Prediction Of Time Series Data Research Articles

An Enhanced Ensemble of Long Short-Term Memory and Vector AutoRegression for Energy Consumption Forecasting

Objectives: To design and develop an enhanced ensemble model for residential energy consumption prediction using time series analysis. Methods: The system is consistent of an ensemble made from two time series models, which are later combined to produce a final prediction through the use of bagging techniques. The energy profile is built for this study using the data collected from a single-phase Minion Energy Monitor, installed in residential buildings, which is developed by Minion Labs India Private Limited. Samples are collected for a time of 7 days with a two second interval. This data is then restructured and normalized for it to fit the enhanced ensemble model of Long Short-Term Memory (LSTM) and Vector Autoregression (VAR) using bagging techniques and weighted average to obtain the predictions.Findings: The proposed model has produced an enhanced R2 score of 98.99% when compared to LSTM (74.85%), SVM (62.41%), VAR (82.914%) and ARIMA (93.152%) standalone models. It makes use of an analyzed lag variable to reduce computation complexity and resource utilization. Further, an ensemble technique is used to pick out the strengths of two models. An analysis performed showed that this architecture is 6.08% better than the algorithms for LSTM and VAR individually. Novelty: A data driven solution is proposed in this study through the enhancement of existing models to create an ensemble and thereby creating a stable structure that predicts values using a weighted average. The weighted average ensures that precise outputs are obtained by giving more importance to predictions that are closer to the actual values. The use of a lag variable further increases the efficiency, learning rate, dealing with non-linear features, less error and faster training of the proposed architecture. All these factors also aid in improving the accuracy for a time series data prediction. Keywords: Energy Consumption Forecast; LSTM; VAR; Ensemble; Bagging; Artificial Neural Networks; Support Vector Machine

Taming the Chaos in Neural Network Time Series Predictions.

Machine learning methods, such as Long Short-Term Memory (LSTM) neural networks can predict real-life time series data. Here, we present a new approach to predict time series data combining interpolation techniques, randomly parameterized LSTM neural networks and measures of signal complexity, which we will refer to as complexity measures throughout this research. First, we interpolate the time series data under study. Next, we predict the time series data using an ensemble of randomly parameterized LSTM neural networks. Finally, we filter the ensemble prediction based on the original data complexity to improve the predictability, i.e., we keep only predictions with a complexity close to that of the training data. We test the proposed approach on five different univariate time series data. We use linear and fractal interpolation to increase the amount of data. We tested five different complexity measures for the ensemble filters for time series data, i.e., the Hurst exponent, Shannon’s entropy, Fisher’s information, SVD entropy, and the spectrum of Lyapunov exponents. Our results show that the interpolated predictions consistently outperformed the non-interpolated ones. The best ensemble predictions always beat a baseline prediction based on a neural network with only a single hidden LSTM, gated recurrent unit (GRU) or simple recurrent neural network (RNN) layer. The complexity filters can reduce the error of a random ensemble prediction by a factor of 10. Further, because we use randomly parameterized neural networks, no hyperparameter tuning is required. We prove this method useful for real-time time series prediction because the optimization of hyperparameters, which is usually very costly and time-intensive, can be circumvented with the presented approach.

Multivariate Time Series Data Prediction Based on ATT-LSTM Network

Deep learning models have been widely used in prediction problems in various scenarios and have shown excellent prediction effects. As a deep learning model, the long short-term memory neural network (LSTM) is potent in predicting time series data. However, with the advancement of technology, data collection has become more accessible, and multivariate time series data have emerged. Multivariate time series data are often characterized by a large amount of data, tight timeline, and many related sequences. Especially in real data sets, the change rules of many sequences will be affected by the changes of other sequences. The interacting factors data, mutation information, and other issues seriously impact the prediction accuracy of deep learning models when predicting this type of data. On the other hand, we can also extract the mutual influence information between different sequences and simultaneously use the extracted information as part of the model input to make the prediction results more accurate. Therefore, we propose an ATT-LSTM model. The network applies the attention mechanism (attention) to the LSTM to filter the mutual influence information in the data when predicting the multivariate time series data, which makes up for the poor ability of the network to process data. Weaknesses have greatly improved the accuracy of the network in predicting multivariate time series data. To evaluate the model’s accuracy, we compare the ATT-LSTM model with the other six models on two real multivariate time series data sets based on two evaluation indicators: Mean Absolute Error (MAE) and Root Mean Square Error (RMSE). The experimental results show that the model has an excellent performance improvement compared with the other six models, proving the model’s effectiveness in predicting multivariate time series data.

GA-Optimized Multivariate CNN-LSTM Model for Predicting Multi-channel Mobility in the COVID-19 Pandemic

The primary factor that contributes to the transmission of COVID-19 infection is human mobility. Positive instances added on a daily basis have a substantial positive association with the pace of human mobility, and the reverse is true. Thus, having the ability to predict human mobility trend during a pandemic is critical for policymakers to help in decreasing the rate of transmission in the future. In this regard, one approach that is commonly used for time-series data prediction is to build an ensemble with the aim of getting the best performance. However, building an ensemble often causes the performance of the model to decrease, due to the increasing number of parameters that are not being optimized properly. Consequently, the purpose of this study is to develop and evaluate a deep learning ensemble model, which is optimized using a genetic algorithm (GA) that incorporates a convolutional neural network (CNN) and a long short-term memory (LSTM). A CNN is used to conduct feature extraction from mobility time-series data, while an LSTM is used to do mobility prediction. The parameters of both layers are adjusted using GA. As a result of the experiments conducted with data from the Google Community Mobility Reports in Indonesia that ranges from the beginning of February 2020 to the end of December 2020, the GA-Optimized Multivariate CNN-LSTM ensemble outperforms stand-alone CNN and LSTM models, as well as the non-optimized CNN-LSTM model, in terms of predicting human movement in the future. This may be useful in assisting policymakers in anticipating future human mobility trends. Doi: 10.28991/esj-2021-01300 Full Text: PDF

Implementation of Fund Recommendation System Using Machine Learning

In this paper, we implement a system for a fund recommendation based on the investment propensity and for a future fund price prediction. The investment propensity is classified by scoring user responses to series of questions. The proposed system recommends the funds with a suitable risk rating to the investment propensity of the user. The future fund prices are predicted by Prophet model which is one of the machine learning methods for time series data prediction. Prophet model predicts future fund prices by learning the parameters related to trend changes. The prediction by Prophet model is simple and fast because the temporal dependency for predicting the time-series data can be removed. We implement web pages for the fund recommendation and for the future fund price prediction.

Design of an Error Estimation Algorithm for Time Series Data Prediction in Attitude Controlled Systems

This research presents an error estimation approach with the combination of traditional multilevel techniques used to minimize errors for an accurate prediction and to investigate the behavior of such an algorithm for a satellite. The traditional techniques mentioned above are a combination derived from multiple regression techniques and perform a case study for data analysis. A linear plot can easily be predicted, however if a system tends to deviate toward non-linearity the overall result derived from such an algorithm can be non-reliable since each value would depict a completely different output at different levels. The stability of the fixed regression derived is used to determine the accuracy of the system.

The forecasting model of discharge at Brantas sub-basin using autoregressive integrated moving average (ARIMA) and decomposition methods

A watershed is a combination of several rivers and tributaries with certain boundaries that function to drain rainwater into a lake or a sea. One of the hydrological data contained in the watershed is discharge data. If there is incomplete discharge data, it must be extended based on historical data. ARIMA and decomposition are methods that can predict time series data. The purposes of this research are to determine the historical discharge patterns of Brantas Sub-basin, to know the discharge forecasting model of Brantas Sub-basin, to know the results of forecasting Brantas Sub-basin discharge, and to compare the accuracy between ARIMA and decomposition methods. The accuracy is obtained by calculating MSE and RMSE values. The best method is a method that has the smallest MSE and RMSE values. The results of the research showed that Brantas Sub-basin discharge data in 2007-2017 has a seasonal pattern. The best ARIMA model is ARIMA (0,0,3)(1,0,1)12 model, while the best decomposition model is the additive decomposition model. The Decomposition method has better accuracy than the ARIMA method in predicting discharge of Brantas Sub-basin.

An Application of AdaBoost-GRU Ensemble Model to Economic Time Series Prediction

Objectives: Given the importance of accurate prediction of financial time series data and their benefits in the real-life, AdaBoost-GRU ensemble learning is proposed in which it’s forecasting accuracy is to be compared with AdaBoost-LSTM, single Long Short Term Memory (LSTM), and single Gated Recurrent Unit (GRU). Methods: The data for Korea Composite Stock Price Index (KOSPI) obtained from Naver Finance from January 2000 to April 2020, the Oil Price data for the entire Gyeongnam region among domestic oil price data obtained from Korea Petroleum Corporation (Opinet) and USD Exchange data provided by Naver Financial from April 2004 to May 2020 were employed. The analyses were made using mean absolute error (MAE), mean squared error (MSE) and root mean squared error (RMSE) as the performance metric. Findings: Empirical results show that the proposed method outperforms all other models that serve as benchmarked models, in all three kinds of data used in this research. This also shows that ensemble models have better performance than the single models as both AdaBoost-GRU and AdaBoost-LSTM outperform their respective single GRU and single LSTM. Novelty/Applications: This empirical study suggests that the AdaBoost-GRU ensemble-learning model is a highly promising approach for forecasting these kinds of data. However, another ensemble model that can combine AdaBoost with other single models such as ConvD1 can be developed and applied. Keywords: Oil Price; Exchange Rate; Stock Price Index; Time Series Forecasting; AdaBoost Algorithm; Gated Recurrent Unit

Intelligent computing on time-series data analysis and prediction of COVID-19 pandemics.

Covid-19 disease caused by novel coronavirus (SARS-CoV-2) is a highly contagious epidemic that originated in Wuhan, Hubei Province of China in late December 2019. World Health Organization (WHO) declared Covid-19 as a pandemic on 12th March 2020. Researchers and policy makers are designing strategies to control the pandemic in order to minimize its impact on human health and economy round the clock. The SARS-CoV-2 virus transmits mostly through respiratory droplets and through contaminated surfacesin human body.Securing an appropriate level of safety during the pandemic situation is a highly problematic issue which resulted from the transportation sector which has been hit hard by COVID-19. This paper focuses on developing an intelligent computing model for forecasting the outbreak of COVID-19. The Facebook Prophet model predicts 90 days future values including the peak date of the confirmed cases of COVID-19 for six worst hit countries of the world including India and six high incidence states of India. The model also identifies five significant changepoints in the growth curve of confirmed cases of India which indicate the impact of the interventions imposed by Government of India on the growth rate of the infection. The goodness-of-fit of the model measures 85% MAPE for all six countries and all six states of India. The above computational analysis may be able to throw some light on planning and management of healthcare system and infrastructure.

Tuning Parameters in Deep Belief Networks for Time Series Prediction through Harmony Search

There have been several researches of applying Deep Belief Networks (DBNs) to predict time series data. Most of these works pointed out that DBNs can bring out better prediction accuracy than traditional Artificial Neural Networks. However, one of the main shortcomings of using DBNs in time series prediction concerns with the proper selection of their parameters. In this paper, we investigate the use of Harmony Search algorithm for determining the parameters of DBN in forecasting time series. Experimental results on several synthetic and real world time series datasets revealed that the DBN with parameters selected by Harmony Search performs better than the DBN with parameters selected by Particle Swarm Optimization (PSO) or random method in most of the tested datasets.

A multiple model framework based on time series clustering for shale gas well pressure prediction

Production performance analysis of shale gas based on dynamic parameters is now playing a more important role as a scientific basis for gas well development plan, and describes the structural features, evolution and predict the future production trends. Owing to multi-gradient of gas demand and high fluctuation of the yield adjustment period, it is difficult to identify whether the change of production parameters of gas well, especially the pressure is caused by natural resource consumption or manual production adjustment. Therefore, time-series prediction for adjustable yield wells is an extraordinarily important and challenging task. In this paper, a prediction framework with a multiple model is proposed. Specifically, the weighted warped K -means clustering (WWKM) algorithm is first presented to partition the dataset into a series of clusters considering the significantly different influence of each variable. Thereafter, a multiple prediction model based on sequence information (MMP-SI) is designed to improve the prediction precision by integrating the overall decreasing trends and local fluctuation features of the dataset. Subsequently, the proposed framework is applied to pressure prediction of real time-series data of three shale gas adjustable yield wells for the Fuling region in China. The experimental results show that the proposed framework provides good prediction precision over other state-of-the-art models in terms of different evaluation criteria. The main benefits of this research study are to better simulate shale gas wells in the future for engineers and academic researchers. • A specialized multiple model prediction framework is proposed for time-series data of shale gas adjustable wells. • A weighted warped K-means clustering (WWKM) algorithm is proposed to construct a series of data subsets for training multiple prediction models. • A multiple model prediction method based on sequence information (MMP-SI) is designed considering both the current gas demand and the overall pressure trend.

Adaptive Synapse Arrangement in Cortical Learning Algorithm

The cortical learning algorithm (CLA) is a time-series data prediction method that is designed based on the human neocortex. The CLA has multiple columns that are associated with the input data bits by synapses. The input data is then converted into an internal column representation based on the synapse relation. Because the synapse relation between the columns and input data bits is fixed during the entire prediction process in the conventional CLA, it cannot adapt to input data biases. Consequently, columns not used for internal representations arise, resulting in a low prediction accuracy in the conventional CLA. To improve the prediction accuracy of the CLA, we propose a CLA that self-adaptively arranges the column synapses according to the input data tendencies and verify its effectiveness with several artificial time-series data and real-world electricity load prediction data from New York City. Experimental results show that the proposed CLA achieves higher prediction accuracy than the conventional CLA and LSTMs with different network optimization algorithms by arranging column synapses according to the input data tendency.

Planning Total Veener Production PT. XYZ

PT. XYZ is engaged in the manufacture and sale of wood veneers. Starting from the constant occurrence of over stock, now the company must make improvements to the production forecasting process so that over stock can be avoided. It can be seen that accurate production forecasting can create conditions for an effective and efficient production system. This study aims to obtain a more accurate forecast of material requirements using the Support Vector Regression (SVR) method, which is the result of the development of a Support Vector Machine (SVM) which has good performance in predicting time series data. Application of the Support Vector Regression (SVR) method with the RBF kernel in predicting the need for veneer production using the MATLAB application, it produces the smallest error rate with a MAPE of 5%, RMSE of 4364.63 and of 0.748274147. on 67 training data and 20 testing data.

Applying data mining technique to predict trends in air pollution in Mumbai

Prediction of air quality is a topic of great interest in air quality research due to direct association with health effect. The prediction provides pre-information to the overall population of the area about the status of pollution on which they can take precautionary measures and can protect their health. The problem arises when the level of SO2, NO2 and residual suspended particulate matters in the air increases than that of theirs restricted level. In this paper, the Prophet Algorithm, open source software, is applied to predict the trend of air pollution in the city of Mumbai, Maharashtra. The Prophet is machine learning algorithm to forecast and also to predict time series data. It is based on additive model where non-linear trends are fit with yearly and weekly seasonality. The graphical results are generated after using this algorithm which shows the trending pattern of the pollutants in the air of Mumbai.

Forecasting of Tomato Yields Using Attention-Based LSTM Network and ARMA Model

Nonlinear autoregressive exogenous (NARX), autoregressive integrated moving average (ARIMA) and multi-layer perceptron (MLP) networks have been widely used to predict the appearance value of future points for time series data. However, in recent years, new approaches to predict time series data based on various networks of deep learning have been proposed. In this paper, we tried to predict how various environmental factors with time series information affect the yields of tomatoes by combining a traditional statistical time series model and a deep learning model. In the first half of the proposed model, we used an encoding attention-based long short-term memory (LSTM) network to identify environmental variables that affect the time series data for tomatoes yields. In the second half of the proposed model, we used the ARMA model as a statistical time series analysis model to improve the difference between the actual yields and the predicted yields given by the attention-based LSTM network at the first half of the proposed model. Next, we predicted the yields of tomatoes in the future based on the measured values of environmental variables given during the observed period using a model built by integrating the two models. Finally, the proposed model was applied to determine which environmental factors affect tomato production, and at the same time, an experiment was conducted to investigate how well the yields of tomatoes could be predicted. From the results of the experiments, it was found that the proposed method predicts the response value using exogenous variables more efficiently and better than the existing models. In addition, we found that the environmental factors that greatly affect the yields of tomatoes are internal temperature, internal humidity, and CO2 level.

Adaptive Online Learning for the Autoregressive Integrated Moving Average Models

This paper addresses the problem of predicting time series data using the autoregressive integrated moving average (ARIMA) model in an online manner. Existing algorithms require model selection, which is time consuming and unsuitable for the setting of online learning. Using adaptive online learning techniques, we develop algorithms for fitting ARIMA models without hyperparameters. The regret analysis and experiments on both synthetic and real-world datasets show that the performance of the proposed algorithms can be guaranteed in both theory and practice.

Prediksi Penyakit Ginjal Kronis Menggunakan Hibrid Jaringan Saraf Tiruan Backpropagation dengan Particle Swarm Optimization

The number of Chronic Kidney Disease patient increased year by year while it doesn’t following by sufficient human resources and infrastructure needs the information of Chronic Kidney Disease patient prediction. Prediction of Chronic Kidney Disease patient is necessary to be done as an anticipation for preparing the better human resources and infrastructure that will effect to patient survival rate. In this study, backpropagation artificial neural network and particle swarm optimization combination used to predict the number of Chronic Kidney Disease patient. Artificial Neural Network has the ability in time series data prediction, such as the number of Chronic Kidney Disease year by year. But, backpropagation artificial neural network has a weakness in weight inisialization which taken unoptimally that could cause bad convergence speed. Particle swarm optimization will resolve the backpropagation artificial neural network weakness by weights optimization that will used in backpropagation artificial neural network. The Artificial Neural Network and Particle Swarm Optimization have several parameters, such as the number of hidden layer neuron, learning rate, and swarm. This research is using RSUD Banyumas Chronic Kidney Disease patient data in 2011 until 2020. Matlab R2019a used in this research as a software to predict chronic kidney disease patient data. The test results shows the prediction accuracy based on Mean Squared Error value is 0,0370 using 12-16-1 artificial neural network architecture, 0.005 learning rate, 1250 epochs and 50 swarms

Deep Learning-Based Stroke Disease Prediction System Using Real-Time Bio Signals.

The emergence of an aging society is inevitable due to the continued increases in life expectancy and decreases in birth rate. These social changes require new smart healthcare services for use in daily life, and COVID-19 has also led to a contactless trend necessitating more non-face-to-face health services. Due to the improvements that have been achieved in healthcare technologies, an increasing number of studies have attempted to predict and analyze certain diseases in advance. Research on stroke diseases is actively underway, particularly with the aging population. Stroke, which is fatal to the elderly, is a disease that requires continuous medical observation and monitoring, as its recurrence rate and mortality rate are very high. Most studies examining stroke disease to date have used MRI or CT images for simple classification. This clinical approach (imaging) is expensive and time-consuming while requiring bulky equipment. Recently, there has been increasing interest in using non-invasive measurable EEGs to compensate for these shortcomings. However, the prediction algorithms and processing procedures are both time-consuming because the raw data needs to be separated before the specific attributes can be obtained. Therefore, in this paper, we propose a new methodology that allows for the immediate application of deep learning models on raw EEG data without using the frequency properties of EEG. This proposed deep learning-based stroke disease prediction model was developed and trained with data collected from real-time EEG sensors. We implemented and compared different deep-learning models (LSTM, Bidirectional LSTM, CNN-LSTM, and CNN-Bidirectional LSTM) that are specialized in time series data classification and prediction. The experimental results confirmed that the raw EEG data, when wielded by the CNN-bidirectional LSTM model, can predict stroke with 94.0% accuracy with low FPR (6.0%) and FNR (5.7%), thus showing high confidence in our system. These experimental results demonstrate the feasibility of non-invasive methods that can easily measure brain waves alone to predict and monitor stroke diseases in real time during daily life. These findings are expected to lead to significant improvements for early stroke detection with reduced cost and discomfort compared to other measuring techniques.

340-P: Nocturnal Hypoglycemia Prediction in Hospitalized Patients with Type 1 Diabetes Using Combined Supervised and Unsupervised Ensemble Learning

The Aim: To assess the efficacy of combined supervised and unsupervised ensemble machine learning based on continuous glucose monitoring (CGM) data for short-term prediction of nocturnal hypoglycemia (NH) in hospitalized patients with type 1 diabetes (T1D). Materials and Methods: We analyzed CGM records with a minimal duration of 72 hours obtained from 406 adult patients admitted to tertiary referral hospital. An episode of NH was defined as ≥3 consequent glucose values of <3.9 mmol/L recorded between 0 and 6 am. Depending on predictor sequence length (30 min - 1 h) and horizon (H) of forecasting (5-30 min), we obtained 209-256 and near 4∙104 records with and without NH respectively. Twenty nine metrics, including mean, minimal and maximum glucose, range, gradient, linear, quadratic and cubic trend coefficients, dynamic time wrapping similarity-based indices, and a number of glucose variability indices, were evaluated. The ensemble clustering was used for extraction of representative samples. Random Forest ensemble model was applied for NH prediction. The obtained quality metrics were averaged over 100 random partitions of the dataset on training and testing subsets. Results: The quality metrics did not depend significantly on predictor sequence length; we used 30 min as a baseline. Depending on H, values of sensitivity and specificity varied from 98% and 97% (H=5 min) to 85% and 87% (H=30 min). The false alarm ratio values were very high (>90%) due to the unbalanced nature of data. Minimal glucose, low blood glucose index, and increment in the penultimate value of sequence were the most important predictors assessed with Random Forest algorithm. Conclusions: The results demonstrate the usefulness of ensemble machine learning models based on CGM time series data for prediction of NH events in hospitalized patients with T1D. Additional studies are needed for improving false alarm ratio metrics of forecasting quality. Disclosure V. Berikov: None. J. F. Semenova: None. V. Klimontov: Advisory Panel; Self; Boehringer Ingelheim International GmbH, Sanofi, Research Support; Self; Boehringer Ingelheim International GmbH, Speaker’s Bureau; Self; AstraZeneca, Medtronic. Funding Russian Science Foundation (20-15-00057)

기상 테이터를 이용한 딥러닝 기반 풍력 발전량 예측에 관한 연구

Although the proportion of wind energy sources in the system is increasing, the variability and stochastic characteristics of wind power have a negative effect on system stability and on the rescheduling of the system’s power generation. Therefore, an accurate prediction of wind power generation is necessary for stable power distribution in the power system. High-precision wind power forecasting provides a reliable basis for dispatching of power system. Since wind power data is time series data with uncertainty, a suitable model, the LSTM algorithm of Keras, was proposed to predict a short-term wind power generation. The LSTM has memory to store past states, so it is suitable for the problem of predicting time series data. This paper proposes a forecasting procedure using an LSTM neural network to forecast wind power. First, Pearson correlation coefficient method is utilized to determine the parameters of LSTM forecasting model. Then a case study was performed using real data collected from a wind farm in Yeongheung to confirm that the LSTM model was suitable for wind power prediction.