Comparison of Dengue Predictive Models Developed Using Artificial Neural Network and Discriminant Analysis with Small Dataset

Silitonga, Permatasari; Bustamam, Alhadi; Muradi, Hengki; Mangunwardoyo, Wibowo; Dewi, Beti Ernawati

doi:10.3390/app11030943

Cited by 15 publications

(11 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most frequently employed data pre-processing techniques to overcame the small size problem are liner and nonlinear Principal component analysis (Jalali, Mallipeddi and Lee, 2017;Feng, Zhou and Dong, 2019;Athanasopoulou, Papacharalampopoulos and Stavropoulos, 2020), Discriminant analysis (Abu Zohair, 2019;Li et al, 2019;Silitonga et al, 2021), Data augmentation (Han, Liu and Fan, 2018;Hagos and Kant, 2019;Fong et al, 2020), Virtual sample (Gong et al, 2017;MacAllister, Kohl and Winer, 2020;Zhu et al, 2020), Feature extraction (Kumar et al, 2018;Dai et al, 2020) and Auto-encoder (Feng, Zhou and Dong, 2019;Pei et al, 2021).…”

Section: Resultsmentioning

confidence: 99%

Machine learning on small size samples: A synthetic knowledge synthesis

Kokol

Kokol²,

Zagoranski³

2022

Science Progress

111

View full text Add to dashboard Cite

Machine Learning is an increasingly important technology dealing with the growing complexity of the digitalised world. Despite the fact, that we live in a ‘Big data’ world where, almost ‘everything’ is digitally stored, there are many real-world situations, where researchers are still faced with small data samples. The present bibliometric knowledge synthesis study aims to answer the research question ‘What is the small data problem in machine learning and how it is solved?’ The analysis a positive trend in the number of research publications and substantial growth of the research community, indicating that the research field is reaching maturity. Most productive countries are China, United States and United Kingdom. Despite notable international cooperation, the regional concentration of research literature production in economically more developed countries was observed. Thematic analysis identified four research themes. The themes are concerned with to dimension reduction in complex big data analysis, data augmentation techniques in deep learning, data mining and statistical learning on small datasets.

show abstract

Section: Resultsmentioning

confidence: 99%

Machine learning on small size samples: A synthetic knowledge synthesis

Kokol

Kokol²,

Zagoranski³

2022

Science Progress

111

View full text Add to dashboard Cite

show abstract

“…Hope in order to achieve more effective result, to get better model performance can combine the models. Other than that, we hope to improve the BiLSTM Chatbot with make modifications to the model architecturethat will result in better accuracy [28], [29]. We will also increase the amount of data analysed, aiming to encourage researchers to propose methods that produce better, more efficient results [30].…”

Section: Resultsmentioning

confidence: 99%

Measuring the accuracy of LSTM and BiLSTM models in the application of artificial intelligence by applying chatbot programme

Anki

Bustamam²

2021

IJEECS

Self Cite

View full text Add to dashboard Cite

Python programme contains a question and answer system that derived from data sets that have used and implemented the chatbot in this modern era. where the data collected is in the form of corpuses containing extensive metadata-rich fictional conversations derived from extracted film scripts, commonly called cornell movie dialogue corpus. The various models have been used chatbots in python programmes, and LSTM and BiLSTM models were specifically used in this study. Where the form of accuracy will be reported as a result of the implementation of LSTM and BiLSTM models in the chatbot programme. The programme performance will be influenced by the data from the model selection, because the level of accuracy is determined by the target programme being taken. So this is the main factor that determines which model to choose. Based on considerations required for choosing the programme model, in the end the LSTM and the BiLSTM models are chosen and will be applied to the programme. Based on the LSTM and BiLSTM chatbot programmes that have been tested, it can be concluded that the best parameters come from a pair of BiLSTM chatbots using the BiLTSM model with an average accuracy value of 0.995217.

show abstract

“…The backpropagation ANN prediction model is composed of one input layer, one hidden layer and one output layer. The number of hidden layers and quantity of neurons are determined through the training process until the prediction accuracy cannot be further improved [43]. However, one hidden layer is commonly used for simple predictions [43].…”

Section: Ann Prediction Modelmentioning

confidence: 99%

“…The number of hidden layers and quantity of neurons are determined through the training process until the prediction accuracy cannot be further improved [43]. However, one hidden layer is commonly used for simple predictions [43]. The quantity of neurons of input and output layers is equal to the number of input and output variables, respectively [44].…”

Section: Ann Prediction Modelmentioning

confidence: 99%

Study on Accuracy Metrics for Evaluating the Predictions of Damage Locations in Deep Piles Using Artificial Neural Networks with Acoustic Emission Data

Jierula

Wang

et al. 2021

Applied Sciences

View full text Add to dashboard Cite

Accuracy metrics have been widely used for the evaluation of predictions in machine learning. However, the selection of an appropriate accuracy metric for the evaluation of a specific prediction has not yet been specified. In this study, seven of the most used accuracy metrics in machine learning were summarized, and both their advantages and disadvantages were studied. To achieve this, the acoustic emission data of damage locations were collected from a pile hit test. A backpropagation artificial neural network prediction model for damage locations was trained with acoustic emission data using six different training algorithms, and the prediction accuracies of six algorithms were evaluated using seven different accuracy metrics. Test results showed that the training algorithm of “TRAINGLM” exhibited the best performance for predicting damage locations in deep piles. Subsequently, the artificial neural networks were trained using three different datasets collected from three acoustic emission sensor groups, and the prediction accuracies of three models were evaluated with the seven different accuracy metrics. The test results showed that the dataset collected from the pile body-installed sensors group exhibited the highest accuracy for predicting damage locations in deep piles. Subsequently, the correlations between the seven accuracy metrics and the sensitivity of each accuracy metrics were discussed based on the analysis results. Eventually, a novel selection method for an appropriate accuracy metric to evaluate the accuracy of specific predictions was proposed. This novel method is useful to select an appropriate accuracy metric for wide predictions, especially in the engineering field.

show abstract

Comparison of Dengue Predictive Models Developed Using Artificial Neural Network and Discriminant Analysis with Small Dataset

Cited by 15 publications

References 31 publications

Machine learning on small size samples: A synthetic knowledge synthesis

Machine learning on small size samples: A synthetic knowledge synthesis

Measuring the accuracy of LSTM and BiLSTM models in the application of artificial intelligence by applying chatbot programme

Study on Accuracy Metrics for Evaluating the Predictions of Damage Locations in Deep Piles Using Artificial Neural Networks with Acoustic Emission Data

Contact Info

Product

Resources

About