Time-series analysis with smoothed Convolutional Neural Network

Wibawa, Aji Prasetya; Utama, Agung Bella Putra; Elmunsyah, Hakkun; Pujianto, Utomo; Dwiyanto, Felix Andika; Hernandez, Leonel

doi:10.1186/s40537-022-00599-y

Cited by 60 publications

(29 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Multivariate forecasting can be used to improve the thoroughness of the experiment and attain the best results since more data sources can improve accuracy. Recently, hybrid models ([ 42 , 43 , 44 ]) were used in time series analysis. For improved outcomes, these models typically incorporate machine learning techniques such as ANN (Artificial Neural Network) and statistical models including ARIMA.…”

Section: Discussionmentioning

confidence: 99%

Time-Series Analysis and Healthcare Implications of COVID-19 Pandemic in Saudi Arabia

et al. 2022

View full text Add to dashboard Cite

The first case of coronavirus disease 2019 (COVID-19) in Saudi Arabia was reported on 2 March 2020. Since then, it has progressed rapidly and the number of cases has grown exponentially, reaching 788,294 cases on 22 June 2022. Accurately analyzing and predicting the spread of new COVID-19 cases is critical to develop a framework for universal pandemic preparedness as well as mitigating the disease’s spread. To this end, the main aim of this paper is first to analyze the historical data of the disease gathered from 2 March 2020 to 20 June 2022 and second to use the collected data for forecasting the trajectory of COVID-19 in order to construct robust and accurate models. To the best of our knowledge, this study is the first that analyzes the outbreak of COVID-19 in Saudi Arabia for a long period (more than two years). To achieve this study aim, two techniques from the data analytics field, namely the auto-regressive integrated moving average (ARIMA) statistical technique and Prophet Facebook machine learning technique were investigated for predicting daily new infections, recoveries and deaths. Based on forecasting performance metrics, both models were found to be accurate and robust in forecasting the time series of COVID-19 in Saudi Arabia for the considered period (the coefficient of determination for example was in all cases more than 0.96) with a small superiority of the ARIMA model in terms of the forecasting ability and of Prophet in terms of simplicity and a few hyper-parameters. The findings of this study have yielded a realistic picture of the disease direction and provide useful insights for decision makers so as to be prepared for the future evolution of the pandemic. In addition, the results of this study have shown positive healthcare implications of the Saudi experience in fighting the disease and the relative efficiency of the taken measures.

show abstract

Section: Discussionmentioning

confidence: 99%

Time-Series Analysis and Healthcare Implications of COVID-19 Pandemic in Saudi Arabia

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Then after that, it can compute the value of the cell gates, which was obtained by combining the values of the forgate gate and the input gate. The output gate and hidden layer values could then be obtained in (7) to (9).…”

Section:  Classificationmentioning

confidence: 99%

“…Deep Learning is a generic sort of learning that can handle issues in all domains, including categorization [7]; it has been defined as such. The Long Short-Term Memory (LSTM) technique [8] and the Convolution Neural Network (CNN) algorithm [9] can be employed for this categorization within this deep learning system. In the mode of deep learning with several levels (layers), the layers are the input layer, the hidden layer, and the output layer [10].…”

Section: Introductionmentioning

confidence: 99%

Comparing LSTM and CNN Methods in Case Study on Public Discussion about Covid-19 in Twitter

Kurniawan¹,

Romadhoni²,

Zahrona³

et al. 2022

IJACSA

View full text Add to dashboard Cite

This study compares two Deep Learning model methods, which include the Long Short-Term Memory (LSTM) method and the Convolution Neural Network (CNN) method. The aim of the comparison is to discover the performance of two different fundamental deep learning approaches which are based on convolutional theory (CNN) and deal with the vanishing gradient problem (LSTM). The purpose of this study is to compare the accuracy of the two methods using a dataset of 4169 obtained by crawling social media using the Twitter API. The Tweets data we've obtained are based on a specific hashtag keyword, namely "covid-19 pandemic". This study attempts to assess the sentiment of all tweets about the Covid-19 viral epidemic to determine whether tweets about Covid-19 contain positive or negative thoughts. Before classification, the Preprocessing and Word Embedding steps are completed, and this study has determined that the epoch used is 20 and the hidden layer is 64. Following the classification process, this study concludes that the two methods are appropriate for classifying public conversation sentences against Covid-19. According to this study, the LSTM method is superior, with an accuracy of 83.3%, a precision of 85.6%, a recall of 90.6%, and an f1-score of 88.5%. While the CNN method achieved an accuracy of 81%, precision of 71.7%, recall of 72%, and f1-score of 72%.

show abstract

“…Penelitian berkaitan dengan Time Series atau data berkala oleh Aji Prasetya dkk (2022) [10] tentang " Time Series Analysis With Smoothed Convulutional Neural Network" dengan menguji optimalisasi performa dari penggunaan algoritma Smoothed CNN dengan memperoleh hasil perbandingan yang lebih baik dalam pengujiannya dengan algoritma Multilayer Perceptron (MLP), Long Short Term Memory (LSTM), dan Convulutional Neural Network (CNN) itu sendiri dengan Mean Square Error (MSE) senilai 0,026.…”

Section: Tinjauan Literaturunclassified

Aplikasi Cerdas Berbasis Website Prediksi Harga Emas dengan Implementasi Algoritma Smoothing Time Series Forecasting

Husaini

Hermansyah

Purwayoga

et al. 2022

dsi

View full text Add to dashboard Cite

Investasi emas merupakan hal yang umum dilakukan oleh masyarakat pada saat ini. Harga emas adalah salah satu hal penting yang menjadi fokus utama dalam melakukan investasi emas yang perlu akurasi ketepatan prediksi baik dalam kurun waktu minggu, hari ataupun tahun sehingga mampu memudahkan untuk menggunakan prediksi tersebut dalam berinvestasi baik untuk membeli atau menjual emas tersebut. Aplikasi berbasis web dengan implementasi algoritma time series forecasting ini dibangun untuk memudahkan dalam prediksi harga emas dengan menggunakan metode pemulusan moving average simple exponential smoothing hingga holt’s exponential dan holt’s winter’s exponential smoothing. Metode penelitian yang digunakan pada rancang bangun aplikasi berbasis web ini menggunakan metode prototype dari pengumpulan atau analisa kebutuhan sistem, membangun prototyping, mengkodekan sistem, evaluasi sistem, pengujian sistem hingga penggunaan sistem. Implementasi menggunakan algoritma pemulusan time-series forecasting yaitu menggunakan dataset yang diambil dari application programming interface (API) https://metalpriceapi.com dengan jumlah data harga emas yang digunakan sejumlah 872 data yang dilakukan pengujian akurasi menggunakan mean absolute percentage error (MAPE) untuk menguji akurasi data aktual dan prediksi dari ketiga algoritma tersebut yaitu dengan menghasilkan 5,517 % untuk metode simple exponential smoothing, 4,93 % pada metode holt’s exponential smoothing, dan 2,78 % untuk holt’s winter’s exponential smoothing. Penggunaan algoritma holt’s-winter’s menghasilkan akurasi yang lebih baik dari kedua algoritma sebelumnya dengan persentase akurasi yang baik berdasarkan pengujian akurasi mean absolute percentage error dengan nilai pengujian kurang dari 5 %.

show abstract

Time-series analysis with smoothed Convolutional Neural Network

Cited by 60 publications

References 39 publications

Time-Series Analysis and Healthcare Implications of COVID-19 Pandemic in Saudi Arabia

Time-Series Analysis and Healthcare Implications of COVID-19 Pandemic in Saudi Arabia

Comparing LSTM and CNN Methods in Case Study on Public Discussion about Covid-19 in Twitter

Aplikasi Cerdas Berbasis Website Prediksi Harga Emas dengan Implementasi Algoritma Smoothing Time Series Forecasting

Contact Info

Product

Resources

About