scholarly journals Deep Learning-Based Maximum Temperature Forecasting Assisted with Meta-Learning for Hyperparameter Optimization

Atmosphere ◽  
2020 ◽  
Vol 11 (5) ◽  
pp. 487 ◽  
Author(s):  
Trang Thi Kieu Tran ◽  
Taesam Lee ◽  
Ju-Young Shin ◽  
Jong-Suk Kim ◽  
Mohamad Kamruzzaman
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Deep Learning ◽  
Short Term Memory ◽  
Human Life ◽  
Time Series Prediction ◽  
Vital Role ◽  
Maximum Temperature ◽  
Hyperparameter Optimization ◽  
Meta Learning

Time series forecasting of meteorological variables such as daily temperature has recently drawn considerable attention from researchers to address the limitations of traditional forecasting models. However, a middle-range (e.g., 5–20 days) forecasting is an extremely challenging task to get reliable forecasting results from a dynamical weather model. Nevertheless, it is challenging to develop and select an accurate time-series prediction model because it involves training various distinct models to find the best among them. In addition, selecting an optimum topology for the selected models is important too. The accurate forecasting of maximum temperature plays a vital role in human life as well as many sectors such as agriculture and industry. The increase in temperature will deteriorate the highland urban heat, especially in summer, and have a significant influence on people’s health. We applied meta-learning principles to optimize the deep learning network structure for hyperparameter optimization. In particular, the genetic algorithm (GA) for meta-learning was used to select the optimum architecture for the network used. The dataset was used to train and test three different models, namely the artificial neural network (ANN), recurrent neural network (RNN), and long short-term memory (LSTM). Our results demonstrate that the hybrid model of an LSTM network and GA outperforms other models for the long lead time forecasting. Specifically, LSTM forecasts have superiority over RNN and ANN for 15-day-ahead in summer with the root mean square error (RMSE) value of 2.719 (°C).

scholarly journals Deep Learning with Long Short-Term Memory for Time Series Prediction

2019 ◽  
Vol 57 (6) ◽  
pp. 114-119 ◽  
Author(s):  
Yuxiu Hua ◽  
Zhifeng Zhao ◽  
Rongpeng Li ◽  
Xianfu Chen ◽  
Zhiming Liu ◽  
...  
Keyword(s):  
Time Series ◽  
Deep Learning ◽  
Short Term Memory ◽  
Time Series Prediction ◽  
Short Term ◽  
Term Memory ◽  
Long Short Term Memory

scholarly journals Time Series Prediction of Viable Embryo and Automatic Grading in IVF using Deep Learning

2021 ◽  
Vol 15 (1) ◽  
pp. 190-203
Author(s):  
Gargee Vaidya ◽  
Shreya Chandrasekhar ◽  
Ruchi Gajjar ◽  
Nagendra Gajjar ◽  
Deven Patel ◽  
...  
Keyword(s):  
Time Series ◽  
Deep Learning ◽  
Short Term Memory ◽  
Time Series Prediction ◽  
Final Grade ◽  
Healthy Pregnancy ◽  
Automatic Grading ◽  
Multiple Samples ◽  
Viable Embryo

Background: The process of In Vitro Fertilization (IVF) involves collecting multiple samples of mature eggs that are fertilized with sperms in the IVF laboratory. They are eventually graded, and the most viable embryo out of all the samples is selected for transfer in the mother’s womb for a healthy pregnancy. Currently, the process of grading and selecting the healthiest embryo is performed by visual morphology, and manual records are maintained by embryologists. Objectives: Maintaining manual records makes the process very tedious, time-consuming, and error-prone. The absence of a universal grading leads to high subjectivity and low success rate of pregnancy. To improve the chances of pregnancy, multiple embryos are transferred in the womb elevating the risk of multiple pregnancies. In this paper, we propose a deep learning-based method to perform the automatic grading of the embryos using time series prediction with Long Short Term Memory (LSTM) and Convolutional Neural Network (CNN). Methods: CNN extracts the features of the images of embryos, and a sequence of such features is fed to LSTM for time series prediction, which gives the final grade. Results: Our model gave an ideal accuracy of 100% on training and validation. A comparison of obtained results is made with those obtained from a GRU model as well as other pre-trained models. Conclusion: The automated process is robust and eliminates subjectivity. The days-long hard work can now be replaced with our model, which gives the grading within 8 seconds with a GPU.

scholarly journals Multivariate Temporal Convolutional Network: A Deep Neural Networks Approach for Multivariate Time Series Forecasting

Electronics ◽  
2019 ◽  
Vol 8 (8) ◽  
pp. 876 ◽  
Author(s):  
Renzhuo Wan ◽  
Shuping Mei ◽  
Jun Wang ◽  
Min Liu ◽  
Fan Yang
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Prediction Accuracy ◽  
Time Series Data ◽  
Short Term Memory ◽  
Time Series Prediction ◽  
Multivariate Time Series ◽  
Series Data ◽  
Asymmetric Structure ◽  
Convolutional Network

Multivariable time series prediction has been widely studied in power energy, aerology, meteorology, finance, transportation, etc. Traditional modeling methods have complex patterns and are inefficient to capture long-term multivariate dependencies of data for desired forecasting accuracy. To address such concerns, various deep learning models based on Recurrent Neural Network (RNN) and Convolutional Neural Network (CNN) methods are proposed. To improve the prediction accuracy and minimize the multivariate time series data dependence for aperiodic data, in this article, Beijing PM2.5 and ISO-NE Dataset are analyzed by a novel Multivariate Temporal Convolution Network (M-TCN) model. In this model, multi-variable time series prediction is constructed as a sequence-to-sequence scenario for non-periodic datasets. The multichannel residual blocks in parallel with asymmetric structure based on deep convolution neural network is proposed. The results are compared with rich competitive algorithms of long short term memory (LSTM), convolutional LSTM (ConvLSTM), Temporal Convolution Network (TCN) and Multivariate Attention LSTM-FCN (MALSTM-FCN), which indicate significant improvement of prediction accuracy, robust and generalization of our model.

scholarly journals Deep learning convolutional neural network in rainfall–runoff modelling

2020 ◽  
Vol 22 (3) ◽  
pp. 541-561 ◽  
Author(s):  
Song Pham Van ◽  
Hoang Minh Le ◽  
Dat Vi Thanh ◽  
Thanh Duc Dang ◽  
Ho Huu Loc ◽  
...  
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Short Term Memory ◽  
Water Cycle ◽  
Machine Learning Techniques ◽  
Analytical Models ◽  
Rainfall Runoff ◽  
Convolutional Network

Abstract Rainfall–runoff modelling is complicated due to numerous complex interactions and feedback in the water cycle among precipitation and evapotranspiration processes, and also geophysical characteristics. Consequently, the lack of geophysical characteristics such as soil properties leads to difficulties in developing physical and analytical models when traditional statistical methods cannot simulate rainfall–runoff accurately. Machine learning techniques with data-driven methods, which can capture the nonlinear relationship between prediction and predictors, have been rapidly developed in the last decades and have many applications in the field of water resources. This study attempts to develop a novel 1D convolutional neural network (CNN), a deep learning technique, with a ReLU activation function for rainfall–runoff modelling. The modelling paradigm includes applying two convolutional filters in parallel to separate time series, which allows for the fast processing of data and the exploitation of the correlation structure between the multivariate time series. The developed modelling framework is evaluated with measured data at Chau Doc and Can Tho hydro-meteorological stations in the Vietnamese Mekong Delta. The proposed model results are compared with simulations of long short-term memory (LSTM) and traditional models. Both CNN and LSTM have better performance than the traditional models, and the statistical performance of the CNN model is slightly better than the LSTM results. We demonstrate that the convolutional network is suitable for regression-type problems and can effectively learn dependencies in and between the series without the need for a long historical time series, is a time-efficient and easy to implement alternative to recurrent-type networks and tends to outperform linear and recurrent models.

scholarly journals A hybrid deep learning model for air quality time series prediction

2021 ◽  
Vol 22 (3) ◽  
pp. 1611
Author(s):  
Samit Bhanja ◽  
Abhisek Das
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Air Quality ◽  
Input Data ◽  
Short Term Memory ◽  
Time Series Prediction ◽  
Key Factors ◽  
Spatial Features ◽  
And Control ◽  
Learning Architectures

Air quality (mainly PM2.5) forecasting plays an important role in the early detection and control of air pollution. In recent times, numerous deep learning-based models have been proposed to forecast air quality more accurately. The success of these deep learning models heavily depends on the two key factors viz. proper representation of the input data and preservation of temporal order of the input data during the feature’s extraction phase. Here we propose a hybrid deep neural network (HDNN) framework to forecast the PM2.5 by integrating two popular deep learning architectures, viz. Convolutional neural network (CNN) and bidirectional long short-term memory (BDLSTM) network. Here we build a 3D input tensor so that CNN can extract the trends and spatial features more accurately within the input window. Here we also introduce a linking layer between CNN and BDLSTM to maintain the temporal ordering of feature vectors. In the end, our proposed HDNN framework is compared with the state-of-the-art models, and we show that HDNN outruns other models in terms of prediction accuracy.

scholarly journals Prediksi Penjualan Supermarket Menggunakan Pendekatan Deep Learning

2021 ◽  
Vol 7 (1) ◽  
pp. 160
Author(s):  
Marchel Thimoty Tombeng ◽  
Zalfie Ardian
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Time Series ◽  
Deep Learning ◽  
Short Term Memory ◽  
Time Series Model ◽  
Time Machine ◽  
Short Term ◽  
Term Memory ◽  
Long Short Term Memory

Berdasarkan data transaksi tahun 2014 sampai 2016 dari salah satu supermarket yang ada di Taiwan, penulis menghasilkan analisa model prediksi dengan menguji data menggunakan metode Deep Learning. Beberapa faktor yang berpengaruh telah di dipelajari dan berguna untuk input prediksi, antara lain keadaan cuacu, diskon, hari raya, dan lain sebagainya. Motivasi utama dari penelitian yang penulis lakukan adalah menggunakan teknologi yang berhubungan dengan eksplorasi data untuk memprediksikan penjualan dari produk-produk dan waktu berkunjung pelangan dalam industry retail, untuk mencari grup target yang tepat dan korelasi produk yang tinggi. Pada akhirnya penulis menciptakan sistem keputusan produk yang berisi analisa visual dan tindakan saran untuk manajer produk pemasaran serta pemangku kepentingan dalam pemasaran produk. Dengan adanya hasil prediksi ini, diharapkan dapat menbantu manajer atau pemangku kepentingan lainnya untuk dapat memasarkan serta menjual produk secara tepat sehingga dapat menghasilkan keuntungan yang banyak dengan menggunkan analisa prediksi yang kami buat. LSTM merupakan model yang sering dipakai dalam Recursive Neural Network (RNN), dan pada dasarnya berfungsi untuk memecahkan masalah dari Time Series. Model Deep Learning yang penulis gunakan adalah Long Short Term Memory (LSTM), dimana model ini menyediakan analisa dan prediksi dari serangkaian data. Sebagai contoh, pada saat akhir pekan pengunjungnya melonjat, maka time machine learning ini akan menambahkan pengartian dari nilai parameter akhir pekan dan nilai ouputnya memiliki korelasi yang kuat.Kata kunci—Predictions, Time Series, LSTM, RNN, Deep Learning

scholarly journals Prediction of Rice Yield via Stacked LSTM

2020 ◽  
Vol 11 (1) ◽  
pp. 86-95
Author(s):  
Xiangyan Meng ◽  
Muyan Liu ◽  
Qiufeng Wu
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Short Term Memory ◽  
Rice Yield ◽  
Time Series Prediction ◽  
Superior Performance ◽  
Heilongjiang Province ◽  
Short Term ◽  
Term Memory ◽  
Long Short Term Memory

In order to guarantee the rice yield more effectively, the prediction of rice yield should be taken into account. Because the rice yield every year can be seen as a sequence of time series, many methods applied in prediction of time series can be considered. Long Short-Term Memory recurrent neural network (LSTM) is one of the most popular methods of time series prediction. In consideration of its own characteristics and the popularity of deep learning, an improved LSTM architecture called Stacked LSTM which has multiple layers is proposed in this article. It is based on the idea of increasing the depth of LSTM. The comparison among the Stacked LSTM architectures which have different numbers of LSTM layers and other methods including ARIMA, GRU, and ANN has been carried out on the data of rice yield in Heilongjiang Province, China, from 1980 to 2017. The results showed the superior performance of Stacked LSTM and the effectiveness of increasing the depth of LSTM.

Sign in / Sign up

Export Citation Format

Share Document