Search Results (19,744)

This study presents a cost-effective and accurate method for assessing nitrogen concentration in vermicompost fertilizer using a low-cost TCS3200 color sensor and a K-Nearest Neighbors (KNN) machine learning model. The objective was to evaluate the performance of four different color spaces—RGB, Lab, LCh, and CMYK—identify the most effective feature representation for a multi-class classification task based on accuracy and theoretical robustness to ambient light variations. A total of 2400 data points were collected from a standard chemical test kit and processed. A rigorous 60-fold cross-validation approach was used to determine the optimal model hyperparameters and to ensure the robustness of the findings. The results demonstrate that the model trained on the LCh color space achieved the highest classification accuracy of 0.9708 with an optimal K-value of 6, significantly outperforming Lab (0.9688), RGB (0.9625), and CMYK (0.9583). A detailed analysis of the confusion matrix revealed that the model successfully classified the ‘High’ and ‘Medium’ nitrogen levels with near-perfect accuracy, while minor misclassifications occurred between the ‘Low’ and ‘Trace’ categories (5 Low ⟶ Trace, 6 Trace ⟶ Low). The proposed system offers a practical, robust, and accessible tool for precision agriculture, enabling farmers to make informed decisions regarding fertilization, and directly supporting sustainable agriculture and responsible resource management. The findings indicate that the LCh color space is highly effective for this application, providing a viable solution for the rapid and reliable assessment of vermicompost quality. Most importantly, this inexpensive, on-site system removes the need for costly, time-consuming laboratory analyses, giving farmers and compost users the instantaneous, accurate nitrogen data they need to maximize crop yield, optimize nutrient application, and significantly reduce input costs from overfertilization. Full article

This paper investigates the joint scheduling problem of unmanned aerial vehicles (UAVs) and trucks for community logistics, where UAVs act as service providers for last-mile delivery and trucks serve as mobile storage platforms for drone deployment. To address the complexity of decision variables, this paper proposes a three-stage solution scheme that divides the problem into the following: (1) UAV mission set generation via clustering, (2) truck-drone route planning, and (3) collaborative scheduling via a Mixed-Integer Linear Programming (MILP) model. The MILP model, solved exactly using Gurobi, optimizes truck movements and drone operations to minimize total delivery time, representing the core contribution. In the experimental section, to verify the correctness and effectiveness of the proposed Mixed-Integer Linear Programming (MILP) model, comparative experiments were conducted against a heuristic algorithm based on empirical intuitive decision-making. The solution results of experiments with different scales indicate that the joint scheduling model outperforms the scheduling strategies based on empirical experience across various scenario sizes. Additionally, multiple experiments conducted under different parameter settings within the same scenario successfully demonstrated that the model can stably be solved without deteriorating results when parameters change. Furthermore, this study observed that the relationship between the increase in the number of drones and the decrease in the total consumed time is not a simple linear relationship. This phenomenon is speculated to be due to the periodic patterns exhibited by the drone scheduling sequence, which align with the average duration of individual tasks. Full article

Background/Objectives: The prevailing paradigm in ophthalmic AI involves siloed, single-disease models, which fails to address the complexity of differential diagnosis in clinical practice. This study aimed to develop and validate a unified deep learning framework for the automated multi-class classification of a wide spectrum of retinal pathologies from fundus photographs, moving beyond the single-disease paradigm to create a comprehensive screening tool. Methods: A publicly available dataset was manually curated by an ophthalmologist, resulting in 1841 images across nine classes, including Diabetic Retinopathy, Glaucoma, and Healthy retinas. After extensive data augmentation to mitigate class imbalance, three pre-trained CNN architectures (ResNet-152, EfficientNetV2, and a YOLOv11-based classifier) were comparatively evaluated. The models were trained using transfer learning and their performance was assessed on an independent test set using accuracy, macro-averaged F1-score, and Area Under the Curve (AUC). Results: The YOLOv11-based classifier demonstrated superior performance over the other architectures on the validation set. On the final independent test set, it achieved a robust overall accuracy of 0.861 and a macro-averaged F1-score of 0.861. The model yielded a validation set AUC of 0.961, which was statistically superior to both ResNet-152 (p < 0.001) and EfficientNetV2 (p < 0.01) as confirmed by the DeLong test. Conclusions: A unified deep learning framework, leveraging a YOLOv11 backbone, can accurately classify nine distinct retinal conditions from a single fundus photograph. This holistic approach moves beyond the limitations of single-disease algorithms, offering considerable promise as a comprehensive AI-driven screening tool to augment clinical decision-making and enhance diagnostic efficiency in ophthalmology. Full article

Background: Internists formulate diagnostic hypotheses and personalized treatment plans by integrating data from a comprehensive clinical interview, reviewing a patient’s medical history, physical examination and findings from complementary tests. The patient treatment life cycle generates a significant volume of data points that can offer valuable insights to improve patient care by guiding clinical decision-making. Artificial Intelligence (AI) and, in particular, Generative AI (GAI), are promising tools in this regard, particularly after the introduction of Large Language Models. The European Federation of Internal Medicine (EFIM) recognizes the transformative impact of AI in leveraging clinical data and advancing the field of internal medicine. This position paper from the EFIM explores how AI can be applied to achieve the goals of P6 Medicine principles in internal medicine. P6 Medicine is an advanced healthcare model that extends the concept of Personalized Medicine toward a holistic, predictive, patient-centered approach that also integrates psycho-cognitive and socially responsible dimensions. An additional concept introduced is that of Digital Therapies (DTx), software applications designed to prevent and manage diseases and disorders through AI, which are used in the clinical setting if validated by rigorous research studies. Methods: The literature examining the relationship between AI and Internal Medicine was investigated through a bibliometric analysis. The themes identified in the literature review were further examined through the Delphi method. Thirty international AI and Internal Medicine experts constituted the Delphi panel. Results: Delphi results were summarized in a SWOT Analysis. The evidence is that through extensive data analysis, diagnostic capacity, drug development and patient tracking are increased. Conclusions: The panel unanimously considered AI in Internal Medicine as an opportunity, achieving a complete consensus on the matter. AI-driven solutions, including clinical applications of GAI and DTx, hold the potential to strongly change internal medicine by streamlining workflows, enhancing patient care and generating valuable data. Full article

Understanding causal structures in data center cooling systems is essential for energy optimization and fault detection. Conventional methods based on physical connectivity ensure interpretability but often miss latent interactions, while Granger causality captures predictive dependencies yet suffers from sensitivity to data quality and ambiguous directionality. To overcome these limitations, we propose a hybrid causal discovery framework that integrates physics-informed priors with Granger-inspired predictive modeling. A key innovation is the use of a relative increment formulation, which focuses on the proportional change in observables immediately after control actions. This design filters out long-term seasonal trends and emphasizes short-term, actionable effects. Applied to a large-scale dataset from a real data center, the framework successfully recovers known control–feedback links, identifies consistent control–temperature relationships, and reveals cross-unit influences overlooked by traditional approaches. By combining physical priors for directionality with predictive causality for flexibility, the method yields a causal network that is both interpretable and robust, offering a principled basis for decision-making in energy-critical infrastructures. Full article

Disaster management requires the development of effective technologies for managing both pre-and post-disaster processes. Therefore, utilizing effective tools and techniques to mitigate the disaster risks or lower the adversarial impacts is essential. Over the last decade, digital twin (DT) applications have found a wider implementation area for varying purposes, but most importantly, they are utilized for simulating disaster impacts. This study aims to develop an open-source digital twin (DT) framework for earthquake disaster management in the Cayirova district of Kocaeli, Türkiye, one of the country’s most seismically active regions. The primary objective is to enhance local resilience by integrating multi-source data into a unified digital environment that supports risk assessment, response planning, and recovery coordination. The digital model developed using QGIS (3.40.9 Bratislava), Autodesk InfraWorks 2025 software for DT modeling integrates various data types, including geospatial, environmental, transportation, utility, and demographic data. As a result, the developed model is expected to be used as a digital database for disaster management, storing both geospatial and building data in a unified structure. The developed model also aims to contribute to sustainable practices in cities, where disaster risks are particularly critical. In this respect, the developed model is expected to create sustainable logistics chains and sustainable targets aiming to reduce the number of people affected by disasters, reducing the direct economic losses caused by disasters. In this framework, the developed model is expected to further assess seismic risk and mitigate risks with DTs. These capabilities enable the project to establish an open-source district-level DT system implemented for the first time in Cayirova, provide an alternative disaster model focused on region-specific earthquakes, and integrate 2D/3D assets into an operational, ready-to-respond digital database. In terms of practical importance, the model provides a digital database (digital backup) that can be used in emergencies, helping decision-makers make faster, data-driven decisions. The significance of this study lies in bridging the gap between urban digitalization and disaster resilience by providing a scalable and transparent tool for local governments. Ultimately, the developed DT contributes to sustainable urban management, enhancing preparedness, adaptive capacity, and post-disaster recovery efficiency. Full article

Defects occurring during the maintenance phase of residential buildings not only undermine the quality of life of residents but also lead to disputes with contractors, which often escalate into litigation rather than being resolved through alternative dispute resolution (ADR), thereby increasing social and economic burdens. While previous studies have mainly focused on identifying the causes of defects, developing classification systems, and improving institutional frameworks, few have sought to predict litigation outcomes from precedent data to support decision-making during pre-litigation dispute resolution. This paper proposes a natural language processing-based multimodal and multitask prediction model that learns from precedent data using information available prior to litigation, such as the claims and evidence of plaintiffs and defendants and the claimed amounts. The proposed model simultaneously predicts judgment outcomes and grant ratios in defect-related disputes and can help to enhance the persuasiveness and voluntariness of ADR by informing parties about the likelihood of settlement and the potential risks of litigation. Furthermore, this paper proposes a decision-support framework for rational and evidence-based dispute resolution which can reduce stakeholder uncertainty and ultimately lower the frequency of litigation related to residential building defects. Full article

Distributed operational data rarely translates directly into business decisions. Meanwhile, in almost all industries, including the automotive industry, especially in the premium segment, it is crucial to identify the factors conducive to closing the transaction at an early stage. The aim of this study is to develop classification models that make it possible to predict the probability of success of a particular Mercedes-Benz offer with regard to vehicle configuration. Such a tool enables optimal allocation of resources (salespeople’s time, media budgets, production capacity), which is confirmed by the literature on customer relationship management. This study evaluates the usefulness of four machine learning algorithms—Random Forest (RF), Gradient Boosting Machine (GBM), eXtreme Gradient Boosting (XGBoost), and Support Vector Machine with an RBF kernel (SVM-RBF)—in forecasting sales, which was encoded as the binary variable Success. Among the tested models, Random Forest achieved the best results with an accuracy of 84.3%, F1-score of 0.73, and AUC of 0.90, indicating a very good ability to distinguish between successful and unsuccessful transactions. The results can be used for lead prioritization, dynamic discounting, optimization of marketing campaigns, and distribution/production planning. Full article

This thorough study looks at the use of machine learning (ML) techniques to forecast energy usage in buildings, with an emphasis on mosques. As energy use has a greater impact on both the environment and the economy, it is becoming increasingly important to optimize energy usage in buildings, especially for religious organizations such as mosques. The study goes into a variety of ML methods and models, including neural networks, regression models, decision trees, and clustering algorithms, each customized to a distinct difficulty in energy management. The paper evaluates the efficacy of several ML techniques, noting their merits, shortcomings, and potential applications. Additionally, it investigates the impact of climate, mosque design, occupancy patterns, and geographical variables on energy use. To achieve accurate energy consumption projections, rigorous data collecting, pre-processing, and model validation procedures are required. The paper also discusses important data sources and methodologies for mosque-specific energy analysis. Furthermore, the study emphasizes the practical benefits of applying ML in energy prediction, such as cost savings, increased environmental sustainability, and better resource allocation. This study’s ramifications extend beyond mosques, providing useful insights into energy management in buildings in general. By summarizing the current state of ML applications in mosque energy prediction, this study is an important resource for researchers, decision-makers, and energy management practitioners, paving the way for future advancements and the adoption of more sustainable energy practices in religious institutions. Full article

One of the main challenges when working with time series captured online using sensors is the appearance of noise or null values, generally caused by sensor failures or temporary disconnections. These errors compromise data reliability and can lead to incorrect decisions. Particularly in the treatment of diabetes mellitus, where medical decisions depend on continuous glucose monitoring (CGM) systems provided by modern sensors, the presence of corrupted data can pose a significant risk to patient health. This work presents an approach that encompasses online detection and imputation of anomalous data using physiological inputs (insulin and carbohydrate intake), which enables decision-making in automatic glucose monitoring systems or for glucose control purposes. Four deep neural network architectures are proposed: CNN-LSTM, GRU, 1D-CNN, and Transformer-LSTM, under a controlled fault injection protocol and compared with the ARIMA model and the Temporal Convolutional Network (TCN). The obtained performance is compared using regression (MAE, RMSE, MARD) and classification (accuracy, precision, recall, F1-score, AUC) metrics. Results show that the CNN-LSTM network is the most effective for fault detection, achieving an F1-score of 0.876 and an accuracy of 0.979. Regarding data imputation, the 1D-CNN network obtained the best performance, with an MAE of 2.96 mg/dL and an RMSE of 3.75 mg/dL. Then, validation on the OhioT1DM dataset, containing real CGM data with natural sensor disconnections, showed that the CNN–LSTM model accurately detected anomalies and reliably imputed missing glucose segments under real-world conditions. Full article

The spatial zoning of wall-rock alteration is a useful guide for exploration of porphyry deposits. The current techniques to typify and quantify alteration types have a component of subjectivity and may not reconcile with mineralogical observations. An alternative is to apply machine learning (ML) to classify alteration based on geochemical and mineralogical feature variables. However, classification loses accuracy because of natural and artificial short-scale variability and missing information, or because it ignores the spatial correlations of the feature variables. Here we show that these inconveniences can be overcome by replacing these variables with proxies obtained through geostatistical simulation. The use of such proxies improves the accuracy scores by eight percentual points by removing the noise affecting the feature variables and infilling their missing values. Furthermore, the uncertainty in the classification predictions can be quantified accurately. Our results demonstrate how geostatistics enriches ML to achieve higher predictive performance and handle incomplete and noisy data sets in a spatial setting. This synergy has far-reaching consequences for decision making in mining exploration, geological modeling, and geometallurgical planning. Beyond the presented pioneering application, we expect our approach to be used in supervised classification problems that arise in varied disciplines of natural sciences and engineering and involve regionalized data. Full article

It is crucial to evaluate the quality of standing timber for the rational and effective management of forest land. In practice, it is often difficult to obtain accurate data on various indicators of standing timber due to constraints such as measurement conditions, accuracy, and cost. Therefore, this study developed a multi-attribute decision-making method based on trapezium clouds and applied it to evaluate the standing timber quality of forest land. Firstly, a trapezium cloud transformation method was designed to handle multi-granularity symmetric linguistic information problems caused by different knowledge backgrounds of decision-makers, and the symmetric structure inherent in trapezium clouds helped to ensure the balanced processing of information from various asymmetric cognitive perspectives. Secondly, a trapezium cloud generalized weighted Heronian mean was proposed for the information aggregation process of trapezium clouds. Then, the concept of trapezium cloud interval similarity was defined, and an optimization model was constructed to determine the normalized interval weights of attributes. Based on the symmetric numerical feature, the calculation formula for the approximate centroid coordinates of trapezium clouds was derived, and based on this, the ranking method of trapezium clouds was obtained. Finally, taking the evaluation of standing timber quality in forest land as a numerical example, the applicability of the constructed multi-attribute decision-making method was demonstrated. In addition, the corresponding comparison analysis verified the superiority and effectiveness of the proposed method. Full article

This manuscript analyzes the relationship between carbon dioxide emissions and selected factors for the agricultural sector in the Visegrad Group (V4) countries. The aim of the study was to identify and assess short-term relationships and directions of causality between carbon dioxide emissions, renewable energy consumption, economic openness, labor productivity, and income levels in the agricultural sector of the V4 countries. Short-term ARDL modeling was used for each V4 country, along with Granger causality. The analyses offer a broad perspective on how agricultural practices shape greenhouse gas emissions and provide information to mitigate their environmental impact. Heterogeneous interactions between the studied factors and specific causal relationships were identified in each country. Only in Hungary and Slovakia was a unidirectional causality observed, namely CO₂ → renewable energy (RE) sources, while in Poland and the Czech Republic, no direct causal relationship with emissions was observed. However, these relationships were indirect through income and economic openness. Strong drivers include, in particular, labor productivity, the share of renewable energy, and economic openness. Based on the analyses, decision-makers are recommended to create incentives, including economic ones, to increase the share of renewable energy in agricultural production. This improves economic and environmental outcomes, both locally and nationally. Full article

This study examines the role of financial literacy as a catalyst for women’s economic empowerment in the MENA region, focusing on its impact on financial performance through the mediating effects of autonomy and family support, as well as the moderating effects of male partners and employment type. Drawing on data from 515 women professionals across five MENA countries, the research employs Partial Least Squares Structural Equation Modeling (PLS-SEM) to examine both direct and indirect relationships among key variables. The findings reveal that financial literacy significantly enhances financial performance, primarily by fostering greater autonomy in financial decision-making. While parental and spousal support also contribute, their mediating effects are comparatively weaker. Moreover, the relationship between financial literacy and autonomy is moderated by employment type and the presence of male partners, with employed women and those in collaborative environments experiencing stronger gains in autonomy. These results underscore the importance of targeted financial education and autonomy-enhancing policies to support women’s economic advancement in culturally complex and economically volatile contexts. The study contributes to the literature on gender and development economics by offering empirical evidence from an under-researched region and provides actionable insights for policymakers, educators, and organizations aiming to promote inclusive economic growth. Full article

This paper investigates the systemic macroeconomic determinants of Pillar 2 Requirements (P2R) imposed by the European Central Bank (ECB) under the Single Supervisory Mechanism (SSM). While P2R is formally calibrated at the individual bank level through the Supervisory Review and Evaluation Process (SREP), we explore the extent to which common macro-financial shocks influence supervisory capital expectations across banks. Using a panel dataset covering euro area banks between 2021 and 2025, we match bank-level P2R data with country-level macroeconomic indicators. Those variables include real GDP growth, HICP inflation and index levels, government fiscal balance, euro yield curve spreads, net turnover, FDI inflows, construction and industrial production indices, the price-to-income ratio in real estate, and trade balance measures. We apply Principal Component Analysis (PCA) to extract latent variables related to the macroeconomic factors from a broad set of variables, which are then introduced into a Bayesian Vector Autoregression (BVAR) model to assess their dynamic impact on P2R. Our results identify three principal components that capture general macroeconomic cycles, sector-specific real activity, and financial/external imbalances. The impulse response analysis shows that sectoral and external shocks have a more immediate and statistically significant influence on P2R adjustments than broader macroeconomic trends. These findings clearly support the use of systemic macro-financial conditions in supervisory decision-making and support the integration of anticipating macro-prudential analysis into capital requirement frameworks. Full article