Search the repository

A+ | A- | | SLO | ENG

Abstract: Measuring sustainability as an efficient tool to achieve sustainable development and improve economic, social, and environmental aspects is always fraught with complications. In this sense, developing a suitable approach for evaluating and recognizing the strengths and weaknesses across these dimensions is paramount. Given the inherent uncertainty in data for many real-world applications, the primary aim of this paper is to present a data envelopment analysis (DEA) model for evaluating sustainability within a stochastic environment. The proposed model is non-radial and incorporates undesirable outputs, enabling the assessment of overall sustainability as well as each of the economic, social, and environmental dimensions simultaneously. This multi-dimensional evaluation capability is a key advantage of the proposed model. Additionally, the proposed model is based on input excesses and output shortfalls. Another notable advantage is the incorporation of the assumption of managerial disposability when dealing with undesirable outputs. To demonstrate the applicability of the proposed model, data from 59 diverse countries across Africa, Europe, North America, and Asia were analyzed over a 12-year period (2010–2022). The country selection was designed to capture global heterogeneity in development levels, policies, and environmental conditions, allowing for robust cross-continental comparisons. Key findings reveal that: (1) Europe achieves the highest stochastic sustainability scores, while North America performs poorest; (2) Environmental sustainability shows the most success cases globally, whereas social sustainability lags; (3) Significant trade-offs exist between economic growth and environmental protection.
Keywords: data envelopment analysis, performance analytics, Stochastic modeling, sustainability efficiency, environmental benchmarking, managerial disposability
Published in DiRROS: 04.02.2026; Views: 605; Downloads: 162
Full text (1,45 MB)

Abstract: Resource allocation in Data Envelopment Analysis (DEA) has been extensively studied, yet most works focus on redistributing available resources rather than allocating unavoidable fixed costs among decision-making units (DMUs). This study addresses the important problem of fixed cost allocation, aiming to ensure that inefficient DMUs can become efficient while keeping allocations as fair as possible, thereby providing a practical decision-making tool in real-world contexts such as banking and manufacturing. We propose a new linear DEA-based model that allocates fixed costs so as to transform an inefficient DMU into an efficient one, with the objective of minimizing the deviation from fair allocation. The model is then generalized to a fuzzy environment by incorporating triangular fuzzy numbers for inputs, outputs, and costs, and validated using benchmark datasets from Cook and Kress and Wang et al. The results demonstrate that the proposed models can successfully enhance the efficiency of targeted DMUs while producing allocations close to fairness, and the fuzzy extension proves robust in handling imprecise data. The key novelties of this research are (i) introducing a linear efficiency-improving allocation model with minimum distance to fairness, (ii) extending the allocation problem to fuzzy DEA by considering fuzzy costs alongside fuzzy inputs and outputs, and (iii) showing that this integrated framework has not been addressed before in the literature, thereby offering a novel, practical, and equitable approach for fixed cost allocation in DEA.
Keywords: data envelopment analysis, efficiency, allocation, fair allocation, triangular fuzzy number
Published in DiRROS: 30.12.2025; Views: 770; Downloads: 249
Full text (904,49 KB)
This document has many files! More...

Abstract: Classical sets are characterized by ‘well-defined’ objects or elements, but this property is relative and linguistic.Classical sets, like the set of natural numbers, are primarily used for counting and measuring quantitative data. However,the literature does not address the differences in the representation of cardinalities between infinite sets and their infinitesubsets. This study investigates the cardinalities of infinite sets and their finite versions (cut cardinalities) within thefiniteapproximation ofthe real number system. Traditional fuzzy sets measure only belongingness or membership values, thuscapturing qualitative data. In the second part, this study introduces nature sets, which describe both the quantitative andqualitative aspects of elements. Quality measurement is provided by various techniques. Several properties of nature setsare examined, and potential applications are highlighted.
Keywords: nature set, qualitative property, quantitative property, cut cardinality
Published in DiRROS: 04.11.2025; Views: 462; Downloads: 330
Full text (1,79 MB)
This document has many files! More...

Abstract: Wireless sensor networks (WSNs) are subject to distributed denial-of-service (DDoS) attacks that impact data dependability, mobility of nodes, and energy drain. The remedy to these challenges in this work is a solution based on deep learning integrated with a blockchain-aided distance-vector hop (DV-HOP) localization algorithm for reliable and secure node localization. Incorporating a blockchain ledger makes the network more trustworthy as it verifies usual and unusual system activities, whereas the DV-HOP algorithm mitigates localization inaccuracies and enhances node placement. The system is evaluated according to different performance measures like localization error, accuracy ratio, average localization error (ALE), probability of location, false positive rate (FPR), false negative rate (FNR), energy utilization, network stability, node failure rate, node recovery rate, and malicious node detection rate. Experimental results reveal improved security, accuracy, and efficiency with 17% FPR and 15% FNR, outperforming the conventional methods. This model enhances WSN performance in different environments via precise data transmission from the source to the destination. The results confirm that integrating deep learning with blockchain and DV-HOP increases network robustness, thus making WSNs more secure against security attacks while reducing energy consumption and localization accuracy. The proposed model presents a strong solution for real-world applications in wireless network environments.
Keywords: wireless network devices, DV-HOP algorithm, blockchain ledger, reliable network devices, deep learning
Published in DiRROS: 09.09.2025; Views: 590; Downloads: 323
Full text (3,73 MB)
This document has many files! More...

Abstract: The agricultural economy heavily relies on poultry production, making accurate forecasting of poultry data crucial for optimizing revenue, streamlining resource utilization, and maximizing productivity. This research introduces a novel application of the N-BEATS architecture for multi-dimensional poultry data forecasting with enhanced interpretability through an integrated Explainable AI (XAI) framework. Leveraging its advanced capabilities in time series modeling, N-BEATS is applied to predict multiple facets of poultry disease diagnostics using a multivariate dataset comprising key environmental parameters. The methodology empowers decision-making in poultry farm management by providing transparent and interpretable forecasts. Experimental results demonstrate that N-BEATS outperforms conventional deep learning models, including LSTM, GRU, RNN, and CNN, across various error metrics, achieving MAE of 0.172, RMSE of 0.313, MSLE of 0.042, R-squared of 0.034, and RMSLE of 0.204. The positive R-squared value indicates the model’s robustness against underfitting and overfitting, surpassing the performance of other models with negative R-squared values. This study establishes N-BEATS as a superior and interpretable solution for complex, multi-dimensional forecasting challenges in poultry production, with significant implications for enhancing predictive analytics in agriculture.
Keywords: poultry, livestock, forecasting, epidemiology, humidity, veterinary diseases, polynomials
Published in DiRROS: 09.09.2025; Views: 553; Downloads: 277
Full text (1,63 MB)
This document has many files! More...