Precipitation prediction using recurrent neural networks and long short-term memory

Priatna, Mishka Alditya; Djamal, Esmeralda C.

doi:10.12928/telkomnika.v18i5.14887

Cited by 15 publications

(13 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…CNN-LSTM is a deep learning model that combines the CNN architecture with the LSTM layer and is designed to solve sequential prediction problems using spatial input such as images or videos [19], [20]. The LSTM layer could learn the temporal information in the feature [12], while CNN is useful for analyzing image data. The combination of CNN and LSTM was used to analyze images with time-domain information (e.g., songs, and videos) [21].…”

Section: Cnn-lstmmentioning

confidence: 99%

“…The proposed method CNN-LSTM uses the same architecture as the simple LSTM as there are LSTM layers and dropout layers respectively throughout the entire architecture [12]. Talafha et al [13] used the LSTM layer as a decoder on RNN architecture, the proposed method uses the CNN layer and CNN-LSTM layer as a decoder on LSTM architecture [14], [15].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multimodal music emotion recognition in Indonesian songs based on CNN-LSTM, XLNet transformers

Sams

Zahra²

2023

Bulletin EEI

View full text Add to dashboard Cite

Music carries emotional information and allows the listener to feel the emotions contained in the music. This study proposes a multimodal music emotion recognition (MER) system using Indonesian song and lyrics data. In the proposed multimodal system, the audio data will use the mel spectrogram feature, and the lyrics feature will be extracted by going through the tokenizing process from XLNet. Convolutional long short term memory network (CNN-LSTM) performs the audio classification task, while XLNet transformers performs the lyrics classification task. The outputs of the two classification tasks are probability weight and actual prediction with the value of positive, neutral, and negative emotions, which are then combined using the stacking ensemble method. The combined output will be trained into an artificial neural network (ANN) model to get the best probability weight output. The multimodal system achieves the best performance with an accuracy of 80.56%. The results showed that the multimodal method of recognizing musical emotions gave better performance than the single modal method. In addition, hyperparameter tuning can affect the performance of multimodal systems.

show abstract

Section: Cnn-lstmmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Multimodal music emotion recognition in Indonesian songs based on CNN-LSTM, XLNet transformers

Sams

Zahra²

2023

Bulletin EEI

View full text Add to dashboard Cite

show abstract

“…So, Figure 4 is the optimal solution given by the SIRD model. In the future, the implementation of various machine learning, such as long short-term memory [27], Jordan recurrent neural network [28], deep learning [29] and support vector regression [30], may present an attractive research challenge.…”

Section: Long-term Covid-19 Forecastingmentioning

confidence: 99%

The susceptible-infected-recovered-dead model for long-term identification of key epidemiological parameters of COVID-19 in Indonesia

Nanda

Faricha²,

Ulyah

et al. 2022

IJECE

View full text Add to dashboard Cite

<span>The COVID-19 epidemic has spread massively to almost all countries including Indonesia, in just a few months. An important step to overcoming the spread of the COVID-19 is understanding its epidemiology through mathematical modeling intervention. Knowledge of epidemic dynamics patterns is an important part of making timely decisions and preparing hospitals for the outbreak peak. In this study, we developed the susceptible-infected-recovered-dead (SIRD) model, which incorporates the key epidemiological parameters to model and estimate the long-term spread of the COVID-19. The proposed model formulation is data-based analysis using public COVID-19 data from March 2, 2020 to May 15, 2021. Based on numerical analysis, the spread of the pandemic will begin to fade out after November 5, 2021. As a consequence of this virus attack, the cumulative number of infected, recovered, and dead people were estimated at ≈ 3,200,000, ≈ 3,437,000 and ≈ 63,000 people, respectively. Besides, the key epidemiological parameter indicates that the average reproduction number value of COVID-19 in Indonesia is 7.32. The long-term prediction of COVID-19 in Indonesia and its epidemiology can be well described using the SIRD model. The model can be applied in specific regions or cities in understanding the epidemic pattern of COVID-19.</span>

show abstract

“…However, the research is not in any way related to the propagation condition of radio signals in southwestern Nigeria. Neural Networks had been used in predicting metrological parameters for certain regions such as Pakistan [13] and West Java [14]. Applying neural networks to metrological data in Nigeria will help in gaining useful insight.…”

Section: Introductionmentioning

confidence: 99%

Refractive Index Perception and Prediction of Radio wave through Recursive Neural Networks using Meteorological Data Parameters

2022

IJE

View full text Add to dashboard Cite

Radio refractivity is very crucial in the optimal performance of radio systems and is one of the attributes that affect electromagnetic waves in the troposphere. This study presented a comparison of different variants of recurrent neural networks to predict radio refractivity index. The radio refractivity index is predicted based on forty-one years (1980 to 2020) metrological data obtained from the MERRA-2 data re-analysis database. The refractivity index was computed using International Telecommunication Union (ITU) standard. The correlation refractivity index was categorized into strong, weak and no correlation. Rainfall, relative humidity, and air pressure fall in the first category, the temperature falls in the second category while wind speed falls in the last one. The true future and predicted values of the radio refractivity index are close with GRU performing better than the other two models (LSTM and BiLSTM) which proves the accuracy of the proposed model. In conclusion, the proposed model can establish a radio refractivity status of locations at different times of the season, which is of great importance in the effective design, development, and deployment of radio communication systems.

show abstract

Precipitation prediction using recurrent neural networks and long short-term memory

Cited by 15 publications

References 25 publications

Multimodal music emotion recognition in Indonesian songs based on CNN-LSTM, XLNet transformers

Multimodal music emotion recognition in Indonesian songs based on CNN-LSTM, XLNet transformers

The susceptible-infected-recovered-dead model for long-term identification of key epidemiological parameters of COVID-19 in Indonesia

Refractive Index Perception and Prediction of Radio wave through Recursive Neural Networks using Meteorological Data Parameters

Contact Info

Product

Resources

About