Comparing Bitcoin's Prediction Model Using GRU, RNN, and LSTM by Hyperparameter Optimization Grid Search and Random Search

Buslim, Nurhayati; Rahmatullah, Imam Lutfi; Setyawan, Bayu; Alamsyah, A

doi:10.1109/citsm52892.2021.9588947

Cited by 21 publications

(9 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed model is compared by integrating different optimization algorithms such as the grid search and the random search. 27 The random selection of parameters in the random search approach results in high variance affecting the precision and recall of the model. It also suffers when handling high-dimensional data.…”

Section: Comparative Resultsmentioning

confidence: 99%

“…The average precision and recall value of a total of three users in three rounds is computed and the results are presented in Table 4. The proposed model is compared by integrating different optimization algorithms such as the grid search and the random search 27 . The random selection of parameters in the random search approach results in high variance affecting the precision and recall of the model.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Personalized ontology and deep training tree‐based optimal gated recurrent unit‐recurrent neural network for prediction of students' behavior

Fernandez

Ramana²,

Shabana³

et al. 2022

Concurrency and Computation

View full text Add to dashboard Cite

Summary Digital libraries are now widely used by students all around the world due to the hassle‐free services it offers in the form of digitized study materials, ebooks, multimedia content and so forth. However, to increase user satisfaction and allegiance, a personalized digital library needs to be deployed to offer customized services to the users. To accomplish this objective, this article presents a novel scheme to design personalized digital libraries via the usage of the Protégé editor and machine learning techniques. The Protégé 4.3 tool is used to generate the digital library ontologies and identify the interrelated concepts. Domain knowledge acquisition, ontology organization, ontology elaboration, ensuring the consistency of the information, and ontology validation. The gated recurrent unit‐recurrent neural network (GRU‐RNN) with a deep training tree (DTT) is used to predict the different user behavior styles such as cognitive behavior, learning speed behavior, sedentary behavior, and aggressive behavior. The DTT is mainly incorporated to overcome the vanishing gradient issue associated with the GRU‐RNN and used in the place of gradient‐based optimization. A black widow optimization approach is employed to update the weights of the GRU‐RNN network in order to increase its accuracy. The efficiency of the proposed methodology is analyzed by using different performance metrics such as F‐score, accuracy, loss, precision, and recall scores. The results show that the personalized digital library created can be efficient in terms of usability.

show abstract

Section: Comparative Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Personalized ontology and deep training tree‐based optimal gated recurrent unit‐recurrent neural network for prediction of students' behavior

Fernandez

Ramana²,

Shabana³

et al. 2022

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…The essence of the GSA is the enumeration method, which is costly in terms of time spent when the objective function is more complex [ 34 ]. Although the RSA no longer tests all values within a parameter range, randomly selected sample points in the search range may ignore optimal values [ 35 ]. The BOA is one of the most popular methods for tuning hyperparameters in deep learning models [ 36 ].…”

Section: Methodsmentioning

confidence: 99%

Evaluation of Rice Degree of Milling Based on Bayesian Optimization and Multi-Scale Residual Model

Chen

Wang

2022

Foods

View full text Add to dashboard Cite

Traditional machine learning-based methods for the detection of rice degree of milling (DOM) that are not comprehensive in feature extraction and have low recognition rates fail to meet the demand for fast, non-destructive, and accurate detection. This paper presents a digital image processing technology combined with deep learning to implement the classification of DOM of rice. An improved multi-scale information fusion model of the InceptionResNet–Bayesian optimization algorithm (IRBOA) was constructed based on the Inception-v3 structure and residual network (ResNet) model. It enables to automatically extract more comprehensive features of rice and determine the DOM of rice. Additionally, the important hyperparameters in the model were tuned by the BOA to optimize the recognition rate of rice DOM. The results show the hyperparameters optimized using the BOA are those that would not be chosen in manual tuning. The classification precision of the IRBOA model reached 99.22%, 94.92%, and 96.55% for well-milled, reasonably well-milled, and substandard rice, respectively, with an average accuracy of no less than 96.90%. This model improved 7.41% over the traditional machine learning model and at least 1.35% over the fashionable CNN model with strong generalization performance. This method effectively completes rapid, non-destructive, and accurate intelligent detection of rice DOM, which can supply a reliable and accurate technical mean for rice processing enterprises to guide the rice processing process.

show abstract

“…This method aims to find the parameter combinations that will make the model perform best by systematically trying all possible combinations within a given set of hyperparameters. Especially in complex models, choosing the right hyperparameters can greatly affect the performance of the model (Buslim et al, 2021). In this study, this method was preferred to provide the best hyperparameter settings for the GRU model.…”

Section: Long and Short Term Memory (Lstm)mentioning

confidence: 99%

Comparative Analysis of Deep Learning Models for Silver Price Prediction: CNN, LSTM, GRU and Hybrid Approach

GÜR

2024

Akdeniz Üniversitesi İktisadi Ve İdari Bilimler Fakültesi Dergisi

View full text Add to dashboard Cite

In this study, the performance of different deep learning algorithms to predict silver prices was evaluated. It was focused on the use of deep learning models such as CNN, LSTM, and GRU for the prediction process, as well as a new hybrid model based on combining these models. Each algorithm was trained on historical silver price data and compared its performance in price prediction using this data. This approach aims to achieve more comprehensive and accurate forecasts by combining the strengths of each model. It also makes a unique contribution to the literature in this area by addressing a specialized area such as the silver market, which is often neglected in financial forecasting. The study presents an innovative approach to financial forecasting and analysis methodologies, highlighting the advantages and potential of deep learning models for time-series data processing. The results compare the ability of these algorithms to analyze silver prices based on historical data only and to assess past trends. The study showed that these algorithms exhibit different performances in analyzing historical data. In conclusion, this study compared the performance of different deep learning algorithms for predicting silver prices based on historical data and found that the CNN-LSTM-GRU hybrid model has the potential to make better predictions. These results can provide guidance to researchers working on financial analysis and forecasting.

show abstract

Comparing Bitcoin's Prediction Model Using GRU, RNN, and LSTM by Hyperparameter Optimization Grid Search and Random Search

Cited by 21 publications

References 13 publications

Personalized ontology and deep training tree‐based optimal gated recurrent unit‐recurrent neural network for prediction of students' behavior

Personalized ontology and deep training tree‐based optimal gated recurrent unit‐recurrent neural network for prediction of students' behavior

Evaluation of Rice Degree of Milling Based on Bayesian Optimization and Multi-Scale Residual Model

Comparative Analysis of Deep Learning Models for Silver Price Prediction: CNN, LSTM, GRU and Hybrid Approach

Contact Info

Product

Resources

About