Time Series Data Research Articles (Page 1)

Rocky desertification governance significantly influences vegetation phenology in karst regions by improving the eco-environment and enhancing ecosystem functions. However, the spatiotemporal dynamics and underlying driving mechanisms of these governance-induced phenological shifts have not been systematically revealed due to the absence of a comprehensive analytical framework. To address the insufficient attention to governance-phenology linkages, this study developed a Governance-Phenological Induction Analysis Framework (GPIAF) and applied it to the Yunnan-Guizhou-Guangxi rocky desertification region from 2003 to 2020. Based on long-term MODIS time-series data, we extracted the rocky desertification indicator (RDI) and three key phenological parameters (SOS, EOS, LOS). Trend analysis and coupling coordination degree models were employed to characterize changing patterns and quantify governance-phenology relationships. Furthermore, gradient boosting machine algorithms combined with SHapley Additive exPlanations were used to identify dominant drivers. The results demonstrated that in effective phenology zones of rocky desertification, RDI decreased significantly in 56.28% of the regions, SOS advanced in 33.46%, EOS was delayed in 26.50%, and LOS extended in 23.41%. A high inductive effect (averaging 93.6%) was exhibited between rocky desertification governance and LOS, and this effect strengthened over time. Environmental factors and human activity indicators made comparable contributions to the inductive mechanism, with precipitation (negative) and nighttime light (positive) being the dominant drivers. The multidimensional analysis of GPIAF indicates that, in addition to climatic factors, rocky desertification governance also exerts significant influences on vegetation phenology, providing a scientific basis for optimizing governance strategies.

This study investigates the dynamic relationship between carbon dioxide (CO 2 ) emissions, financial development, and economic growth in Oman from 1998 to 2022 within the framework of the Environmental Kuznets Curve (EKC) hypothesis. Using time series data from the World Bank, IMF, and Oman’s National Centre for Statistics and Information, the autoregressive distributed lag (ARDL) model is applied to evaluate both long-run and short-run interactions. Diagnostic tests, including Breusch–Godfrey, Breusch–Pagan–Godfrey, and Ramsey’s RESET, confirm the robustness of the model. The results reveal a cointegrating relationship, with economic growth and financial development exerting significant long-term impacts on CO 2 emissions. The error correction term indicates a 70% annual adjustment towards equilibrium, underscoring the dynamic nature of the linkage. Bidirectional causality is observed between CO 2 emissions, economic growth, and financial development. While economic diversification has contributed to short-term emission reductions, long-term sustainability requires enhanced green investment and renewable energy development. These research data provide fundamental knowledge that Gulf Cooperation Council region governments, along with national decision-makers in Oman, can use to handle economic progress without sacrificing environmental preservation.

The analysis of time series data from a complex system is challenging, because apart from its multiple stable states arising as low-dimensional manifolds, contribution from the rest of the many variables manifest themselves as state-dependent noise. To identify and characterize these stable states, and detect transitions between them, we need to construct slowly varying order parameters from the noisy time series. In this paper, we propose a model-free method to extract the slowly varying parts of noisy time series data, by taking the difference between the integrated information in a sliding pair of adjoining time windows. Because this differential information has the structure of a derivative, we call it a quasi-derivative and the method quasi-differentiation. We tested this method on some simple examples, before applying it successfully to identify the Oct 2008 Lehman Brothers and Mar 2020 COVID-19 market crashes in the daily returns of the Dow Jones Industrial Average (DJIA) index from 2003 to 2023. We then describe how we can approximate the slowly varying part of the noisy time series, by re-integrating the quasi-derivative obtained. After testing this method of integrated quasi-differentiation on a few other examples, we applied it successfully to extract the slowly varying mean and variance of the DJIA. Finally, we discuss how the method of integrated quasi-differentiation can be used to obtain point estimates of the Hurst exponent and linear cross correlation. Although we have illustrated the above methods on stock market data, we believe they can be applied to a large variety of quantities in many other complex systems.

Socioeconomic inequalities in mortality are large and persistent. While the differential timing and impact of the smoking, alcohol, and obesity epidemics among socioeconomic groups likely influenced past trends in socioeconomic mortality inequalities, the evidence is scarce. We estimated the combined impact of smoking, alcohol, and obesity on past trends in educational inequalities in remaining life expectancy at age 30 (e30) in England and Wales, Finland, and Italy (Turin). To do so, we used long-term timeseries of annual individually-linked mortality data by educational level (low, middle, high), sex, and age (30+). We multiplicatively aggregated estimates of smoking-, alcohol-, and obesity-attributable mortality by educational level to obtain "lifestyle-attributable mortality" (LAM) by educational level. We compared trends in educational inequalities in e30 with and without LAM using segmented regression. We found that smoking-, alcohol-, and obesity-attributable mortality individually contributed 23%, 14%, and 10%, respectively, to the average educational inequality in e30 of 4.4 years in 1992-2017, and 44% combined (males: 51%; females: 34%). LAM contributed 57%, 63%, and 43%, respectively, to the increase in educational inequalities in e30 among Finnish males (1987-2008), Finnish females (1987-2017), and Italian males (1990-2018); tempered the decline in inequalities among British females (1992-2017); and was responsible for the reversal in 2008 from increasing to declining inequalities among Finnish males. Targeting socioeconomic inequalities in smoking, alcohol, and obesity could, thus, substantially reduce socioeconomic inequalities in e30, and the increasing time trends in these inequalities. The observed country differences in the importance of these lifestyle factors demonstrate the need for context-specific strategies.

Abstract Pulsar searching with next-generation radio telescopes requires efficiently sifting through millions of candidates generated by search pipelines to identify the most promising ones. This challenge has motivated the utilization of Artificial Intelligence (AI)-based tools. In this work, we explore an optimized pulsar search pipeline that utilizes deep learning to sift “snapshot” candidates generated by folding de-dispersed time series data. This approach significantly accelerates the search process by reducing the time spent on the folding step. We also developed a script to generate simulated pulsars for benchmarking and model fine-tuning. The benchmark analysis used the NGC 5904 globular cluster data and simulated pulsar data, showing that our pipeline reduces candidate folding time by a factor of ∼10 and achieves 100% recall by recovering all known detectable pulsars in the restricted parameter space. We also tested the speed-up using data of known pulsars from a single observation in the Southern-sky MWA Rapid Two-metre (SMART) survey, achieving a conservatively estimated speed-up factor of 60 in the folding step over a large parameter space. We tested the model’s ability to classify pulsar candidates using real data collected from the FAST, GBT, MWA, Arecibo, and Parkes, demonstrating that our method can be generalized to different telescopes. The results show that the optimized pipeline identifies pulsars with an accuracy of 0.983 and a recall of 0.9844 on the real dataset. This approach can be used to improve the processing efficiency for the SMART and is also relevant for future SKA pulsar surveys.

Electronic noses (e-noses) offer a practical solution for real-time monitoring of ammonia (NH3) in agricultural environments, where NH3 often coexists with interfering gases such as CO2, CH4, and H2S. However, semiconductor-based gas sensors commonly used in e-nose systems suffer from inherent cross-sensitivity, which reduces measurement accuracy. This study investigates the cross-sensitivity of NH3 detection and introduces a mitigation strategy through convolutional neural networks (CNNs) for sensor data fusion. Experimental results show that WO2-based sensors exhibit strong NH3 selectivity, with response ratios of 7.3:1 against CH4 and 17.8:1 against H2S. Density functional theory (DFT) analysis confirmed that the WO3 sensor exhibited strongest NH3 binding energy (- 1.45eV), compared to SnO2 (- 1.10eV), explaining the observed selectivity. Measurement uncertainties (± 8%) were quantified under varying humidity (30-90% RH) and temperature (10-40°C) using a weighted least squares error propagation model. A quasi-2D sensor array improved NH3 classification accuracy to 96.4% (7.2% increase) while reducing concentration errors by 50.8%, as validated by linear discriminant analysis. Long-term stability tests demonstrated that SnO2 sensors maintained a low baseline drift of 0.18%/day over 180days, outperforming CH4 (0.31%/day) and ZnO (0.42%/day) sensors. Furthermore, the CNN model, trained on multi-sensor time-series data, achieved 91.7% accuracy in mixed-gas environments by capturing non-linear response patterns, ensuring reliable NH3 quantification despite interferents. These findings highlight the promise of CNN-enhanced e-nose systems for precise NH3 monitoring in complex agricultural settings, addressing key challenges of cross-sensitivity and environmental stability.

ABSTRACT This study introduces a novel and interpretable hybrid framework for ultrasonic non-destructive evaluation. This methodology synergistically integrates advanced feature engineering with a bidirectional long short-term memory network to accurately localise defects and identify specimen configurations using one-dimensional acoustic time-series data. Motivated by the need for data-efficient and explainable deep learning solutions in industrial inspection, the proposed approach explores multiple categories of physically-interpretable features derived from acoustic signals (amplitude spectrum, power spectrum, convolutional neural network features, statistical descriptors) and various fusion strategies (concatenation, element-wise operations). Results demonstrate consistent defect localisation precision below 0.1 mm. Moreover, the model also achieves high performance in classifying specimen configurations. This study offers a robust, scalable, and industrially relevant pathway towards high-precision ultrasonic inspection by providing a framework that prioritises both accuracy and transparency.

Agricultural exports in Nigeria have been adversely affected by fluctuations in macroeconomic indicators. Insufficient private agricultural investment and limited public expenditure directed toward the sector have resulted in inadequate productivity and suboptimal export performance. This study investigates the macroeconomic determinants of agricultural exports in Nigeria. A multiple regression model is specified, with agricultural exports (as a percentage of total merchandise exports) as the dependent variable. The independent variables are national output (economic growth rate), inflation rate, interest rate, exchange rate, and tariff rate. The analysis employs descriptive statistics, correlation, stationarity, and cointegration tests. After confirming the absence of multicollinearity, heterogeneity, autocorrelation, and nonstationarity in the time series data, the variables are deemed suitable for regression analysis. The model is estimated using ordinary least squares, and the results are interpreted at the 5% significance level. The findings indicate that all macroeconomic indicators, except the tariff rate, significantly influence agricultural exports. It is recommended that Nigerian policymakers reassess the effects of macroeconomic policies on the country's external balance, with particular attention to agricultural exports.

Stock price prediction is a complex problem because financial time series data are volatile and complicated. The model should learn the temporal relationship and complex spatial patterns in data for precise stock price prediction. Conventional methods used for stock price forecasting have many limitations regarding handling nonlinear, complex, and dynamic data. This study assesses a hybrid deep learning model integrated with a triple attention mechanism to predict stock prices. It is experimental that the proposed MTA-HDCRNN model performs well on intricate data. The deep CNN works well on finding the local patterns in the data, whereas the simple RNN supports to learn sequential data. The triple attention mechanism emphasizes which features to focus on and where to focus. The dataset used for analysis is the BSE and Nifty 50. Web scraping is done to get the news data. Feature extraction includes statistical features, entropy features, PCA features, and technical indicators. Overall, the complete architecture of the proposed model is vigorous. It is observed that there is a 2% to 6% decrease in error values when the model is compared with existing state-of-the-art models. Experimentation shows that the proposed model enhances the stock price prediction, making it useful for investors and financial analysts for decision-making.

In the context of Industry 4.0 and smart manufacturing, predicting cutting tool remaining useful life (RUL) is crucial for enabling and enhancing the reliability and efficiency of CNC machining. This paper presents an innovative predictive model based on the data fusion architecture of Graph Neural Networks (GNNs) and Transformers to address the complexity of shallow multimodal data fusion, insufficient relational modeling, and single-task limitations simultaneously. The model harnesses time-series data, geometric information, operational parameters, and phase contexts through dedicated encoders, employs graph attention networks (GATs) to infer complex structural dependencies, and utilizes a cross-modal Transformer decoder to generate fused features. A dual-head output enables collaborative RUL regression and health state classification of cutting tools. Experiments are conducted on a multimodal dataset of 824 entries derived from multi-sensor data, constructing a systematic framework centered on tool flank wear width (VB), which includes correlation analysis, trend modeling, and risk assessment. Results demonstrate that the proposed model outperforms baseline models, with MSE reduced by 26–41%, MAE by 33–43%, R2 improved by 6–12%, accuracy by 6–12%, and F1-Score by 7–14%.

This study assesses the connection between environmental degradation, agro-climate financing, and economic growth in Sub-Saharan Africa (SSA) using yearly time series data from 2000 to 2022. The system generalized method of moments (GMM) was employed to tackle endogeneity issues, with robustness checks performed using DOLS and FMOLS to address cross-sectional dependence through robust standard errors. This method revealed important insights into the dynamics of economic growth. The findings show a significant positive connection between the economy’s past success and its current growth. CO2 emissions negatively impact economic growth, demonstrating the detrimental effects of environmental degradation. Agricultural finance has a positive influence on economic growth by boosting productivity and fostering economic growth. However, climate financing has a short-term negative impact on growth owing to high initial costs and inefficiencies, but it promotes long-term growth when combined with agricultural finance. The interaction between CO2 emissions and agricultural finance shows that increasing emissions reduces the benefits of agricultural investments, underscoring the vulnerability of agriculture-dependent economies. Conversely, the interaction of agricultural finance with climate finance enhances economic growth, demonstrating the relevance of combining climate and agricultural investments. Additionally, the study finds that exchange rate stability positively affects growth, while inflation has a negative impact. Robustness checks validate these findings and underscore the need for varied analytical methods to capture economic interactions comprehensively. The study recommends comprehensive policy measures to tackle environmental, agricultural, and climate challenges, promote sustainable growth, and leverage integrated financial solutions for long-term development in Sub-Saharan Africa.

The Skoura oasis, located in the Ouarzazate region of southern Morocco, represents a fragile agro-ecosystem increasingly affected by land degradation processes. This study aims to analyze the spatio-temporal dynamics of desertification in the oasis from 1984 to 2024, in light of climate variability and anthropogenic pressures. An integrated approach combining remote sensing data and environmental indicators is adopted to characterize changes in vegetation and soil conditions. High-resolution satellite imagery from Pléiades 2023 and time series data from the Landsat (5, 7, 8) and Sentinel-2 missions are processed using object-based image analysis and segmentation techniques. Three key indicators are employed: the Modified Soil Adjusted Vegetation Index (MSAVI), surface albedo, and the Sand Fraction Index (SFI). These indicators are integrated to construct a Desertification Monitoring Index (DMI) within the Google Earth Engine platform. Results reveal that in 1984, 24.3% of the oasis area was already classified as highly desertified, particularly in the eastern, southern, and central zones. A slight improvement was ob-served by 1996, with the desertified surface decreasing to 8.6 %. However, a renewed intensification occurred between 1996 and 2010, especially in areas dominated by date palms and olive groves. From 2010 to 2024, desertification progressed further, marked by significant vegetation loss. The findings highlight the persistence and aggravation of land degradation over four decades. The study demonstrates the value of integrated remote sensing approaches for monitoring desertification and supports the need for adaptive strategies to ensure the sustainable management of oasis ecosystems.

In recent years, the integration of computer vision and deep learning in the financial sector has become a research hotspot. Traditional stock price prediction primarily relies on time-series data, while individual investors in the market often make decisions by analyzing visual charts such as candlestick charts. Consequently, research utilizing stock price-related images as input has gradually emerged. This paper proposes an architecture based on the Long Short-Term Memory (LSTM) network to predict future trends using stock price images. By converting stock price informationincluding opening price, high price, low price, closing price into standardized images.Then employs the enhanced LSTM structure proposed in Sequencer (bidirectional LSTM, Bi-LSTM) for feature extraction and modeling, using machine learning to simulate human investment decisions. Experimental results demonstrate that this model not only outperforms traditional momentum strategies and short-term reversal strategies in stock price prediction accuracy but also maintains robust performance across varying market conditions and transaction delays. This research offers novel insights for stock price forecasting and validates the effectiveness of LSTM in processing image-based financial data.

The electrical activity of the human heart, recorded via an electrocardiogram (ECG), is characterized by distinct waveforms such as the P wave, QRS complex, and T wave. By analyzing the duration, morphology, and intervals between these waveforms, various cardiac disorders can be identified. This study aims to develop a deep learning-based approach for the accurate classification of congenital heart disease (CHD) using ECG data. We employed convolutional neural networks (CNNs) and recurrent neural networks (RNNs) to analyze ECG signals, leveraging their ability to detect multiple features in time-series data. A deep learning model was developed and trained using features such as estimated peak locations, inter-peak intervals, and other ECG parameters. To address class imbalance, we applied the synthetic minority oversampling technique (SMOTE), which generates synthetic samples to balance each class. The analysis was conducted using the MIT-BIH Arrhythmia Database, enabling CHD classification based on ECG patterns. The proposed method improved classification accuracy by effectively balancing the dataset with SMOTE. Compared to conventional methods, the deep learning algorithms demonstrated robust performance in analyzing ECG data and detecting disease-related patterns, achieving superior results. This study highlights the potential of CNNs and RNNs for classifying CHD from ECG signals. By mitigating data imbalance with SMOTE, the approach enhances both accuracy and reliability. Future work will focus on validating the model with additional datasets and addressing real-world challenges such as noise handling and external validation.

Background Tourism is a vital component of economic development, particularly in emerging economies like India, where international tourist arrivals contribute significantly to foreign exchange earnings, employment generation, and regional growth. While prior research has explored various determinants of tourism demand, limited empirical studies have assessed the macroeconomic underpinnings of ITA using time series models capable of handling mixed integration orders. This study investigates the short-run and long-run effects of international tourist arrivals on GDP, FDI, and inflation in India. Methods This study uses the Autoregressive Distributed Lag bounds testing approach on annual data spanning from 1995 to 2022. The Augmented Dickey-Fuller (ADF) test was conducted to determine the stationarity properties of the time series data, after which the optimal lag structure for the ARDL model was identified using the Akaike Information Criterion (AIC). The model was built on a time series dataset spanning 1995 to 2022, and the empirical results provide both statistically significant findings and interpretive depth that are relevant to policy and theory. Results The findings of this study confirm a statistically significant and positive relationship between GDP and international tourist arrivals in both the short and long run. The ARDL (1,2,0,2) model demonstrated strong explanatory power (Adjusted R² = 0.9565), and the bounds test confirmed the presence of cointegration among the variables. However, FDI and inflation were found to be statistically insignificant in influencing ITA. The error correction term was negative and empirically significant, indicating that approximately 51% of the disequilibrium adjusts each year toward long-run equilibrium. Conclusion This study highlights GDP as the primary macroeconomic driver of international tourism demand in India, with implications for economic planning and tourism policy. While FDI and inflation were not significant in this model, their potential indirect effects needs further investigation.

Detection of damage in the mooring systems of Floating Offshore Wind Turbines (FOWTs) is essential to guarantee operational reliability and reduce corrective maintenance costs. However, the complex nature of environmental conditions, the high costs of data collection, and the rarity of damage events make it challenging to obtain extensive labelled datasets. As a result, addressing damage detection from limited labelled data is necessary, yet it remains a relatively under-explored area in the literature. To tackle these challenges, this paper introduces an image-transformed semi-supervised generative adversarial network (ITSGAN) technique based on deep generative models. The method transforms time series data into multichannel image representations, enabling deep learning models to more effectively capture both spatial and temporal features. By combining adversarial training with supervised learning, ITSGAN leverages both labelled and unlabelled data to improve damage detection ability, particularly in scenarios where labelled data is scarce. A comparative analysis with established models such as traditional semi-supervised GAN, Deep Convolutional Neural Networks (DCNN), Support Vector Machines (SVM), and Extreme Gradient Boosting (XGB) shows that ITSGAN consistently outperforms these models in accuracy, precision, recall, and F1 score. It is also demonstrated that the proposed ITSGAN model preserves richer feature representations by transforming time series data into images, resulting in enhanced performance in damage detection tasks.

Backgroundα-Synuclein (α-syn) is a prominent protein associated with neurodegenerative conditions such as Parkinson's disease (PD), dementia, and multiple system atrophy, and is a key player in synucleinopathies. Despite its significance, the specific changes in α-syn fibril conformations during the progression of PD remain a subject of uncertainty.ObjectiveThis study investigates the structural alterations in α-syn aggregation from cerebrospinal fluid samples at different PD stages (pre-PD, mid-PD, and late-PD).MethodsIn the present study, we used multifractal detrended fluctuation analysis (MFDFA) and persistent homology. The analysis involves constructing protein contact networks for major and minor α-syn polymorphs. The subsequent application of MFDFA to vertex degree, vertex clustering coefficients, and vertex closeness centrality on this time series data reveals multifractal properties and scaling behaviors. Simultaneously, topological analyses, including Rips complexes, Alpha complexes, and Betti numbers, uncover essential structural features and connectivity patterns in α-syn networks.ResultsThis study illuminates α-syn multifractal dynamics and topological characteristics, providing valuable insights into disease-related protein aggregation and network alterations in the progression of PD.ConclusionsThis study provides unique information on MFDFA and persistent homology of α-syn aggregates across disease stages.

The sheep tick Ixodes ricinus is the vector associated with the highest incidence of vector-borne disease in humans in Europe. Several studies have been published about the effect of future climate change on the potential distribution of I. ricinus, despite a limited understanding of how climate change has resulted in distribution changes to date. The objective of the present study was to assess whether temperature changes have already influenced the northern distribution limit of I. ricinus in Europe. To this end, we estimated a thermal threshold for the presence of the species and then used this estimated threshold to hindcast the geographical location of the thermal limit over the past 40years. We used a public dataset of I. ricinus abundance at the northern edge of its European distribution for 2016-2017 and temperature data obtained from the ERA5Land dataset to identify a thermal threshold for I. ricinus distribution. We first modelled nymphal tick abundance as a function of cumulative annual degree days (ADD) > 0°C stratified by biogeographical regions using observations for 2016-2017. We then identified the thermal limit for each biogeographical region as the minimum DD > 0°C value where the predicted nymph abundance is greater than zero and projected it onto ERA5Land temperature data for the period 1979-2020. Hindcasting the identified thermal limit suggested that I. ricinus has expanded its range by approximately 400km in the Boreal biogeographical region between 1979 and 2020. This finding helps explain numerous observations of I. ricinus in areas presumed to be newly colonised. Our findings suggest a substantial northward expansion of I. ricinus over the past four decades. Our approach appears promising for understanding species distribution changes driven by recent climate change, acknowledging that multiple other factors affect tick distribution and abundance at the local scale, such as host distribution and microhabitat. Our results underline the relevance of long-term time series data and the risk associated with short time series for observing changes in distribution.

The endoplasmic reticulum (ER) comprises smooth tubules, ribosome-studded sheets, and peripheral sheets that can present as tubular matrices. ER shaping proteins determine ER morphology, however, understanding their role in tubular matrix formation requires reconstructing the dynamic, convoluted ER network. Existing reconstruction methods are sensitive to parameters or require extensive annotation and training for deep learning. We introduce nERdy, an image processing based approach, and nERdy+, a D4-equivariant neural network, for accurate extraction and representation of ER networks and junction dynamics, outperforming previous methods. Comparison of stable and dynamic representations of the extracted ER structure reports on tripartite junction movement and distinguishes tubular matrices from peripheral ER networks. Analysis of live cell confocal and Stimulated emission depletion microscopy (STED) time series data shows that Atlastin and Reticulon 4 promote dynamic tubular matrix formation and enhance junction dynamics, identifying novel roles for these ER shaping proteins in regulating ER structure and dynamics.

This study investigates the comparative assessment of institutional reforms, insecurity on sustainable economic development in Nigeria. Despite numerous governance reform initiatives, Nigeria continues to experience weak institutional performance, corruption, and persistent insecurity that undermine sustainable growth. The study adopts an ex-post facto research design and utilizes secondary time-series data sourced from the World Bank’s World Development Indicators (WDI) and Worldwide Governance Indicators (WGI), the Global Terrorism Database (GTD), the Uppsala Conflict Data Program (UCDP), and the Numbeo Crime Index. Descriptive and correlation analyses were applied to examine the effects of institutional quality and insecurity on economic sustainability, proxied by real GDP growth and adjusted net savings. Findings reveal that periods of heightened insecurity, particularly between 2011 and 2017, coincided with declines in GDP growth and savings, while indicators of governance effectiveness, control of corruption, and regulatory quality remained persistently low. This pattern indicates that insecurity adversely affects investment and productivity, whereas institutional reforms exert a weak but positive influence on economic performance. The study concludes that economic sustainability in Nigeria is strongly dependent on institutional efficiency and national security. It recommends strengthening governance capacity and accountability, integrating security operations with socio-economic development programmes, diversifying the economy beyond oil dependence, and enhancing the rule of law and fiscal transparency. Effective coordination between institutional reform and security policy is essential to achieving inclusive, resilient, and sustainable economic growth in Nigeria.