This paper addresses the evolving landscape of electricity markets in Europe, with a focus on the integration of Renewable Energy Communities as introduced by the Renewable Energy Directive 2018/2001. Residents within a postal code area are highly incentivized to join a community, which enables them to exchange energy among themselves at lower procurement costs. Thereby, energy management systems optimize the operation of respective energy systems, with electrical load forecasting playing a key role. Given that prosumers may switch between communities on a daily basis, electricity demands within these groups will vary, leading to data that is non-stationary, discontinuous as well as non-identical and independently distributed. To encounter this issue, we propose a sophisticated forecasting model that applies federated learning, using informations from various distributed communities to learn domain-invariant features. To achieve this, we initially utilize synthetic electrical load time series at district level and aggregate them to profiles of Renewable Energy Communities with dynamic portfolios. Subsequently, we develop a forecasting model that accounts for the composition of residents of a Renewable Energy Community, adapt data pre-processing in accordance with the time series process, and detail a federated learning algorithm that incorporates weight averaging and data sharing. Following the training of various experimental setups, we ultimately evaluate their effectiveness. The findings suggest that our proposed framework is capable of effectively forecast non-stationary and discontinuous time series and that it can be applied to new, unseen data through the integration of knowledge from multiple sources.

The definition of UTC in 1972 balanced the needs of the time and frequency community for a universal time scale that was traceable to the definition of frequency in the SI system of units with the needs of the astronomical community for a time scale that was closely linked to UT1, a time scale related to the rotation of Earth. The balance between these two considerations has changed very significantly since 1972, and there is widespread agreement that the method of relating UTC to UT1 should be changed by increasing the maximum tolerance between the two scales to more than the current limit of 0.9 s. I propose to realize this decision by means of an algorithmic adjustment process based on the variation in the length of the day over the previous centuries. I use these historical data to extrapolate the length of the day for a century into the future, and to compute a periodic rate adjustment to UTC based on this extrapolation. The adjustment process will not use time steps. The magnitude of the periodic rate adjustment will be re-considered every century, but the basic adjustment algorithm will not change. I suggest a maximum tolerance between UT1 and UTC that is large enough to absorb the irregular and unpredictable variations in the length of the day with respect to the long-term average increase in this value but plays no role in determining the parameters of the adjustment process that is proposed. I also propose that the adjustment be implemented at 12 UTC on 1 January since that is closest to a universal holiday in all time zones.

MIMO (multiple-input multiple-output) radar provides much more flexibility than the traditional radar for its ability to realize far more observation channels than the actual number of T/R (transmit and receive) elements. Designing the array of MIMO imaging radar, the commonly used virtual array theory generally assumes that all elements are placed on the same line. However, due to the physical size of the antennas and coupling effect between T/R elements, a certain height difference between T/R arrays is essential, resulting in the defocusing of edge points of the scene. On the other hand, the virtual array theory implies far-field approximation, leading to inevitable high grating lobes in the imaging result of near-field edge points of the scene observed by common MIMO array. To tackle these problems, this paper derives the relationship between target’s PSF (point spread function) and pattern of T/R arrays, by which the design criterion of near-field imaging MIMO array is presented. Firstly, the proper height between T/R arrays is designed to focus the near-field edge points well. Secondly, the far-field array is modified to suppress the grating lobes in the near-field area. Finally, the validity of the proposed methods is verified by simulations and an experiment.

Recognizing the need to enhance immune cells' ability to target and eliminate tumor cells by focusing on tumor-associated antigens is crucial for the success of immunotherapy. Numerous cell-based therapies, such as CAR-T cell therapy, tumor-infiltrating lymphocyte (TIL) therapy, CAR-NK cell therapy, and T-cell receptor (TCR)-based therapies, are currently undergoing clinical and pre-clinical evaluation across various cancer types. However, a significant challenge lies in managing the inflammatory responses that are harmful to cancer patients. To overcome this, developing advanced strategies to target tumor cells precisely while preserving immune balance in cancer patients is imperative. One promising approach involves using modified tumor-associated macrophages (TAMs), which constitute approximately 50% of the tumor microenvironment (TME) and play a pivotal role in tumor progression. CAR-Macrophage (CAR-M) therapy is an emerging potential asset of immunotherapy for a wide range of tumors.

The current work reveals the fine tuning between stability zones and randomness of Pointwise Stationary Fluid Flow Approximation (PSFFA) model of the non-stationary queueing D/M/1 system. More specifically, this clearly provides more insights into developing a contemporary PSFFA theory that unifies non-stationary queueing theory with chaos theory and fields in both theoretical physics and chaotic systems. This opens new grounds for stability analysis of non-stationary queueing systems.

While the beneficial effects of using magnetic and electromagnetic treatment (ET) of brackish and saline waters on soil salinity reduction in the root zone were widely reported more studies are needed to answer questions about the soil salt leaching efficiency and the effect of the duration of the exposure to ET. For this aim, pot experiments were conducted using an Aqua-4DR physical water treatment device. The first experiment included two trials. The first considered 5 concentrations: C0:1.0; C1:4.5; C2:9; C3:13.5; and C4:18 dSm-1. The results revealed that the volume and the salt concentrations of the drained waters were significantly higher under irrigation with ET saline waters than those provided by untreated waters. The drained fraction of water varied from 20 to 26% under irrigation with untreated water and increased from 33 to 56% under irrigation with electromagnetized water indicating an improvement of salt leaching. The second trial was carried out with different irrigation doses. The result showed that the higher the dose, the more obvious and significant ET effect. The different treatment durations of water exposure revealed that the volume and salinity of drained water significantly increase as the ET duration increases. An increase in ET duration induces also an increase in soil water content of around 2.5%. Based on the experimental findings, we may conclude that the ET of saline water can reduce the adverse effect of salinity on the top soil, but these leached salts are carried away in depth and there is no concentration limit of water to the effect of the ET.

The European Green Deal poses a two-pronged challenge for the automotive industry: migrating to solutions based in light structures, requiring light weight concepts and light materials, while at the same time avoiding dependence towards the importation of these advanced materials. Aluminium alloys are lightweight and cost-effective materials that can successfully cover the requirements of many structural applications, however their production requires from bauxite and other Critical Raw Materials (CRM), such as Si and Mg. Aluminium alloys are fully recyclable, but scrap is usually contaminated and its use is related to an increment of impurities, tramp element and undesired inclusions. Traditionally, the use of secondary alloys has been restricted to low performance applications. The present work analyses the effect that the use of scrap has in the quantity of inclusions present in the alloy and in other properties relevant for the material processing. The study was carried out for common alloys belonging to 3 of the most common aluminium processes used in the car manufacturing industry: High Pressure Die Casting (HPDC) (EN AC-43500), extrusion (6063) and sheet metal forming (5754 and 6181). Reference alloy were mixed with different level of scrap (0, 20, 40, 60, 80 and 100%) trying to keep the chemical composition as unaffected as possible. The inclusions level of the alloy was characterized with the Prefil Foot-printer® test. In addition, the obtained materials, after being cast in an open mould, were subjected to metallographic characterization. Relevant properties to assess the formability quality of the alloys for the corresponding transforming process, were obtained: flowability test for HPDC alloy and high temperature compression for extrusion alloys. The results obtained suggest that the number of inclusions present in the melt highly increase with the amount of scrap used to produce the alloy. These inclusions are also related with an important lost of flowability, but do not have a noticeable impact on microstructure.

In the field of railroad safety, effective detection of surface cracks is critical, necessitating reliable, high-speed non-destructive testing (NDT) methods. This study introduces a hybrid Eddy Current Testing (ECT) probe, specifically engineered for railroad inspection, to address the common issue of ’lift-off noise’ due to varying distances between the probe and test material. Unlike traditional ECT methods, this probe integrates transmit and differential receiver coils, aiming to enhance detection sensitivity and minimize lift-off impact. The study optimizes ECT probes employing different driver coils, emphasizing three main objectives: a) quantitatively evaluating each probe using signal- to-noise ratio (SNR) and outlining a real-time data processing algorithm based on SNR methodology; b) exploring the frequency range proximal to the electrical resonance of the receiver coil; c) examining sensitivity variations across varying lift-off distances. The experimental outcomes indicate that the newly designed probe with figure 8-shape driver coil significantly improves sensitivity in detecting surface cracks on railroads. It achieves an impressive SNR exceeding 100 for defects with minimal dimensions of 1 mm in width and depth. Simulation results closely align with experimental findings, validating the investigation of optimal operational frequency and lift-off distance for selected probe performance, determined to be 0.3 MHz and 0.5 mm, respectively. The realization of this project would lead to notable advancements in enhancing railroad safety by improving crack detection efficiency.

Quadruped robots possess significant mobility in complex and uneven terrains due to their outstanding stability and flexibility, making them highly suitable in rescue missions, environmental monitoring, and smart agriculture. With the increasing use of quadruped robots in more demanding scenarios, ensuring accurate and stable state estimation in complex environments has become particularly important. Existing state estimation algorithms relying on multi-sensor fusion, such as those using IMU, LiDAR, and visual data, often face challenges on non-stationary terrains due to issues like foot-end slippage or unstable contact, leading to significant state drift. To tackle this problem, this paper introduces a state estimation algorithm that integrates an Invariant Extended Kalman Filter (InEKF) with a disturbance observer, aiming at estimating the motion state of quadruped robots on non-stationary terrains. Firstly, foot-end slippage is modeled as a deviation in body velocity and explicitly included in the state equations, allowing for a more precise representation of how slippage affects the state. Secondly, the state update process integrates both foot-end velocity and position observations to improve the overall accuracy and comprehensiveness of the estimation. Lastly, a foot-end contact probability model, coupled with an adaptive covariance adjustment strategy, is employed to dynamically modulate the influence of the observations. These enhancements significantly improve the filter's robustness and the accuracy of state estimation in non-stationary terrain scenarios. Experiments conducted with the Jueying Mini quadruped robot on various non-stationary terrains show that the enhanced InEKF method offers notable advantages over traditional filters in compensating for foot-end slippage and adapting to different terrains.

We have implemented quantum modeling mainly based on Bohmian Mechanics to study time series that contain strong coupling between their events. Compared to time series with normal densities, such time series are associated with rare events. Hence, employing Gaussian statistics drastically underestimates the occurrence of their rare events. The central objective of this study is to investigate the effects of rare events in the probability densities of time series from the point of view of quantum measurements. For this purpose, we first model the non-Gaussian behavior of time series using the multifractal random walk (MRW) approach. Then, we examine the role of the key parameter of MRW, λ, which controls the degree of non-Gaussianity, in quantum potentials derived for time series. Our Bohmian quantum analysis shows that the derived potential takes some negative values in high frequencies (its mean values), then substantially increases, and the value drops again for rare events. Thus, rare events can generate a potential barrier in the high-frequency region of the quantum potential, and the effect of such a barrier becomes prominent when the system transverses it. Finally, as an example of applying quantum potential beyond the microscopic world, we compute quantum potentials for the S&P financial market time series to verify the presence of rare events in the non-Gaussian densities and demonstrate deviation from the Gaussian case.

This study aims to spatially analyze the distribution characteristics of vacant homes in Asan-si, Chungcheongnam-do, and understand the differences in factors causing vacant homes by type. We use a variety of statistical methods to examine these factors and identify key influencing factors such as the number of vacant stores, changes in overall population, land use complexity, and physical characteristics of land and buildings. The findings reveal that the factors contributing to the occurrence of vacant homes vary significantly by region and property type, highlighting the need for region-specific policies. For instance, in old town areas, small lot ratios and land use complexity are significant, while in rural village, the average number of floors and land use complexity play a major role. This study underscores the diversity of factors influencing vacant homes, suggesting that policies should be tailored to the unique characteristics of different regions to effectively address this issue.

In this paper, we study the asymptotic behavior of the sequential empirical process and the sequential empirical copula process, both constructed from residuals of multivariate stochastic volatility models. Applications for the detection of structural changes and specification tests of the distribution of innovations are discussed. It is also shown that if the stochastic volatility matrices are diagonal, which is the case if the univariate time series are estimated separately instead of being jointly estimated, then the empirical copula process behaves as if the innovations were observed; a remarkable property. As a by-product, one also obtains the asymptotic behavior of rank-based measures of dependence applied to residuals of these time series models.

Leishmaniasis is the third most common vector-borne disease and a very important protozoan infection. Cutaneous leishmaniasis is one of the most common types of leishmaniasis infectious diseases with up to 2 million occurrences of new cases each year worldwide. A dynamic transmission multivariate time series model was applied to the data to account for overdispersion and evaluate the effects of three environmental layers as well as seasonality in the data. Furthermore, ecological niche modeling was used to investigate the geographical suitable conditions for cutaneous leishmaniasis using temperature, precipitation and altitude as environmental layers, together with the leishmaniasis presence data. A retrospective analysis of the cutaneous leishmaniasis spatial data in Afghanistan between 2003 and 2009 indicates a steady increase from 2003 to 2007, a small decrease in 2008, then another increase in 2009. An upward trend and regularly repeating patterns of highs and lows was observed related to the months of the year which suggests seasonality effect in the data. Two peaks were observed in the disease occurrence-- January to March and September to December -- which coincide with the cold period. Ecological niche modelling indicates that precipitation has the greatest contribution to the potential distribution of leishmaniasis.

As one of the typical deposits in Sichuan-Yunnan-Guizhou Pb-Zn metallogenic province, the Daliangzi Pb-Zn deposit has a close genetic relation with the structural system of “black/fracture zone” formed under the action of NWW-approx. EW strike-slip structures in the metallogenic province, but the mechanism of rock and ore-controlling action of the structural system remains unclear. Based on detailed analysis of tectonite-mineralized alteration lithofacies of R1 “black/fracture zone”, the tectonite-mineralized alteration lithofacies zones can be divided into 4 types in succession outward from the Pb-Zn mineralization center, i.e., ① brecciated and stockwork-like Pb-Zn mineralization-complex breccia facies zone, ② stockwork-like Pb-Zn mineralization-simple breccia and cataclasite facies zone, ③ veined pyrite-sulfide-dolomitic cataclasite facies zone, and ④ fine-veined calcite-black carbonized dolomite facies zone; Cl- and SO42--rich high-temperature oxidizing ore-bearing fluid mixes with reducing fluid in Zone ① while migration and precipitation occur in Zone ④. With the evolution of ore-forming fluid, the homogenization temperature decreases from Zone ① to Zone ④, the salinity increases from Zone ① to Zone ② and then decreases to Zones ③ and ④, and the fluid density has little change on the whole; the contents of Zn, Pb, Cu, Ga, Ge, Cd, Ag, and other metallogenic elements, the Zn/Pb ratio, and the CaO/MgO mole ratio decrease gradually from Zone ① to Zone ④; and REE fractionation, calcilization, silicification, and pyritization enhance gradually from Zone ① to Zone ④. This series of changes are the product of diapirism (cryptoexplosion) of strike-slip structures and “black/fracture zone”, among which the second-order structures (F5, F100, and other faults) derived from NWW-approx. EW striking dextral shear-tension faults F1 and F15 control the brecciated and stockwork-like Pb-Zn mineralized complex breccia facies zones and the stockwork-like Pb-Zn mineralized simple breccia and cataclasite facies zones. Therefore, this paper establishes the zoning mode of tectonite-mineralized alteration lithofacies of “black/fracture zone” and proposes that Zones ① and ② are important prospecting criteria. conclusions.

Recommendation systems are crucial in navigating the vast digital market. However, user data’s dynamic and non-stationary nature often hinders their efficacy. Traditional models struggle to adapt to the evolving preferences and behaviours inherent in user interaction data, posing a significant challenge for accurate prediction and personalisation. Addressing this, we propose a novel theoretical framework, the Non-stationary Transformer, designed to capture and leverage the temporal dynamics within data effectively. This approach enhances the traditional transformer architecture by introducing mechanisms accounting for non-stationary elements, offering a robust and adaptable solution for recommendation systems. Our experimental analysis, encompassing deep learning and reinforcement learning paradigms, demonstrates the framework’s superiority over benchmark models. The empirical results confirm the efficacy of our proposed framework, which not only provides significant performance enhancements, approximately 8% in Logloss reduction and up to 2% increase in F1 score but also underscores its potential applicability across accumulative reward scenarios. These findings advocate adopting Non-stationary Transformer models to tackle the complexities of today’s recommendation tasks.

The current paper is devoted to the introduction of simpler Eulerian variational principles from which all the relevant equations of non-barotropic stationary magnetohydrodynamics can be derived for magnetic fields which lie on surfaces. A variational principle is given in terms of three independent variables for stationary non-barotropic magnetohydrodynamic flows. This is a smaller number of variables than the eight variables which appear in the standard equations of non-barotropic magnetohydrodynamics which are the magnetic field, the velocity field, the specific entropy and the density. We further investigate the case in which the flow along magnetic lines is not ideal.

Accurate forecasting and efficient management of commodities are crucial for stakeholders in the industry, given the volatile nature of these markets. This study addresses these needs by leveraging advanced forecasting techniques and machine learning models to predict prices and enhance supply chain efficiency. TThe focus is on utilizing ARIMA, SARIMAX, and LSTM models to analyze historical trading data for commodities such as cocoa, coffee, and sugar sourced from Kaggle’s comprehensive dataset. The research applies ARIMA and SARIMAX models to forecast price trends, overcoming initial challenges related to data index frequency and seasonality. LSTM models are employed for more nuanced demand forecasting, particularly for random-length lumber, demonstrating the model's capability to predict future market trends accurately. The study highlights significant improvements in prediction accuracy and supply chain management through meticulous feature engineering and model optimization, offering valuable insights for strategic decision-making in the supply chain sector.

In this study, we present a novel approach to estimate the Hurst exponent of time series data using a variety of machine learning algorithms. The Hurst exponent is a crucial parameter in characterizing long-range dependence in time series, and traditional methods such as Rescaled Range (R/S) analysis and Detrended Fluctuation Analysis (DFA) have been widely used for its estimation. However, these methods have certain limitations, which we sought to address by modifying the R/S approach to distinguish between fractional Lévy and fractional Brownian motion, and by demonstrating the inadequacy of DFA and similar methods for data that resembles fractional Lévy motion. This inspired us to utilize machine learning techniques to improve the estimation process. In an unprecedented step, we train various machine learning models, including LightGBM, MLP, and AdaBoost, on synthetic data generated from random walks, namely fractional Brownian motion and fractional Lévy motion, where the ground truth Hurst exponent is known. Meaning that we can initialize and create these stochastic processes with a scaling Hurst/scaling exponent which, is then used as the ground truth for training. Furthermore, we perform the continuous estimation of the scaling exponent directly from the time series, without resorting to the calculation of the power spectrum or other sophisticated preprocessing steps, as done in past approaches. Our experiments reveal that the machine learning-based estimators outperform traditional R/S analysis and DFA methods in estimating the Hurst exponent, particularly for data akin to fractional Lévy motion. Validating our approach on real-world financial data, we observe a divergence between the estimated Hurst/scaling exponents and results reported in the literature. Nevertheless, the confirmation provided by known ground truths reinforces the superiority of our approach in terms of accuracy. This work highlights the potential of machine learning algorithms for accurately estimating the Hurst exponent, paving new paths for time series analysis. By marrying traditional finance methods with the capabilities of machine learning, our study provides a novel contribution towards the future of time series data analysis.

The current work reveals the fine tuning between stability zones and randomness of GI/M/1 Pointwise Stationary Fluid Flow Approximation (PSFFA) model of the non-stationary D/M/1 queueing system. More specifically, this clearly provides more insights into developing a contemporary PSFFA theory that unifies non-stationary queueing theory with chaos theory and fields in both theoretical physics and chaotic systems. This opens new grounds for stability analysis of non-stationary queueing systems. A notable application of GI/M/1 queueing model to achieve ultra-low latency of autonomous driving service is highlighted. Concluding remarks associated with future avenues of research are given.

Catastrophic mass flows originating from the high mountain cryosphere often cause hazard cascades. With increasing human activities in the alpine region and the sensitivity of glaciers, snow and permafrost to climate warming, the cryospheric hazard risks tend to be more active in the Tibetan Plateau(TP). The remoteness and inaccessibility of high mountain regions make the remote sensing technology the most effective approach for monitoring and investigating the cryospheric hazards. Exploring the evolution process and impact of ice avalanches and subsequent hazards are crucial to understand drivers and nature of mass flow process chain in order to prevent and mitigate potential hazard consequences. In this study, the glacier and ice-rock avalanches occurred in Arutso and Sedongpu basins in Tibet were investigated on the basis of Sentinel-2 time-series images and in-situ investigation, the evolution process of these events were reconstructed, and impacts and driving factors were analyzed. The massive Chamoli rock-ice avalanche occurred in February 2021 in the western Himalayas was also reviewed using using same methods. The study shows that Arutso glacier No. 53 (Arutso-53) avalanche completely melted away in July 2018 after two years from occurrence to final disappearance, while Arutso glacier No. 50 (Arutso-50) avalanche completely melted by the end of August 2023 after lasting for seven years. Four large-scale ice-rock avalanche and debris flow events in the Sedongpu basin in 2017 and 2018 not only had significant impacts on the river flow, landscape and geomorphologic shape in the basin, but also caused serious disasters in the basin and downstream. In March 2021, a small-scale ice-rock avalanche and debris flow event occurred again in the Sedongpu basin. The glacier and ice-rock avalanches occurred in Tibet area were mainly induced by climate warming, heavy precipitation and seismic activity, which acting on specific topographic and geomorphic structure of glacier properties in the high mountain regions. Catastrophic hazard events originating from the high-elevation glacier and ice-rock collapses in the mountain cryosphere and subsequent hazard cascades in the TP and Himalayas highlight the importance of mountain hazard monitoring, early warning systems and sustainable mountain development.

This paper provides the first-time ever analytic modelling for Pointwise Stationary Fluid Flow Approximation(PSFFA) model of the non-stationary

The relaxation process of lithium batteries caused by load variation is considered. It is shown that such processes have strong dependence on internal physical and chemical processes and battery technical conditions. Theoretical expressions of the relaxation process caused by a step-like load variation have been obtained for 1^st and 2^nd order equivalent electrical circuits. The experimental investigations show that the obtained models fit the real relaxation processes and the behavior of the identified parameters could be explained by specific features of physical and chemical processes within the lithium battery. It should be noted that the obtained results can be generalized for a different type of electrochemical power source. The proposed approach makes it possible to provide means for electrochemical power source characterization and diagnostic, the main advantages of which are good time localization of measurement procedures and inexpensive apparatus implementation.

We propose a novel approach for time series forecasting with many predictors, referred to as the GO-sdPCA, in this paper. The approach employs a variable selection method known as the group orthogonal greedy algorithm and the high-dimensional Akaike information criterion to mitigate the impact of irrelevant predictors. Moreover, a novel technique, called peeling, is used to boost the variable selection procedure so that many factor-relevant predictors can be included in prediction. Finally, the supervised dynamic principal component analysis (sdPCA) method is adopted to account for the dynamic information in factor recovery. In simulation studies, we found that the proposed method adapts well to unknown degrees of sparsity and factor strength, which results in good performance even when the number of relevant predictors is large compared to the sample size. Applying to economic and environmental studies, the proposed method consistently performs well compared to some commonly used benchmarks in one-step-ahead out-sample forecasts.

The anomaly detection task is very important in computer science. And there are a lot of anomaly detection methods. Different from some thresholding methods, some unsupervised methods could make us get more accurate and faster result, which is the object of the project. In this paper, I tried to use EWMA and some other methods in two datasets: Webank time consuming indicators dataset and AIOps Challenge dataset. The paper consists nine parts: background of the project, related work, description of algorithms, implementation details, experimental setup and data sets used, experimental results and discussion, future directions, reference and meeting notes.

This article is devoted to methods of processing random processes. Of particular relevance is the task of processing broadband non-stationary random processes. The processing of random processes is usually related to the assessment of their probabilistic characteristics. Very often, a non-stationary broadband random process is represented by a single implementation in a priori uncertainty about the type of distribution function. Such random processes occur in information and measuring communication systems in which information is transmitted at a real time pace (for example, radio telemetry systems of spacecraft). The use of methods of traditional mathematical statistics, for example, maximum likelihood methods to determine probability characteristics, in this case is not possible. The article discusses a method of processing non-stationary broadband random processes based on the use of non-parametric methods of decision theory. An algorithm for dividing the observation interval into stationary intervals using non-parametric Kendall statistics is considered, as well as methods for estimating probabilistic characteristics on the stationary interval using ordinal statistics. The article presents the results of statistical modeling using the Mathcad program.

When dealing with limited sample sizes or missing values in time series data, achieving high accuracy in forecasting becomes challenging. This challenge is particularly common in wind energy forecasting, where many wind farms lack complete data. In this paper, we employ the widely-used ARIMA (Autoregressive Integrated Moving Average) model for time series forecasting. To address the difficulties posed by limited sample sizes and missing values, we adopt a unique approach by utilizing multiple ARIMA models for different datasets. A key distinction from other multiple models methods for time series forecasting lies in each model within our approach using its own dataset, making the fusion process more intricate. To overcome this, we incorporate neural networks and two techniques for model fusion: direct fusion with a learning mechanism and compensation for missing data through training. For each ARIMA model, we introduce a noise estimation method to circumvent the white noise assumptions inherent in ARIMA models. Finally, we apply these methods to wind energy prediction, and our experimental results showcase a significant enhancement in forecasting accuracy.

Time series forecasting has been a challenging area in the field of Artificial Intel-ligence. Various approaches such as linear Neural Networks, Recurrent Linear Neural Networks, Convolutional Neural Networks and recently Transformers have been attempted for the time series forecasting domain. Although, Trans-former-based architectures have been outstanding in the Natural Language Pro-cessing domain, especially in autoregressive language modeling, the initial at-tempts to use transformers in the time series arena have met with mixed success. One of the recent papers demonstrated that modeling the multi-variate time se-ries problem as independent channels on a transformer architecture produced lower mean square and mean absolute errors on benchmarks, however, another recent paper claimed that a simple linear neural network out-performs previous approaches including transformer-based designs. We investigate this paradox in detail comparing the linear Neural Network and Transformer based designs, provide insights to why a certain approach may be better for a particular type of problem. We also improve upon the recently proposed simple linear Neural Network based architecture by using dual pipelines with batch normalization and reversible instance normalization. Our enhanced architecture outperforms all existing architectures for time series forecasting on majority of the popular benchmarks.

Due to increase demand of food grain in the world, assessment of yield before actual production is important in making policies and decisions in agricultural production system. For a large area, forecast models developed from vegetation indices derived from remote sensing satellite data possesses the potential to give quantitative and timely information on crops over large areas. Different vegetation indices are being made used for this purpose, however, their efficiency in estimating crop yield is needed to be certainly tested. In this study, wheat yield forecast was derived by regressing ground truthing yield data against time series of spatial vegetation indices for the 2013 to 2019 growing seasons. These spatial vegetation indices derived from Landsat 8 image data: Normalized Difference Vegetation Index (NDVI) and Soil Adjusted Vegetation Index (SAVI) were compared to evaluate the most appropriate index that performs better in forecasting wheat production at Karcag, Kunhegyes and Ecsegfalva settlements in Jász-Nagykun-Szolnok county, in the Northern Great Plain region of central Hungary. The best time for making wheat yield prediction with Landsat 8- SAVI and NDVI was found to be the beginning of ripening period (160th day of the year) with higher correlation between the vegetation indices and the wheat yield. The validation results revealed that the model from SAVI provides more consistent and accurate forecasts yield compared to NDVI. The SAVI model forecast yield for the validation years, 2018 and 2019 were within 6.00% and 4.41% of the final reported values while that of NDVI model were within 8.31% and 6.27%. Nash-Sutcliffe efficiency index is positive with E1= 0.99 for the model from SAVI and for NDVI, E1=0.57, which connote that the forecasting method developed and evaluated performs acceptable forecast efficiency.

Noise model selection criteria has a significant impact on identifying the stochastic noise proper-ties of any GNSS daily coordinate time series. The low-frequency random walk noise existing in these time series could lead to overestimation of the tectonic rate, so it is of great significance to accurately detect the random walk component. This study focuses on noise model estimation cri-terion (BIC_tp) derived from the AIC and the BIC by introducing 2π factors. It is more sensitive to abnormal steps (random jumps). Using observation data from 72 GNSS stations from 1992 to 2022 and simulated data, four combined noise models are used to explore the impacts of time se-ries lengths (ranging from2 to 24 years) and data loss (between 2% and 30%) on noise models and velocity estimation. The results show that as the time length increased, the selected optimal noise model, and the estimated uncertainty of the tectonic trend with different data gap, gradually con-verge. When the time length is short (less than 8 years), it could lead to the FNRWWN, FNWN, and PLWN models being mistakenly estimated as GGMWN models, thereby affecting the accura-cy of determining the station velocity parameters. When the time length is 12 years, the RW noise component is more probably detected, As the time length increases, the impact of RW on velocity uncertainty is weakened. Finally, we conclude that for a time series with a minimum time length of 12 years, both the selection of the optimal stochastic noise model and the estimation of the ve-locity parameters are reliable.

The purpose of this project is to explore the potential of Long Short-Term Memory (LSTM), a type of recurrent neural network (RNN), as a tool for making directional predictions for assets. The focus will be on using LSTM for classifying up/down moves in stock indices, stocks, and FX rates (EUR/USD). Various financial ratios, advanced technical indicators, and volatility estimators will be used as features to enhance the predictive power of the model. Incorporating credit spreads and news indicators can also improve the model. The advantage of LSTM is its ability to handle sequences of arbitrary length, which means that longer time frames such as 5-day, 10-day, or 1-week returns can be used for prediction. Before using RNNs, exploratory data analysis (EDA) will be performed to understand the underlying patterns in the data. This may include dimensionality reduction techniques such as autoencoding, self-organizing maps, or decision tree regression. The results of the EDA will be used to guide the selection of features for the LSTM model. It is important to note that long memory and stationarity are common characteristics of time series data, such as interest rates or economic indicators. Power-law autocorrection, Hurst exponent fractional, or Markov processes may be used to model these data. Predicting 5-day, 10-day returns for equities or 1-week, 1-month returns for financial factors presents two challenges. First, a large amount of data is required, typically 7–10 years of data. Second, positive autocorrelation in the 5-day or 10-day returns in equity time series must be isolated.

We study the problem of predicting time series data using the autoregressive integrated moving average (ARIMA) model in an online manner. Existing algorithms require model selection, which is time consuming and inapt for the setting of online learning. Using adaptive online learning techniques, we develop algorithms for fitting ARIMA models with fewest possible hyperparameters. We analyse the regret bound of the proposed algorithms and examine their performance using experiments on both synthetic and real world datasets

Time irreversibility, i.e. the lack of invariance of the statistical properties of a system under time reversal, is a fundamental property of all systems operating out of equilibrium. Time reversal symmetry is associated with important statistical and physical properties and is related to the predictability of the system generating the time series. Over the past fifteen years, various methods to quantify time irreversibility in time series have been proposed, but these can be computationally expensive. Here we propose a new method, based on permutation entropy, which is essentially parameter-free, temporally local, yields straightforward statistical tests, and has fast convergence properties. We apply this method to the study of financial time series, showing that stocks and indices present a rich irreversibility dynamics. We illustrate the comparative methodological advantages of our method with respect to a recently proposed method based on visibility graphs, and discuss the implications of our results for financial data analysis and interpretation.

We propose novel spectrometer designs that aim to enhance the measured spectral range 1 of ions on a finite-sized detector. In contrast to the traditional devices that use uniform magnetic 2 field, in which the deflection of particles increases inversely proportional to their momentum, in a 3 gradient magnetic field, the deflection of particles will be decreased due to the reduction of the 4 magnetic field along their propagation. Low energy ions are particularly impacted, as they are 5 deflected less and are more likely to reach the detector compared to being driven out of it while 6 using a uniform magnetic field. By the means of a gradient magnetic field, the nonlinear dispersion 7 of ions in a homogeneous magnetic field can approach a nearly linear dispersion. Nonetheless, 8 the dispersion of low energy ions in a homogeneous magnetic field remains unnecessarily high. 9 In this article, we explore linear, quadratic, and higher-order field profiles in comparison to the 10 homogeneous field case. We discuss the employed methodology and present simulation results of 11 the spectrometer with an extended ion spectral range, focusing on the minimum detectable energy 12 (energy dynamic range) and energy resolution

In this paper, we compile the fractional power series method and the Laplace transform to design a new algorithm for solving the fractional Volterra integro-differential equation. For that, we assume the Laplace power series (LPS) solution in terms of power q=1m,m∈Z+, where the fractional derivative of order α=qγ for which γ∈Z+. This assumption will help us to write the integral, the kernel, and the nonhomogeneous terms as a LPS with the same power. The recurrence relations for finding the series coefficients can be constructed using this form. To demonstrate the algorithm's accuracy, the residual error is defined and calculated for several values of the fractional derivative. Two strongly nonlinear examples are discussed to provide the efficiency of the algorithm. The algorithm gains powerful results for this kind of problem. Under Caputo meaning the obtained results are illustrated numerically, and graphically. Geometrically, the behavior of the solution declares that the changing of the fractional derivative parameter values' in their domain alters the style of the attained solution in a symmetrical meaning and fully coinciding to the ordinary derivative value'. From these simulations, the results report that the recommended novel algorithm is a straightforward, accurate, and superb tool to generate analytic-approximate solutions for Integral, and integro-differental equations of fractional order.

The aim of this work is to analyze and investigate the shape preserving properties of ternary 4-point non-stationary interpolating subdivision schemes constructed by Beccari et al. [1] with a tension parameter !k+1 which can reproducing exponential. Moreover, the conditions on the initial control points are developed that allow user to generate shape preserving limit curves after a nite number of subdivision steps and generalize these results in limiting case. Signicance of derived conditions are illustrated through graphs and the whole discussion is followed by examples.

This work focuses on analyzing acoustic emission (AE) signals as a means to predict failure in structures. Two main approaches are considered: (i) long-range correlation analysis using both the Hurst (H) and the Detrended Fluctuation Analysis (DFA) exponents, and (ii) natural time domain (NT) analysis. These methodologies are applied to the data collected from two application examples: a glass fiber reinforced polymeric plate and a spaghetti bridge model, where both structures were subjected to increasing loads until collapse. A traditional (AE) signal analysis is also performed to reference the study of the other methods. Results indicate that the proposed methods yield a reliable indication of failure in the studied structures.

The aerospace industry develops prognosis and health management algorithms to ensure better safety on board. Particularly for in-flight controls where jamming is dreaded. For that, vibration signals are monitored to predict future defect occurrences. However, time series are not labeled according to severity level, and the user can only assess the system health from the data mining procedure. To that extent, we developed a clustering algorithm using a deep neural network core. We encoded the time series into pictures to be feed into an artificially trained neural network: U-NET. From the segmented output, one-dimensional information on cluster frontiers is extracted and filtered without any parameter selection. Then, a kernel density estimation finally transforms the signal into an empirical density. Ultimately, a Gaussian mixture model extracts the latter independent components. The method empowered us to reveal different degrees of severity faults in the studied data, with their respective likelihood without prior knowledge. We compared it to state-of-the-art machine learning algorithms. However, internal clustering results evaluation for time series is an open question. As state-of-the-art indexes were not producing relevant results, we built a new indicator to fulfill this task. We applied the whole method to an actuator consisting of an induction machine linked to a ball screw. This study lays the groundwork for future training of diagnosis and prognosis structures in the health management framework.

The goal of clustering is to identify common structures in a data set by forming groups of homogeneous objects. The observed characteristics of many economic time series motivated the development of classes of distributions that can accommodate properties such as heavy tails and skewness. Thanks to its flexibility, the Skewed Exponential Power Distribution (also called Skewed Generalized Error Distribution) ensures a unified and general framework for clustering possibly skewed and heavy tailed time series. This paper develops a clustering procedure of model-based type, assuming that the time series are generated by the same underlying probability distribution but with different parameters. Moreover, we propose to optimally combine the estimated parameters to form the clusters with an entropy weighing $k$-means approach. The usefulness of the proposal is showed by means of application to financial time series, demonstrating also how the obtained clusters can be used to form portfolio of stocks.

Measuring bias is important as it helps identify flaws in quantitative forecasting methods or judgmental forecasts. It can, therefore, potentially help improve forecasts. Despite this, bias tends to be under-represented in the literature: many studies focus solely on measuring accuracy. Methods for assessing bias in single series are relatively well-known and well-researched, but for datasets containing thousands of observations for multiple series, the methodology for measuring and reporting bias is less obvious. We compare alternative approaches against a number of criteria when rolling-origin point forecasts are available for different forecasting methods and for multiple horizons over multiple series. We focus on relatively simple, yet interpretable and easy-to-implement metrics and visualization tools that are likely to be applicable in practice. To study the statistical properties of alternative measures we use theoretical concepts and simulation experiments based on artificial data with predetermined features. We describe the difference between mean and median bias, describe the connection between metrics for accuracy and bias, provide suitable bias measures depending on the loss function used to optimise forecasts, and suggest which measures for accuracy should be used to accompany bias indicators. We propose several new measures and provide our recommendations on how to evaluate forecast bias across multiple series.

The removal of non-climatic biases, so-called inhomogeneities, from long climatic records needs sophistically developed statistical methods. One principle is that usually the differences between a candidate series and its neighbour series are analysed instead of directly the candidate series, in order to neutralize the possible impacts of regionally common natural climate variation on the detection of inhomogeneities. In most homogenization methods, two main kinds of time series comparisons are applied, i.e. composite reference series or pairwise comparisons. In composite reference series the inhomogeneities of neighbour series are attenuated by averaging the individual series, and the accuracy of homogenization can be improved by the iterative improvement of composite reference series. By contrast, pairwise comparisons have the advantage that coincidental inhomogeneities affecting several station series in a similar way can be identified with higher certainty than with composite reference series. In addition, homogenization with pairwise comparisons tends to facilitate the most accurate regional trend estimations. A new time series comparison method is presented here, which combines the use of pairwise comparisons and composite reference series in a way that their advantages are unified. This time series comparison method is embedded into the ACMANT homogenization method, and tested in large, commonly available monthly temperature test datasets.

In this paper, Lyapunov-Razumikhin technique, design of state-dependent switching laws, a fixed point theorem and variational methods are employed to derive the existence and the unique existence results of (globally) exponentially stable positive stationary solution of delayed reaction-diffusion cell neural networks under Dirichlet zero boundary value, including the global stability criteria \textbf{in the classical meaning}. Next, sufficient conditions are proposed to guarantee the global stability invariance of ordinary differential systems under the influence of diffusions. New theorems show that the diffusion is a double-edged sword in judging the stability of diffusion systems. Besides, an example is constructed to illuminate that any non-zero constant equilibrium point must be not in the phase plane of dynamic system under Dirichlet zero boundary value, or it must lead to a contradiction. Next, under Lipschitz assumptions on active function, another example is designed to prove that the small diffusion effect will cause the essential change of the phase plane structure of the dynamic behavior of the delayed neural networks via a Saddle point theorem. Finally, a numerical example illustrates the feasibility of the proposed methods.

Gradual disability worsening in Multiple Sclerosis (MS) is indicative of confirmed progression that mostly involves progression independent of relapse activity (PIRA) and is associated with neurodegeneration. Insights from pathology reveal grey matter involvement (neocortex, hippocampus, spinal cord, and deep grey matter structures) and microglia activation in early stages of MS. Cortical lesions result in thinning and atrophy and are considered accurate predictors of disability progression and cognitive decline.Neuroimaging biomarkers, such as high-resolution 7T MR images and TSPO-PET, have been examined for the detection of cortical pathology linked to cognitive deficits and thus progression, but are limited in clinical practice due to availability, time constraints, and cost.Electroencephalography (EEG) emerges as a non-invasive, cost-effective tool that reflects cortical activity in MS. Its potential in monitoring cognitive impairment is explored by focusing on nonlinear EEG analysis. The MuST PREDICT^TM project aims to extract linear and nonlinear EEG features, investigating their role in predicting disease progression and optimizing treatment. The study employs retrospective, cross-sectional, and prospective designs, utilizing EEGs from various MS forms, cognitive assessments, serum/cerebrospinal fluid biomarkers and neuroimaging. The methodology involves time-based and spectral feature extraction, employing artificial intelligence classifiers and brain criticality-based approaches.The conceptual framework of an innovative modality is herein presented, that would EEG for early MS progression detection. Standardization of the methodology could lead to the creation of a digital tool for better prognostication and treatment strategy optimization.

In recent years, transformer-based models have gained prominence in multivariate long-term time series forecasting (LTSF), demonstrating significant advancements despite facing challenges such as high computational demands, difficulty in capturing temporal dynamics, and managing long-term dependencies. The emergence of LTSF-Linear, with its straightforward linear architecture, has notably outperformed transformer-based counterparts, prompting a reevaluation of the transformer's utility in time series forecasting. In response, this paper presents an adaptation of a recent architecture termed extended LSTM (xLSTM) for LTSF. xLSTM incorporates exponential gating and a revised memory structure with higher capacity that has good potential for LTSF. Our adopted architecture for LTSF termed as xLSTMTime surpasses current approaches. We compare xLSTMTime's performance against various state-of-the-art models across multiple real-world datasets, demonstrating superior forecasting capabilities. Our findings suggest that refined recurrent architectures can offer competitive alternatives to transformer-based models in LTSF tasks, potentially redefining the landscape of time series forecasting.

While increasing empirical evidence suggests that global time series forecasting models can achieve better forecasting performance than local ones, there is a research void regarding when and why the global models fail to provide a good forecast. This paper uses anomaly detection algorithms and Explainable Artificial Intelligence (XAI) to answer when and why a forecast should not be trusted. To address this issue, a dashboard was built to inform the user regarding (i) the relevance of the features for that particular forecast, (ii) which training samples most likely influenced the forecast outcome, (iii) why the forecast is considered an outlier, and (iv) provide a range of counterfactual examples to understand value changes, in the feature vector or the predicted value, can lead to a different outcome. Moreover, a modular architecture and a methodology were developed to iteratively remove noisy data instances from the train set, to enhance the overall global time series forecasting model performance. Finally, to test the effectiveness of the proposed approach, it was validated on two publicly available real-world datasets.

The understanding of water quality and its underlying processes is important for the protection of aquatic environments enabling the rare opportunity of access to a domain expert. Hence, an explainable AI (XAI) framework is proposed that is applicable to multivariate time series resulting in explanations that are interpretable by a domain expert. The XAI combines in three steps a data-driven choice of a distance measure with explainable cluster analysis through supervised decision trees. The multivariate time series consists of water quality measurements, including nitrate, electrical conductivity, and twelve other environmental parameters. The relationships between water quality and the environmental parameters are investigated by identifying similar days within a cluster and dissimilar days between clusters. The XAI does not depend on prior knowledge about data structure, and its explanations are tendentially contrastive. The relationships in the data can be visualized by a topographic map representing high-dimensional structures. Two comparable decision-based XAIs were unable to provide meaningful and relevant explanations from the multivariate time series data. Open-source code in R for the three steps of the XAI framework is provided.

Real-world time series data sets contain a combination of linear and nonlinear patterns, making the time series forecasting problem more challenging. In this paper, a new hybrid methodology is introduced for forecasting univariate time series data sets using a multiplicative error modeling approach. An autoregressive integrated moving average (ARIMA) model is combined with an autoregressive neural network (ARNN) for improving the predictions of individual forecast models. The proposed multiplicative ARIMA-ARNN model glorifies the chances of capturing the different combinations of linear and nonlinear patterns in time series. The model shows outstanding performance on six standard time-series data sets compared to other widely used single and hybrid forecasting models.

In this paper, we study the usage of machine learning models for sales time series forecasting. The effect of machine learning generalization has been considered. A stacking approach for building regression ensemble of single models has been studied. The results show that using stacking technics, we can improve the performance of predictive models for sales time series forecasting.

We define a new seasonal forecasting method based on fuzzy transforms. We use the best interpolating polynomial for extracting the trend of the time series and generate the inverse fuzzy transform on each seasonal subset of the universe of discourse for predicting the value of a an assigned output. Like first example, we use the daily weather dataset of the municipality of Naples (Italy) starting from data collected from 2003 till to 2015 making predictions on the following outputs: mean temperature, max temperature and min temperature, all considered daily. Like second example, we use the daily mean temperature measured at the weather station “Chiavari Caperana” in the Liguria Italian Region. We compare the results with our method, the average seasonal variation, ARIMA and the usual fuzzy transforms concluding that the best results are obtained under our approach in both examples.

This study explores novel techniques to improve the detection accuracy of skarn iron deposits using advanced image processing methodologies. Leveraging the capabilities of Aster image, Band Ratio (BR) images, and Principal Component Analysis (PCA), alongside the power of 3D Convolutional Neural Networks (3D-CNN), the research aims to enhance the precision and efficiency of ore detection in complex geological environments. The proposed method employs a specific 3D-CNN architecture, accepting input as a 7×7×C image patch, where C represents the combined number of selected Aster image bands, Principal Component (PC) bands, and computed BR images. To evaluate the accuracy of the proposed method, five distinct image bands combinations, including the proposed bands combination, were tested and evaluated based on the overall accuracy (OA), average accuracy (AA), and kappa coefficient. The results demonstrated that while the incorporation of BR images alongside Aster bands initially seemed promising, it introduced significant confusion in certain classifications, leading to unexpected mis-classification rates. Surprisingly, utilizing solely Aster bands as input parameters yielded higher accuracy rates (OA= 93.13%, AA = 91.96%, Kappa = 90.91%) compared to scenarios involving the integration with band ratios (OA = 87.02%, AA = 79.15, and Kappa = 82.60%) or the integration of BR images to PC bands (OA= 87.78%, AA = 82.39%, Kappa = 83.81%). However, the amalgamation of Aster bands with selected PC bands showed slight improvements in accuracy (OA= 94.65%, AA = 92.93%, Kappa = 93.45%), although challenges in accurately classifying certain features persisted. Ultimately, the proposed combination of Aster bands, PC bands, and BR images (proposed bands combination) presented the most visually appealing and statistically accurate results (OA = 96.95%, AA= 94.87%, and Kappa = 95.93%), effectively addressing misclassifications observed in the other combinations. These findings underscore the synergistic contributions of each of the Aster bands, PC bands, and BR images, with Aster bands proving pivotal for optimal skarn classification, PC bands enhancing intrusions classification accuracy, and BR images strengthening wall rock classification accuracy. In conclusion, the proposed combination of input image bands emerges as a robust and comprehensive methodology, demonstrating unparalleled accuracy in the remote sensing detection of skarn iron minerals.

In recent experimental studies, we reported the aggravating effects of Asian sand dust (ASD) on male reproductive function in mice. However, the effects of fetal ASD exposure on male reproductive function have not been investigated. The present study investigated the effects of fetal ASD exposure on reproductive function in male offspring. Using pregnant CD-1 mice, ASD was administered intratracheally on days 7 and 14 of gestation, and the reproductive function of male offspring was determined at 5, 10, and 15 weeks after birth. The secondary sex ratio was significantly lower in the fetal ASD-exposed mice than in the controls. Histologic examination showed partial vacuolation of seminiferous tubules in immature mice. Moreover, daily sperm production (DSP) was significantly less in the fetal ASD-exposed mice than in the controls. DSP in the fetal ASD-exposed mice was approximately 10% less than the controls at both 5 and 10 weeks. However, both the histologic changes and the DSP decrease were reversed as the mice matured. These findings suggest that ASD exposure affects both the fetal development and the reproductive function of male offspring. In the future, it will be necessary to clarify the onset mechanisms of ASD-induced male fetus death and male reproductive disorders.

Accurate streamflow forecasting is crucial for effectively managing water resources, particularly in countries like Colombia, where hydroelectric power generation significantly contributes to the national energy grid. Although highly interpretable, traditional deterministic, physically-driven models often suffer from complexity and require extensive parameterization. Data-driven models like Linear Autoregressive (LAR) and Long Short-Term Memory (LSTM) networks offer simplicity and performance but cannot quantify uncertainty. This work introduces Sparse Variational Gaussian Processes (SVGPs) for forecasting streamflow contributions. The proposed SVGP model reduces computational complexity compared to traditional Gaussian Processes, making it highly scalable for large datasets. The methodology employs optimal hyperparameters and shared inducing points to capture short-term and long-term relationships among reservoirs. Training, validation, and analysis of the proposed approach consider the streamflow dataset from 23 geographically dispersed reservoirs recorded during twelve years in Colombia. Performance assessment reveals that the proposal outperforms baseline Linear Autoregressive (LAR) and Long Short-Term Memory (LSTM) models in three key aspects: adaptability to changing dynamics, provision of informative confidence intervals through Bayesian inference, and enhanced forecasting accuracy. Therefore, the SVGP-based forecasting methodology offers a scalable and interpretable solution for multi-output streamflow forecasting, thereby contributing to more effective water resource management and hydroelectric planning.

Multivariate Time Series Classification (MTSC) is one of most important tasks in time series analysis, aiding in activities such as human motion recognition and medical diagnostics. Existing methods for MTSC do not explicitly model temporal differences and generalize the idea of temporal difference into a efficient temporal module. Additionally, existing methods are not yet able to capture cross-variable relationships well during network training. As a result, they are unable to achieve convincing feature representation, leading to suboptimal classification accuracy. In this paper, we propose a novel MTSC model called Temporal Difference and Cross-variate Fusion Network (TDCFN), which integrates a two-stream differential LSTM network and a cross-variate feature extraction network to enhance feature representation. TDCFN achieves superior classification accuracy by capturing dynamic temporal evolution and inter-variable relationships. The experimental results show that TDCFN can achieve competitive performance with state-of-the-art multivariate time series classification approaches.

Early detection of wildfires has been limited using the sun-synchronous orbit satellites due to their low temporal resolution and wildfires’ fast spread in the early stage. NOAA’s geostationary weather satellites GOES-R can acquire images every 15 minutes at 2km spatial resolution, and have been used for early fire detection. However, advanced processing algorithms are needed to provide timely and reliable detection of wildfires. In this research, a deep learning framework, based on Gated Recurrent Units (GRU), is proposed to detect wildfires at early stage using GOES-R dense time series data. GRU model maintains good performance on temporal modelling while keep a simple architecture, makes it suitable to efficiently process time-series data. 36 different wildfires in North and South America under the coverage of GOES-R satellites are selected to assess the effectiveness of the GRU method. The detection times based on GOES-R are compared with VIIRS active fire products at 375m resolution in NASA’s Fire Information for Resource Management System (FIRMS). The results show that GRU-based GOES-R detections of the wildfires are earlier than that of the VIIRS active fire products in most of the study areas. Also, results from proposed method offer more precise location on the active fire at early stage than GOES-R Active Fire Product in mid-latitude and low-latitude regions.

The evaluation of geometric defects is necessary in order to maintain the integrity of structures over time. These assessments are designed to detect damages of structures and ideally help inspectors to estimate the remaining life of structures. Current methodologies for monitoring structural systems, while providing useful information about the current state of a structure, are limited in the monitoring of defects over time and in linking them to predictive simulation. This paper presents a new approach to the predictive modeling of geometric defects. A combination of segmented from point clouds are parametrized using the convex hull algorithm to extract features from detected defects, and a stochastic dynamic model is then adapted to these features to model the evolution of the hull over time. Describing a defect in terms of its parameterized hull enables consistent temporal tracking for predictive purposes, while implicitly reducing data dimensionality and complexity as well. In this study, 2D point clouds analogous to information derived from point clouds were first generated over simulated life-cycles. The evolutions of point cloud hull parameterizations were modeled as stochastic dynamical processes via autoregressive integrated moving average (ARIMA) and vectorized autoregression (VAR) and compared against ground truth. The results indicate that this convex hull approach provides consistent and accurate representations of defect evolution across a range of defect topologies and is reasonably robust to noisy measurements, however assumptions regarding the underlying dynamical process play a significant the role in predictive accuracy. The results were then validated on experimental data from fatigue testing with high accuracy. Longer term, the results of this work will support finite element model updating for predictive analysis of structural capacity.

The aim of this study is to analyze the characteristics of drought such as intensity, cumulative curves and trends, based on SPEI (Standardized Precipitation Evapotranspiration Index) at 8 stations in Korea from 1981 to 2010. The traditional SPEI is based on Thornthwaite equation for estimating evapotranspiration; SPEI_th. However, a standard of agricultural water management in Korea suggests FAO Penman-Monteith equation; SPEI_pm. In this study, we analyzed the intensity and trends of drought using SPEI_th and SPEI_pm, respectively, and analyzed the relationship between them. Both of central and southern region, the SPEIs were below -1.0 (moderated drought) for the periods May-August in the representative drought year such as 1988, 2001, and 2008-09. The frequency of drought was higher in southern region than central region. In addition, SPEI_pm showed slightly more intensive drought rather than SPEI_th except for Chuncheon and Gwangju. In 5 stations except for Cheoncheon, Gwangju and Jinju, the cumulative probability that SPEI_pm is below -1.5 was significantly increased from 1981-1995 to 1996-2010. As the results of drought trends, the increasing trend of SPEIs was shown on fall season, and the cumulative probability that SPEI_pm is below -1.5 was also significantly increased.

In this study, the generality and prediction accuracy of a generalised series model for large eddy simulation of premixed and non-premixed turbulent combustion is explored. The model is based on Taylor series expansion of the chemical source term in scalar space and implemented into OpenFOAM. The mathematical model does not depend on the combustion regimes, and has the correct limiting behaviour. The numerical error sources are outlined and analysed. The model is first applied to a piloted methane/air non-premixed jet flame (Sandia Flame D). The statistical (time-averaged and RMS) results agree well with experimental measurements, particularly with regard to the mixture fraction, velocity, temperature, and concentrations of major species CH4, CO2, H2O, and O2. The concentrations of intermediates CO and H2 are over-predicted, due to the limitations of the reduced reaction mechanism employed. Then, a Bunsen piloted flame is simulated. Most of the statistical properties of both reactive species and progress variable are well reproduced. The only major discrepancy evident is in the temperature, which is attributed to the experimental uncertainties of temperature fields in the pilot stream. These findings have demonstrated the model`s generality for both premixed and non-premixed combustion simulation, as well as the accuracy of prediction of reactive species distribution.

Microplastics (plastic particles < 5 mm) are ubiquitous pollutants that pose the ability to carry microbiota, including pathogens. Microbial adhesion is usually a sign of pathogenicity, thus we investigated the adherent strains found on 4 mm nylon strips, which were ingested and excreted by wild fish specimens. Polymer analysis of the excreted samples shown no signs of degradation, nor have their controls, represented by the nylon strips submerged in the same water tanks. Both the ingested samples and controls presented pathogens in large numbers, revealing the fact that nylon microplastics can be physical carriers for pathogens in the aquatic environment.

This paper explores the application of machine learning in financial time series analysis, focusing on predicting trends in financial enterprise stocks and economic data. It begins by distinguishing stocks from stocks and elucidates risk management strategies in the stock market. Traditional statistical methods such as ARIMA and exponential smoothing are discussed in terms of their advantages and limitations in economic forecasting. Subsequently, the effectiveness of machine learning techniques, particularly LSTM and CNN-BiLSTM hybrid models, in financial market prediction is detailed, highlighting their capability to capture nonlinear patterns in dynamic markets. The study demonstrates the advancements in predictive accuracy and robustness achieved by deep learning methods through empirical analysis and model validation. The findings contribute significantly to academic discourse and offer practical insights for investors, financial analysts, and policymakers navigating market volatility and optimizing investment strategies. Finally, the paper outlines prospects for machine learning in financial forecasting, laying a theoretical foundation and methodological framework for achieving more precise and reliable economic predictions.

Mechanically homogenized composite of expanded graphite and cobalt(II) rhenate(VII) has been described. Cobalt(II) rhenate(VII) was obtained in a reaction of perrhenic acid with cobalt(II) nitrate. A simple mortar homogenization method was used to enhance intercalation of cobalt species within carbon matrix. The specific capacity of composite was enhanced by 50% in comparison to bare expanded graphite. The electrochemical characteristic was significantly improved including better cyclability, lower resistance of electrode material, lower iR drop, with respect to expanded graphite without cobalt(II) rhenate(VII) active species. Expanded graphite with its unique specific surface area and pore size diameter was proved as potential and cheap carbon support.

Background: Although confirmed cases of infection with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) have been declining since late 2020 due to general vaccination, little research has been done regarding the impact of vaccines against SARS-CoV-2 in Spain in terms of hospitalizations and deaths. Objective: Our aim was to identify the reduction in severity and mortality of coronavirus disease 2019 (COVID-19) at a nationwide level due to vaccination. Methods: We designed a retrospective, population-based study to define waves of infection and to describe the characteristics of the hospitalized population. We also studied the rollout of vaccination and its relationship with the decline in hospitalizations and deaths. Finally, we developed two mathematical models to estimate non-vaccination scenarios using machine learning modeling (with the ElasticNet and RandomForest algorithms). The vaccination and non-vaccination scenarios were eventually compared to estimate the number of averted hospitalizations and deaths. Results: In total, 498,789 patients were included, with a global mortality of 14.3%. We identified six waves or epidemic outbreaks during the observed period. We established a strong relationship between the beginning of vaccination and the decline in both hospitalizations and deaths due to COVID-19 in all age groups. We also estimated that vaccination prevented 170,959 hospitalizations (CI 95% 77,844–264,075) and 24,546 deaths (CI 95% 2,548–46,543) in Spain between March 2021 and December 2021. We estimated a global reduction of 9.19% in total deaths during the first year of COVID-19 vaccination. Conclusions: Demographic and clinical profiles changed over the first months of the pandemic. Patients over 80 years old and other age groups obtained clinical benefit from early vaccination. The severity of COVID-19, in terms of hospitalizations and deaths, decreased due to vaccination.

Due to the long duration and high cost of traditional pumping tests, the response of well water level to seismic wave, earth tide, and barometric pressure provides a feasible method for determining continuous changes in aquifer hydraulic parameters. Aiming at the problem that the response phase shift of well BB water level to tidal tide M2 is greater than that of tide O1, this paper preferentially calculated the time series changes of S, Be, n and BKu based on the response mechanism of well water level to barometric pressure and earth tide and with the help of smooth moving method. Then by using the mixed flow model, the variation of transmissivity and leakage coefficient over time were simultaneously obtained, and the evolution process and characteristics of aquifer parameters near well BB caused by the Wenchuan earthquake were ultimately discussed. The calculation results are basically consistent with the previous pumping test, and have been verified and compared by using other scholars' methods. This solving process avoids the problems such as excessive dependence on initial values, multiple solutions, and unstable tide O1, which has a promoting effect on the study of the impact of seismic activity on aquifer systems.

The present article addresses the long-standing problem of the polymer brush bilayers under stationary shear flow at non-linear response regime where the system gets a non-Newtonian fluid. The main idea behind this research would be the fact that the immense lubricity of the polymer brush bilayers originates from a global restructuring that takes place at large shear rates. It is shown here that physical quantities like, stress tensor, viscosity tensor, the friction coefficient and the chain extensions could become dependent on the shear rate at non-Newtonian regime. Apparently, the sub-linear scaling of the physical quantities at large shear rates is solely due to the fact that the chains stretch in the shear direction.

Machine learning methods have widely been applied to detect anomalies in machine and cutting tool behavior during lathe or milling. However, detecting anomalies in the workpiece itself did not get the same attention by researchers. That is why in this article, the authors present a pub-licly available multivariate time series dataset which was recorded during milling of 16MnCr5. Due to artificially introduced, though realistic anomalies in the workpiece the dataset can be ap-plied for anomaly detection. By using a convolutional autoencoder as a first model good results in detecting the location of the anomalies in the workpiece were achieved. Furthermore, milling tools with two different diameters where used which led to a dataset eligible for transfer learn-ing. The objective of this article is to provide researchers with a real-world time series dataset of the milling process which is suitable for modern machine learning research topics like anomaly detection and transfer learning.

Time series data are significant and are derived from temporal data, which involve real numbers representing values collected regularly over time. Time series have a great impact on many types of data. However, time series have anomalies. We introduce hybrid algorithm named novel matrix profile (NMP) to solve the all-pairs similarity search problem for time series data. The proposed NMP inherits the features from two state-of-the art algorithms: similarity time-series automatic multivariate prediction (STAMP), and short text online microblogging protocol (STOMP). The proposed algorithm caches the output in an easy-to-access fashion for single- and multidimensional data. The proposed NMP algorithm can be used on large data sets and generates approximate solutions of high quality in a reasonable time. The proposed NMP can also handle several data mining tasks. It is implemented on a Python platform. To determine its effectiveness, it is compared with the state-of-the-art matrix profile algorithms i.e., STAMP and STOMP. The results confirm that the proposed NMP provides higher accuracy than the compared algorithms.

Traditional applications of Interferometric Synthetic Aperture Radar (InSAR) data involved inverting an interferogram stack to determine the average displacement velocity. While this approach has useful applications in continuously deforming regions, much information is lost by simply fitting a line through the time series. Thanks to regular acquisitions across most of the the world by the ESA Sentinel-1 satellite constellation, we are now in a position to explore opportunities for near-real time deformation monitoring. In this paper we present a simple statistical approach for detecting offsets and gradient changes in InSAR time series. Our key assumption is that 5 years of Sentinel-1 data is sufficient to calculate the population standard deviation of the detection variables. Our offset detector identifies statistically significant peaks in the first, second and third difference series. The gradient change detector identifies statistically significant movements in the second derivative series. We exploit the high spatial resolution of Sentinel-1 data and the spatial continuity of geophysical deformation signals to filter out false positive detections that arise due to signal noise. When combined with near-real time processing of InSAR data these detectors, particularly the gradient change, could be used to detect incipient ground deformation associated with geophysical phenomena, for example from landslides or volcanic eruptions.

Modern energy systems collect high volumes of data that can provide valuable information about energy consumption. Electric companies can now use historical data to make informed decisions on energy production by forecasting the expected demand. Many deep learning models have been proposed to deal with these type of time series forecasting problems. Deep neural networks, such as recurrent or convolutional, can automatically capture complex patterns in time series data and provide accurate predictions. In particular, Temporal Convolutional Networks (TCN) are a specialised architecture that has advantages over recurrent networks for forecasting tasks. TCNs are able to extract long-term patterns using dilated causal convolutions and residual blocks, and can also be more efficient in terms of computation time. In this work, we propose a TCN-based deep learning model to improve the predictive performance in energy demand forecasting. Two energy-related time series with data from Spain have been studied: the national electric demand, and the power demand at charging stations for electric vehicles. An extensive experimental study has been conducted, involving more than 1900 models with different architectures and parametrisations. The TCN proposal outperforms the forecasting accuracy of Long Short-Term Memory (LSTM) recurrent networks, which are considered the state-of-the-art in the field.

The study of order patterns of three equally spaced values $x_t,x_{t+d},x_{t+2d}$ in a time series is a powerful tool. The lag $d$ is changed in a wide range so that differences of frequencies of order patterns become autocorrelation functions. Similar to a spectrogram in speech analysis, four ordinal autocorrelation functions are used to visualize big data series, as for instance heart and brain activity over many hours. The method applies to real data without preprocessing, outliers and missing data do not matter. On the theoretical side, we study properties of order correlation functions and show that the four autocorrelation functions are orthogonal in a certain sense. An analysis of variance of a modified permutation entropy can be performed with four variance components associated with the functions.

This paper has three objectives, the first is to present a detailed overview in the form of a tutorial for the developments of several key quantile time series modelling approaches. The second objective is to develop a general framework to represent such quantile models in a unifying manner in order to easily develop extensions and connections between existing models that can then be developed to further extend these models in practice. In this regard, the core theme of the paper is to provide perspectives to a general audience of core components that go into construction of a quantile time series model and then to explore each of these core components in detail. The paper is not addressing the concerns of estimation of these models, as there is existing literature on these aspects in many settings, we provide references to relevant works on these aspects in several classes of model. Instead, the focus is rather to provide a unified framework to construct such models for practitioners, therefore the focus is instead on the properties of the models and links between such models from a constructive perspective. The third objective is to compare and discuss the application of the different quantile time series models on several sets of interesting demographic and mortality based time series data sets of relevance to life insurance analysis. The exploration included detailed mortality, fertility, births and morbidity data in several countries with more detailed analysis of regional data in England, Wales and Scotland.

Landsat and Sentinel-2 data archives provide ever-increasing amounts of satellite data for studying land cover and land use change (LCLUC) over the past four decades. However, the availability of cloud-, shadow-, and snow-free observations varies spatially and temporally due to climate and satellite data acquisition schemes. Spatio-temporal heterogeneity poses a major issue for some time-series analysis approaches, but can be addressed with pixel-based compositing that generates temporally equidistant cloud-free or near-cloud free synthetic images. Although much consideration is given to methods identifying the ‘best’ pixel value for each composite, determining the aggregation period receives less attention and is often done arbitrary, or based on expert intuition. Here, we evaluated data compositing windows ranging from five days to one year for 1984-2021 Landsat and 2015-2021 Sentinel‑2 time series across Europe. We considered separate and joint use of both data archives and analyzed spatio-temporal availability of composites during each calendar year and pixel-specific growing season. We reported mean annual composites’ availability investigating differences among biogeographical regions, checked feasibility of pan‑European analyses for three LCLUC applications based on annual, monthly and 10-day composites, and analyzed the shortest feasible compositing window ensuring ≥50% temporal data availability and interpolation of the remaining composites for individual years and across a variety of medium- and long‑term time windows. Our results highlighted low data coverage in the 1980s, 1990s, and in 2012, as well as spatial variability in data availability driven by climate and orbit overlaps, which altogether impact spatio-temporal consistency of medium- and long-term time series, limiting feasibility of some LCLUC analyses. We demonstrated that prior to 2011 monthly composites ensured overall 50-62% data coverage for each calendar year, and ~75% afterwards, with further increase to ~82% when Landsat and Sentinel-2 were combined. Temporal consistency of monthly composites was overall low and temporal interpolation augmenting up to 50% missing data each year and across a time window of interest, ensured feasibility of analyses. Applications based on shorter than monthly composites were challenging without joining Landsat and Sentinel‑2 archives after 2015, and beyond the Mediterranean biogeographical region. Using pixel-specific growing season data typically boosted data availability in most geographies and diminished most of the latitudinal differences, but feasibility of complete time series with sub-monthly compositing windows was still restricted to the most recent years, and required data interpolation. Overall, our analyses provided a detailed assessment of Landsat and Sentinel-2 data availability over Europe, and based on selected application examples, highlighted often lacking spatio-temporal consistency of time series with sub-monthly compositing windows and long-time periods, which might hinder feasibility of some LCLUC applications.

This study considers the change-point test problem for time series based on the self-normalization ratio statistic test, which is constructed using residuals obtained from a support vector regression (SVR)-autoregressive moving average (ARMA) model. Under the null hypothesis, the series is a stationary process, and our test statistic converges to a non-degenerate distribution. Under the alternative hypothesis, there are change-points in the time series, and the self-normalization test statistic diverges to infinity. The simulations show that our proposed new test has better finite sample performance than other SVR-based tests in the literature. Finally, we illustrate its usefulness by analyzing two actual data sets.

Soybean maturity is a trait of critical importance for the development of new soybean cultivars, nevertheless, its characterization based on visual ratings has many challenges. Unmanned aerial vehicles (UAVs) imagery-based high-throughput phenotyping methodologies have been proposed as an alternative to the traditional visual ratings of pod senescence. However, the lack of scalable and accurate methods to extract the desired information from the images remains a significant bottleneck in breeding programs. The objective of this study was to develop an image-based high-throughput phenotyping system for evaluating soybean maturity in breeding programs. Images were acquired twice a week, starting when the earlier lines began maturation until the latest ones were mature. Two complementary convolutional neural networks (CNN) were developed to predict the maturity date. The first using a single date and the second using the five best image dates identified by the first model. The proposed CNN architecture was validated using more than 15,000 ground truth observations from five trials, including data from three growing seasons and two countries. The trained model showed good generalization capability with a root mean squared error lower than two days in four out of five trials. Four methods of estimating prediction uncertainty showed potential at identifying different sources of errors in the maturity date predictions. The architecture used solves limitations of previous research and can be used at scale in commercial breeding programs.

Satellite Crop Detection technologies are focused on detection of different types of crops on the field in the early stage before harvesting. Crop detection is usually done on a time series of satellite data by classification of the desired fields. Currently, data obtained from Remote Sensing (RS) are used to solve tasks related to the identification of the type of agricultural crops, also modern technologies using AI methods are desired in the postprocessing part. In this challenge Sentinel-1 and Sentinel-2 time series data were used due to their periodic availability. Our focus was to develop methodology for classification of time series of Sentinel 2 and Sentinel 1 data and compare how accuracy of classification can be increased, but also how to guarantee availability of data. We analyse phenology of single crops and on the basis of this analysis we started to provide crop classification. Original crop classifications were made from Enhanced Vegetation Index (EVI) layers made from Sentinel-2 time-series data and then we added also . To increase accuracy we also integrate into the process parcel borders and provide classification of fields..

Mapping forest extent and forest cover classification are important for the assessment of forest resources in socio-economic as well as ecological terms. Novel developments in the availability of remotely sensed data, computational resources, and advances in areas of statistical learning have enabled fusion of multi-sensor data, often yielding superior classification results. Most former studies of nemoral forests fusing multi-sensor and multi-temporal data have been limited in spatial extent and typically to a simple classification of landscapes into major land cover classes. We hypothesize that multi-temporal, multi-censor data will have a specific strength in further classification of nemoral forest landscapes owing to the distinct seasonal patterns of the phenology of broadleaves. This study aimed to classify the Danish landscape into forest/non-forest and further into forest types (broadleaved/coniferous) and species groups, using a cloud-based approach based on multi-temporal Sentinel 1 and 2 data and machine learning (random forest) trained with National Forest Inventory (NFI) data. Mapping of non-forest and forest resulted in producer accuracies of 99% and 90 %, respectively. The mapping of forest types (broadleaf and conifer) within the forested area resulted in producer accuracies of 95% for conifer and 96% for broadleaf forest. Tree species groups were classified with producer accuracies ranging 34-74%. Species groups with coniferous species were the least confused whereas the broadleaf groups, especially Oak, had higher error rates. The results are applied in Danish National accounting of greenhouse gas emissions from forests, resource assessment and assessment of forest biodiversity potentials.

Sialylated milk oligosaccharides (SMOs) is the most important oligosaccharides in human milk oligosaccharides (HMOs), and have a multifunctional health benefit, and the most abundant SMOs are sialyllactose (SLs). The previous studies indicate that the growth of tumor cells, and angiogenesis on tumor tissues with Lewis lung carcinoma, melanoma, and colon carcinoma cells could be prevented by SL. Thus, it has been proposed that SL might be an ideal candidate for the development of anti-angiogenic drugs without any side effects. It has been proposed that the Sialic acid (Sia) can be produced through SL’s hydrolysis, and the dietary Sia is further transported to the brain and other tissues though blood for formation of CMP-Sia, the activated precursor of Sia, and then is catalyzed by polysialyltransferases (polySTs) for synthesis of polysialic acid (polySia) or polysialylation of neural cell adhesion molecule (NCAM). Thus, it’s necessary to study and develop new inhibitors, which not only modulate a proper balance between the gut health and neuros system development, but also inhibit the overexpression of polySia, and thus block the tumor cell migration. In this study, we proposed that 3’-SL and 6’-SL may be more ideal inhibitors comparing with two previous inhibitors, the low molecular weight heparin (LMWH) and cytidine monophosphate (CMP) in the previous studies.

Color change is the most obvious characteristic of tomato ripening stage and an important indicator of tomato ripening condition, which directly affects the commodity value of tomato. To visualize the color change of tomato fruit in mature stage, a gated recurrent unit network with an encoder-decoder structure that dynamically simulates tomato growth and development with time-dependent lines using tomato color and shape as real-time data was proposed in this paper. Firstly, the .json file was converted into a mask.png file, the tomato mask was extracted, and the tomato was separated from the complex background environment, and the tomato growth and development data set was successfully constructed. Then, a network of gated recurrent units with encoder-decoder structure was constructed to predict the future growth trend of tomato under different greenhouse temperatures. The experimental results showed that for the gated recurrent unit network of encoder-decoder structure proposed, when the hidden layer number was 1 and hidden layer number was 512, a high consistency and similarity between the model predicted image sequence and the actual growth and development image sequence would be realized, and the structural similarity index measure was 0.746. It was proved that when the average temperature was 24.93℃, the average soil temperature was 24.06℃, and the average light intensity was 11.26 Klux, the environment was the most suitable for tomato growth. The environmental data-driven tomato growth model was constructed to explore the growth status of tomato under different environmental conditions, thus to understand the growth status of tomato in time. The statement provided a theoretical foundation for determining the optimal greenhouse environmental conditions to achieve tomato maturity. And it offered recommendations for investigating the growth cycle of tomatoes, as well as technical assistance for standardized cultivation in solar greenhouses.

GNSS time series prediction plays a significant role in monitoring crustal plate motion, landslide detection, and maintenance of the global coordinate framework. Long Short-Term Memory (LSTM), a deep learning model has been widely applied in the field of high-precision time series prediction especially when combined with Variational Mode Decomposition (VMD) to form the VMD-LSTM hybrid model. To further improve the prediction accuracy of the VMD-LSTM model, this paper proposes a dual variational modal decomposition long short-term memory (DVMD-LSTM) model to effectively handle the noise in GNSS time series prediction. This model extracts fluctuation features from the residual terms obtained after VMD decomposition to reduce the prediction errors associated with residual terms in the VMD-LSTM model. Daily E, N, and U coordinate data recorded at multiple GNSS stations between 2000 and 2022 are used to validate the performance of the proposed DVMD-LSTM model. The experimental results demonstrate that compared to the VMD-LSTM model, the DVMD-LSTM model achieves significant improvements in prediction performance across all measurement stations. The average RMSE is reduced by 9.86%, and the average MAE is reduced by 9.44%. Furthermore, the average accuracy of the optimal noise model for the predicted results is improved by 36.50%, and the average speed accuracy of the predicted results is enhanced by 33.02%. These findings collectively attest to the superior predictive capabilities of the DVMD-LSTM model, thereby enhancing the reliability of the predicted results.

This paper investigates the search for an exact analytic solution to a temporal first-order differential equation that represents the number of customers in a non-stationary or time-varying

Non-neural Machine Learning (ML) and Deep Learning (DL) are used to predict system failures in industrial maintenance. However, only a few studies have assessed the effect of varying the amount of past data used to make a prediction and the extension in the future of the forecast. This study evaluates the impact of the size of the reading window and of the prediction window on the performances of models trained to forecast failures in three data sets of (1) an industrial wrapping machine working in discrete sessions, (2) an industrial blood refrigerator working continuously and (3) a nitrogen generator working continuously. A binary classification task assigns the positive label to the prediction window based on the probability of a failure to occur in such an interval. Six algorithms (logistic regression, random forest, support vector machine, LSTM, ConvLSTM and Transformers) are compared using multivariate time series. The dimension of the prediction windows plays a crucial role and the results highlight the effectiveness of DL approaches in classifying data with diverse time-dependent patterns preceding a failure and the effectiveness of ML approaches in classifying similar and repetitive patterns preceding a failure.

Augmented reality (AR) provides an opportunity for mobile fitness applications to show users real-time feedback on their current fitness activity. For such applications, it is essential to accurately track the user’s current fitness activity using available mobile sensors, such as inertial measurement units (IMUs). Convolutional neural networks (CNNs) have been shown to produce strong results in different time series classification tasks, including the recognition of activities of daily living. However, fitness activities can present unique challenges to the human activity recognition task (HAR), including greater similarity between individual activities and fewer available data for model training. In this paper, we evaluate the applicability of CNNs to the fitness activity recognition task (FAR) using IMU data and determine the impact of input data size and sensor count on performance. For this purpose, we adapted three existing CNN architectures to the FAR task and designed a fourth CNN variant, which we call the scaling fully convolutional network (Scaling-FCN). We designed a preprocessing pipeline and recorded a running exercise data set with 20 participants, in which we evaluated the respective recognition performances of the four networks, comparing them with three traditional machine learning methods commonly used in HAR. On our data set, all CNN architectures significantly outperformed traditional machine learning methods, reaching up to 97.14±1.36% classification accuracy on the test set for ResNet. Whereas a reduced input data size invariably led to a performance loss, removing specific sensors improved the performance of all CNN architectures, with our Scaling-FCN reaching the highest accuracy of 99.86±0.11%. Our results suggest that CNNs are generally well suited for fitness activity recognition, and noticeable performance improvements can be achieved if sensors are dropped selectively.

With an explosion of data in the nearly every domain, from physical and environmental sciences to econometrics and even social science, we have entered a golden era of time-domain data science. In addition to ever increasing data volumes and varieties of time-series, there's a plethora of techniques available to analyses them. Unsurprisingly, machine learning approaches are very popular. In environmental sciences (ranging from climate studies to space weather/solar physics), machine learning (ML )and deep learning (DL) approaches complement the traditional data assimilation approaches. In solar and astrophysics, multiwavelength time-series or lightcurves along with observations of other messengers like gravitational waves provide a treasure trove of time-domain data for ML/DL approaches for modeling and forecasting. In this regard, deep learning algorithms such as recurrent neural networks (RNNs) should prove extremely powerful for forecasting as it has in several other domains. Such methods agnostic of the physics can only predict transient flares that are represented in the original distribution trained on (eg. coloured noise fluctuations) and not special, isolated episodes (eg. a one-off outburst like a major coronal mass ejection) potentially distinguishing them. Therefore it is vital to test robustness of these techniques ; here we attempt to make a small contribution to this by exploring sensitivity of RNNs with some rudimentary experiments. We test the performance of a very successful class of RNNs, the Long Short Term Memory (LSTM) algorithms with simulated lightcurves. As an example, we focus on univariate forecasting of time-series (or lightcurves) characteristic certain variable astrophysical objects (eg. active galactic nuclei or AGN). Specifically, we explore the sensitivity of training and test losses to key parameters of the LSTM network and data characteristics namely gaps and complexity measured in terms of number of Fourier components. We find that typically, the performances of LSTMs are better for pink or flicker noise type sources. The key parameters on which performance is dependent are batch size for LSTM and the gap percentage of the lightcurves. While a batch size of $10-30$ seems optimal, the most optimal test and train losses are under $10 \%$ of missing data for both periodic and random gaps in pink noise. The performance is far worse for red noise. This compromises detectability of transients. Thus, we show that generative models (time-series simulations) are excellent guides for use of RNN-LSTMs in building forecasting systems

The environmental issues we are currently facing require long-term prospective efforts for sustainable growth. Renewable energy sources seem to be one of the most practical and efficient alternatives in this regard. Understanding a nation's pattern of energy use and renewable energy production is crucial for developing strategic plans. No previous study has been performed to explore the dynamics of power consumption with the change in renewable energy production on a country-wide scale. In contrast, a number of deep learning algorithms demonstrated acceptable performance while handling sequential data in the era of data-driven predictions. In this study, we developed a scheme to investigate and predict total power consumption and renewable energy production time series for eleven years of data using a Recurrent Neural Network (RNN). The dynamics of the interaction between the total annual power consumption and renewable energy production are investigated through extensive Exploratory Data Analysis (EDA) and a feature engineering framework. The performance of the model is found satisfactory through the comparison of the predicted data with the observed data, visualization of the distribution of the errors and Root Mean Squared Error (RMSE) value of 0.084. Higher performance is achieved through the increase in the number of epochs and hyperparameter tuning. The proposed framework can be used and transferred to investigate the trend of renewable energy production and power consumption and predict the future scenarios for different communities. Incorporation of the cloud-based platform into the proposed pipeline may lead to real-time forecasting.

To detect aberrant human behaviors from large volume of passive data collected by smartphones in real time, we propose an online anomaly detection method using Hotelling’s T-squared test. The test statistic is a weighted average, with more weight on the between-individual component when there are little data available for the individual and more weight on the within-individual component when the data are adequate. The algorithm takes only O(1) run time in each update and the required memory usage is fixed after a pre-specified number of updates. The performance of the proposed method, in terms of accuracy, sensitivity and specificity, is consistently better than or equal to the offline method that it builds upon depending on the sample size of the individual data.

This article explores the required amount of time series points from a high-speed traffic network to accurately estimate the Hurst exponent. The methodology consists in designing an experiment using estimators that are applied to time series, followed by addressing the minimum amount of points required to obtain accurate estimates of the Hurst exponent in real-time. The methodology addresses the exhaustive analysis of the Hurst exponent considering bias behavior, standard deviation, mean square error, and convergence using fractional Gaussian noise signals with stationary increases. Our results show that the Whittle estimator successfully estimates the Hurst exponent in series with few points. Based on the results obtained, a minimum length for the time series is empirically proposed. Finally, to validate the results, the methodology is applied to real traffic captures in a high-speed network based on the IEEE 802.3ab standard.

In data-scarce regions, prudent planning and precise decision-making for sustainable development especially in agriculture remains a challenging task due to the lack of correct information. Remotely sensed satellite images provide a powerful source for assessing land use land cover (LULC) classes and crop identification. Applying Remote Sensing (RS) in conjunction with the Geographical Information System (GIS) and modern tools/ algorithms of artificial intelligence (AI) and deep learning has been proven effective for strategic planning and integrated resources management. The (this)study was conducted in the canal command area of the Lower Chenab Canal system in Punjab, Pakistan. Crop features/ classes were assessed using the Normalized Difference Vegetation Index (NDVI) algorithm. The MODIS (Moderate Resolution Imaging Spectroradiometer) 250 m and Landsat 5 TM (thematic mapper) images were deployed for NDVI time-series analysis with unsupervised classification technique to get LULC classes that helped to discern cropping pattern, crop rotation, and the area of specific crops, which were then used as a key input for agricultural mechanization planning and resources management. The accuracy of the LULC map was 78%, assessed by the error matrix approach. Limitations of high-resolution RS data availability and the accuracy of the results are the concerns observed in this study that could be managed by the availability of good quality local sources and advanced techniques of processing, which will make it more useful and applicable for regional agriculture and environmental management.

The enhanced multi-objective symbolic discretization for time series (eMODiTS) method employs a flexible discretization scheme using different value cuts for each non-equal time interval, which requires a computational cost for evaluating each objective function. Therefore, surrogate models were implemented to minimize this disadvantage. Nevertheless, each solution found by eMODiTS is a different-sized vector, so the surrogate model must be able to handle data sets under this characteristic. Consequently, this work's contribution lies in analyzing the surrogate models' implementation on the time series discretization, where each potential scheme is a real-number different-sized vector. For this reason, the surrogate model proposed was k-nearest Neighbors for regression with Dynamic Time Warping as a distance measure. Results suggest our proposal finds a suitable approximation to the final eMODiTS solutions with a functions evaluation reduction rate between 15% and 95%. However, according to Pareto front performance measures, the proposal Pareto front is competitive compared to the eMODiTS Pareto front, reaching an average Generational Distance (GD) between 0.0447 and 0.0536. Moreover, the average Hypervolume Ratio (HVR) ranges between 0.334 and 0.3891. Finally, our proposal compared against SAX-based methods presents a similar behavior regarding classification tasks and statistical tests.

Accurately predicting electrical signals of three-phase Direct Torque Control (DTC) induction motors is crucial for optimal motor performance and effective condition monitoring. However, multiple DTC motors’ complexity and operating conditions’ variations pose challenges for traditional prediction methods. To overcome these challenges, we propose an innovative approach that combines Fast Fourier Transform (FFT) to transform electrical motor simulation data and a Bi-directional Long Short-Term Memory (Bi-LSTM) network to forecast processed motor data. By transforming the DTC induction motor signals from the time domain to the frequency domain, we enhance the capability of learning models to capture subtle differences and generate various input features. The Bi-LSTM model effectively captures both forward and backward dependencies in time series data, enabling accurate prediction of electrical signals. We evaluate the proposed approach using our simulated dataset and compare the proposed method to a state-of-the-art model, the Gated Recurrent Unit (GRU), demonstrating its effectiveness in improving the accuracy and reliability of induction motor signals forecasting. The finding provides valuable insights for advancing motor control and operation in industrial applications.

In this study, UAV (Unmanned Aerial Vehicle) photogrammetry was used to monitor the ground displacement on the slope below a coal waste-rock stockyard, and to investigate the role of rainfall on this displacement. The study area is a mountainous region in Korea, where coal mining continues, and coal waste-rock is stored on the slopes of the mountain. In this area, ma-terial removal work was undertaken to reduce the steepness of the slope and driving forces in order to prevent disasters, but the strategy requires continuous monitoring to confirm the stabilization of the slope. For slope monitoring, a total of six UAV photogrammetry campaigns were conducted between April 2019 and August 2020. As a result of data processing, an orthoimage and DSM (Digital Surface Model) were generated. The ground displacement was estimated through four ways: slope extraction, displacement area evaluation, horizontal displacement, and vertical displacement analysis. During the study period, the maximum vertical displacement was 3.3 m and the maxi-mum horizontal displacement was 3.5 m. The horizontal displacement was effectively evaluated through the measurement of the movement of the drainage system using orthoimages that captured with a periodic survey. The effects of rainfall on ground displacement were also investigated. A very clear linear relationship between rainfall intensity higher than 20mm/d and ground displacement was identified. Accumulated amount of rainfall also showed good correlation with slope movement, but the frequency of rainfall intensity below 20 mm/d showed relatively low correlation with ground dis-placements.

Background: The current coronavirus disease 2019 (COVID-19) is spreading globally at an accelerated rate. There is some previous evidence that weather may influence the incidence of COVID-19 infection. We assessed the role of meteorological factors including temperature (T) and relative humidity (RH) considering the concentrations of two air pollutants, inhalable coarse particles (PM10) and nitrogen dioxide (NO2) in the incidence of COVID-19 infections in Finland, located in arctic-subarctic climatic zone. Methods: We retrieved daily counts of COVID-19 in Finland from Jan 1 to May 31, 2020, nationwide and separately for all 21 hospital districts across the country. The meteorological and air quality data were from the monitoring stations nearest to the central district hospital. A quasi-Poisson generalized additional model (GAM) was fitted to estimate the associations between district-specific meteorological factors and the daily counts of COVID-19 during the study period. Sensitivity analyses were conducted to test the robustness of the results. Results: The incidence rate of COVID-19 gradually increased until a peak around April 6 and then decreased. There were no associations between daily temperature and incidence rate of COVID-19. Daily average RH was negatively associated with daily incidence rate of COVID-19 in two hospital districts located inland. No such association was found nationwide. The sensitivity analyses indicate the results are robust. Conclusions: Weather conditions, such as air temperature and relative humidity, may not be important factors affecting the COVID-19 incidence in the arctic and subarctic winter and spring. More evidence is needed on the associations between weather and COVID-19 during different seasons.

Time recordings of impulse-type oscillation responses are short and highly transient. These characteristics may complicate the usage of classical spectral signal processing techniques for a) describing the dynamics and b) deriving discriminative features from the data. However, common model identification and validation techniques mostly rely on steady-state recordings, characteristic spectral properties and non-transient behavior. In this work, a recent method, which allows reconstructing differential equations from time series data, is extended for higher degrees of automation. With special focus on short and strongly damped oscillations, an optimization procedure is proposed that fine-tunes the reconstructed dynamical models with respect to model simplicity and error reduction. This framework is analyzed with particular focus on the amount of information available to the reconstruction, noise contamination and non-linearities contained in the time series input. Using the example of a mechanical oscillator, we illustrate how the optimized reconstruction method can be used to identify a suitable model and to extract features from uni-variate and multivariate time series recordings in an engineering-compliant environment. Moreover, the determined minimal models allow for identifying the qualitative nature of the underlying dynamical systems as well as testing for the degree and strength of non-linearity. The reconstructed differential equations would then be potentially available for classical numerical studies, such as bifurcation analysis. These results represent a physically interpretable enhancement of data-driven modeling approaches in structural dynamics.

Introduction: The association between epilepsy and myasthenia gravis has rarely been reported, and only in small case series. Objective: To report the frequency of epilepsy and myasthenia gravis and to describe a case series of patients with myasthenia gravis and epilepsy, focusing on their clinical characteristics and searching for a possible physiopathological mechanism. Methods: A retrospective, observational, adult center study was conducted in 2022. Patients were recruited from the database of the outpatient clinic of the Myasthenia Gravis unit and Epilepsy unit. Results: Five patients were included. Frequency of epilepsy in the myasthenia gravis cohort was 5/469 (1.1%), and of myasthenia gravis in the epilepsy cohort was 5/1432 (0.35%). All patients suffered focal epilepsy, mainly fronto-central, and drug-resistant in half of them. Myasthenia gravis was generalized and with exacerbations in half of them. Three patients were thymectomized. Other autoimmune diseases were found in 2 (40%). Epilepsy onset preceded myasthenia gravis onset in all patients. Both diseases were considered autoimmune-related in 3/5 (60%). Conclusion: Epilepsy and myasthenia gravis are only infrequently associated. In adult patients, epilepsy onset precedes myasthenia onset in most cases. In some cases, epilepsy has an autoimmune aetiology and coexists with other autoimmune conditions.

The current work reports the upper bound of the state variable of the of the Pointwise Steady Fluid Flow Approximation (PSFFA) model of non-stationary M/Ek/1 queueing system.

Gait is a basic cognitive propositive action that has been shown to be altered in late stages of neurodegenerative dementias. Nevertheless, alterations are less clear in mild forms of dementia, and the potential use of gait analysis as a biomarker of initial cognitive decline has hitherto mostly been neglected. We here report the results of a study of gait kinematic time series for two groups of patients (Mild Cognitive Impairment and mild Alzheimer's disease) and a group of matched control subjects. Two metrics based on permutation patterns are considered, respectively measuring the complexity and irreversibility of the time series. Results indicate that kinematic disorganisation is present at early phases of cognitive impairment; in addition, they depict a rich scenario, in which some joint movements display an increased complexity and irreversibility, while others a marked decrease. Beyond their potential use as biomarkers, complexity and irreversibility metrics can open a new door towards the understanding of the role of the nervous system in gait, as well as its adaptation and compensatory mechanisms.

Heat index (HI) is a biometeorological indicator that combines temperature and relative humidity. This study aimed to investigate the relationship between heat index and daily counts of diarrhoea hospitalisation in Dhaka, Bangladesh. Data on daily diarrhoea hospitalisations and meteorological variables from 1981–2010 were collected. We categorised heat index of >94.3°F, >100.7°F and >105°F as high, very high and extremely high heat index, respectively. We applied time-series adjusted generalised linear model (GLM) with negative binomial distribution to investigate the effects of heat index and extreme heat index on hospitalisations for diarrhoea. Effects were assessed for all ages, <5 children and by gender. A unit higher HI, and high, very high and extremely high HI were associated with 0.8%, 8%, 7% and 9% increase in diarrhoea hospitalisation in all ages, respectively. The effects varied slightly by gender and were most pronounced in <5 children with a rise of 1°F in high, very high and extremely high HI associated with a 14.1% (95% CI: 11.3% – 17.0%), 18.3% (95% CI: 13.4% – 23.5%) and 18.1% (95% CI: 8.4% – 28.6%) increase of diarrhoea, respectively. This suggest that heat index may serve as an alternative indicator for measuring the combined effects temperature and humidity on diarrhoea.

Fractal analysis of time series aims to extract the hidden or complex structures issued from the associated real data, such as scaling laws, non-stationary, dynamics, and so on. In the present work, the air quality index and its components are considered as time series owing fractal structures. To understand their underlying dynamics, wavelet multifractal approach is applied starting with a wavelet multifractal spectrum test to confirm the multifractality of the underlying data. Next, a new model is introduced improving the classical minmax one, provided with a statistical measure for the adequacy of the new model. The theoretical findings are applied to the north west Tabuk region of Saudi Arabia for environmental and climate data related to pollutants and factors involved in the estimation of the air quality index.

Today, there is a time series analysis that has gained significant popularity across various industries to provide effective solutions for any specific challenges. Artificial intelligence logic is generally used to solve time-series problems with the help of various frameworks that are available for the development of AI-based applications. Currently, there is a significant framework in Python that is driven by its comprehensive libraries and their practical implementations. Time series analysis can be built with the help of some specific models that give results to differentiate the efficiency and domains of great work. This paper focuses on three diverse libraries of Python to predict the Gulf stock exchange market. These libraries are prediction models that are helpful in predicting future values. These models utilized include SARIMA (Seasonal Auto-Regressive Integrated Moving Average), Neural Prophet Model, and Fb Prophet model. Each model is trained using the provided datasets, which are followed by evaluation parameters such as MSE, RMSE, recall, MDAPE, accuracy, precision, etc. The main purpose of using these three models for stock market prediction is to find the better-suited models. In the past few decades, the stock market industry has seemed to have promising growth after 2022 onwards. This paper will help us make a significant decision about model usage for addressing such complex challenges. Especially, the research findings indicate that all three models demonstrate in different domains. SARIMA can perform well in overall prediction tasks, while the Prophet model works great with smaller datasets that contain seasonality trends.

For more than half a century, Manfred Deistler has been contributing to the construction of the rigorous theoretical foundations of the statistical analysis of time series and more general stochastic processes. Half a century of unremitting activity is not easily summarized in a few pages. In this short note, we chose to concentrate on a relatively little-known aspect of Manfred's contribution which nevertheless had quite an impact on the development of one of the most powerful tools of contemporary time series and econometrics: dynamic factor models.

In an epoch characterized by the swift pace of digitalization and urbanization, the essence of community well-being hinges on the efficacy of urban management. As cities burgeon and transform, the need for astute strategies to navigate the complexities of urban life becomes in-creasingly paramount. This study employs time series analysis to scrutinize citizen interactions with the coordinate-based problem mapping platform in the Municipality of Patras in Greece. The research explores the temporal dynamics of reported urban issues, with a specific focus on identifying recurring patterns through the lens of seasonality. The analysis, employing the sea-sonal decomposition technique, dissects time series data to expose trends in reported issues and areas of the city that might be obscured in raw big data. It accentuates a distinct seasonal pattern, with concentrations peaking during the summer months. The study extends its approach to forecasting, providing insights into the anticipated evolution of urban issues over time. Projec-tions for the coming years show a consistent upward trend in both overall city issues and those reported in specific areas, with distinct seasonal variations. This comprehensive exploration of time series analysis and seasonality provides valuable insights for city stakeholders, enabling informed decision-making and predictions regarding future urban challenges.

Background: Digital clinical measures collected via various digital sensing technologies such as smartphones, smartwatches, wearables, ingestible, and implantable are increasingly used by individuals and clinicians to capture health outcomes or behavioral and physiological characteristics of individuals. Time series classification (TSC) is very commonly used in modeling digital clinical measures. While deep learning models for TSC are very common and powerful, there exist some fundamental challenges. This review presents non-deep learning models commonly used for time series classification in biomedical applications that achieve high performance. Objective: We performed a systematic review to characterize the techniques used in time series classification of digital clinical measures throughout all stages of data processing and model building. Methods: We conducted a literature search on PubMed, and the Institute of Electrical and Electronics Engineers (IEEE), Web of Science, and SCOPUS databases using a range of search terms to retrieve peer-reviewed articles reporting academic research on digital clinical measures in the five year period between June 2016 and June 2021. We identified and categorized research studies based on the types of classification algorithms and sensor input types. Results: We found 452 papers in total from four different databases: PubMed, IEEE, Web of Science Database, and SCOPUS. After removing duplicates and irrelevant papers, 135 articles remained for detailed review and data extraction. Among these, engineered features using time series methods that were subsequently fed into widely-used machine learning classifiers was the most commonly used technique and also most frequently achieved the best performance metrics (77 out of 135 articles). Statistical modeling (24 out of 135 articles) algorithms were the second most common and also second best classification technique. Wavelet-based classification models (8 out of 135 articles) were also common. Electroencephalogram (29 out of 135 articles) was the most common data type used as an input. Accuracy was the most commonly reported performance metric, with 67.65% of articles reporting on accuracy. In this review paper, we provide summaries of signal pre-processing methods, feature engineering and selection methods, time series models, as well as model interpretations. Importantly, we found that about 50% of the papers only report one performance metric, which may result in a skewed view of overall performance. Conclusion: While high time series classification performance has been achieved in digital clinical, physiological, or biomedical measures, no standard benchmark datasets, modeling methods, or reporting methodology exist. There is no single widely used method for time series model development or feature interpretation– many different methods have proven successful.

InSAR and associated analytic methods can measure surface deformation from low earth orbit with a claimed accuracy of centimeters to millimeters. The realized accuracy depends on the area being measured and on the choice of analytic method, suggesting one choose a method in response to the area being measured. Here we consider a specific fixed analytic method and compare the results it produces to measurements gathered from other means in a variety of settings. In particular we compare Sentinel-1 InSAR with GPS at the Kilauea volcano around the 2018 eruption, with GPS in the city of Arica, Chile, and with public survey data at a decommissioned tailings mine. In addition, we compare two independent Sentinel-1 InSAR analyses for a railway station in Oslo, Norway. Our goal is estimate the accuracy of a fully automated Sentinel-1 InSAR pipeline in various settings. Our conclusions are that centimeter level accuracy is a reasonable claim in many, but not all settings, and that accuracy is typically not lost by using an automated pipeline, instead of hand-selecting and tuning parameters.

This paper realizes early bearing fault warning through bearing fault time series prediction, and proposes a bearing fault time series prediction model based on optimized maximum correlation kurtosis deconvolution (MCKD) and long short-term memory (LSTM) recurrent neural network to ensure bearings operation reliability. The model is based on lifecycle vibration signal of the bearing, to begin, the cuckoo search (CS) is utilized to optimize the parameter filter length L and deconvolution period T of MCKD, taking into account the influence and periodicity of the bearing time series, the fault impact component of the optimized MCKD deconvolution time series is improved. Then select the LSTM learning rate α depending on deconvolution time series. Finally, the dataset obtained through various preprocessing approaches are used to train and predict the LSTM model. The average prediction accuracy of the optimized MCKD-LSTM model is 26 percent higher than that of the original time series, proving the efficiency of this method, and the prediction results track the real fault data well, according to the XI'AN JIAOTONG University XJTU-SY bearing dataset.