Search Results (7)

Addressing the challenges of scarce measured data for Class 3–4 bridges and strong subjectivity in manual assessments in bridge technical-condition evaluation, this study innovatively proposes a FastText+CNN evaluation model that integrates semantic features with spatial pattern recognition. By constructing a hierarchical data structure of bridge scale matrices using the analytic hierarchy process (AHP) and generating a balanced training set encompassing Class 1–5 bridges through computational code, the model overcomes the bottleneck of training under small-sample conditions. It employs N-Gram embeddings to achieve semantic representation of defect feature combinations, combines one-dimensional convolutional neural networks to capture cross-component spatial correlation patterns, and utilizes hierarchical Softmax to optimize multi-classification efficiency. Experiments show that the model achieves 92.4% accuracy on the test set, outperforming random forest and multi-layer CNN models by 15.9% and 3.7%, respectively, with recognition rates for Class 3–5 bridges rising to 85% and cross-entropy loss reduced to 0.36. Validated with data from 30 actual bridges, the model maintains 92.3% accuracy and demonstrates the ability to discover implicit patterns in cross-component defect chains, providing an intelligent solution for bridge technical condition evaluation that combines semantic understanding with spatial feature extraction. Full article

Fine-grained feature extraction and affective semantic mapping remain significant challenges in product form analysis. To address these issues, this study proposes a contrastive learning-based cross-modal fusion approach for product form imagery recognition, using the front-end design of new energy vehicles (NEVs) as a case study. The proposed method first employs the Biterm Topic Model (BTM) and Analytic Hierarchy Process (AHP) to extract thematic patterns and compute weight distributions from consumer review texts, thereby identifying key imagery style labels. These labels are then leveraged for image annotation, facilitating the construction of a multimodal dataset. Next, ResNet-50 and Transformer architectures serve as the image and text encoders, respectively, to extract and represent multimodal features. To ensure effective alignment and deep fusion of textual and visual representations in a shared embedding space, a contrastive learning mechanism is introduced, optimizing cosine similarity between positive and negative sample pairs. Finally, a fully connected multilayer network is integrated at the output of the Transformer and ResNet with Contrastive Learning (TRCL) model to enhance classification accuracy and reliability. Comparative experiments against various deep convolutional neural networks (DCNNs) demonstrate that the TRCL model effectively integrates semantic and visual information, significantly improving the accuracy and robustness of complex product form imagery recognition. These findings suggest that the proposed method holds substantial potential for large-scale product appearance evaluation and affective cognition research. Moreover, this data-driven fusion underpins sustainable product form design by streamlining evaluation and optimizing resource use. Full article

The water resource carrying capacity (WRCC) system comprises multiple complex and non-linear interactions related to society, economy, water resources, and the water environment. A comprehensive comprehension of its internal mechanisms is essential for the continual enhancement of the regional WRCC. This study concentrates on the temporal and spatial variability of the WRCC to investigate a method for dynamic successive assessment. Firstly, the pressure–state–response (PSR) framework is used to develop a systematic and causal indicator system. Then, the variable fuzzy pattern recognition (VFPR) model and an analytic hierarchy process—entropy (AHP-E) model are combined to successively and dynamically assess WRCC. The proposed method is applied to the dynamic successive assessment of WRCC in Hebei Province, and it is obtained that the poor water resource carrying capacity in Hebei Province is mainly due to the basic attribute of the decision on the water resource shortage, but Hebei Province actively adopts a variety of measures to save water and pressurize mining, which has made the province’s water resource carrying capacity tend to become better gradually. Simultaneously, a system dynamics model (SD) for water resource carrying capacity was established based on an analysis of the model structure. Moreover, three scenarios were designed, including existing continuation, high-efficiency water saving, and cross-regional water transfer. Subsequently, each scenario is further categorized into high- and low-speed economic development and population growth schemes. Afterward, simulations and predictions were conducted for a total of six schemes spanning from 2023 to 2030. The results indicate that if the current development model is adopted, the water resource carrying capacity will continue to maintain low levels. It was concluded that the high-speed development of the economy and population, the efficient water conservation, and the interbasin transfer scenario (scenario 2 with high speed) are the best choices for the sustainable development of water resources and social economy in Hebei. Full article

Based on experiences about the planning of decentralized wastewater treatment systems for slums of two rural towns in India, the paper asks to what extent affordability for the future users may impede the realization of other sustainability goals. The planning aimed at ensuring economic, social, and environmental sustainability. To this end the planning process promoted the participation of stakeholders and it was supplemented by an in-depth analysis (using novel methods) of the socio-economic situation of the future users. In particular, an approach towards estimating willingness to pay from small samples was developed. Taking all this information into account, planning identified a well-established technology that it is inexpensive, robust, and easy to maintain. The experiences of this planning process may generalize to other developing countries seeking socially acceptable low cost solutions with reasonable pollution reduction for resolving the sanitation crisis. Full article

Comprehensive assessment of water quality is an important technological measure for water environmental management and protection. Previous assessment methods tend to ignore the influences of sediment pollutant release and dynamic change of the water boundary. In view of this, this paper explores a new method for comprehensive water quality assessment. Laboratory simulation experiments are conducted to analyze the influences of sediment pollutant release on water quality, and the results are taken as increments, coupled with original samples, to constitute a new set of evaluation samples. Dynamic and comprehensive water quality assessment methods are created based on a principal component analysis (PCA)/analytic hierarchy process (AHP)–variable fuzzy pattern recognition (VFPR) model and adopted to evaluate water quality. A geographic information system (GIS) is applied to visually display the results of water quality assessment and the change of the water boundary. This study takes Biliuhe Reservoir as an engineering example. The results show the change process of the water boundary, during which the water level is reduced from 63.10 m to 54.15 m. The reservoir water quality is fine, of which the water quality level (GB3838-2002) is between level 2 and level 3, and closer to level 2 taking no account of sediment pollutant release. The water quality of Biliuhe Reservoir, overall, is worse in summer and better in winter during the monitoring period. Meanwhile, the water quality shows the tendency of being better from upstream to downstream, and the water quality in the surface layer is better than that in the bottom layer. However, water quality is much closer, or even inferior, to level 3 when considering the release of nitrogen and phosphorus in sediments, and up to 42.7% of the original assessment results of the samples undergo changes. It is concluded that the proposed method is comparatively reasonable as it avoids neglecting sediment pollutant release in the water quality assessment, and the presentation of the evaluation results and change of the water boundary is intuitive with the application of GIS. Full article

Sustainable watershed management (SWM) can be achieved through recognition and reflection upon the values of citizens. Collaborative governance consisting of citizens is crucial for successful SWM. Collaborative governance definitely requires an active participatory decision-making process that reflects citizens’ preferences. Citizen preference also tends to substantially change with life pattern and life quality. These shifts can be caused by slight variations in both social priorities and personal preferences for SWM. Therefore, collaborative water governance must be frequently renewed in response to citizens’ values through the participatory framework. The An’yang Stream in South Korea is generally regarded as a representative urban stream restoration case that has been successfully led by collaborative governance. By conducting individual surveys with citizens on-site, this study addresses how citizens’ preferences of the stream’s management have changed between 2005 and 2015. In addition, this study used three quantitative hydrologic vulnerability indices: potential flood damage (PFD), potential streamflow depletion (PSD), and potential water quality deterioration (PWQD). They can spatially quantify citizen preference using the Analytic Hierarchy Process (AHP), which can systematically derive citizens’ subjective relative-weighted preferences. In the end, this study identified critical differences in priorities in regard to vulnerable areas between in 2005 and in 2015. Full article

Water quality assessment is an important foundation of water resource protection and is affected by many indicators. The dynamic and fuzzy changes of water quality lead to problems for proper assessment. This paper explores a method which is in accordance with the water quality changes. The proposed method is based on the variable fuzzy pattern recognition (VFPR) model and combines the analytic hierarchy process (AHP) model with the entropy weight (EW) method. The proposed method was applied to dynamically assess the water quality of Biliuhe Reservoir (Dailan, China). The results show that the water quality level is between levels 2 and 3 and worse in August or September, caused by the increasing water temperature and rainfall. Weights and methods are compared and random errors of the values of indicators are analyzed. It is concluded that the proposed method has advantages of dynamism, fuzzification and stability by considering the interval influence of multiple indicators and using the average level characteristic values of four models as results. Full article