Search

GoogLeNet is a pre-trained Convolutional Neural Network (CNN) that allows transfer learning and has achieved high recognition rates in image classification tasks. A Recurrence Plot (RP) is an imaging method that depicts the recurrence of the state space system using coloured points and lines in 2D images. This work contributes to facilitating time series feature extraction by proposing a method that applies the GoogLeNet to time series images obtained with RP. The developed method is tested using simulated time series and selected time series from the M3 competition dataset. The results shows that the transfer learning approach allowed the extraction of business time series features by means of a GoogLeNet fine-tuned using 100 simulated time series. The combination of GoogLeNet and RPs outperforms the alternative and easier combination of GoogLeNet and plots of the time series and support the convenience of the RP transformation step. This application of deep learning techniques to business time series imaging offers opportunity for further developments. [ABSTRACT FROM AUTHOR]

Genomic time series from experimental evolution studies and ancient DNA datasets offer us a chance to directly observe the interplay of various evolutionary forces. We show how the genome-wide variance in allele frequency change between two time points can be decomposed into the contributions of gene flow, genetic drift, and linked selection. In closed populations, the contribution of linked selection is identifiable because it creates covariances between time intervals, and genetic drift does not. However, repeated gene flow between populations can also produce directionality in allele frequency change, creating covariances. We show how to accurately separate the fraction of variance in allele frequency change due to admixture and linked selection in a population receiving gene flow. We use two human ancient DNA datasets, spanning around 5,000 y, as time transects to quantify the contributions to the genome-wide variance in allele frequency change. We find that a large fraction of genome-wide change is due to gene flow. In both cases, after correcting for known major gene flow events, we do not observe a signal of genome-wide linked selection. Thus despite the known role of selection in shaping long-term polymorphism levels, and an increasing number of examples of strong selection on single loci and polygenic scores from ancient DNA, it appears to be gene flow and drift, and not selection, that are the main determinants of recent genome-wide allele frequency change. Our approach should be applicable to the growing number of contemporary and ancient temporal population genomics datasets.

Automated Machine Learning (AutoML) tools are revolutionizing the field of machine learning by significantly reducing the need for deep computer science expertise. Designed to make ML more accessible, they enable users to build high-performing models without extensive technical knowledge. This study delves into these tools in the context of time series analysis, which is essential for forecasting future trends from historical data. We evaluate three prominent AutoML tools—AutoGluon, Auto-Sklearn, and PyCaret—across various metrics, employing diverse datasets that include Bitcoin and COVID-19 data. The results reveal that the performance of each tool is highly dependent on the specific dataset and its ability to manage the complexities of time series data. This thorough investigation not only demonstrates the strengths and limitations of each AutoML tool but also highlights the criticality of dataset-specific considerations in time series analysis. Offering valuable insights for both practitioners and researchers, this study emphasizes the ongoing need for research and development in this specialized area. It aims to serve as a reference for organizations dealing with time series datasets and a guiding framework for future academic research in enhancing the application of AutoML tools for time series forecasting and analysis.

Spectral density estimation is a well-studied problem for the case of directly observed time series. If data are censored then add hoc methods, like ignoring censored observations or treatment them as missing and using imputation, are recommended. This article, for the first time in the literature, presents the theory and methodology of efficient non parametric spectral density estimation for censored time series. Recommended estimator is based on estimation of autocovariances for censored time series which is of interest on its own. Similarly to the case of direct observations, the theory and methodology are first developed for Gaussian time series, and then robustness of the estimator is verified for a larger class of mixing time series. Simulations and practical examples complement the theory. [ABSTRACT FROM AUTHOR]

Interaction between public and private sector real wages in the U.S. are examined over the periods 1952–2019, 1952–1972, and 1973–2019. Industries considered include all private industries and five broad industry subcategories. Measures of U.S. state & local governments and federal government are considered, and their changing contributions to total employment across periods provides context for wage leadership. Private sector wages caused federal wages as federal employment's share of total employment decreased throughout the periods. In contrast, state & local government's share of total employment grew substantially in the early period, with their wages causing private sector wages. In the later period, state & local government's share of total employment stabilized and their wages cause those in half of the private sectors to be considered, with feedback in the remaining industries. [ABSTRACT FROM AUTHOR]

Forest resilience, the ecosystem's capacity to withstand perturbations and retain primary functions and characteristics, is an essential indicator in evaluating the fate of an ecosystem under rapid climate change. Detailed information about forest resilience change, such as number of changes, direction (reduced vs increased), timing (start/end year), or duration of the change, is critical but is often not well demonstrated at the global scale. Here, we applied lag-one autocorrelation (AC1) as a forest resilience indicator on time series MODIS vegetation index images from 2001 to 2022 and employed LandTrendr spectral-temporal segmentation algorithms to track forest resilience change. Our results showed that the resilience of global forests changed nearly 3 times on average, and over 50% of global forests had an overall downward trend from the early 2000s up to recently. However, the current condition is changing for the better globally with approximately 53% of global forests currently showing an increased resilience during the recent change, and average patches of reduced resilience becoming smaller and more scattered. Over half of the forests in arid and temperate domains still show decreased resilience recently, which highlights the need for improved management practices. [ABSTRACT FROM AUTHOR]

In this study, we propose a probabilistic approach to predict rare events by exploiting coevolving time series. The probability of a failure is calculated based on the weighted autologistic regression of these time series, accounting for specific characteristics of failures such as data imbalance. We estimate the model parameters using the maximum likelihood of the Bernoulli process. By incorporating the temporal behaviors of the various phenomena underlying the occurrence of failures and the nature of the data, we improve the prediction of rare events. Evaluations on both synthetic and real datasets demonstrate that our approach outperforms existing methods in predicting home equipment failures. [ABSTRACT FROM AUTHOR]

We introduce a clustering method for time series based on tail dependence. Such a method also considers spatial constraints by means of a suitable procedure merging temporal and spatial dependence via extreme-value copulas. The cluster composition depends on the choice of the hyper-parameter α ∈ (0 , 1) used to calibrate the contribution of the spatial dependence to the overall dissimilarity. A novel heuristic approach to select α based on a suitable connectedness index associated to each cluster of the partition is proposed. [ABSTRACT FROM AUTHOR]

Approximating a series of timestamped data points through a sequence of line segments with a maximum error guarantee is a fundamental data compression problem, termed as Piecewise Linear Approximation (PLA). As the demand for analyzing large volumes of time-series data across various domains continues to grow, the significance of this problem has recently received considerable attention. Recent PLA algorithms have emerged to help us handle the overwhelming amount of information, albeit at the expense of some precision loss. More precisely, these algorithms involve a delicate balance between the maximum acceptable precision loss and the space savings that can be achieved. In our recent work we proposed Sim-Piece, offering a fresh perspective on the long-standing challenge of PLO approximation. Sim-Piece identifies similarities among line segments in a PLA representation enabling their grouping and joint representation. This way, Sim-Piece delivers space-saving advantages that outperform even the optimal PLA approximation. In this work, we present Mix-Piece, an improved PLA compression algorithm that builds upon the core idea of Sim-Piece (i.e., exploiting similar PLA segments) but improves further its performance by (1) considering multiple candidate PLA segments when ingesting a time series, (2) enabling grouping of additional segments not utilized by Sim-Piece, and, (3) making use of a versatile output format that exploits all segment similarities. Our experimental evaluation demonstrates that Mix-Piece outperforms Sim-Piece and previous competing techniques, attaining compression ratios with more than twofold improvement on average over what PLA algorithms can offer. This allows for providing significantly higher accuracy with equivalent space requirements. [ABSTRACT FROM AUTHOR]

Public spending influences a country's economic activities due to its effect on aggregate demand. Although existing research has focused on government expenditures to understand the multiplier impacts of public spending, there is scant literature focusing on the spending of state-owned enterprises (SOEs), especially in strategic sectors such as the oil sector. This study analyzes the spending behaviour of an important Brazilian SOE, Petrobras, to understand its consequences to the Brazilian economic activity. The results suggest that multiplier impacts during recessions are bigger than those during economic expansions. The accumulated multiplier of Petrobras's investment expenditures is higher compared to current spending, especially in periods of recession. Moreover, the forecast error variance decomposition showed the impact that changes in government spending in Petrobras had on the Brazilian GDP growth in periods of expansion and contraction. [ABSTRACT FROM AUTHOR]

Copyright of GeSec: Revista de Gestao e Secretariado is the property of Sindicato das Secretarias e Secretarios do Estado de Sao Paulo (SINSESP) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Crime against women (CAW) is not a present-day problem but has been prevalent in the world through the ages and since the beginning of civilizations. The cases of CAW have been increasing in almost all parts of the world and India is no exception. The distribution of CAW cases has not been found uniform across the country. The evidence of heterogeneity of cases has been a concern. Rajasthan, the largest state in India, has witnessed a very high surge in CAW in recent years. Therefore, there arises a need to study and analyze the pattern of CAW to identify the areas with high intensity for prevention and control. The CAW data from the National Crime Records Bureau (NCRB) website for the period 2014 to 2021 and the population census data of 2011 are used for the analysis. The Statistical analysis software, SaTScan, is employed for hotspot (areas with a high concentration of crimes) detection. Python programming is used to compute the data's trend or pattern through visualization and descriptive statistics. In addition, the simple exponential smoothing method is applied for predicting the CAW for the year 2021. Our work elucidates Jhalawar, Baran, Kota, Bundi, Sawai Madhopur, and Chittorgarh districts as consistently occurring hotspots of CAW in the state. A comparative study of the hotspots found is made with the result obtained from the descriptive analysis. The trend in the data explains the years 2017 and 2019 as trough and crest of CAW cases. The hotspot detected using the forecast value of 2021 appears to be the same districts as for the period 2014 to 2020. Our work concludes that the consistency and the most likely cluster of CAW are distributed distinctly. We also found that the hotspot of CAW is not by chance but has certain man-made reasons. Most of the clusters have been identified as districts sharing boundaries with adjacent states. This further implies that if sincere efforts to collaborate with the government of the adjacent states like Madhya Pradesh, Haryana, Punjab, Uttar Pradesh, and Gujarat, the incidences resulting in detrimental effects due to CAW could reduce effectively and significantly. Thus, our study may help the government, law enforcement agencies, police organizations, judiciaries, and other stakeholders to optimize their scarce resources most effectively to curb such incidents. [ABSTRACT FROM AUTHOR]

In this paper, we show that traditional comparisons of mean squared prediction error (MSPE) between two competing forecasts may be highly controversial. This is so because when some specific conditions of efficiency are not met, the forecast displaying the lowest MSPE will also display the lowest correlation with the target variable. Given that violations of efficiency are usual in the forecasting literature, this opposite behavior in terms of accuracy and correlation with the target variable may be a fairly common empirical finding that we label here as "the MSPE paradox." We characterize "paradox zones" in terms of differences in correlation with the target variable and conduct some simple simulations to show that these zones may be non‐empty sets. Finally, we illustrate the relevance of the paradox with a few empirical applications. [ABSTRACT FROM AUTHOR]

Traditional 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. [ABSTRACT FROM AUTHOR]

Magnesium silicate hydrate (M‐S‐H) represents a promising alternative to traditional cement, particularly for low‐pH construction applications such as nuclear waste encapsulation and carbon dioxide injection. The durability of construction materials, a critical aspect of their suitability for various purposes, is primarily governed by the kinetics of dissolution of the binder phase under service conditions. In this study, we employed in situ atomic force microscopy to assess the dissolution rates of M‐S‐H in water equilibrated with air. Quantitative analysis based on changes in volume and height revealed dissolution rates ranging from 0.18 to 3.09 × 10−12 mol/cm2/s depending on the precipitate Mg/Si ratio and morphology. This rate surpasses its crystalline analogs, talc (Mg3Si4O10(OH)2) and serpentine (Mg3(Si2O5)(OH)4), by about three to five orders of magnitude. Interestingly, oriented M‐S‐H dissolved faster than non‐oriented M‐S‐H. Spatially resolved assessments of dissolution rates facilitated a direct correlation between rates and morphology, showing that edges and smaller crystallites dissolve at a faster pace compared to facets and larger crystallites. The outcomes of this study provide insights into the mechanisms governing the dissolution of M‐S‐H and the factors dictating its durability. These findings hold implications for the strategic design and optimization of M‐S‐H for various applications. [ABSTRACT FROM AUTHOR]

Background: Rifampicin resistant tuberculosis (RR-TB) poses a growing threat to individuals and communities. This study utilized a seasonal autoregressive integrated moving average (SARIMA) model to quantitatively predict the monthly incidence of RR-TB in Yunnan Province which could guide government health administration departments and the centers for disease control and prevention (CDC) in preventing and controlling the RR-TB epidemic. Methods: The study utilized routine surveillance reporting data from the infectious Disease Network Surveillance and Reporting System. Monthly incidence rates of RR-TB were collected from January 2019 to December 2022. A time series SARIMA model was used to predict the number of monthly RR-TB cases in Yunnan Province in 2023, and the model was validated using time series plots, seasonal and non-seasonal differencing, autocorrelation and partial autocorrelation analysis, and white noise tests. Results: From 2019 to 2022, the incidence of RR-TB decreases as the incidence of all TB decreases (P < 0.05). There was no significant change in the proportion of RR-TB among all TB cases, which remained within 2.5% (P>0.05). The time series decomposition shows that it presented obvious seasonality, periodicity and randomness after being decomposed. Time series analysis was performed on the original series after 1 non-seasonal difference and 1 seasonal difference, the ADF test showed P < 0.05. According to ACF and PACF, the SARIMA (1, 1, 1) (1, 1, 0)12 model was chosen and statistically significant model parameter estimates (P < 0.05). The predicted seasonal trend of RR-TB incidence in 2019 to 2023 was similar to the actual data. The percentage accuracy in the prediction excesses 80% in 2019 to 2022 and is all within 95% CI. However there was a certain gap between the actual incidence and the predicted value in 2023, and the acutual incidence had increased by 12.4% compared to 2022. The percentage of accuracy in the prediction was only 70% in 2023. Conclusions: We found the incidence of RR-TB was based on that of all TB in Yunnan. The SARIMA model successfully predicted the seasonal incidence trend of RR-TB in Yunnan Province in 2019 to 2023, but the prediction precision could be influenced by factors such as new infectious disease outbreaks or pandemics, social issues, environmental challenges or other unknown risks. Hence CDCs should pay special attention to the post epidemic effects of new infectious disease outbreaks or pandemics, carry out monitoring and early warning, and better optimize disease prediction models. [ABSTRACT FROM AUTHOR]

Background Methods Results Conclusions In the early 2020s, nearly half of New Zealand adults reported that cost of treatment had prevented them from accessing dental care, with higher rates among Māori, Pasifika and individuals living in the most deprived areas. Unaffordable dental care may be explained by a rise in dental service fees over time relative to personal income, as documented in New Zealand between 1978 and 1993. However, there have been no contemporary estimates in New Zealand of how the affordability of dental care has changed. The aims of this study were to analyse the change in dental treatment fees and the personal income of New Zealanders from 1978 to 2023 and to explore differences in affordability of dental care by ethnicity.Average fees for dental treatments were sourced from surveys completed by practising New Zealand dentists. Earnings (from 1978) and personal income data (full population from 2000 and by ethnicity from 2008) were sourced from Statistics NZ and NZ Official Yearbooks. Inflation‐adjusted changes in average fees, weekly personal earnings and income were calculated as a percentage change from 1978 levels for fees and earnings and from 2000 for personal income.For the five dental treatments with data available from 1978 to 2023, fees increased in the range of 75%–236%, while earnings increased by 46% over the same period. Fees for other treatments (with data available from 1981 to 2009) similarly increased and mostly surpassed changes in earnings. From 2008 to 2023 the overall increase in personal income (about 21% across all ethnic groups) kept pace with the rising cost of most treatments. However, due to persistent income inequalities, in 2023, Māori and Pasifika would need to spend a higher proportion of their weekly income (approximately 16% and 23% respectively) to receive the same dental treatments as NZ Europeans.Fees for dental treatments have risen markedly in recent decades, more sharply than the price of other goods and services. [ABSTRACT FROM AUTHOR]

Background: From March 7 to April 7, 2020, the Community of Madrid (CoM), Spain, issued interventions in response to the COVID-19 epidemic, including hospital referral triage protocols for long-term care facility (LTCF) residents (March 18–25). Those with moderate to severe physical disability and cognitive impairment were excluded from hospital referral. This research assesses changes in the association between daily hospital referrals and the deaths of LTCF residents attributable to the triage protocols. Methods: Daily hospital referrals and all-cause mortality from January to June 2020 among LTCF residents and the CoM population aged 65 + were obtained. Significant changes in LTCF resident daily hospital referrals time series, and in-LTCF and in-hospital daily deaths, were examined with tests for breaks and regimes in time series. Multivariate time series analyses were conducted to test changes in the associations between LTCF resident hospital referrals with daily deaths in-hospital and in-LTCF, and in the CoM population aged 65 + when the triage protocols were implemented. Results: Among LTCF residents, hospital referrals declined sharply from March 6 to March 23, 2020. Increases in LTCF residents' daily deaths occurred from March 7 to April 1, followed by a decrease reaching pre-epidemic levels after April 28. The daily ratio of in-hospital deaths to in-LTCF deaths reached its lowest values from March 9 to April 19, 2020. The four versions of the triage protocol, published from March 18 to March 25 had no impact on further changes in the association of hospital referrals with daily deaths of LTCF residents in-hospital or in-LTCF. Conclusions: While LTCF residents' deaths increased, hospital referrals of LTCF residents decreased with the introduction of the CoM governmental interventions on March 7. They were implemented before the enactment of the triage protocols, protecting hospitals from collapse while overlooking the need for standards of care within LTCFs. The CoM triage protocols sanctioned the existing restrictions on hospital referrals of LTCF residents. [ABSTRACT FROM AUTHOR]

The rapid development of big data technology and artificial intelligence has provided a new perspective on sports injury prevention. Although data-driven algorithms have achieved some valuable results in the field of sports injury risk assessment, the lack of sufficient generalization of models and the inability to automate feature extraction have made it challenging to deploy research results in the real world. Therefore, this study attempts to build an injury risk prediction model using a combination of time-series image encoding and deep learning algorithms to address this issue better. This study used the time-series image encoding approach for feature construction to represent relationships between values at different moments, including Gramian Angular Summation Field (GASF), Gramian Angular Difference Field (GADF), Markov Transition Field (MTF), and Recurrence Plot (RP). Deep Convolutional Auto-Encoder (DCAE) learned the image-encoded data for representation to obtain features with good discrimination, and the classifier was performed using Deep Neural Network (DNN). The results from five repeated experiments show that the GASF-DCAEDNN model is overall better in the training (AUC: 0.985 ± 0.001, Gmean: 0.930 ± 0.007, Sensitivity: 0.997 ± 0.003, Specificity: 0.868 ± 0.013) and test sets (AUC: 0.891 ± 0.026, Gmean: 0.830 ± 0.027, Sensitivity: 0.816 ± 0.039, Specificity: 0.845 ± 0.022), with good discriminative power, robustness, and generalization ability. Compared with the best model reported in the literature, the AUC, Gmean, Sensitivity, and Specificity of the GASF-DCAE-DNN model were higher by 23.9%, 27.5%, 39.7%, and 16.2%, respectively, which confirmed the validity and practicability of the model in injury risk prediction. In addition, differences in injury risk patterns between the training and test sets were identified through shapley additivity interpretation. It was also found that the training volume was an essential factor that affected injury risk prediction. The model proposed in this study provides a powerful injury risk prediction tool for future sports injury prevention practice. [ABSTRACT FROM AUTHOR]

Utilizing the direct current‐side electrical data resources of the photovoltaic power generation system on the FusionSolar platform, this study investigates the impact of hot spot faults on the output characteristics of photovoltaic strings and proposes a hot spot fault diagnosis method based on time series waveform characteristics. By analyzing the mechanisms of hot spot generation and evolution, as well as the characteristic differences in I–V curves and time series compared to other types of faults, the waveform variation patterns of hot spots in current and voltage time series are obtained. A function form suitable for hot spot fault waveform characteristics in time series graphs is constructed, and fault diagnosis feature vectors are extracted. Combining field operation and maintenance experience, a fuzzy reasoning fault diagnosis system is established to determine the causes and estimate the severity of hot spot faults. Experimental results indicate that hot spot faults have unique and corresponding variations in the current/voltage time series waveforms of the string output. The constructed function form can clearly represent the waveform variation patterns, and the established fuzzy reasoning system can achieve effective and reliable diagnosis of hot spot faults. [ABSTRACT FROM AUTHOR]

The energy market operates in a highly deregulated and competitive environment, where electricity price plays a crucial role. Forecasting electricity prices presents a significant challenge due to the influence of complex factors such as weather patterns, fuel costs, and the advancement of renewable energy technologies. This study focuses on monthly electricity prices in four neighboring European countries: Bulgaria, Greece, Hungary, and Romania, which share similar weather conditions and economic characteristics. The research investigates the efficacy of four forecasting methods: Grey Verhulst Model (GVM), Nonlinear Regression, Feedforward Neural Network, and Support Vector Regression (SVR). These methods are applied to both short-term (1 month-ahead) and long-term (up to 7 months) electricity price forecasting in the aforementioned countries. The findings reveal that GVM proves suitable for short-term predictions. However, when it comes to long-term forecasting, SVR accurately captures the trends and turning points in electricity prices, albeit with unsatisfactory error rates. To address this issue, a modified version of SVR, referred to as Modified SVR (MSVR), is proposed to mitigate the errors. The results demonstrate that MSVR is an effective approach for long-term electricity price prediction. [ABSTRACT FROM AUTHOR]

Human-made structures, particularly artificial reefs, have played an increasingly important role in restoration, conservation, and management efforts aimed at mitigating the detrimental effects of anthropogenic activities on habitats and their associated communities. However, the extent to which artificial reefs support marine assemblages resembling those of natural habitat remains unclear. In this study, we used a 10-year dataset of reef fish visual surveys performed on paired reefs located in the eastern Gulf of Mexico, complemented by functional trait data, to examine whether artificial and natural reefs support fish assemblages with similar taxonomic and functional diversities. Our results revealed compositionally and functionally distinct assemblages between reef types, a pattern that was consistent across depths. The inclusion of functional diversity allowed us to explicitly identify generalized patterns in the composition of these assemblages that may have only been inferred from a strictly taxonomic-based approach. Specifically, large-bodied, midwater predators were relatively more abundant on artificial reefs, whereas smaller-bodied, benthic-associated invertivores or mesopredators were more frequently observed on natural reefs. The artificial reefs in this study were previously characterized as having greater vertical relief than their natural counterparts, a feature that likely contributed to the greater abundances of midwater predators on those reefs. Similarly, natural reefs typically offered a greater abundance of medium-to-small refugia necessary for smaller-bodied taxa to forage and avoid predation. Previous work also demonstrated that these artificial reefs were visited 2–10 times more frequently by boaters than natural reefs, presumably for recreational fishing purposes. These findings led us to infer that local-scale environmental filtering and variable predator–prey dynamics resulting from differences in the physical characteristics of these reefs coupled with asymmetric fishing activity influenced the observed differences among reef fish assemblages. Additionally, our work underscored the utility of multiple diversity measures in comparative assemblage studies, provided insight into reef-fish assemblage dynamics, and helped to emphasize a pressing need to better understand the role of human-made structures in marine ecosystems. [ABSTRACT FROM AUTHOR]

To predict air traffic flow reasonably, research is conducted in conjunction with complex network link prediction. First, the time series is converted into a visual graph to obtain the topological feature quantity, and then combined with the algorithms based on local information, path, and random walk, the prediction accuracy in different sectors of Sanya is compared. It is found that the RWR0.85 algorithm has the highest prediction accuracy. Due to the fact that link prediction can only predict possible edges and cannot predict nodes, the D-S evidence theory is introduced to predict traffic values, with a maximum prediction accuracy of 99.85%. The results indicate that the combination of complex network link prediction and D-S evidence theory for predicting air traffic flow is feasible and effective, laying a foundation for further in-depth research. [ABSTRACT FROM AUTHOR]

We propose a new methodology to transform a time series into an ordered sequence of any entropic and information functionals, providing a novel tool for data analysis. To achieve this, a new algorithm has been designed to optimize the Probability Density Function (PDF) associated with a time signal in the context of non-parametric Kernel Density Estimation (KDE). We illustrate the applicability of this method for anomaly detection in time signals. Specifically, our approach combines a non-parametric kernel density estimator with overlapping windows of various scales. Regarding the parameters involved in the KDE, it is well-known that bandwidth tuning is crucial for the kernel density estimator. To optimize it for time-series data, we introduce an adaptive solution based on Jensen–Shannon divergence, which adjusts the bandwidth for each window length to balance overfitting and underfitting. This solution selects unique bandwidth parameters for each window scale. Furthermore, it is implemented offline, eliminating the need for online optimization for each time-series window. To validate our methodology, we designed a synthetic experiment using a non-stationary signal generated by the composition of two stationary signals and a modulation function that controls the transitions between a normal and an abnormal state, allowing for the arbitrary design of various anomaly transitions. Additionally, we tested the methodology on real scalp-EEG data to detect epileptic crises. The results show our approach effectively detects and characterizes anomaly transitions. The use of overlapping windows at various scales significantly enhances detection ability, allowing for the simultaneous analysis of phenomena at different scales. [ABSTRACT FROM AUTHOR]

With LiDAR (Light Detection and Ranging) time series being used for various applications, the optimal realization of a common geodetic datum over many epochs is a highly important prerequisite with a direct impact on the accuracy and reliability of derived measures. In our work, we develop and define several approaches to the adjustment of multi-temporal LiDAR data in a given software framework. These approaches, ranging from pragmatic to more rigorous solutions, are applied to an 8-year time series with 21 individual epochs. The analysis of the respective results suggests that a sequence of bi-temporal adjustments of each individual epoch and a designated reference epoch brings the best results while being more flexible and computationally viable than the most extensive approach of using all epochs in one single multi-temporal adjustment. With a combination of sparse control patches measured in the field and one selected reference block, the negative impacts of changing surfaces on orientation quality are more effectively avoided than in any other approach. We obtain relative discrepancies in the range of 1–2 cm between epoch-wise DSMs for the complete time series and mean offsets from independent checkpoints in the range of 3–5 cm. Based on our findings, we formulate design criteria for setting up and adjusting future time series with the proposed method. [ABSTRACT FROM AUTHOR]

Continuous and dense time series of satellite remote sensing data are needed for several land monitoring applications, including vegetation phenology, in-season crop assessments, and improving land use and land cover classification. Supporting such applications at medium to high spatial resolution may be challenging with a single optical satellite sensor, as the frequency of good-quality observations can be low. To optimize good-quality data availability, some studies propose harmonized databases. This work aims at developing an 'all-in-one' Google Earth Engine (GEE) web-based workflow to produce harmonized surface reflectance data from Landsat-7 (L7) ETM+, Landsat-8 (L8) OLI, and Sentinel-2 (S2) MSI top of atmosphere (TOA) reflectance data. Six major processing steps to generate a new source of near-daily Harmonized Landsat and Sentinel (HLS) reflectance observations at 30 m spatial resolution are proposed and described: band adjustment, atmospheric correction, cloud and cloud shadow masking, view and illumination angle adjustment, co-registration, and reprojection and resampling. The HLS is applied to six equivalent spectral bands, resulting in a surface nadir BRDF-adjusted reflectance (NBAR) time series gridded to a common pixel resolution, map projection, and spatial extent. The spectrally corresponding bands and derived Normalized Difference Vegetation Index (NDVI) were compared, and their sensor differences were quantified by regression analyses. Examples of HLS time series are presented for two potential applications: agricultural and forest phenology. The HLS product is also validated against ground measurements of NDVI, achieving very similar temporal trajectories and magnitude of values (R2 = 0.98). The workflow and script presented in this work may be useful for the scientific community aiming at taking advantage of multi-sensor harmonized time series of optical data. [ABSTRACT FROM AUTHOR]

Rare events are occurrences that take place with a significantly lower frequency than more common, regular events. These events can be categorized into distinct categories, from frequently rare to extremely rare, based on factors like the distribution of data and significant differences in rarity levels. In manufacturing domains, predicting such events is particularly important, as they lead to unplanned downtime, a shortening of equipment lifespans, and high energy consumption. Usually, the rarity of events is inversely correlated with the maturity of a manufacturing industry. Typically, the rarity of events affects the multivariate data generated within a manufacturing process to be highly imbalanced, which leads to bias in predictive models. This paper evaluates the role of data enrichment techniques combined with supervised machine learning techniques for rare event detection and prediction. We use time series data augmentation and sampling to address the data scarcity, maintaining its patterns, and imputation techniques to handle null values. Evaluating 15 learning models, we find that data enrichment improves the F1 measure by up to 48% in rare event detection and prediction. Our empirical and ablation experiments provide novel insights, and we also investigate model interpretability. [ABSTRACT FROM AUTHOR]

Accompanying the climate crisis is the more enigmatic biodiversity crisis. Rapid reorganization of biodiversity due to global environmental change has defied prediction and tested the basic tenets of conservation and restoration. Conceptual and practical innovation is needed to support decision making in the face of these unprecedented shifts. Critical questions include: How can we generalize biodiversity change at the community level? When are systems able to reorganize and maintain integrity, and when does abiotic change result in collapse or restructuring? How does this understanding provide a template to guide when and how to intervene in conservation and restoration? To this end, we frame changes in community organization as the modulation of external abiotic drivers on the internal topology of species interactions, using plant–plant interactions in terrestrial communities as a starting point. We then explore how this framing can help translate available data on species abundance and trait distributions to corresponding decisions in management. Given the expectation that community response and reorganization are highly complex, the external‐driver internal‐topology (EDIT) framework offers a way to capture general patterns of biodiversity that can help guide resilience and adaptation in changing environments. [ABSTRACT FROM AUTHOR]

Accurate forecasting of duty-free shopping demand plays a pivotal role in strategic and operational decision-making processes. Despite the extensive literature on sustainability, operations management, and consumer behavior in the context of duty-free shopping, there is a noticeable absence of an integrated end-to-end solution for precise demand forecasting. Furthermore, existing forecasting models often encounter limitations in effectively leveraging multi-source data as reliable indicators for duty-free shopping demand. To address these gaps, our study introduces a pioneering deep-learning architecture known as the Attention-Aided Interaction-Driven Long Short-Term Memory-Convolutional Neural Network Model (AI-LCM). Designed to capture intricate cross-correlations within multi-source data, encompassing search queries, COVID-19 impact, economic factors, and historical data; this model represents a significant methodological advancement. Rigorous evaluation against state-of-the-art benchmarks conducted on robust real-world datasets confirms the superior forecasting performance exhibited by our AI-LCM model. We elucidate the manifold implications for various stakeholders while illustrating the extensive applicability of our model and its potential to inform data-driven decision-making strategies. [ABSTRACT FROM AUTHOR]

This research proposes a new forecasting model for time series with important improvements. The first improvement is the use of the variation between two consecutive times as a universal set and dividing it into intervals with an appropriate number using an automatic clustering technique. The second improvement is the establishment of fuzzy relationships between the built intervals and between each element in the series and these intervals. Finally, using the established relationships, a new forecasting rule is created. The model is presented step by step and detailed with numerical examples, and the proofs for algorithm convergence are provided. It outperforms existing models on well-known datasets including the M3 Competition with 3003 series and M4 Competition datasets with 100,000 series. Another important contribution of this study is the establishment of the R procedure to effectively apply the proposed model to real series. [ABSTRACT FROM AUTHOR]

Accurate mapping of winter wheat provides essential information for food security and ecosystem protection. Deep learning approaches have achieved promising crop discrimination performance based on multitemporal satellite imagery. However, due to the high dimensionality of the data, sequential relations, and complex semantic information in time-series imagery, effective methods that can automatically capture temporal-spatial features with high separability and generalizability have received less attention. In this study, we proposed a U-shaped CNN-Transformer hybrid framework based on an attention mechanism, named the U-Temporal-Spatial-Transformer network (UTS-Former), for winter wheat mapping using Sentinel-2 imagery. This model includes an "encoder-decoder" structure for multiscale information mining of time series images and a temporal-spatial transformer module (TST) for learning comprehensive temporal sequence features and spatial semantic information. The results obtained from two study areas indicated that our UTS-Former achieved the best accuracy, with a mean MCC of 0.928 and an F1-score of 0.950, and the results of different band combinations also showed better performance than other popular time-series methods. We found that the MCC (MCC/All) of the UTS-Former using only RGB bands decreased by 4.53 %, while it decreased by 13.36 % and 35.02 % for UNet2d-LSTM and CNN-BiLSTM, respectively, compared with that of all the band combinations. The comparison demonstrated that the proposed UTS-Former could capture more global temporal-spatial information from winter wheat fields and achieve greater precision in terms of local details than other methods, resulting in high-quality mapping. The analysis of attention scores for the available acquisition dates revealed significant contributions of both beginning and ending growth images in winter wheat mapping, which is valuable for making appropriate selections of image dates. These findings suggest that the proposed approach has great potential for accurate, cost-effective, and high-quality winter wheat mapping. [ABSTRACT FROM AUTHOR]

Fram Strait is one of the main gateways for fresh water leaving the Arctic Ocean toward the deep‐water formation regions of the North Atlantic. Monitoring transport through Fram Strait is important to quantify the impact of Arctic amplification on the hydrography in lower latitudes. We update existing time series from the moorings in the western Fram Strait and investigate the monthly and interannual variability of the liquid freshwater transport (FWT, reference salinity 34.9), volume transport and freshwater content between 2003 and 2020. We examine composites and correlations of sea‐level pressure (SLP) reanalysis, and remote‐sensing dynamic‐ocean topography (DOT) in the Arctic Ocean. We identify two remote forcing mechanisms of FWT: (a) North Pole convergence freshens the region north of Fram Strait 13–24 months before high FWT events. (b) Beaufort Gyre weakening allows spreading of fresh water to the margins of the Arctic Basin zero to 9 months before high FWT events. In addition a third mechanism occurs locally, (b) Fram Strait northerly winds confine freshwater to the Greenland shelf and drive stronger southward FWT. Additionally, we find a decreasing trend in the total volume transport, concurrent with weakening northerly winds and reducing north‐south DOT gradient across the strait. We also examined correlations between the Fram Strait time series and the Arctic Oscillation and Arctic Ocean Oscillation. Both are found to correlate positively with the total volume transport, while the Arctic Oscillation correlates negatively with FWT with 1‐year lag. Plain Language Summary: The East Greenland Current brings fresh water from the central Arctic Ocean to lower latitudes. The exported fresh water affects stratification, and can contribute to variations of the global meridional overturning circulation. In Fram Strait, between Greenland and Svalbard, the properties of this current have been systematically monitored using moored instruments. We present updated time series of freshwater transport from the moorings in the Fram Strait, and analyze their variability between 2003 and 2020. We identify three mechanisms that contribute to high freshwater transport in the Strait. (a) 13–24 months before, clockwise wind anomalies in the Eurasian Arctic drive converging current anomalies and freshen the area preconditioning fresh outflow events. (b) 0–9 months before, anticlockwise wind anomalies in the Canadian Arctic drive diverging current anomalies directing fresh water to the periphery and Fram Strait. (c) Northerly winds over the strait drive southward transport instantly. We find additionally that total volume transport in the Fram Strait decreases in relation to weakening northerlies that could be a result of a warming Greenland. Key Points: Fram Strait local northerly winds force instant southward volume and freshwater transportArctic Ocean large‐scale wind variability forces two distinguished lagged responses of freshwater content and transport in Fram StraitBetween 2004 and 2019 freshwater transport shows no trend but total volume transport of the East Greenland Current decreases by ∼0.1 SV/year [ABSTRACT FROM AUTHOR]

Copyright of Bearing is the property of Bearing Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Health Sciences / Sağlık Bilimleri Dergisi is the property of Erciyes Universitesi Saglik Bilimleri Dergisi and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Time series anomaly detection is an important field of data science. Statistical, distance-based, clustering-based, or density-based approaches can detect anomalies. Generally, distance-based methods are relatively straightforward, but the method's effectiveness depends on how well they handle the distribution of data points. To address the challenge, a preprocessing step is used to convert the underlying time series into a more useful format. In this paper, a novel clustering-based representation of time series is proposed. This representation is then used to compute anomaly scores and detect anomalies. Experimental studies on synthetic and real datasets show that proposed method outperforms other methods by up to 75% for five standard performance metrics. [ABSTRACT FROM AUTHOR]

In the context of fundamental flow studies, experimental databases are expected to provide uncertainty margins on the measured quantities. With the rapid increase in available computational power and the development of high-resolution fluid simulation techniques, Direct Numerical Simulation and Large Eddy Simulation are increasingly used in synergy with experiments to provide a complementary view. Moreover, they can access statistical moments of the flow variables for the development, calibration, and validation of turbulence models. In this context, the quantification of statistical errors is also essential for numerical studies. Reliable estimation of these errors poses two challenges. The first challenge is the very large amount of data: the simulation can provide a large number of quantities of interest (typically about 180 quantities) over the entire domain (typically 100 million to 10 billion of degrees of freedom per equation). Ideally, one would like to quantify the error for each quantity at any point in the flow field. However, storing a long-term sequence of signals from many quantities over the entire domain for a posteriori evaluation is prohibitively expensive. The second challenge is the short time step required to resolve turbulent flows with DNS and LES. As a direct consequence, consecutive samples within the time series are highly correlated. To overcome both challenges, a novel economical co-processing approach to estimate statistical errors is proposed, based on a recursive formula and the rolling storage of short-time signals. [ABSTRACT FROM AUTHOR]

Many time series data mining algorithms work by reasoning about the relationships the conserved shapes of subsequences. To facilitate this, the Matrix Profile is a data structure that annotates a time series by recording each subsequence's Euclidean distance to its nearest neighbor. In recent years, the community has shown that using the Matrix Profile it is possible to discover many useful properties of a time series, including repeated behaviors (motifs), anomalies, evolving patterns, regimes, etc. However, the Matrix Profile is limited to representing the relationship between the subsequence's shapes. It is understood that, for some domains, useful information is conserved not in the subsequence's shapes, but in the subsequence's features. In recent years, a new set of features for time series called catch22 has revolutionized feature-based mining of time series. Combining these two ideas seems to offer many possibilities for novel data mining applications; however, there are two difficulties in attempting this. A direct application of the Matrix Profile with the catch22 features would be prohibitively slow. Less obviously, as we will demonstrate, in almost all domains, using all twenty-two of the catch22 features produces poor results, and we must somehow select the subset appropriate for the domain. In this work, we introduce novel algorithms to solve both problems and demonstrate that, for most domains, the proposed C22MP is a state-of-the-art anomaly detector. [ABSTRACT FROM AUTHOR]

Introduction: Low birth weight (LBW) is a global issue prevalent in low-income countries. Economic assessments of interventions to reduce this burden are crucial to guide health policies. However, there is a relative scarcity of research that illustrates the magnitude of LBW by country and region to support the design of public policies. Objective: This study aimed to analyze the temporal trend of fetal growth in newborns in Brazil between 2010 and 2020. Methods: A time series study was conducted using data from the Live Births Information System (SINASC), which is managed by the Department of Information and Informatics of the Unified Health System (DATASUS) of the Brazilian Ministry of Health. The Prais-Winsten linear model was applied to analyze the annual proportions of LBW. The annual percentage changes (APC) and their respective 95% confidence intervals (95%CI) were calculated. Prevalence rate averages of LBW were calculated and displayed on thematic maps to visualize the evolution dynamics in each Federation Unit (FU). Results: A total of 31,887,329 women from all Federative Units of Brazil were included in the study from 2010 to 2020. The Southeast region had the largest proportion of participants, with records from 2015 accounting for 9.5% of the total. Among the women in the study, 49.6% were between the ages of 20 and 29, and the majority (75.5%) had between 8 and 12 years of schooling. The newborns of these women were predominantly male (58.8%) and non-white (59.5%). The study found that there was a trend towards stabilization of increasing proportions of LBW in the North, Northeast, and Centre-West regions between 2010 and 2020. In Brazil and other regions, these tendencies remained stable. Conclusion: To improve living conditions and reduce social inequalities and health inequities, public policies and actions are necessary. Strengthening the Unified Health System (SUS), income transfer programs, quota policies for vulnerable groups, and gender equality measures such as improving access to education for women and the labor sector are among the suggested approaches. [ABSTRACT FROM AUTHOR]

Traffic forecasting is a crucial task of an Intelligent Transportation System (ITS), which remains very challenging as it is affected by the complexity and depth of the road network. Although the decision‐makers focus on the accuracy of the top‐level roads, the forecasts on the lower levels also improve the overall performance of ITS. In such a situation, a hierarchical forecasting strategy is more appropriate as well as a more accurate prediction methods to reach an efficient forecast. In this paper, we present a deep learning (DL) approach for hierarchical forecasting of traffic flow by exploring the hierarchical structure of the road network. The proposed approach is considered an improved variation on the top‐down strategy for the reconciliation process. We propose a model based on two deep neural network components to generate a coherent forecast for the total number of road segments. We use N‐BEATS, a pure deep learning forecasting method, at the highest levels for traffic time series, then disaggregate these downwards to get coherent forecasts for each series of the hierarchy using a combination of CNN and LSTM. Experiments were carried out using Beijing road traffic dataset to demonstrate the effectiveness of the approach. [ABSTRACT FROM AUTHOR]

This paper proposes a novel explainable artificial intelligence (AI) driven ensemble machine learning (ML) framework for predicting fertilizer price movements and assessing the contributions of the technical and macroeconomic indicators. We integrate the Boruta algorithm, Maximal Overlap Discrete Wavelet Transformation (MODWT), Random Forest (RF), and explainable AI. The predictive analytics exercise utilises the residual of the previous stage as an additional indicator for arriving at the subsequent stage forecasts. We observe a significant influence of the residual in providing forecasts for time series with higher frequencies. The explainable AI is used at the global and local levels to explain the impacts of the indicators on fertilizer price movements. We have used monthly urea and diammonium phosphate (DAP) prices for nearly the last 30 years for predictive analytics. The explainable AI identifies the more significant impacts of the technical indicators compared to macroeconomic counterparts in forecasting urea and DAP prices at the global level. Also, the price movements of urea and DAP are similar at the global level. On the contrary, macroeconomic indicators influence more at the local level. The CBOE volatility index for urea, geopolitical risk, and commodity industrial input for DAP significantly influence the price movements at the local level. [ABSTRACT FROM AUTHOR]

The missing readings in various sensors of air pollution monitoring stations is a common issue. Those missing sensor readings may greatly influence the performance of monitoring and analysis of air pollution data. To address this problem, in this paper, a multi-view based missing value (MV) imputation method called MVDI (Multi-View Data Imputation) is proposed for air pollution related time series data. MVDI combines four models namely LSTM (Long-Short Term Memory), IDS (Inverse Distance Squared), SVR (Support Vector Regressor), and KNN (K-Nearest Neighbors) to estimate MVs. These four models are mainly employed to capture the variations in data from different views of the dataset. Here, different views represent different portions (subsets) of the actual dataset. The estimates of MVs from all the views are combined using a kernel function to get an overall result. The proposed model MVDI is evaluated on real-world air pollution dataset in terms of RMSE, MAE, MAPE, and R2. The experimental results show that MVDI dominates over the baseline methods namely AR (AutoRegressive), ARIMA (AutoRegressive Integrated Moving Average), RFR (Random Forest Regressor), ANN (Artificial Neural Network), LI (Linear Interpolation), NN (Nearest Neighbors), MI (Mean Imputation), CNN (Convolutional Neural Network), ConvLSTM (Convolutional LSTM). [ABSTRACT FROM AUTHOR]

With technological advancements, much data is being captured by sensors, smartphones, wearable devices, and so forth. These vast datasets are stored in data centres and utilized to forge data‐driven models for the condition monitoring of infrastructures and systems through future data mining tasks. However, these datasets often surpass the processing capabilities of traditional information systems and methodologies due to their significant size. Additionally, not all samples within these datasets contribute valuable information during the model training phase, leading to inefficiencies. The processing and training of Machine Learning algorithms become time‐consuming, and storing all the data demands excessive space, contributing to the Big Data challenge. In this paper, we propose two novel techniques to reduce large time‐series datasets into more compact versions without undermining the predictive performance of the resulting models. These methods also aim to decrease the time required for training the models and the storage space needed for the condensed datasets. We evaluated our techniques on five public datasets, employing three Machine Learning algorithms: Holt‐Winters, SARIMA, and LSTM. The outcomes indicate that for most of the datasets examined, our techniques maintain, and in several instances enhance, the forecasting accuracy of the models. Moreover, we significantly reduced the time required to train the Machine Learning algorithms employed. [ABSTRACT FROM AUTHOR]

Graph neural networks (GNNs) have gained significant attention in diverse domains, ranging from urban planning to pandemic management. Ensuring both accuracy and robustness in GNNs remains a challenge due to insufficient quality data that contains sufficient features. With sufficient training data where all spatiotemporal patterns are well-represented, existing GNN models can make reasonably accurate predictions. However, existing methods fail when the training data are drawn from different circumstances (e.g., traffic patterns on regular days) than test data (e.g., traffic patterns after a natural disaster). Such challenges are usually classified under domain generalization. In this work, we show that one way to address this challenge in the context of spatiotemporal prediction is by incorporating domain differential equations into graph convolutional networks (GCNs). We theoretically derive conditions where GCNs incorporating such domain differential equations are robust to mismatched training and testing data compared to baseline domain agnostic models. To support our theory, we propose two domain-differential-equationinformed networks: Reaction-Diffusion Graph Convolutional Network (RDGCN), which incorporates differential equations for traffic speed evolution, and the Susceptible-Infectious-Recovered Graph Convolutional Network (SIRGCN), which incorporates a disease propagation model. Both RDGCN and SIRGCN are based on reliable and interpretable domain differential equations that allow the models to generalize to unseen patterns. We experimentally show that RDGCN and SIRGCN are more robust with mismatched testing data than state-of-the-art deep learning methods. [ABSTRACT FROM AUTHOR]

Background: Female breast cancer stands as the prime type of cancer in the Kingdom of Saudi Arabia (KSA), with a high incidence and mortality rates. This study assessed the burden of female breast cancer in KSA by analyzing and forecasting its incidence, mortality, and disability-adjusted life years (DALYs). Methods: We retrieved data from the Global Burden of Disease (GBD) about female breast cancer from 1990 to 2021. Time-series analysis used the autoregressive integrated moving average (ARIMA) model to forecast female breast cancer statistics from 2022 to 2026. Results: From 1990 to 2021, KSA reported 77,513 cases of female breast cancer. The age groups with the highest number of cases are 45–49 years, followed by 40–44 years, 50–54 years, and 35–39 years. The analysis also showed fewer cases in the younger age groups, with the lowest number in the less than 20-year-old age group. From 1990 to 2021, KSA reported 19,440 deaths due to breast cancer, increasing from 201 cases in 1990 to 1,190 cases in 2021. The age-standardized incidence rate/100,000 of breast cancer increased from 15.4 (95% confidence interval (CI) 11.2–21.0) in 1990 to 46.0 (95%CI 34.5–61.5) in 2021. The forecasted incidence rate of female breast cancer will be 46.5 (95%CI 45.8–46.5) in 2022 and 49.6 (95%CI 46.8–52.3) in 2026. The age-standardized death rate per 100,000 Saudi women with breast cancer increased from 6.73 (95%CI 6.73–9.03) in 1990 to 9.77 (95%CI 7.63–13.00) in 2021. The forecasted female breast cancer death rate will slightly decrease to 9.67 (95%CI 9.49–9.84) in 2022 and to 9.26 (95%CI 8.37–10.15) in 2026. DALYs increased from 229.2 (95%CI 165.7–313.6) in 1990 to 346.1 (95%CI 253.9–467.2) in 2021. The forecasted DALYs of female breast cancer will slightly decrease to 343.3 (95%CI 337.2–349.5) in 2022 reaching 332.1 (95%CI 301.2–363.1) in 2026. Conclusions: Female breast cancer is still a significant public health burden that challenges the health system in KSA, current policies and interventions should be fashioned to alleviate the disease morbidity and mortality and mitigate its future burden. [ABSTRACT FROM AUTHOR]

Wind power forecasting techniques have been well developed over the last half-century. There has been a large number of research literature as well as review analyses. Over the past 5 decades, considerable advancements have been achieved in wind power forecasting. A large body of research literature has been produced, including review articles that have addressed various aspects of the subject. However, these reviews have predominantly utilized horizontal comparisons and have not conducted a comprehensive analysis of the research that has been undertaken. This survey aims to provide a systematic and analytical review of the technical progress made in wind power forecasting. To accomplish this goal, we conducted a knowledge map analysis of the wind power forecasting literature published in the Web of Science database over the last 2 decades. We examined the collaboration network and development context, analyzed publication volume, citation frequency, journal of publication, author, and institutional influence, and studied co-occurring and bursting keywords to reveal changing research hotspots. These hotspots aim to indicate the progress and challenges of current forecasting technologies, which is of great significance for promoting the development of forecasting technology. Based on our findings, we analyzed commonly used traditional machine learning and advanced deep learning methods in this field, such as classical neural networks, and recent Transformers, and discussed emerging technologies like large language models. We also provide quantitative analysis of the advantages, disadvantages, forecasting accuracy, and computational costs of these methods. Finally, some open research questions and trends related to this topic were discussed, which can help improve the understanding of various power forecasting methods. This survey paper provides valuable insights for wind power engineers. [ABSTRACT FROM AUTHOR]

Time series similarity matrices (informally, recurrence plots or dot-plots), are useful tools for time series data mining. They can be used to guide data exploration, and various useful features can be derived from them and then fed into downstream analytics. However, time series similarity matrices suffer from very poor scalability, taxing both time and memory requirements. In this work, we introduce novel ideas that allow us to scale the largest time series similarity matrices that can be examined by several orders of magnitude. The first idea is a novel algorithm to compute the matrices in a way that removes dependency on the subsequence length. This algorithm is so fast that it allows us to now address datasets where the memory limitations begin to dominate. Our second novel contribution is a multiscale algorithm that computes an approximation of the matrix appropriate for the limitations of the user's memory/screen-resolution, then performs a local, just-in-time recomputation of any region that the user wishes to zoom-in on. Given that this largely removes time and space barriers, human visual attention then becomes the bottleneck. We further introduce algorithms that search massive matrices with quadrillions of cells and then prioritize regions for later examination by either humans or algorithms. We will demonstrate the utility of our ideas for data exploration, segmentation, and classification in domains as diverse as astronomy, bioinformatics, entomology, and wildlife monitoring. [ABSTRACT FROM AUTHOR]