Search Results (174)

Modern fire alarm systems are essential for public safety, yet they often fail to exploit the wealth of historical alarm data and the complex spatiotemporal dependencies inherent in urban environments. Graph Neural Networks (GNNs) are currently among the most popular methods for handling complex spatiotemporal dependencies. While a range of dynamic GNN approaches have been proposed, many existing GNN-based predictors still rely on a static topology, which limits their ability to fully capture the evolving nature of risk propagation. Furthermore, even among dynamic graph methods, most focus on temporal link prediction or social interaction modeling, with limited exploration in safety-critical applications such as fire alarm prediction. DeaGAT dynamically updates inter-building edge weights through an attention mechanism, enabling the graph structure to evolve in response to shifting risk patterns. A margin-based contrastive learning objective further enhances the quality of node embeddings by distinguishing subtle differences in risk states. In addition, DeaGAT jointly models static building attributes and dynamic alarm sequences, effectively integrating long-term semantic context with short-term temporal dynamics. Extensive experiments on real-world datasets, including comparisons with state-of-the-art baselines and comprehensive ablation studies, demonstrate that DeaGAT achieves superior accuracy and F1-score, validating the effectiveness of dynamic graph updating and contrastive learning in enhancing proactive fire early-warning capabilities. Full article

This study evaluates the economic dimension of sustainable supply chain efficiency among Korean automotive suppliers using an SCOR-aligned two-stage Network Range-Adjusted Measure (NRAM) Data Envelopment Analysis (DEA) model. The framework separates performance into Stage 1 (internal operations: Plan/Source/Make/Deliver) and Stage 2 (external outcomes: sales and profitability), enabling stage-specific assessment of operational versus market-facing efficiency. Firm-level financial data for about 1200 suppliers annually from 2021 to 2024, spanning five sectors, were analyzed with descriptive statistics, visualizations, and non-parametric tests. Results show that Stage 1 efficiency was consistently high and stable, while Stage 2 efficiency was lower, more variable, and declined in 2022 and 2024, revealing vulnerability to systemic market disruptions. Overall efficiency mirrored Stage 2, underscoring the fact that downstream financial outcomes drive total performance. Rather than introducing a new methodology, the contribution of this study lies in applying an established two-stage NRAM DEA within an SCOR-aligned framework to a large-scale longitudinal dataset. This application provides sectoral and temporal benchmarks on a national scale, offering evidence-based insights into how structural interdependence and systemic shocks influence supply chain efficiency. While the scope is limited to the economic pillar of sustainability, the findings contribute contextualized benchmarks that can inform managerial practice and future research integrating environmental and social performance dimensions. Full article

Economic efficiency plays a crucial role in both resource conservation and food security, which is why numerous scholars have expressed a keen interest in improving production stage efficiency. Nevertheless, only a few have studied allocation stage efficiency, and even fewer researchers have explored production stage efficiency in close conjunction with allocation stage efficiency. As a result, this paper constructs a two-stage dynamic network SBM model based on the value chain theory, taking 24 counties (cities and districts) in Dongting Lake Region, the most typical region in China, as a case study, and integrating the production and allocation stages. The conclusions are as follows: (1) Economic efficiency is heterogeneous in both time and space. (2) Production stage efficiency and allocation stage efficiency are always positively or negatively correlated, and the different correlations reflect the different situations in the production stage and allocation stage. (3) The production stage and allocation stage efficiency can help us to identify the weak links in the agricultural production process so as to realize the target. The research methodology in this paper can not only be applied to the analysis of multi-stage efficiency, but the production efficiency can also be expanded to multi-dimensional efficiency, which involves economic efficiency, ecological efficiency and social efficiency. Full article

This paper innovatively constructs a comprehensive material cycle network framework for the circular economy system of the coal industry and evaluates the circular economy efficiency of China’s provincial coal industry from 2011 to 2021 using a comprehensive evaluation model that integrates emergy analysis and dynamic network data envelopment analysis (DEA). The research delves into the evolutionary characteristics of the coal industry’s circular economy and identifies the underlying causes of inefficiency. The results reveal that the circular economy in China’s coal industry has gone through three stages: the transformation period, the reinforcement period, and the growth period, with the inefficiency of waste reutilization being the key factor restricting the overall improvement in efficiency. The circular economy model in the production phase is gradually shifting from an extensive linear model to a clean, closed-loop model, while a significant gap remains between the high-emission linear model and the low-pollution closed-loop model in the utilization phase. Furthermore, regional heterogeneity mainly arises from imbalances in the operational efficiency of the circular economy system. This study not only reveals the deep-seated reasons for the low efficiency of circular economy in China’s coal industry but also provides strategies and directions for achieving a more efficient circular economy and carbon mitigation goals. Full article

Under the background of global green sustainable development and the urgent need to understand complex regional innovation systems, it is crucial to scientifically assess China’s Tourism Green Innovation Efficiency (TGIE) as a dynamic networked system and reveal its system-level evolution driving mechanism. This article presents the construction of the TGIE evaluation indicator system, measures the inter-provincial TGIE in China in 2011–2023 based on the three-stage super-efficiency SBM-DEA model, analyzes the spatial correlation network characteristics of TGIE by using the motif analysis method and the social network analysis method, and explores the evolutionary driving mechanism by using the time-exponential random graph model (TERGM). The study shows the following: (1) The TGIE of China exhibits a regional distribution pattern characterized by “high in the east and low in the west.” The efficiency of the eastern coastal region is significantly higher than that of the central and western regions, and the overall efficiency shows a fluctuating upward trend. (2) The local structure of China’s TGIE network is dominated by the chain structure, and the partially closed structure is gradually enhanced. It indicates that the bridge role of intermediary nodes in the cross-regional flow of innovation resources is becoming more and more significant. (3) The overall network evolves from a single center to a polycentric collaboration model. High-efficiency regions attract low-efficiency regions to collaborate through high connectivity, and intermediary nodes play a key role in connecting high- and low-efficiency regions. (4) The evolution of China’s TGIE network is driven by both exogenous and endogenous dynamics, showing significant path dependence and path creation characteristics. This study enhances the theoretical framework of complex systems in tourism innovation and offers theoretical support and policy insights for optimizing the network structure of China’s TGIE as a complex adaptive system and maximizing regional cooperation networks. Full article

Developing and identifying the correct reactor model for a reaction system characterized by a high number of reaction pathways and flow regimes can be challenging. In this work, artificial neural networks (ANNs), used in deep learning, are used to develop a hybrid modelling framework for physics-based model discovery in reactions systems. The model discovery accuracy of the framework is investigated considering kinetic model parametric uncertainty, noise level, features in the data structure and experimental design optimization via a differential evolution algorithm (DEA). The hydrodynamic behaviours of both a continuously stirred tank reactor and a plug flow reactor and rival chemical kinetics models are combined to generate candidate physics-based models to describe a benzoic acid esterification synthesis in a rotating cylindrical reactor. ANNs are trained and validated from in silico data simulated by sampling the parameter space of the physics-based models. Results show that, when monitored using test data classification accuracy, ANN performance improved when the kinetic parameters uncertainty decreased. The performance improved further by increasing the number of features in the data set, optimizing the experimental design and decreasing the measurements error (low noise level). Full article

The realization of forest ecological functions value is an important path for implementing the “Two Mountains” theory. Improving the efficiency of forest ecological functions and benefits value realization faces several challenges, such as an underdeveloped value evaluation system that makes it difficult to quantify ecological value, a weak policy system lacking effective incentive mechanisms, and unclear ecological property rights leading to unfair benefits distribution. Forest new quality productive drivers are a key factor in promoting high-quality forestry development, and can effectively address several issues hindering the efficiency of forest ecological functions and benefits value realization. Forest ecological functions and benefits are divided into tangible forest products and intangible ecological services, with the efficiency of realizing their economic and welfare values reflecting the input–output status of forest ecological value. This paper constructs an indicator system for assessing the modern productive capacity in forestry and the efficiency of forest ecological value realization, and uses a two-stage network DEA model and a double fixed effects model for empirical analysis. The study finds that the advanced drivers of forestry productivity significantly enhance the efficiency of forest ecological economic value realization but constrain the efficiency of ecological welfare value realization, with significant regional differences. As a moderating variable, enhancing the resilience of the industry chain can significantly deepen the effect throughout the process, while improving the informatization level of residents can weaken the constraints of forest new quality productive drivers on the efficiency of forest ecological welfare value realization. Therefore, this paper offers targeted recommendations aimed at providing theoretical support and practical guidance for optimizing the efficiency of forest ecological value realization. Full article

This paper proposes a hybrid methodology for portfolio optimization by integrating the data envelopment analysis (DEA) model with the mean semivariance (MSV) framework. The goal is to construct portfolios that achieve targeted returns while minimizing downside risk. The methodology comprises two stages: (1) identifying efficient stocks through DEA, where semivariance and beta ($\beta$) are employed as input risk metrics and the expected return serves as the output, and (2) determining optimal portfolio weights through the MSV model, solved using artificial neural networks (ANNs) and evolutionary algorithms. The empirical results demonstrate that portfolios optimized with ANNs exhibit significantly lower risk compared to those derived from evolutionary algorithms, highlighting the superiority of ANN-based approaches in balancing risk and return under the proposed framework. This study underscores the potential of hybrid DEA-MSV models enhanced by machine learning techniques for advanced portfolio management. Full article

Transportation infrastructure serves a pivotal role in driving regional development. This study proposes a decision-making framework for rural road network planning within the context of China’s common prosperity initiative. An integrated model combining Data Envelopment Analysis (DEA) and the Analytic Hierarchy Process (AHP) is developed, where DEA is employed to identify technically efficient planning alternatives and AHP is used to rank these alternatives based on social and environmental benefits. Applying the model to the case of Yueqing City, Zhejiang Province, the findings reveal that common prosperity-oriented schemes, particularly the Scheme, which emphasizes full industrial coverage and balanced equity, achieve a superior balance among construction costs, industrial coverage, regional equity, and carbon emissions. Theoretically, this research advances transportation planning by incorporating equity-focused metrics, such as the Gini coefficient, into efficiency analyses, thus promoting a socially sustainable approach to infrastructure development. Practically, the proposed method offers a systematic and actionable tool for local governments to optimize rural transportation networks in support of common prosperity and balanced regional growth. The resulting framework not only identifies technically efficient and equitable layouts but also offers planners a transparent tool for balancing cost, social equity, and environmental impact in future rural infrastructure projects. Full article

Accurately characterizing the structural features of the spatial correlation network of comprehensive transportation green efficiency (CTGE) is essential for achieving balanced regional transportation development and eliminating regional disparities. This study employs the slacks-based measure-data envelopment analysis (SBM-DEA) model to assess the CTGE of China. Furthermore, the standard deviational ellipse (SDE) model and social network analysis (SNA) method are adopted to delineate the spatiotemporal evolution patterns and spatial correlation network characteristics of CTGE, based on input–output data from the transportation industry across 30 provinces (municipalities and autonomous regions) between 2003 and 2020. The findings reveal that China’s CTGE exhibits a fluctuating trend of an initial decline followed by subsequent increase, with a national average of 0.555 and an average of 0.722 in eastern regions, 0.434 in central regions, and 0.478 in western regions. This demonstrates that China’s CTGE maintains an overall low level while showing significant regional disparities. The spatial center of gravity of China’s CTGE has shifted from a southwestern to a northeastern trajectory, with a generally concentrated spatial distribution pattern. Furthermore, China’s CTGE demonstrates a distinct “core-edge” hierarchical structure, with regions occupying varied roles and statuses within the network. The central and western regions are positioned at the network periphery, predominantly receiving spillover effects from other regions, while the eastern region, driven by its strong spillover effect, serves as the network’s “engine”. The most significant contribution of this study lies in developing a more comprehensive CTGE evaluation framework and precisely identifying the structural positions and functional roles of different regions within the network, which holds substantial theoretical and practical value for advancing sustainable development in China’s transportation sector. Full article

Benchmarking railway infrastructure managers (RIMs) has become a crucial tool in the context of European transport market liberalization, facilitating efficiency improvements and strategic decision-making. RIMs face challenges in increasing capacity, optimizing operations, and ensuring competitive, safe, and economically sustainable services. To address these challenges, this study proposes a hybrid benchmarking model that integrates Principal Component Analysis (PCA) to identify key performance indicators (KPIs) and reduce data dimensionality, the Grey Best–Worst Method (G-BWM) to determine KPI weight coefficients based on expert evaluations, and Assurance Region Data Envelopment Analysis (AR-DEA) to assess the relative efficiency of RIMs while incorporating real-world constraints. The research findings confirm that RIM8 is the most efficient unit, driven by high electrification levels, strong accident prevention measures, and optimal use of infrastructure. In contrast, RIM2 and RIM4 record the lowest efficiency scores, primarily due to poor safety performance, high infrastructure-related delays, and suboptimal resource utilization. By introducing weight constraints through AR-DEA, the model ensures that efficiency assessments reflect actual operational conditions, rather than relying on unrestricted weight allocations. The main contribution of this study lies in developing a systematic and objective framework for evaluating RIM efficiency, ensuring consistency and reliability in performance measurement. The practical implications extend to policy development and operational decision-making, providing insights for infrastructure managers, regulatory bodies, and policymakers to optimize resource allocation, enhance infrastructure resilience, and improve railway sector sustainability. The results highlight key efficiency factors and offer guidance for targeted improvements, reinforcing benchmarking as a valuable tool for long-term railway infrastructure management and investment planning. By offering a quantitatively grounded efficiency assessment, this model contributes to the competitiveness and sustainability of railway networks across Europe. Full article

Eco-efficiency, which integrates environmental and economic variables, is crucial for decision-making in agriculture, particularly within the framework of European environmental policy. The SBM-DEA tool has been applied in several studies, and facilitates the optimization of greenhouse gas (GHG) emissions in the agricultural sector. Despite the significance of the Spanish agricultural economy at both European and international levels, the analysis of its eco-efficiency is limited and fragmented, and does not consider the regional disparities within the country. The objective of this study is therefore to assess the eco-efficiency of the Spanish regional agricultural sector during the period from 2004 to 2022, considering its regional and productive differences. This has been achieved using data from the Farm Accounting Network and the non-oriented SBM-DEA method with constant returns to scale. The eco-efficiency of the Spanish regional agricultural sector as a whole was estimated to range from 0.644 to 0.837, with an average value of 0.772 for the period analyzed. Forty-seven percent of the regions exceeded the average eco-efficiency. The data indicate significant opportunities to improve eco-efficiency and reduce GHG emissions at both the national (65.6%) and regional (ranging from 7.4 to 86.5%) levels. This paper discusses the need to develop regionalized strategies to optimize resource allocation and reduce greenhouse gas emissions within the Common Agricultural Policy. Full article

This study evaluates the efficiency of EU countries in utilizing their geographical potential for wind and solar energy production. A two-stage radial network data envelopment analysis (NDEA) is used to estimate the efficiency of the utilization of natural resources. The research is of a computational-empirical nature on the basis of publicly available data. The basic variables included in the model are: mean wind speed, Global Horizontal Irradiance, population, land area, wind energy capacity, solar PV capacity, wind energy generation, and solar power generation. The relationship between the environmental potential and the installed power capacity is evaluated in the first stage. In the second stage, the actual production from the installed capacity is analyzed. The efficiency trends over time are also investigated. This approach offers a comprehensive assessment by considering both the technical performance and environmental constraints. Considering all studied countries together, a slight increase in the relative efficiency of renewable energy potential utilization is observed—from 23.2% in 2018 to 28.7% in 2022. Germany and the Netherlands achieved 100% relative efficiency in 2022. The results reveal that the development of alternative energy sources and the efficiency of the installed power capacity utilization are not always in line with the local environmental conditions. The average efficiency of the analyzed countries from this perspective was 26.8% in 2018, with an improvement to 37.4% in 2022. The relative efficiency of the installed capacity utilization was high in both periods (76.3% and 74.9%, respectively). The impact of exogenous variables on performance (GDP and R&D expenditures) is discussed. Broader implications of the results for a responsible renewable energy policy in the EU demonstrate the need to combine overarching targets with a flexible governance system. That flexibility should allow for individual energy transition pathways, cooperative mechanisms, market integration, and targeted funding in order to account for the diversity of renewable resource utilization potentials among countries. Full article

In this study, we investigated the influence of an epoxy end-capped polypropylene oxide crosslinker (epoxy-PPO) on the formation of the crosslinked network structure, the stress–strain response, and the electro-mechanical actuation performance of a maleic anhydride functionalized liquid isoprene rubber (LIR). The crosslinker amount varied from 10 (C-LIR-10) to 50 (C-LIR-50) weight parts per hundred parts (phr) of LIR. The swelling test of the cured rubbers revealed that C-LIR-20 formed the densest crosslinked network with the lowest chloroform uptake value within this series. The crosslinked rubber became stiffer in tensile response upon increasing the epoxy-PPO amount from C-LIR-10 to C-LIR-20 and then softened at higher amounts. The SEM measurements were used to relate this composition-induced softening of the rubbers to the phase morphology evolution from nanoscale homogeneity in C-LIR-10 to microscale segregations of excess crosslinkers in C-LIR-50. The use of epoxy-PPO improved the dielectric constant value of LIR; however, the leakage current through the films also increased from 25 µA DC to 320 µA DC for LIR-30 and LIR-50, respectively, during DEA operation. The electro-mechanical actuation tests with circular actuators showed that the C-LIR-10 elastomer film demonstrated a radial strain of 1.7% on activation at an electric field strength of 17.5 V/µm. At higher crosslinker amounts, the close proximity of excess epoxy-PPO molecules caused leakage current across elastomer films thus diminishing the actuation strain of otherwise relatively softer elastomers with higher dielectric constant values. Full article

Efficient logistics is a key factor in the competitiveness of seaports, especially in regions such as the Baltic Sea, where ports play important roles as hubs in the European Union’s Trans-European transport network (TEN-T). However, there are a lack of comprehensive studies focusing on the logistics efficiency of Baltic Sea ports, especially those integrating technical and technological factors. This study aimed to assess changes in the logistics efficiency of 15 major ports in the Baltic Sea region between 2019 and 2023, taking into account the technological and infrastructure-related elements that influence port performance. The model developed by the authors integrates the nearest neighbour method for cluster identification, data envelopment analysis using the Banker, Charnes, and Cooper (DEA-BCC) model to assess the overall technical, pure technical, and scale logistics efficiency, and spatial autocorrelation analysis to explore spatial interactions. For the DEA-BCC model, constraints were defined for each port based on inputs (number and length of berths) and outputs (cargo and container volumes for 2019–2023). The spatial autocorrelation analysis examined the relationships among the Baltic Sea ports, container volumes, and logistic efficiency values derived from the DEA model. Recognizing the sensitivity of the weight matrix in previous studies, this paper introduced an enhanced two-factor weighting matrix that incorporated geographical distance and the port connectivity index, calculated by the United Nations Conference on Trade and Development (UNCTAD). The statistical reliability of the results was validated using z-scores and p-values. The results showed that the overall technical efficiency of the ports analysed during the period considered was 47.2%, the pure technical efficiency was 61.0%, and the average scale efficiency was around 76%, indicating that diminishing returns to scale dominated. The spatial analysis showed a strong correlation between port connectivity and efficiency, indicating that well-connected ports, such as Gdańsk and Gdynia, had a higher efficiency. The findings make a significant contribution to the understanding of the logistics efficiency of Baltic Sea ports and highlights the importance of regional cooperation, infrastructure improvements, and better connectivity strategies to improve the overall efficiency of seaports in the region. Full article