Abstract Background: Numerous studies have demonstrated that the amalgamation of populations belonging to the same breed or closely related breeds leads to enhanced accuracies in genomic predictions (GP). Extensive experimentation with diverse Bayesian and Genome-enabled best linear unbiased prediction (GBLUP) models has been conducted to explore multi-breed genomic selection (GS) in livestock, ultimately establishing they as successful approaches for predicting genomic estimated breeding value (GEBV). This study aimed to examine the efficacy of BayesR and GBLUP model with different weighted genomic relationship matrices (GRM) in making genomic predictions for three distinct beef cattle breeds. Subsequently, we conducted a comparative analysis of the predictive accuracy pertaining to various marker densities and genetic correlations across three distinct beef cattle breeds. This investigation aimed to identify the optimal approach for enhancing the predictive accuracy of multi-breed genomic selection in beef cattle. Results：Genetic relationship matrices revealed moderate similarities between YL and the other breeds, with a striking genetic similarity of 0.87 between WG and HX. In HX cattle, BayesR demonstrated an enhancement in prediction accuracy, achieving 0.52 with HD and 0.46 with WGS, a marked improvement over 0.41 with HD and 0.42 with WGS in GBLUP. In WG and YL breeds, both methods showed comparable accuracies with HD, but BayesR slightly outperformed GBLUP with WGS. Further, multi-breed GS analysis indicated that BayesR consistently surpassed GBLUP in prediction accuracy, particularly with WGS data. For instance, in a combined HX and WG reference population, BayesR achieved a superior accuracy of 0.53 with WGS in HX cattle, a significant enhancement over GBLUP models. The study also underscores the advantage of incorporating multiple breeds in the reference population, which improved prediction accuracy, underscoring the value of broad-based genomic selection strategies. Conclusion: The results show that accuracy of multi-breed genomic predictions was higher with BayesR than with GBLUP, especially for the distantly genetic relationship between reference and validation breeds. Further improvements of multi-breed accuracy of genomic predictions could be achieved by increasing the density of the SNP marker. These findings underscore that BayesR providing a substantial improvement in genomic prediction and the importance of considering genetic relationships in the development of GS strategies for multi-breed cattle populations. Further research is warranted to optimize GRM construction and to explore alternative models for genomic prediction across breeds.

Technological innovations and the expansion of Internet access have produced significant changes in the configurations of organizations and, consequently, in the relationships between employees and employers. This new scenario generates the need for greater monitoring in the workplace in order to control inappropriate behavior or situations that may generate misfortunes. Two important problems faced are the dissemination of hate through networks and data leakage that can have social, psychological, and financial impacts. Thus, monitoring tools can be incorporated to assist in surveillance, and thus ensure the achievement of organizational objectives. This paper presents a workplace computer monitoring solution that integrates Spyware techniques, and text sentiment classification, along with a distributed microservices architecture, which aims to collect a range of information and generate alerts to managers regarding hate speech and vulnerabilities. Preliminary tests have been conducted to evaluate the performance of Spyware integrated with prediction models.

This research deals with risk assessment for human life, man-made infrastructure, and agriculture in a landslide-prone area using GIS-based spatial methods. The study area landslide inventory map was prepared based on previous landslide information, aerial photograph analysis, and several field observations. A total of 550 landslides have been included with 182 debris flow and 368 soil slides. All included landslides were classified into two groups by random selection; half were used for model calibration and the rest were used for cross-validation. In the analysis, fourteen causative factors were vastly used, such as aspect, slope, curvature, elevation, topographic wetness index, forest timber diameter, forest type, forest crown density, forest age, land-use, geology, soil drainage, soil depth, and soil texture. Moreover, to identify the interaction between occurred landslides and causative factors, the affected pixels were divided into different sub-classes using a frequency ratio method. Based on the total dataset, three landslide susceptibility maps were constructed using Bayesian prediction, likelihood ratio, and fuzzy set method. By evaluating cross-validation and success rate curve, model susceptibility results were plotted with a receiver operating characteristic (ROC) curve and the area under the curve (AUC) was estimated. In addition, for risk assessment, each social data layer such as agriculture, house, industry, business, road, river, population intensity, monetary value, and vulnerability level was added based on the local standard and incident time and was converted into US dollars. During the analysis, each method hazard map was used with a specific group of thematic data layers. Subsequently, for preparing the probability table, study area total pixels and predictive landslide affected pixels were considered. Matching with the affected pixels, a standard of 5000 pixels was selected to run the final evaluation. Based on the results, the agricultural field showed the highest vulnerability and estimated risk of US $ 16.3 million. Further, the man-made infrastructure map showed a risk of US $ 31.3 million. The total estimated population casualties were 6.77, which was relatively similar to the published data.

Arctic sea ice prediction holds significant importance for facilitating Arctic route planning, optimizing fisheries management, and advancing the field of sea ice dynamics research. While various deep learning models have been developed for sea ice prediction, they predominantly operate at the seasonal or sub-seasonal scale, often focusing on localized areas, and few cater to full-region daily scale prediction. This study introduces the use of spatiotemporal sequence data prediction models, namely, the convolutional LSTM (ConvLSTM) and predictive recurrent neural network (PredRNN), for the prediction of sea ice concentration (SIC). Our analysis reveals that, when solely utilizing SIC historical data as the input, the ConvLSTM model outperforms the PredRNN model in SIC prediction. To enhance the model's capacity to capture spatiotemporal relationships between multiple variables, we expanded the range of input data types to form the ConvLSTM-multi and PredRNN-multi models. Experimental findings demonstrate that the ConvLSTM-multi model excels in assimilating the influence of reanalysis data on sea ice within the sea ice edge region, thus exhibiting superior performance in predicting daily Arctic SIC over the subsequent 10 days. Furthermore, sensitivity tests on various model parameters highlight the substantial impact of sea surface temperature and prediction date on the accuracy of daily sea ice prediction. Additionally, meteorological and oceanographic parameters primarily affect the prediction accuracy of the thin ice region at the edge of the sea ice.

Living organisms are active open systems far from thermodynamic equilibrium. The ability to behave actively corresponds to dynamical metastability: minor but supercritical internal or external effects may trigger major substantial actions such as gross mechanical motion, dissipating internally accumulated energy reserves. Gaining selective advantage from beneficial use of activity requires a consistent combination of sensual perception, memorised experience, statistical or causal prediction models, and resulting favourable decisions on actions. This information processing chain originated from mere physical interaction processes prior to life, here denoted as structural information exchange. From there, the self-organised transition to symbolic information processing marks the beginning of life, evolving by novel purposivity of trial-and-error feedback and accumulation of symbolic information. The emergence of symbols and prediction models can be described as a ritualisation transition, a symmetry-breaking kinetic phase transition of the 2^nd kind previously known from behavioural biology. The related new symmetry is the neutrally stable arbitrariness, conventionality or code invariance of symbols with respect to their meaning. The meaning of such symbols is given by the structural effect they ultimately unleash, directly or indirectly, by deciding on which actions to take. The early genetic code represents the first symbols. The genetically inherited symbolic information is the first prediction model for activities sufficient for survival under the condition of environmental continuity, sometimes understood as a “final causality” property of the model.

For disciplines like biological science, security, and the medical field, link prediction is a popular research area. To demonstrate the link prediction many methods have been proposed. Some of them that have been demonstrated through this review paper are TransE, Complex, DistMult, and DensE models. Each model defines link prediction with different perceptions. We argue that the practical performance potential of these methods, having similar parameter values, using the fine-tuning technique to evaluate their reliability and reproducibility of results. We describe those methods and experiments; provide theoretical proofs and experimental examples, demonstrating how current link prediction methods work in such settings. We use the standard evaluation metrics for testing the model's ability.

One of the most important sources of energy is the sun. Taiwan is located at north 22-25° latitude. Due to its proximity to the equator, it experiences only a small angle of sunlight incidence. Its unique geographical location which can obtain sustainable and stable solar resources. This study takes research on the forecast of solar radiation to maximize the benefits of solar power generation, and develops methods that can predict the future solar radiation pattern to help reduce the costs of solar power generation. This study builds supervised machine learning models, known as deep neural network (DNN) and long short-term memory neural network (LSTM). The hybrid supervised and unsupervised model, namely cluster-based artificial neural network (k-means clustering and fuzzy C-means clustering-based models), was developed. After establishing these models, the study evaluated their prediction results. For different prediction periods, the study selected the best-performing model based on the results and proposed combining them to establish a real-time updated solar radiation forecast system capable of predicting the next 12 hours. The study area covered Kaohsiung, Hualien, and Penghu in Taiwan. Data from ground stations of the Central Weather Administration, collected between 1993 and 2021, as well as the solar angle parameters of each station, were used as input data for the model. The results of this study show that different models have their advantages and disadvantages in predicting different future times. Therefore, the hybrid prediction system can predict future solar radiation more accurately than a single model.

A combination of physical-chemical analysis has been used to monitor the aging of red wines from D.O. Toro (Spain). The changes in the chemical composition of wines that occur along aging time can be permitted to discriminate wine samples collected after one, four, seven and ten months of aging. Different computational models were used to develop a good authenticity tool to certificate wines. In this research different models have developed: Artificial Neural Network models (ANNs), Support Vector Machine (SVM) and Random Forest (RF) models. The results obtained for the ANN model developed with sigmoidal function in the output neuron and the RF model permit to determine the aging time, with an average absolute percentage deviation below 1% and it can conclude that these two models have demonstrated its capacity as a valid tool to predict the wine age.

In the context of artificial intelligence's pervasive integration across sectors, the rigorous examination of methodologies used in constructing mathematical models is imperative. This study delves into facial recognition models, particularly in their ability to extract features such as age. We address the prevalent practice of training models with unbalanced datasets and its implications for model performance and bias introduction. Utilizing 27,305 facial images, we investigate the influence of dataset imbalance on age prediction based on ethnicity. Employing preprocessing and oversampling techniques, we equalize sample sizes across ethnicities. A Convolutional Neural Network trained on the balanced dataset serves as our baseline, while three additional models undergo training with a 50% sample size reduction for each group to assess accuracy degradation. Our findings reveal a notable decline in accuracy for ethnic groups with reduced representation. The Asian group experiences a 67.94% accuracy deterioration, followed by a 51.60% drop for the Black group, and a 38.46% decline for the White group. These results underscore the sensitivity of certain ethnic groups to underrepresentation, highlighting the nuanced impact on age prediction accuracy. While a 50% reduction in representation does not uniformly result in a 50% accuracy decline, it unquestionably influences predictive accuracy for affected groups.

Background: Novel technologies like continuous glucose monitor (CGM) systems are improving diabetes management by means of real-time sensor glucose levels, retrospective course of glucose and trend arrows. Continuous Glucose Monitoring (CGM) offers real-time alerts for (prognostic) hypo- and hyperglycemia, fast dropping or increasing glucose, and hence improving glycaemia under unstable conditions like during meals, physical activity and exercise management. Complex CGM systems challenge people with diabetes and health care professionals in interpreting rapid changes, sensor delay (~10-minute difference between interstitial and plasma glucose), and malfunctions. Enhanced prediction models are necessary for optimal insulin dosing, daily activities, and especially for future fully closed-loop systems. Methods: The aim of this study was to investigate the efficacy of three different predictive models for glucose responses: 1) an autoregressive integrated moving average model (ARIMA), 2) logistic regression, 3)and long short-term memory networks (LSTM), in predicting glucose levels after 15 minutes and one hour. We compared and evaluated the performance of these models in predicting hypoglycemia (<70 mg/dL), euglycemia (70-180 mg/dL), and hyperglycemia (>180 mg/dL). In more detail, by assessing metrics such as precision, recall, F1-score, and accuracy, we specifically assessed which model provided the most accurate and reliable predictions for glucose levels Results: As expected, ARIMA showed the worst accuracy especially predicting hypoglycaemia withing 1-hour (7.3%). The accuracy of the logistic regression model, predicting hypoglycemia during the first 15 min was higher (98%), comparing to LSTM (88%). However, the LSTM model (87%) exceeded the accuracy of hypoglycemia prediction of the logistic regression (83%) during an hour prognosis. The same pattern observed in hyperglycemia - ARIMA model (60%, 1 hour), logistic regression (96%, 15 minutes) and LSTM (85%, 1 hour) Conclusions: These findings suggest that different models may have varying strengths and weaknesses in predicting glucose levels, and the choice of model should be carefully considered based on the specific requirements and context of the clinical application. The logistic regression model was more accurate for the next 15 minutes, especially predicting hypoglycemia. However, the LSTM model exceeded logistic regression for the next one hour prediction. Future research could explore hybrid models or ensemble approaches that combine the strengths of multiple models to further improve the accuracy and reliability of glucose predictions.

MicroRNAs (miRNAs) are small non-coding RNAs that play a central role in the post-transcriptional regulation of biological processes. miRNAs regulate transcripts by direct binding involving the Argonaute protein family. The exact rules of binding are not known, and several in silico miRNA target prediction methods have been developed to date. Deep Learning has recently revolutionized miRNA target prediction. However, the higher predictive power comes with decreased ability to interpret increasingly complex models. Here, we present a novel interpretation technique, called attribution sequence alignment, for miRNA target site prediction models that can interpret such Deep Learning models on a two-dimensional representation of miRNA and putative target sequence. Our method produces a human readable visual representation of miRNA:target interactions and can be used as a proxy for further interpretation of biological concepts learned by the neural network. We demonstrate applications of this method in clustering of experimental data into binding classes, as well as using the method to narrow down predicted miRNA binding sites on long transcript sequences. Importantly, the presented method works with any neural network model trained on a two-dimensional representation of interactions and can be easily extended to further domains such as protein-protein interactions.

The models used to estimate disease transmission, susceptibility and severity determine what epidemiology can (and cannot tell) us about COVID-19. These include: ‘model organisms’ chosen for their phylogenetic/aetiological similarities; multivariable statistical models to estimate the strength/direction of (potentially causal) relationships between variables (through ‘causal inference’), and the (past/future) value of unmeasured variables (through ‘classification/prediction’); and a range of modelling techniques to predict beyond the available data (through ‘extrapolation’), compare different hypothetical scenarios (through ‘simulation’), and estimate key features of dynamic processes (through ‘projection’). Each of these models: address different questions using different techniques; involve assumptions that require careful assessment; and are vulnerable to generic and specific biases that can undermine the validity and interpretation of their findings. It is therefore necessary that the models used: can actually address the questions posed; and have been competently applied. In this regard, it is important to stress that extrapolation, simulation and projection cannot offer accurate predictions of future events when the underlying mechanisms (and the contexts involved) are poorly understood and subject to change. Given the importance of understanding such mechanisms/contexts, and the limited opportunity for experimentation during outbreaks of novel diseases, the use of multivariable statistical models to estimate the strength/direction of potentially causal relationships between two variables (and the biases incurred through their misapplication/misinterpretation) warrant particular attention. Such models must be carefully designed to address: ‘selection-collider bias’, ‘unadjusted confounding bias’ and ‘inferential mediator adjustment bias’ – all of which can introduce effects capable of enhancing, masking or reversing the estimated (true) causal relationship between the two variables examined. Selection-collider bias occurs when these two variables independently cause a third (the ‘collider’), and when this collider determines/reflects the basis for selection in the analysis. It is likely to affect all incompletely representative samples, although its effects will be most pronounced wherever selection is constrained (e.g. analyses focusing on infected/hospitalised individuals). Unadjusted confounding bias disrupts the estimated (true) causal relationship between two variables when: these share one (or more) common cause(s); and when the effects of these causes have not been adjusted for in the analyses (e.g. whenever confounders are unknown/unmeasured). Inferentially similar biases can occur when: one (or more) variable(s) (or ‘mediators’) fall on the causal path between the two variables examined (i.e. when such mediators are caused by one of the variables and are causes of the other); and when these mediators are adjusted for in the analysis. Such adjustment is commonplace when: mediators are mistaken for confounders; prediction models are mistakenly repurposed for causal inference; or mediator adjustment is used to estimate direct and indirect causal relationships (in a mistaken attempt at ‘mediation analysis’). These three biases are central to ongoing and unresolved epistemological tensions within epidemiology. All have substantive implications for our understanding of COVID-19, and the future application of artificial intelligence to ‘data-driven’ modelling of similar phenomena. Nonetheless, competently applied and carefully interpreted, multivariable statistical models may yet provide sufficient insight into mechanisms and contexts to permit more accurate projections of future disease outbreaks.

Hepatitis C presents a significant global health challenge, necessitating early diagnosis and precise severity classification for timely medical intervention. This study explores the application of machine learning techniques to predict the severity of hepatitis C, leveraging an extensive dataset. Our approach encompasses rigorous data preprocessing, advanced model development, and fine-tuned hyperparameter optimization to ensure accurate and reliable predictions. We evaluated four classification models: Logistic Regression, Random Forest, Gradient Boosting, and Support Vector Machine (SVM), comparing their accuracy in classifying patients. The results showed that the Random Forest and Gradient Boosting models outperformed the others with an accuracy of approximately 93.50%, demonstrating their potential in assisting Hepatitis C diagnosis. Further model enhancements through hyperparameter tuning and feature engineering can improve the precision of Hepatitis C diagnosis, contributing to better patient care.

Antimicrobial peptides (AMPs) are considered as promising alternatives to conventional antibiotics in order to overcome the growing problems of antibiotic resistance. Computational prediction approaches receive an increasing interest to identify and design the best candidate AMPs prior to the in-vitro tests. In this study, we focused on the linear cationic peptides with non-hemolytic activity, which are downloaded from the Database of Antimicrobial Activity and Structure of Peptides (DBAASP). Referring to the MIC (Minimum inhibition concentration) values, we have assigned a positive label to a peptide if it shows antimicrobial activity; otherwise the peptide is labeled as negative. Here, we focused on the peptides showing antimicrobial activity against Gram-negative and against Gram-positive bacteria separately, and we created two datasets accordingly. Ten different physico-chemical properties of the peptides are calculated and used as features in our study. Following data exploration and data preprocessing steps, a variety of classification algorithms are used with 100-fold Monte Carlo Cross Validation to build models and to predict the antimicrobial activity of the peptides. Among the generated models, Random Forest has resulted in the best performance metrics for both Gram-negative dataset (Accuracy: 0.98, Recall: 0.99, Specificity: 0.97, Precision: 0.97, AUC: 0.99, F1: 0.98) and Gram-positive dataset (Accuracy: 0.95, Recall: 0.95, Specificity: 0.95, Precision: 0.90, AUC: 0.97, F1: 0.92) after outlier elimination is applied. This prediction approach might be useful to evaluate the antibacterial potential of a candidate peptide sequence before moving to the experimental studies.

The Dst index is the geomagnetic storm index used to measure the energy level of geomagnetic storms, and the prediction of this index is of great significance for the geomagnetic storm study and the solar activity. In contrast to traditional numerical modelling techniques, machine learning, which has emerged in decades ago based on rapidly developing computer hardware and software and artificial intelligence methods, has been unprecedentedly developed in geophysics, especially solar-terrestrial space physics. This study chooses two machine learning models, the LSTM (Long-Short Time Memory, LSTM) and EMD-LSTM model (Empirical Mode Decomposition, EMD), to model and predict the Dst index. By building the Dst index data series from 2018-2023, two models were built to fit and predict the data. Firstly, we evaluated the influences of the learning rate and the amount of training data on the prediction accuracy of the LSTM model, and finally, 10-3 was thought as the optimal learning rate; secondly, the two models were used to predict the Dst index in the solar active and quiet periods, respectively, and the RMSE (Root Mean Square Error) of the LSTM model in the active period is 7.34 nT, the CC (correlation coefficient) is 0.96, those of the quiet period are 2.64nT and 0.97; the RMSE and r of EMD-LSTM model are 8.87nT and 0.93 in active time and 3.29nT and 0.95 in the quiet time. Finally, the prediction accuracy of the LSTM model in short time period is slightly better than the EMD-LSTM model. However, there will be a problem of prediction lag, which the EMD-LSTM model can then solve, and can better predict the geomagnetic storm.

In cognitive radio systems, identifying spectrum opportunities is fundamental to efficiently use the spectrum. Spectrum occupancy prediction is a convenient way of revealing opportunities based on previous occupancies. Studies have demonstrated that usage of the spectrum has a high correlation over multidimensions which includes time, frequency, and space. Accordingly, recent literature uses tensor-based methods to exploit the multidimensional spectrum correlation. However, these methods share two main drawbacks. First, they are computationally complex. Second, they need to re-train the overall model when no information is received from any base station for any reason. Different than the existing works, this paper proposes a method for dividing the multidimensional correlation exploitation problem into a set of smaller sub-problems. This division is achieved through composite two-dimensional (2D)-long short-term memory (LSTM) models. Extensive experimental results reveal a high detection performance with more robustness and less complexity attained by the proposed method. The real-world measurements provided by one of the leading mobile network operators in Turkey validate these results.

The use of machine learning techniques in predictive health care is on the rise with minimal data used for training machine-learning models to derive high accuracy predictions. In this paper, we propose such a system, which utilizes Heart Rate Variability (HRV) as features for training machine learning models. This paper further benchmarks the usefulness of HRV as features calculated from basic heart-rate data using a window shifting method. The benchmarking has been conducted using different machine-learning classifiers such as artificial neural network, decision tree, k-nearest neighbour and naive bays classifier. Empirical results using MIT-BIH Arrhythmia database shows that the proposed system can be used for highly efficient predictability of abnormality in heartbeat data series.

Different machine learning models (multiple linear regression, vector support machines, artificial neural networks and random forests) are applied to predict the monthly global irradiation (MGI) from different input variables (latitude, longitude and altitude of meteorological station, month, average temperatures, among others) of different areas of Galicia (Spain). The models were trained, validated and queried using data from three stations, and each best machine model was checked in two independent stations. The results obtained confirmed that the best ML methodology is the ANN model which presents the lowest RMSE value in the validation and querying phases 122.6·10kJ/(m2∙day) and 113.6·10kJ/(m2∙day), respectively, and predict conveniently for independent stations, 201.3·10kJ/(m2∙day) and 209.4·10kJ/(m2∙day), respectively. Given the good results obtained, it is convenient to continue with the design of artificial neural networks applied to the analysis of monthly global irradiation.

This paper aims to provide an overall review of degradation, damage evolution and fatigue models in the literature of various engineering materials, mostly metals, and composites.

In the modern world where research is taking a huge leap, the collaboration network between authors is also expanding, increasing the probability of different authors coming together to work on the same project, same research paper making them co-authors. In coauthorship, link prediction is used to anticipate new interactions between its members that are likely to occur in the future. Researchers have concentrated their efforts on studying and suggesting methods for providing effective reviews for authors who can collaborate on a scientific endeavor. In order to provide a precise link prediction, a graph database approach is proposed in this paper using nodes to determine most possible co-authors in future. In order to forecast the connections, we preprocessed the data set for the maximum relative contents. A supervised learning approach is used to execute the solution, which includes random forest classifier and logistic regression. The first findings of our technique reveal that the total of two author node’s research collaboration indices has the greatest influence on the performance of supervised link prediction than that of the traditional approach, which stimulates us to conduct further study on employing such a forecast.

A crucial aspect in developing machine learning algorithms (or any type of predictive models) is the comparison of different algorithmic candidates based on evaluation criteria that measure their accuracy and practical value in terms of successfully capturing the complexity of the underlying problem and generalizing in a wide range of real-world scenarios. In the domain of diabetes mellitus machine learning techniques are widely employed in the prediction of future values of glucose concentration in the blood in order to assist the patient in avoiding deviations from the normo-glycemic value range and the consequences of hyper- and hypoglycemia. In the relative literature there is an apparent lack of a uniformly adopted evaluation metric which could combine the clarity and direct comparative nature of statistical mathematical formulas dealing with prediction error residuals (e.g., the RMSE) with the clinical insights and the visual-qualitative approach of clinical evaluation tools (e.g., Clarke's EGA). Mean Adjusted Exponent (MADEX) error metric, proposed in this paper, attempts to address this need by providing a validation tool based on an easy to implement mathematical formula, that incorporates adjustable parameters of clinical significance.

The Cancer Genome Atlas (TCGA) has classified papillary thyroid carcinoma (PTC) into indolent RAS-like and aggressive BRAF-like based on its distinct driver gene mutations. This study aimed to assess clinicopathology and pERK1/2 expression variations between BRAF-like and RAS-like PTCs and establish predictive models for BRAFV600E and RAS-mutated PTCs. A total of 222 PTCs underwent immunohistochemistry staining to assess pERK1/2 expression and Sanger sequencing to analyze the BRAF and RAS genes. Multivariate logistic regression was employed to develop prediction model. Independent predictors for the BRAFV600E mutation include a nuclear score of 3, the absence of capsules, an aggressive histology variant, and pERK1/2 levels exceeding 10% (X2=0.128, P&gt;0.05, AUC=0.734, P&lt;0.001). RAS mutation predictive model includes follicular histology variant and pERK1/2 expression &gt;10% (X2=0.174, P&gt;0.05, AUC=0.8, P&lt;0.001). We proposed using the prediction model concurrently with four potential combination group outcomes. PTC cases included in combination of low BRAFV600E-scoring group and high RAS-scoring group are categorized as RAS-like (adjOR=4.857, P=0.01, 95% CI=1.470-16.049). PTCs included in combination of high BRAFV600E-scoring group and low RAS-scoring group are categorized as BRAF-like PTCs (adjOR=3.091, P=0.001, 95% CI=1.594-5.995). The different prediction models indicate variations in biological behaviour between BRAF-like and RAS-like PTCs, necessitating adjustments in treatment approaches.

Predicting human trajectories poses a significant challenge due to the complex interplay of pedestrian behavior, which is influenced by environmental layout and interpersonal dynamics. This complexity is further compounded by variations in scene density. To address this, we introduce a novel dataset from the Festival of Lights in Lyon 2022, characterized by a wide range of densities (0.2-2.2 ped/m2). Our analysis demonstrates that density-based classification of data can significantly enhance the accuracy of predictive algorithms. We propose an innovative two-stage processing approach, surpassing current state-of-the-art methods in performance. Additionally, we utilize a collision-based error metric to better account for collisions in trajectory predictions. Our findings indicate that the effectiveness of this error metric is density-dependent, offering prediction insights. This study not only advances our understanding of human trajectory prediction in dense environments but also presents a methodological framework for integrating density considerations into predictive modeling, thereby improving algorithmic performance and collision avoidance.

The study of the area model of Pinus tabulaeformis forest provides an important reference for improving the management of Pinus tabulaeformis and revealing the growth law of Pinus tabulaeformis. According to the classification method proposed by Munro, stand growth and harvest prediction models are divided into three categories: full stand model, single wood model and diameter distribution model. Based on the fixed sample data of Shangluo Pinus tabulaeformis, the spatial instead of time method is used to process the data, and the weight coefficient of each model in the combined prediction model is calculated by using the optimal weighting method. The single wood model, the whole forest model and the diameter distribution model are combined by the combined prediction method to integrate the fault area prediction of Pinus tabulaeformis forest. The results show that the combined prediction method is more accurate than the single model (single wood model, whole forest model and diameter distribution model). At the same time, the method can improve the compatibility of the forest break area prediction model, ensure the consistency of the forest break area prediction, and provide a new direction for the research of forest resource monitoring and investigation.

The assessment of concrete structures' durability in chlorine environments is significantly impacted by the uncertainty inherent in existing durability models. It introduce an integrated approach for updating these models, based on detection information of existing structures. This approach narrows the gap between theoretical predictions and observed structural durability. Specifically, we refine the probability model of critical chloride content by analyzing steel bar corrosion sample proportions, using Bayesian theory for greater accuracy. The enhanced model enables more reliable life expectancy prediction, forming a solid foundation for maintaining and strengthening existing structures.This method was demonstrated through a case study of a reinforced concrete industrial building with a service life of 12 years.

Crop yield estimation supported by satellite remote sensing data can provide expeditious and strategic information for farmers’ decision-making. Most recent forecasting methods have indicated a promising pathway based on machine learning algorithms. However, validation performances, demand for big data and their inherent inexplicability have not yet consolidated a substantial differential to replace methods based on simpler and more understandable models. This paper proposes an approach based on simple linear models fitted from vegetation indices (VIs) assessed at regular intervals of time series derived from MODIS satellite images, aiming to forecast cotton yields in representative areas of the Brazilian Cerrado. Data from 281 commercial production plots were taken to train (167 plots) and test (114 plots) linear regression models relating seed cotton yield and nine well-known VIs averaged in 15-days intervals. Among the evaluated VIs, EVI (Enhanced Vegetation Index) and TVI (Triangular Vegetation Index) showed the lowest root mean square errors (RMSE) and the highest determination coefficients. The best periods for in-season yield prediction were from the 90-105 to 135-150 days after sowing (DAS), i.e. phenological phases corresponding to boll development, open boll and fiber maturation, with lowest RMSE of about 750 kg ha-1 and R2=0.70. The best forecasts for early crop stages were provided by models at the peaks (maximum value of the VI time-series) for EVI and TVI, which occurred around 80-90 DAS. The proposed approach makes the yield predictability more inferable along the crop time series just by providing sowing dates, contour maps and its respective VIs.

Despite being considered as natural components of many ecosystems, forest fires pose significant threats to the environment and human health. In order to ensure public safety and effective fire suppression planning, it is necessary to develop reliable prediction models to mitigate forest fire danger. These models should account for specific environmental conditions. The advent of big data in recent years has opened new avenues for improving forest fire predictions. Machine learning techniques, surpassing traditional forecasting methods, have shown significant promise in this area. By applying the Cross-Industry Standard Process for Data Mining (CRISP-DM) methodology to a real-world dataset, this paper explores the application of machine learning approaches to understand forest fire patterns and predict fire danger. We consider six distinct time stages and incorporate feature selection to refine our predictions. It is important to note that forest fire behavior models are not universally effective due to geographical variations in data. Nevertheless, advanced decision-making techniques are vital in forest fire management. Our research presents a systematic exploration of the topic, comparing various machine learning models, thereby providing a comprehensive baseline for future investigations in this crucial environmental arena.

Liver cirrhosis development is a multifactorial process resulting by a combination of environmental and genetic factors. The aim of the study was to develop accurate non-invasive diagnostic and prognostic models for alcoholic cirrhosis. Consecutive subjects with at-risk alcohol intake were retrospectively enrolled (110 cirrhotic patients and 411 non-cirrhotics). At enrollment, the data about the lifetime drinking history were collected and all patients were tested for PNPLA3 rs738409, TM6SF2 rs58542926 and HSD17B13 rs72613567 variants. In cross-sectional analyses, models for the diagnosis of cirrhosis were developed using multivariate logistic regression. A predictive score for cirrhosis development over 24 years was built by evaluating time-dependent AUC curves. The best diagnostic accuracy was demonstrated by the model which also includes daily alcohol consumption, duration of hazardous alcohol use and genetic variants, with AUCs of 0.951 (95% CI 0.925-0.977) and 0.887 (95% CI 0.925-0.977) for cirrhosis and compensated cirrhosis, respectively. The predictive model for cirrhosis future development (AUC of 0.836 95% CI: 0.769 - 0.904) accounted for age at onset of at-risk alcohol consumption and the number of PNPLA3 and HSD17B13 variant alleles. We have developed accurate genetic and alcohol consumption models for the diagnosis of alcoholic cirrhosis and the prediction of its future risk.

Asphalt pavement temperature has several applications, including pavement structural design and evaluation, asphalt mixture design, asphalt binder grade determination and material aging characterization. However, available asphalt pavement temperature prediction models were mostly developed for temperate climatic conditions, outside of the tropics. Before such models are adopted for use in a tropical climate, their applicability must be evaluated. This study evaluated five empirical asphalt pavement temperature prediction models developed by Lukanen et al. [1], Park et al. [2], Diefenderfer et al. [3], Taamneh [4] all in the United States and Asefzadeh et al. [5] in Canada to ascertain their prediction accuracy in tropical climate, using Ghana as a case study. In-situ asphalt pavement temperature data were measured at two sites for eight months: Kumasi and Tamale in the Forest and Savannah climatic zones, respectively. The measured pavement temperature data were statistically compared with predicted temperatures, and it was found that the Park et al. [2] model provided a more accurate pavement temperature prediction in both climatic zones. The other models either over-predicted or under-predicted asphalt pavement temperature with significant error margins. However, there is a need to improve the prediction accuracy of the Park et al. [2] model or a local model developed.

The widely spread CoronaVirus Disease (COVID)- 19 is one of the worst infectious disease outbreaks in history and has become an emergency of primary international concern. As the pandemic evolves, academic communities have been actively involved in various capacities, including accurate epidemic estimation, fast clinical diagnosis, policy effectiveness evaluation and development of contract tracing technologies. There are more than 23,000 academic papers on the COVID-19 outbreak, and this number is doubling every 20 days while the pandemic is still on-going [1]. The literature, however, at its early stage, lacks a comprehensive survey from a data analytics perspective. In this paper, we review the latest models for analyzing COVID19 related data, conduct post-publication model evaluations and cross-model comparisons, and collect data sources from different projects.

Entangled metallic wire material (EMWM) can be utilized as a novel elastic element in vibration isolation devices for mechanical actuators. This paper presents a vibration experiment aimed at investigating the degradation behavior of mechanical performance in EMWM under cyclic compressive environment. An electric vibration testing system, coupled with an isolation structure, is employed to apply compressive loads to the EMWM specimens. Through visual observations and quasi-static compression tests, the variations in geometric morphology and mechanical properties are studied, considering different relative densities and stress amplitudes. The results incidate a significant reduction in the compressed dimension of the specimens as the number of cycles increases, without any wire fractures or wear. Moreover, the mechanical properties exhibit an increasing secant modulus and a decreasing loss factor. These variations ultimately lead to a gradual deviation of the vibration characteristics of the isolation structure from its design state. To predict the mechanical property degradation of EMWM, prediction models are proposed, incorporating dimension, modulus and damping by fitting the obtained results. This research provides valuable experimental data and presents an effective method to determine the operational lifetime of vibration isolators utilizing EMWM.

Achieving global goals on sustainable nutrition, health, and wellbeing will depend on delivering enhanced diets to humankind. This will require, among others, instantaneous access to information on food quality at key points within agri-food systems. Although stationary methods are usually used to quantify grain quality (wet-lab chemistry, benchtop NIR spectrometer); these do not suit many required user-cases, such as stakeholders in decentralized agri-food-chains that are typical for emerging economies. Therefore, we explored new technologies and models that might aid these particular user-cases. For this purpose, we generated the NIR spectra of 328 grain samples from multiple cereals (finger millet, foxtail millet, maize, pearl millet, sorghum) with a standard benchtop NIR Spectrometer (DS2500, FOSS) and a novel mobile NIR-based sensor (HL-EVT5, Hone). We explored a range of classical deterministic and novel machine learning (ML)-driven models to build calibrations out of the NIR spectra. We were able to build relevant calibrations out of both types of spectra. At the same time, ML-based methods enhanced the prediction capacity of calibration models compared to classical deterministic methods. We also documented that the prediction of grain protein content based on NIR spectra generated by a mobile sensor (HL-EVT5, Hone) was highly relevant for quantitative protein predictions (R2 = 0.91, RMSE = 0.97, RPD = 3.48). Thus, the findings of this study lay the foundations on which to expand the utilization of NIR spectroscopy applications for agricultural research and development.

Commercial buildings situated in hot and humid tropical climates rely significantly on cooling systems to maintain optimal occupant comfort. A well-accurate day-ahead load profile prediction plays a pivotal role in planning the energy requirements of cooling systems. Despite the pressing need for effective day-ahead cooling load predictions, current methodologies have not fully harnessed the potential of advanced deep-learning techniques. This research paper aims to address this gap by investigating the application of innovative deep learning models in day-ahead hourly cooling load prediction for commercial buildings situated in tropical climates. A range of deep learning techniques, including Deep Neural Network, Convolutional Neural Networks, Recurrent Neural Networks, and Long Short-Term Memory networks are employed to enhance prediction accuracy. Furthermore, these individual deep learning techniques are synergistically integrated to create hybrid models, such as CNN-LSTM and Sequence-to-Sequence models. An extensive comparative analysis is conducted to identify the most effective hybrid model. Sequence-to-sequence model provided better performance compared to the other single and hybrid models. Experiments are conducted to choose the time horizons from the past that can serve as input to the models. Further, the influence of various categories of input parameters on prediction performance has been assessed. Historical cooling load, calendar features and outdoor weather parameters are found in decreasing order of influence on prediction accuracy. This research focuses on buildings located in Singapore and presents a comprehensive case study to validate the proposed models and methodologies.

Deep learning has been applied in many areas that have had a significant impact on applications that improves real-life challenges. The success of deep learning in a wide range of areas is due in part to the use of activation functions, which are particularly effective at solving non-linear problems. Activation functions are a key focus for researchers in artificial intelligence who aim to improve the performance of neural networks. This article provides a comprehensive explanation and comparison of different activation functions, with a focus on the arc tangent and its variations specifically. The paper presents experimental results that show that variations of the arc tangent using irrational numbers such as pi, the golden ratio, and Euler’s number, as well as a self-arctan function, produce promising results. Since we experimented with promising activation functions on two different problems, and datasets, we reached a result that different irrationals work well for different problems. In other words, arctan ϕ gives the best results mostly for multiclass classification and arctan e gives the best results for time series prediction problems. The paper focuses on a multiclass classification problem applied to the Reuters Newswire dataset and a time-series prediction problem on Türkiye energy trade value to show the impacts of activation functions.

Accurate forecast of tail water level (TWL) is of great importance for the safe and economic operation and management of hydropower stations. The predictive performance is significantly influenced by the backwater effect of downstream hydropower stations and tributaries, but the explicit quantification method of the backwater effect is lacked. In this study, a deep learning model based forecasting framework for TWL predictions is established and applied to forecast TWL of Xiangjiaba (XJB) hydropower stations, which is influenced by the backwater effect of downstream tributaries including Hengjiang River (HJR) and Minjiang River (MJR). Firstly, the lag time of the backwater effect of HJR and MJR is analyzed based on the permutation importance. The results demonstrate that the lag time of backwater effect on the TWL of XJB is 5-7 hours for the HJR and 1-2 hours for the MJR. Then, the runoff thresholds of the HJR and MJR for impacting the TWL of the XJB station are obtained by scenario comparison, and the results show that the thresholds of HJR and MJR are 700 m3/s and 7000 m3/s respectively. Finally, the deep learning methods based TWL forecasting model is established based on the lag time and threshold analysis. The model is used to forecast the TWL in future 48 hours. The results show that the forecasting model has a good predictive performance with 98.22% of absolute errors less than 20 cm. The mean absolute error over the validation dataset is 5.27 cm and the maximum absolute error is 63.35 cm.

Deep learning has been applied in many areas that have had a significant impact on applications that improves real-life challenges. The success of deep learning in a wide range of areas is due in part to the use of activation functions, which are particularly effective at solving non-linear problems. Activation functions are a key focus for researchers in artificial intelligence who aim to improve the performance of neural networks. This article provides a comprehensive explanation and comparison of different activation functions, with a focus on the arc tangent and its variations specifically. The paper presents experimental results that show that variations of the arc tangent using irrational numbers such as pi, the golden ratio, and Euler’s number, as well as a self-arctan function, produce promising results. Since we experimented with promising activation functions on two different problems, and datasets, we reached a result that different irrationals work well for different problems. In other words, arctan ϕ gives the best results mostly for multiclass classification and arctan e gives the best results for time series prediction problems. The paper focuses on a multi-class classification problem applied to the Reuters Newswire dataset and a time-series prediction problem on Türkiye energy trade value to show the impacts of activation functions.

Indian cities are increasingly becoming susceptible to PM10 induced health effects which have become a matter of concern for the policymakers of the country. Air pollution is engulfing the comparatively smaller cities as the rapid pace of urbanization, and economic development seems not to lose steam ever. A review of air pollution of 28 cities of India, which includes tier-I, II, and III cities of India, found to have grossly violated both WHO and NAAQS standards in respect of acceptable daily average PM10 concentrations by a wide margin. Predicting the city level PM10 concentrations in advance and accordingly initiate prior actions is an acceptable solution to save the city dwellers from PM10 induced health hazards. Predictive ability of three models, linear MLR, nonlinear MLP (ANN), and nonlinear CART, for one day ahead PM10 concentration forecasting of tier-II Guwahati city, were tested with 2016-2018 daily average observed climate data, PM10, and gaseous pollutants. The results show that the non-linear algorithm MLP with feedforward backpropagation network topologies of ANN class, giving the best prediction value when compared with linear MLR and nonlinear CART model. ANN (MLP) approach, therefore, may be useful to effectively derive a predictive understanding of one day ahead PM10 concentration level and thus provide a tool to the policymakers for improving decision-making associated with air pollution and public health.

Large lithium-ion batteries (LIBs) in electric vehicles and energy storage systems demonstrate different performance and lifetime compared to small LIB cells, owing to the size effects generated by the electrical configuration and property imbalance. However, the calculation time for performing life predictions with three-dimensional (3D) cell models is undesirably long. In this paper, a lumped cell model with equivalent resistances (LER cell model) is proposed as a reduced order model of the 3D cell model, which enables accurate and fast life predictions of large LIBs. The developed LER cell model is validated via the comparisons with results of the 3D cell models by simulating a 20-Ah commercial pouch cell (NCM/graphite) and the experimental values. In addition, the LER cell models are applied to different cell types and sizes, such as a 20-Ah cylindrical cell and a 60-Ah pouch cell.

In the present paper, an aerodynamic investigation of a high-speed train is performed. In the first section of this article, a generic high-speed train against a turbulent flow is simulated, numerically. The Reynolds-Averaged Navier-Stokes (RANS) equations combined with the SST turbulence model are applied to solve incompressible turbulent flow around a high-speed train. Flow structure, velocity and pressure contours and streamlines at some typical wind directions are the most important results of this simulation. The maximum and minimum values are specified and discussed. Also, the pressure coefficient for some critical points on the train surface is evaluated. In the following, the wind direction influence the aerodynamic key parameters as drag, lift, and side forces at the mentioned wind directions are analyzed and compared. Moreover, the effects of velocity changes (50, 60, 70, 80 and 90 m/s) are estimated and compared on the above flow and aerodynamic parameters. In the second section of the paper, various data-driven methods including Gene Expression Programming (GEP), Gaussian Process Regression (GPR), and random forest (RF), are applied for predicting output parameters. So, drag, lift and side forces and also minimum and a maximum of pressure coefficients for mentioned wind directions and velocity are predicted and compared using statistical parameters. Obtained results indicated that RF in all coefficients of wind direction and most coefficients of free stream velocity provided the most accurate predictions. As a conclusion, RF may be recommended for the prediction of aerodynamic coefficients.

High-rise building machines (HBMs) play a critical role in the successful construction of super-high skyscrapers, providing essential support and ensuring safety. The HBM’s climbing system relies on a jacking mechanism consisting of several independent jacking cylinders. A reliable control system is imperative to maintain a smooth posture of the construction steel platform (SP) under the action of the jacking mechanism. This research introduces three multivariate time series neural network models—namely, Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and Temporal Convolutional Network (TCN)—to predict the posture of HBM. The models take pressure and stroke measurements from the jacking cylinders as inputs, and their outputs determine the levelness of the SP and the posture of the HBM at various climbing stages. The development and training of these neural networks are based on historical on-site data, with the predictions subjected to thorough comparative analysis. All proposed neural network models exhibit the capability to dynamically predict the posture of the HBM during the climbing process, using data from sensors. Notably, the GRU model shows better predictive performance.

As renewable energy generation prediction system has been introduced into the energy trading market, making a model to accurately predict the quantity of solar photovoltaic (PV) energy generation has become a significant problem. Moreover, to encourage an accurate prediction of the quantity of energy generation, an incentive system has been implemented for those who predict the quantity of solar PV energy under the error rate of 8%. Therefore, it has become more important to investigate and analyze current prediction technology numerically and develop more advanced prediction system. In this study, we tried to develop a better model to improve the accuracy of solar PV energy generation quantity by comparing three models made with gradient boosting machine (GBM), Model 1, Model 2, Model 3 respectively. Model 1 was built with the whole training data set without any additional preprocessing. After conducting some additional preprocessing procedure to predict solar energy generation more accurately, we made Model 2 with the whole training data set and Model 3 with only upper 10% of energy generation capacity. To compare the accuracy of three models, normalized mean absolute error (nMAE) was used as an evaluation index. The nMAE of Model 1 was 9.64% while the Model 2 showed 8.41%. Also, Model 3, which was constructed with the training set of upper 10% energy generation capacity, outperformed with the nMAE of 8.08%. For further study, to check the effectiveness of models constructed with GBM, a time series model, autoregressive integrated moving average (ARIMA), was also built and the nMAE was compared.

Electricity demand prediction is vital for energy production management and proper exploitation of the present resources. Recently, several novel machine learning (ML) models have been employed for electricity demand prediction to estimate the future prospects of the energy requirements. The main objective of this study is to review the various ML models applied for electricity demand prediction. Through a novel search and taxonomy, the most relevant original research articles in the field are identified and further classified according to the ML modeling technique, perdition type, and the application area. A comprehensive review of the literature identifies the major ML models, their applications and a discussion on the evaluation of their performance. This paper further makes a discussion on the trend and the performance of the ML models. As the result, this research reports an outstanding rise in the accuracy, robustness, precision and the generalization ability of the prediction models using the hybrid and ensemble ML algorithms.

Transportation authorities aim to boost road safety by identifying risky locations and applying suitable safety measures. The Highway Safety Manual (HSM) is a vital resource for US transportation professionals, aiding in the creation of Safety Performance Functions (SPFs), which are predictive models for crashes. These models rely on Negative Binomial distribution-based regression and misinterpreting them due to unmet statistical assumptions can lead to erroneous conclusions, including inaccurately assessing crash rates or missing high-risk sites. The Florida Department of Transportation (FDOT) has introduced context classifications to HSM SPFs, complicating assumption violation identification. This study, part of an FDOT-sponsored project, investigates established statistical diagnostic tests to identify model violations and proposes a novel approach to determine optimal spatial regions for Empirical Bayes adjustment. This adjustment aligns HSM-SPFs with regression assumptions. The study employs a case study involving Florida roads. Results indicate that a 20-mile radius offers an optimal spatial sample size for modeling crashes of all injury levels, ensuring accurate assumptions. For severe injury crashes, which are less frequent and harder to predict, a 60-mile radius is suggested to fulfill statistical modeling assumptions. This methodology guides FDOT practitioners in assessing the conformity of HSM-SPFs with intended assumptions and determining appropriate region sizes.

The aim of this study was to develop a basic model to predict enteric methane emission from dairy cows and to update operational calculations for the national inventory in Norway. Basic models were developed using a database with 63 treatment means from 19 studies. The database included records for enteric CH4 production (MJ/day), dry matter intake (DMI), and dietary nutrient composition. The basic models were evaluated against an external database (n=36, from ten studies) along with other extant models. When evaluated by low root mean square prediction errors and high concordance correlation coefficients, the developed basic models that included DMI, dietary concentrations of fatty acids and neutral detergent fiber performed slightly better in predicting CH4 emissions than extant models. In order to propose country-specific values for the CH4 conversion factor Ym (% of gross energy intake partitioned into CH4) and thus to carry out the national inventory for Norway, the existing operational model was updated for the prediction of Ym over a wide range of feeding situations using energy corrected milk and dietary concentrate share as predictor variables. Input values of Ym were updated based on the results from the basic models. The predicted Ym ranged from 6.22 to 6.72%. In conclusion, the prediction of CH4 production from dairy cows was improved with the help of newly published data, which enabled an update of the operational model for calculating the national inventory of CH4 in Norway.

The ability to predict the skin sensitization potential of small organic molecules is of high importance to the development and safe application of cosmetics, drugs and pesticides. One of the most widely accepted methods for predicting this hazard is the rodent local lymph node assay (LLNA). The goal of this work was to develop in silico models for the prediction of the skin sensitization potential of small molecules that go beyond the state of the art, with larger LLNA data sets and, most importantly, a robust and intuitive definition of the applicability domain, paired with additional indicators of the reliability of predictions. We explored a large variety of molecular descriptors and fingerprints in combination with random forest and support vector machine classifiers. The most suitable models were tested on holdout data, on which they yielded competitive performance (Matthews correlation coefficients up to 0.52; accuracies up to 0.76; areas under the receiver operating characteristic curves up to 0.83). The most favorable models are available via a public web service at https://nerdd.zbh.uni-hamburg.de/skinDoctor/ that, in addition to predictions, provides assessments of the applicability domain and indicators of the reliability of the individual predictions.

Heavy rains have created significant threats to human health and life. Floods and other natural disasters, which have a global impact annually, can be attributed to extended durations of intense precipitation. Accurate rainfall predictions are crucial in nations such as Bangladesh, where agriculture is the predominant occupation. The efficiency of machine learning (ML) methods is enhanced by the non-linearity of rainfall, surpassing the effectiveness of other alternative ways. Machine learning techniques show that individual classifiers exhibit worse accuracy than ensemble learning (EL) methodologies. Ensemble Learning techniques are utilized for rainfall prediction and estimating rainfall quantity and daily average temperature to enhance comprehension of the diverse Machine Learning algorithms. This research implements the machine learning techniques and ensemble-based classifier to predict the rainfall occurrence, along with the machine learning regressor models and ensemble-based regressor for the rainfall amount prediction and daily average temperature prediction, using Bangladesh Weather Dataset. The results of the machine learning and ensemble-based models are compared using the Accuracy and F1 score for rainfall occurrence prediction. In contrast, MAE and RMSE evaluation metrics are used for ensemble regressor and regression algorithms for the rainfall amount and daily average temperature prediction. With an accuracy of 83.41% and a recall of 78.17%, the Ensemble Classifier is the best at predicting when it will rain, but its precision of 51.16% stands in for the lowest. The Ensemble Regression model outperforms Linear Regression, Random Forest, and SVR in rainfall amount prediction, with the lowest MAE of 0.36 and RMSE of 0.90. The Ensemble Regression provides the most precise results for daily average temperature prediction with the lowest MAE 0.42 and RMSE 0.54 highlighting its superiority over the other regression models in forecasting temperature with less error. Ensemble approaches consistently lead task performance metrics.

The prediction of tertiary RNA structures is significant to the field of medicine (e.g. mRNA vaccines, genome editing), and the exploration of viral transcripts. Though many RNA folding software exist, few studies have condensed their locus of attention solely to viral pseudoknotted RNA. These regulatory pseudoknots play a role in genome replication, gene expression, and protein synthesis. This study explores five RNA folding engines that compute either the minimum free energy (MFE) or the maximum expected accuracy (MEA). These folding engines were tested against 26 experimentally derived short pseudoknotted sequences (20-150nt) using metrics that are commonly applied to software prediction accuracy (e.g. F1 scoring, PPV). This paper reports higher accuracy RNA prediction engines (pKiss) when compared to previous iterations of the software, and when compared to older folding engines. They show that MEA folding software does not always outperform MFE folding software in prediction accuracy when assessed with metrics such as percent error, sensitivity, PPV, and F1 scoring when applied to viral pseudoknotted RNA. Moreover, the results suggest that thermodynamic model parameters will not ensure accuracy if auxiliary parameters such as Mg2+ binding, dangling end options, and H-type penalties are not applied. The observations reported in this paper highlight the quality between different ab initio prediction methods while enforcing the idea that a better understanding of intracellular thermodynamics is necessary for a more efficacious screening of RNAs.

With the rapid development of artificial intelligence, machine learning is gradually becoming popular in predictions in all walks of life. In meteorology, It is gradually competing with traditional climate predictions dominated by physical models. This survey aims to consolidate the current understanding of Machine Learning (ML) applications in weather and climate prediction—a field of growing importance across multiple sectors including agriculture and disaster management. Building upon an exhaustive review of more than 20 methods highlighted in existing literature, this survey pinpointed eight techniques that show particular promise for improving the accuracy of both short-term weather and medium-to-long-term climate forecasts. According to the survey, while ML demonstrates significant capabilities in short-term weather prediction, its application in medium-to-long-term climate forecasting remains limited, constrained by factors such as intricate climate variables and data limitations. Current literature tends to focus narrowly on either short-term weather or medium-to-long-term climate forecasting, often neglecting the relationship between the two, as well as general neglect of modelling structure and recent advances. By providing an integrated analysis of models spanning different time scales, this survey aims to bridge these gaps, thereby serving as a meaningful guide for future interdisciplinary research in this rapidly evolving field.

Context: CYP21A2 deficiency represents 95% of congenital adrenal hyperplasia cases (CAH), a group of genetic disorders that affect steroid biosynthesis. The genetic and functional analysis provides critical tools to elucidate complex CAH cases. One of the most accessible tools to infer the pathogenicity of new variants is in silico prediction. Objective: Analyze the performance of in silico prediction tools to categorize missense single nucleotide variants (SNVs) of the CYP21A2. Methods: SNVs of the CYP21A2 characterized in vitro by functional assays were selected to assess the performance of online single and meta predictors. SNVs were tested separately or in combination with the related phenotype (severe or mild CAH form). In total, 103 SNVs of the CYP21A2 (90 pathogenic and 13 neutral) were used to test the performance of 13 single-predictors and four meta-predictors. Results: SNVs associated with the severe phenotypes were well categorized by all tools, with an accuracy between 0.69 (PredictSNP2) and 0.97 (CADD), and Matthews' correlation coefficient (MCC) between 0.49 (PoredicSNP2) and 0.90 (CADD). However, SNVs related to the mild phenotype had more variation, with the accuracy between 0.47 (S3Ds&GO and MAPP) and 0.88 (CADD), and MCC between 0.18 (MAPP) and 0.71 (CADD). Conclusion: From our analysis, we identified four predictors of CYP21A2 pathogenicity with good performance. These results can be used for future analysis to infer the impact of uncharacterized SNVs' in CYP21A2.

Prediction models in mobility and transportation maintenance systems have been dramatically improved through using machine learning methods. This paper proposes novel machine learning models for an intelligent road inspection. The traditional road inspection systems based on the pavement condition index (PCI) are often associated with the critical safety, energy and cost issues. Alternatively, the proposed models utilize surface deflection data from falling weight deflectometer (FWD) tests to predict the PCI. Machine learning methods are the single multi-layer perceptron (MLP) and radial basis function (RBF) neural networks as well their hybrids, i.e., Levenberg-Marquardt (MLP-LM), scaled conjugate gradient (MLP-SCG), imperialist competitive (RBF-ICA), and genetic algorithms (RBF-GA). Furthermore, the committee machine intelligent systems (CMIS) method was adopted to combine the results and improve the accuracy of the modeling. The results of the analysis have been verified through using four criteria of average percent relative error (APRE), average absolute percent relative error (AAPRE), root mean square error (RMSE), and standard error (SD). The CMIS model outperforms other models with the promising results of APRE=2.3303, AAPRE=11.6768, RMSE=12.0056, and SD=0.0210.

Crash prediction of the sharp horizontal curve segment (SHCS) of a freeway is an important tool in analyzing safety of SHCSs and in building a crash prediction model (CPM). The design and crash report data of 88 SHCSs from different institutions were surveyed and three negative binomial (NB) regression models and three generalized negative binomial (GNB) regression models were built to prove that the interactive influence of explanatory variables plays an important role in fitting goodness. The study demonstrates the effective use of the GNB model in analyzing the interactive influence of explanatory variables and in predicting freeway basic segments. Traffic volume, highway horizontal radius, and curve length have been formulated as explanatory variables. Subsequently, we performed statistical analysis to determine the model parameters and conducted sensitivity analysis. Among the six models, the result of model 6, which considered interactive influence, is much better than those of the other models by fitting rules. We also compared the actual results from crashes of 88 SHCSs with those predicted by models 1, 3, and 6. Results demonstrate that model 6 is much more reasonable than models 1 and 3.

It has been an outstanding challenge for global climate models to simulate and predict East Asia (EA) summer monsoon (EASM) rainfall. This study evaluates the dynamical hindcast skills with the newly developed Nanjing University of Information Science and Technology Earth System Model version 3.0 (NESM3.0). To improve the poor prediction of an earlier version of NESM3.0, we have modified convective parameterization schemes to suppress excessive deep convection and enhance insufficient shallow and stratiform clouds. The new version of NESM3.0 with modified parameterizations (MOD hereafter) yields significantly improved rainfall prediction in the northern and southern China but not over the Yangtze River Valley. The improved prediction is primarily attributed to the improvements in the predicted climatological summer mean rainfall and circulations, seasonal march of the subtropical rain belt, Nino 3.4 SST anomaly, and the rainfall anomalies associated with the development and decay of El Nino events. However, the MOD still has notable biases in the predicted leading mode of interannual variability of precipitation. The leading mode captures the dry (wet) anomalies over the South China Sea (northern EA) but misplaced precipitation anomalies over the Yangtze River Valley. The model can capture the interannual variation of the circulation indices very well, but the bias in the circulation-rainfall connection caused predicted rainfall errors. The results here suggest that over EA land regions, the skillful rainfall prediction relies on not only model’s capability in predicting better summer mean and seasonal march of rainfall and ENSO teleconnection with EASM, but also accurate prediction of the leading modes of interannual variability.

One of the most important problems in the presence of epidemics and pandemics is an accurate prediction and preparedness. Scholars and experts argue that future pandemics and/or epidemics are almost inevitable events and is not whether next pandemics will happen, but when a new heath emergency will emerge. Epidemiologic models for prediction of Coronavirus Disease 2019 (COVID-19) have shown many limitations because of unpredictable dynamics of the new viral agent SARS-CoV-2 in environment and society. The main goals of this study are twofold: first, the analysis of anthropogenic activities and factors that may trigger pandemic threats; second, the planning of new directions for strategies to reduce risks that a pandemic threat emerges and/or in the initial phase to reduce vast diffusion and negative impact of new viral agents that can generate hazards and problems in public health, environment and socioeconomic systems. In particular, the investigation and understanding of sources and driving factors concerning the emergence and diffusion of new pandemics have critical aspects for strategic actions of forecast, prevention and preparation of effective policy responses to cope with next pandemic crises and health emergencies. Insights here endeavor, whenever possible, to clarify these problems to increase the knowledge of the sources and factor determining the emergence of new viral agents in order to design optimal response policies to face next pandemic diseases similar to COVID-19. .

Rising incidences of cutaneous melanoma have fueled the development of statistical models that predict the individual melanoma risk. Our aim was to assess the validity of published prediction models for incident cutaneous melanoma using a standardized procedure based on PROBAST (Prediction model Risk Of Bias ASsessment Tool). We included studies that were identified by a recent systematic review and updated the literature search to ensure that our PROBAST rating included all relevant studies. Six reviewers assessed the risk of bias (ROB) for each study using the published “PROBAST Assessment Form” that consists of four domains and an overall rating of ROB. We further examined a temporal effect regarding changes in overall and domain-specific ROB rating distributions. Altogether 42 studies were assessed, of which a vast majority (n=34; 81%) was rated as having high ROB. Only one study was judged as having low ROB. The main reasons for high ROB ratings were the use of hospital controls in case-control studies and the omission of any validation of prediction models. However, our results of the temporal analysis showed a significant reduction in the number of studies with high ROB for the domain analysis. Nevertheless, the evidence base of high-quality studies that can be used to draw conclusions on the prediction of incident cutaneous melanoma is currently much weaker than the high number of studies on this topic would suggest.

This work describes a method to carry out 2-D inversion of gravity data in terms of porosity and matrix density distribution using previous DC resistivity inversion results to constraint the fractional pore-water content in the rocks. The inversion is carried out using a controlled random search (CRS) algorithm for global optimization. The method was tested on synthetic data generated from a model representing a graben, and the results show that it can estimate accurate values of contrast-density and porosity. The method was also applied to gravity and dc experimental data collected in NE Portugal, showing results that agree quite well with the known geological information.

To minimise environmental impact, avoid regulatory penalties, and improve competitiveness, energy-intensive manufacturing firms require accurate forecasts of their energy consumption so that precautionary and mitigation measures can be taken. Deep learning is widely touted as a superior analytical technique to traditional artificial neural networks, machine learning, and other classical time series models due to its high dimensionality and problem solving capabilities. Despite this, research on its application in demand-side energy forecasting is limited. We compare two benchmarks (Autoregressive Integrated Moving Average (ARIMA), and an existing manual technique used at the case site) against three deep learning models (simple Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU)) and three machine learning models (Support Vector Regression (SVM), Random Forest, and K-Nearest Neighbors (KNN)) for short term load forecasting (STLF) using data from a Brazilian thermoplastic resin manufacturing plant. We use the grid search method to identify the best configurations for each model, and then use Diebold-Mariano testing to confirm the results. Results suggests that the legacy approach used at the case site is the worst performing, and that the GRU model outperformed all other models tested.

As the coronavirus disease 2019 (COVID-19) continues to rage worldwide, the United States has become the most affected country with more than 34.1 million total confirmed cases up to June 1, 2021. In this work, we investigate correlations between online social media and Internet search for the COVID-19 pandemic among 50 U.S. states. By collecting the state-level daily trends through both Twitter and Google Trends, we observe a high but state-different lag correlation with the number of daily confirmed cases. We further find that the predictive accuracy measured by the correlation coefficient is positively correlated to a state’s demographic, air traffic volume and GDP development. Most importantly, we show that a state’s early infection rate is negatively correlated with the lag to the previous peak in Internet search and tweeting about COVID-19, indicating that earlier collective awareness on Twitter/Google correlates with lower infection rate. Lastly, we demonstrate that correlations between online social media and search trends are sensitive to time, mainly due to the attention shifting of the public.

The intense motion of a ship can greatly impacts the comfort of crew members and the safety of the vessel. Therefore, accurately estimating and predicting ship attitudes has become an important issue. This paper introduces the latest development in functional deep learning model called DeepOnet. It takes wave height as input and ship motion as output, using a cause-to-result prediction approach. The modeling data used in this study is sourced from publicly available experimental data from the Iowa Institute of Hydraulic Research. Firstly, parameters system tuning was conducted for the neural network's hyperparameters to determine the appropriate combination of parameters. Secondly, the DeepOnet model for wave height and multi-degree-of-freedom motion was established, and the influence of increasing time steps on prediction accuracy was examined. Finally, a comparison was made between the DeepOnet model and the classical time series model LSTM. It was found that the DeepOnet model had a 10-fold improvement in accuracy for roll and heave attitudes. Moreover, as the forecast duration increased, the advantage of DeepOnet showed a trend of strengthening. As a functional prediction model, DeepOnet provides a new promising tool for very short-term prediction of ship motion.

Marker-assisted selection (MAS) and genomic selection (GS) have been used to select individuals with desirable traits. MAS used a few markers associated with a specific trait to select individuals with desirable traits, which are determined after a Genome-wide association studies (GWAS). On the contrary, GS uses a large number of markers distributed across the genome to predict the genomic breeding values for a further selection of the individuals. In general, MAS has shown a high prediction accuracy but is not suitable for traits that are controlled for multiple genes, and has another constraint, it is required the phenotypic data; on the contrary, GS has not shown the highest prediction accuracy as MAS but it takes into account the effect of multiple genes controlling a target trait and it can be used without phenotypic data. Including GWAS-selected markers in GS can enhance the reduced prediction accuracy that GS shows in comparison with MAS. Thus, the objective of this study was to compare the prediction accuracy of MAS, and some models of genomic prediction (gBLUP, gBLUP including GWAs-selected markers, and some Bayesian models such as Bayes A, Bayes B, Bayes LASSO and Bayesian Ridge Regression) with GWAS-selected markers incorporated in gBLUP in order to confirm if the incorporation of GWAS in GS increases the prediction accuracy of GS. As a model for this study, it was used data from Sorghum which has shown population structure, to evaluate if the incorporation of GWAs-selected markers into GS improves prediciton accuracy. It was used a sample of 6000 SNPs out of the 265.487 reported in the study conducted by Morris et al (2013), and also it was considered some parameters that affect the efficiency of the selection such as the size of the training population, the heritability, and the number of QTNs. The GWAS-selected SNPs were identified after using the model BLINK. The results showed that the incorporation of GWAS-selected markers enhanced the performance of the genomic selection with similar prediction accuracy as MAS, the number of QTNs and size of the training population affected the accuracy, with higher accuracy with a bigger size of the training population and with a lower number of QTNs, but it seems that the heritability does not have any impact in the model where GWAS-selected SNPs were included in gBLUP.

Commercial buildings are a significant consumer of energy worldwide. Logistics facilities, and specifically warehouses, are a common building type yet under-researched in the demand-side energy forecasting literature. Warehouses have an idiosyncratic profile when compared to other commercial and industrial buildings with a significant reliance on a small number of energy systems. As such, warehouse owners and operators are increasingly entering in to energy performance contracts with energy service companies (ESCOs) to minimise environmental impact, reduce costs, and improve competitiveness. ESCOs and warehouse owners and operators require accurate forecasts of their energy consumption so that precautionary and mitigation measures can be taken. This paper explores the performance of three machine learning models (Support Vector Regression (SVR), Random Forest, and Extreme Gradient Boosting (XGBoost)), three deep learning models (Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU)), and a classical time series model, Autoregressive Integrated Moving Average (ARIMA) for predicting daily energy consumption. The dataset comprises 8,040 records generated over an 11-month period from January to November 2020 from a non-refrigerated logistics facility located in Ireland. The grid search method was used to identify the best configurations for each model. The proposed XGBoost models outperform other models for both very short load forecasting (VSTLF) and short term load forecasting (STLF); the ARIMA model performed the worst.

Cricket, the most popular sports in the world to chase by the fans. Many cricket fans are interested in analyzing the elements and activities that affect the outcomes of matches. Machine learning in sports analytics is a relatively new topic in computer science. The purpose of this survey is to anticipate the outcome of a PSL champion team and build a winning strategy. Machine learning (ML) has exhibited favorable outcomes in a variety of sectors for diverse prediction using classification, regression, and so on, and is proven to be accurate. The innovative frameworks based on ML have the ability to learn from previous experiences. The cricket pitch is the most important aspect, alongside home game an edge, coin toss, innings of play, day/night match, physical conditioning, and dynamic plans, among other things. The dataset from previously ESPN Cricifno was used for this purpose. Recent classification approaches including, Random Forest, Gradient Boost, Deep Neural Networks used to conduct a comparative analysis based on their results and performances, as well as team strategies.

Software defect prediction models enable test managers to predict defect-prone modules and assist with delivering quality products. A test manager would be willing to identify the attributes that can influence defect prediction and should be able to trust the model outcomes. The objective of this research is to create software defect prediction models with a focus on interpretability. Additionally, it aims to investigate the impact of size, complexity, and other source code metrics on the prediction of software defects. This research will also assess the reliability of cross-project defect prediction. Well-known machine learning techniques such as support vector machines, k-nearest neighbors, random forest classifiers, and artificial neural networks were applied to publicly available PROMISE datasets. The interpretability of this approach has been demonstrated by SHapley Additive exPlanations (SHAP) and local interpretable model-agnostic explanations (LIME) techniques. The developed interpretable software defect prediction models showed reliability on independent and cross-project data. Finally, the results demonstrate that static code metrics can contribute to the defect prediction models, and the inclusion of explainability assists in establishing trust in the developed models.

The use of Artificial Neural Networks (ANN) is a great contribution to medical studies since the application of forecasting concepts allows the analysis of future diseases propagations. In this context, this paper presents a study of the new coronavirus SARS-COV-2 with a focus on verifying the virus propagation associated with mitigation procedures and massive vaccination campaigns. There were proposed two methodologies to predict 28 days ahead the number of new cases, deaths, and ICU patients of five European countries: Portugal, France, Italy, United Kingdom, and Germany, and a case study of the results of massive immunization in Israel. The data input of cases, deaths, and daily ICU patients was normalized to reduce discrepant numbers due to the countries size, and the cumulative vaccination values by the percentage of population immunized, at least with one dose of vaccine. As a comparative criterion, the calculation of the mean absolute error (MAE) of all predictions presents the best methodology and targets other possibilities of use for the proposed method. The best architecture achieved a general MAE for the 1 to 28 days ahead forecast lower than 30 cases, 0,6 deaths and 2,5 ICU patients by million people.

Intelligent Tutoring Systems (ITS) are increasingly popular for online learning. These systems use adaptive algorithms to recommend relevant content based on students' profiles. However, instructors need to periodically assess students' performance to ensure learning outcomes and adjust strategies accordingly. Our objective is to predict students' progress in advance, enabling teachers to make quicker decisions and facilitating the iterative process of adaptive algorithms. For this study, we collected a dataset from ALIN, an online learning platform, consisting of over 5,000 students' learning records and test results. Using this dataset, we conducted experiments employing various machine learning algorithms. The results indicate that learning behavior contributes to improving forecast performance, while students' progress strongly correlates with their previous test results. Additionally, we discovered that students' progress can be indirectly predicted by forecasting their scores. Furthermore, by breaking down overall scores into several distinct components and predicting individual scores for each component, the accuracy of the forecasts can be improved.

Data mining techniques have garnered significant attention within the realm of education. However, the procurement of ample student data poses a formidable challenge. In response to this challenge, we present a student dataset characterized by its size and distinctive attributes. This dataset encompasses various task-related topics interconnected through a learning pathway, thereby enabling researchers to delve into the data from novel perspectives. Moreover, it encompasses extensive longitudinal student behavioral data, a rarity that adds substantial value. Spanning the years from 2010 to 2021, our dataset comprises a cohort of 7,933 students, 64,344 test scores, and 183,390 behavior records, solidifying its status as a valuable resource for educational research. In our experiments, we achieved successful predictions of students' test outcomes based on behavioral learning data. The strengths of our dataset render it apt for analyzing the nexus between student conduct and academic performance, crafting personalized learning recommendations, and pursuing various other research pursuits.

Culture exploits the acquisition of meaningful content by crafting regimes of shared attention, determining what is relevant, valuable, and salient. Culture changes the field of relevant social affordances worthy of being acted upon in a context-sensitive manner. When relevant affordances are highly weighted, their attentional capture and their salience increase the probability of them being enacted due to the associated expectation for minimizing prediction error. This process is known as active inference. In the digital era, individuals need to infer the action-related attributes of digital cues, here characterized as digital affordances. The digital affordances of digital social platforms are of particular interest here. Digital social affordances are defined as online possibilities of social interactions. By their own nature, these are salient because they are related to social interactions and relevant social cues. However, the problem of digital social platforms is that they are not equivalent to situated social interactions because their structure is built, mediated, and defined by third-parties with diverse interests. The third-parties behind the digital social platforms are using the same mechanism exploited by culture to manipulate the shared patterns of attention. Moreover, digital social platforms are deliberately designed to be hyper-stimulating, making digital social affordances highly rewarding and increasingly salient. This appropriation, for economic purposes, is an issue of great importance, especially as the COVID-19 pandemic brought deep global changes, pushing societies to an online digital way of life. Here, we examined different types of digital social affordances under an active inference view, placing them into two categories, those for self-identity formation, and those for belief-updating. This paper aims to analyze digital social affordances in light of the prediction error dynamics they might elicit to their users. Although each of the analyzed digital social affordances allows different epistemic and instrumental digital actions, they all share the characteristic of having an "easy" and a fast expected rate of error reduction. Here, we aim to provide a new hypothesis about how the design behind digital social affordances is built on our natural attractiveness to minimize prediction error and the resulting positive embodied feelings when doing so. Finally, it is suggested that because digital social affordances are becoming highly weighted in the field of affordances, this might be putting at risk our context-sensitive grip on a rich, dynamic and varied field of relevant affordances.

Soil moisture is an important factor affecting the plant growth. For a long time, the convenience, timeliness and accuracy of soil moisture monitoring have been limited due to the backward of observation methods and equipment. Therefore, the quantitative prediction of soil moisture has become a difficult problem. Aiming at the problems of high erection cost, easily damaged sensors and low measurement accuracy of the existing fixed sensor soil moisture monitoring system, a soil moisture prediction model based on the long short term memory neural network (LSTM) integrating the particle swarm optimization (PSO) (PSO-LSTM) is designed and implemented. The hyperparameters of the LSTM network can be obtained based on the excellent global search ability of the PSO algorithm. According to the meteorological data and soil moisture data of Haidian Park in 2019, the long short term memory(LSTM) neural network based prediction model is constructed with input vectors of surface temperature, average temperature, evaporation, sunshine hours, precipitation and average wind speed, and the output vector of soil relative humidity. The results show that compared with the back propagation(BP) neural network, the Elman neural network and the LSTM neural network, the proposed PSO-LSTM model has higher prediction performance.

This paper describes a stochastic clustering architecture that is used in the paper for making predictions over energy data. The design is discrete, localised optimisations based on similarity, followed by a global aggregating layer, which can be compared with the recent random neural network designs, for example. The topic relates to the IDEAS Smart Home Energy Project, where a client-side Artificial Intelligence component can predict energy consumption for appliances. The proposed data model is essentially a look-up table of the key energy bands that each appliance would use. Each band represents a level of consumption by the appliance. This table can replace disaggregation from more complicated methods, usually constructed from probability theory, for example. Results show that the table can accurately disaggregate a single source to a set of appliances, because each appliance has quite a unique energy footprint. As part of predicting energy consumption, the model could possibly reduce costs by 50% and more than that if the proposed schedules are also included. The hyper-grid has been changed to consider rows as single units, making it more tractable. A second case study considers wind power patterns, where the grid optimises over the dataset columns in a self-similar way to the rows, allowing for some level of feature analysis.

The main objective of this study is to search better prediction result of rainy seasonal rainfall (15 June-15 August). A correlation between rainfall of Bengali rainy seasons at Rangpur, Dhaka, Barisal and Sylhet and global sea surface temperature (SST) of different areas of the world was studied by using the both data of 1975- 2008 years with the help of the Climate Predictability Tool (CPT) to find more positive correlated SST with observed rainfall and use as predictor for giving the prediction of the year 2009. Using SST of one month before rainy season as predictor, the positive deviation of predicted rainfall from observed rainfall was 1.34 mm/day at Sylhet and 0.9 mm/day at Dhaka. The negative deviation of mean rainfall was 1.16 mm/day at Rangpur and 1.10 mm/day at Barisal. Again, using of starting one month SST of rainy season as predictor, positive deviation of predicted rainfall from observed rainfall was 4.03 mm/day at Sylhet. The positive deviation of daily mean rainfall was found 6.58 mm/day at Dhaka and 6.23 mm/day over southern Bangladesh. The study reveals that sea surface temperature (SST) of one month before rainy season was better predictor than SST of starting month of rainy season.

Floods are among the most destructive natural disasters, which are highly complex to model. The research on the advancement of flood prediction models has been contributing to risk reduction, policy suggestion, minimizing loss of human life and reducing the property damage associated with floods. To mimic the complex mathematical expressions of physical processes of floods, during the past two decades, machine learning (ML) methods have highly contributed in the advancement of prediction systems providing better performance and cost effective solutions. Due to the vast benefits and potential of ML, its popularity has dramatically increased among hydrologists. Researchers through introducing the novel ML methods and hybridization of the existing ones have been aiming at discovering more accurate and efficient prediction models. The main contribution is to demonstrate the state of the art of ML models in flood prediction and give an insight over the most suitable models. The literature where ML models are benchmarked through a qualitative analysis of robustness, accuracy, effectiveness, and speed have been particularly investigated to provide an extensive overview on various ML algorithms usage in the field. The performance comparison of ML models presents an in-depth understanding about the different techniques within the framework of a comprehensive evaluation and discussion. As the result, the paper introduces the most promising prediction methods for both long-term and short-term floods. Furthermore, the major trends in improving the quality of the flood prediction models are investigated. Among them, hybridization, data decomposition, algorithm ensemble, and model optimization are reported the most effective strategy in improvement of the ML methods. This survey can be used as a guideline for the hydrologists as well as climate scientists to assist them choosing the proper ML method according to the prediction task conclusions.

Interactions between proteins and ions are essential for various biological functions like structural stability, metabolism, and signal transport. Given that more than half of all proteins bind to ions, it becomes crucial to identify ion-binding sites. Accurate identification of protein-ion binding sites helps us to understand proteins’ biological functions and plays a significant role in drug discovery. While several computational approaches have been proposed, this remains a challenging problem due to the small size and high versatility of metals and acid radicals. In this study, we propose IonPred, a sequence-based approach that employs ELECTRA (Efficiently Learning an Encoder that Classifies Token Replacements Accurately) to predict ion binding sites using only raw protein sequences. We successfully fine-tuned our pretrained model to predict the binding sites for nine metal ions (Zn2+, Cu2+, Fe2+, Fe3+, Ca2+, Mg2+, Mn2+, Na+, and K+) and four acid radical ion ligands (CO32−, SO42−, PO43−, NO2−). IonPred surpassed six current state-of-the-art tools by over 44.65% and 28.46% respectively in F1 score and MCC when compared on an independent test dataset. Our method is more computationally efficient than existing tools producing prediction results for a hundred sequences for a specific ion in under ten minutes.

The review aims to examine how well numerical indicators of business bankruptcy can predict outcomes. The paper examines ten critical studies that concentrate on statistical models for bankruptcy predictions utilizing PRISMA criteria. The findings highlight the usefulness of numerical indicators in indicating financial hardship, particularly cash flow ratios. In order to connect theoretical knowledge with real-world corporate strategy applications, the study ends by reaffirming the importance of these indicators in strategic decision-making.

Artificial intelligence algorithms have gained widespread adoption in the field of air conditioning load prediction. However, their prediction accuracy is substantially influenced by the quality of training samples. Training samples that lack relevance to the predicted moments can introduce interference into the neural network's learning process, potentially leading to a state of local convergence during its iterative process. This, in turn, diminishes the robustness and generalization capabilities of the prediction model. To enhance the prediction accuracy of air conditioning load prediction models based on artificial intelligence algorithms, this study presents an artificial intelligence algorithm prediction model based on the method of sample similarity sample screening. Initially, the comprehensive similarity coefficient between samples is computed using the gray correlation analysis method, enriched with enhancements in information entropy. Subsequently, a subset of closely related samples is extracted from the original dataset and employed as the training dataset for the artificial intelligence prediction model. Finally, the trained artificial intelligence algorithm prediction model is deployed for air conditioning load prediction. The results illustrate that the method of screening training samples based on sample similarity effectively improves the prediction accuracy of BP neural network (BPNN) and extreme learning machine (ELM) prediction models. However, it is important to note that this approach may not be suitable for genetic algorithm BPNN (GABPNN) and support vector regression (SVR) models.

The primary goal of picture compression is to reduce the amount of unused image data while still storing or transmitting it in a format that is appropriate. The compression of raw binary data is quite different from the compression of a picture, and these differences may be rather substantial. In light of this, compression is often regarded as an essential technique for the purposes of both data storage an d transmission in order to mitigate the excessive amounts of data that are generated by these images. In order to transmit enormous datasets, particularly for the purposes of telemedicine and teleradiology, one needs a significant amount of storage capacity as well as an expansive network. As a result, compression is an important aspect of medical imaging. In addition to the importance of compression, the quality of the photos themselves is also an essential factor in the success of analysis. In addition to this, the amount of time necessary to compress the photographs before sending them should be reduced.

Research in brain stroke prediction is very crucial as it can lead to the development of early detection techniques and interventions that can enhance the prognosis for stroke victims. Early detection and intervention can help to minimise the damage caused by a stroke, reduce the risk of long-term complications, and enhance the general quality of life for people who have survived a stroke. Additionally, research in stroke prediction can help to identify risk factors and improve understanding of the underlying causes of stroke, which can lead to the development of better prevention strategies. Research on brain stroke prediction is ongoing and has led to the development of various models and tools for predicting the risk of stroke and detecting it early. However, the implementation and use of these tools in clinical practise vary depending on several factors, such as the availability of resources, the specific healthcare system, and the level of awareness and acceptance of these tools among healthcare providers and patients. In general, risk prediction models may be used to quickly identify individuals at high risk of stroke and target them for preventive interventions, such as lifestyle changes, medication management, and screenings. Early detection tools can be used to quickly identify stroke symptoms and initiate appropriate treatment, which can improve outcomes for stroke patients. However, it is important to note that research and development of these models and tools are ongoing, and their use in clinical practise is constantly evaluated and updated. It may take time for these tools to be widely adopted in clinical practise and to see their real-world impact. This research paper focuses on predicting brain stroke occurrence using a range of machine learning algorithms such as Logistic Regression (LR), Decision Tree (DT), Random Forest (RF), Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Gaussian Naive Bayes (GNB), Bernoulli Naive Bayes (BNB), and a Voting Classifier. The main emphasis of this research was to compare the effectiveness of oversampling techniques, as the data was significantly imbalanced. We have used evaluation metrics in this research to assess the accuracy, precision, recall, and other key performance indicators of a model's predictions. Area under the Receiver Operating Characteristics Curve (AUC), minority class accuracy, and majority class accuracy were used to assess the approaches.

Safety is very important in aviation since a loss of safety frequently results in both fatalities and financially damaging situations that are typically unrecoverable. Thus, achieving safety as much as possible is the primary goal of practically all aviation technology work. In this study, an Adaptive Neuro-Fuzzy Inference System (ANFIS)-based classifier is created to estimate the fault risk factor of airplanes. Five categories of real fleet data belonging to structure, electrical, avionic, motor systems, and incident statistics of the planes have been used for classifier development. A risk factor determination for each plane is the output of the developed intelligent classifier, and it can be used to identify general overhaul candidate planes and stop defects and crashes before they happen. The obtained results show that using ANFIS provides a great capability in processing many inputs and outputs depending on different types and classes in the aviation industry and thus predicting the failure risk of the airplane efficiently.

Human monkeypox, caused by monkeypox virus, has spread unprecedentedly to more than 100 countries since May 2022. Here we summarized the epidemiology of monkeypox through a literature review and elucidated the risks and elimination strategies of this outbreak mainly based on the summarized epidemiology. We demonstrated that monkeypox virus became more contagious and less virulent in 2022, which could result from the fact that the virus entered a special transmission network favoring close contacts (i.e., sexual behaviors of men who have sex with men outside Africa) and the possibility that the virus accumulated a few adaptive mutations. We gave the reasons to investigate whether cattle, goats, sheep, and pigs are susceptible to monkeypox virus and whether infection with monkeypox virus could be latent in some primates. We listed six potential scenarios for the future of the outbreak (e.g., the outbreak could lead to endemicity outside Africa with increased transmissibility or virulence). We also listed multiple factors aiding or impeding the elimination of the outbreak. We showed that the control measures strengthened worldwide after the World Health Organization declared the outbreak a public health emergency of international concern (PHEIC) could eliminate the outbreak in 2022. We clarified eight strategies, i.e., publicity and education, case isolation, vaccine stockpiling, risk-based vaccination or ring vaccination, importation quarantine, international collaboration, and laboratory management, for the elimination of the outbreak.

Real estate has the dual characteristics of consumption and investment. Under the inherent concept of "where there is land, there is wealth", real estate has become the investment target of the main asset. In addition to the supply and demand of the market will affect the price of real estate, many general economic factors will also have a certain impact on the price of real estate. This paper pays a special focus on the effects of MRT on housing prices, finding the closer a house is to an MRT station, the higher its price. In addition, convenience stores are very popularized, and this research report is also interested in whether the number of convenience stores within walking distance will affect the house price. In a word, these two factors do affect housing prices significantly.

Developing new ways to estimate probabilities can be valuable for science, statistics, and engineering. By considering the information content of different output patterns, recent work invoking algorithmic information theory has shown that a priori probability predictions based on pattern complexities can be made in a broad class of input-output maps. These algorithmic probability predictions do not depend on a detailed knowledge of how output patterns were produced, or historical statistical data. Although quantitatively fairly accurate, a main weakness of these predictions is that they are given as an upper bound on the probability of a pattern, but many low complexity, low probability patterns occur, for which the upper bound has little predictive value. Here we study this low complexity, low probability phenomenon by looking at example maps, namely a finite state transducer, natural time series data, RNA molecule structures, and polynomial curves. Some mechanisms causing low complexity, low probability behaviour are identified, and we argue this behaviour should be assumed as a default in the real world algorithmic probability studies. Additionally, we examine some applications of algorithmic probability and discuss some implications of low complexity, low probability patterns for several research areas including simplicity in physics and biology, a priori probability predictions, Solomonoff induction and Occam's razor, machine learning, and password guessing.

Three-phase motors are commonly adopted in several industrial contexts and their failures can result in costly downtime causing undesired service outages; this way, motor diagnostics is an issue that assumes great importance. To prevent their failures and timely face the considered service outages, a non-invasive method to identify electrical and mechanical faults in three-phase asynchronous electric motors is proposed in the paper. In particular, a measurement strategy along with a machine learning algorithm based on Artificial Neural Network is exploited to properly classify failures. In particular, digitized current samples of each motor phase are first processed by means of FFT and PSD in order to estimate the associated spectrum. Suitable features (in terms of frequency and amplitude of the spectral components) are then singled out to either train or feed a neural network acting as a classifier. The method is preliminary validated on a set of 28 electric motors, and its performance is compared with common state-of-art machine learning techniques. The obtained results show that the proposed methodology is able to reach accuracy levels greater than 98\% in identifying anomalous conditions of three-phase asynchronous motors.

Reliability assessment is an important component and tool used for process plants since the facility consists of many loops and instruments attached and operates based on each other availability, thus it requires a statistical method to visualize the reliability. The paper focuses on reliability assessment and prediction based on available statistical models such as normal, log-normal, exponential, and Weibull distribution. This paper also visualizes, which model fits best for assessment and prediction and also considers failure modes caused during a simulation mode process control operation. A simulation model is designed in this paper to observe the failure of the control valve causing stiction to visualize the failure modes and predict the best-fit model for reliability assessment.

Predicting copper price is essential for making decisions that can affect companies and governments dependent on the copper mining industry. Copper prices follow a time series that is non-linear, non-stationary, and which have periods that change as a result of potential growth, cyclical fluctuation and errors. Sometimes the trend and cyclical components together are referred to as a trend-cycle. In order to make predictions, it is necessary to consider the different characteristics of trend-cycle. In this paper, we study a copper price prediction method using Support Vector Regression. This work explores the potential of the Support Vector Regression with external recurrences to make predictions at 5, 10, 15, 20 and 30 days into the future in the copper closing price at the London Metal Exchanges. The best model for each forecast interval is performed using a grid search and balanced cross-validation. In experiments on real data-sets, our results obtained indicate that the parameters (C, ε, γ) of the model Support Vector Regression do not differ between the different prediction intervals. Additionally, the amount of preceding values used to make the estimates does not vary according to the predicted interval. Results show that the support vector regression model has a lower prediction error and is more robust. Our results show that the presented model is able to predict copper price volatilities near reality, being the RMSE equal or less than the 2.2% for prediction periods of 5 and 10 days.

The pile foundation in the permafrost region is in a negative temperature environment, so the concrete is affected by the negative temperature of the surrounding soil.It not only affects the formation of concrete strength, but also leads to engineering quality accidents in serious cases.Based on the actual measurement of temperature at different strata depths and the comprehensive consideration of surface temperature, terrestrial heat flux and other parameters, the law curve of temperature change along depth in Greater Khingan is established.The calculated results of the curve are consistent with the measured results of ground temperature.The results show that the variation trend of ground temperature along the strata depth at different monitoring sites is basically the same. From June to November, the ground temperature at different depths tends to be constant.From December to May, the ground temperature at any depth within the depth range of 0 to 5.5m follows the law of the cosine function.Below 5.5m, the earth temperature no longer varies with depth.The research results can be used as reference for pile foundation construction under negative temperature environment.

With the development of computer science and software engineering, software becomes more and more complex. Traditional software reliability assurance techniques including software testing and evaluation can't ensure software reliable execution after being deployed. Software failure prediction techniques based on failure indicators can predict software failures according to abnormal indicator values. The latter can be collected using runtime monitoring techniques. An essential part of this method is finding proper indicators which have strong correlation with software failures. We propose a novel type of indicators in this work named software runtime entropy, which takes both software module execution time and call times into consideration. Three common open source software, grep, flex and gzip are used as study cases for finding the relationships between the indicators and software failures. Firstly, a series of fault injection experiments are conducted on those three software respectively. The decision tree algorithm is used to train those data to build the correlation models between software runtime entropy and software failures. Several common measures in machine learning domains such as accuracy, recall rates, and F-measure are used to evaluate the models. The decision tree models can be used as failure mechanisms to assist the failure prediction work. One can examine the value of runtime entropy and make a warning report when it ranges from the normal interval to abnormal one.

The bHLH-PAS proteins are a family of transcription factors regulating expression of a wide range of genes involved in different functions, from differentiation and development control, by oxygen and toxins sensing to circadian clock setting. In addition to the well-preserved DNA-binding bHLH and PAS domains, bHLH-PAS proteins contain long intrinsically disordered C-terminal regions, responsible for their activity regulation. Our aim was to analyse the potential connection between disordered regions of the bHLH-PAS transcription factors with posttranscriptional modifications and liquid-liquid phase separation in the context of the disease-associated missense mutations. Highly flexible disordered regions, enriched in short more ordered motives, are responsible for wide spectrum of interactions with transcriptional co-regulators. Based on our in silico analysis and taking into account fact that transcription factors functions can be modulated by posttranslational modifications and spontaneous phase separation, we assume that the location of missense mutations inducing disease states, is clearly related to sequences directly undergoing these processes or to sequences responsible for their activity regulation.

This study focuses on predicting traffic speed using the simple Multilayer Perceptron (MLP) model, despite the availability of various models for traffic prediction, with artificial intelligence demonstrating superior predictive capabilities. Emphasizing that the quality of the data holds greater significance than the model itself, the research underscores the challenges posed by data containing significant errors and fluctuations. Unlike relying solely on criteria such as Mean Absolute Deviation (MAD) or coefficient of determination (r2), this study advocates for the use of MAD/range as a more robust metric for prediction accuracy, especially when dealing with data exhibiting substantial order.The study sets the speed limit and traffic value at 0.65 and 0.88, respectively. Notably, both criteria yield identical accuracy results of 13% for MAD/R in predicting speed and 14% for traffic. This parity suggests that the artificial intelligence model performs equally well for both variables, highlighting the importance of considering alternative evaluation metrics in the face of data complexities.

This study was conducted to compare the fertility and hatchability performance of the indigenous helmeted guinea fowls and exotic birds of the French strain, and predict egg weight from egg indices in Nigeria. A total of 300 randomly selected 8-month old guinea fowls comprising 150 indigenous (30 males and 120 females) and 150 French strain (30 males and 120 females) were utilized in the study. From these, a total of 240 randomly selected eggs (120 per genetic group) were used separately for the reproductive and egg quality assessment. The fertility and hatchability parameters were subjected to descriptive statistics, while the seventeen egg quality parameters were analysed using T-test, phenotypic correlation, principal component analysis, multiple linear regression and CHAID decision tree. Percentage fertility (90.0 versus 73.3%) and hatchability (66.7 versus 56.8%) were higher in the French strain compared to their indigenous counterparts. The egg quality parameters of the French strain were higher (P<0.05) than those of their indigenous counterparts with the exception of egg shell index (18.88±0.79 versus 16.41±0.69) and haugh unit (92.37±3.13 versus 91.09±3.22). However, the mean yolk/albumen ratio was similar (P>0.05). The phenotypic correlation coefficients between egg weight and egg quality indices in both genetic groups ranged from low to high values [-0.05-0.95 (indigenous); -0.19-0.96 (French strain)]. Three principal components sufficiently accounted for the variations in the egg quality traits of both genetic groups. The CHAID algorithm was more consistent in egg weight prediction with egg width as the primary explanatory variable. The present information may guide breeding and management strategies geared towards the improvement of the reproductive and egg quality traits of the helmeted guinea fowls.

The fidelity of the decadal experiment in Coupled Model Intercomparison Project Phase-5 (CMIP5) has been examined, over different climate variables for different temporal and spatial scales, in many previous studies. However, most of the studies were for the temperature and temperature-based climate indices. A quite limited study was conducted on precipitation of decadal experiment and no attention was paid to a catchment level. This study evaluates the performances of eight GCMs (MIROC4h, EC-EARTH, MRI-CGCM3, MPI-ESM-MR, MPI-ESM-LR, MIROC5, CMCC-CM, and CanCM4) for the monthly hindcast precipitation of decadal experiment over the Brisbane River catchment in Queensland, Australia. First, the GCMs datasets were spatially interpolated onto a spatial resolution of 0.050×0.050 (5 km× 5 km) matching with the grids of observed data and then were cut for the catchment. Next, model outputs are evaluated for temporal skills, dry and wet periods, and total precipitation (over time and space) based on the observed values. Skill test results reveal that model performances varied over the initialization years and showed comparatively higher scores from the initialization year 1990 and onward. Models with finer spatial resolutions show comparatively better performances as opposed to the models of coarse spatial resolutions where MIROC4h outperformed followed by EC-EARTH and MRI-CGCM3. Comparing the skills, models are divided into three categories (Category-I: MIROC4h, EC-EARTH, and MRI-CGCM3; Category-II: MPI-ESM-LR and MPI-ESM-MR; and Category-III: MIROC5, CanCM4, and CMCC-CM). Three multimodel ensembles’ mean (MMEMs) are formed using the arithmetic mean of Category-I (MMEM1), Category-I and II (MMEM2), and all eight models (MMEM3). The performances of MMEMs are also assessed using the same skill tests and MMEM2 performed best which suggests evaluating the models before the formation of MMEM.

Purpose: To compare refractive prediction error (PE)s between phacotrabeculectomy and phacoemulsification. Methods: Refractive PE was defined as the difference of spherical equivalent between the predicted value using the Barrett Universal II formula and the actual value obtained at postoperative one month. Forty-eight eyes that had undergone phacotrabeculectomy (19 eyes, open-angle glaucoma; 29 eyes, angle-closure glaucoma) were matched with 48 eyes that had undergone phacoemulsification by age, average keratometry value and axial length (AL), and their PEs were compared. The factors associated with PE were analyzed by multivariable regression analyses. Results: Phacotrabeculectomy group showed a larger absolute PE compared to the phacoemulsification group (0.51 ± 0.37 Diopters vs. 0.38 ± 0.22, P=0.033). Larger absolute PE was associated with longer AL (P=0.010) and higher intraocular pressure (IOP) difference (P=0.012). Hyperopic shift (PE>0) was associated with shallower preoperative anterior chamber depth (ACD) (P=0.024) and larger IOP difference (P=0.031). In the phacotrabeculectomy group, the PE was inversely correlated with AL: long eyes showed myopic shift and short eyes hyperopic shift (P=0.002). Conclusions: Surgeons should be aware of the possibility of worse refractive outcomes when planning phacotrabeculectomy especially in eyes with high preoperative IOP, shallow ACD, and/or extreme AL.

Link prediction is to complete the missing links in the network or to predict the generation of new links according to the current network structure information, which is very important for mining and analyzing the evolution of the network such for construction and analysis of logical architecture in 6G network. Link prediction algorithms based on node similarity need predefined similarity functions, which is highly hypothetical and only applies to specific network structures without generality. To solve this problem, this paper proposes a link prediction algorithm based on the subgraph of the target node pair. In order to automatically learn the graph structure characteristics, the algorithm firstly extracts the h-hop subgraph of the target node pair, and then predicts whether the target node pair will be linked according to the subgraph. Experiments on seven real data sets show that the link prediction algorithm based on target node pair subgraph is suitable for various network structures and superior to other link prediction algorithms.

In this work, we propose a self-supervised multi-agent system that meets the online learning of clustering tasks for video behavior recognition spatio-temporal tasks. Encoding visual behavioral actions as discrete temporal sequence(DTS). Real-time clustering recognition task in a multi-agent system for continuous model building, training, and correction. Finally, we implemented a fully decentralized multi-agent system and completed its feasibility verification in a surveillance video application scenario on vehicle path clustering.

(1) Background: Preeclampsia (PE) prediction in the first trimester of pregnancy is a challenge for the clinicians. The aim of this study was to evaluate and compare the predictive performances of machine-learning based models for the prediction of preeclampsia, and its subtypes; (2) Methods: This prospective case-control study evaluated pregnancies that occurred in women who attended a tertiary maternity hospital in Romania between November 2019 and September 2022. The patients’ clinical and paraclinical characteristics were evaluated in the first trimester, and were included in 4 machine learning based models: decision tree (DT), naïve Bayes (NB), support vector machine (SVM), and random forest (RF), and their predictive performance was assessed; (3) Results: early-onset PE was best predicted by DT (accuracy: 94.1%), and SVM (accuracy: 91.2%) models, while NB (accuracy: 98.6%), and RF (accuracy: 92.8%) models had the highest performance when used to predict all types of PE. The predictive performance of these models was modest for moderate and severe types of PE, with accuracies ranging from 70.6% and 82.4%; (4) The machine learning-based models could be useful tools for PE prediction in the first trimester of pregnancy.

Retweet prediction is an important task related to different problems such as information spreading analysis, the automatic detection of fake news, social media monitoring, etc. In this study we explore the possibilities of retweet prediction based on heterogeneous data sources. In order to classify the tweet according to the amount of retweets, we combine features extracted from the multilayer network and the text. More specifically, we introduce a multilayer framework that proposes the multilayer network representation of Twitter. This formalism captures different users' actions and complex relationships as well as other key properties of communication on Twitter. We select a set of local network measures from each layer and construct a set of multilayer network features. In addition, we adopt a BERT-based language model, namely Cro-CoV-cseBERT to capture high-level semantics and structure of tweets as a set of text features. Then, we train six machine learning (ML) algorithms: random forest, multilayer perceptron, light gradient boosting machine, category embedding model, neural oblivious decision ensembles and attentive interpretable tabular learning model in the task of retweet prediction. We compare the performance of all six algorithms in three different setups (i) using only text features, (ii) using only multilayer network features and (iii) using both sets of features. We evaluate all setups in terms of standard evaluation measures i.e. precision, recall, F1-score and accuracy. For this task, we first prepare and use an empirical dataset of 199,431 tweets in the Croatian language posted during the period between January 1, 2020 and May 31, 2021. Our results indicate that by integrating multilayer network features with text features the prediction model would perform better than using just one set of features.

Link prediction is an unbalanced early retrieval problem, whose goal is to prioritize a small cohort of positive links on top of a list largely populated by unlabelled links. Differently from binary classification, here the evaluation focuses on how the predictor prioritizes the positive class because, in practice, a negative class does not exist. Previous studies explained that AUC-ROC is not apt for unbalanced class problems and is misleading for early retrieval problems, therefore standard AUC-ROC is not appropriate for evaluation of link prediction. However, some scholars argue that an AUC-ROC like evaluation accounting for the relative positioning of the few positive links among the vastness of unlabelled links remains a valid concept to pursue. Here we propose the area under the magnified ROC (AUC-mROC), a new measure that adjusts the standard AUC-ROC to work also for unbalanced early retrieval problems such as link prediction.

The enormous increase in the volume of Earth Observations (EOs) has provided the scientific community with unprecedented temporal, spatial, and spectral information. However, this increase in the volume of EOs has not yet resulted in proportional progress with our ability to forecast agricultural systems.This study examines the applicability of EOs obtained from Sentinel2 and Landsat8 for constraining the APSIM-Maize model parameters. We leveraged leaf area index (LAI) retrieved from Sentinel2 and Landsat8 NDVI to constrain a series of APSIM-Maize model parameters in three different Bayesian multi-criteria optimization frameworks across 13 different sites across the U.S Midwest. A time variant sensitivity analysis was performed to identify the most influential parameters driving the LAI estimates in APSIM-Maize model. Then surrogate models were develop using random samples taken from the parameter space using Latin hypercube sampling to emulate APSIM’s behavior in simulating NDVI and LAI at all sites. Site-level, global and hierarchical Bayesian optimization models were then developed using the site-level emulators to simultaneously constrain all parameters and estimate the site to site variability in crop parameters. For within sample predictions, site-level optimization showed the largest predictive uncertainty around LAI and crop yield, whereas the global optimization showed the most constraint predictions for these variables. Lowest RMSE for within sample yield prediction was found for hierarchical optimization scheme (1423 Kg ha−1) while the largest RMSE was found for site-level (1494 Kg ha−1). In out-of-sample predictions within the spatio-temporal extent of the training sites, global optimization showed lower RMSE (1627 Kg ha−1) compared to the hierarchical approach (1822 Kg ha−1) across 90 independent sites in the U.S Midwest. On comparison between these two optimization schemes across another 242 independent sites outside the spatio-temporal extent of the training sites, global optimization also showed substantially lower RMSE (1554 Kg ha−1) as compared to the hierarchical approach (2532 Kg ha−1). Overall, EOs demonstrated their real use case for constraining process-based crop models and showed comparable results to model calibration exercises using only field measurements.

Quality of Experience (QoE) metrics can be used to assess user perception and satisfaction in data services applications delivered over the Internet. End-to-end metrics are formed because QoE is dependent on both the users’ perception and the service used. Traditionally, network optimization has focused on improving network properties such as the QoS. In this paper we examine the Adaptive streaming over a software defined network environment. We aimed to evaluate and study the media streams, aspects affecting the stream, and network. This was done to eventually reach a stage of analysing the network’s features and their direct relationship with the perceived QoE. We then use machine learning to build a prediction model based on subjective user experiments. This will help to eliminate future physical experiments and automate the process of predicting QoE.

The concept of distributed generation has made photovoltaic an integral source of energy in smart grid systems, especially in peer-to-peer energy trading frameworks that exploit excess power to fulfill the energy requirements of consumers in cost-efficient and eco-friendly manner. It is believed that P2P energy trading will dominate a significant portion of research in forthcoming power generation systems due to the excessive rise of energy demands across the globe. Despite a plethora of studies on energy optimization solutions in P2P trading, minimizing nanogrid energy trading cost and efficient energy sharing between consumers and prosumers are deemed among the challenging problems. This study overcomes essential issues overlooked by the contemporary P2P energy trading models by introducing a predictive optimization-oriented nanogrid energy trading model. The proposed study encompasses two stages: (1) predictive optimization model which harnesses BD-LSTM-based forecasted energy parameters (energy load, energy consumption, and PV generation) that are later incorporated in PSO-enabled objective function to reduce nanogrid trading cost, (2) optimal energy sharing plan is devised to decide the role of nanogrids as prosumers or consumers by emphasizing the use of PV-produced energy. The proposed model is validated on the case study containing nanogrid houses data. The simulation provides detailed experiments by comparing the energy demand and response using the proposed energy sharing model. The outcomes yield that the energy sharing plan holds a significant potential to fulfill maximum energy requirements of nanogrid house in P2P cluster and significantly reduces the energy cost compared to grid.

Reservoir computing is a machine learning method that uses the response of a dynamical system to a certain input in order to solve a task. As the training scheme only involves optimising the weights of the responses of the dynamical system, this method is particularly suited for hardware implementation. Furthermore, the inherent memory of dynamical systems which are suitable for use as reservoirs mean that this method has the potential to perform well on time series prediction tasks, as well as other tasks with time dependence. However, reservoir computing still requires extensive task dependent parameter optimisation in order to achieve good performance. We demonstrate that by including a time-delayed version of the input for various time series prediction tasks, good performance can be achieved with an unoptimised reservoir. Furthermore, we show that by including the appropriate time-delayed input, one unaltered reservoir can perform well on six different time series prediction tasks at a very low computational expense. Our approach is of particular relevance to hardware implemented reservoirs, as one does not necessarily have access to pertinent optimisation parameters in physical systems but the inclusion of an additional input is generally possible.

The prediction of drug--target interactions is always a key task in the field of drug redirection. However, traditional methods of predicting drug--target interactions are either mediocre or rely heavily on data stacking. In this work, we merged heterogeneous graph information and obtained effective node information and substructure information based on mutual information in graph embeddings. We then learned high quality representations for downstream tasks, and proposed an end--to--end auto--encoder model to complete the task of link prediction. Experimental results show that our method outperforms several state--of--art models. The model can achieve the area under the receiver operating characteristics (AUROC) curve of 0.959 and area under the precise recall curve (AUPR) of 0.848. We found that the mutual information between the substructure and graph--level representations contributes most to the mutual information index in a relatively sparse network. And the mutual information between the node--level and graph--level representations contributes most in a relatively dense network.

This work presents an analytical methodology to predict meat juiciness (discriminant semi-quantitative analysis using groups of intervals of intramuscular fat) and intramuscular fat (regression analysis) in Longissimus thoracis et lumborum (LTL) muscle of Bísaro pigs using as independent variables the animal carcass weight and parameters from color and image analysis. These are non-invasive and non-destructive techniques which allow development of rapid, easy and inexpensive methodologies to evaluate pork meat quality in a slaughterhouse. The proposed predictive supervised multivariate models were non-linear. Discriminant mixture analysis to evaluate meat juiciness by classified samples into three groups—0.6 to 1.1%; 1.25 to 1.5%; and, greater than 1.5%. The obtained model allowed 100% of correct classifications (92% in cross-validation with seven-folds with five repetitions). Polynomial support vector machine regression to determine the intramuscular fat presented R2 and RMSE values of 0.88 and 0.12, respectively in cross-validation with seven-folds with five repetitions. This quantitative model (model’s polynomial kernel optimized to degree of three with a scale factor of 0.1 and a cost value of one) presented R2 and RSE values of 0.999 and 0.04, respectively. The overall predictive results demonstrated the relevance of photographic image and color measurements of the muscle to evaluate the intramuscular fat, rarther than the usual time-consuming and expensive chemical analysis.