As a vital component of the terrestrial ecosystem, grassland accounts for one-third of the global vegetation system. Grassland degradation has been exacerbated due to extreme overgrazing in China's Inner Mongolia Autonomous Region (IMAR). While conservation was carried out as the Ecological Subsidy and Award Program (ESAP) to mitigate grassland degradation, little is known about its effectiveness in improving the biophysical conditions of grassland. This paper integrates the conceptual frameworks of total socio-environmental systems to assess how ecological systems respond to ESAP, investigate spatial heterogeneity of ESAP, and explore the meddling effects of socio-environmental interactions on ESAP. We integrate ecological, climate, and socioeconomic data and developed several hierarchical linear mixed models (HLMM) to investigate how these factors interact with ESAP in IMAR. Our findings prove that the above-ground biomass between 2011 and 2015 responds significantly to variations in socioeconomic conditions and ecological communities. Available land resources, hospital and medical facilities, and net farmer and herdsman income are the most critical factors contributing to grassland productivity. Primary industries like mining, total consumer retail value, farming, forestry, animal husbandry, fishery productions, and GDP are the most damaging factors affecting biomass. Our study recommends a regionally or locally tailored ecological recovery policy, instead of a generalized one, in the future effort to conserve grassland.

Mammarenavirus Wenzhouense (WENV) is broadly distributed in Asia, while the he dynamics process of WENV infection remains unclear. A field derived strain of WENV was used to inoculate Sprague-Dawley (SD) rats by intramuscular injection, the process of virus infection was de-tected by controlling time for 28 days. Viral RNA became detectable in the blood at 3 d pi, and remained detectable for about 12 d. In most organ tissues, viral RNA peaked at 7 d pi, then began to decline by 14 d, however remained detectable in intestine and brain tissues at 21 and 28 d pi. Virus shedding had been detected from fecal samples for 5 days from 6 to 11 d pi using qRT-PCR, and was recovered from feces collected at 8 d pi. Horizontal contact infection occurred among cage-mates at 14 and 21 d pi. Antibodies against the nucleocapsid were detected at 5 dpi, next increased and persisted until the end of experiment. The results enabled to discriminate the kinetic of viremic response, virus shedding in feces and horizontal transmission, as well as the potential sites for WENV replication or maintenance of the virus in nature.

A new model for international bed numbers is applied to local area populations for English Clinical Commissioning Groups (CCGs) where the Age Standardized Mortality Rate (ASMR) is used as a measure of population health and hence for total occupied hospital bed demand (elective plus emergency admission types, including acute, rehabilitation, mental health, and maternity), rather than simple bed availability. A 100-unit increase in ASMR (European Standard population) leads to a 15.3 – 30.7 (feasible range) unit increase in occupied beds per 1,000 deaths. ASMR shows why the Australian states of the Northern Territory and Tasmania have an intrinsic higher bed demand than the other states – although in both cases the bed planning methodologies failed to indicate this need and both states show a large bed deficit. Due to the high volatility in bed demand the average bed demand for 2019 was determined by a linear trend using data for 2014/15 to 2019/20 — as the pre-COVID-19 baseline. The slope of the relationship between occupied beds per 1,000 deaths and deaths per 1,000 population shows a power law function. As is to be expected there is scatter around the trend line which will partly arise from uncertainty in the expected occupied beds in 2019, fluctuations in both ASMR and deaths per 1,000 population from one year to another, changes in the number of persons on the elective, outpatient and diagnostic waiting lists, and local area variation in births and consequently upon maternity, neonatal and pediatric bed demand. Additional variation in bed demand will arise from differences in the level of funding for social care, especially elderly care, and to a lesser extent upon patients using private health care, and charitable hospices for palliative care. However, after including the change in bed demand arising from ASMR the model is sufficiently accurate to identify gross differences in bed demand as a prelude to further investigation. The model requires further extension to cover specialty-level demand, and perhaps segregation between elective and emergency types of inpatient demand. A method for benchmarking the whole hospital’s average bed occupancy is given which enables them to run at optimum efficiency and safety. Using this method English hospitals can be shown to operate at highly disruptive and unsafe levels of bed occupancy leading to deleterious ‘turn-away’. Turn-away implies bed unavailability for the next arriving patient. The problems associated with crafting effective bed planning are illustrated using the English NHS as an example.

The Eastern Kunlun Fault Zone (EKFZ) is located in a seismic blank area. This study investigates the hydrogeochemical characteristics of varied-temperature springs in the EKFZ to understand the relationship between fractures, fluids and earthquakes. It aids in establishing their induction mechanisms and assists in monitoring the earthquake precursors of the EKFZ. In this study, the main elements, trace elements, hydrogen and oxygen isotopes and strontium isotopes of 23 varied-temperature springs in the EKFZ were analyzed. The results reveal the source of groundwater recharge, hydrochemical types, mineral saturation, and for a select few springs indicative of geothermal activity, collected geothermal reservoir temperatures. The study also explores the relationship between earthquakes and springs, identifying sensitive chemical indicators. Based on continuous monitoring at Maqu Station, we found that before the occurrence of the Maerkang Ms 6.0 earthquake, the concentration of Cl− rose by 2.9 times, and 46 days before the Gande earthquake (Ms = 4.7), the concentrations of Na+ and SO42− significantly increased. Finally, a conceptual model of the hydrogeochemistry of springs is presented to describe the groundwater circulation in the study area. This research is of great significance for the analysis of fluid geochemistry in this area and for assessing the seismic hazards of the EKFZ.

Launched on 2 February 2018, CSES is the first constellation in China to advance our understanding of seismo-ionospheric influence and lithosphere-atmosphere-ionosphere coupling process in electromagnetic environment during earthquake prediction practice. For this purpose, a software platform developed for automatically searching ionospheric perturbations from the CSES plasma data had been put into service immediately after the Wushi MS 7.1 earthquake occurred on 23 January 2024 to weekly detect possible precursory information before impending aftershocks. Effective ionospheric variations were successfully detected two times during more than four weeks. An ionospheric perturbation with an enhanced magnitude 38.3% was primarily detected on electron density but none on ion density on 24 January 2024 at night orbit 33175 and the corresponding variations in different parameters recorded at the same orbit presented a complex features. There irregularities possibly combined with influence both from three following strong aftershocks with magnitudes over 5.0 during 25–30, January and magnetic storm disturbance due to Kp value once up to 3.7 on 24 January. An electron perturbation with an amplitude 24.6%, as well as an ion one with 27.3%, was successfully searched automatically at the same revisiting orbit 33251 occurred on the revisiting date of 3 February 2024 in a magnetic quiet period. These two plasma variations, as well as ones on other ionospheric parameters, were characterized by highly similar properties, which increases the availability as seismic precursors. However, no obvious variations had been observed at other revisiting orbits or other orbits near the aftershock areas during this period till the occurrence of a magnitude 5.3 earthquake on 24 February and the strongest one 5.8 on 25 February, respectively, 20 days after and 1000 km away.

The pollution of the bays in Abidjan is a major concern for the Ivorian policy makers. In fact, the pollution of the bays induce high costs to the society while impacting population health dramatically. As a result, pollution reduction management of production activities has been undertaken in the Cocody Bay area. To our knowledge, no study has yet proposed a model to evaluate the cost-effectiveness of these pollution management strategies. A cost-effectiveness model, based on Monte Carlo simulation, was developed to assess the economic and environmental impacts of various scenarios characterized by a set of production practices, both in the short term and in the long term. The authors discuss the steps and input parameters of the model presented. The proposed model may serve as the basis for identifying an optimal production scenario defined as the scenario with the best incremental cost-effectiveness ratio considering a willingness to pay (WTP) threshold. The WTP, to be estimated based on the gross domestic product of Côte d’Ivoire, represents the opportunity costs associated with selecting the optimal scenario. The current framework can also be applied to other settings facing similar challenge.

Dhaka one of the fastest-growing megacities in the world is increasingly vulnerable to urban flooding due to rapid urbanization, inadequate drainage infrastructure, and climate change-induced extreme weather events. This study presents the development of an urban flood forecasting system for Dhaka City using the MIKE+ hydrodynamic modeling software. The system integrates detailed hydrological and hydraulic models to simulate urban flooding scenarios, accounting for complex drainage networks and catchment characteristics. Real-time data from river gauges, rainfall stations, and drainage systems are incorporated to enhance the accuracy and reliability of the forecasts. The model's predictive capability is validated against historical flood events, demonstrating its effectiveness in forecasting flood extents, depths, and durations in critical areas of the city. This system serves as a valuable tool for city planners, emergency response teams, and decision-makers, enabling proactive flood management and risk mitigation. The study underscores the importance of such advanced modeling tools in safeguarding urban populations and infrastructures from the increasing threat of urban floods in Dhaka and similar rapidly urbanizing cities.

The Simultaneous Localization And Mapping (SLAM) scanner is an easy and portable Light Detection And Ranging (LiDAR) data acquisition device. Its main output is a 3D point cloud covering the scanned scene. Regarding the importance of accuracy in the survey domain, this paper aims to assess the accuracy of two SLAM scanners: the NavVis VLX and the BLK2GO Scanner. This assessment is conducted for both outdoor and indoor environments. In this context, two types of reference data are used: the Total Station (TS) and the static scanner Z+F Imager 5016. To carry out the assessment, four comparisons are tested: cloud to cloud, cloud to mesh, mesh to mesh, and edge detection board assessment. However, the results of the assessments confirm that the accuracy of indoor SLAM scanner measurements (5 mm) is greater than that of outdoor ones (between 10 mm and 60 mm). Moreover, the comparison of cloud to cloud provides the best accuracy regarding direct accuracy measurement without manipulations. Finally, based on the high accuracy, scanning speed, flexibility, and the accuracy differences between tested cases, it is confirmed that SLAM scanners are effective tools for data acquisition.

BACKGROUND Detecting total cholesterol in dried blood spots could aid in identifying individuals with a high likelihood of familial hypercholesterolemia and could be used as a screening measure. This study aims to assess the diagnostic accuracy of dried blood spots on Whatman 903 paper cards using a manual enzymatic technique. METHODS A total of 394 samples collected as serum and dried blood spots were compared. Cholesterol was determined in serum using the automated reference method, while cholesterol on paper was measured using a manual enzymatic method. Within- and between-day diagnostic variability were analyzed. The correlation between both methods was assessed using Passing-Bablok regression and Bland-Altman plot. Internal validation of our correlation formula was performed on 149 samples, along with external validation of the formula proposed by Corso et al. RESULTS The within- and between-day coefficient of variation was found to be lower than 10.14% and 14.09%, respectively. Method comparison yielded an area under the curve of 0.976, with a standard error of 0.009. Passing-Bablok regression indicated a precision of 0.803 and an accuracy of 0.96. Internal validation precision was measured at 0.716. Regarding internal validation, calculated cholesterol with our regression line did not differ from serum cholesterol analysis, while significant differences were observed in calculated cholesterol levels using the external formula. CONCLUSIONS Total cholesterol analysis in dot blood spots demonstrates high precision and reproducibility. This method reliably enables the incorporation of this biological marker into neonatal screening for familial hypercholesterolemia detection.

This paper investigates five different GARCH models (GARCH, EGARCH, IGARCH, Component GARCH (CGARCH) and GJR-GARCH) along with six distributions (Normal, Student’s t, GED and their skewed forms), which are used to forecast the volatility for the Bulgarian Stock index SOFIX. We use a GARCH model to predict how much time it will take, after the latest crisis, for the SOFIX index to reach its historical peak once again. The empirical data covers the period between the years 2000 and 2024, including the 2008 financial crisis and the COVID-19 pandemic. The purpose is to answer which of the five models is the best at forecasting the volatility of SOFIX and which distribution is most appropriate. The results, based on BIC and AIC information criteria, show that the ARMA(1,1)-CGARCH(1,1) specification with the Student t-distribution is preferred for forecasting. With the help of 5000 simulations, it is estimated that the chances of Index SOFIX reaching its historical peak value of 1976.73 (08.10.2007) are higher than 90% at 13.08.2087.

Day-ahead forecasting of electricity prices is important in deregulated electricity markets for all the stakeholders: energy wholesalers, traders, retailers, and consumers. Electricity price forecasting is an inherently difficult problem due to its special characteristic of dynamicity and non-stationarity. In this paper, we present a robust price forecasting mechanism that shows resilience towards aggregate demand response effect and provides highly accurate forecasted electricity prices to the stakeholders in a dynamic environment. We employ an ensemble prediction model in which a group of different algorithms participate in predicting the price for each hour of a day. We propose two different strategies, namely, Fixed Weight Method (FWM) and Varying Weight Method (VWM), for selecting each hour's expert algorithm from the set of participating algorithms. In addition, we utilize a carefully engineered set of features selected from a pool of features derived from information such as past electricity price data, weather data, and calendar data. The proposed ensemble model offers better results than both the Pattern Sequence-based Forecasting (PSF) method and our own previous work using Artificial Neural Networks (ANN) alone do on the datasets for New York, Australian, and Spanish electricity markets.

The goal of the study presented in this article is to investigate interconnection issues of the Intelligent Electrical Networks (IENs) with the existing ones, as well as the deployment of the appropriate load forecasting demand techniques. The concept of IENs has recently emerged as a potential solution to the global energy problem, due to the more flexible dispersed production units that are involved. In the same context, additional issues, such as the reduction of production-transfer-distribution costs as well as power losses are analyzed as well, via the penetration of Renewable Energy Sources (RESs). To this end, it is necessary to use appropriate advanced infrastructure, where in combination with modern telecommunication networks will make possible the full exploitation of IENs. Moreover, to make the electricity system more efficient, to avoid voltage and frequency imbalance issues and to implement optimal production and consumption planning, the Electric Load Forecast (ELF) is a vital process and plays a key role in the planning as well as in the management of electricity systems. Therefore, recent state of the art approaches in ELF methods are discussed as well.

This research introduces a hybrid feature extraction approach that combines Linear Discriminant Analysis (LDA) and Multilayer Perceptron (MLP) methods to address the challenges of reducing feature vector dimensionality and accurately classifying smartphone-based human activities. Moreover, to refine activity classification accuracy, Support Vector Machine (SVM) optimization with Stochastic Gradient Descent (SGD) is employed. LDA, a statistical tool, is leveraged to derive a new feature space for data projection, enhancing class separation and test feature label prediction. The proposed approach, named LMSS, was evaluated using the UCI-HAR dataset and compared with state-of-the-art models. The results demonstrate that the proposed approach outperformed the best-performing method over this dataset. It achieved an accuracy rate of 99.52%, precision of 99.55%, recall of 99.53%, and an F1-score of 99.54%, highlighting the effectiveness of the proposed method in accurately classifying the data.

The high penetration of distributed energy resources poses significant challenges to the dispatch and operation of power systems. Improving the accuracy of short-term load forecasting (STLF) can optimize grid management, leading to increased economic and social benefits. Currently, some simple AI and hybrid models has issues to deal with and struggle with multivariate dependencies, long-term dependencies, and non-linear relationships. This paper proposes a novel hybrid model for short-term load forecasting (STLF) that integrates multiple AI models with Lasso regression using the stacking technique. The base learners include ANN, XgBoost, LSTM, Stacked LSTM, and Bi-LSTM, while Lasso regression serves as the meta-learner. By considering factors such as temperature, rainfall, and daily electricity prices, the model aims to more accurately reflect real-world conditions and enhance predictive accuracy. Empirical analyses on real-world datasets from Australia and Spain show significant improvements in forecasting accuracy, with a substantial reduction in Mean Absolute Percentage Error (MAPE) compared to existing hybrid models and individual AI models. This research highlights the efficiency of the stacking technique in improving STLF accuracy, suggesting potential operational efficiency benefits for the power industry.

This study addresses a gap in the literature by conducting a comparative analysis of statistical and artificial intelligence techniques for predicting bankruptcy in small and medium-sized enterprises (SMEs). Using a comprehensive database of 7,104 Belgian SMEs, our findings demonstrate that intelligent techniques offer superior predictive accuracy for bankruptcy. Notably, our results indicate that a firm's position in the global value chain significantly affects prediction accuracy, with lower performance for firms operating upstream in the production process. This suggests that bankruptcy risk may spread upward along the value chain. This insight is particularly valuable for practitioners, as it highlights the importance of focusing on specific performance factors based on the type of firms they manage, advise, or collaborate with.

Objective: The aim of this in vitro study was to evaluate the accuracy of resin-based fixed dental restorations, namely veneers, single crowns, and four-unit fixed partial dental prosthesis (FPDs) using two different 3D printers and polymer-based materials. Materials and Methods: A standard maxillary polyurethane jaw model containing prepared teeth was scanned using an intraoral scanner. The generated STL data were used to design the restorations virtually using CAD software. Two 3D printers were utilized for the provisional digital light processing and stereolithography for the castable resin patterns. Each printer produced 10 specimens of each type of restoration, for a total of 80 restorations. The 3d-printed restorations were then 3D scanned using the same intraoral scanner and evaluated for external and internal dimensional accuracy in terms of trueness and precision. A one-way ANOVA and Two-sample T-Test were implemented to compute the precision (variability between groups) and trueness (with the designed CAD model). A level of statistical significance of p-Value

The assortment of low-cost 3D printers for “in-practice” use, e.g., for clear aligner therapies, is ever increasing. To address concerns about the accuracy of orthodontic models produced on such printers when cost efficient modes of 3D printing are employed, this study examined the effect of print model body type and print angulation on accuracy. Six printing-configuration groups were included: 2 model types (solid or hollow shell) combined with 3 print angles (0°, 70°, or 90°) with 10 models/group; all models were printed with 100-µm layer thickness using a digital light processing-based 3-dimensional printer. Eleven selected structures and distances were measured on the printed models with a digital microscope and compared to the same measures on a digitized master model. The clinically-acceptability range was set at ±0.25 mm difference from the master model for single tooth measurements (intra-tooth) and ±0.5 mm for cross-arch measurements (inter-tooth). For individual measurements across all models, 98% fell within clinical acceptability. For mean measurements within each model group, only canine height for the shell-0° model had a mean difference (0.26 mm ± 0.03) outside the clinically acceptable range for intra-tooth measurements. Standard deviations for all intra-tooth measurements were within 0.07 mm. While none of the mean inter-tooth measurements exceeded the acceptability range, the standard deviations were larger (0.04 to 0.30 mm). Accuracy of orthodontic models for clear aligner therapies was not impacted beyond the clinically acceptable range when altering model body type and print angulation to improve efficiency of 3D printing. These findings suggest greater flexibility of the practitioner to alter print settings to address time and cost efficiency in various clinical scenarios and still maintain clinically acceptable model accuracy.

Non-toroidal shape primary pass through protection current transformers (CTs) are used to measure high currents. Their design provides them with a big airgap that allow passing several cables per phase though them, which is the main advantage versus toroidal types, as the number of CTs required to measure the whole phase current is drastically reduced. The cables pass through the transformer window can be in several positions. As the isolines of the magnetic field generated by the primary currents are centered in the cables, if these cables are not centered in the transformer window, the magnetic field will be non-uniform along the transformer core. Consequently, local saturations can appear if the cables are not properly disposed causing the malfunction of the CT. In this paper, the performance of a non-toroidal shape protection CT is studied. The research is focused on the cable position influence in possible partial saturations of the CT when it is operating near to its accuracy limit. Depending on the cable position, the ratio of the primary and secondary currents can depart from assigned ratio. The validation of this phenomenon has been carried out via Finite Element Analysis (FEA) showing that partial transformer core saturations appears in areas of the magnetic core close to the cable. Applying FEA, also the admissible accuracy region for cable positioning inside the CT is delimited. Finally, the simulation results are ratified with experimental tests performed in non-toroidal protection CTs varying the primary cables’ positions, which are subjected to currents up to 5 kA, achieving satisfactory results. From this analysis, installation recommendations are given.

Additive manufacturing processes offer various options to fabricate metal parts, which show numerous ecological and technological advantages compared to formative and subtractive manufacturing methods. Due to quick availability and high accuracy, they are particularly suitable to produce complex prototypes. Metal fused deposition modeling is a relatively new material extrusion additive manufacturing technique based on the widely used fused filament deposition process. This study focuses on the Inconel 625 metal filament from Markforged Inc., it consists of a mixture of metal powder and a binder system, the latter being removed during washing and sintering. In this article, the mechanical properties of printed and sintered Inconel were investigated using tensile testing specimens with three different infill patterns, solid, triangular, and gyroid, printed in flatwise and upright direction. In addition, investigations into the dimensional accuracy of the printed specimens and the sintering shrinkage were carried out. The results showed that neither the dimensional accuracy nor the sintering shrinkage was significantly influenced by the printing orientation. In the context of lightweight engineering, the structures proofed beneficial especially within the elastic region. Generally, triangular infill patterns resulted in higher stiffness, while gyroids led to more ductile specimens. A mass-related evaluation of tensile testing elucidates that with aid of the infill structures weight savings of 40 % resulted in mechanical performance decreased by only 20 % on average.

Electricity price forecasting has become a crucial element for both private and public decision-making. This importance has been growing since the wave of deregulation and liberalization of energy sector worldwide late 1990s. Given these facts, this paper tries to come up with a precise and flexible forecasting model for the wholesale electricity price for the Italian power market on an hourly basis. We utilize artificial intelligence models such as neural networks and bagged regression trees that are rarely used to forecast electricity prices. After model calibration, our final model is bagged regression trees with exogenous variables. The selected model outperformed neural network and bagged regression with single price used in this paper, it also outperformed other statistical and non-statistical models used in other studies. We also confirm some theoretical specifications of the model. As a policy implication, this model might be used by energy traders, transmission system operators and energy regulators for an enhanced decision-making process.

The enormous growth in the penetration of electric vehicles (EVs), has laid the path to advancements in the charging infrastructure. Connectivity between charging stations is an essential prerequisite for future EV adoption to alleviate users’ “range anxiety”. The existing charging stations fail to adopt power provision allocation and scheduling management. To improve the existing charging infrastructure data based on real-time information and availability of reserves at charging stations could be uploaded to the users to help them locate the nearest charging station for an EV. This research article focuses on an a interactive user application developed through SQL and PHP platform to allocate the charging slots based on estimated battery parameters, which uses data communication with charging stations to receive the slot availability information. The proposed server-based real-time forecast charging infrastructure avoids waiting times and its scheduling management efficiently prevents the EV from halting on road due to battery drain out. The proposed model is implemented using a low-cost microcontroller and the system etiquette tested.

The infrared (IR) satellite remote sensing of sea surface skin temperature (SSTskin) is challenging in the northern high latitude region, especially in the Arctic because of its extreme environmental conditions, and thus the accuracy of SSTskin retrievals is questionable. Several Saildrone uncrewed surface vehicles were deployed at the Pacific side of the Arctic in 2019, and two of them, SD-1036 and SD-1037, were equipped with a pair of IR pyrometers on the deck whose measurements have been shown to be useful in the derivation of SSTskin with sufficient accuracy for scientific applications, providing an opportunity to validate satellite SSTskin retrievals. This study aims to assess the accuracy of MODIS-retrieved SSTskin from both Aqua and Terra satellites by comparisons with collocated Saildrone-derived SSTskin data. The mean differences in SSTskin from the SD-1036 and SD-1037 measurements are different by ~0.4 K, largely resulting from differences in the atmospheric conditions experienced by the two Saildrones. The performance of MODIS on Aqua and Terra in retrieving SSTskin is comparable. Negative brightness temperature (BT) differences between 11 μm and 12 μm channels are identified as being physically based, but are removed from the analyses as they present anomalous conditions for which the atmospheric correction algorithm is not suited. Overall, the MODIS SSTskin retrievals show negative mean biases, -0.234 K for Aqua and -0.295 K for Terra. The variations in the retrieval inaccuracies show an association with diurnal warming events in the upper ocean from long periods of sunlight in the Arctic. Also contributing to inaccuracies in the retrieval is the surface emissivity effect in BT differences characterized by the Emissivity-introduced BT difference (EΔBT) index. This study demonstrates the characteristics of MODIS-retrieved SSTskin in the Arctic, at least at the Pacific side, and underscores that more in situ SSTskin data at high latitudes are needed for further error identification and algorithm development of IR SSTskin.

Electricity load forecasting is a crucial undertaking within all the deregulated markets globally. In contemporary times, the transition from conventional electricity grids to Smart Grids constitutes an area where extensive research is conducted on a global scale. Among the research challenges, the investigation of Deep Transfer Learning (DTL) in the field of electricity load forecasting represents a fundamental effort that imparts generality to Artificial Intelligence applications, due to new capabilities, such as knowledge transfer and computational power reduction. In this paper a comprehensive study is conducted for day-ahead electricity load forecasting. For this purpose, three Sequence-to-Sequence (Seq2seq) Deep Learning (DL) models are used, namely the Multilayer Perceptron (MLP), the Convolutional Neural Network (CNN) and the Ensemble Learning Model (ELM), which is consisted of the weighted combination of the outputs of MLP and CNN models. Also, the study focuses on the development of different forecasting strategies based on DTL and emphasizing the way the datasets are trained and fine-tuning for higher forecasting accuracy. In order to implement the forecasting strategies using Deep Learning models, load datasets from three Greek islands, Rhodes, Lesvos, and Chios, are used. The main purpose is to apply DTL for day-ahead predictions (1-24 hours) for each month of the year for Chios dataset after training and fine-tuning the models using the datasets of the three islands in various combinations. After several trials, four DTL strategies are illustrated. In the first strategy (DTL Case 1), each of the three DL models is trained using only Lesvos dataset, while fine-tuning is performed on the dataset of Chios island, in order to create day-ahead predictions for Chios load. In the second strategy (DTL Case 2), data from both Lesvos and Rhodes concurrently are used for the DL model training period, and fine-tuning is performed on the data from Chios. The third DTL strategy (DTL Case 3) contains the training of the DL models using Lesvos dataset, and the testing period performed directly on the Chios dataset without fine-tuning. The fourth strategy is a Multi-task Deep Learning (MTDL) approach, which has been extensively studied in recent years. In MTDL, the three DL models are trained simultaneously on all three datasets and the final predictions are made on the unknown part of the dataset of Chios. In this paper, we explore the performance of DTL and compare the results with those produced with MTDL. The results demonstrated that DTL can be applied with high efficiency for day-ahead load forecasting. Specifically, the two cases with fine-tuning (DTL Case 1 and 2) outperformed MTDL in terms of load prediction accuracy. Regarding the DL models, all three exhibit very high prediction accuracy, especially in the two cases with fine-tuning. The ELM excels compared to the single models. More specifically, for conducting day-ahead predictions, it has been concluded that the MLP model presents best monthly forecasts with a MAPE of 6.24% and 6.01% for the first two cases, the CNN model presents best monthly forecasts with a MAPE of 5.57% and 5.60% respectively and the ELM model achieves best monthly forecasts with a MAPE of 5.29% and 5.31%, respectively, indicating the very high accuracy it can achieve.

Heavy rains result in significant threats to human health and life. Floods and other natural disasters, which have a global impact annually, can be attributed to extended periods of intense precipitation. Accurate rainfall prediction is crucial in nations such as Bangladesh, where agriculture is the predominant field of occupation. The efficiency of machine learning methods is enhanced by the nonlinearity of rainfall, surpassing the effectiveness of other approaches. This study proposes the novel combination of rainfall occurrence prediction, rainfall amount prediction, and daily average temperature prediction. This research implements machine learning techniques and an ensemble-based classifier to predict rainfall occurrence, as well as machine learning regressor models and an ensemble-based regressor to predict the rainfall amount and daily average temperature, using the Bangladesh Weather Dataset. The ensemble classifier demonstrated an accuracy of 83.41% and a recall of 78.17%, exhibiting the best performance in predicting when it will rain, but its precision was the lowest, at 51.16%. The ensemble regression model outperformed the base models, including linear regression, random forest, and support vector regression in rainfall amount prediction, with the lowest mean absolute error of 0.36 and root mean squared error of 0.90. Additionally, this model provided the most precise daily average temperature prediction results with the lowest mean absolute error of 0.42 and root mean squared error of 0.54, highlighting its superiority over the other regression models in forecasting temperature. Ensemble approaches consistently exhibit superior task performance metrics.

Accurate measurement of systemic financial risk is critical to maintaining the stability of financial markets. Taking China as the subject of investigation, the Chinese Financial Stress Index (CFSI) indicator system was con-structed by integrating six dimensions and employing Gray Relation Analysis (GRA) for dimensionality reduction of the indicators. The CFSI was derived using the Attribute Hierarchy Model (AHM) method with the Criteria Importance Through the Intercriteria Correlation (CRITIC) method, and an Improved Gravitational Search Algorithm (IGSA) optimized Radial Basis Function Neural Network (RBFNN) was proposed for out-of-sample prediction of CFSI trends from 2024 to 2026. By analyzing the trend of financial pressure indicators, the relationship between financial pressure and economic activity can be effectively identified. The research findings indicate that: (1) The CFSI is capable of accurately reflecting the current financial stress situation in China; (2) The IGSA-RBFNN demonstrates good robustness and generalization capabilities, predicting that the CFSI index will reach a peak value of 0.543 by the end of 2024, and there exists a regular pattern of stress rebound towards the end of each year. The novel methodology benefits policymakers and regulatory authorities to formulate preventive measures and risk management by identifying potential risks and vulnerabilities in advance.

This study considers an application of the first-order Grey Markov Model to foresee the values of Italian power generation in relation to the available energy sources. The model is used to fit data from the Italian energy system from 2000 to 2022. The integration of Markovian error introduces a random element to the model, which is able now to capture inherent uncertainties and misalignments between the Grey model predictions and the real data. This application provides valuable insights for strategic planning in the energy sector and future developments. The results show good accuracy of the predictions, which provides powerful information for the effective implementation of energy policies concerning the evolution of energy demand in the country. Despite advancements, Italy’s 2032 energy mix will still significantly rely on fossil fuels, emphasizing the need for sustained efforts beyond 2032 to enhance sustainability.

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.

Logistics plays an important role in globalized companies and contributes to the development of foreign trade. A large number of external conditions, such as recession and inflation, affect logistics. Therefore, managers should find ways to improve operational performance, enabling them to increase efficiency while considering environmental sustainability due to the industry’s large scale of energy consumption. Based on data collected from the financial reports of top global logistics companies, this study uses a DEA model to calculate corporate efficiency by implementing a Grey forecasting approach to forecast future sustainability values. Consequently, the study addresses the problem of how to enhance operational performance while accounting for the impact of external conditions. This research can help logistics companies develop operation strategies in the future that will enhance their competitiveness vis-à-vis rivals in a time of global economic volatility.

To enhance the safety of power grid operations, this study proposes a high-precision short-term photovoltaic power prediction method that integrates information from surrounding pho-tovoltaic stations and the Conv-LSTM-ATT model. In the deep learning prediction model, not only is numerical weather prediction (NWP) data from the target photovoltaic station used as input features, but also highly correlated features from nearby photovoltaic stations are incor-porated. The research begins by analyzing the correlation between irradiance and power se-quences, along with distance factors, to calculate a composite similarity index between the target and other regional photovoltaic stations. Stations with high similarity indices are then selected as data sources. Subsequently, Bayesian optimization techniques are employed to find the optimal data fusion ratios. Ultimately, using the selected data, power prediction mod-eling is conducted via the Conv-LSTM-ATT deep neural network. Experimental results con-firm the superiority of the proposed model, which demonstrates higher predictive accuracy compared to three other classical models. The data fusion strategy determined by Bayesian optimization significantly enhances prediction accuracy, reducing the root mean square error (RMSE) of the test set by 20.04%, 28.24%, and 30.94% for three weather types, respectively.

Globalization and industrialization have significantly disturbed the environmental ecosystem, leading to critical challenges such as global warming, extreme weather events, and water scarcity. Forecasting temperature trends is crucial for enhancing the resilience and quality of life in smart sustainable cities, enabling informed decision-making and proactive urban planning. This research specifically targets Ahmedabad city in India and employs the Seasonal Auto Regressive Integrated Moving Average with eXogenous factors (SARIMAX) model to forecast temperatures over a ten-year horizon using two decades of real-time temperature data. The stationarity of the dataset was confirmed using the Augmented Dickey-Fuller test, and the Akaike Information Criterion (AIC) method helped identify the optimal seasonal parameters of the model, ensuring a balance between fidelity and predictive accuracy. The model achieved an RMSE of 1.0265, indicating high accuracy within the typical range for urban temperature forecasting. This robust measure of error underscores the model’s precision in predicting temperature deviations, which is particularly relevant for urban planning and environmental management. The findings provide city planners and policymakers with valuable insights and tools for preempting adverse environmental impacts, marking a significant step towards operational efficiency and enhanced governance in future smart urban ecosystems. Future work may extend the model's applicability to broader geographical areas and incorporate additional environmental variables to refine predictive accuracy further.

Accurate forecasting of available energy portion that corresponds to the reservoir inflow of the month(s) ahead provides important decision support for the hydropower plants in energy pro-duction planning for revenue maximization, as well as for the environmental impact prevention, and flood control at the upstream and downstream of a basin. Therefore, a reliable forecasting tool or model is deemed necessary and crucial. Considering the fluctuation and nonlinearity of data which significantly influence the forecasting results, this study develops an effective hybrid model by integrating Artificial Neural Network (ANN) and Particle Swarm Optimization (PSO) called “PSO-ANN” model based on the hydrological and meteorological data pre-processed by cross-correlation function (CCF), autocorrelation function (AFC), and normalization techniques for predicting the available energy portion corresponding to the reservoir inflow mentioned above for a case study hydropower plant in Laos namely, Theun-Hinboun hydropower plant (THHP). The model was evaluated by using correlation coefficient (r), relative error (RE), root mean square error (RMSE), and Taylor diagram plots in comparison with the popular single algorithm approaches such as ANN, and NARX models. Results demonstrated the superiority of the proposed PSO-ANN approach over the other two models.

Recent studies have shown the potential of Transformer-based neural networks in increasing prediction capacity. However, classical transformers present several problems such as computational time complexity and high memory requirements, which make Long Sequence Time-Series Forecasting (LSTF) challenging. The contribution to the prediction of time series of flood events using deep learning techniques is examined, with a particular focus on evaluating the performance of the Informer model (a particular implementation of transformer architecture), which attempts to address the previous issues. This study explores the predictive capabilities of the Informer model compared to statistical methods, stochastic models and traditional deep neural networks. The accuracy, efficiency as well as the limits of the approaches are demonstrated via numerical benchmarks relating to real river streamflow applications. Using daily flow data from the River Test in England as the main case study, we conduct a rigorous evaluation of the Informer efficacy in capturing the complex temporal dependencies inherent in flood time series. Among other things, the present work extends its analysis to encompass diverse time series datasets from various locations (>100) in the United Kingdom, providing insights into the generalizability of the Informer. The results highlight the significant superiority of the Informer model over established forecasting methods, especially regarding the LSTF problem. Furthermore, it is observed that the structure of time series, as expressed by climacogram, affects the performance of the Informer network.

In this paper, we present an experimental procedure to enhance the dimensional accuracy of fabrication via Stereolithography (SLA) of features at the micro-scale. Using a custom benchmark part, deviations in feature dimensions (micro-pores diameters and depths) were detected and measured by confocal microscopy. Samples characterization and experimental observations allowed the identification of inaccuracy sources, mainly due to the laser beam scanning strategy and to the incomplete removal of uncured liquid resin in post-processing (i.e., IPA washing). As a technology baseline, the measured dimensional errors on pores diameters were up to -46%. A compensation method of the nominal laser spot diameter (85m) was defined and implemented resulting in relevant improvements in dimensional accuracy of 9.8% and 11.3% on full-open pores diameter and depth, respectively. Further investigation was performed on a customized test part to adjust the calibration procedure. The measurements revealed that the estimate of the laser beam spot size is 968m. Measurements on micro-pores having different sizes revealed that a constant compensation parameter (i.e., C=85, 96, 120m) is not fully effective at the micro-scale, where average errors still remain at -24%, -18.8%, and -16% for compensations equals to 85, 96 and 120m, respectively. A further experimental campaign allowed the identification of an effective nonlinear compensation law where the compensation parameter depends on the micro-feature size C= f (D). Results show a sharp improvement in dimensional accuracy on micro-pore fabrication, with errors consistently below +8.2%. The proposed compensation method can be extended for the fabrication of any micro-features without restrictions on the specific technology implementation. Concerning the inaccuracy introduced by the laser path, experimentation with a customized part allowed the optimization of the part orientation to reduce the errors and their differences along the X and Y machine axes.

The Imbalance Cost Pass-Through (ICPT) is a flexible component of the Incentive Regulation (IBR) that empowers power producers to adjust tariffs in response to variable fuel prices, thereby enhancing the economic resilience of electricity generation. However, the cost of electricity generation is significantly influenced by the volatility of commodity prices, including coal, gas and LNG. In Malaysia, the Energy Commission has conducted biannual reviews of fuel and other generation costs. Any cost savings or increases identified during these reviews will be passed on to customers in the form of rebates or surcharges. Due to that reason, this study proposes ICPT price forecasting for the electricity market in Peninsular Malaysia. The study aims to construct an ICPT-related baseline model for the peninsular generation data by employing three forecasting methods. The forecasting performance is analysed by a Mean Absolute Percentage Error (MAPE). In findings, the ARIMA method is one of the most accurate forecasting methods for fuel prices compared to the Moving Average (MA) and LSSVM methods. The observed price differences between the ARIMA and LSSVM models for ICPT are minimal. The ICPT price for July-December 2022 and January-June 2023 is MYR 0.21/ kWh for ARIMA and MYR 0.18/kWh for LSSVM, which are close to the actual TNB’s ICPT tariff. As for the forecasting, the ICPT price is expected to drop for the next announcement. The findings of this study may contribute to a positive impact on the sustainability of the energy sector in Malaysia.

With the global objectives of achieving a ‘carbon peak’ and ‘carbon neutrality’, along with the implementation of carbon reduction policies, China’s industrial structure has undergone significant adjustments, resulting in constraints on high-energy consumption and high-emission industries while promoting the rapid growth of green industries. Consequently, these changes have led to an increasingly complex power system structure and presented new challenges for electricity demand forecasting. To address this issue, this study proposes a 24-step multivariate time series short-term load forecasting algorithm model based on KNN data imputation and BiTCN bidirectional temporal convolutional networks combined with BiGRU bidirectional gated recurrent units and attention mechanism. The Kepler adaptive optimization algorithm (KOA) is employed for hyperparameter optimization to effectively enhance prediction accuracy. Furthermore, using real load data from a wind farm in Xinjiang as an example, this paper predicts the electricity load from January 1st to December 30th in 2019. Experimental results demonstrate that our comprehensive short-term load forecasting model exhibits lower prediction errors and superior performance compared to traditional methods, thus holding great value for practical applications.

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.

Dengue fever is a persistent public health issue in tropical regions, including Vietnam, where climate variability plays a crucial role in disease transmission dynamics. This study focuses on developing climate-based machine learning models to forecast dengue outbreaks in Ba Ria Vung Tau (BRVT) province, Vietnam, using meteorological data from 2003 to 2022. We utilized four predictive models—Negative Binomial Regression (NBR), Seasonal AutoRegressive Integrated Moving Average with Exogenous Regressors (SARIMAX), Extreme Gradient Boosting (XGBoost), and Long Short-Term Memory (LSTM)—to predict weekly dengue incidence. Key climate variables, including temperature, humidity, precipitation, and wind speed, were integrated into these models, with lagged variables included to capture delayed climatic effects on dengue transmission. The NBR model demonstrated the best performance in terms of predictive accuracy, achieving the lowest Mean Absolute Error (MAE) compared to other models. The inclusion of lagged climate variables significantly enhanced the model’s ability to predict dengue cases. SARIMAX and LSTM models, although effective in capturing seasonal trends, struggled with overfitting and failed to accurately predict short-term outbreaks. XGBoost exhibited moderate predictive power but was sensitive to overfitting, particularly without fine-tuning. Our findings confirm that climate-based machine learning models, particularly the NBR model, offer valuable tools for forecasting dengue outbreaks in BRVT. However, improving the models’ ability to predict short-term peaks remains a challenge. The integration of meteorological data into early warning systems is crucial for public health authorities to plan timely and effective interventions. This research contributes to the growing body of literature on climate-based disease forecasting and underscores the need for further model refinement to address the complexities of dengue transmission in highly endemic regions.

Background: Low back pain (LBP) is a major cause of disability globally, and the diagnosis of LBP is challenging for clinicians. Objective: This study aimed to assess the accuracy level of arti-ficial intelligence as a Clinical Decision Support System (CDSS) called Therapa compared to MRI in predicting lumbar disc herniated patients. Methods: One hundred low back pain patients aged ≥18 years old were included in the study. The study was conducted in 3 stages, at first, a case se-ries was conducted by matching MRI and Therapha diagnosis for 10 patients. Subsequently, Delphi methodology was employed to establish a clinical consensus. Lastly, to determine the ac-curacy of the newly developed software, a cross-sectional study was undertaken, involving 100 patients. Results: The software showed a significant diagnostic accuracy with the area under the curve in the ROC analysis determined as 0.84 with a sensitivity of 88% and a specificity of 80%. Conclusion: The study’s findings revealed that CDSS using Therapha has a reasonable level of ef-ficacy, and this can be utilized clinically to acquire faster and more accurate screening of patients with lumbar disc herniation.

The accurate forecasting of solar power output is essential for ensuring the stable and efficient operation of grid-connected photovoltaic (PV) systems, especially when faced with variable weather patterns. This research focuses on the integration of Machine Learning (ML) methodologies and climatic parameters to predict solar panel energy generation, with a specific emphasis on addressing consumption-production imbalances. Leveraging a dataset sourced from the Kaggle platform, the study is conducted in the context of Estonia, aiming to optimize solar energy utilization in this geographic region. The dataset, obtained from Kaggle, encompasses comprehensive information on climatic variables, including sunlight intensity, temperature, and humidity, alongside corresponding solar panel energy output. Leveraging machine learning algorithms, including XGBoost regression and neural networks, our model aims to identify complex patterns and relationships within the datasets. By tailoring the model to Estonia's climatic nuances, we seek to enhance the accuracy of energy production forecasts and, consequently, better manage the challenges associated with consumption-production imbalances. Furthermore, the research investigates the adaptability of the proposed model to diverse climatic conditions, ensuring its applicability for similar endeavors in other geographical locations. The performance of the forecasting model will be evaluated using error metrics like mean absolute error (MAE) and root mean squared error (RMSE). This study leverages a comprehensive dataset from Kaggle and utilizes advanced machine learning techniques to generate valuable insights. These insights can inform the development of sustainable energy policies and practices, ultimately leading to a more efficient and reliable renewable energy infrastructure.

Droughts have negative impacts on agricultural productivity and economic growth. Effective monitoring and accurate forecasting of drought occurrences and trends are crucial for minimizing drought losses and mitigating their spatial and temporal effects. In this study, trend dynamics in monthly total rainfall time series measured at Cape Town International Airport were analyzed using Mann-Kendall (MK) test, Modified Mann-Kendall (MMK) and innovative trend analysis (ITA) were examined. Additionally, we utilized hybrid prediction method that combined the model with the complementary ensemble empirical mode decomposition with adaptive noise (CEEMDAN) technique, the autoregressive integrated moving average (ARIMA) model, the long short-term memory (LSTM) network (i.e. CEEMDAN-ARIMA-LSTM) to forecast SPI values of 6-, 9-, and 12-months using rainfall data between 1995 and 2020 from Cape Town International Airport meteorological rainfall stations. The results demonstrate the following essential points: (1) The trend analysis results of the total monthly rainfall values indicate a significant decreasing trend with the negative z-score (MK= -3.7541 and MMK= - 4.0773). ITA also indicated a significant downwards trend of rainfall in the study area. (2) As the forecasting horizon increases, the prediction accuracy of the models and CEEMDAN-combined models gradually improves, reaching their optimum performance at the 12-month horizon. (3) CEEMDAN efficiently stabilizes time-series data, resulting in greater prediction accuracy in the hybrid model compared to individual models at all timescales. (4) The RMSE and R2 values for the hybrid CEEMDAN-ARIMA-LSTM model at a 12-month forecasting horizon are 0.042 and 0.995, demonstrating the applicability of this hybrid approach for drought forecasting.

(1) Background: To determine the diagnostic accuracy that optical coherence tomography (OCT) can add to fundus photography (FP) in assessing the condition of the retinal posterior pole; (2) Methods: Two blocks of analysis: at first, the posterior pole of each eye was examined using FP non-mydriatic imaging device. Secondly: OCT was used in addition to FP. After consolidating specific diagnostic criteria, the assessments were evaluated by two blinded independent investigation groups (by optometrists, and by ophthalmologists who was considered the gold standard); (3) Results: We calculated the diagnostic accuracy of FP compared to OCT and found that both had similar sensitivity, FP had slightly higher specificity, (p-value: 0.01) and OCT had a higher kappa coefficient 0.50 (95%CI: 0.46-0.55) vs 0.39 (95%CI: 0.34-0.45) of FP; (4) Conclusions: Based on the premise that the role of the optometrist in Spain is not to diagnose but to detect lesions and refer patients to an ophthalmologist, the results of this study support the use of OCT, that it provided gradable images in almost all examined eyes (97.5%), compared to FP (73.5%). However, the optometrist need a detailed and standardized guide in order to evaluate according to the ophthalmologist's criteria.

Objective: This study aimed to demonstrate the availability of portable devices for nasal FeNO measurement, which could replace exhaled NO measurement based on the continuous aspiration of multiple flow measurement systems. Methods: A descriptive cross-sectional study. The healthy subjects without rhinosinusis disorders (control group) and those with diagnosed allergic rhinitis (AR group) were enrolled in the study. They underwent nasal and bronchial FeNO measurements by both fixed flow NObreath® connected to nasal mask and multiple flows HypAir FeNO®. Results: A total of 153 people were recruited including 63 healthy subjects and 90 subjects with AR. There were no statistically significant differences in anthropometric characteristics between the two groups (P > 0.05). There were a significant increase in FeNO values in the AR group compared to the control group; concentrations of nasal and bronchial FeNO mearsured by NObreath® were 76.0 ± 50.7 ppb (vs 36.0 ± 28.1 ppb, P < 0.01) and 32.3 ± 15.4 ppb (vs 9.2 ± 5.6 ppb, P < 0.001), and those mearsured by NObreath® Hypair FeNO® were 1796.9 ± 523.3 ppb (vs 400.2 ± 123.1 ppb, P < 0.001) and 37.3 ± 23.0 ppb (vs 17.4 ± 18.3 ppb, P < 0.01). A weak correlation between the values measured by NObreath® and Hypair FeNO® devices was observed (r = 0.023 and r = 0.089, respectively; p < 0.05). Conclusions: The handheld NObreath® device is effective in measuring FeNO concentrations in both normal subjects and AR patients. The advantages in price and size, creating a compact, low-cost device that is convenient for use and research.

Effective solar forecasting has become a critical topic in the scholarly literature in recent years due to the rapid growth of photovoltaic energy production worldwide and the inherent variability of this source of energy. Due to the technological and econonomic limitations of energy storage solutions, using other, mosty conventional, sources to cover energy shortfalls and at the same time utilising solar surpluses production becomes necessary. The need to optimize energy systems, ensuring power continuity, and balancing energy supply and demand has led to the development of various forecasting methods and approaches based on meteorological data or photovoltaic plant characteristics. This article presents the results of a meta-review of the solar forecasting literature, including the current state of knowledge and methodological discussion. It presents a comprehensive set of forecasting methods, evaluates current classifications, and proposes a new synthetic typology. The article emphasizes the increasing role of artificial intelligence (AI) and machine learning (ML) techniques in improving forecast accuracy, alongside traditional statistical and physical models. It explores the challenges of hybrid and ensemble models, which combine multiple forecasting approaches to enhance performance. The paper addresses the emerging trends in solar forecasting research, such as the integration of big data and advanced computational tools. Additionally, from a methodological perspective, the article outlines a rigorous approach to the meta-review research procedure, addresses the scientific challenges associated with conducting bibliometric research, and highlights best practices and principles. This includes defining research questions, selecting eligibility criteria, literature search, data extraction, synthesis, and assessing bias and quality. The article contributes to the solar forecasting field by providing up-to-date knowledge, along with insights on the emerging trends, future research directions, and anticipating implications for the theory and practicce.

: Leveraging the sustainability of the power system market, researchers have developed various ML models for forecasting electricity demand. The LSSVM is well suited to handle complex non-linear power load series. However, the less optimal regularization parameter and the Gaussian kernel function in the LSSVM model have contributed to flawed forecasting accuracy and random generalization ability. Thus, these parameters of LSSVM need to be chosen appropriately using intelligent optimization algorithms. This study proposes a hybrid model based on the LSSVM optimized by the IBFOA for forecasting the daily electricity load in Peninsular Malaysia. The IBFOA for parameter optimization of LSSVM is introduced. The IBFOA based on the sine cosine equation is proposed to adjust the constant step size in the BFOA, which creates an imbalance between the exploration and exploitation during optimization. Finally, the load forecasting model based on LSSVM-IBFOA is constructed using MAPE as the objective function. Comparative analysis demonstrates the model, achieving the highest R2 (0.9880) and significantly reducing error metrics (MAPE, MAE, RMSE, MSE, NRMSE) compared to the baseline LSSVM (average reduction of 27.72% to 47.72%). Additionally, IBFOA exhibits faster convergence and higher accuracy compared to BFOA, highlighting the accuracy of LSSVM-IBFOA for short-term load forecasting.

This study focuses on predicting PM2.5 levels at the University of Petroșani by employing advanced machine learning techniques to analyze a dataset that encapsulates a wide array of air pollutants and meteorological factors. Utilizing data from IoT sensors and established environmental monitoring stations, the research leverages Random Forest, Gradient Boosting Machines, and Support Vector Regression models to forecast air quality, emphasizing the complex interplay between various pollutants. The models demonstrate varying degrees of accuracy, with the Random Forest model achieving the highest predictive power, indicated by an R2 score of 0.82764. Our findings highlight the significant impact of specific pollutants such as NO, NO2, and CO on PM2.5 levels, suggesting targeted mitigation strategies could enhance local air quality. Additionally, the study explores the role of temporal dynamics in pollution trends, employing time-series analysis to further refine the predictive accuracy. This research contributes to the field of environmental science by providing a nuanced understanding of air quality fluctuations in a university setting and offering a replicable model for similar environments seeking to reduce airborne pollutants and protect public health.

This study challenges the prevailing belief in the necessity of complex models for accurate forecasting by demonstrating the effectiveness of parsimonious econometric models, namely ARCH(1) and GARCH(1,1), over deep learning robust approaches, such as LSTM and 1D-CNN neural networks, in modeling historical volatility within pre-emerging stock markets, specifically the Moroccan and Bahraini stock markets. The findings suggest reevaluating the balance between model complexity and predictive accuracy. Future research directions include investigating the potential existence of threshold effects in market capitalization for optimal model performance. This research contributes to a deeper understanding of volatility dynamics and enhances forecasting models’ effectiveness in diverse market conditions.

Introduction: Biliary Atresia (BA) is a common cause of neonatal cholestatic jaundice which, if recognized and treated early, can be life-saving for the infant. If the liver biopsy suggests the presence of BA, exploratory laparotomy is then carried out to confirm the diagnosis, along with the Kasai procedure to provide drainage to the bile secreted by the liver. The purpose of this study is to get a deep dive into all the various imaging modalities that can diagnose BA more effectively and with absolute certitude, thus helping prevent several children from a grave prognosis.Methodology: For the collection of the data, a search was done by two individuals using PubMed, Google Scholar, and Cochrane Library databases for all relevant literature. Each qualifying paper was evaluated independently by two reviewers. Each article was analyzed for the number of patients, their age, procedure modality, complexity of ethology, and incidence of the pre-decided complications. The statistical software packages RevMan (Review Manager, version 5.3), SPSS (Statistical Package for the Social Sciences, version 20), Google Sheets, and Excel in Stata 14 were used to perform the statistical analyses. The data was obtained and entered into analytic software.Results: A total of 39 studies with 3,679 subjects were selected for the study, out of which 7 studies showed sensitivity above or equal to 95%, and an astounding 14 studies showed specificity above 95%. The value of True Positive (TP) was 1280, that of True Negative (TN) was 1817, that of False Positive (FP) was 239, and that of False Negative (FN) was 343. With a confidence interval of 95%, sensitivity, specificity, and positive predictive values were calculated. The sensitivity of Ultrasonography for Biliary Atresia is 0.79, with a CI of 95% in a range of 0.77 to 0.81. The specificity of Ultrasonography for Biliary Atresia is 0.88, with a CI of 95% in a range of 0.87 to 0.90. Conclusion: Even though several radiological techniques at present help to detect BA, USG of the abdomen proves to be an effective diagnostic and a modest screening test for the detection of BA.

Sentiment analysis to characterize properties of Bitcoin prices and their forecasting is here developed thanks to the capability of the Fuzzy transform to capture stylized facts and mutual connections between time series having different nature. Six years of daily Bitcoin Prices and Google Trends are analyzed in order to establish new perspectives in the management of their dynamics.

Background: Forecasting nonlinear stochastic systems most often is quite difficult, without giving in to temptations to simply simplify models for the sake of permitting simple computations. Objective: Here, two basic algorithms, Adaptive Simulated Annealing (ASA) and path-integral codes PATHINT/PATHTREE (and their quantum generalizations qPATHINT/qPATHTREE) are offered to detail such systems. Method: ASA and PATHINT/PATHTREE have been effective to forecast properties in three disparate disciplines in neuroscience, financial markets, and combat analysis. Applications are described for COVID-19. Results: Results of detailed calculations have led to new results and insights not previously obtained. Conclusion: These 3 applications give strong support to a quite generic application of these tools to stochastic nonlinear systems.

Background: Visual acuity (VA) assessments are crucial in ophthalmology but traditionally rely on in-clinic evaluations. The emergence of telemedicine has spurred interest in creating dependable self-administered VA tests for use beyond standard clinical environments. This study evaluates the practicality and validity of a self-administered Near VA card test against traditional Snellen and Rosenbaum Pocket Vision Screener (RPVS) methods for home monitoring and enhancing clinical workflow. Methods: In a cross-sectional study a near VA card (Hadassah Self-Visual Acuity Screener-HSVA) was developed with written and videotaped instructions for self-use. Patients with a minimal best corrected VA (BCVA) of 1.0 LogMAR in at least one eye were recruited from Ophthalmology and Optometry clinics. Outcomes included mean BCVA difference between the self-administered and those obtained by the examiner, and correlations among BCVA values obtained by Snellen, RPVS, HSVA and previous distance BCVA according to the patient electronic medical records. Results: A total of 275 participants (mean age: 42.5±19.4 years, range: 18-89 years, 47% female) were included. Test-retest reliability analysis for the HSVA demonstrated very good correlation and repeatability (n=38 patients.; Rs=1.0, P

A method for estimating river water surface elevation (WSE) from Landsat imagery using the river inundation area - water surface elevation (RIA-WSE) rating curve constructed from the U.S. Geological Survey Topobathymetric Elevation Model (TEM) data was developed and tested at six gauging stations along the upper Mississippi River. The Otsu's automatic threshold selection algorithm was employed for the image classification and estimation of inundation areas within each pre-defined polygon around each gauging station. In addition to the commonly used green-band based water indices, Landsat 8 and 9 OLI's ultra-blue, blue, and red band-based water indices were also tested in this study, which resulted in twenty different water indices: NDWIv (Normalized Difference Water Index), MNDWI1v and MNDWI2v (Modified Normalized Difference Water Index), AWEIsv (Automatic Water Extraction Index with shadow), and AWEInsv (AWEI without shadow), where v represents the visible light band used in the water index. At each station, about 60-80 Landsat 8 or 9 images during 2013-2023 were used for assessing the performances of the twenty water indices through comparing the estimated WSEs with the measured WSEs. Results showed that the ultra-blue or red band-based AWEIs yielded the most accurate estimations of WSEs among the twenty tested water indices.

The Geopyörä breakage test uses two counter-rotating wheels to nip and crush rock specimens with a tightly controlled gap between rollers. The force applied and energy consumed during breakage are measured with instrumentation. In contrast to drop weigh test (DWT) methods, the breakage energy is a response to the rock compressive strength and degree of compression, not a controlled test input, such as the kinetic input energy of a falling weight. This paper presents the detailed measures conducted to evaluate the accuracy and precision of energy measurements across various ore types using the Geopyörä device. While force measurement was assessed just for its precision. The outputs are compared directly to the DWT measures of fragmentation at the same energy and fitted A and b parameters. The test reproducibility was evaluated using a Round-Robin methodology, testing several samples in multiple laboratories. The results confirmed that the new test has sufficient accuracy to match DWT results and excellent precision to assure reproducibility.

We conducted a study to determine if antenatally collected maternal urine cotinine (a me- 13 tabolite of nicotine) measurements can be used to assess the neonatal impact of nicotine exposure 14 during pregnancy. This was a prospective longitudinal cohort of mother-infant dyads. Only term 15 singleton pregnancies were included. The primary outcome measure was the correlation between 16 maternal urine cotinine and infant birth weight. We analysed data from 238 mother-neonates' dy- 17 ads. Urine cotinine was detected in 50.4 % (120/238) women from the whole cohort, but only 16% 18 (38/238) self-reported as smokers (chi-square 39.7, p<0.0001), and these women had significantly 19 smaller babies (p=0.010). There was a significant negative correlation between maternal urine co- 20 tinine and birth weight (Spearman's coefficient = -0.0226, p=0.013). Female babies born to women 21 with nicotine in the urine were significantly smaller (p= 0.001). The number of women exposed to 22 nicotine during late pregnancy (measured in urine) was markedly higher than self-reported and 23 National smoking percentages, suggesting an urgent need for improvement of medical record re- 24 porting on smoking habits to better assess neonatal outcomes.

Persistent land subsidence or uplift can cause serious latent hazards to urban infrastructure. To thoroughly investigate the causes and impacts of land surface deformation, this study examines the case of Wuxi City, focusing on the land fluctuation patterns in the region following the enforcement of the groundwater abstraction prohibition policy in 2005. This research utilizes the PS-InSAR technique to quantify land surface deformations in the Wuxi region from November 2015 to June 2023 and analyzes 100 SAR images to obtain comprehensive spatiotemporal evolution data of the land surface. Furthermore, this study conducts an in-depth analysis of the effects of various factors, including groundwater, precipitation, and soil geology, on the characteristics of land surface deformation. It pioneers the application of the GARCH (Generalized Autoregressive Conditional Heteroskedasticity) model to analyze the time-series displacement in the study area and innovatively introduces the "amplitude factor" index to assess land surface fluctuations. This study investigates the recent land surface deformation patterns and mechanisms in Wuxi City. By integrating the "amplitude factor", it provides a scientific foundation for future urban development and disaster mitigation strategies in Wuxi City, offering valuable insights for related research.

Accurate forecasting of icing thickness has a great significance for ensuring the security and stability of power grid. In order to improve the forecasting accuracy, this paper proposes an icing forecasting system based on fireworks algorithm and weighted least square support vector machine (W-LSSVM). The method of fireworks algorithm is employed to select the proper input features with the purpose of eliminating the redundant influence. In addition, the aim of W-LSSVM model is to train and test the historical data-set with the selected features. The capability of this proposed icing forecasting model and framework is tested through the simulation experiments using real-world icing data from monitoring center of key laboratory of anti-ice disaster, Hunan, South China. The results show that the proposed W-LSSVM-FA method has a higher prediction accuracy and it may be a promising alternative for icing thickness forecasting.

The objective of this study is to evaluate the effect of constitutive equations on the prediction accuracy for springback in cold stamping with various deformation modes. In this study, two types of yield functions—Hill’48 and Yld2000-2d—were considered to describe yield behavior. Isotropic and kinematic hardening models based on the Yoshida–Uemori model were also adopted to describe hardening behavior. Various material tests (such as uniaxial tension, tension- compression, loading-unloading, and hydraulic bulging tests) were carried out to determine the material parameters of the models. The obtained parameters were implemented in the finite element (FE) simulation to predict springback, and the results were compared with experimental data. U-bending and T-shape drawing were employed to evaluate the springback prediction accuracy. Obviously, the springback prediction accuracy was greatly influenced by constitutive equations. Therefore, it is important to choose appropriate constitutive equations for accurate description of material behaviors in FE simulation.

This paper compares Demand Response algorithms suitable for Short-term Forecasting based on Advanced Metering Infrastructure (AMI). It selects ARIMA (AutoRegressive Integrated Moving Average), SARIMA (Seasonal ARIMA), LSTM (Long Short-Term Memory), and SVM (Support Vector Machine) as the primary research algorithms and delves into their theoretical foundations and functional characteristics. The theoretical background section explores each algorithm’s applicability in analyzing time-series data, recognizing nonlinear patterns, and solving optimization and classification problems. The methodology section will detail the methods of AMI data collection, the implementation of the algorithms, and the experimental setup. In the experiments and results section, the performance of each algorithm will be assessed by applying AMI data and presenting the outcomes of comparative analyses, with a focus on evaluating the predictive accuracy of the algorithms. The discussion will interpret the experimental results, analyzing the advantages and disadvantages of each algorithm and their applicability in the AMI system. It will also explore the limitations of the current research and directions for future research. The conclusion will summarize the key findings of the study and affirm how this research contributes to understanding and improving short-term forecasting and demand response systems based on AMI.

Especially for drought periods, the higher the accuracy of reservoir inflow forecasting, the more reliable the water supply from a dam. The article focuses on probabilistic forecasting of seasonal inflow to reservoirs and determines estimates from the probabilistic seasonal inflow according to drought forecast results. The probabilistic seasonal inflow was forecasted by a copula-based Bayesian network employing a Gaussian copula function. Drought forecasting was performed by calculation of the standardized streamflow index value. The calendar year is divided into four seasons; the total inflow volume of water to a reservoir for a season is referred to as the seasonal inflow. Seasonal inflow forecasting curves conforming to drought stages produce estimates of probabilistic seasonal inflow according to the drought forecast results. The forecasted estimates of seasonal inflow were calculated by using the inflow records of Soyanggang and Andong dams in the Republic of Korea. Under the threshold probability of drought occurrence ranging from 50 to 55 %, the forecasted seasonal inflows reasonably matched critical drought records. Combining the drought forecasting with the seasonal inflow forecasting may produce reasonable estimates of drought inflow from the probabilistic forecasting of seasonal inflow to a reservoir.

This paper presents the methods of estimating the mean square error of hydrological forecasts, allowing for assessment of their practical applicability. Depending upon the amount and composition of available hydrometeorological data, an appropriate method for forecast error estimation is chosen. A system of statistical tests for comparison of different forecasting methods for the same hydrologic characteristic with the same lead time is presented. These tests allow for choosing an optimal and most accurate forecasting method. Hydrological forecasting method efficiency estimation is based on comparing the forecast error with climatology or inertial (persistence) forecast error using presented tests.

Augmented and Virtual Reality have been experiencing a rapidly growth in recent years, but there is not still a deep knowledge on their capabilities and where they could be explored. In that sense, this paper presents a study on the accuracy and repeatability of the Microsoft's HoloLens 2 (Augmented Reality device) and HTC Vive (Virtual Reality device) using an OptiTrack system as ground truth. For the HoloLens 2, the method used was hand tracking, while in HTC Vive, the object tracked was the system's hand controller. A series of tests in different scenarios and situations were performed to explore what could influence the measures. The HTC Vive obtained results in the millimetre scale, while the HoloLens 2 revealed not so accurate measures (around 2 centimetres). Although the difference can seem to be considerable, the fact that HoloLens 2 was tracking the user's hand and not an inherit controller made a huge impact. The results were considered a significant step for the on going project of developing a human-robot interface to program by demonstration an industrial robot using Extended Reality, which shows great potential to succeed based on this data.

YG-13A represents the highest level of Chinese SAR satellites to date. In this paper, we report on experiments conducted to improve and validate ranging accuracy with YG-13A. We analyze the error sources in the YG-13A ranging system, such as atmospheric path delay, and transceiver channel delay. A real-time atmospheric delay correction model is established to calculate the atmospheric path delay, considering the troposphere delay and ionosphere delay. Six corner reflectors (CRs) were set up to ensure the accuracy of validation methods. Pixel location accuracies of up to 0.479-m standard deviation can be achieved after a complete calibration. We further demonstrate that the adjustment of the CRs can cause a marginal loss of ranging precision. After eliminating this error, the ranging accuracy is improved to 0.237 m. For YG-13A, a single frequency GPS receiver is used and the orbital nominal accuracy is 0.3 m, which is the biggest factor restricting its ranging accuracy. Our results show that the ranging accuracy of YG-13A can achieve decimeter-level, which is lower than centimeter-level accuracy with TerraSAR-X loading a dual frequency GPS. YG-13A has great convenience in terms of access to control points and target location that does not depend on ground equipment.

This research project aimed to address the growing concern about methane emissions from seaweed by developing a Convolutional Neural Network (CNN) model capable of accurately predicting these emissions. The study used PANDAS to read and analyze the dataset, incorporating statistical measures like mean, median, and standard deviation to understand the dataset. The CNN model was trained using the ReLU activation function and mean absolute error as the loss function. Model performance was evaluated through MAPE graphs, comparing the mean absolute percentage error (MAPE) between training and validation sets and between true and predicted emissions, and analyzing trends in yearly greenhouse gas emissions. The results demonstrated that the CNN model achieved a high level of accuracy in predicting methane emissions, with a low MAPE between the expected and actual values. This approach should enhance our understanding of methane emissions from Sargassum, contributing to more accurate environmental impact assessments and effective mitigation strategies.

Spatial light modulators (SLMs) have been widely used to achieve dynamic control of optical traps. Often, holographic optical tweezers have been presumed to provide nanometer or sub-nanometer positioning accuracy. It is known that some features concerning the digitalized structure of SLMs cause a loss in steering efficiency of the optical trap, but their effect on trap positioning accuracy has been scarcely analyzed. On the one hand, the SLM look-up-table, which we found to depend on laser power, produces positioning deviations when the trap is moved at the micron scale. On the other hand, phase quantization, which makes linear phase gratings become phase staircase profiles, leads to unexpected local errors in the steering angle. We have tracked optically-trapped microspheres with sub-nanometer accuracy to study the effects on trap positioning, which can be as high as 2 nm in certain cases. We have also implemented a correction strategy that enabled the reduction of errors down to 0.3 nm.

Link prediction is a significant field in network science, which focuses on predicting the probability of the existence or formation of a link between nodes in a social network based on currently observed connections. The effectiveness of traditional algorithms can vary depending on the type of network, making some methods more suitable than others for specific scenarios. Recently, several efficient link prediction algorithms have been developed, demonstrating robust results in both prediction accuracy and interpretability. However, existing research has not clearly established the relationship between network characteristics and link creation mechanisms for community influence analysis and anomaly detection. The ability to predict complex networks with diverse features still requires further investigation. In light of this, we introduce a novel framework designed to combine the best features of different link prediction algorithms when applied to the network, with the aim of achieving more reliable predictions about how networks will evolve. According to the proposed framework, we first focus on the feature extraction stage. During this phase, we systematically identify and extract a comprehensive set of features from the network before moving onto the classification phase. Here, we utilize state-of-the-art ensemble learning models to assess and classify potential links within the network. By training our machine learning models on the extracted features, we can effectively predict whether a particular link is likely to form (positive link) or unlikely to form (negative link). The ML models were trained and evaluated using two datasets: Twitch and Facebook. Results: Additionally, we assessed their performance on these datasets by conducting specific preprocessing and hyperparameter tuning steps. The final prediction model achieves AUC values between 94% and 99.3%. This research contributes significantly to efforts aimed at enhancing link prediction in dynamic socisal network contexts, providing valuable insights into the effectiveness of different ML algorithms in predicting future connections and enhancing our understanding of network dynamics.

Hybrid forecasting methods have emerged as a solution surpassing the limitations of both statistical and deep learning approaches. While the first emphasize the significance of variables, they often produce worse forecasting results when compared to newer techniques. In contrast, deep learning models remain enigmatic "black boxes" in terms of interpretability, although achieving better results in forecasting. This article introduces the Comprehensive Cross-Correlation and Lagged Linear Regression Deep Learning (CCLR-DL) framework, designed to harness the best of both approaches, enhancing forecasting accuracy while retaining model interpretability through a feature selection process. CCLR-DL blens cross-correlation analysis, lagged multiple linear regression and granger's causality procedures with deep learning architectures based on LSTM. In a practical demonstration, CCLR-DL was applied to a real database of clinical visits associated to diagnoses in Catalonia, Spain (tracking a population of 6.3 million patients during 10 years). Predicting visits enables the healthcare managers to be ready for future demand shifts. Results demonstrate a consistent and substantial improvement over standalone statistical and deep learning methods when predicting healthcare demand. This hybrid approach not only showcases its efficacy but also offers a promising solution to the challenge of balancing predictive accuracy with model explicability. In this context, this work aims to design and validate a method for feature selection and forecasting of multivariate high dimensional time series datasets not only to improve prediction accuracy but also to model transparency by identifying a subset of variables that improve predictions and G-cause the target variable.

Saliva, as a diagnostic medium, offers a promising alternative to blood by virtue of its non-invasive collection, which enhances patient compliance, especially in paediatric and geriatric populations. In this study, we assessed the utility of saliva as a non-invasive medium for measuring V. cholerae-specific serum antibodies in naturally infected individuals. We tested paired serum and saliva samples obtained from a total of 63 cholera patients enrolled in a cohort study. Vibriocidal antibodies assay (IgM/IgG) as markers for accurate determination was used to determine cholera specific antibody levels. Using receiver operating characteristics (ROC) curve, we found that the best cut-off that maximizes (sensitivity + specificity) is 10 titers. At this saliva titer, the sensitivity is 76.9% (95%CI: 60.9%, 87.7%) and specificity is 80.0% (95%CI: 56.6%, 92.5%). Using Spearman’s correlation coefficient, we also found evidence of a positive correlation between Vibrio Cholerae saliva and serum antibodies (rho=0.66, p&lt;0.001). In conclusion, saliva-based diagnostic cholera tests has high diagnostic accuracy, and would be advantageous, cheaper, and quicker for early diagnosis of severe cholera outcomes.

Flood forecasting helps anticipate floods and evacuate people, but due to the access of a large number of iot data acquisition devices, the explosive growth of multidimensional data and the increasingly demanding prediction accuracy, classical parameter models and traditional machine learning algorithms are unable to meet the high efficiency and high precision requirements of prediction tasks. In recent years, deep learning algorithms represented by convolutional neural networks, recurrent neural networks and Informer models have achieved fruitful results in time series prediction tasks. The Informer model is used to predict the flood flow of the reservoir. At the same time, the prediction results are compared with the prediction results of the traditional method and the LSTM model, and how to apply the Informer model in the field of flood prediction to improve the accuracy of flood prediction is studied. The data of 28 floods in the Wan 'an Reservoir control basin from May 2014 to June 2020 were used, with areal rainfall in five subzones and outflow from two reservoirs as inputs and flood processes with different sequence lengths as outputs. The results show that the Informer model has good accuracy and applicability in flood forecasting. In the flood forecasting with sequence length of 4, 5 and 6, Informer has higher prediction accuracy, and the prediction accuracy is better than other models under the same sequence length, but the prediction accuracy will decline to a certain extent with the increase of sequence length. The Informer model stably predicts the flood peak better, and its average flood peak difference and average maximum flood peak difference are the smallest. As the length of the sequence increases, the number of fields with a maximum flood peak difference less than 15% increases, and the maximum flood peak difference decreases. Therefore, the Informer model can be used as one of the better flood forecasting methods, and it provides a new forecasting method and scientific decision-making basis for reservoir flood control.

Since December 2019, the world is fighting against coronavirus disease (COVID-19). This disease is caused by a novel coronavirus termed as severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). This work focuses on the applications of machine learning algorithms in the context of COVID-19. Firstly, regression analysis is performed to model the number of confirmed cases and death cases. Our experiments show that autoregressive integrated moving average (ARIMA) can reliably model the increase in the number of confirmed cases and can predict future cases. Secondly, a number of classifiers are used to predict whether a COVID-19 patient needs to be admitted to an intensive care unit (ICU) or semi-ICU. For this, classification algorithms are applied to a dataset having 5644 samples. Using this dataset, the most significant attributes are selected using features selection by ExtraTrees classifier, and Proteina C reativa (mg/dL) is found to be the highest-ranked feature. In our experiments, random forest, logistic regression, support vector machine, XGBoost, stacking and voting classifiers are applied to the top 10 selected attributes of the dataset. Results show that random forest and hard voting classifiers achieve the highest classification accuracy values near 98%, and the highest recall value of 98% in predicting the need for admission into ICU/semi ICU units.

Background: Forecasting nonlinear stochastic systems most often is quite difficult, without giving in to temptations to simply simplify models for the sake of permitting simple computations. Objective: Here, two basic algorithms, Adaptive Simulated Annealing (ASA) and path-integral codes PATHINT/PATHTREE (and their quantum generalizations qPATHINT/qPATHTREE) are offered to detail such systems. Method: ASA and PATHINT/PATHTREE have been effective to forecast properties in three disparate disciplines in neuroscience, financial markets, and combat analysis. Applications are described for COVID-19. Results: Results of detailed calculations have led to new results and insights not previously obtained. Conclusion: These 3 applications give strong support to a quite generic application of these tools to stochastic nonlinear systems.

The presence of anti SARS-CoV2-RBD antibody (Anti-RBD) prevents severe COVID-19. We aimed to determine the accuracy of a point-of-care Anti-RBD test implemented in person living with HIV (PLWH), systemic lupus erythematosus (SLE), and chronic kidney disease (CKD). We enrolled 182 non-comorbid subjects and 335 persons with comorbid (PLWH, SLE, CKD) to test anti-RBD assay compared to surrogate viral neutralization (SVNT) as the reference test. We performed linear correlation analysis between anti-RBD vs SVNT and a ROC analyses to ascertain anti-RBD cut-off at 30%, 60%, and 90% inhibition of SVNT to calculate accuracy. Correlations of anti-RBD to SVNT among all groups were excellent with R= 0.7903, R=0.7843, R=0.8153 among non-comorbid, SLE and CKD groups, respectively, with significantly higher correlation among the PLWH group (R=0.8877; p-value=0.0072) compared to non-comorbid group. The accuracy of the anti-RBD test among PLWH and CKD group was similar with the non-comorbid but showed lower sensitivity in the SLE group (p=0.000014). The specificity of the test remained high in all groups. In conclusion, the Anti-RBD test had excellent correlation to SVNT. The persistently high specificity in all groups suggests that this test can be reliably utilized to detect presence of low neutralization capacity, prompting additional vaccination.

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 Earth’s synthetic gravitational and density models can be used to validate numerical procedures applied for a global (or large-scale regional) gravimetric forward and inverse modelling. Since the Earth’s lithospheric structure is better constrained by tomographic surveys than a deep mantle, most of existing 3-D density models describe only a lithospheric density structure, while 1-D density models are typically used to describe a deep mantle density structure below the lithosphere-asthenosphere boundary. The accuracy of currently available lithospheric density models is examined in this study. The error analysis is established to assess the accuracy of modelling the sub-lithospheric mantle geoid, while focusing on the largest errors (according to our estimates) that are attributed to lithospheric thickness and lithospheric mantle density uncertainties. Since a forward modelling of the sub-lithospheric mantle geoid comprises also numerical procedures of adding and subtracting gravitational contributions of similar density structures, the error propagation is derived for actual rather than random errors (that are described by the Gauss’ error propagation law). Possible systematic errors then either lessen or sum up after applying particular corrections to a geoidal geometry that are attributed to individual lithospheric density structures (such as sediments) or density interfaces (such as a Moho density contrast). The analysis indicates that errors in modelling of the sub-lithospheric mantle geoid attributed to lithospheric thickness and lithospheric mantle density uncertainties could reach several hundreds of meters, particularly at locations with the largest lithospheric thickness under cratonic formations. This numerical finding is important for a calibration and further development of synthetic density models of which mass equals the Earth’s total mass (excluding the atmosphere). Consequently, the (long-to-medium wavelength) gravitational field generated by a synthetic density model should closely agree with the Earth’s gravitational field.

Chi-squared automatic interaction detector (CHAID) algorithm is considered to be one of the mostly used supervised learning methods as it is adaptable to solving any kind of problem at hand. We have been starkly aware of CHAID maps non-linear relationships quite well, and it can empower predictive models with stability. But we don’t know how high its accuracy is precisely. To find out the perfect scope CHAID algorithm fits into, this paper presents the analysis of the accuracy of the CHAID algorithm. We introduce the causes, applicable conditions and application scope of CHAID algorithm at first, and then highlight the difference of branching principal between the CHAID algorithm and several other common decision tree algorithms, which is our first step towards basic analysis on CHAID algorithm. We next employee an actual branching case to help us understand CHAID algorithm better. Specifically, we use vehicle customer satisfaction data to compare multiple decision tree algorithms, and cite some factors that affecting the accuracy and some corresponding countermeasures which are more conducive to us to obtain accurate results. The results show that CHAID can analyze the data very well, and detect the significantly correlated factors surely. In this paper, we learn the clear information required to understand CHAID algorithm, thereby make better choices when we need to use decision tree algorithms.

The objective of this work was to investigate the use of remotely sensed vegetation indices to improve the quality of yield maps. The method was applied to the yield data of twelve cornfields from the Data Intensive Farm Management project. The results revealed the need to time shift the yield values up to three seconds to better match the sensor readings with the geographic coordinates. The residuals of the yield prediction model were used to identify points with unlikely yield values for that location, as an alternative to traditional approaches using local spatial statistics, without any assumption of spatial dependence or stationarity. The temporal and spatial distribution of the standardized coefficients for each experimental unit highlighted the presence of trends in the data. At least five out of the twelve fields presented trends that could have been induced by data collection.

The article discusses issues related to the optimization of the operation of medium voltage networks, focusing on the optimization of network division points and the selection of the optimal network configuration aimed at reducing power and energy losses. The article provides a critical review of selected scientific works from recent years on the issue of network configuration optimization. The developed solution uses non-deterministic network models and statistical and probabilistic approaches. Optimization studies were carried out using heuristic optimization methods and proprietary algorithms for forecasting the load and power generated from renewable energy sources. The solution proposed in the article has many application possibilities. It can be used to optimize the location of network division points (reducing economic costs related to the modernization of network infrastructure) as well as to optimize the reconfiguration process in order to reduce power losses while maintaining voltage criteria.

This study proposes a short- and medium-term electricity consumption prediction algorithm by combining the GRU model suitable for long-term forecasting and the Prophet model suitable for seasonality and event handling. (1) Manufacturing Company B's Electricity consumption data and meteorological data in Naju, Jeollanam-do, South Korea are collected and preprocessed. (2) The preprocessed data proposes the Prophet model in the first step for seasonality and event handling prediction. (3) In the second step, seven multivariate data are experimented with GRU. Specifically, the seven multivariate data consist of six meteorological data and the residuals between the predicted data from the proposed Prophet model in Step 1 and the observed data. These are utilized to predict electricity consumption at 15-minute intervals. (4) Electricity consumption is predicted for short-term (2 days and 7 days) and medium-term (15 days and 30 days) scenarios. The experimental results demonstrate that the proposed method outperforms the conventional Prophet model by more than 23 times and the modified GRU model by more than 2 times in terms of MAPE.

In this short communication, a concept has been presented to model geographical data to predict future temperature of Tabuk, region. Machine learning has been applied to the weather station data to develop a prediction model. The preliminary results are promising and encouraging and are envisaging to further this research towards the determination of unknown temperature rise in the region. This is important to mention here, that the problem has been formulated as a Regression problem, NOT as a classification problem. Hence, applying Convolutional neural networks is not possible, due to the non-existence of classes or converting the temperature values to classes does not make any sense. Hence, this is defined as a regression problem which achieved encouraging desirable results.

The proton exchange membrane fuel cell (PEMFC) is a critical and essential component of zero-emission electro-hydrogen generators. An accurate prediction of its performance is important for optimal operation management and preventive maintenance of these generators. However, the prediction is not simple because the PEMFCs have complex electrochemical reactions with multiple nonlinear relations between operating variables as inputs and voltage as output. In this paper, we propose an efficient prediction approach based on XGBRegressor and Tree-structured Parzen Estimator. In addition, to better select relevant features, Kernel Principal Component Analysis and Mutual Information are jointly used. The proposed approach allows consideration of the dynamic operating conditions of the PEMFC. To test and validate the robustness of the proposed approach, a real data-set of ten PEMFCs was considered. Furthermore, a comparison study with traditional machine learning models, such as artificial neural networks and support vector machine regression, was investigated. The obtained results confirm that our model outperforms the considered traditionel machine learning models.

We investigate the power of time series analysis based on a variety of information-theoretic approaches from statistics (AIC, BIC) and machine learning (Minimum Message Length) - and we then compare their efficacy with traditional time series model and with hybrids involving deep learning. More specifically, we develop AIC, BIC and Minimum Message Length (MML) ARMA (autoregressive moving average) time series models - with this Bayesian information-theoretic MML ARMA modelling already being new work. We then study deep learning based algorithms in time series forecasting, using Long Short Term Memory (LSTM), and we then combine this with the ARMA modelling to produce a hybrid ARMA-LSTM prediction. Part of the purpose of the use of LSTM is to seek capture any hidden information in the residuals left from the traditional ARMA model. We show that MML not only outperforms earlier statistical approaches to ARMA modelling, but we further show that the hybrid MML ARMA-LSTM models outperform both ARMA models and LSTM models.

Currently, electromagnetic and radar methods are the most common non-destructive tests for non-destructive rebar location in structures.. Both methods have some advantages, disadvantages and limitations. This article is an attempt to describe possibilities of particular methods with emphasizing their advantages and limitations. The first stage of tests included results from tests conducted on a lintel beam made of autoclaved aerated concrete (AAC) and reinforced with small-diameter rebars and rebars placed close to each other. The second stage consisted in testing nine lightweight concrete specimens, each with three bars having a diameter of 10, 16 and 20 mm at three different space arrangements, to determine the effect of bar diameter and spacing on the measurement accuracy. The reinforcement of lintels and specimens was tested with two different electromagnetic scanners and a ground-penetrating radar (GPR) device. Received results from direct tests were compared with results from non-destructive tests (NDT). NDT tests conducted in such an element were found to perform the correct assessment of the concrete cover, and at the same time to give ambiguous results with reference to shape and number of rebars.

The aim of this technical note is to describe the Cycle 46 reference configuration of the HARMONIE-AROME convection-permitting numerical weather prediction (NWP) model. HARMONIE-AROME is a configuration of the shared ALADIN-HIRLAM system, which is developed, maintained, and validated in the ACCORD consortium, a collaboration of 26 countries in Europe and northern Africa on short-range mesoscale NWP. This technical note describes updates to the physical parametrizations, both upper-air and surface, configuration choices such as lateral boundary conditions, model levels, horizontal resolution, model time step and databases associated with the model, such as for physiography and aerosols. An outlook on upcoming developments is also included.

Building electric energy is characterized by a significant increase of its uses (e.g. vehicle charging), a rapidly declining cost of all related data collection and a proliferation of smart grid concepts, including diverse and flexible electricity pricing schemes. Not surprisingly, an increased number of approaches have been proposed for its modeling and forecasting. In this work, we place our emphasis on three forecasting related issues. First, on the forecasting explainability, i.e. the ability to understand and explain to the user what shapes the forecast. To this extent we rely on concepts and approaches that are inherently explainable, such as the evolutionary approach of genetic programming (GP) and its associated symbolic expressions, as well as the so-called SHAP (SHapley Additive eXplanations) values, which is a well established model agnostic approach for explainability, especially in terms of feature importance. Second, we investigate the impact of the training timeframe on the forecasting accuracy; this is driven by the realization that a fast training would allow for faster deployment of forecasting in real life solutions. And third, we explore the concept of counterfactual analysis on actionable features, i.e. features that the user can really act upon and which therefore present an inherent advantage when it comes to decision support. We have found that SHAP values can provide important insights into the model explainability. As for GP models, we have found comparable and in some cases superior accuracy when compared to its neural-network and time-series counterparts but a rather questionable potential to produce crisp and insightful symbolic expressions, allowing a better insight into the model performance. We have also found, and report here on an important potential especially for practical, decision support, solutions of counterfactuals built on actionable features and short training timeframes.

Weather forecast has a big impact on the global economy, accurate and timely weather forecast is required by all, it affects many aspects of human livelihood and lifestyle, it also plays a critical role in decision making for severe weather management and for primary and secondary sectors like agriculture, transportation, tourism, and industry as they rely on good weather conditions for production and operations. The erratic and uncertain complex nature of the weather makes traditional weather forecasting tedious and a challenging task, traditional weather forecast involves applying technology and scientific knowledge on numerical weather prediction (NWP), and weather radar to solve complex mathematical equations to obtain forecasts based on current weather conditions. These traditional processes utilize expensive, complex physical and computational power to produce forecasts, which can be inaccurate and have various catastrophic impacts on society. In this research, a machine learning-based weather forecasting model was proposed, the model was implemented using 4 classifier algorithms which include Random Forest classifier, Decision Tree Algorithm, Gaussian Naïve Bayes model, and Gradient Boosting Classifier, these algorithms were trained using a publicly available dataset from Kaggle for the city of Seattle for the period 2012 to 2015. The model’s performance was evaluated; the Gaussian Naive Bayes algorithm proved to be the best performing algorithm with a predictive accuracy of 84.153 %.

Electricity demand forecasting has been a real challenge for power system scheduling in the different levels of the energy sectors. Various computational intelligence techniques and methodologies have been employed in the electricity market for load forecasting; although, scant evidence is available about the feasibility of each of these methods considering the type of data and other potential factors. This work introduces several scientific, technical rationale behind intelligent forecasting methods, based on the work of previous researchers in the field of energy. The fundamental benefits and main drawbacks of the aforementioned methods are discussed in order to depict the efficiency of each approach in various situations. In the end, a proposed hybrid strategy is represented.

Electricity demand forecasting has been a real challenge for power system scheduling in the different levels of the energy sectors. Various computational intelligence techniques and methodologies have been employed in the electricity market for load forecasting; although, scant evidence is available about the feasibility of each of these methods considering the type of data and other potential factors. This work introduces several scientific, technical rationale behind intelligent forecasting methods, based on the work of previous researchers in the field of energy. The fundamental benefits and main drawbacks of the aforementioned methods are discussed in order to depict the efficiency of each approach in various situations. In the end, a proposed hybrid strategy is represented.

Accurate electricity price forecasting has become a substantial requirement since the liberalization of the electricity markets. Due to the challenging nature of the electricity prices, which includes high volatility, sharp price spikes and seasonality, various types of electricity price forecasting models still compete and can not outperform each other consistently. Neural Networks have been successfully used in machine learning problems and Recurrent Neural Networks (RNNs) have been proposed to address time-dependent learning problems. In particular, Long Short Term Memory and Gated Recurrent Units (GRU) are tailor-made for time series price estimation. In this paper, we propose to use Gated Recurrent Units as a new technique for electricity price forecasting. We have trained a variety of algorithms with rolling 3-year window and compared the results with the RNNs. In our experiments, 3-layered GRUs outperformed all other neural network structures and state of the art statistical techniques in a statistically significant manner in the Turkish day-ahead market.

The deep energy method (DEM), a type of physics-informed neural network, is evolving as an alternative to finite element analysis. This method employs the principle of minimum potential energy to predict deformations under static loading conditions. However, the model’s accuracy is contingent upon choosing the appropriate architecture for the model, which can be challenging due to the high interactions between hyperparameters, large search space, difficulty in identifying objective functions, and non-convex relationships with the objective functions. To improve DEM’s accuracy, we first introduce random Fourier feature (RFF) mapping. RFF mapping helps with the training of the model by reducing bias towards high frequencies. The effects of six hyperparameters are then studied under compression, tension, and bending loads in planar linear elasticity. Based on this study, a systematic automated hyperparameter optimization approach is proposed. Due to the high interaction between hyperparameters and the non-convex nature of the optimization problem, Bayesian optimization algorithms are used. The models trained using optimized hyperparameters and having Fourier feature mapping can accurately predict deflections compared to finite element analysis. Additionally, the deflections obtained for tension and compression load cases are more sensitive to variations in hyperparameters than bending.

A method of accuracy error compensation for the time interval is examined, allowing to eliminate the dependence of accuracy error on the duration of measured intervals and minimising the influence of destabilising factors - ambient temperature changes and the initial deviation of the meter clock generator frequency from the nominal value. The compensation method is based on a calibration procedure that measures precise time intervals under conditions of changing ambient temperature. Then the dependence of the accuracy error on temperature for a particular meter is recorded. Based on these data, a correction table is compiled containing correction factors and temperature values at which these factors were determined. Under real measurement conditions, the correction factor corresponding to the current temperature is determined from the table for measured results correction. The table with correction factor values could be stored in the memory of the meter or processing computer. Experimental verification of the method showed that applying a correction for a meter with a standard XO class clock generator (certificated instability of ±50 ppm) can obtain an equivalent clock generator instability of ±0.15 ppm. The application of the method is efficient in cases where the use of high-end clocking to ensure the required measurement accuracy is not economically feasible.

Determination of indoor location based on fine time measurement (FTM) of the round trip time (RTT) of a signal between an initiator (smartphone) and a responder (Wi-Fi access point) enables a number of applications. However, the accuracy currently attainable — standard deviations of 1–2 meter in distance measurement under favorable circumstances — limits the range of possible application. A first responder, for example, may not be able to unequivocally determine on which floor someone in need of help is in a multi-story building. The error in location depends on several factors, including the bandwidth of the RF signal, delay of the signal due to the high relative permittivity of construction materials, and the geometry-dependent “noise gain” of location determination. Errors in distance measurements have unusual properties that are exposed here for the first time. Improvements in accuracy depend on understanding all of these error sources. This paper introduces “frequency diversity,” a method for doubling the accuracy of indoor location determination using weighted averages of measurements with uncorrelated errors obtained in different channels. The properties of this method are verified experimentally with a range of responders. Finally, different ways of using the distance measurements to determine indoor location are discussed and the Bayesian grid update method shown to be more useful than others, given the non- Gaussian nature of the measurement errors.

In this study, we have first studied the trend in meteorological data from the Harmaleh, Vanai and Farsesh stations in the 50-year period in the Dez catchment area. The meteorological data will be then forecasted using SWAT and Mann-Kendall. Forecasting the results in the Mann-Kendall and SWAT model has been done using the code written in MATLAB software and RCP (4.5, 8.5) scenarios, respectively. Studying the results of the trend in the data of meteorological stations in this catchment area indicated that these two parametric and non-parametric methods have been used to determine trends in meteorological data. The results of the parametric method are positive in all meteorological parameters. Non-parametric method over a period of 50 years shows the presence of trends in the data. The comparison on the forecasting results at maximum temperature suggested that during summer, we will see an increase in temperature compared to the ground state in all three forecasts. The results of the minimum temperature forecast show a decrease in the minimum increase during the winter and the precipitation forecast indicates that at the end of autumn (Nov) precipitation decreased by 20 mm in the Mann-Kendall and 4.5 RCP while RCP8.5 suggests the increase in precipitation compared to the ground state. Studying the runoff forecast results using SWOT show that at the end of winter (Feb) and almost all spring (Mar, Apr) a decrease of about 40%, 15% and 14% will be seen, respectively

Background: Strength assessment is one of the main fields in sports performance, physical rehabilitation, physical activity and health. Purpose: To compare maximal voluntary isometric contractions (MVIC) and paired voluntary isometric contractions (VIC) of knee extensors between an isokinetic dynamometer (BIODEX) and a portable and lightweight device (DINABANG). Methods: From 19 volunteers (age: 28.7±7 y; body mass: 72±10 kg and height: 173±7 cm) we obtained 114 paired MVIC measures and, from the force-time curves of these repetitions, 22507 paired VIC measures of knee extensors. Results: We observed “excellent” repeatability for MVIC (ICC:1.00; p&lt;0.001) between BIODEX (247±79.5 Nm) and DINABANG (247±74.8 Nm), with “trivial” effect (mean difference: 0.12 Nm (0.02%); 95%CI: -0.13 to 0.23 Nm; p=0.606; d=0.048). Bland-Altman plots revealed high accuracy for MVIC (bias: 0.12 Nm) and consistent distribution (precision) inside the limits of agreement (-4.81 to 5.06 Nm) and respective 95%CI. “Excellent” repeatability was also observed for VIC (ICC:1.00; p&lt;0.001) between BIODEX (219±84.1 Nm) and DINABANG (218±84.0 Nm), with “trivial” effect (0.24 Nm (0.11%); 0.08 to 0.11 Nm; p&lt;0.001; d=0.100). Bland-Altman plots revealed high accuracy for VIC (bias: 0.24 Nm) and consistent distribution (precision) inside the limits of agreement (-4.5 to 4.9 Nm) and respective 95%CI. Conclusion: DINABANG is accurate, precise and reliable for torque measurement.

The objective of this research is to evaluate four distinct models for multi-population mortality projection in order to ascertain the most effective approach for forecasting the impact of COVID-19 pandemic on mortality. Utilising data from the Human Mortality Database for five countries Finland, Germany, Italy, the Netherlands, and the United States, the study identifies the generalized additive model (GAM) within the age-period-cohort (APC) analytical framework as the most promising for precise mortality forecasts. Consequently, this model serves as the basis for projecting the impact of the COVID-19 pandemic on future mortality rates. By examining various pandemic scenarios, ranging from mild to severe, the study concludes that projections assuming a diminishing impact of the pandemic over time are most consistent, especially for middle-aged and elderly populations. Projections derived from the superior GAM-APC model offer guidance for strategic planning and decision-making within sectors facing the challenges posed by extreme historical mortality events and the uncertain future mortality trajectories.

This work focuses on short-term forecasting of PV output power. The multilayer perception (MLP), convolutional neural networks (CNN), and k-nearest neighbour (kNN) neural networks have been used singly or in a hybrid (with other algorithms) to forecast solar PV power or global solar irradiance with good success. Their performances in forecasting PV power have been compared with other algorithms but not with themselves. The study aims to compare performance of a number of neural network algorithms in solar PV energy yield forecasting under different weather conditions. The performance of MLPNN, CNN and kNN are being compared using solar PV (hourly) energy yield data for Grahamstown, Eastern Cape, South Africa. The choice of location is part of the study parameters to provide insight into renewable energy power integration in specific areas in south Africa that may be prone to extreme weather conditions. The kNN algorithm was found to have RMSE value of 4.95% and MAE value of 2.74% at its worst performance, and RMSE value of 1.49% and MAE value of 0.85% at its best performance. It outperformed the others by a good margin and kNN could serve as a fast, easy, and accurate tool to forecast solar PV output power.

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.

Modern countries generally deal with significant budget deficits and public debt. These countries need to rationalize their expenditures and increase revenue without major interference to economic flows. The aim of this paper is to create a model for forecasting public revenue and expenditure based on data from previous years. In the paper we formulated two hypotheses related to the validity of the set models. After detailed analysis, both hypotheses were accepted. The analysis includes all EU Member States and public revenue and expenditure data for the last decade. The significance of the analysis is reflected on the practical foundation of the pre-set theoretical views, which will have their basis in statistically significant results. By analyzing the model, we formulated the regression formulas of revenues and expenditures, which can be efficiently used in predicting these variables.

Retailers must have accurate sales forecasts to operate their businesses efficiently and effectively and to remain competitive in the marketplace. Global forecasting models like RNNs can be a powerful tool for forecasting in retail settings, where multiple time series are often interrelated and influenced by a variety of external factors. By including covariates in a forecasting model, we can better capture the various factors that can influence sales in a retail setting. This can help improve the accuracy of our forecasts and enable better decision-making for inventory management, purchasing, and other operational decisions. In this study we investigate how the accuracy of global forecasting models is affected by the inclusion of different potential demand covariates. To ensure the significance of the study's findings, we used the M5 forecasting competition's openly accessible and well-established dataset. The results obtained from the DeepAR models, which were trained on various combinations of features including time, price, events, and IDs, suggest that individually only the features corresponding to IDs improve the baseline model. However, when all the features are used together, the best performance is achieved, indicating that the individual relevance of each feature is emphasized when the information is given jointly. Comparing the model with features to the model without features, there is an improvement of 1.76\% for MRMSSE and 6.47\% for MMASE.

This paper applies a new artificial intelligence architecture, the Temporal Fusion Transformer (TFT), for the joint GDP forecasting of 25 OECD countries at different time horizons. This new attention-based architecture offers significant advantages over other deep learning methods. First, results are interpretable since the impact of each explanatory variable on each forecast can be calculated. Second, it allows to visualize persistent temporal patterns and to identify significant events and different regimes. Third, it provides quantile regressions and permits to train the model on multiple time series from different distributions. Results suggest that TFTs outperform regression models, especially in periods of turbulence such as the COVID-19 shock. Interesting economic interpretations are obtained depending on whether the country is domestic demand-led or export-led growth. In essence, TFT is revealed as a new tool that artificial intelligence provides to economists and policy makers, with enormous prospects for the future.

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.

Canine distemper virus (CDV) poses a substantial threat to diverse carnivores, leading to sys-temic and often fatal diseases. Accurate and prompt diagnosis is paramount for effective man-agement and curbing further transmission. This study evaluates the diagnostic efficacy of drop-let digital PCR (ddPCR) in comparison to conventional reverse transcription (RT-PCR) and quantitative reverse transcription real-time PCR (RT-qPCR). Seventy-six clinical samples were collected from dogs with CDV symptoms diagnosed by specialized veterinarians, and sixteen samples from asymptomatic individuals. Conventional PCR, quantitative real-time PCR, and ddPCR were deployed, and their diagnostic capabilities were meticulously assessed. DdPCR ex-hibited heightened analytical sensitivity, reaching a detection limit of 3 copies/μL, whereas RT-qPCR had a detection limit of 86 copies/μL. The comparative analysis between clinical diagnosis and molecular techniques, including RT-PCR and RT-qPCR, demonstrated low concordance, with Kappa coefficients of 0.268 and 0.324, respectively. In contrast, ddPCR, showed a moderate concordance, with a Kappa coefficient of 0.477. Sensitivity was 42.39% for RT-PCR, 57.89% for RT-qPCR and 72.37% for ddPCR, with 100% of specificity for all methods. This study under-scores ddPCR's superior sensitivity and concordance with clinical CDV diagnosis, even at low viral concentrations, suggesting it as a promising alternative for CDV diagnosis.

Aiming at the problem of small size of some spots on apple leaves and the difficulty of accurate detection of spot targets brought by the complex background of the orchard, this paper takes the alternaria leaf spot, rust, brown spot, grey spot and frog eye leaf spot on apple leaves as the research object, and proposes a high-accuracy detection model YOLOv5-Res and lightweight detection model YOLOv5-Res4 are proposed. Firstly, a multiscale feature extraction module ResBlock is designed by combining the Inception multi-branch structure and ResNet residual idea. Secondly, a lightweight feature fusion module C4 is designed to reduce the number of model parameters while improving the detection ability of small targets. Finally, a parameter streamlining strategy based on optimized model architecture is proposed. The experimental results show that the performance of YOLOv5-Res model and YOLOv5-Res4 model is significantly improved, the [email protected] value is improved by 2.8% and 2.2% compared with YOLOv5s model and YOLOv5n model, respectively, and the size of YOLOv5-Res model and YOLOv5-Res4 model is only 10.8MB and 2.4MB, and the number of model parameters is reduced compared with YOLOv5s model and YOLOv5n model. counts are reduced by 22% and 38.3% compared to the YOLOv5s model and YOLOv5n model.