Time Series Data Research Articles

Comparative analysis of ARIMA and LSTM for predicting fluctuating time series data

The investigation of time series data forecasting is a critical topic within the realms of economics and business. The autoregressive integrated moving average (ARIMA) model has been prevalently utilized, notwithstanding its limitations, which include the necessity for a substantial quantity of data points and the presumption of data linearity. However, with recent developments, the long short-term memory (LSTM) network has emerged as a promising alternative, potentially overcoming these limitations. The objective of this study is to determine an effective approach for managing time series data characterized by volatility and missing values. Evaluation was conducted using RMSE for accuracy assessment, and the execution time measured using the Python Timeit library. The findings indicates that in a dataset comprising 60 data points, the LSTM model (RMSE 0.037618) surpasses the ARIMA model (RMSE 0.062667) in terms of accuracy. However, this trend reverses in a larger dataset of 228 data points, where the ARIMA model demonstrates superior accuracy (RMSE 0.006949) compared to the LSTM model (RMSE 0.036025). In scenarios with missing data, the LSTM model consistently outperforms the ARIMA model, although the accuracy of both models diminishes with an increase in the number of missing values. The ARIMA model significantly outpaces the LSTM model.

Mix-method toolbox for monitoring greenhouse gas production and microbiome responses to soil amendments

In this study, we adopt an interdisciplinary approach, integrating agronomic field experiments with soil chemistry, molecular biology techniques, and statistics to investigate the impact of organic residue amendments, such as vinasse (a by-product of sugarcane ethanol production), on soil microbiome and greenhouse gas (GHG) production. The research investigates the effects of distinct disturbances, including organic residue application alone or combined with inorganic N fertilizer on the environment. The methods assess soil microbiome dynamics (composition and function), GHG emissions, and plant productivity. Detailed steps for field experimental setup, soil sampling, soil chemical analyses, determination of bacterial and fungal community diversity, quantification of genes related to nitrification and denitrification pathways, measurement and analysis of gas fluxes (N2O, CH4, and CO2), and determination of plant productivity are provided. The outcomes of the methods are detailed in our publications (Lourenço et al., 2018a; Lourenço et al., 2018b; Lourenço et al., 2019; Lourenço et al., 2020). Additionally, the statistical methods and scripts used for analyzing large datasets are outlined. The aim is to assist researchers by addressing common challenges in large-scale field experiments, offering practical recommendations to avoid common pitfalls, and proposing potential analyses, thereby encouraging collaboration among diverse research groups.•Interdisciplinary methods and scientific questions allow for exploring broader interconnected environmental problems.•The proposed method can serve as a model and protocol for evaluating the impact of soil amendments on soil microbiome, GHG emissions, and plant productivity, promoting more sustainable management practices.•Time-series data can offer detailed insights into specific ecosystems, particularly concerning soil microbiota (taxonomy and functions).

Utility-Aware Time Series Data Release With Anomalies Under TLDP

Utility-Aware Time Series Data Release With Anomalies Under TLDP

Path to clean and sustainable energy from nuclear and renewable sources: Evidence from France

France is one of the countries that have made commendable progress towards accomplishing sustainable development goals but still struggles with combating environmental challenges. Decarbonizing the energy sector by deploying clean energy and reducing fossil fuels in the energy mix are essential steps. The study uses annual time series data from 1980 to 2021 and employs the ridge regression estimation technique to estimate a twice-differentiable transcendental production function, which approximates the second-order Taylor series to explore the potential for such decarbonization for France. The study finds that substitution possibilities exist between clean energy and fossil fuels, with substantial substitution possibilities coming from nuclear energy. Nuclear energy and renewables are found to be complements that can be deployed concurrently, but since nuclear energy already constitutes a significant proportion of clean energy for France, the study recommends increasing the proportion of renewable energy in the overall energy mix as the most plausible path to decarbonization. Other complementary sustainable energy policies are recommended in the body of the paper.

Study the impact of renewable and non-renewable energy sources on micro-grid using time series data based information transfer

This paper addresses the challenges arising from the integration of renewable energy sources into microgrids, focusing on the impact on system dynamics and stability. Employing an advanced time series-based information transfer approach, the study identifies critical parameters influencing system instability under small perturbations. Unlike traditional methods, this technique effectively analyzes information flow and interactions within the complex system, providing insights into the influence of states on different operating modes. The study specifically investigates the disturbance caused by increased load demand and employs a three-layered small signal stability index to pinpoint crucial system-affecting parameters. Subsequently, Distributed Generation (DG) units are strategically placed to restore stability, guided by the identified critical parameters. The proposed approach is validated on IEEE 3 Bus and IEEE 39 Bus systems, demonstrating its effectiveness and outperforming existing methodologies in predicting and addressing system uncertainties. These systems experienced instability as a result of an introduced disturbance in the form of increased load, affecting the dynamics of the generator at the immediate bus. To enhance the generator dynamics and address the impact of the disturbance, a new DG unit was introduced to provide support. The DG unit was placed at the bus which was deduced to be most critical from the three-layered small signal stability.

Assessing the Impact of Seasonal Decomposition on the Time Series Analysis Accuracy: A Comprehensive Study

Abstract: Time series forecasting plays a pivotal role in decision-making across various domains, ranging from finance to healthcare and weather prediction. The accurate prediction of future values in a time series is vital for informed planning and resource allocation. The aim of this study is to explore whether the utilization of seasonal decomposition techniques, such as classical decomposition, X-12-ARIMA, and seasonal decomposition of time series (STL), can improve the effectiveness of time series forecasting models by separating the data into its distinct components, including trend and seasonality. We conduct a comprehensive analysis using real-world time series data, employing popular forecasting models like ARIMA, exponential smoothing, and machine learning-based approaches. By comparing the forecasting accuracy of these models with and without the application of seasonal decomposition techniques, we provide empirical evidence to support the hypothesis. Our research results provide valuable insights into the tangible ad- vantages of integrating seasonal decomposition techniques in time series forecasting, potentially contributing to enhanced decision support systems across diverse application domains.

Analysing impact of corporate attributes on sustainability disclosures through India’s new BRSR framework

Purpose The purpose of this study is to analyse the impact of corporate attributes like a company’s profitability, size, age, leverage and board size on companies’ sustainability reporting as measured through India’s new business responsibility and sustainability reporting (BRSR) framework. Design/methodology/approach A random sample of 130 companies was taken from the top 1,000 listed companies on the National Stock Exchange. Sequential mixed methods research approach was used to prepare a sustainability quality index. Then, a hierarchical multiple regression analysis was performed to examine the impact on the quality of reporting by Indian companies. Findings Interestingly, the analysis revealed that traditional metrics like age, profitability, board size and leverage did not have significant associations with reporting quality. Rather, the size of a company in terms of market capitalisation was found to have a strong positive impact on sustainability reporting. Research limitations/implications This was a cross-sectional study, as time series data for BRSR reporting is not yet available. Also, only five parameters were taken for analysis. Lastly, subjective judgment in content analysis may be involved. Practical implications This suggests that only larger companies in India are prioritising sustainability reporting over smaller ones. It affirms the legitimacy and stakeholder theory in the Indian context. Originality/value To the best of the authors’ knowledge, this study is one of the first endeavours to assess the efficacy of the new Indian BRSR framework and test its primary objectives. Furthermore, significant implications have been given for managers to catalyse and reinforce the sustainability momentum down the lane across companies of all sizes in India.

Persistence of fisheries production: a disaggregated analysis in 31 OECD Countries

Previous studies have focussed on different aspects of fisheries production in several countries. However, the literature has been largely silent on the persistence of fisheries production, which has numerous important policy implications. In this article, we examine time series data corresponding to fisheries production in a group of 31 OECD countries. The analysis focuses on three distinct production series for each country: total fisheries production, aquaculture production, and capture fisheries production, and the time period spans from 1960 to 2020. Using fractional integration methods, the empirical findings provide evidence for persistence in fisheries production and its two components in the majority of the OECD countries examined. Persistence is observed in 29 countries in the case of the total fisheries production, 28 countries in the case of capture fisheries production, and 28 countries in the case of aquaculture production. Evidence of mean reversion is observed in Chile and Colombia for the total fisheries production, and in Belgium, Colombia, and Israel for the capture fisheries production. There is support for mean reversion in aquaculture production data for France, the Netherlands and Poland. An implication of the results is that shocks to the fisheries production or its components are permanent or long-term in nature. Therefore, long-term measures are need to address any disruptions in the fishery sector.

Unraveling Financial Markets: Deep Neural Network-Based Models for Stock Price Prediction

This paper delves into the potential and challenges of leveraging deep neural networks (DNNs) in stock price forecasting. Traditional econometric models often grapple with the complexities of financial time series data, leading to the exploration of DNNs, especially architectures like Long Short-Term Memory (LSTM) networks, to capture intricate patterns in such data. While these networks present promising results, challenges such as model interpretability, non-stationarity of data, overfitting, and computational demands remain. The financial sector's increasing digitization and influx of alternative data offer a unique opportunity for DNNs, emphasizing their capability for automatic feature extraction. However, the integration of DNNs necessitates a multi-disciplinary approach, involving financial experts, data scientists, and computational specialists. The paper concludes with an optimistic outlook for the synergy between deep learning and traditional financial theories, aiming for a harmonious blend of modern computational techniques with foundational financial principles.

Population Aging, Housing Price, and Household Consumption

Population aging and housing price can affect household consumption, and population aging can indirectly affect household consumption through housing price. This study uses panel data from 31 provinces and cities in China between 2001 and 2018 to construct a panel vector autoregression model for analyzing the impact of population aging and housing price on household consumption level. We determine that population aging and housing price positively impact household consumption level, and population aging also has a positive effect on housing price. The mediating effect model using time series data from 2001 to 2018, with housing price as the mediating variable reveals that population aging directly increases household consumption level, and indirectly increases it through housing price. Finally, this study proposes suggestions such as optimizing the population structure, improving the housing system, and advancing the development of the older adult industry.

Number of Cyber Attacks Predicted With Deep Learning Based LSTM Model

The increasing number of cyber attacks will result in various damages to the functioning of technological infrastructure. A prediction model for the number of cyber attacks based on the type of attack, handling actions and severity using time-series data has never been done. A deep learning-based LSTM prediction model is proposed to predict the number of cyberattacks in a time series on 3 evaluated data sets MSLE, MSE, MAE, RMSE, and MAPE, and displays the predicted relationships between prediction variables. Cyber attack dataset obtained from kaggle.com. The best prediction model is epoch 20, batch size 16, and neuron 32 with the lowest evaluation value on MSLE of 0.094, MSE of 9.067, MAE of 2.440, RMSE of 3.010, and MAPE of 10.507 (very good model because the value is less than 15) compared other variations. There is a negative correlation for INTRUSION-MALWARE, BLOCKED-IGNORED, IGNORED-LOGGED, and LOW-MEDIUM. The predicted results for the next 12 months will increase starting from the second month at the same time. The resulting predictions can be used as a basis for policy and strategy decisions by stakeholders in dealing with fluctuations in cyber attacks that occur.

Effect of Different Measurement Tasks on the Frequency of Microsaccades

In recent years, several attempts have been made to quantitatively evaluate covert attention using microsaccades. However, several unclear aspects exist regarding the measurement method of microsaccades, and a unified analysis method does not exist. Therefore, the current status is such that the interpretation of the results is divided among the research groups. To address this problem, empirical studies on microsaccades must be accumulated and measured and evaluated using a unified method. Therefore, in this study, to accumulate empirical studies on microsaccades, an experiment was conducted to investigate the effect of the presence or absence of gazing at a fixation point on the interval of occurrence of microsaccades in a measurement task. The participants were 15 healthy young people, and we compared the following two types of measurement tasks. Task-I: The participants freely visually searched a white wall 1 m away for 120 s. Task-II: The participants gazed at a fixation point located 1 m ahead at eye level for 120 s. For the microsaccade detection algorithm, we adopted a method imitating the EK method proposed by Engbert and Kliegl in 2003, divided 120 s of time-series data and analyzed it every 2 s, and subsequently evaluated the time-series data for the entire 120 s by concatenating them. Consequently, the interval of occurrence of microsaccades during Task-II decreased by more than 1 Hz compared with that of Task-I (p<0.05). The study confirmed that the presence or absence of gazing at the fixation point during microsaccade measurement affected the interval of occurrence of microsaccades.

Using Wearable Skin Temperature Data to Advance Tracking and Characterization of the Menstrual Cycle in a Real-World Setting.

The menstrual cycle is a loop involving the interplay of different organs and hormones, with the capacity to impact numerous physiological processes, including body temperature and heart rate, which in turn display menstrual rhythms. The advent of wearable devices that can continuously track physiological data opens the possibility of using these prolonged time series of skin temperature data to noninvasively detect the temperature variations that occur in ovulatory menstrual cycles. Here, we show that the menstrual skin temperature variation is better represented by a model of oscillation, the cosinor, than by a biphasic square wave model. We describe how applying a cosinor model to a menstrual cycle of distal skin temperature data can be used to assess whether the data oscillate or not, and in cases of oscillation, rhythm metrics for the cycle, including mesor, amplitude, and acrophase, can be obtained. We apply the method to wearable temperature data collected at a minute resolution each day from 120 female individuals over a menstrual cycle to illustrate how the method can be used to derive and present menstrual cycle characteristics, which can be used in other analyses examining indicators of female health. The cosinor method, frequently used in circadian rhythms studies, can be employed in research to facilitate the assessment of menstrual cycle effects on physiological parameters, and in clinical settings to use the characteristics of the menstrual cycles as health markers or to facilitate menstrual chronotherapy.

Widespread seawater intrusions beneath the grounded ice of Thwaites Glacier, West Antarctica

Warm water from the Southern Ocean has a dominant impact on the evolution of Antarctic glaciers and in turn on their contribution to sea level rise. Using a continuous time series of daily-repeat satellite synthetic-aperture radar interferometry data from the ICEYE constellation collected in March-June 2023, we document an ice grounding zone, or region of tidally controlled migration of the transition boundary between grounded ice and ice afloat in the ocean, at the main trunk of Thwaites Glacier, West Antarctica, a strong contributor to sea level rise with an ice volume equivalent to a 0.6-m global sea level rise. The ice grounding zone is 6 km wide in the central part of Thwaites with shallow bed slopes, and 2 km wide along its flanks with steep basal slopes. We additionally detect irregular seawater intrusions, 5 to 10 cm in thickness, extending another 6 km upstream, at high tide, in a bed depression located beyond a bedrock ridge that impedes the glacier retreat. Seawater intrusions align well with regions predicted by the GlaDS subglacial water model to host a high-pressure distributed subglacial hydrology system in between lower-pressure subglacial channels. Pressurized seawater intrusions will induce vigorous melt of grounded ice over kilometers, making the glacier more vulnerable to ocean warming, and increasing the projections of ice mass loss. Kilometer-wide, widespread seawater intrusion beneath grounded ice may be the missing link between the rapid, past, and present changes in ice sheet mass and the slower changes replicated by ice sheet models.

ABCD4 is associated with mammary gland development in mammals.

Mammary gland development is a critical process in mammals, crucial for their reproductive success and offspring nourishment. However, the functional roles of key candidate genes associated with teat number, including ABCD4, VRTN, PROX2, and DLST, in this developmental process remain elusive. To address this gap in knowledge, we conducted an in-depth investigation into the dynamic expression patterns, functional implications, and regulatory networks of these candidate genes during mouse mammary gland development. In this study, the spatial and temporal patterns of key genes were characterized in mammary gland development. Using time-series single-cell data, we uncovered differences in the expression of A bcd4, Vrtn, Prox2, and Dlst in cell population of the mammary gland during embryonic and adult stages, while Vrtn was not detected in any cells. We found that only overexpression and knockdown of Abcd4 could inhibit proliferation and promote apoptosis of HC11 mammary epithelial cells, whereas Prox2 and Dlst had no significant effect on these cells. Using RNA-seq and qPCR, further analysis revealed that Abcd4 can induce widespread changes in the expression levels of genes involved in mammary gland development, such as Igfbp3, Ccl5, Tlr2, and Prlr, which were primarily associated with the MAPK, JAK-STAT, and PI3K-AKT pathways by functional enrichment. These findings revealed ABCD4 as a candidate gene pivotal for regulating mammary gland development and lactation during pregnancy by influencing PRLR expression.

Integrating gated recurrent unit in graph neural network to improve infectious disease prediction: an attempt

ObjectiveThis study focuses on enhancing the precision of epidemic time series data prediction by integrating Gated Recurrent Unit (GRU) into a Graph Neural Network (GNN), forming the GRGNN. The accuracy of the GNN (Graph Neural Network) network with introduced GRU (Gated Recurrent Units) is validated by comparing it with seven commonly used prediction methods.MethodThe GRGNN methodology involves multivariate time series prediction using a GNN (Graph Neural Network) network improved by the integration of GRU (Gated Recurrent Units). Additionally, Graphical Fourier Transform (GFT) and Discrete Fourier Transform (DFT) are introduced. GFT captures inter-sequence correlations in the spectral domain, while DFT transforms data from the time domain to the frequency domain, revealing temporal node correlations. Following GFT and DFT, outbreak data are predicted through one-dimensional convolution and gated linear regression in the frequency domain, graph convolution in the spectral domain, and GRU (Gated Recurrent Units) in the time domain. The inverse transformation of GFT and DFT is employed, and final predictions are obtained after passing through a fully connected layer. Evaluation is conducted on three datasets: the COVID-19 datasets of 38 African countries and 42 European countries from worldometers, and the chickenpox dataset of 20 Hungarian regions from Kaggle. Metrics include Average Root Mean Square Error (ARMSE) and Average Mean Absolute Error (AMAE).ResultFor African COVID-19 dataset and Hungarian Chickenpox dataset, GRGNN consistently outperforms other methods in ARMSE and AMAE across various prediction step lengths. Optimal results are achieved even at extended prediction steps, highlighting the model’s robustness.ConclusionGRGNN proves effective in predicting epidemic time series data with high accuracy, demonstrating its potential in epidemic surveillance and early warning applications. However, further discussions and studies are warranted to refine its application and judgment methods, emphasizing the ongoing need for exploration and research in this domain.

Government Religious Discrimination, Support of Religion, and Muslim Minority-Related Societal Violence in Western Democracies

Does government-based religious discrimination against religious minorities and government support of majority religion affect religiously motivated societal violence between minorities and majority religious groups in Western democracies? Analyzing Muslim minorities, this study tries to answer the question by looking specifically at the religious violence perpetrated by and against these minorities in the West. Using a novel cross-national time-series data on 25 Western countries disaggregated by victim and perpetrator groups, this paper finds that while discrimination contributes to a country encountering religiously driven societal violence perpetrated by both Muslim and majority religious groups, government support for majority religion seems to pose no security threat. Furthermore, a case study analysis of the UK employing the synthetic control method corroborates the results of the cross-country analysis. The findings have important policy implications for counter-strategies against both Islamic and right-wing violent extremism in the West.

A modified spatial house price to income ratio and housing affordability drivers study: using the post-LASSO approach

Purpose The purpose of this paper is to develop an index for measuring urban house price affordability that integrates spatial considerations and to explore the drivers of housing affordability using the post-least absolute shrinkage and selection operator (LASSO) approach and the ordinary least squares method of regression analysis. Design/methodology/approach The study is based on time-series data collected from 2005 to 2021 for 256 prefectural-level city districts in China. The new urban spatial house-to-price ratio introduced in this study adds the consideration of commuting costs due to spatial endowment compared to the traditional house-to-price ratio. And compared with the use of ordinary economic modelling methods, this study adopts the post-LASSO variable selection approach combined with the k-fold cross-test model to identify the most important drivers of housing affordability, thus better solving the problems of multicollinearity and overfitting. Findings Urban macroeconomics environment and government regulations have varying degrees of influence on housing affordability in cities. Among them, gross domestic product is the most important influence. Research limitations/implications The paper provides important implications for policymakers, real estate professionals and researchers. For example, policymakers will be able to design policies that target the most influential factors of housing affordability in their region. Originality/value This study introduces a new urban spatial house price-to-income ratio, and it examines how macroeconomic indicators, government regulation, real estate market supply and urban infrastructure level have a significant impact on housing affordability. The problem of having too many variables in the decision-making process is minimized through the post-LASSO methodology, which varies the parameters of the model to allow for the ranking of the importance of the variables. As a result, this approach allows policymakers and stakeholders in the real estate market more flexibility in determining policy interventions. In addition, through the k-fold cross-validation methodology, the study ensures a high degree of accuracy and credibility when using drivers to predict housing affordability.

A big data analysis of the adoption of quoting encouragement policy on Twitter during the 2020 U.S. presidential election

AbstractThis research holds significance for the fields of social media and communication studies through its comprehensive evaluation of Twitter’s quoting encouragement policy enacted during the 2020 U.S. presidential election. In addressing a notable gap in the literature, this study introduces a framework that assesses both the quantitative and qualitative effects of specific platform-wide policy interventions, an aspect lacking in existing research. Employing a big data approach, the analysis includes 304 million tweets from a randomly sampled cohort of 86,334 users, using a systematic framework to examine pre-, within-, and post-intervals aligned with the policy timeline. Methodologically, SARIMAX models and linear regression are applied to the time series data on tweet types within each interval, offering an examination of temporal trends. Additionally, the study characterizes short-term and long-term adopters of the policy using text and sentiment analyses on quote tweets. Results show a significant retweeting decrease and modest quoting increase during the policy, followed by a swift retweeting resurgence and quoting decline post-policy. Users with fewer connections or higher activity levels adopt quoting more. Emerging quoters prefer shorter, positive quote texts. These findings hold implications for social media policymaking, providing evidence for refining existing policies and shaping effective interventions.

Analisis Determinan Pertumbuhan Ekonomi Inklusif Di Pulau Sumatera

This research is used to determine the factors that influence inclusive economic growth on the island of Sumatra. The analysis used is panel data regression analysis using panel data with the Fixed Effect Model (FEM) method with time series data from 2012 to 2021 and cross-section data for ten provinces on Sumatra Island. The analysis results explain that the Labor Force Participation Rate does not affect the Inclusive Economic Development Index. Meanwhile, the average length of schooling, the poor population, and the Open Unemployment Rate significantly impact the Inclusive Economic Development Index.