Determining the estrous cycle stages in mice is essential for optimizing breeding strategies, synchronizing experimental time lines, and facilitating studies in behavior, drug testing, and genetics. It is critical for reducing the production of genetically unmodified offspring in the generation and investigation of genetically modified animal models. An accurate detection of the estrus cycle is particularly relevant in the context of the 3Rs—Replacement, Reduction and Refinement. The estrous cycle, encompassing the reproductive phases of mice, is key to refining experimental designs and addressing ethical issues related to the use of animals in research. This study presents results from two independent laboratories on the efficacy of the Mouse Estrus Detector (MED) from Elmi Ltd. (Latvia) for the accurate determination of the estrus phase. The female mice of five strains/stocks (CD1, FVB/N, C57Bl6/J, B6D2F1, and Swiss) were used. The results showed that the MEDProTM is a low -traumatic, simple, rapid and painless method of estrus detection that supports the principles of the 3Rs. The use of the MEDProTM for estrus detection in mice caused minimal stress, enhanced mating efficiency, facilitated an increase in the number of embryos for the in vitro fertilization and allowed the production of the desired number of foster animals.

This paper aims to investigate appropriate mathematical models devoted to optimization of some cleaning processes related to pharmaceutical contaminants removal. In our previous recent works has been reported that a possibility for removal from water sources of this type of micropollutants is to rehabilitate the existing cleaning plants by introducing efficient techniques such as adsorption on granulated active carbon filters, micro-, nano- or ultrafiltration. To have such processes under a better control and to pass from small to large scale treatment stations, specific mathematical models are necessary. Starting from Navier-Stokes equations and imposing proper boundary conditions, some mathematical physics problems are obtained for which adequate solving methods via variational methods and surjectivity results are proposed. The importance of these solution characterizations consists in their continuation in a numerical method and the possibility to visualize the result by using CFD program.

This paper explores the utilization of ensemble models and learning analytics techniques to predict student academic performance. With the advent of educational big data, institutions are increasingly leveraging advanced analytics to gain insights into student learning patterns and optimize educational outcomes. Ensemble models, which combine the predictive power of multiple algorithms, offer a robust approach to enhance prediction accuracy. The performance of the ensemble models was analyzed and compared using the Open University Learning Analytics Dataset, which consists of sources such as demographic information, historical performance data, and engagement metrics for 23,344 students. The evaluation of various ensemble models across different classification scenarios revealed that the proposed stacking model consistently emerges as the best-performing model, excelling in both multi-class and binary classification tasks.

There are uncertainties associated with every phase of the stock assessment process, ranging from the collection of data, assessment model choice, model assumptions and interpretation of risk to the implementation of management advice. The dynamics of fish populations are complex, and our incomplete understanding of those dynamics (and limited observations of important mechanisms) necessitate that models are simpler than nature. The aim is for the model to capture enough of the dynamics to accurately estimate trends and abundance and to provide advice to managers about sustainable harvests. The \textit{status quo} approach to assessment modelling has been to identify the `best' model, based on diagnostics and model selection criteria, and to generate advice from that model, mostly ignoring advice from other model configurations regardless of how closely they performed relative to the chosen model. We review the suitability of the ensemble modelling paradigm to more fully capture uncertainty in stock assessment model building and the provision of advice. We recommend further research to evaluate potential gains in modelling performance and advice from the use of ensemble modelling, while also suggesting revisions to the formal process for reviewing models and providing advice to management bodies.

Traffic Inspection (TI) work in this article is positioned as a specific module of road traffic with its primary function oriented towards monitoring and controlling safe traffic and the execution of significant events within a particular geographic area. Exploratory research on the significance of event execution in simple, complicated and complex traffic flow and process situations is related to the activities of monitoring and controlling functional states and performance of categorical variables, which include objects and locations of road infrastructure, communication infrastructure and networks of traffic inspection resources. It is emphasized that the words “work” and “traffic” have the semantic status as synonyms (in one world language), which is explained in the design of the Agent-based model of the complexity of content and contextual structure of TI work at the singular and plural level with 12 points of interest (POI) in the thematic research. An Event Execution Log (EEL) was created for on-site data collection with eight variables, seven of which are independent (event type, activities, objects, locations, host, duration-period and periodicity of the event) and one dependent (significance of the event) variable. The structured data set includes 10,994 input-output vectors in 970 categories collected in the EEL created by 32 human agents (traffic inspectors) over a 30-day period. An algorithmic presentation of the methodological research procedure for preprocessing and final data processing in the ensemble of machine learning models for classification and selection of TI tasks is given. Data cleaning was performed on the available dataset to increase data consistency for further processing. Vector elimination was carried out based on the Location variable, such that the total number of vectors equals the number of unique categories of this variable, which is 636. The main result of this research is the Classification modeling of the significance of events in TI work based on machine learning techniques and the Stacking ensemble. The created machine learning models for event significance classification modeling have high accuracy values. To evaluate the performance metrics of the Stacking ensemble of models, the confusion matrix, Precision, Recall, ND F1-score are used.

Ensembles of Species Distribution Models (SDMs) represent the geographic ranges of pathogen vectors by combining alternative analytical approaches and merging information on vector occurrences with more extensive environmental data. Biased collection data impact SDMs, regardless of the target species but no studies have compared the differences in the distributions predicted by the ensemble models when different sampling frameworks are used for the same species. We compared Ensemble SDMs for two important Ixodid tick vectors, Amblyomma americanum and Ixodes scapularis in mainland Florida, USA, when inputs were either convenience samples of ticks, or collections obtained using the standard protocols promulgated by the U.S. Centers for Disease Control and Prevention. The Ensemble SDMs for the convenience samples and standard surveys showed only a slight agreement (Kappa = 0.060, A. americanum; 0.053, I. scapularis). Convenience sample SDMs indicated A. americanum and I. scapularis should be absent from 34.5% and 30.9% of the state where standard surveys predicted the highest likelihood of occurrence of the respective vectors. Ensemble models from standard surveys predicted 81.4% and 72.5% (A. americanum and I. scapularis) of convenience sample sites. Omission errors by standard survey SDMs, of the convenience collections, frequently were associated with adjacency to at least one SDM or errors in geocoding algorithms that failed to correctly locate convenience samples. These geocoding errors emphasize commonly overlooked needs to explicitly evaluate and improve data quality for vector survey data used in spatial models.

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

Bootstrap resampling techinques, introduced by Efron and Rubin, can be presented in a general Bayesian framework, approximating the statistical distribution of a statistical functional φ(F), where F is a random distribution function. Efron’s and Rubin’s bootstrap procedures can be extended introducing an informative prior through the Proper Bayesian bootstrap. In this paper different bootstrap techniques are used and compared in predictive classification and regression models based on ensemble approaches, i.e. bagging models involving decision trees. Proper Bayesian bootstrap, proposed by Muliere and Secchi, is used to sample the posterior distribution over trees, introducing prior distributions on the covariates and the target variable. The results obtained are compared with respect to other competitive procedures employing different bootstrap techniques. The empirical analysis reports the results obtained on simulated and real data.

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

The age-related loss of muscle mass and strength is referred to as “sarcopenia”. The combined effect of sarcopenia and osteoporosis is a devastating threat to the old adult, accounting for reduced mobility, risk for falls and subsequent fractures. In previous studies, we observed a high degree of inter-individual variability of paraspinal muscle fatty infiltration, one most relevant index of muscle wasting. This aspect solicited us to develop a computerized method to quantitatively characterize muscle fatty infiltration in aging and diseases. Magnetic resonance images of paraspinal muscles from 58 women of different age (age range 23-85 years) and physio-pathological status (healthy young, pre-menopause, post-menopause, and os-teoporosis), were used to set up the method. It is based on fractal analysis of lean muscle area (contractile muscle) to estimate muscle fatty infiltration. In particular, lacunarity was computed by parameter β from our hyperbola model function, used to fit the GBA (gliding box algorithm) curvilinear plot. Succolarity was estimated by parameter µ, for the four main directions, through an algorithm implemented on purpose. Results show that fractal lacunarity, by quantifying muscle fatty infiltration, can discriminate be-tween osteoporosis and healthy aging while succolarity can separate the other three groups showing similar lacunarity. Therefore, fractal features of contractile muscle, by measuring fatty infiltration, can represent good indices of sarcopenia in aging and disease.

Ultrasound (US) is commonly used for the diagnosis of liver masses. Ensemble learning has been widely used for image classification, but its methods have not been fully optimized. This study was performed to investigate the usefulness of ensemble learning and compare a number of ensemble learning techniques using multiple convolutional neural network (CNN)-trained models for image classification of liver masses in US images. The US imaging data set was classified into four categories: benign liver tumor (BLT, 6320 images), liver cyst (LCY, 2320 images), metastatic liver cancer (MLC, 9720 images), and primary liver cancer (PLC, 7840 images). In this study, 250 test images were randomly selected for each class, for a total of 1000 images, and the remaining images were used for training. Sixteen different CNNs were used for to train and test the US images. All four types of ensemble learning—soft voting (SV), stacking (ST), weighted average voting (WAV), and weighted hard voting (WHV)—showed greater accuracy than the single CNN. All four types also showed significantly better deep learning performance than ResNeXt101 alone. For image classification of liver masses using US images, ensemble learning improved the performance of deep learning over a single CNN.

Site Index has been widely used as an age normalised metric to account for variation in forest height at a range of spatial scales. Although previous research has used a range of modelling methods to describe regional variation in Site Index little research has examined gains that can be achieved through use of regression kriging or spatial ensemble methods. In this study an extensive set of environmental surfaces were used as covariates to predict Site Index measurements covering the environmental range of \textit{Pinus radiata} D. Don plantations in Chile. Using this dataset, the objectives of this research were to (i) compare predictive precision of a range of geostatistical, parametric and non-parametric models, (ii) determine if significant gains in precision can be attained through use of regression kriging, (iii) evaluate the precision of a spatial ensemble model that utilises predictions from the five most precise models, through using the model prediction with lowest error for a given pixel and (iv) produce a map of Site Index across the study area. The five most precise models were all geostatistical and included ordinary kriging and four regression kriging models that were based on partial least squares or random forests. A spatial ensemble model constructed from these five models was the most precise of those developed (RMSE = 1.851 m, RMSE% = 6.38%) and had relatively little bias. Climatic and edaphic variables were the strongest determinants of Site Index and in particular, variables related to soil water balance were well represented within the most precise predictive models. These results highlight the utility of predicting Site Index using a range of approaches, as these can be used to construct a spatial ensemble that may be more precise than predictions from the constituent models.

The development of plant-based meat analogues has become a significant challenge for the food industry in recent years due to the increasing demand for sustainable and healthier proteins in the context of a global protein transition. Plant-based meat analogues imitate the visual, textural, and chemical properties of traditional meat products and are required to closely resemble meat to appeal to consumers. In addition, consumers demand natural, clean-label, and nutritional and healthy products. To address these challenges, the food industry must develop highly healthy, nutritious, and E-number-free meat analogue products. Understanding the functionality of each ingredient and its role in the food matrix is crucial to being a key player in the innovation of the meat analogues market. This review provides updated information on the primary ingredients utilized for the development of plant-based burger meat alternatives and their functionality. The key components of meat analogue burgers are outlined, including plant proteins, binding agents, fats and oils, flavorings, colorings, preservatives, fortificants, and clean-label considerations.

A better understanding of the expected future cyclonic activity, especially in the Mediterranean Basin in winter, is essential for developing scientifically based adaptation and mitigation methods to extreme precipitation and wind anomalies. The aim of this study is to analyze the change of winter cyclonic activity in the Mediterranean-Black Sea region, within the Atlantic–European region, at the beginning (as the recent historical period), middle and end of the 21st century. The projections are based on an ensemble of seven CMIP6 models, which showed the best consistency with NCEP/NCAR and ERA5 reanalysis, under the intermediate SSP2-4.5 and highest-emission SSP5-8.5 scenarios. The results show a consistent increase of the frequency of cyclones over Central Europe and the British Isles associated with the shift of cyclone tracks: norward from the Western Mediterranean region and southward from the Iceland Low. The latter leads to a decrease of the frequency in the north of the Atlantic–European region. At the same time, there is a reduction of the frequency of cyclones over the east of the Mediterranean Sea consistent with the decrease of cyclogenesis events. Area-averaged cyclone numbers in the Western and Eastern Mediterranean and the Black Sea subregions reduce to the end of the century under the highest-emission scenario, but not constantly and with a raise in the middle of the 21st century under both scenarios, which may be linked to the long-term multidecadal variability or regional features. In general, our study shows that the future winter cyclonic activity in the Mediterranean-Black Sea region responds unevenly to global climate changes, because regional and monthly features are important, as well as accounting for the long-term quasiperiodic variability.

This paper explores how smart cities can cope with land subsidence and liquefaction in the context of rapid urbanization in Japan. Since the 1960s, liquefaction has become an important topic in geotechnical engineering, and great efforts have been made to evaluate the resistance of soil to liquefaction. There is currently a lack of machine learning applications specifically for smart cities in areas such as geological hazards. This study uses two machine learning techniques, artificial neural networks and ensemble learning, to obtain a prediction model with high performance in predicting the bearing layer depth to improve the accuracy of geo-engineering surveys. The model was developed by analyzing actual survey data from 433 locations in Setegaya, Tokyo, by using artificial neural networks (ANNs) and bagging, respectively. The results show that machine learning has great advantages in predicting the bearing layer depth. In addition, compared with a single model such as artificial neural networks, the prediction performance of ensemble learning can be improved by about 20%. Both interdisciplinary approaches can help predict address risks and thus promote sustainable urban development, highlighting the potential of smart cities in the future.

Recently, methods to detect DoS and spoofing attacks that occur on in-vehicle networks using CAN Protocol are being studied through deep learning models such as CNN, RNN, and LSTM. These studies have produced significant results in the field of In-Vehicle Network attack detection using deep learning models. In addition, significant results are being achieved through research on applying time series-based deep learning models such as LSTM to detect DoS attacks and replay attacks occurring in in-drone networks by expanding them to drones using the UAVCAN protocol. In this paper, we conducted an experiment to detect in-drone network attacks through non-time series analysis using machine learning models and deep learning models, and through appropriate learning for each attack type, it can also be analyzed through non-time series analysis. The results showed that it was possible to detect attacks.

If we assume that: a. The four fundamental forces of nature are independent waves without rest masses, and their speeds are constant in a vacuum, just like light. b. Light or electromagnetic waves and gravity are comparable in structures. Weak and strong interactions are similar in structures. c. Light and weak interaction have the same speed c_L with spin number +1 or –1. d. Gravity and strong interaction have the same speed c_G without spin. e. The primary particles, namely electrons, electron neutrinos, and dark neutrinos in this paper, are made by the above four waves. We can find and describe some fundamental characteristics of the primary particles (e.g., their sizes, energies, and interactions) and introduce new attractive results from them (e.g., the source of the Pauli exclusion principle, the solution to the Einstein-Podolsky-Rosen paradox, and c_G slightly faster than c_L).

Ubiquitin-specific protease 2 (USP2) maintains mitochondrial integrity in culture myoblasts. In this study, we investigated molecular mechanisms underlying the protective role of USP2 on mitochondria. Knockout (KO) of the Usp2 gene or chemical inhibition of USP2 induced robust accumulation of mitochondrial reactive oxygen species (ROS), accompanied by defects in mitochondrial membrane potential, in C2C12 myoblasts. ROS removal by N-acetyl-L-cysteine restored the mitochondrial dysfunction induced by USP2 deficiency. Comprehensive RT-qPCR screening and following protein analysis indicated that both genetic and chemical inhibition of USP2 elicited a decrease of uncoupling protein 2 (UCP2) at mRNA and protein levels. Accordingly, the introduction of a Ucp2-expressing construct effectively recovered mitochondrial membrane potentials, entailing an increment of the intracellular ATP level in Usp2KO C2C12 cells. In contrast, USP2 deficiency also decreased peroxisome proliferator-activated receptor  coactivator 1 (PGC1 protein in C2C12 cells, while it upregulated Ppargc1a mRNA. Overexpression studies indicate that USP2 potentially stabilizes PGC1 in an isopeptidase-dependent manner. Given that PGC1 is an inducer of UCP2 in C2C12 cells, USP2 might ameliorate mitochondrial ROS by maintaining the PGC1–UCP2 axis in myoblasts.

This work compared the performance of three methods for constructing a regional ensemble prediction system (EPS) for wind speed forecasts: dynamical downscaling, breeding of growth modes (BGM), and blending method. The Weather Research and Forecasting (WRF) model was used to downscale the European Centre for Medium-range Weather Forecast (ECMWF) EPS. In addition, as the BGM method needs observation data for generating scaling factors, an alternative method for generating scaling factors was proposed to eliminate dependence on observation data. One-month tests between October 1st and October 30th, 2020, were implemented to evaluate the performance of three methods in the Gansu province of China. The results demonstrate that the blending method outperforms the other two methods. Furthermore, the difference in performance is evident mainly in early forecast lead time and becomes negligible as forecast time increases.

The abilities of quantitative description of noise are restricted due to its origin and only the statistical and spectral analysis methods can be applied while an exact time evolution cannot be defined or predicted. It emphasizes the challenges faced in many applications including communication systems where noise can play, on one hand, a vital role impacting signal-to-noise ratio but possessing, on the other hand, unique properties such as infinite entropy (infinite information capacity), exponentially decaying correlation function and so on. Despite the deterministic nature of chaotic systems, the predictability of chaotic signals is limited for a short time window putting them close to random noise. In this article, we propose and experimentally verify an approach to achieve Gaussian-distributed chaotic signals by processing the outputs of chaotic systems. The mathematical criteria, on which the main idea of the study is based on, is the Central Limit Theorem which states that the sum of a large number of independent random variables with similar variances approaches a Gaussian distribution. The study involves more than 40 mostly three-dimensional continuous-time chaotic systems (Chua’s, Lorenz’s, Sprott’s, memristor-based, etc.) whose output signals are analyzed according to criteria that encompass the probability density functions of a chaotic signal itself and its envelope and phase, statistical and entropy-based metrics such as skewness, kurtosis, and entropy power. We found that two chaotic signals of Chua’s and Lorenz’s systems exhibited superior performance across the chosen metrics. Furthermore, our focus extended to determining the minimum number of independent chaotic signals necessary to yield a Gaussian-distributed combined signal. The analytic and experimental results indicate that the sum of at least three non-Gaussian chaotic signals closely approximates Gaussian distribution. It allows generation of reproducible Gaussian-distributed deterministic chaos by modeling simple chaotic systems.

Rock materials failures are accompanied by the co-existence of various failure mechanisms, in-cluding rock fracturing, shearing, and compaction yield. These mechanisms manifest macro-scopically as multiple failure modes and nonlinear strength characteristics related to stress levels. Considering the limitations of current rock mechanics strength theories, which are primarily derived from single failure mechanisms, this study evaluates the applicability of alternative strength theories. Based on the extensional-strain criterion and the PMC (Paul-Mohr-Coulomb) model, a piecewise linear strength model was proposed that is suitable for analyzing multiple failure mechanisms in rocks and revealing the intrinsic mechanisms of multi-mechanism rock material failure. A multiple failure mechanism strength model in the form of inequalities was proposed, using the generalized shear stress, mean stress, and stress Lode angle as parameters. Strength tests conducted on sandstone and granite rock material samples under different stress conditions revealed distinct piecewise linear strength characteristics for both rock types, vali-dating the rationality and applicability of the multiple failure mechanism model. The findings construct a multi-mechanism failure model for rocks, providing enhanced predictive capabilities and aiding in the prevention of rock structural failures.

One of the primary causes of the mechanical seal failure is rotor vibration. Traditional dynamic seal models often would not be able to fully explaining the failure mechanisms. The seal dynamic models proposed in this paper, including those developed by the authors, prove valuable in predicting seal dynamics during operation in specific turbomachinery and in explaining the causes of seal failure. The single-mass dynamic model is suitable for analyzing contact mechanical seal and simple design dry gas seals dynamics. The two-mass dynamic model is used for investigating operational dynamics processes in classical dry gas seals under complex loading conditions. The three-mass dynamic model is used to study various complex mechanical seal types. This model is able to determine the normal operating condition range and to explain leakage mechanisms in the presence of excessive rotor vibrations.

Type 2 diabetes mellitus (T2DM) is a global health concern driven by factors such as obesity, sedentary behavior, and poor diet. This study uses data from the 2017-18 Bangladesh Demographic and Health Survey (BDHS) to analyze regional and individual predictors of diabetes and predi-abetes. Employing a Bayesian multinomial mixed-effects model, we account for regional varia-bility and individual factors like age, gender, BMI, residence, wealth, education, employment, and hypertension. Our results indicate significant regional differences and associations between de-mographic and health-related factors with diabetes risk. Younger individuals and those with higher BMI are more likely to be diabetic, while hypertension significantly increases diabetes risk. We applied machine learning (ML) models, including logistic regression, decision trees, k-nearest neighbor, linear discriminant analysis, and random forest, to classify diabetic status using these predictors, assessing their accuracy through 10-fold cross-validation. Logistic regression and linear discriminant analysis demonstrated robust performance across various response distributions. Simulation studies further examined the impact of different response distributions on model performance, revealing significant differences in classification accuracies. This approach of esti-mating parameters with a Bayesian model, applying ML for prediction, and conducting simulation studies to explore various scenarios highlights the importance of integrating these methodologies for effective diabetes prediction, providing insights for public health strategies to mitigate T2DM's impact.

Software project estimating (SPE) is a powerful but necessary step in the production of projects for software. Software project estimating includes several components, estimating software time, software resources, software costs, and software effort estimation (SEE). SEE seeks to estimate the number of "hours-person" and "months-person" of work required for developing or managing a software program. During the initial phase of the development of software, future efforts are impossible to predict. To estimate effort, many deep learning (DL) and machine learning (ML) models were previously created. For estimate, single-model techniques and ensemble methods were investigated in this research. Ensemble methods involve a combination of multiple separate models. Bagging, boosting, and voting were the ensemble methods looked into for estimation. Datasets considered for estimation were COCOMO81, COCOMONasa I, COCOMONasa II, Albrecht, Maxwell, China, Desharnais, Desharnais_1_1, Kitchenham, Boehm, and Belady. The evaluation criteria used MAE, RAE, RMSE, RRSE, and CC. The result from previous studies is that the total size of the set of data utilized is small in predicting the effort, as the largest size of the set of data used is the China dataset containing only 499 projects. So, in this study, the dataset has been merged to increase the total size of the set of data and increase the accuracy of prediction. The results indicated that the suggested merged dataset increased effort estimation accuracy.

Multilabel learning goes beyond standard supervised learning models by associating a sample with more than one class label. Among the many techniques developed in the last decade to handle multilabel learning best approaches are those harnessing the power of ensembles and deep learners. This work proposes merging both methods by combining a set of gated recurrent units, temporal convolutional neural networks, and long short-term memory networks trained with variants of the Adam optimization approach. We examine many Adam variants, each fundamentally based on the difference between present and past gradients, with step size adjusted for each parameter. We also combine Incorporating Multiple Clustering Centers and a bootstrap-aggregated decision trees ensemble, which is shown to further boost classification performance. In addition, we provide an ablation study for assessing the performance improvement that each module of our ensemble produces. Multiple experiments on a large set of datasets representing a wide variety of multilabel tasks demonstrate the robustness of our best ensemble, which is shown to outperform the state-of-the-art. The MATLAB code for generating the best ensembles in the experimental section will be made available at https://github.com/LorisNanni.

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

The conformity assessment of products or a measured value with the given standards is carried out based on the global risk of producers and consumers calculation. A product may conform to specifications but be falsely rejected as non-conforming. This is about the producer's risk. If a product doesn't meet the requirements but is falsely accepted as conforming, that poses a risk to the consumer. The conventional approach to risk assessment, which yields only a single numerical value for the global risk of producers and consumers, is naturally extended, and utilized for assessing risk in measurement models with linear regression. The outcomes of the two-dimensional extension, along a moderate scale, are the parabolas with an opening upwards. Risk surfaces were obtained through three-dimensional extension over the area limited by the moderate scale and guard band axes. Four models with different ranges of tolerance intervals were used to test this innovative method of risk assessment in linear regression. The corresponding standard measurement uncertainties are determined by applying a simplified measurement model with the use of comprehensive data on the measurement performance and by determining measurement uncertainty derived from consideration of the functional relationship obtained by linear regression analysis. Models that utilize information from linear regression analysis to determine measurement uncertainty are biased towards risks at the edges of the moderate scale. Testing the model's performances with metrics related to the confusion matrix, such as the F1 score, further substantiated this assertion. The diagnostic odds ratio has been proven to be extremely effective in identifying the curve along the guard band axis, along which the global risks of producers and consumers are at their lowest.

Facing global warming consequences is a major issue of present times. For what concerns climate, projections say that heavy rainfalls are going to increase with high probability together with temperature rise, thus also the hazard related to rainfall induced shallow landslides will likely increase in density over susceptible territories. Different modeling approaches exist and any of them is forced to make simplifications in order to reproduce landslide occurrences over space and time. Process based models can help in quantifying the consequences of heavy rainfall on the different involved processes. In this paper, a narrative review about physically-based deterministic distributed models (PBDDMs) is presented. Models were selected based on: the adoption of the infinite slope scheme (ISS), the use of a deterministic approach (i.e., input and output are treated as absolute values), the inclusion of new approaches in modeling slope stability through the ISS. Models are presented in chronological order with the aim of drawing a timeline of the evolution of PBDDMs and to give researchers and practitioners a basic knowledge on how much has been already done. Results indicate that including vegetation effects on slope stability has raised in importance over time but that there is still the need of finding an efficient way to include them, and that in the last years the literature production seems to be more focused on probabilistic approaches.

As Artificial Intelligence (AI) technology, particularly Machine Learning algorithms, becomes increasingly ubiquitous, our abilities to understand and interpret AI and machine learning algorithms are becoming increasingly desirable. Visualization has been used as a common tool to view and understand complex machine learning processes. In this paper, we will focus on developing a general framework for the visualization of machine learning models as a scalar valued multi-dimensional function to help users understand how the models behave over different viewing spaces. We first give a formal definition of the visualization problem. Interpolation-based morphing and subspace sampling techniques are applied to generate various renderings through projections and cross-sections of the model space as 3D surfaces or heatmap images. This method will be applied to two real-world datasets and applications: the diagnosis of Alzheimer's Disease (AD) using a human brain networks dataset and a real-world benchmark dataset for predicting home credit default risks. The visualizations show that different machine learning algorithms can behave quite differently under different conditions.

Explosion monitoring is performed by infrasound and seismoacoustic sensor networks that are distributed globally, regionally, and locally. However, these networks are unevenly and sparsely distributed, especially in the local scale as maintaining and deploying networks is costly. With increasing interest in smaller yield explosions, the need for more dense networks has increased. To address this issue, we propose using smartphone sensors for explosion detection as they are cost-effective and easy to deploy. Although there are studies using smartphone sensors for explosion detection, the field is still in its infancy and new technologies need to be developed. We applied a machine learning model for explosion detection using smartphone microphones. The data used were from the Smartphone High-explosion Audio Recordings Dataset (SHAReD), a collection of 326 waveforms from 70 high-explosive (HE) events recorded on smartphones, and the ESC-50 dataset, a benchmarking dataset commonly used for environmental sound classification. Two machine learning models were trained and combined into an ensemble model for explosion detection. The resulting ensemble model classified audio signals as either “explosion,” “ambient,” or “other” with true positive rates (recall) greater than 96% for all three categories.

With the development of organizational biology and forced from the EU Cosmetic Regulation (EU/1223/2009) with the complete ban of animal testing for cosmetic purposes, 3D skin models have been widely developed due to their similar physiological structure and metabolic function to native human tissue. 3D skin models for in vitro cosmetic evaluation are still promising alternative methods for evaluating phototoxicity, corrosivity and irritation. These models have been used for early screening and later validation of toxicity and efficacy evaluation by many well-known cosmetic companies. 3D skin models have become an important tool in cosmetic evaluation research. This article reviews the development of 3D skin models and their application in cosmetic evaluation. An outlook on the current application and future technological development directions in the cosmetic field is also presented.

This paper introduces a novel framework for zero-shot learning (ZSL), i.e., to recognize new categories that are unseen during training, by distilling knowledge from foundation models. Specifically, we first employ ChatGPT and DALL-E to synthesize reference images of unseen categories from text prompts. Then, the test image is aligned with text and reference images using CLIP and DINO. Finally, the predicted logits are aggregated according to their confidence to produce the final prediction.Experiments are conducted on multiple datasets, including CIFAR-10, CIFAR-100, and TinyImageNet. The results demonstrate that our model can significantly improve classification accuracy compared to previous approaches, achieving AUROC scores above 96\% across all test datasets. Our code is available at https://github.com/1134112149/MICW-ZIC.

Object classification is a crucial task in deep learning, which involves the identification and categorization of objects in images or videos. Although humans can easily recognize common objects, such as cars, animals, or plants, performing this task on a large scale can be time-consuming and error-prone. Therefore, automating this process using neural networks can save time and effort while achieving higher accuracy. Our study focuses on the classification step of human chromosome karyotyping, an important medical procedure that helps diagnose genetic disorders. Traditionally, this task is performed manually by expert cytologists, which is a time-consuming process that requires specialized medical skills. Therefore, automating it through deep learning can be immensely useful. To accomplish this, we implemented and adapted existing preprocessing and data augmentation techniques to prepare the chromosome images for classification. We used ResNet-50 convolutional neural networks and an ensemble approach to classify the chromosomes, obtaining state-of-the-art performance in the tested dataset.

The conventional machine learning (ML) algorithms are continuously advancing and evolving at a fast-paced by introducing the novel learning algorithms. ML models are continually improving using hybridization and ensemble techniques to empower computation, functionality, robustness, and accuracy aspects of modeling. Currently, numerous hybrid and ensemble ML models have been introduced. However, they have not been surveyed in a comprehensive manner. This paper presents the state of the art of novel ML models and their performance and application domains through a novel taxonomy.

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

Recommender Systems (RecSys) are crucial in managing information overload and enhancing user satisfaction across various digital platforms, including e-commerce and entertainment. Evolving from traditional models to Deep Neural Networks (DNNs) and, more recently, Large Language Models (LLMs), these systems leverage sophisticated algorithms to analyze user behaviors and preferences. LLMs, such as GPT-4, are trained on extensive datasets to comprehend and generate natural language, significantly advancing their ability to deliver personalized recommendations. This tutorial explores the transformative impact of LLMs on RecSys, discussing their development, application in handling complex datasets, and the integration of contextual insights. Real-world examples illustrate how LLMs enhance recommendation accuracy and user experience, highlighting challenges and future directions in the field.

Developing effective trend estimators is a main method to solve the online portfolio selection problem. Although the existing portfolio strategies have demonstrated good performance through the development of various trend estimators, it is still challenging to determine in advance which estimator will yield the maximum final cumulative wealth in online portfolio selection tasks. This paper studies an online ensemble approach for online portfolio selection by leveraging the strengths of multiple trend estimators. Specifically, a return-based loss function and a cross-entropy-based loss function are first designed to evaluate the adaptiveness of different trend estimators in a financial environment. On this basis, a passive aggressive ensemble model is proposed to weigh these trend estimators within a unit simplex according to their adaptiveness. Extensive experiments are conducted on benchmark datasets from various real-world stock markets to evaluate the performance. The results show that the proposed strategy achieves the state-of-the-art performance including efficiency and cumulative return.

We propose a new ensemble classification algorithm, named Super Random Subspace Ensemble (Super RaSE), to tackle the sparse classification problem. The proposed algorithm is motivated by the Random Subspace Ensemble algorithm (RaSE). The RaSE method was shown to be a flexible framework that can be coupled with any existing base classification. However, the success of RaSE largely depends on the proper choice of the base classifier, which is unfortunately unknown to us. In this work, we show that Super RaSE avoids the need to choose a base classifier by randomly sampling a collection of classifiers together with the subspace. As a result, Super RaSE is more flexible and robust than RaSE. In addition to the vanilla Super RaSE, we also develop the iterative Super RaSE, which adaptively changes the base classifier distribution as well as the subspace distribution. We show the Super RaSE algorithm and its iterative version perform competitively for a wide range of simulated datasets and two real data examples. The new Super RaSE algorithm and its iterative version are implemented in a new version of the R package RaSEn.

In this paper, we propose methods for brain tumor detection in MRI images based on ensemble learning. We build upon prior research on ensemble methods by testing the concatenation of pre-trained models: features extracted via transfer learning are merged and segmented by classification algorithms or a stacked ensemble of those algorithms. The proposed approach achieved accuracy scores of 0.98 , outperforming a benchmark VGG-16 model. Considerations to granular computing are given in the paper as well.

Artificial neural networks are highly efficient tools for numerous kinds of tasks, which include forecasting, regression, and recognizing patterns in classification and pattern recognition. An artificial neural network is a model for processing information using essential components called artificial neurons that are inspired by the human brain. Two significant aspects of delayed neural networks dynamic activity are their stability and the synchronization phenomenon. This work presents a bidirectional associative memory (BAM) incommensurate fractional-order delay neural network model. The incommensurate fractional orders are calculated within the stability region through the corresponding eigenvalues and their points of equilibrium. The involved neuron states are synchronized with each other for the calculated incommensurate stable fractional orders. The reduction of the time delay will give more relaxation time for the state variable $w_4(t)$ to be stable as compared to the state variable $w_3(t)$ due to the induction of extra activation functions. The theoretical findings of this research have significance for providing guidance and controlling the dynamic behavior of artificial neural networks.

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

The rapid advancement of large language models (LLMs), such as ChatGPT, has revolutionized natural language processing, enabling these models to generate coherent and contextually relevant text. These capabilities hold significant potential for various applications, particularly in the medical field. LLMs can assist healthcare professionals by providing accurate information, supporting diagnostic processes, and enhancing medical education. However, the implementation of LLMs in clinical settings faces several barriers, including technical limitations, ethical concerns, regulatory constraints, and practical challenges. Ensuring accuracy, reliability, and interpretability is crucial, along with addressing biases, ensuring data privacy, and establishing ethical guidelines. Future research should focus on improving training techniques, developing explainable AI methods, and creating efficient, resource-saving models. Expanding applications through domain-specific models and multi-modal integration can further unlock the potential of LLMs. By addressing these challenges and prioritizing responsible development, LLM technology can be safely and effectively integrated into various domains, driving innovation and improving outcomes. This paper explores the current state of LLM technology, its medical applications, barriers to implementation, and directions for future research and development

Accurate traffic simulation models play a crucial role in developing intelligent transport systems that offer timely traffic information to users and efficient traffic management. However, calibrating these models to represent real-world traffic conditions accurately poses a significant challenge due to the dynamic nature of traffic flow and the limitations of traditional calibration methods. This article introduces a machine learning-based approach to calibrate macroscopic traffic simulation models using real-time traffic video stream data. By leveraging computer vision technologies to extract key traffic parameters from video streams, the approach demonstrated a notable improvement in aligning the generated data from the calibrated simulation model with car sensor data, achieving an average improvement of over 50% compared to the uncalibrated macroscopic model. Moreover, there was a substantial reduction in data drift for the machine learning model integrated into the virtual transport space using vehicle-to-everything technology, resulting in a more than fourfold decrease in the average absolute error of the model.

Pain diagnosis remains a challenging task due to its subjective nature, the variability in pain expression among individuals, and the difficult assessment of the underlying biopsychosocial factors. In this complex scenario, artificial intelligence (AI) can offer the potential to enhance diagnostic accuracy, predict treatment outcomes, and personalize pain management strategies. This review aims at dissecting the current literature on computer-aided diagnosis methods. It also discusses how AI-driven diagnostic methods can be integrated into multimodal models that combine various data sources, such as facial expression analysis, neuroimaging, and physiological signals, with advanced AI techniques. Despite the significant advancements in AI technology, its widespread adoption in clinical settings faces crucial challenges. Ethical considerations related to patient privacy, biases, and lack of reliability and generalizability are the main issues. Furthermore, there is a need for high-quality real-word validation as well as the development of standardized protocols and policy rules to guide the implementation of these technologies in diverse clinical settings.

Drug-induced liver injury (DILI) stands as a significant cause of drug attrition. To mitigate clinical DILI risks, assessing drugs using human liver models is crucial since animal studies may fall short due to species-specific liver pathway variations. Cell-based preclinical hepatotoxicity testing is often pertinent. In the present study, cells from a human liver cancer line (HepG2, HepaRG) were cultured in both formats of 2D and 3D spheroids to explore their responses to drugs. Liver-specific marker expressions across cell lines and culture formats were also examined to assess disparities in drug-induced liver injury marker expressions. In cytotoxicity assays, HepG2 cells exhibited heightened sensitivity to amiodarone HCl, while HepaRG cells showed greater sensitivity to acetaminophen. Generally, 2D cultures were more responsive to drugs than 3D cultures. Consistency was observed between cytotoxicity assays and liver injury markers AST and ALT. Variations were also noted in liver cell marker secretion, with albumin and urea concentrations declining post-drug treatment, particularly with higher baseline expression in HepaRG cells and 3D cultures. Additionally, mRNA expression levels of CYP enzymes involved in hepatocellular drug metabolism were compared following treatment with enzyme inducers. CYP1A2 and CYP2C9 were not expressed in HepG2 cells. On the other hand, CYP3A4 was expressed higher in 3D culture than in 2D culture. HepaRG cells exhibited significantly increased expression of all three enzymes post-treatment. Notably, enzyme expression was notably higher in 3D cultures than in 2D cultures. Collectively, these findings suggest that HepaRG cells and 3D cultures hold promise for evaluating DILI during early-stage drug development.

To effectively preserve marine environments and manage endangered species, it is necessary to employ efficient, precise, and scalable solutions for environmental monitoring. Ecoacoustics provides several benefits as it enables non-intrusive, prolonged sampling of environmental sounds, making it a promising tool for conducting biodiversity surveys. However, analyzing and interpreting acoustic data can be time-consuming and often demands substantial human supervision. This challenge can be addressed by harnessing contemporary methods for automated audio signal analysis, which have exhibited remarkable performance due to advancements in deep learning research. This paper introduces a research investigation into developing an automatic computerized system to detect dolphin whistles. The proposed method utilizes a fusion of various resnet50 networks integrated with data augmentation techniques. Through extensive experiments conducted on a publically available benchmark, our findings demonstrate that our ensemble yields significant performance enhancements across all evaluated metrics. The MATLAB/PyTorch source code is freely available at: https://github.com/LorisNanni/

Lower Back Pain (LBP) is a disease that needs immediate attention. Person with back pain shall go immediately to doctor for treatment. Injury, excessive works and some medical conditions are result of back pain. Back pain is common to any age of human for different reasons. Due to factors such as previous occupation and degenerative disk disease the chance of developing lower back pain increases for older people. It hampers the working condition of people common reason for seeking medical treatment. The result is absence from work and is unable to normal due to pain. It creates uncomfortable and debilitating situations. Hence, detecting this disease at an early stage will assist the medical field experts to suggest counter measures to the patients. Detection of lower back pain is implemented in this paper by applying ensemble machine learning technique. This paper proposes Stacking ensemble classifier as an automated tool that will predict lower back pain tendency of a patient. Experimental result implies that the proposed method reaches an accuracy of 76.34%, f1-score of 0.76 and MSE of 0.34.

Variable-Angle Tow (VAT) laminates can improve straight fiber composites mechanical properties thanks to the application of curvilinear fibers. This characteristic allows to achieve ambitious objectives for design and performance purposes. Nevertheless, the wider design space and the higher number of parameters result in a more complex structural problem. Among the various approaches that have been used for VATs study, Carrera’s Unified Formulation (CUF) allows to obtain multiple theories within the same framework, guaranteeing a good compromise between the results accuracy and the computational cost. In this article, the linear buckling behavior of VAT laminates is analyzed through the extension of CUF 2D plate models within the Reissner’s Mixed Variational Theorem (RMVT). Results show that RMVT can better approximate the prebuckling non-uniform stress field of the plate when compared to standard approaches, thus improving the prediction of the linear buckling loads of VAT composites.

The human eye is a vital source of collecting information worldwide via daily observation. The computer science area recognizes it in research as a human-computer interaction. Human blink is an integral part of this observation as a research topic. Several studies have been conducted on eye blinking and left-right eye movements. Previous studies conducted on the eye blink consider the availability of hardware devices high in the budget, high Precision, and low light expo-sure, unlike our study, which uses low-budget devices as simple as a webcam and more versatile usable techniques, incredibly both dim and high light to name a few. This study offers the observational approach via ResNet101v2, VGG-19, and Convolution Neural Network (CNN) architectures. Outperforming both VGG-19 and CNN in this study, ResNet101v2 achieves an impressive accuracy of 98.2%. In contemporary times, deep learning in AI is taking an advanced form. This study attempts to provide a new insight into the real-world implementation of the eye blink.

Nowadays, rotor-stator mixers are widely used in the chemical process industry to carry out the dispersion and de-agglomeration processes for manufacturing the homogenous electrode slurries. Development of the process simulation models for the turbulent mixing of these slurries helps to optimize the mixing parameters such as rotational speed and dispersion time. In this work, computational fluid dynamics (CFD) approach through ANSYS Fluent are explored to determine and analyze the flow patterns, velocity fields and viscosity distribution during the dispersion of anode slurries. It utilizes a non-homogeneous Eulerian multiphase approach and the typical k-ε model to create turbulence fields and compute the mixing rate. This work significantly improves our understanding of the relationship between rotor speed, dispersion time, viscosity distribution, and mixer geometry in rotor-stator mixers.

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.

This study evaluates the effectiveness of Darknet53 and VGG16 pretrained models to develop a hybrid ensemble model named HybridPlantNet23 deep learning model for effective plant disease classification, using the publicly available dataset ‘A Dataset of Leaf Images’ from Mendeley webpage. The preprocessing of the dataset involved resizing the images to the respective requirements of the pretrained models to develop a combined datastore which served as the input. All experiments were conducted using MATLAB R2023b deep network designer interface. Model performances were evaluated based on the conventional accuracy, precision, recall, and F1-score. VGG16 achieved the highest accuracy (97.25%), precision (96.30%), recall (96.96%), and F1-score (96.55%), outperforming both Darknet53 and the ensemble HybridPlantNet23 model. Despite the advanced architecture of the ensemble model, its performance (accuracy: 95.37%, precision: 93.56%, recall: 94.20%, F1-score: 93.74%) was not significantly superior, thus highlighting scientific reasons behind this development. Recommendations for future works were provided accordingly.

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

The extent of correlation or co-movement among the returns of developed and/or emerging stock markets remains pivotal for efficiently diversifying global portfolios. This correlation is prone to variation over time as a consequence of escalating economic interdependence fostered by international trade and financial markets. In this study, we analyzed the time-varying correlation and co-movement between the JSE.JO stock market of South Africa and its developed and developing stock market partners. The Dynamic Conditional Correlation - Exponential Generalized Autoregressive Conditional Heteroscedasticity (DCC-EGARCH) methodology is employed with different multivariate distributions to explore the time-varying correlation and volatilities between the JSE.JO stock market and its partners. Based on the conditional correlation results, the JSE.JO stock market is integrated and co-moves with its partners, and the conditional correlation for all markets exhibit time-variant behavior. The conditional volatility results show that the JSE.JO stock market behaves differently from other markets, especially after 2015, indicating a positive sign for investors to diversify between JSE.JO and its partners. The highest value of conditional volatility for markets was in 2020 during the COVID-19 pandemic, representing the riskiest period that investors should avoid due to the lack of diversification opportunities during crises.

Recent advances in organoid technology have revolutionized cancer biology and thera-peutic interventions, offering personalized immunotherapy treatment. Organoids, three-dimensional cell cultures derived from patient tumors, accurately replicate the tumor microenvi-ronment, providing unprecedented insights into tumor-immune interactions and therapeutic re-sponses. In this literature-based study, we discuss various culture methods for the diverse appli-cations of organoids in cancer immunotherapy, including drug screening, personalized treatment strategies, and mechanistic studies. Additionally, we address the technological challenges asso-ciated with these methods and propose potential future solutions to accelerate the development of novel immunotherapeutic approaches. This review highlights the transformative potential of or-ganoid models in advancing preclinical cancer immunotherapy modeling, screening, and evalua-tion, paving the way for more effective and personalized cancer treatments.

The study combines two critical aspects of climate research in Nigeria. The first segment focuses on improving predictive performance of global circulation models (GCMs) employing ensemble techniques. ANN ensemble displayed significant improvement in the accuracy of climate projections, particularly in high-altitude geographic areas where traditional models exhibit limitations. Performance evaluation metrics such as Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and Nash–Sutcliffe Efficiency (NSE) demonstrate the effectiveness of the ANN multimodal ensemble. Building on the improved climate modelling, the second segment delves into a spatial and temporal analysis of rainfall and mean temperature patterns under climate change in Nigeria. By considering two Representative Concentration Pathways (RCPs), namely RCP4.5 and RCP8.5, the study utilizes dynamically downscaled GCMs obtained from the Coupled Model Intercomparison Project phase 5 (CMIP5). The Mann-Kendall test reveals significant spatiotemporal variations in climate trends across the country. The warming trend is particularly pronounced in the northern regions, with RCP8.5 showing more severe impacts compared to RCP4.5. This integrated approach not only highlights the importance of multimodal ensembles in climate modelling but also provides valuable insights into the spatial and temporal patterns of climate change to inform effective adaptation and mitigation strategies for Nigeria.

In this paper, solar irradiance and wind speed forecasts were performed considering time horizons ranging from 10 min to 60 min, under a 10 min time-step. Global horizontal irradiance (GHI) and wind speed were computed using four forecasting models (Random Forest, k-Nearest Neighbours, Support Vector Regression, and Elastic Net) to compare their performance against two alternative dynamic ensemble methods (windowing and arbitrating). Forecasting models and dynamic forecasting ensembles were implemented in Python for performance evaluation. The performance comparison between the prediction models and the dynamic ensemble methods was carried out by evaluating the RMSE, MAE, R² and MAPE, to evaluate whether the dynamic ensemble forecasting method obtained greater. According to the results obtained windowing dynamic ensemble method was the most efficient among the tested. For the wind speed data, by varying its parameter λ (from 1 to 100), a variable performance profile was obtained, where from λ =1 to λ = 74, windowing proved to be the most efficient, reaching maximum efficiency for λ = 19. Windowing was the best method for the GHI analysis, reaching its best performance for λ = 1. The efficiency gain using windowing was 0.56% when using the wind speed model and 1.96% for GHI.

The multiphase motors due to their reliability find new areas of application in the industry and transportation. Developing of any system with multiphase motors at first requires elaborate model of the system, define control mode and controllers. The model of control system for the six-phase drive is based on its conventional d-q mathematical model and indirect field-oriented control. Simulink model of six-phase drive with indirect field-oriented control and simulated with two types PID and PID fuzzy controllers. The simulation results, reflecting step response and provided speed reference law as well as load application at constant speed, are presented and analyzed. Fuzzy controller with 49 rules is considered and applied. Six-phase electric drive with field-oriented control at well-tuned PID controller has good step response specifications: settling time 0.13 s at starting without load, step response has no overshoot, small about 1 % short time decrease of speed at load of 5 Nm application. The system employing PID fuzzy controller shows slightly better results in response to torque application: the decrease in speed 1 % is eliminated in shorter time. Simulation results indicate the robustness of both systems with six-phase drive to disturbance and provide high quality transient specifications at determined reference speed.

Large Language Models (LLMs) have demonstrated promising capabilities to solve complex tasks in critical sectors such as healthcare. However, LLMs are limited by their training data which is often outdated, the tendency to generate inaccurate ("hallucinated") content and a lack of transparency in the content they generate. To address these limitations, retrieval augmented generation (RAG) grounds the responses of LLMs by exposing them to external knowledge sources. However, in the healthcare domain there is currently a lack of systematic understanding of which datasets, RAG methodologies and evaluation frameworks are available. This review aims to bridge this gap by assessing RAG-based approaches employed by LLMs in healthcare, focusing on the different steps of retrieval, augmentation and generation. Additionally, we identify the limitations, strengths and gaps in the existing literature. Our synthesis shows that proprietary models such as GPT-3.5/4 are the most used for RAG applications in healthcare. Also, there is a lack of standardized evaluation frameworks for RAG-based applications. In addition, the majority of the studies do not assess or address ethical considerations related to RAG in healthcare. It is important to account for ethical challenges that are inherent when AI systems are implemented in the clinical setting. Lastly, we highlight the need for further research and development to ensure responsible and effective adoption of RAG in the medical domain.

Molnupiravir, a prodrug known for its broad antiviral activity, demonstrated efficacy in animal models of Covid-19, prompting clinical trials where initial results indicated a significant effect against the disease. However, subsequent clinical studies did not confirm these findings, leading to the rejection of molnupiravir for permanent market authorization in many countries. This report critically assessed 19 studies published in 17 reports that investigated the efficacy of molnupiravir in animal models of Covid-19 with the purpose of determining how well the design of these models informed human studies. We found that the administered doses of molnupiravir in most studies involving animal Covid-19 models were disproportionately higher than the dose rec-ommended for human use. Specifically, when adjusted for body surface area, half of the doses of molnupiravir used in the animal studies were more than twice as high as the human dose. Addi-tionally, the drug was frequently given prophylactically or shortly after SARS-CoV-2 inoculation in these models, in contrast to clinical trials where such timing is not consistently achieved. Furthermore, the recommended five-day treatment duration for humans was exceeded in several animal studies. Collectively, we suggest that these design elements in the reported animal studies contributed to a bias favoring molnupiravir, and thus inflated expectations for its efficacy against Covid-19. Addressing these elements may offer avenues to enhance the clinical efficacy of mol-nupiravir for treatment of Covid-19 that include dose increment, early treatment, and admin-istration by inhalation along with use of molnupiravir in antiviral combination therapy.

Despite significant advancements in Artificial Intelligence (AI) and Large Language Models (LLMs), detecting and mitigating bias remains a critical challenge, particularly within social media platforms like X (formerly Twitter) and in addressing cyberbullying present on them. This research investigates the effectiveness of leading LLMs in generating synthetic biased and cyberbullying data and evaluates the proficiency of Transformer AI models in detecting bias and cyberbullying within both authentic and synthetic contexts. The study involves semantic analysis and feature engineering on a dataset of over 48,000 sentences related to cyberbullying collected from Twitter (before it became X). Leveraging state-of-the-art LLMs such as ChatGPT-4o, Pi AI, Claude 3 Opus, and Gemini-1.5, synthetic biased, cyberbullying, and neutral data were generated to deepen the understanding of bias in human-generated data. AI models including DeBERTa, Longformer, BigBird, HateBERT, MobileBERT, DistilBERT, BERT, RoBERTa, ELECTRA, and XLNet were initially trained to classify Twitter cyberbullying data and subsequently fine-tuned, optimized, and quantized for multilabel classification (detecting both biases and cyberbullying). The study's outcomes include a prototype of a hybrid application that combines a Bias Data Detector and a Bias Data Generator, validated through extensive testing.

In this study, we investigated the features of co-infection with SARS-CoV-2 and nonpathogenic strain LEV8 of coxsackievirus A7 or enterovirus A71 for Vero E6 cells and Syrian hamsters. The investigation of co-infection with SARS-СoV-2 and LEV-8 or EV-A71 in the cell model was shown that a competitive inhibitory effect for these viruses were especially significant against SARS-CoV-2. Pre-infection with enteroviruses in animals caused more than a 100-fold decrease in the levels of SARS-CoV-2 virus replication in the respiratory tracts and more rapid clearance of the lower respiratory tract from infectious SARS-CoV-2. Co-infection with SARS-CoV-2 and LEV-8 or EV-A71 also reduced the severity of clinical manifestations of the SARS-CoV-2 infection for animals. Additionally, the histological data illustrated that co-infection with nonpathogenic coxsackievirus decreased the level of pathological changes by SARS-CoV-2 in the lungs. Research into the chemokine/cytokine profile demonstrated that the studied enteroviruses efficiently triggered this part of antiviral immune response, which can be associated with significant inhibition of SARS-CoV-2 infection. These results demonstrate that there exists a strong viral interference between the studied nonpathogenic strain of coxsackievirus A7 or enteroviruses A71 and SARS-CoV-2 pathogenic for humans in vitro and in vivo.

The world health organisation (WHO) revealed approximately 280 million people in the world suffer from depression. Yet, existing studies on early-stage depression detection using machine learning (ML) techniques are limited. Prior studies have applied a single stand-alone algorithm which are unable to deal with data complexities, prone to overfitting and limited in generalisation. To this end, our paper examined the performance of several ML algorithms for early-stage depression detection using two benchmark social media datasets (D1 and D2). More specifically, we incorporated sentiment indicator to improve our model performance. Our experimental results showed that sentence bidirectional encoder representations from transformers (SBERT) numerical vectors fitted into stacking ensemble model achieved comparable F1 scores of 69% in dataset (D1) and 76% in dataset (D2). Our findings suggest that utilising sentiment indicators as additional feature for depression detection yields an improved model performance and thus, we recommend the development of depressive term corpus for future work.

Communication is a key method of expressing one's thoughts and opinions. Amongst many modalities, speech and writing are the most powerful and common forms of human communication. Analysing what and how people think has inherently been an interesting and progressive research domain. This includes bimodal sentiment analysis which is an emerging area in natural language processing (NLP) and has received a great deal of attention in recent years in a variety of areas including social opinion mining, health care, banking, and so on. At present, there are limited studies on bimodal conversational sentiment analysis as it proves to be a challenging area given the complex nature of the way humans express sentiment cues across various modalities. To address this gap, a comparison of the performance of multiple data modality models has been conducted on the MELD dataset, a widely-used dataset for benchmarking sentiment analysis within the research community. Our work then demonstrates the results of combining acoustic and linguistic representations. Lastly, our proposed neural network-based ensemble learning technique is employed over six transformer and deep learning-based models, achieving a State-Of-The-Art (SOTA) accuracy.

Software fault prediction is the very consequent research topic for software quality assurance. Data driven approaches provide robust mechanisms to deal with software fault prediction. However, the prediction performance of the model highly depends on the quality of dataset. Many software datasets suffers from the problem of class imbalance. In this regard, under-sampling is a popular data pre-processing method in dealing with class imbalance problem, Easy Ensemble (EE) present a robust approach to achieve a high classification rate and address the biasness towards majority class samples. However, imbalance class is not the only issue that harms performance of classifiers. Some noisy examples and irrelevant features may additionally reduce the rate of predictive accuracy of the classifier. In this paper, we proposed two-stage data pre-processing which incorporates feature selection and a new Rough set Easy Ensemble scheme. In feature selection stage, we eliminate the irrelevant features by feature ranking algorithm. In the second stage of a new Rough set Easy Ensemble by incorporating Rough K nearest neighbor rule filter (RK) afore executing Easy Ensemble (EE), named RKEE for short. RK can remove noisy examples from both minority and majority class. Experimental evaluation on real-world software projects, such as NASA and Eclipse dataset, is performed in order to demonstrate the effectiveness of our proposed approach. Furthermore, this paper comprehensively investigates the influencing factor in our approach. Such as, the impact of Rough set theory on noise-filter, the relationship between model performance and imbalance ratio etc. comprehensive experiments indicate that the proposed approach shows outstanding performance with significance in terms of area-under-the-curve (AUC).

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

The pursuit of Artificial Intelligence (AI) that emulates human cognitive processes is a cornerstone of ethical AI development, ensuring that emerging technologies can integrate seamlessly into societal frameworks requiring nuanced understanding and decision-making. Zero-Shot Instance Retrieval (ZSIR) stands at the forefront of this endeavour, potentially providing a robust platform for AI systems, particularly large visual language models, to demonstrate and refine cognition-aligned learning without the need for direct experience. In this paper, we critically evaluate current cognition alignment methodologies within traditional zero-shot learning paradigms, using visual attributes and word embedding generated by large AI models. We propose a unified similarity function that quantifies the cognitive alignment level, bridging the gap between AI processes and human-like understanding. Through extensive experimentation, our findings illustrate that this similarity function can effectively mirror the visual-semantic gap, steering the model towards enhanced performance in zero-shot instance retrieval. This work not only benchmarks the cognition alignment of AI, but also sets a new precedent for the development of visual language models attuned to the complexities of human cognition.}

Automating pruning tasks entails overcoming several challenges, encompassing not only robotic manipulation but also environment perception and detection. To achieve efficient pruning, robotic systems must accurately identify the correct cutting points. A possible method to define these points is to choose the cutting location based on the number of nodes present on the targeted cane. For this purpose, in grapevine pruning, it is required to correctly identify the nodes present on the primary canes of the grapevines. In this paper, a novel method of node detection in grapevines is proposed with four distinct state-of-the-art versions of the YOLO detection model: YOLOv7, YOLOv8, YOLOv9 and YOLOv10. These models were trained on a public dataset with images containing artificial backgrounds and afterwards validated on different cultivars of grapevines from two distinct Portuguese viticulture regions with cluttered backgrounds. This allowed to evaluate the robustness of the algorithms on the detection of nodes in diverse environments, compare the performance of the YOLO models used, as well as create a publicly available dataset of grapevines obtained in Portuguese vineyards for node detection. Overall, all used models were capable of achieving correct node detection on images of grapevines from the three distinct datasets. Considering the trade-off between accuracy and inference speed, the YOLOv7 model demonstrated to be the most robust in detecting nodes in 2D images of grapevines, achieving F1-Score values between 70 % and 86.5 % with inference times of around 89 ms for an input size of 1280×1280 px. Considering these results, this work contributes with an efficient approach for real-time node detection for further implementation on an autonomous robotic pruning system.

Abstract This study delved into the application of various machine learning (ML) models for the classification of lung cancer levels. Through meticulous monitoring of parameters such as minimum child weight and learning rate, efforts were made to mitigate overfitting while optimizing model performance. The Deep Neural Network (DNN) emerged as a standout performer, showcasing robust performance across training, validation, and testing stages. Ensemble methods like voting and bagging also demonstrated promising results. However, Support Vector Machine (SVM) models with the Sigmoid kernel faced challenges in achieving satisfactory performance. Overall, the investigation sheds light on the efficacy of different ML models in lung cancer level classification and underscores the importance of parameter tuning to address overfitting concerns.

This paper presents a methodology based on deep learning models and metaheuristic algorithms for the optimization of airfoils for the design of aircraft wings with large endurance. The use of AZTLI-NN (a neural network with an architecture composed of a multilayer perceptron and a variational autoencoder) is implemented for the prediction of graphs of the aerodynamic coefficients of the airfoil as a function of the angle of attack. This neural network presents good predictions of the aerodynamic coefficients, similar to the coefficients obtained with computational fluid dynamics simulations. AZTLI-NN in combination of metaheuristic algorithms and the CST profile parameterization method show excellent performance in single-objective and multi-objective profile optimization tasks.

As the primary secondary tree species in Northeast China, Quercus mongolica possesses significant ecological and economic value. This study employed the Biomod2 platform in conjunction with ArcGIS spatial analysis to assess the potential suitable habitat distribution area of Q. mongolica under current climatic conditions. Furthermore, it forecasted the distribution range and niche changes of potentially suitable habitats for Q. mongolica from 2022 to 2090, and pinpointed the key environmental factors influencing its distribution. The findings reveal that the total potential suitable area for Q. mongolica covers 74,994.792 km², predominantly spread across Inner Mongolia, Heilongjiang, Jilin, and other regions. The primary determinants of suitable area distribution were peak temperature of hottest month, lowest temperature of coldest month and altitude. Under future climate scenarios, the potentially suitable habitats of Q. mongolica are anticipated to diminish to varying extents, with the distribution center exhibiting a tendency towards northward migration. Concurrently, the overlap among different climate scenarios is predicted to expand over time. This investigation facilitates a comprehensive understanding of Q. mongolica's adaptation to climate change, enabling informed adjustments and serving as a valuable reference for the preservation and sustainable management of Q. mongolica populations.

This study investigates the effects of xylitol, a natural sugar alcohol, on tumor progression in syngeneic mouse cancer models. Xylitol has been known for its dental health benefits, but emerging evidence suggests broader biological roles, including potential anti-cancer properties. We explored xylitol's impact on two mouse cancer models: 4T1 mammary carcinoma and B16F10 melanoma. Xylitol's efficacy in inhibiting cancer cell lines and modulating tumor progression was assessed using immunocompetent female mice. The experiments involved intratumoral and peri-tumoral administration of a 20% xylitol solution in two mouse strains: BALB/c (4T1 mammary carcinoma) and C57BL/6 (B16F10 melanoma). Tumor volume, histopathology, and metabolomic analyses were conducted to gauge xylitol's influence. The study revealed that xylitol administration initially reduced tumor growth in the B16F10 melanoma model, accompanied by alterations in tumor metabolism. However, similar effects were not observed in the 4T1 mammary carcinoma model, and melanoma tumor growth re-commenced after stroma deterioration permitted xylitol solution leakage. These findings suggest that xylitol may have potential as an adjunct therapy in cancer treatment, specifically in melanoma. The differential response between the two cancer models underscores the complexity of cancer biology and the need for further investigation into xylitol's mechanisms of action and its role in cancer therapy.

Ice formation on aircraft surfaces poses significant safety risks, and current detection systems often struggle to provide accurate, real-time predictions. This paper presents the development and comprehensive evaluation of a smart ice control system using a suite of machine learning models. The system utilizes various sensors to detect temperature anomalies and signal potential ice formation. We trained and tested supervised learning models (Logistic Regression, Support Vector Machine, Random Forest), unsupervised learning models (K-means clustering), and neural networks (Multi-Layer Perceptron) to predict and identify ice formation patterns. Experimental results demonstrate that our smart system, driven by machine learning, accurately predicts ice formation in real-time, optimizes de-icing processes, and enhances safety while reducing power consumption. This solution holds the potential for improving ice detection accuracy in aviation and other critical industries requiring robust predictive maintenance.

This research centres on advancing the utilisation of a novel Deep Ensemble model called RicEns-Net for predicting crop yields through sophisticated multi-modal data engineering. Initially, data for the study were acquired from Ernst \& Young (EY), a prominent global technology and management consulting firm, as part of their annual data science challenge (EY Open Science Challenge 2023). The predictive models leverage multi-modal data by integrating radar and optical-type remote sensing data alongside meteorological data to create supplementary features essential for predicting crop yield. The primary data features are derived from spectral indices extracted from Sentinel 2 satellites, while more advanced features are generated through combinations and interactions of these fundamental features. Furthermore, data from Sentinel 1 and 3, along with meteorological measurements such as surface temperature and rainfall, account for the intricate natural factors influencing crop yield, creating a comprehensive set of data features based on existing research. To tackle the complexity introduced by numerous data features, extensive data engineering was conducted to identify the most predictive features among 100+ and mitigate the "curse of dimensionality," resulting in 15 features from 5 different modalities. The proposed RicEns-Net comprises multiple machine learning algorithms in a deep ensemble approach to leverage the best features of each of these techniques, achieving optimal performance. The proposed model achieves an MAE value of 341 kg/Ha for prediction, surpassing the performance of the EY Open Science Challenge 2023 winner models and state-of-the-art deep/machine learning approaches.

Recent advancements in Artificial Intelligence (AI) and generative models have significantly accelerated the evolution of internet services. In data centers, where data is often distributed across multiple machines, leveraging these machines to expedite the training of machine learning applications is common. However, this approach incurs substantial communication overhead. To mitigate this, data compression techniques such as quantization, sparsification, and dimension reduction are gaining attention, especially with iterative training algorithms that frequently exchange gradients. With the advancement of FPGA technology, FPGA-based bump-in-the-wire network interface controllers (smartNICs) have demonstrated notable benefits for data centers, matching ASIC switches in port-to-port latency and capacity. However, FPGA-based switches often have spare hardware resources beyond their switching functions, which are typically wasted. we propose a novel architecture that integrates FPGA-based switches with ensemble learning methods, utilizing these spare resources on FPGA-based network switches. This architecture employs random projection as a compression method to accelerate machine learning tasks while maintaining high accuracy. Our system accelerates the training process for Multilayer Perceptron (MLP) models with a speedup of 2.1-6.7 times across four high-dimensional datasets. In addition, it leverages the Hamming distance metric for k-Nearest Neighbors (kNN) classification, combining random projection with Hamming encoding, to offload large-scale classification tasks from downstream servers. This achieves a worst-case speedup of 2.3-8.7 times and a memory reduction of 3.9-27.7 times compared to CPU-based kNN classifiers using cosine distance. Our architecture addresses the challenges of high-dimensional data processing and exemplifies the potential of AI-driven solutions in accelerating and optimizing internet services. Moreover, the programmability of FPGAs allows the system to adopt various compression methods, extending its applicability. Offloading tasks to FPGAs can significantly reduce query response times, showcasing a crucial step towards achieving greater levels of autonomic computing and the rapid evolution of internet systems.

Solar radiation corresponds to fundamental parameters for solar photovoltaic (PV) technology. Reliable solar radiation prediction became valuable to design solar PV systems, performance, operatively efficient planning, safety operation, grid dispatch and financial characteristics. However, high quality ground-based solar radiation measurements are scarce, especially for very short-term time horizon. Most of the existent studies trained the machine learning (ML) model used dataset with time horizon of 1-hour or day, very fewer studies have been reported using a dataset with a 1-mitute time horizon. In this study, a comprehensive evaluation of nine ensemble learning algorithms (ELA) is performed to estimate the solar radiation in Santo Domingo with a 1-minute time horizon dataset collected from a local weather station. The ensemble learning evaluated included seven homogeneous ensembles; Random Forest (RF), Extra Tree (ET), Adaptive Gradient Boosting (AGB), Gradient Boosting (GB), Extreme Gradient Boosting (XGB), Light Gradient Boosting (LGBM), Histogram-based Gradient Boosting (HGB) and heterogeneous ensemble named as Voting and Stacking. RF, ET, GB, HGB were combined to develop Voting and Stacking and Linear Regression (LR) was adopted in the second layer of the Stacking. Five technical metrics, Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE) and Coefficient of Determination (R2) were used as criteria to determine the prediction quality of the developed ensemble algorithms. Comparison of the results indicates that the HGB algorithm offers superior prediction performance among the homogeneous ensemble learning and overall, the Stacking provides the best accuracy with metric values of MSE=3218.27, RMSE= 56.73, MAE=29.87, MAPE=10.60, R2=0.964.

With the increasing use of data-driven modeling methods new approaches to complex problems in the field of wind energy can be addressed. Topics reviewed through literature include wake modeling, performance monitoring and controls applications, condition monitoring and fault detection, and other data-driven research. Literature shows the advantages of data-driven methods reduce computational expense or complexity, particularly in the cases of wake modeling and controls, as well as various data-driven methodologies’ aptitude for predictive modeling and classification, as in the cases of fault detection and diagnosis. Significant work exists for fault detection while less work is found for controls applications. A methodology for creating data-driven wind turbine models for arbitrary performance parameters is proposed. Results are presented utilizing the methodology to create wind turbine models relating active adaptive twist to steady-state rotor thrust as a performance parameter of interest. Resulting models are evaluated by comparing root-mean-square-error (RMSE) on both the training and validation data sets, with Gaussian Process Regression (GPR), deemed an accurate model for this application. The resulting model undergoes particle swarm optimization to determine the optimal aerostructure twist shape at a given wind speed with respect to the modeled performance parameter, aerodynamic thrust load. The optimization process shows an improvement of 3.15% in thrust loading for the 10 MW reference turbine, and 2.66% for the 15 MW reference turbine.

The speed-density or flow-density relationship is a fundamental aspect of traffic flow theory. Single-regime models often face challenges in consistently fitting empirical data under diverse traffic conditions. This paper addresses the inaccuracies of single-regime models, attributing them not only to their functional forms but also to data dispersion and sample selection bias. To mitigate these issues, the data is segmented into day and night periods, leading to the creation of separate models for each. Calibration results, conducted on data from two freeways, Tehran-Karaj and Tehran-Qom, reveal distinct challenges, with the former exhibiting high dispersion and the latter showing low dispersion. Surprisingly, single-regime models demonstrate notable effectiveness when applied to distinct day and night data. Further analysis, categorizing data into day and night, results in reduced errors (20-60% improvement in R-Square), emphasizing the potential for enhanced accuracy by considering distinct regimes. Overall, the study underscores the significance of regime-specific considerations for accurate traffic flow modeling. Upon thorough evaluation, the study highlights the superiority of the neural network Multi-layer Perceptron (MLP) over traditional models. The research discusses the implications of incorporating day and night parameters into the models, emphasizing their potential for accuracy enhancement.

Predicting credit default risk is important to financial institutions, as accurately predicting the likelihood of a borrower defaulting on their loans will help to reduce financial losses, thereby maintaining profitability and stability. Although machine learning models have been used in assessing large applications with complex attributes for these predictions, there is still a need to identify the most effective techniques and to also address the issue of data imbalance. In this research, we conducted a comparative analysis of random forest, decision tree, SVM (Support Vector Machine), XGBoost (eXtreme Gradient Boosting), ADABoost (ADAptive Boosting) and multilayered perceptron with three-hidden layers, to predict credit default using loan data from LendingClub. Additionally, we also combined the model predictions using voting and stacking ensemble methods to enhance the models' performance. Furthermore, various sampling techniques was explored to handle the issue of class imbalance observed in the dataset, with the result showing that the balanced data performs better than the imbalanced data. Our proposed model achieved an accuracy of 93.7%, a precision of 95.6% and a recall of 95.5%, which shows the potential of ensemble methods in improving credit default predictions and can provide lending platforms with the tool to reduce default rates and financial losses. In conclusion, the findings from this study have broader implications for financial institutions, offering a robust approach to risk assessment beyond the Lend-ingClub dataset.

Financial fraud poses a severe threat to the integrity of corporate financial statements and market efficiency. While auditors play a crucial role in detecting and preventing such fraud, the unique characteristics of this domain, including class imbalance, high misclassification costs, and am-biguous attributes, pose significant challenges. Traditional classification algorithms may not be optimally suited for this task. This paper proposes a novel stacking ensemble learning approach to enhanced detecting of Financial Statement Scam. By combining the strengths of multiple base learners, including Random Forest, XGBoost, and Gradient Boosting Decision Trees, our model leverages their diverse predictions to improve overall performance. A Logistic Regression me-ta-learner is employed to integrate the outputs of the base learners, capturing their collective wisdom while mitigating individual weaknesses. Extensive experimentation using a real-world dataset shown the superiority of our approach, achieving remarkable recall, precision, accuracy, and area under the curve metrics. The proposed model outperforms individual base learners, under-scoring the efficacy of ensemble learning in tackling the intricate problem of financial fraud detection. This research contributes to the creation of substantial and robust fraud detection systems, fostering trust and transparency in financial markets.

In the era of digital advancements, the escalation of credit card fraud necessitates the development of robust and efficient fraud detection systems. This paper delves into the application of machine learning models, specifically focusing on ensemble methods, to enhance credit card fraud detection. Through an extensive review of existing literature, we identified limitations in current fraud detection technologies, including issues like data imbalance, concept drift, false positives/negatives, limited generalisability, and challenges in real-time processing. To address some of these shortcomings, we propose a novel ensemble model that integrates a Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Random Forest (RF), Bagging, and Boosting classifiers. This ensemble model tackles the dataset imbalance problem associated with most credit card datasets by implementing under-sampling and the Synthetic Over-sampling Technique (SMOTE) on some machine learning algorithms. The evaluation of the model utilises a dataset comprising transaction records from European credit card holders, providing a realistic scenario for assessment. The methodology of the proposed model encompasses data pre-processing, feature engineering, model selection, and evaluation, with Google Colab computational capabilities facilitating efficient model training and testing. Comparative analysis between the proposed ensemble model, traditional machine learning methods, and individual classifiers reveals the superior performance of the ensemble in mitigating challenges associated with credit card fraud detection. Across accuracy, precision, recall, and F1-score metrics, the ensemble outperforms existing models. This paper underscores the efficacy of ensemble methods as a valuable tool in the battle against fraudulent transactions. The findings presented lay the groundwork for future advancements in the development of more resilient and adaptive fraud detection systems, crucial as credit card fraud techniques continue to evolve.

Due to the recent trend of unmanned economy, retail stores have gradually reduced their service and cashier manpower. The retail product recognition becomes one of key issues for unmanned shopping. Although the success of deep neural networks has made object recognition feasible in a variety of applications, it still struggles to perform well on a large number of classes of retail products. In this paper, we propose an improved ensemble learning-based approach for retail product recognition. In the proposed approach, the object classification network is first improved through feature extraction and block attention. An ensemble model is then built by integrating multiple network models and using loss selection as model weights. In the experiments, the feasibility of our ensemble learning-based approach has been evaluated through many production items. The results demonstrate the effectiveness of the proposed approach compared with previous retail product recognition methods.

Many quantum devices signals are proportional to the number of the participating atoms that take part in the detection devices. Among these are optical magnetometers, atomic clocks, and atoms interferometers. One way to enhance the signal to noise ratio is to introduce atoms entanglement that increases the signal in a super-radiant like effect. An initial novel experiment to test the realization of atoms correlation is described here. A Cs optical magnetometer is used as a tool to test the operation of a cell-in-cavity laser and its characteristics. A vapor cell is inserted in-to an elongated external cavity of the pump laser in Littrow configuration. Higher atom polarization and reduced laser linewidth are obtained leading to better magnetometer sensitivity and signal-to-noise ratio. The Larmor frequency changes of the Free Induction Decay of optically pumped Cs atomic polarization in ambient earth magnetic field at room temperature is measured. Temporal changes in the magnetic field of less than 10 pT/Hz are measured. The first order dependence of the magnetic field on temperature and temperature gradients is eliminated, important in many practical applications. Single and gradiometric magnetometer con-figurations are presented.

Energy demand forecasting is a fundamental aspect of modern energy management. It impacts resource planning, economic stability, environmental sustainability, and energy security. This importance is making it critical for countries worldwide, particularly in cases like Türkiye, where the energy dependency ratio is notably high. The goal of this study is to propose ensemble machine learning methods such as boosting, bagging, blending, and stacking with hyperparameter tuning and k-fold cross-validation, and investigate the application of these methods for predicting Türkiye's energy demand. This study utilizes population, GDP per capita, imports and exports as input parameters based on historical data from 1979 to 2021 in Türkiye. Eleven combinations of all predictor variables were analyzed, and the best one was selected. It was observed that a very high correlation exists among population, GDP, imports, exports, and energy demand. In the first phase, the preliminary performance was investigated of 19 different machine learning algorithms using 5-fold cross-validation and measured their performance using five different metrics: MSE, RMSE, MAE, R-squared, and MAPE. Secondly, ensemble models were constructed by utilizing individual machine learning algorithms, and the performance of these ensemble models was compared with both each other and the best-performing individual machine learning algorithm. The analysis of the results revealed that placing Ridge as the meta-learner and using ET, RF and Ridge as the base learners in the stacking ensemble model produced superior results compared to the other models across performance metrics. It is anticipated that the findings of this research can be applied globally and prove valuable for energy policy planning in any country. The results obtained not only highlight the accuracy and effectiveness of our predictive model but also underscore the broader implications of this study within the framework of the United Nations' Sustainable Development Goals (SDGs).

This paper presents a study of an automated system for identifying planktic foraminifera at the species level. The system uses a combination of deep learning methods, specifically Convolutional Neural Networks (CNNs), to analyze digital images of foraminifera taken at different illumination angles. The dataset is composed of 1437 groups of sixteen grayscale images, one group for each foraminifer, that are then converted to RGB images with various processing methods. These RGB images are fed into a set of CNNs, organized in an Ensemble Learning (EL) environment. The ensemble is built by training different networks using different approaches for creating the RGB images. The study finds that an ensemble of CNN models trained on different RGB images improves the system's performance compared to other state-of-the-art approaches. The proposed system was also found to outperform human experts in classification accuracy.

Talbot effect is a self-imaging or lensless imaging phenomenon of a periodic grating illuminated by a collimated light beam at regular distances from the grating. Research on the Talbot effect has recently made significant strides thanks to the quick development of optical superlattices. The emergence of various applications of this effect in fields such as optics, acoustics, X-ray, plasmonics, and information processing has led to the increasing importance of obtaining a Talbot carpet with the use of different structures. In this paper, we investigate the Talbot effect that originates from the tunneling effect between an ensemble of vertically coupled cylindrical quantum dots (QDs). The Talbot carpet can be manipulated by changing the parameters of the QD system. In the current paper, two modified Pöschl-Teller potentials were used to model the QDs ensemble. The exciton’s lifetime and tunneling time’s dependence on the first QD’s potential half-width is found for a fixed value of the external electric field. The nonlinear changes in the refractive index and absorption spectrum dependent on the tunneling effect are obtained. Afterward, the Talbot carpet formation is investigated, particularly the dependences of the formed periodic wavefront’s visibility on medium length, coupling field’s strength, and tunneling parameter. Finally, we have observed the intensity distribution of the diffraction field at Talbot half-distance.

Ransomware is one of the most dangerous types of malware, which is frequently intended to spread through a network to damage the designated client by encrypting the client’s vulnerable data. Conventional signature-based ransomware detection technique falls behind because it can only detect known anomalies. When it comes to new and non-familiar ransomware traditional system unveils huge shortcomings. For detecting unknown patterns and sorts of new ransomware families,behavior-based anomaly detection approaches are likely to be the most efficient approach. In the wake of this alarming condition, this paper presents an ensemble classification model consisting of three widely used machine learning techniques that include Decision Tree (DT), RandomForest (RF), and K-nearest neighbor (KNN). To achieve the best outcome ensemble soft voting and hard voting techniques are used while classifying ransomware families based on attack attributes. Performance analysis is done by comparing our proposed ensemble models with standalone models on behavioral attributes based ransomware dataset..

The relative operating characteristic (ROC) curve is a popular diagnostic tool in forecast verification, with the area under the ROC curve (AUC) used as a verification metric measuring the discrimination ability of a forecast. Along with calibration, discrimination is deemed as a fundamental probabilistic forecast attribute. In particular, in ensemble forecast verification, AUC provides a basis for the comparison of potential predictive skill of competing forecasts. While this approach is straightforward when dealing with forecasts of common events (e.g. probability of precipitation), the AUC interpretation can turn out to be oversimplistic or misleading when focusing on rare events (e.g. precipitation exceeding some warning criterion). How should we interpret AUC of ensemble forecasts when focusing on rare events? How can changes in the way probability forecasts are derived from the ensemble forecast affect AUC results? How can we detect a genuine improvement in terms of predictive skill? Based on verification experiments, a critical eye is cast on the AUC interpretation to answer these questions. As well as the traditional trapezoidal approximation and the well-known bi-normal fitting model, we discuss a new approach which embraces the concept of imprecise probabilities and relies on the subdivision of the lowest ensemble probability category.

While the use of crime data has been widely advocated in the literature, its availability is often limited to large urban cities and isolated databases tend not to allow for spatial comparisons. This paper presents an efficient machine learning framework capable of predicting spatial crime occurrences, without using past crime as a predictor, and at a relatively high resolution: the U.S. Census Block Group level. The proposed framework is based on an in-depth multidisciplinary literature review allowing the selection of 188 best-fit crime predictors from socio-economic, demographic, spatial, and environmental data. Such data are published periodically for the entire United States. The selection of the appropriate predictive model was made through a comparative study of different machine learning families of algorithms, including generalized linear models, deep learning, and ensemble learning. The gradient boosting model was found to yield the most accurate predictions for violent crimes, property crimes, motor vehicle thefts, vandalism, and the total count of crimes. Extensive experiments on real-world datasets of crimes reported in 11 U.S. cities demonstrated that the proposed framework achieves an accuracy of 73 and 77% when predicting property crimes and violent crimes, respectively.

Developments in artificial intelligence techniques allow for an improvement in sustainable mobility strategies with particular reference to energy consumption estimates of electric vehicles (EVs). This research proposes a vehicle energy model developed on the basis of Deep Neural Network (DNN) technology. The study also explores the potential application of the model developed for the movement data of new vehicles in the province of Enna, Sicily, Italy. which is characterized by numerous attractors and the increasing number of hybrid and electric cars circulating. The energy model for electric vehicles shows high accuracy and versatility, requiring vehicle velocity and acceleration as input data to predict energy consumption. The research article also provides recommendations for the energy modeling of electric vehicles and outlines additional steps for model development. The implemented methodological approach and its results can be used by transport decision makers to plan new transport policies in Italian cities aimed at optimizing vehicle charging infrastructure. They can also help vehicle users accurately estimate energy consumption, generate maps, and identify locations with the highest energy consumption.

EIMIs face the challenge of adapting to the Paris Agreement and the European Green Deal to achieve carbon neutrality. This change is being driven by consumer interest in low-carbon products, regulatory requirements from climate agreements and investors prioritizing sustainability. This pressure is pushing companies to go beyond short-term financial gains and integrate sustainability into their business. The growing awareness of the environmental impact of business models (BM) has fueled the development of Sustainable Business Models (SBMs). This study aims to link the discussion on the role of SBMs in the drivers of decarbonization, to improve the understanding of how the drivers can be integrated and enable new BMs for EIMIs. Based on a structured literature review, semi-structured interviews were conducted in the EIMIs. The study identifies BM-components that are influenced by these drivers and require sustainable business model innovation (SBMI). The results show that decarbonization drivers have a significant impact on all BM components. Experts emphasize the importance of collaborative approaches and cooperation throughout the value chain. This research elaborates on the importance of systematic analysis to understand how companies can effectively manage decarbonization drivers and suggests in-depth exploration within BM-research to uncover potential SBM design options.

Significant Wave Height(SWH) is a crucial parameter in oceanographic research, essential for understanding various marine and atmospheric processes. Traditional methods for obtaining SWH, such as ship-based and buoy measurements, face limitations like limited spatial coverage and high operational costs. With the advancement of Global Navigation Satellite Systems reflectometry(GNSS-R) technology, a new method for retrieving SWH has emerged, demonstrating promising results. This study utilizes Radio occultation sounder(GNOS) data from the FY-3E satellite and incorporates the latest Vision Transformer(ViT) technology to investigate GNSS-R-based SWH retrieval. We designed and evaluated various deep learning models, including ANN-Wave, CNN-Wave, Hybrid-Wave, Trans-Wave, and ViT-Wave. Through comparative training using ERA5 data, the ViT-Wave model was identified as the optimal retrieval model. The ViT-Wave model achieved an Root Mean Square Error(RMSE) accuracy of 0.4052 meters and Mean Absolute Error(MAE) accuracy of 0.2700 meters, significantly outperforming both traditional methods and newer deep learning approaches utilizing Cyclone Global Navigation Satellite Systems(CYGNSS) data. These results underscore the potential of integrating GNSS-R technology with advanced deep learning models to enhance SWH retrieval accuracy and reliability in oceanographic research.

The success of deep learning (DL) in offline brain-computer interfaces (BCIs) has not yet translated into efficient online applications. This is due to three primary challenges. First, most DL solutions are designed for offline decoding, making the transition to online decoding complex and unclear. Second, the use of sliding windows in online decoding increases the computational complexity of DL training. Third, DL models typically require large amounts of training data, which are often scarce in BCI applications. To address these issues and enable real-time decoding, even across different subjects without calibration data, we first introduce a novel approach called real-time adaptive pooling (RAP). RAP modifies the pooling layers of existing offline DL models towards the online decoding requirements. Additionally, it significantly reduces the computational demand during training by jointly decoding consecutive windows. To reduce the amount of training data required, our approach leverages different levels of domain adaptation. We show how different settings enable different adaptation solutions. The results demonstrate that our approach is both powerful and can be calibration-free, providing a robust and practical solution for real-time BCI applications. These findings pave the way for the development of co-adaptive and highly efficient DL-based online BCI systems.

A review of quantitative risk assessment (QRA) models of L. monocytogenes in produce was carried out, with the objective of appraising and contrasting the effectiveness of the control strategies placed along the food chains. Despite nine of the thirteen QRA models recovered focused on fresh or RTE leafy greens, none of them represented important factors or sources of contamination in the primary production, such as type of cultivation, water, fertilisers or irrigation method/practices. Cross-contamination at processing and during consumer’s handling was modelled using transfer rates, which were shown to moderately drive the final risk of listeriosis; highlighting therefore the importance of accurately representing the transfer coefficient parameters. Many QRA models coincided in the fact that temperature fluctuations at retail or temperature abuse at home were key factors contributing to increasing the risk of listeriosis. In addition to a primary module that could help assess current on-farm practices and potential control measures, future QRA models for minimally-processed produce should also contain a refined sanitisation module able to estimate the effectiveness of various sanitisers as a function of type, concentration and exposure time. Finally, L. monocytogenes growth in the products down the supply chain should be estimated by using realistic time-temperature trajectories, and validated microbial kinetic parameters, both of them currently available in the literature.

Automated medical diagnosis is one of the important machine learning applications in the domain of healthcare. In this regard, most of the approaches primarily focus on optimizing the accuracy of classification models. In this research, we argue that unlike general-purpose classification problems, medical applications, such as chronic kidney disease (CKD) diagnosis, require special treatment. In the case of CKD, apart from model performance, other factors such as the cost of data acquisition may also be taken into account to enhance the applicability of the automated diagnosis system. In this research, we have proposed two techniques for cost-sensitive feature ranking. An ensemble of decision tree models is employed in both the techniques for computing the worth of a feature in the CKD dataset. An automatic threshold selection heuristic is also introduced which is based on the intersection of features’ worth and their accumulated cost. A set of experiments are conducted to evaluate the efficacy of the proposed techniques on both tree-based and non-tree based classification models. The proposed approaches are also evaluated against several comparative techniques. Furthermore, it is demonstrated that the proposed techniques select around 1/4^th of the original CKD features while reducing the cost by a factor of 7.42 of the original feature set. Based on the extensive experimentation it is concluded that the proposed techniques employing feature-cost interaction heuristic tend to select feature subsets that are both useful and cost-effective.

The integration of the Internet of Things (IoT) and Distributed Computer Systems (DCS) is transforming business models across industries. IoT devices enable real-time monitoring of equipment and processes, reducing downtime and enhancing efficiency. In the case, manufacturing companies use IoT sensors to monitor machinery, predict failures, and schedule maintenance. Also, automation via IoT, reduces manual intervention, resulting in boosted productivity in smart factories and automated supply chains. IoT devices generate thus vast amounts of data, which businesses analyze to gain insights into customer behavior, operational inefficiencies, and market trends. In turn, distributed computer systems process this data, providing actionable insights and enabling advanced analytics and machine learning for future trend predictions. While, IoT facilitates personalized products and services by collecting data on customer preferences and usage patterns, enhancing satisfaction and loyalty, IoT devices support new customer interactions, like wearable health devices, and enable subscription-based and pay-per-use models in transportation and utilities. Conversely, real-time monitoring enhances security, as distributed systems quickly respond to threats, ensuring operational safety. It also aids regulatory compliance by providing accurate operational data. In this way, this study, through a Bibliometric Literature Review (LRSB) of 91 screened pieces of literature, aims at ascertaining to what extent the aforementioned capacities enhance business models. The study concludes that those systems leverage businesses, promoting competitive edge, continuous innovation, and adaptability to market dynamics. A review of 91 academic documents from the Scopus database highlights these impacts.

Due to the increasing use of computer equipment, institutions and companies face challenges, such as sensitive data leaks and the spread of hate speech, which have severe consequences for organizations and their employees. Addressing these challenges is essential to avoid financial losses, reputational damage, and impacts on the psychological health of those involved. This paper presents a solution based on microservices for monitoring computers used by employees in organizations, including capturing information from the equipment using spyware techniques and a web application for managing alerts. The solution seeks to detect data leaks, suspicious behaviour, and hate speech. The results of the evaluation indicate that the proposed solution has an efficient data capture time and can identify unwanted behaviour in a short period. The solution also includes applying prediction models to detect hate speech, achieving an average accuracy of approximately 87%. The performance, scalability, and security evaluation demonstrate that the solution is suitable for dealing with data leakage and hate speech challenges in the corporate environment.

Appropriate animal models of human diseases are a cornerstone in the advancement of science and medicine. To create animal models of neuropsychiatric and neurobehavioral diseases such as ASD necessitates the development of sufficient neurobehavioral measuring tools to translate human behavior to expected measurable behavioral features in animals. Indeed, at least in rodents, adequate neurobehavioral and neurological tests have been developed. Since ASD is characterized by a number of specific behavioral trends with significant severity, animal models of autistic-like behavior have to demonstrate the specific characteristic features, namely impaired social interactions, and communication, restricted, repetitive behavioral patterns with association to several additional impairments such as somatosensory, motor and memory impairments. Thus, an appropriate model must show behavioral impairment of a minimal number of neurobehavioral characteristics using an adequate number of behavioral tests. The proper animal models enable the study of ASD like-behavior from the etiologic, pathogenetic and therapeutic aspects. From the etiologic aspects, models have been developed by the use of immunogenic substances like polyinosinic-polycytidylic acid (PolyIC), Lipopolysaccharide (LPS) and propionic acid or other well-documented immunogens or pathogens, like mycobacterium tuberculosis. Another approach is the use of chemicals like valproic acid, Polychlorinated biphenyls (PCBs), organophosphate pesticides - chlorpyrifos (CPF) and others. These substances were administered either prenatally, generally after the period of major organogenesis, or, especially in rodents, during the early postnatal life. In addition, using modern genetic manipulation methods, genetic models have been created of almost all human genetic diseases that are manifested by autistic like behavior (i.e. fragile X, Rett syndrome, SHANK gene mutation Neuroligin genes and others). Ideally, we should not only evaluate the different behavioral modes affected by the ASD-like behavior but also assess the severity of the behavioral deviations by an appropriate scoring system, as applied to humans.

Count data analysis presents unique challenges due to its discrete nature, often exhibiting excessive zeros and overdispersion. To address these complexities, count models, such as Poisson regression and Negative Binomial regression, have been developed, enabling modeling and prediction of count-based phenomena. Additionally, it’s important to notice that zero inflation, a phenomenon commonly observed in count data, requires specialized techniques for robust analysis. This article provides an overview of count data and count models, explores zero inflation, introduces Likelihood Ratio Tests, and explains how the Vuong Test can be used as a model selection criteria. Furthermore, we created a Vuong Test implementation from scratch using the Python programming language. This implementation enhances the accessibility and applicability of the Vuong Test in real-world scenarios, providing a valuable contribution to the academic community, since Python didn’t have an implementation of this statistical test.

Previously, we described a 19-base pair double-stranded RNA with 3'-trinucleotide overhangs, acting as immunostimulatory RNA (isRNA). This molecule demonstrated notable antiproliferative effects on cancer cells, inhibited tumor growth, and elicited immunostimulatory and antiviral responses by inducing cytokine and interferon production. Within this study, we compared the efficiency of lung fibrosis development, initiated in mice by BLM or LPS using different schemes of induction. Then we compared the effect of isRNA used in a preventive or therapeutic regimen on the development of fibrosis in selected BLM- and LPS-induced mouse models and showed that isRNA can be used in pathological conditions accompanied by the development of inflammation and the risk of fibrosis formation, without adverse side effects. Prophylactic regimen of isRNA application is beneficial for prevention of the development of pulmonary fibrosis.