Chaotic Data Research Articles

Guest Editorial of the Special Issue: Multiresolution Analytics for Chaotic and Fractal Data

Guest Editorial of the Special Issue: Multiresolution Analytics for Chaotic and Fractal Data

Prediction of the Remaining Useful Life of Lithium-Ion Battery Using Multilayer Perceptron

Cogitating the reliability of the supply and ensuring continuous delivery of power to the loads, especially in the growing demand for Lithium-Ion batteries in electric vehicle applications, prediction of the remaining useful life of Lithium-Ion batteries is crucial for the timely replacement. For prediction of non-linear and chaotic relationship, experience-based approach, physics-based approach and data driven approach are used among which data driven approach is a model free, accurate and reliable approach. Therefore, a driven approach in predicting remaining useful life can be implemented in the battery management system. This research uses a multilayer perceptron to predict the remaining useful life of the battery. The NASA Ames Prognostics Center of Excellence (PCoE) battery dataset is used to test the proposed methodology. The use of multilayer perceptron for remaining life prediction seems promising despite the significant number of jump points, gaps in data and a small quantity of experimental data in the National Aeronautics and Space Administration (NASA) dataset. The predicted result was obtained with 8.52 % mean absolute error and 9.59 % root mean square error. When compared with the predicted results of different literatures, proposed multilayer perceptron with sliding window approach outperforms most of the existing approach. Incorporation of optimization techniques and hybrid algorithm in proposed approach can further enhance the accuracy of the model.

Matryoshka multistability: Coexistence of an infinite number of exactly self-similar nested attractors in a fractal phase space

Multistability, and its special types such as megastability and extreme multistability, is an important phenomenon in modern nonlinear science that provides several possible practical applications. In this paper, we propose a new special type of multistability when the infinite number of exactly self-similar attractors nested inside each other coexist in a system. We called it matryoshka multistability due to its resemblance to the famous Russian wooden doll. We theoretically explain and experimentally confirm the properties of a new type of multistable behavior using two representative examples based on the Chua and Sprott Case J chaotic systems. In addition, we construct an adaptive controller for synchronizing two Chua-type matryoshka multistable systems when the amplitude of the master system is of arbitrary scale. The proposed type of multistability can find several applications in chaotic communication, cryptography, and data compression.

Reservoir computing based encryption-then-compression scheme of image achieving lossless compression

Image encryption-then-compression (ETC), combining encryption and compression techniques, is a powerful strategy for image privacy protection. One of the most significant concerns in ETC is to realize a trade-off between high compression and high-quality recovery. To this end, we propose a novel ETC scheme based on a ring-network optical dynamic system and a reservoir computing (RC) system. This optical dynamics system is newly constructed by using three QD spin-VCSELs, then the optical RC system is further specifically designed. To ensure security, we develop a secret key generation method, which involves jointly injecting the original image and chaotic data into the RC system for chaotic transformation to produce high-security secret keys. In our scheme, the original image is first encrypted through scrambling and diffusion using the generated keys, then the obtained encrypted image is segmented into multiple sub-blocks, followed by using uniform down-sampling to select data, the unsampled data will be discarded and the sampled data is to be retained as the resulting compressed image. Flexible compression ratio can be achieved by varying sub-block sizes, with larger sub-blocks yielding higher compression. To realize high-quality recovery, the relationship between the compressed image and the discarded data is constructed in a learning manner by means of the designed RC system, which is conducive to the reconstruction process, resulting in lossless recovery. This work can effectively overcome the limitations of existing schemes in terms of simultaneously achieving both well-performing compression and lossless reconstruction. Experimental results are given which demonstrate the high security and superior performance of the proposed scheme.

A spatiotemporal chaos based deep learning model watermarking scheme

With deep learning techniques achieving great results in modern industry, the intellectual property (IP) protection for deep learning models has attracted the attention of academics and engineers. However, training a commercially viable deep learning model usually needs professional resources and time. Once a malicious user clones, illegally distributes and uses the model, it can infringe on the model owner's IP and even steal its market share. Among the existing IP protection methods, scholars prefer the black-box watermarking approaches, of which the content of the trigger set and the label are the key part of the watermarking technique. However, most schemes do not consider the security and invisibility of the trigger set, which allows attackers to easily trigger the model by creating a fake trigger set, thereby committing a fraudulent ownership claim attack and claiming the ownership belongs to themselves. To overcome these drawbacks, we proposed a spatiotemporal chaotic data annotation method. Firstly, the unpredictability and acyclicity of chaos make the model resistant to fraudulent ownership claim attacks, statistical inference and other common machine learning attacks; Secondly, the trigger set and parameters are independent of each other, guaranteeing the security of the key; Thirdly, the spatiotemporal chaotic system provides a large key space, which meets the commercialization needs of deep learning models. Theoretical analysis and experimental results show that our scheme has security, practicality and robustness. To further validate the superiority of the proposed method, we also compare it with the Logistic chaotic annotation watermarking-based method, and the results show that our method performs better in terms of robustness, effectiveness, completeness, fidelity, security and practicality.

High-Speed Optical Chaotic Data Selection Logic Operations with the Performance of Error Detection and Correction

High-Speed Optical Chaotic Data Selection Logic Operations with the Performance of Error Detection and Correction

Predictive analysis of stochastic stock pattern utilizing fractional order dynamics and heteroscedastic with a radial neural network framework

Modelling of high-dimension chaotic, noisy, and non-stationary time series of complex fractal dynamics is a big challenge. In this research work, a novel approach of Leverage Convolution LC ARFIMA– GARCH model is presented for sequential learning of irregular, fractal dynamic patterns of stochastic time series dynamics. Different classical methods including the auto-regressive approach indecently are unable to capture fragile patterns and consequently convert some weak signals into random errors by creating white noise patterns. The Convolution Leverage provides an additional degree of freedom for critical noisy points and asymmetrical distribution dynamics to regulate the frequency of imbalance and skewed observation. The designed transformation in the ARFIMA model preserves the loss of information by shifting the skewed data distribution toward a normal pattern. The pattern of population parameters in the proposed leverage paradigm provides out of box approach to track and extract additional information on population variance patterns in the form of an additional degree of freedom to stabilize imbalance signals. The model can provide reliable performance for long-range dependence, particularly for mean reversion chaotic phase variation at critical non-differentiable points. The performance of the dynamic model is verified on chaotic real data of the Ireland Stock Market (ISEQ). The result statistics confirmed the optimized outcome with the addition of the GARCH heteroscedastic multimodal and radial basis neural network. The novel technique can help to address inherited challenges in the imbalance learning and extreme events of the time series modeling by monitoring the chaotic trajectory of fractal physical phenomena, particularly in, finance healthcare, climate, and intelligent sustainability.

Support vector machine-based stock market prediction using long short-term memory and convolutional neural network with aquila circle inspired optimization

ABSTRACT Predicting the stock market is one of the significant chores and has a successful prediction of stock rates, and it helps in making correct decisions. The prediction of the stock market is the main challenge due to blaring, chaotic data as well as non-stationary data. In this research, the support vector machine (SVM) is devised for performing an effective stock market prediction. At first, the input time series data is considered and the pre-processing of data is done by employing a standard scalar. Then, the time intrinsic features are extracted and the suitable features are selected in the feature selection stage by eliminating other features using recursive feature elimination. Afterwards, the Long Short-Term Memory (LSTM) based prediction is done, wherein LSTM is trained to employ Aquila circle-inspired optimization (ACIO) that is newly introduced by merging Aquila optimizer (AO) with circle-inspired optimization algorithm (CIOA). On the other hand, delay-based matrix formation is conducted by considering input time series data. After that, convolutional neural network (CNN)-based prediction is performed, where CNN is tuned by the same ACIO. Finally, stock market prediction is executed utilizing SVM by fusing the predicted outputs attained from LSTM-based prediction and CNN-based prediction. Furthermore, the SVM attains better outcomes of minimum mean absolute percentage error; (MAPE) and normalized root-mean-square error (RMSE) with values about 0.378 and 0.294.

Comparative Analysis of Weather Forecasting Using LSTM, BiLSTM, and CLSTM Networks

Weather prediction plays vital role in the evaluation of various processes and phenomenon for the betterment of society. Weather forecasting depends on many parameters hence, it’s a multivariable prediction problem. Behavior of data involved in the prediction are in majority of time stochastics hence, conventional mathematical approaches are failed to predict accurate data. Classical computational methods fail in predicting chaotic data due to its limitation to have know-how about behavior of data. Artificial Intelligence and Data Processing techniques is appealing investigators due to its efficiency to predict data based on its learning capability, without any know-how about the behavior of data. In this paper, Artificial Intelligence based approach LSTM, BiLSTM, and CLSTM are used to predict time series weather data prediction. Data considered are Pressure, Humidity, Temperature, and Maximum wind speed as input data. Neural Network based approaches are used to predict Average wind speed based on above inputs. The performance of above Artificial based approaches is compared to predict time series Average wind speed. MATLAB is used as software tool to implement Artificial Intelligence approaches. It has been observed that CLSTM algorithm outperformed other two algorithms LSTM and BiLSTM algorithm.

Stock Market Prediction and Visualisation

Abstract: Stock price forecasting is a widely discussed and significant topic in both financial and academic circles. The stock market is inherently unpredictable, lacking clear rules for estimating or predicting share prices. Various methods, including technical analysis, fundamental analysis, time series analysis, and statistical analysis, have been employed to forecast stock prices. However, none of these methods consistently serve as reliable prediction tools. In this paper, we explore the implementation, prediction, and analysis of stock market prices. Artificial Neural Networks and Machine Learning prove effective for forecasting stock prices, returns, and modeling stock behavior. By conducting statistical analyses, we establish relationships between selected factors and share prices, contributing to more accurate predictions. While the stock market remains inherently uncertain, this paper aims to apply data analysis and prediction concepts to forecast stock prices. In the era of global digitization, stock market prediction has undergone significant technological advancements, transforming traditional trading models. As market capitalization continues to rise, stock trading becomes a focal point for financial investors. Analysts and researchers have developed tools and techniques to predict stock price movements, aiding decision-making. Advanced models leverage non-traditional textual data from social platforms for market prediction. Machine learning approaches, including text data analytics and ensemble methods, have significantly improved prediction accuracy. However, analyzing and predicting stock markets remains challenging due to dynamic, erratic, and chaotic data. This study explores machine learning-based approaches for stock market prediction, emphasizing a generic framework. By critically analyzing findings from the last decade (2011–2021) from digital libraries like ACM and Scopus, we provide insights for emerging researchers to delve into this promising area.

Diabetes Mellitus prediction using Improved Chaotic Whale Optimization and Data mining techniques

Automation of disease detection is now prevalent in healthcare systems. Diabetes mellitus is a serious issue that has become prominent worldwide. It is a hereditary illness that impairs human existence at every stage of development. Each year, millions more people develop diabetes, which also has an impact on young people. Currently, the medical industry is shifting toward automation, as the process of identifying diseases needs periodic human verification. A single model for diabetes prediction is insufficient for complicated problems since it might not be appropriate for training huge data. In this proposed approach, a novel method which combines the outcomes of more than one algorithm is suggested. An ensemble approach using data mining techniques such as Decision Trees, Random Forests, AdaBoost, Gradient Boosting and XGBoost is employed to predict diabetes mellitus. Feature selection methods such as Averaged Fisher score and Kolmogorov-Smirnov score are used to choose the prominent characteristics from PIMA Indian Diabetes dataset. Further, the most optimal features are selected using Improved Chaotic Whale Optimization algorithm. The proposed approach produces predictions that are 98.8% accurate and reliable.

Financial Crisis Prediction and Stock Market Analysis: A Systematic Review

Abstract: It is common known that attempting to foresee the movements of the stock market is a huge task that calls for a great lot of focus and concentration. Because of this, precisely predicting stock prices might potentially result in attractive rewards if the necessary decisions are made. This is the reason why this is the case. The non-stationary, noisy, and chaotic data that is accessible makes it difficult to generate correct forecasts about the stock market. This is because accurate predictions are difficult to produce. Because of this, it is difficult for investors to generate accurate forecasts in order to invest their money and earn a return from their investments. Various strategies are developed within the framework of the existing methodologies in order to forecast stock market movements. An overview of research articles arguing for different approaches is the goal of this study. In addition to being great academic publications, these research articles provide calculation methodologies, machine learning algorithms, performance factors, and other information. To address this recognized need, this study attempts to provide a comprehensive and current evaluation of the stock market forecasting approaches now in use. This research will include the categorization, analysis, and comparison of various approaches. In the end, the process of training and testing the model is evaluated using machine learning models. Based on the data, it is abundantly evident that logistic regression is better than any other approach that is presently being used.

Empirical analysis of Deep Learning Models in forecasting Chaotic Time series data

Empirical analysis of Deep Learning Models in forecasting Chaotic Time series data

Dynamic adaptive graph convolutional transformer with broad learning system for multi-dimensional chaotic time series prediction

Chaotic time series data is extensively applied in financial stocks, climate monitoring, and sea clutter, in which data fusion from various sources and multi-sensor information make accurate predictions of chaotic time series challenging under complex nonlinear conditions. Previous works focus on designing different model frameworks to capture the temporal dependence and extract richer nonlinear features to improve the accuracy of univariate chaotic time series prediction, which ignores the spatial dependence of multivariable. However, in this paper, we argue that spatial correlation among multiple variables is essential to improve the prediction accuracy of chaotic time series. To fill the gap, we innovatively propose a Dynamic Adaptive Graph Convolutional Transformer with a Broad Learning System (DAGCT-BLS), a GCN and Transformer-based model utilizing multivariate spatial dependence for multi-dimensional chaotic time series forecasting. In DAGCT-BLS, the multivariate chaotic time series are reconstructed into the phase space, and the reconstructed data are rapidly feature-extracted using a cascade network BLS with frozen weights to maximize the retention of chaotic properties and nonlinear relationships. Then, the Dynamic Adaptive Graph Convolutional Network (DAGCN) is proposed to capture the spatial correlation among the multiple variables. Finally, improved multi-head attention of the Transformer Encoder is used to capture the temporal dependence of the phase point sequence. Experiments of our proposed model on three datasets (Lorenz, Rossler, and Sea clutter) show that DAGCT-BLS can achieve the best prediction performance and have strong interpretability, and multivariate-based joint modeling of chaotic time series helps to improve the prediction performance.

Exploring Latent Dirichlet Allocation (LDA) in Topic Modeling: Theory, Applications, and Future Directions

In an era dominated by an unprecedented deluge of textual information, the need for effective methods to make sense of large datasets is more pressing than ever. This article takes a pragmatic approach to unraveling the intricacies of topic modeling, with a specific focus on the widely used Latent Dirichlet Allocation (LDA) algorithm. The initial segment of the article lays the groundwork by exploring the practical relevance of topic modeling in real-world scenarios. It addresses the everyday challenges faced by researchers and professionals dealing with vast amounts of unstructured text, emphasizing the potential of topic modeling to distill meaningful insights from seemingly chaotic data. Moving beyond theoretical abstraction, the article then delves into the mechanics of Latent Dirichlet Allocation. Developed in 2003 by Blei, Ng, and Jordan, LDA provides a probabilistic framework to identify latent topics within documents. The article takes a step-by-step approach to demystify LDA, offering a practical understanding of its components and the Bayesian principles governing its operation. A significant portion of the article is dedicated to the practical implementation of LDA. It provides insights into preprocessing steps, parameter tuning, and model evaluation, offering readers a hands-on guide to applying LDA in their own projects. Real-world examples and case studies showcase how LDA can be a valuable tool for tasks such as document clustering, topic summarization, and sentiment analysis. However, the journey through LDA is not without challenges, and the article candidly addresses these hurdles. Topics such as determining the optimal number of topics, the sensitivity of results to parameter settings, and the interpretability of outcomes are discussed. This realistic appraisal adds depth to the article, helping readers navigate the nuances and potential pitfalls of employing LDA in practice. Beyond the technical intricacies, the article explores the broad spectrum of applications where LDA has proven its efficacy. From text mining and information retrieval to social network analysis and healthcare informatics, LDA has left an indelible mark on diverse domains. Through practical examples, the article illustrates how LDA can be adapted to different contexts, showcasing its versatility as a tool for uncovering latent patterns. Keywords: Topic Modeling, Latent Dirichlet Allocation, Text Mining, Natural Language Processing, Document Clustering, Bayesian Inference.

Parallel multivariate deep learning models for time-series prediction: A comparative analysis in Asian stock markets

<span lang="EN-US">This study investigates deep learning models for financial data prediction and examines whether the architecture of a deep learning model and time-series data properties affect prediction accuracy. Comparing the performance of convolutional neural network (CNN), long short-term memory (LSTM), Stacked-LSTM, CNN-LSTM, and convolutional LSTM (ConvLSTM) when used as a prediction approach to a collection of financial time-series data is the main methodology of this study. In this instance, only those deep learning architectures that can predict multivariate time-series data sets in parallel are considered. This research uses the daily movements of 4 (four) Asian stock market indices from 1 January 2020 to 31 December 2020. Using data from the early phase of the spread of the Covid-19 pandemic that has created worldwide economic turmoil is intended to validate the performance of the analyzed deep learning models. Experiment results and analytical findings indicate that there is no superior deep learning model that consistently makes the most accurate predictions for all states' financial data. In addition, a single deep learning model tends to provide more accurate predictions for more stable time-series data, but the hybrid model is preferred for more chaotic time-series data.</span>

Innovative Deep Learning Strategies for Chaotic Data Classification: A Multi-Algorithm Comparison in the Presence of Noise

Chaos is prevalent in both nature and science, appearing in data, time series and complex systems. Chaotic systems exhibit numerous uncertainties, akin to noise, which challenge researchers to distinguish or analyze potential underlying patterns or even identify the type of system involved. However, determining the kind of chaotic system is essential, as it enables prediction, synchronization, control, treatment and application. This study employs machine learning to classify chaotic data through a simulation involving three types of research data: Lorenz data, Lorenz combined with Gaussian white noise, Gaussian white noise and pink noise, utilizing six distinct algorithms. The most effective testing results are achieved using Mobilenet, with a classification accuracy of 97.38% and a loss of 0.2680 across these six data types.

Functional data learning using convolutional neural networks

In this paper, we show how convolutional neural networks (CNNs) can be used in regression and classification learning problems for noisy and non-noisy functional data (FD). The main idea is to transform the FD into a 28 by 28 image. We use a specific but typical architecture of a CNN to perform all the regression exercises of parameter estimation and functional form classification. First, we use some functional case studies of FD with and without random noise to showcase the strength of the new method. In particular, we use it to estimate exponential growth and decay rates, the bandwidths of sine and cosine functions, and the magnitudes and widths of curve peaks. We also use it to classify the monotonicity and curvatures of FD, the algebraic versus exponential growth, and the number of peaks of FD. Second, we apply the same CNNs to Lyapunov exponent estimation in noisy and non-noisy chaotic data, in estimating rates of disease transmission from epidemic curves, and in detecting the similarity of drug dissolution profiles. Finally, we apply the method to real-life data to detect Parkinson’s disease patients in a classification problem. We performed ablation analysis and compared the new method with other commonly used neural networks for FD and showed that it outperforms them in all applications. Although simple, the method shows high accuracy and is promising for future use in engineering and medical applications.

An Analytic Review on Stock Market Price Prediction using Machine Learning and Deep Learning Techniques

: Anticipating stock market trends is a challenging endeavor that requires a lot of attention because correctly predicting stock prices can lead to significant rewards if the right judgments are made. Due to non-stationary, loud, and chaotic data, stock market prediction is challenging. Investors need help to forecast where they should spend their money to make a profit. Investment methods in the stock market are intricate and based on the analysis of large datasets. Expert analysts and investors have placed a high value on developments in stock price prediction. Due to intrinsically noisy settings and increased volatility concerning market trends, the stock market forecast for assessing trends is tricky. The intricacies of stock prices are influenced by several elements, including quarterly earnings releases, market news, and other altering habits. Traders use a number of technical indicators based on stocks that are collected on a daily basis to make decisions. Even though these indicators are used to analyze stock returns, predicting daily, and weekly market patterns are difficult. Machine learning techniques have been extensively studied in recent years to see if they might boost market predictions compared to legacy or conventional methods. The existing methodologies have devised several strategies for predicting stock market trends. Various machine learning and deep learning algorithms, such as SVM, DT, LR, NN, kNN, ANN, and CNN, can boost performance in predicting the stock market. Based on a survey of current literature, this work aims to identify future directions for machine learning stock market prediction research. This research aims to provide a systematic literature review process to discover relevant peer-reviewed journal papers from the last two decades and classify studies with similar methods and situations into the machine learning approach and deep learning. In the current article, the methods and the performance of those adopted methods will be identified for measuring the effectiveness of those techniques.

Optimisation-Enabled Transfer Learning Framework for Stock Market Prediction

Stock market prediction is a vital task with high attention for gaining attractive profits with proper decisions to invest. Predicting the stock market is becoming a major challenge nowadays due to chaotic data, non-stationary data, and blaring data. Hence, it’s challenging for investors to invest money to make profits. Many techniques are developed to predict stock market trends, but each differs based on time and year. In this paper, hybridised optimisation algorithm, namely the proposed Gannet Ladybug Beetle Optimisation (GLBO), is used for training Transfer Learning (TL), which considers Convolutional Neural Network-enabled Long Short-Term Memory (CNN-enabled LSTM). This TL is responsible for predicting the stock market from augmented data. Here, the stock market dataset of two companies is used as input time series data. Moreover, many features are extracted from those input data and then from those features, necessary features are selected based on Motyka similarity. The bootstrap method is used in this paper for data augmentation. Also, GLBO is hybridised with Gannet Optimisation Algorithm (GOA) along Ladybug Beetle Optimisation (LBO) algorithm. Furthermore, the proposed model is verified for its performance capability based on three metrics, Mean Squared Error (MSE), Root Mean Squared Error (RMSE), as well as Mean Absolute Percentage Error (MAPE) with values of 5.8%, 24.1%, and 78.8%.