subsequent SMAP retrievals. It showed smaller error than NRT forecasts reported in the literature, especially at longer forecast latency. The comparative advantage was due to LSTM’s structural improvements, as well as its ability to utilize more input variables and more training data. The DI-LSTM was compared to the original LSTM model that runs without data integration, referred to as the projection model here. We found that the DI procedure removed the autocorrelated effects of forcing errors and errors due to processes not represented in the inputs, for example, irrigation and floodplain/lake inundation, as well as mismatches due to unseen forcing conditions. The effects of this purely data-driven DI kernel are discussed for the first time in the geosciences. Furthermore, this work presents an upper-bound estimate for the random component of the SMAP retrieval error.

Download Full-text

Airfoil buffet aerodynamics at plunge and pitch excitation based on long short-term memory neural network prediction

CEAS Aeronautical Journal ◽

10.1007/s13272-021-00550-6 ◽

2021 ◽

Author(s):

R. Zahn ◽

C. Breitsamter

Keyword(s):

Neural Network ◽

Short Term Memory ◽

Training Data ◽

Good Prediction ◽

Short Term ◽

Data Set ◽

Term Memory ◽

Identification Approach ◽

Long Short Term Memory ◽

Transonic Buffet

AbstractIn the present study, a nonlinear system identification approach based on a long short-term memory (LSTM) neural network is applied for the prediction of transonic buffet aerodynamics. The identification approach is applied as a reduced-order modeling (ROM) technique for an efficient computation of time-varying integral quantities such as aerodynamic force and moment coefficients. Therefore, the nonlinear identification procedure as well as the generalization of the ROM are presented. The training data set for the LSTM–ROM is provided by performing forced-motion unsteady Reynolds-averaged Navier–Stokes simulations. Subsequent to the training process, the ROM is applied for the computation of the aerodynamic integral quantities associated with transonic buffet. The performance of the trained ROM is demonstrated by computing the aerodynamic loads of the NACA0012 airfoil investigated at transonic freestream conditions. In contrast to previous studies considering only a pitching excitation, both the pitch and plunge degrees of freedom of the airfoil are individually and simultaneously excited by means of an user-defined training signal. Therefore, strong nonlinear effects are considered for the training of the ROM. By comparing the results with a full-order computational fluid dynamics solution, a good prediction capability of the presented ROM method is indicated. However, compared to the results of previous studies including only the airfoil pitching excitation, a slightly reduced prediction performance is shown.

Download Full-text

Data science approach to stock prices forecasting in Indonesia during Covid-19 using Long Short-Term Memory (LSTM)

Journal Of Big Data ◽

10.1186/s40537-021-00430-0 ◽

2021 ◽

Vol 8 (1) ◽

Author(s):

Widodo Budiharto

Keyword(s):

Stock Prices ◽

Stock Price ◽

Data Science ◽

Short Term Memory ◽

Training Data ◽

Market Process ◽

Short Term ◽

Term Memory ◽

Share Prices ◽

Long Short Term Memory

Abstract Background Stock market process is full of uncertainty; hence stock prices forecasting very important in finance and business. For stockbrokers, understanding trends and supported by prediction software for forecasting is very important for decision making. This paper proposes a data science model for stock prices forecasting in Indonesian exchange based on the statistical computing based on R language and Long Short-Term Memory (LSTM). Findings The first Covid-19 (Coronavirus disease-19) confirmed case in Indonesia is on 2 March 2020. After that, the composite stock price index has plunged 28% since the start of the year and the share prices of cigarette producers and banks in the midst of the corona pandemic reached their lowest value on March 24, 2020. We use the big data from Bank of Central Asia (BCA) and Bank of Mandiri from Indonesia obtained from Yahoo finance. In our experiments, we visualize the data using data science and predict and simulate the important prices called Open, High, Low and Closing (OHLC) with various parameters. Conclusions Based on the experiment, data science is very useful for visualization data and our proposed method using Long Short-Term Memory (LSTM) can be used as predictor in short term data with accuracy 94.57% comes from the short term (1 year) with high epoch in training phase rather than using 3 years training data.

Download Full-text