Electricity Consumption Prediction Based on Time Series Data Features Integrate with Long Short-Term Memory Model

Forecasting time-series data are imperative especially when planning is required through modelling using uncertain knowledge of future events. Recurrent neural network models have been applied in the industry and outperform standard artificial neural networks in forecasting, but fail in long term time-series forecasting due to the vanishing gradient problem. This study offers a robust solution that can be implemented for long-term forecasting using a special architecture of recurrent neural network known as Long Short Term Memory (LSTM) model to overcome the vanishing gradient problem. LSTM is specially designed to avoid the long-term dependency problem as their default behavior. Empirical analysis is performed using quantitative forecasting metrics and comparative model performance on the forecasted outputs. An evaluation analysis is performed to validate that the LSTM model provides better forecasted outputs on Standard & Poor’s 500 Index (S&P 500) in terms of error metrics as compared to other forecasting models.

Download Full-text

Deep Network based on Long Short-Term Memory for Time Series Prediction of Microclimate Data inside the Greenhouse

International Journal of Computational Intelligence and Applications ◽

10.1142/s1469026820500133 ◽

2020 ◽

Vol 19 (02) ◽

pp. 2050013

Author(s):

Sawsan Morkos Gharghory

Keyword(s):

Time Series ◽

Relative Humidity ◽

Time Series Data ◽

Short Term Memory ◽

Weather Data ◽

Series Data ◽

Short Term ◽

Term Memory ◽

Long Short Term Memory ◽

Lstm Network

An enhanced architecture of recurrent neural network based on Long Short-Term Memory (LSTM) is suggested in this paper for predicting the microclimate inside the greenhouse through its time series data. The microclimate inside the greenhouse largely affected by the external weather variations and it has a great impact on the greenhouse crops and its production. Therefore, it is a massive importance to predict the microclimate inside greenhouse as a preceding stage for accurate design of a control system that could fulfill the requirements of suitable environment for the plants and crop managing. The LSTM network is trained and tested by the temperatures and relative humidity data measured inside the greenhouse utilizing the mathematical greenhouse model with the outside weather data over 27 days. To evaluate the prediction accuracy of the suggested LSTM network, different measurements, such as Root Mean Square Error (RMSE) and Mean Absolute Error (MAE), are calculated and compared to those of conventional networks in references. The simulation results of LSTM network for forecasting the temperature and relative humidity inside greenhouse outperform over those of the traditional methods. The prediction results of temperature and humidity inside greenhouse in terms of RMSE approximately are 0.16 and 0.62 and in terms of MAE are 0.11 and 0.4, respectively, for both of them.

Download Full-text

Implementation of Long Short-Term Memory and Gated Recurrent Units on Grouped Time-Series Data to Predict Stock Prices Accurately

10.21203/rs.3.rs-1057875/v1 ◽

2021 ◽

Author(s):

Armin Lawi ◽

Hendra Mesra ◽

Supri Amir

Keyword(s):

Time Series ◽

Stock Prices ◽

Stock Price ◽

Time Series Data ◽

Short Term Memory ◽

Series Data ◽

Percentage Error ◽

Short Term ◽

Term Memory ◽

Long Short Term Memory

Abstract Stocks are an attractive investment option since they can generate large profits compared to other businesses. The movement of stock price patterns on the stock market is very dynamic; thus it requires accurate data modeling to forecast stock prices with a low error rate. Forecasting models using Deep Learning are believed to be able to accurately predict stock price movements using time-series data, especially the Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) algorithms. However, several previous implementation studies have not been able to obtain convincing accuracy results. This paper proposes the implementation of the forecasting method by classifying the movement of time-series data on company stock prices into three groups using LSTM and GRU. The accuracy of the built model is evaluated using loss functions of Rooted Mean Squared Error (RMSE) and Mean Absolute Percentage Error (MAPE). The results showed that the performance evaluation of both architectures is accurate in which GRU is always superior to LSTM. The highest validation for GRU was 98.73% (RMSE) and 98.54% (MAPE), while the LSTM validation was 98.26% (RMSE) and 97.71% (MAPE).

Download Full-text

Deep machine learning for detection of acoustic wave reflections

Structural Health Monitoring ◽

10.1177/1475921719881642 ◽

2019 ◽

Vol 19 (5) ◽

pp. 1340-1350

Author(s):

Mulugeta A Haile ◽

Edward Zhu ◽

Christopher Hsu ◽

Natasha Bradley

Keyword(s):

Neural Networks ◽

Time Series ◽

Acoustic Emission ◽

Time Series Data ◽

Short Term Memory ◽

Series Data ◽

Short Term ◽

Term Memory ◽

Propagating Waves ◽

Long Short Term Memory

Acoustic emission signals are information rich and can be used to estimate the size and location of damage in structures. However, many existing algorithms may be deceived by indirectly propagated acoustic emission waves which are modulated by reflection boundaries within the structures. We propose two deep learning models to identify such waves such that existing algorithms for damage detection and localization may be used. The first approach uses long short-term memory recurrent neural networks to learn distinct patterns directly from the time-series data. In the second approach, we transform the time-series data into spectrograms and utilize convolutional neural networks to perform binary classification by leveraging spectro-temporal features. We achieved 80% classification accuracy using long short-term memory and near-perfect accuracy using convolutional neural networks on a dataset of acoustic emission signals generated by the Hsu-Nielsen sources. Both long short-term memory and convolutional neural network models were able to learn general and context-specific features of the direct and reflected acoustic emission waves. Once accurately identified, the indirectly propagating waves are filtered out while the directly propagating waves are used for source location using existing methods.

Download Full-text

The Prediction of Collisions in Connected Vehicle Systems with A Long Short-Term Memory Model

Proceedings of the Human Factors and Ergonomics Society Annual Meeting ◽

10.1177/1071181320641178 ◽

2020 ◽

Vol 64 (1) ◽

pp. 775-779

Author(s):

Rohit Mishra ◽

Yiqi Zhang ◽

Fenglong Ma ◽

Anlong Li

Keyword(s):

Time Series Data ◽

Short Term Memory ◽

Behavioral Experiment ◽

Memory Model ◽

Series Data ◽

Connected Vehicle ◽

Short Term ◽

Term Memory ◽

Vehicle Systems ◽

Long Short Term Memory

The advances in connected vehicle systems (CVS) allow vehicles to communicate with each other and with infrastructures via wireless communication networks. This technology enables vehicles to detect potential hazards on the road, generate warnings, and assist the driver in taking preventive actions. To date, few mathematical models have been developed to predict the collision rates in connected vehicle systems. In this work, a Long Short-Term Memory model (LSTM) using time-series data of human drivers was developed to predict the collision rates in CVS by quantifying warning parameters and hazard scenario features. The model was validated with the driving performance data before and after warnings from thirty-two drivers in a behavioral experiment. The results indicated the LSTM model showed a prediction accuracy of 74% higher than SVM and logistic regression models. The LSTM model showed the potential to help optimize the warning algorithm in the connected vehicle systems to improve driver safety.

Download Full-text

Prediksi Indeks BEI dengan Ensemble Convolutional Neural Network dan Long Short-Term Memory

Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) ◽

10.29207/resti.v5i3.3111 ◽

2021 ◽

Vol 5 (3) ◽

pp. 456-465

Author(s):

Harya Widiputra ◽

Adele Mailangkay ◽

Elliana Gautama

Keyword(s):

Time Series ◽

Stock Market ◽

Time Series Data ◽

Short Term Memory ◽

Series Data ◽

Stock Market Index ◽

Short Term ◽

Term Memory ◽

Market Index ◽

Long Short Term Memory

The Indonesian Stock Exchange (IDX) stock market index is one of the main indicators commonly used as a reference for national economic conditions. The value of the stock market index is often being used by investment companies and individual investors to help making investment decisions. Therefore, the ability to predict the stock market index value is a critical need. In the fields of statistics and probability theory as well as machine learning, various methods have been developed to predict the value of the stock market index with a good accuracy. However, previous research results have found that no one method is superior to other methods. This study proposes an ensemble model based on deep learning architecture, namely Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM), called the CNN-LSTM. To be able to predict financial time series data, CNN-LSTM takes feature from CNN for extraction of important features from time series data, which are then integrated with LSTM feature that is reliable in processing time series data. Results of experiments on the proposed CNN-LSTM model confirm that the hybrid model effectively provides better predictive accuracy than the stand-alone time series data forecasting models, such as CNN and LSTM.

Download Full-text

Neural Probabilistic Forecasting of Symbolic Sequences With Long Short-Term Memory

Journal of Dynamic Systems Measurement and Control ◽

10.1115/1.4039281 ◽

2018 ◽

Vol 140 (8) ◽

Cited By ~ 3

Author(s):

Michael Hauser ◽

Yiwei Fu ◽

Shashi Phoha ◽

Asok Ray

Keyword(s):

Time Series ◽

Time Series Data ◽

Short Term Memory ◽

Probability Distributions ◽

Series Data ◽

Model Parameters ◽

Short Term ◽

Term Memory ◽

Experimental Apparatus ◽

Long Short Term Memory

This paper makes use of long short-term memory (LSTM) neural networks for forecasting probability distributions of time series in terms of discrete symbols that are quantized from real-valued data. The developed framework formulates the forecasting problem into a probabilistic paradigm as hΘ: X × Y → [0, 1] such that ∑y∈YhΘ(x,y)=1, where X is the finite-dimensional state space, Y is the symbol alphabet, and Θ is the set of model parameters. The proposed method is different from standard formulations (e.g., autoregressive moving average (ARMA)) of time series modeling. The main advantage of formulating the problem in the symbolic setting is that density predictions are obtained without any significantly restrictive assumptions (e.g., second-order statistics). The efficacy of the proposed method has been demonstrated by forecasting probability distributions on chaotic time series data collected from a laboratory-scale experimental apparatus. Three neural architectures are compared, each with 100 different combinations of symbol-alphabet size and forecast length, resulting in a comprehensive evaluation of their relative performances.

Download Full-text

Otomatisasi Pengoperasian Alat Elektronik Berdasarkan Hasil Prediksi Algoritma Long Short Term Memory

Journal on Information Technology and Computer Engineering ◽

10.25077/jitce.4.02.83-89.2020 ◽

2020 ◽

Vol 4 (02) ◽

pp. 83-89

Author(s):

Afriansyah Afriansyah ◽

Ade Irawan

Keyword(s):

Time Series Data ◽

Short Term Memory ◽

Electronic Device ◽

Electricity Consumption ◽

Series Data ◽

Short Term ◽

Term Memory ◽

Electricity Cost ◽

Series Of Experiments ◽

Long Short Term Memory

Excessive use of household electricity is one of the causes of the largest amount of national electricity consumption coming from households. One way to reduce the amount of household electricity consumption is to automate the operation of electronic devices. This research proposes utilizing Long Short Term Memory (LSTM) algorithm to predict the habit of operating an electronic device. The prediction is then applied to automate the operation of that by exploiting the time series data from the usage. A series of experiments are conducted to capture the data of operating a manual lamp. Then, an LSTM model is built by training the data. The experiment results show the prediction accuracy of 99,28% and Root Mean Square Error of 0,091. Furthermore, the LSTM model is used to automatically operate a lamp in a month. The electricity cost from the automation is 36,38% lower than the manual.

Download Full-text