Search Results (1,243)

Identifying and reducing customer churn have become a priority for financial institutions seeking to retain clients. Our research focuses on customer churn rate analysis using advanced machine learning (ML) techniques, leveraging a synthetic dataset sourced from the Kaggle platform. The dataset undergoes a preprocessing phase to select variables directly impacting customer churn behavior. SMOTETomek, a hybrid technique that combines oversampling of the minority class (churn) with SMOTE and the removal of noisy or borderline instances through Tomek links, is applied to balance the dataset and improve class separability. Two cutting-edge ML models are applied—random forest (RF) and the Light Gradient-Boosting Machine (LGBM) Classifier. To evaluate the effectiveness of these models, several key performance metrics are utilized, including precision, sensitivity, F1 score, accuracy, and Brier score, which helps assess the calibration of the predicted probabilities. A particular contribution of our research is on calibrating classification probabilities, as many ML models tend to produce uncalibrated probabilities due to the complexity of their internal mechanisms. Probability calibration techniques are employed to adjust the predicted probabilities, enhancing their reliability and interpretability. Furthermore, the Shapley Additive Explanations (SHAP) method, an explainable artificial intelligence (XAI) technique, is further implemented to increase the transparency and credibility of the model’s decision-making process. SHAP provides insights into the importance of individual features in predicting churn, providing knowledge to banking institutions for the development of personalized customer retention strategies. Full article

Individual physiotherapy is crucial in treating patients with various pain and health issues, and significantly impacts abdominal surgical outcomes and further medical problems. Recent technological and artificial intelligent advancements have equipped healthcare professionals with innovative tools, such as sensor systems and telemedicine equipment, offering groundbreaking opportunities to monitor and analyze patients’ physical activity. This paper investigates the potential applications of mobile accelerometers in evaluating the symmetry of specific rehabilitation exercises using a dataset of 1280 tests on 16 individuals in the age range between 8 and 75 years. A comprehensive computational methodology is introduced, incorporating traditional digital signal processing, feature extraction in both time and transform domains, and advanced classification techniques. The study employs a range of machine learning methods, including support vector machines, Bayesian analysis, and neural networks, to evaluate the balance of various physical activities. The proposed approach achieved a high classification accuracy of 90.6% in distinguishing between left- and right-side motion patterns by employing features from both the time and frequency domains using a two-layer neural network. These findings demonstrate promising applications of precise monitoring of rehabilitation exercises to increase the probability of successful surgical recovery, highlighting the potential to significantly enhance patient care and treatment outcomes. Full article

In analyzing the decoupling of emissions from economic growth, current literature foregoes the nonlinear complexities of macroeconomic systems, leading to ineffective energy transition policies, specifically for developing countries. This study focuses on the Indian energy–economy–emission nexus to establish a control system that internalizes inflation, trade openness, and fossil fuel imports with economic growth and macro-emissions to visualize the complex pathways of decoupling. Through long-term cointegration and vector error correction modeling, it was found that GDP and energy affect capital, inflation and energy imports, which are locked in a long-run negative feedback loop that ultimately increases emissions. Capital growth enables decoupling at 0.7% CO₂ emissions reduction for every 1% capital growth, while 1% inflation growth inhibits decoupling by increasing CO₂ emissions by 0.8%. A cybernetic fractional circuit of R-C elements and operational amplifiers was utilized to examine the delay of pulses from GDP to the loop elements, which revealed that capital is periodic with GDP pulses. However, inflation, being aperiodic with the clock pulses of GDP, causes the pulse-width of capital to decrease and fossil fuel imports to increase. Through the circuital model, it was possible to determine the exact policy intervention schedule in business cycle growth and recession phases that could build clean energy capital and limit inflation-induced recoupling. Full article

Fake news is one of the biggest challenging issues in today’s technological world and has a huge impact on the population’s decision-making and way of thinking. Disinformation can be classified as a subdivision of fake news, the main purpose of which is to manipulate and generate confusion among people in order to influence their opinion and obtain certain advantages in multiple domains (politics, economics, etc.). Propaganda, rumors, and conspiracy theories are just a few examples of common disinformation. Therefore, there is an urgent need to understand this phenomenon and offer the scientific community a paper that provides a comprehensive examination of the existing literature, lay the foundation for future research areas, and contribute to the fight against disinformation. The present manuscript provides a detailed bibliometric analysis of the articles oriented towards disinformation detection, involving high-performance machine learning and deep learning algorithms. The dataset has been collected from the popular Web of Science database, through the use of specific keywords such as “disinformation”, “machine learning”, or “deep learning”, followed by a manual check of the papers included in the dataset. The documents were examined using the popular R tool, Biblioshiny 4.2.0; the bibliometric analysis included multiple perspectives and various facets: dataset overview, sources, authors, papers, n-gram analysis, and mixed analysis. The results highlight an increased interest from the scientific community on disinformation topics in the context of machine learning and deep learning, supported by an annual growth rate of 96.1%. The insights gained from the research bring to light surprising details, while the study provides a solid basis for both future research in this area, as well for the development of new strategies addressing this complex issue of disinformation and ensuring a trustworthy and safe online environment. Full article

This article deals with a mutual comparison of indexable cutting inserts of the CNMG 120408 type from two different manufacturers during the machining of hardened steel AISI 4337 and austenitic stainless steel AISI 316 L. The main goal is to analyse the different wear processes depending on the difference in the manufacturer’s design and also depending on the properties of the different machined materials. The progress of the wear of the main spine of the tool, the types of wear and the service life of the cutting edge were monitored, with the achievement of the critical value VB_max = 300 µm being the standard. In addition to the wear of the inserts, the production of chips was monitored in terms of their shape, average size and number of chips per 100 g of chips produced. In order to understand the relationships arising from the obtained data, an SEM equipped with an elemental analyser was used to analyse the coating layers and the substrate of the unworn inserts and the types of wear and the intensity of the surface damage of the worn inserts. A several-fold difference in the lifetime of the cutting edge was found, both in terms of design and in terms of the selected machined material, while in both cases the cutting edge with Al₂O₃ and TiCN layers of half thickness achieved a better result in liveness. From the point of view of chip formation, very similar results in shape and average length were observed despite the different designs of chip breakers. Cutting inserts with half the thickness of the coating layers achieved longer cutting edge life in the non-primary material application compared to the target workpiece material. At the same time, it was observed that a thinner coating layer has a positive effect on chip formation in terms of its length and shape. Full article

This paper introduce advancements in agricultural robotics in response to the increasing demand for automation in agriculture. Our research aims to develop humancentered agricultural robotic systems designed to enhance efficiency, sustainability, and user experience across diverse farming environments. We focus on essential applications where human labor and experience significantly impact performance, addressing four primary robotic systems, i.e., harvesting robots, intelligent spraying robots, autonomous driving robots for greenhouse operations, and multirobot systems, as a method to expand functionality and improve performance. Each system is designed to operate in unstructured agricultural environments, adapting to specific needs. The harvesting robots address the laborintensive demands of crop collection, while intelligent spraying robots improve precision in pesticide application. Autonomous driving robots ensure reliable navigation within controlled environments, and multirobot systems enhance operational efficiency through optimized collaboration. Through these contributions, this study offers insights into the future of agricultural robotics, emphasizing the transformative potential of integrated, experience-driven intelligent solutions that complement and support human labor in digital agriculture. Full article

The adversarial robustness of image quality assessment (IQA) models to adversarial attacks is emerging as a critical issue. Adversarial training has been widely used to improve the robustness of neural networks to adversarial attacks, but little in-depth research has examined adversarial training as a way to improve IQA model robustness. This study introduces an enhanced adversarial training approach tailored to IQA models; it adjusts the perceptual quality scores of adversarial images during training to enhance the correlation between an IQA model’s quality and the subjective quality scores. We also propose a new method for comparing IQA model robustness by measuring the Integral Robustness Score; this method evaluates the IQA model resistance to a set of adversarial perturbations with different magnitudes. We used our adversarial training approach to increase the robustness of five IQA models. Additionally, we tested the robustness of adversarially trained IQA models to 16 adversarial attacks and conducted an empirical probabilistic estimation of this feature. Full article

The main computationally expensive task of realistic computer graphics is the calculation of global illumination. Currently, most of the lighting simulation methods are based on various types of Monte Carlo ray tracing. One of them, the Langevin Monte Carlo ray tracing, generates samples using the time series of a system of the Langevin dynamics. The method seems to be very promising for calculating the global illumination. However, it remains poorly studied, while its analysis could significantly speed up the calculations without losing the quality of the result. In our work, we analyzed the most computationally expensive operations of this method and also conducted the computational experiments demonstrating the contribution of a particular operation to the convergence speed. One of our main conclusions is that the computationally expensive drift term can be dropped because it does not improve convergence. Another important conclution is that the preconditioning matrix makes the greatest contribution to the improvement of convergence. At the same time, calculation of this matrix is not so expensive, because it does not require calculating the gradient of the potential. The results of our study allow to significantly speed up the method. Full article

In the agricultural sector, where factors like the type of agriculture, management techniques, and access to funding are critical, disadvantaged people face significant barriers to employment. This study investigated the effects of these factors, especially with regard to sustainability and social farming, on the employment of disadvantaged persons in the Czech Republic. We sent questionnaires to 2036 agricultural businesses within the Czech Republic, and the data we received were sorted and analyzed. There was a favorable relationship between farm size and employment chances. Disadvantaged people were more likely to be hired by large farms, especially those larger than 250 hectares. Furthermore, mixed-production farms were more capable of employing disadvantaged persons, unlike conventional farms, which reached their maximum employment levels at one, three, or six workers. Organic farming had a more even distribution, while biodynamic farming showed limited capacity to employ disadvantaged persons. Farms involved in fundraising had fewer farms but employed more disadvantaged persons (number of employees peaked at two, four, and six), while farms that did not engage in fundraising hired more disadvantaged individuals (peaked at one and three employees). The motivations for employing disadvantaged persons were primarily social concerns, as well as labor shortages and economic and innovative factors. These findings show the importance of agricultural enterprises using these factors to improve the social and economic well-being of disadvantaged persons. Full article

Recent research has drawn attention to the ambiguity surrounding the definition and learnability of Out-of-Distribution recognition. Although the original problem remains unsolved, the term “Out-of-Model Scope” detection offers a clearer perspective. The ability to detect Out-of-Model Scope inputs is particularly beneficial in safety-critical applications such as autonomous driving or medicine. By detecting Out-of-Model Scope situations, the system’s robustness is enhanced and it is prevented from operating in unknown and unsafe scenarios. In this paper, we propose a novel approach for Out-of-Model Scope detection that integrates three sources of information: (1) the original input, (2) its latent feature representation extracted by an encoder, and (3) a synthesized version of the input generated from its latent representation. We demonstrate the effectiveness of combining original and synthetically generated inputs to defend against adversarial attacks in the computer vision domain. Our method, TRust Your GENerator (TRYGEN), achieves results comparable to those of other state-of-the-art methods and allows any encoder to be integrated into our pipeline in a plug-and-train fashion. Through our experiments, we evaluate which combinations of the encoder’s features are most effective for discovering Out-of-Model Scope samples and highlight the importance of a compact feature space for training the generator. Full article

This study aims to address the persistent regional economic disparities in Romania by evaluating economic performance through Panel Autoregressive Distributed Lag (pARDL) and panel quantile regression (PQR) models. The analysis focuses on the impact of key economic variables, including research and development expenditures (CTCRD), IT infrastructures (IT), the number of universities (FCL), and the average number of employees (NMSP), on regional gross domestic product (GDPR). Using data from the Romanian National Institute of Statistics for the period 2003–2022, this research seeks to understand how targeted investments and policy interventions can stimulate growth and reduce inequalities across regions. The findings highlight the important role of R&D, IT infrastructures, and technological advancements in driving economic growth, especially in less developed areas. The study also emphasizes the importance of region-specific strategies in fostering sustainable growth, promoting economic resilience, and bridging the gap between more and less prosperous regions. Full article

Understanding user challenges with light dosimeters is crucial for designing more acceptable devices and advancing light exposure research. We systematically evaluated the usability and acceptability of a light dosimeter (lido) with 29 participants who wore the dosimeter near the corneal plane of the eye for 5 days. Common reasons for not wearing the dosimeter included exercise, recharging, wet environments, public places, and discomfort. Despite these issues, participants adhered to using the dosimeter with high compliance (89% of recording time). Our findings revealed a significant discrepancy between mean (300 lx_mEDI) and median (51 lx_mEDI) melanopic equivalent daylight illuminance. This discrepancy indicates that the participants were exposed to significantly lower light levels most of the time. Specifically, participants were exposed to light levels above 250 lx_mEDI for only 14% of their wearing time. This highlights the need for increased exposure to recommended light levels. In the evening, participants were exposed to less than the recommended 10 lx_mEDI for 58% of their wearing time, which is in line with the guidelines for reducing light exposure before sleep. This study highlights the urgent need for strategies to increase daily light exposure that are more in line with circadian health recommendations. Full article

This paper introduces an autonomous self-propelled Napa cabbage harvester, designed to significantly improve the efficiency and effectiveness of the traditionally labor-intensive harvesting process. The harvester integrates three key modules: a cutting, an attitude control, and a loading module. The cutting module is equipped with an attitude control module that ensures precise severance of the Napa cabbage stems, minimizing damage to the crop and maintaining product quality. The attitude control module employs a backstepping-based force control that continuously adjusts the cutting angle and height to ensure consistent cutting precision, even on uneven terrain, thereby optimizing the quality of the Napa cabbages. The loading module automates the collection and transfer of harvested Napa cabbages into storage, significantly reducing the physical burden on workers and improving operational efficiency. Field experiments demonstrated improvements, including a 42–66% reduction in task time compared to manual harvesting, as well as a 37% increase in cutting accuracy through the use of autonomous control. The proposed system presents a comprehensive solution for enhancing productivity, reducing labor demands, and maintaining high crop quality in Napa cabbage harvesting, offering a practical approach to modernizing agricultural practices. Full article

Background: There is paucity of data in the available medical literature regarding the parameters of the volumetric perfusion of pancreas grafts. Methods: From 5 February 2016 to 23 December 2021, we performed perfusion computed tomography in 41 patients at different times after simultaneous pancreas and kidney transplantation. The study group consisted of 18 men (44%) and 23 women (56%) with a long history of type 1 diabetes mellitus complicated by terminal chronic renal failure. The results of the perfusion computed tomography of the pancreas graft were studied, and the effects of post-transplantation timing and graft revascularization peculiarities on volumetric perfusion parameters were evaluated. Results: The median arterial blood flow, arterial blood volume, and permeability of the pancreas graft were 115.1 [99.7;130.3] mL/100 mL/min, 46.7 [37.4;56.9] mL/min, and 8.6 [4.1;11.4] mL/100 mL/min, respectively. No statistically significant differences in the averaged perfusion values were found in the head, body, and tail of the pancreas graft. The post-transplantation timing and the number of arteries involved in graft revascularization did not have a significant effect on the volumetric perfusion of the graft. Conclusion: The volumetric perfusion results of the pancreas graft correspond to those obtained in the study of pancreatic perfusion in healthy participants. Full article

In 2021, Ejsmont and Biernacki showed that the free tangent distribution can be used to measure household satisfaction with durable consumer goods. This distribution arises as the limit of free random variables. This, new article serves as the theoretical introduction to the continuation of the research presented in the paper from 2021. We continue the study of the limit of specific quadratic forms in free probability, which is the first step towards constructing a new distribution for the evaluation of satisfaction with material affluence among household. We formulate a non-central limit theorem for weighted sums of commutators and square of the sums for free random variable. In addition we give the random matrix models for these limits. Full article