Time Series Prediction Problems Research Articles

A modified artificial electric field algorithm and its application

Abstract As an efficient meta-heuristic technique, artificial electric field algorithm (AEFA) has been extensively applied to tackle various challenging tasks posed by practical scenarios. However, in the classical AEFA, the fitness function has a cumulative effect on the charge, resulting in limited search capability. To address this issue, a modified AEFA (MAEFA) is presented in this paper. More specifically, a novel charge calculation scheme is introduced to overcome the cumulative effect by gradually distinguishing the charges of particles during the evolutionary process. Further, an alternating search strategy is developed to calculate the total electrostatic force, thereby reinforcing the guiding effect of excellent individuals on the entire population. Subsequently, the performance of MAEFA is investigated using 42 well-benchmarked functions, two chaotic time series prediction problems, and two engineering design problems. Experimental results reveal that MAEFA is more competitive in comparison with several established AEFAs and 20 popular meta-heuristic techniques.

Time-series water prediction based on feature clustering fusion and XGboost

Abstract. The time series prediction problem has a very wide range of applications in many fields. Most scholars use the LSTM class of algorithms for prediction. However, this method consumes a significant amount of computational power and presents several challenges. To address this issue, this paper proposes a time series forecasting method based on feature fusion and XGBoost. Specifically, we first utilize holiday information and the K-Means algorithm for feature extraction to expand the feature dimensions of the dataset, and then employ XGBoost as a model for training and prediction. Experiments demonstrate that the method proposed in this paper significantly reduces error compared to other traditional machine learning and deep learning methods, while the training time is much shorter than these methods. For example, compared with LSTM, the MSLE of this model decreases by 1.42%, while the training time is only 0.15% of that of LSTM. This greatly saves on training costs and computational power consumption. This confirms the effectiveness of using machine learning and clustering algorithms in time series prediction and provides new methods and practical application directions for future time series prediction models.

Textual data for electricity load forecasting

AbstractTraditional mid‐term electricity forecasting models rely on calendar and meteorological information such as temperature and wind speed to achieve high performance. However depending on such variables has drawbacks, as they may not be informative enough during extreme weather. While ubiquitous, textual sources of information are hardly included in prediction algorithms for time series, despite the relevant information they may contain. In this work, we propose to leverage openly accessible weather reports for electricity demand and meteorological time series prediction problems. Our experiments on French and British load data show that the considered textual sources allow to improve overall accuracy of the reference model, particularly during extreme weather events such as storms or abnormal temperatures. Additionally, we apply our approach to the problem of imputation of missing values in meteorological time series, and we show that our text‐based approach beats standard methods. Furthermore, the influence of words on the time series' predictions can be interpreted for the considered encoding schemes of the text, leading to a greater confidence in our results.

Forecasting international tourist arrivals in South Korea: a deep learning approach

Purpose This study aims to develop a robust long short-term memory (LSTM)-based forecasting model for daily international tourist arrivals at Incheon International Airport (ICN), incorporating multiple predictors including exchange rates, West Texas Intermediate (WTI) oil prices, Korea composite stock price index data and new COVID-19 cases. By leveraging deep learning techniques and diverse data sets, the research seeks to enhance the accuracy and reliability of tourism demand predictions, contributing significantly to both theoretical implications and practical applications in the field of hospitality and tourism. Design/methodology/approach This study introduces an innovative approach to forecasting international tourist arrivals by leveraging LSTM networks. This advanced methodology addresses complex managerial issues in tourism management by providing more accurate forecasts. The methodology comprises four key steps: collecting data sets; preprocessing the data; training the LSTM network; and forecasting future international tourist arrivals. The rest of this study is structured as follows: the subsequent sections detail the proposed LSTM model, present the empirical results and discuss the findings, conclusions and the theoretical and practical implications of the study in the field of hospitality and tourism. Findings This research pioneers the simultaneous use of big data encompassing five factors – international tourist arrivals, exchange rates, WTI oil prices, KOSPI data and new COVID-19 cases – for daily forecasting. The study reveals that integrating exchange rates, oil prices, stock market data and COVID-19 cases significantly enhances LSTM network forecasting precision. It addresses the narrow scope of existing research on predicting international tourist arrivals at ICN with these factors. Moreover, the study demonstrates LSTM networks’ capability to effectively handle multivariable time series prediction problems, providing a robust basis for their application in hospitality and tourism management. Originality/value This research pioneers the integration of international tourist arrivals, exchange rates, WTI oil prices, KOSPI data and new COVID-19 cases for forecasting daily international tourist arrivals. It bridges the gap in existing literature by proposing a comprehensive approach that considers multiple predictors simultaneously. Furthermore, it demonstrates the effectiveness of LSTM networks in handling multivariable time series forecasting problems, offering practical insights for enhancing tourism demand predictions. By addressing these critical factors and leveraging advanced deep learning techniques, this study contributes significantly to the advancement of forecasting methodologies in the tourism industry, aiding decision-makers in effective planning and resource allocation.

MCGnet with multi-level gated unit transformations: A time series prediction-based model for unknown pattern abnormality detection

The task of anomaly detection in data patterns remains challenging due to the diverse of fault patterns, which often render existing models ineffective when encountered with unknown or unseen data patterns in the training data. Furthermore, insufficient samples, the presence of chaotic behavior, unbalanced anomaly patterns are potential limiting factors in the practical application. While prediction error-based approaches attempt to address these challenges, the discriminability of abnormal patterns in existing scenarios is not yet sufficient, thus limiting the ability to identify abnormal phenomena. To overcome these limitations, we proposed a novel model called MCGnet. The backbone architecture of MCGnet employed a novel design of continuous multi-layer circular convolution transformations. This design enhances the expressive capability of the model by expanding the differences among data patterns. Additionally, we introduced in parallel the newly proposed temporal-frequency gated Gaussian unit, which generates richer feature representations. Subsequently, the obtained feature representations were fed into an explicit causal network to learn complex patterns of data along temporal dependencies. The MCGnet not only solves high-precision time series prediction problems but also significantly improves the discriminability between normal and abnormal patterns. Since the proposed model is accurately modeled using only a small amount of normal data, it bypasses the limiting factors such as insufficient fault samples and sample imbalance, and is able to effectively deal with various unknown data patterns. The accuracy of the proposed method was verified through simulation data (Duffing system) and its potential for engineering applications was demonstrated through real-world data (rotor system).

Using Unsupervised Methods to Find Attack Points for Time Series Prediction Models

Time series prediction models are extensively utilized across different industries in everyday life, and the security of industry data is linked to the susceptibility of these prediction models to adversarial attacks. This paper focuses on the method of fi nding vulnerable positions for adversarial attacks in time series prediction problems. Currently, most related studies use supervised methods to fi nd attack points, but they require labeled training data, which may be diffi cult to obtain or costly in some cases, and they may not adapt well to new attacks because the model only learns the features of known attacks during training. Therefore, in this paper, We defi ne the common vulnerable position identifi ed by the brute force method as the real common vulnerable position. Next, we introduce the application of unsupervised methods (such as Kmeans) to identify common vulnerable positions. We compare the positions identifi ed by these two methods and validate them using an LSTM time series prediction model.

A Meta-learner approach to multistep-ahead time series prediction

AbstractThe utilization of machine learning has become ubiquitous in addressing contemporary challenges in data science. Moreover, there has been significant interest in democratizing the decision-making process for selecting machine learning algorithms, achieved through the incorporation of meta-features and automated machine learning techniques for both classification and regression tasks. However, this paradigm has not been readily applied to multistep-ahead time series prediction problems. Unlike regression and classification problems, which utilize independent variables not derived from the target variable, time series models typically rely on past values of the series to forecast future outcomes. The structure of a time series is often characterized by features such as trend, seasonality, cyclicality and irregularity. In our study, we illustrate how time series metrics representing these features, in conjunction with an ensemble-based regression Meta-Learner, were employed to predict the standardized mean square error of candidate time series prediction models. Our experiments utilized datasets covering a broad feature space, facilitating the selection of the most effective model by researchers. A rigorous evaluation was conducted to assess the performance of the Meta-Learner on both synthetic and real time series data.

Multi level perspectives in stock price forecasting: ICE2DE-MDL.

This study proposes a novel hybrid model, called ICE2DE-MDL, integrating secondary decomposition, entropy, machine and deep learning methods to predict a stock closing price. In this context, first of all, the noise contained in the financial time series was eliminated. A denoising method, which utilizes entropy and the two-level ICEEMDAN methodology, is suggested to achieve this. Subsequently, we applied many deep learning and machine learning methods, including long-short term memory (LSTM), LSTM-BN, gated recurrent unit (GRU), and SVR, to the IMFs obtained from the decomposition, classifying them as noiseless. Afterward, the best training method was determined for each IMF. Finally, the proposed model's forecast was obtained by hierarchically combining the prediction results of each IMF. The ICE2DE-MDL model was applied to eight stock market indices and three stock data sets, and the next day's closing price of these stock items was predicted. The results indicate that RMSE values ranged from 0.031 to 0.244, MAE values ranged from 0.026 to 0.144, MAPE values ranged from 0.128 to 0.594, and R-squared values ranged from 0.905 to 0.998 for stock indices and stock forecasts. Furthermore, comparisons were made with various hybrid models proposed within the scope of stock forecasting to evaluate the performance of the ICE2DE-MDL model. Upon comparison, The ICE2DE-MDL model demonstrated superior performance relative to existing models in the literature for both forecasting stock market indices and individual stocks. Additionally, to our knowledge, this study is the first to effectively eliminate noise in stock item data using the concepts of entropy and ICEEMDAN. It is also the second study to apply ICEEMDAN to a financial time series prediction problem.

Temporal feature decomposition fusion network for building energy multi-step prediction

Accurate building energy prediction methods have become a key factor in achieving energy-saving goals. Traditional methods for building energy multi-step prediction often use recursive or direct strategies to address time series prediction problems, which may neglect the data sequence correlation and result in the cumulative error. To solve the above problem, this paper proposed a Temporal Feature Decomposition Fusion Network (TFDFNet) model for building energy consumption multi-step prediction, with an encoder-decoder architecture. In the encoder, feature fusion layers is employed to consider the influence of different feature sequences on the predicted sequence. Through the decomposition of historical load data sequences, different hierarchical sequence structures are constructed to enhance the interpretability and predictability of the data. In the decoder, a simple and efficient network is constructed using MLP to decode the encoded information and obtain the prediction results. Experimental results show that, the proposed model achieves higher prediction accuracy and more stable convergence than the other five comparable methods, which also indicates the potential of achieving excellent building energy consumption multi-step prediction results with a simple model design.

IoT-Based Energy Consumption Prediction Using Transformers

With the advancement of various IoT-based systems, the amount of data is steadily increasing. The increase of data on a daily basis is essential for decision-makers to assess current situations and formulate future policies. Among the various types of data, time-series data presents a challenging relationship between current and future dependencies. Time-series prediction aims to forecast future values of target variables by leveraging insights gained from past data points. Recent advancements in deep learning-based algorithms have surpassed traditional machine learning-based algorithms for time-series in IoT systems. In this study, we employ Enc&Dec Transformer, the latest advancements in neural networks for time-series prediction problems. The obtained results were compared with Encoder-only and Decoder-only Transformer blocks as well as well-known recurrent based algorithms, including 1D-CNN, RNN, LSTM, and GRU. To validate our approach, we utilize three different univariate time-series datasets collected on an hourly basis, focusing on energy consumption within IoT systems. Our results demonstrate that our proposed Transformer model outperforms its counterparts, achieving a minimum Mean Squared Error (MSE) of 0.020 on small, 0.008 on medium, and 0.006 on large-sized datasets.

A Modified Sine Cosine Algorithm for Numerical Optimization

Sine cosine algorithm (SCA) is a recently developed meta-heuristic method based on the characteristics of sine and cosine functions. However, SCA algorithm may suffer premature convergence in solving complex optimization problems. To mitigate this limitation, a modified SCA (MSCA) is developed to achieve an effective balance between exploration and exploitation. Specifically, the conversion parameter can be configured adaptively by using the individual fitness information in the evolution process to guide the individual search behavior. After that, an inertia weight is embedded in the position updating equation to further improve the search accuracy and accelerate the convergence speed. The performance of MSCA algorithm is investigated on 13 benchmark functions and the chaotic time series prediction problem. Experimental results demonstrate that MSCA algorithm is more effective than the other optimization methods.

Detection of Rotating Stall Inception of Axial Compressors Based on Deep Dilated Causal Convolutional Neural Networks

The anomaly detection of outliers and fault diagnosis in the imperfect time-series data is crucial in aero-engine industry. Early detection of the rotating stall is significant for the active stabilization control of the axial compressors, because the rotating stall and surge can cause enormous vibratory stresses in the blades and gives rise to surge to limit the performance of compressors. An aerodynamic instability inception and short-length-scale periodic anomaly prior to stall onset known as stall inception in axial compressors is observed in aero-engine. Based on deep learning theory, this paper conducts the accurate and rapid detection of stall precursors based on deep neural network. The deep dilated causal convolutional neural network combined with logistic regression(LR) named as LR-WaveNet is applied to the detection and prediction of stall inception in the imperfect time-series data of axial compressors with the rotating stall. The LR-WaveNet model can implement fast anomaly detection and stall prediction in long-time term series data. Furthermore, a single LR-WaveNet can be trained to capture and learn the time-domain statistical characteristics of many different stall inception training data with equal fidelity. The trained LR-WaveNet model can rapidly detect the occurrence of anomaly point and predict the probability of rotating stall and surge in axial compressors as an early warning signal. By comparing with the time domain analysis and the wavelet analysis, the calculation results are represented with experimental data to show the effectiveness and feasibility of the stall detection approach based on LR-WaveNet. Especially, the LR-WaveNet can detect the irregular and imperfect stall inception and capture the small fault features when the characteristics of stall inception sigals or data are not very unobvious, irregular and imperfect. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —Note to Practitioners–This paper was motivated by the problem of detecting the stall and surge of axial compressor for aeroengine, but it also applies to other small fault diagnosis with imperfect data or time series prediction problem. The stall Inception is very difficult to detect for the reason of imperfect data with small fault or features. These existing detection methods of stall inception can only be applied under certain conditions, because they can only extract the pre-stall features partly. Meanwhile, the excessive number of compressor sensors is demanded in this method, so the application of these traditional methods are limited in practical situations in the stall inception detection. This paper suggests a new approach using Deep Dilated Causal Convolutional Neural Networks. The deep dilated causal convolutional neural network combined with logistic regression(LR) named as LR-WaveNet is applied to the detection and prediction of stall inception in the imperfect time-series data of axial compressors with the rotating stall. In this paper, the new approach is proved to be suitable and feasible to all the types of stall inception including the irregular stall inception with imperfect data. We then show how the deep learning method can be efficiently applied in the imperfect data situation with small fault and time series prediction. The experiments suggest that this approach is feasible. In future research, we will create the novel approach and theory for the detection of stall inception and small fault diagnostics with the imperfect data.

Is Single Enough? A Joint Spatiotemporal Feature Learning Framework for Multivariate Time Series Prediction.

A fuzzy cognitive map (FCM) is a simple but effective tool for modeling and predicting time series. This article focuses on the problem of multivariate time series prediction (TSP), which is essential and challenging in data mining. Although several FCM-based approaches have been designed to solve this problem, their feature extraction module designed for single mode falls short in capturing the nonlinear spatiotemporal dependencies among variates, thereby resulting in low prediction accuracy in forecasting multivariate time series, which shows that the single mode learning is not enough. Therefore, in this article, we propose a joint spatiotemporal feature learning framework for multivariate TSP, where a mix-resolution spatial module consisting of multiple sparse autoencoders (SAEs) is designed to extract the feature series with different spatial resolutions, and a mix-order spatiotemporal module concluding multiple high-order FCMs (HFCMs) is designed to model the spatiotemporal dynamics of these feature series. Finally, the outputs of the two modules are concatenated to predict future values. We refer to this framework as the spatiotemporal FCM (STFCM). Especially, an efficient learning algorithm is designed to update the integral weights of STFCM based on the batch gradient descent algorithm when it deems necessary. We validate the performance of the STFCM on four real-world datasets. Compared with the existing state-of-the-art (SOTA) methods, the experimental results not only show the advantages of the two designed modules in the STFCM but also show the excellent performance of the STFCM.

Premonition-driven deep learning model for short-term ship violent roll motion prediction based on the hull attitude premonition mechanism

Ship transit forecasting can provide advanced movement information to a multidimensional wave motion compensation system. However, traditional deep learning models based on data-driven or physical data have difficulty in accurately predicting the rapid variations in ship motion attitudes that frequently occur in complex ocean environments. Therefore, a premonition-driven deep learning model is proposed in this paper to significantly improve the prediction accuracy of ship violent roll motion. This model applies precursor information to predict premonitory values of ship prospective motion attitudes based on an integrated statistical regression model and then employs these premonitory values to revise the outputs of the deep learning time series model. First, a hull attitude premonition mechanism is presented based on biological premonition cognitive behaviour, which captures the correlation relationships between extreme values by downgrading the globally continuous time series prediction problem to a time-independent regression problem. The corresponding methods for predicting local extreme values and deep feedforward neural network cluster are established based on these correlation relationships between the extreme values to achieve precise premonitory values. Second, the time and amplitude variables of the extreme angle values are transformed to countdown time variables and sequential sets of premonitory angle values. Two types of premonition units and their respective premonitory long short-term memory neural networks are constructed to upgrade the regression problem to a globally continuous time series prediction problem. Finally, a single-step output recurrent strategy is applied to forecast the short-term ship motion attitude for fifteen seconds by considering eleven initially predicted points across the two datasets. In sixty-six simulation experiments, the mean absolute error, root mean squared error, and mean absolute percentage error of the premonition-driven long short-term memory neural networks are considerably lower than those of traditional deep learning models. These simulation experiments verify that the premonition-driven deep learning model can effectively forecast short-term violent ship roll motion and provide safeguards for cargo transfer.

A data-driven implicit deep adaptive neuro-fuzzy inference system capable of manifold learning for function approximation

Fuzzy Neural Networks (FNN) have the ability of decision-making based on constructing semi-ellipsoidal clusters in the input space as the antecedent parts of their fuzzy rules. To determine the output value for each input instance, FNNs consider its membership degree to different sub-regions of the input space. However, forming such meaningful sub-regions is not possible in all applications due to the nonlinear interactions among input variables and their low information gain. Indeed, the samples could be distributed on a manifold in the input space. Therefore, to cover the input space, we need lots of rules, each representing a small region of input space. This issue decreases the generalization ability of the model along with its explainability. Consequently, to efficiently form fuzzy rules, first, it is necessary to unfold the manifold by mapping the samples to an appropriate embedding space. Next, the fuzzy rules in the form of semi-ellipsoidal regions should be constructed in this extracted feature space. Deep Fuzzy Neural Networks address this problem by representation learning through stacking multiple cascade mapping layers. In this paper, we propose a novel approach for nonlinear function approximation and time-series prediction problems, based on using the kernel trick to implicitly learn the mapping function to the new feature space. Moreover, to initialize the fuzzy rules, a KNN-based method using the kernel trick is proposed. A hierarchical Levenberg–Marquardt approach is applied to learn the model’s parameters. The performance and structure of the proposed method are studied and compared with some other relevant methods in synthetic and real-world benchmarks. Based on these experiments, the proposed method has the best performance with the most parsimonious architecture. According to these experiments, the test RMSE of the proposed method is 0.002 for Mc-Glass chaotic time-series prediction, 0.015 for a Nonlinear dynamic system identification, 0.0345 for Box–Jenkins nonlinear system identification, 0.0609 for Fuel consumption prediction of automobiles, 10.24 for Sydney stock price tracking, and 0.595 for California housing.

Predicting the core thermal hydraulic parameters with a gated recurrent unit model based on the soft attention mechanism

Accurately predicting the thermal hydraulic parameters of a transient reactor core under different working conditions is the first step toward reactor safety. Mass flow rate and temperature are important parameters of core thermal hydraulics, which have often been modeled as time series prediction problems. This study aims to achieve accurate and continuous prediction of core thermal hydraulic parameters under instantaneous conditions, as well as test the feasibility of a newly constructed gated recurrent unit (GRU) model based on the soft attention mechanism for core parameter predictions. Herein, the China Experimental Fast Reactor (CEFR) is used as the research object, and CEFR 1/2 core was taken as subject to carry out continuous predictive analysis of thermal parameters under transient conditions., while the subchannel analysis code named SUBCHANFLOW is used to generate the time series of core thermal-hydraulic parameters. The GRU model is used to predict the mass flow and temperature time series of the core. The results show that compared to the adaptive radial basis function neural network, the GRU network model produces better prediction results. The average relative error for temperature is less than 0.5 % when the step size is 3, and the prediction effect is better within 15 s. The average relative error of mass flow rate is less than 5 % when the step size is 10, and the prediction effect is better in the subsequent 12 s. The GRU model not only shows a higher prediction accuracy, but also captures the trends of the dynamic time series, which is useful for maintaining reactor safety and preventing nuclear power plant accidents. Furthermore, it can provide long-term continuous predictions under transient reactor conditions, which is useful for engineering applications and improving reactor safety.

Comparison of Prediction Effectiveness in Deep Learning Perspective of China’s Data Finance

The study has developed a financial time series forecasting model, the Transformer-Encoder model, which utilizes the attention mechanism. This model has been applied to predict the closing price of the Shanghai Stock Exchange (SSE) index, a reliable indicator of financial trends. Furthermore, the study has conducted a comparative analysis, evaluating the performance of our model against other deep learning models, machine learning models, and traditional time series data forecasting models across short, medium, and long-term forecasting periods. Our study has yielded the following key findings: Firstly, the Transformer-Encoder model, leveraging the attention mechanism, demonstrates strong performance in predicting closing prices across short, medium, and long-term periods. This indicates the model’s viability in handling non-stationary financial data and its potential as a forecasting tool applicable to time series prediction problems within the economic sphere. Secondly, compared to alternative deep learning models, machine learning models, and traditional time series data forecasting models, our proposed model consistently outperforms them.

Speech Inpainting Based on Multi-Layer Long Short-Term Memory Networks

Audio inpainting plays an important role in addressing incomplete, damaged, or missing audio signals, contributing to improved quality of service and overall user experience in multimedia communications over the Internet and mobile networks. This paper presents an innovative solution for speech inpainting using Long Short-Term Memory (LSTM) networks, i.e., a restoring task where the missing parts of speech signals are recovered from the previous information in the time domain. The lost or corrupted speech signals are also referred to as gaps. We regard the speech inpainting task as a time-series prediction problem in this research work. To address this problem, we designed multi-layer LSTM networks and trained them on different speech datasets. Our study aims to investigate the inpainting performance of the proposed models on different datasets and with varying LSTM layers and explore the effect of multi-layer LSTM networks on the prediction of speech samples in terms of perceived audio quality. The inpainted speech quality is evaluated through the Mean Opinion Score (MOS) and a frequency analysis of the spectrogram. Our proposed multi-layer LSTM models are able to restore up to 1 s of gaps with high perceptual audio quality using the features captured from the time domain only. Specifically, for gap lengths under 500 ms, the MOS can reach up to 3~4, and for gap lengths ranging between 500 ms and 1 s, the MOS can reach up to 2~3. In the time domain, the proposed models can proficiently restore the envelope and trend of lost speech signals. In the frequency domain, the proposed models can restore spectrogram blocks with higher similarity to the original signals at frequencies less than 2.0 kHz and comparatively lower similarity at frequencies in the range of 2.0 kHz~8.0 kHz.

Simplification of ANFIS based on importance-confidence-similarity measures

Adaptive-network-based fuzzy inference system (ANFIS) is a well-known neuro-fuzzy system, which is widely implemented in nonlinear system approximation, prediction, control, and pattern classification. However, either too many fuzzy sets or fuzzy rules are indispensable to establish an accurate ANFIS for a high-dimensional system, which increases the complexity and limits the widespread application of the ANFIS. In this paper, an approach to simplify the ANFIS is developed based on importance-confidence-similarity (ICS) measures. The simplification process consists of selection of fuzzy rules with large importance-confidence (IC) values and reduction of similar fuzzy rules. The importance is defined as the average normalized firing strength of the rule. The confidence which reflects the approximation performance of a T-S fuzzy rule is estimated by the weighted orthogonal distance from the output data to the rule hyperplane (the consequent of a linear T-S fuzzy rule). The IC measures provide a comprehensive basis for the selection of the appropriate fuzzy rules. Furthermore, to the best of our knowledge, an approach to measure similarities of the T-S fuzzy rules including the rule premises and consequents is first proposed in this paper. We also develop a direct and simple method to remove the similar fuzzy rules based on a hierarchical tree and the IC measures. The proposed simplification approach is applied to Mackey-Glass chaotic time series prediction problem and the strip temperature increment prediction problem of the indirect-fired furnace of the annealing heating line. The results show that our proposed method achieves a balance between simplicity and accuracy of the ANFIS for the high-dimensional system.

Crypto Trend Prediction Based on Wavelet Transform and Deep Learning Algorithm

Crypto currency price prediction is one of the biggest challenges for any prediction system owing to its volatility and dependence on many factors. Artificial intelligence powered by the development of sophisticated computing technology and developments in research has opened up a wide variety of applications and new possibilities to solve complicated problems. Extraction of appropriate features and input with features affecting the output is equally important in time series prediction problems. Wavelet transform is considered an effective method to split a non-stationary signal into uncorrelated components. This work attempts to extract the advantage of wavelets to extract features from an available data set and to predict the trend of the crypto price for next 16 days using the Bi-LSTM network. Historic data of crypto currencies available in Yahoo finance through the yFinance API with the python code is used as the primary data for this work. Due to the gaining importance of SHIB crypto due to its multiplication of value from its start, we have taken SHIB trend analysis as a case study with the use of a data set provided by Yahoo Finance API. The novelty of the proposed system lies largely on the combination of wavelet and deep learning system to improve the performance measures. The proposed systems evaluates the wavelet transform coefficients of the historic data available from the Yahoo Finance API and feed the wavelet transform values to the input of Bi-LSTM network to predict the wavelet transform coefficients for the next 16 days. Finally an inverse wavelet transform is used to get the price of the crypto currency for next 16 days. The results obtained shows that the model was able to estimate the trend in crypto price. The trend analysis shows whether there is an increase or decrease of prices in upcoming days and this could be useful to invest or to withdraw the funds to improve the returns. The proposed scheme resulted in lower Mean Square Error (MSE), Mean Average Error (MAE) and Root Mean Square Error (RMSE) compared with the currently available methods. The method could be useful for trend analysis of other crypto currencies as well. Though it is practically impossible to get the trend analysis from the price and volume history alone, the proposed scheme gives a reasonable estimate of the trend of the crypto price. The work may be extended in future to applications like prediction of agricultural product price, variation in climatic conditions, and availability of certain agricultural products like Onion in the market.