Saved Queries

Eggshell thickness is a critical indicator for evaluating egg breakage resistance and hatchability, yet traditional measurement methods remain destructive and inefficient. To address this, this study proposes a robust prediction approach by integrating Gradient Boosting Decision Tree (GBDT) feature optimization with an improved CatBoost algorithm. First, a joint strategy of Standard Normal Variate (SNV) and Multiplicative Scatter Correction (MSC) was employed to eliminate spectral scattering noise and enhance organic matrix fingerprint information. Subsequently, GBDT was introduced for nonlinear feature evaluation to adaptively screen the top 50 wavelengths, effectively mitigating the “curse of dimensionality” and multicollinearity in full-spectrum data. A CatBoost regression model was then constructed using an Ordered Boosting mechanism, supported by a dual anti-overfitting strategy that merged 10-fold nested cross-validation with Bootstrap resampling. Experimental results demonstrate that this method significantly outperforms traditional algorithms in both prediction accuracy and generalization. The coefficients of determination (R²) for the calibration and prediction sets reached 0.930 and 0.918, respectively, with a root mean square error of prediction (RMSEP) of 0.008 mm. Residual analysis confirms that prediction errors follow a zero-mean Gaussian distribution, indicating that systematic bias was effectively eliminated. This research provides a reliable theoretical foundation and technical support for the intelligent grading of poultry egg quality. Full article

(This article belongs to the Section Food Analytical Methods)

19 pages, 2591 KB

Open AccessArticle

Integrated Glyco-Analytical Strategy for Comprehensive Characterization of a Complex Therapeutic Glycoprotein: Fabrazyme

by Mikhail Afonin, Polina Novikova, Andrei Vinalev and Natalia Mesonzhnik

Int. J. Mol. Sci. 2026, 27(8), 3358; https://doi.org/10.3390/ijms27083358 (registering DOI) - 8 Apr 2026

Abstract

Fabrazyme (agalsidase beta) is a therapeutic enzyme whose clinical efficacy is contingent upon its complex N-glycosylation patterns. Nevertheless, comprehensive glycosylation profiling remains challenging due to high site-specific heterogeneity. To address this, three orthogonal liquid chromatography–mass spectrometry (LC-MS) approaches were employed: (1) released N-glycan analysis with fluorescence detection and MS annotation, (2) site-specific glycopeptide mapping, and (3) intact protein MS. The released glycan profiling method was validated for reproducibility, intermediate precision, and inter-laboratory transferability, thereby enabling reliable separation and quantification of neutral, phosphorylated, and sialylated species. Glycopeptide mapping revealed distinct site-specific distributions: N108 was found to predominantly carry sialylated complex glycans; N161 was enriched in phosphorylated oligomannose structures; and N184 displayed the highest heterogeneity, including bisphosphorylated and sialylated glycans. Intact protein analysis was performed on both intact and desialylated Fabrazyme, thereby enabling confirmation of glycan assignments. Desialylation reduced spectral complexity, thereby facilitating accurate mass matching with a combinatorial library generated from glycopeptide-level data. The complementary use of these three analytical levels provides a comprehensive view of Fabrazyme glycosylation, offering a robust reference for quality control and biosimilar development. Full article

(This article belongs to the Special Issue Latest Insights into Glycobiology)

25 pages, 5625 KB

Open AccessArticle

Design and Simulation of a Three-DOF Profiling Header for Forage Harvesters in Hilly Terrain

by Zuoxi Zhao, Yuanjun Xu, Wenqi Zou, Shenye Shi and Yangfan Luo

AgriEngineering 2026, 8(4), 145; https://doi.org/10.3390/agriengineering8040145 - 8 Apr 2026

Abstract

To address the problems of uneven stubble height and high missed-cutting rate caused by the insufficient profiling capability of traditional forage harvesters in complex hilly terrain, this paper designs a three-degrees-of-freedom (DOF) profiling header primarily for typical hilly terrain with gentle slopes of 8–15°. Through pitch, roll, and height adjustments, it stably maintains stubble height at 150 mm. Subsequently, geometric analysis and structural optimization achieved kinematic decoupling among all degrees of freedom, thereby overcoming the inherent limitations of the two-DOF header, such as poor adaptability to longitudinal slope and strong adjustment coupling. Three-dimensional modeling was completed in SolidWorks, multibody dynamics simulation was performed in ADAMS, and a profiling control system incorporating a hydraulic system, multi-source sensor fusion, and a fuzzy PID controller was built. The dynamics simulation results show that under the working conditions of 15° longitudinal and 10° transverse slopes, the stubble height error of the header is controlled within 10%, the attitude angle adjustment error is less than 0.5°, and the dynamic response is excellent. Prototype field tests showed that, compared with the two-DOF header, the three-DOF profiling header improved the stubble height stability by about 35%, reduced the missed-cutting rate by about 5%, and increased the operating efficiency by about 15%. No cutting blade contact with the soil occurred, verifying the rationality of the mechanism design and its adaptability to terrain. This study provides an effective technical solution for improving the mechanization level of forage harvesting in hilly and mountainous areas. Full article

(This article belongs to the Special Issue Data-Driven Fields: AI and Unmanned Sensing Technologies in Agricultural Optimization)

►▼ Show Figures

Figure 1

19 pages, 3130 KB

Open AccessArticle

SGMLN: Sentiment-Guided Mutual Learning Network for Multimodal Sarcasm Detection

by Yiran Wang, Xin Zhao and Yongtang Bao

Sensors 2026, 26(8), 2304; https://doi.org/10.3390/s26082304 - 8 Apr 2026

Abstract

Social networks such as Twitter have grown rapidly and are now flooded with sarcastic comments, both in text and in images. Detecting sarcasm in multimodal data has significant social value and is attracting increasing research attention. However, most studies overlook the role of sentiment, even though sentiment information in text is closely linked to clues of sarcasm. Additionally, few consider how text and images align semantically. To address these issues, we propose a sentiment-guided mutual learning network (SGMLN) for multimodal sarcasm detection. SGMLN utilizes sentiment information to inform the combination of text and image features, and employs mutual learning to facilitate knowledge sharing among classifiers. We design a sentiment-guided attention layer that injects sentiment into both modalities, producing features that capture sarcasm more effectively. Sentic-BERT extracts sentiment-aware vectors from text, using word-level sentiment as a mask. In mutual learning, a logistic distribution function measures differences between classifiers, improving knowledge transfer between modalities. This step boosts multimodal understanding and model performance. By introducing sentiment-aware representations and semantic alignment, SGMLN bridges the gap between text and images, making them more consistent. Experiments on public datasets demonstrate that our model is effective and outperforms alternatives. Full article

(This article belongs to the Section Sensing and Imaging)

►▼ Show Figures

Figure 1

17 pages, 2087 KB

Open AccessReview

Tackling Paediatric Dynapenia: AI-Guided Neuromuscular Active Break Model for Early-Year Primary School Students

by Andrew Sortwell, Carmel Mary Diezmann, Rodrigo Ramirez-Campillo and Aron J. Murphy

Appl. Sci. 2026, 16(8), 3654; https://doi.org/10.3390/app16083654 - 8 Apr 2026

Abstract

School-based neuromuscular training interventions have the potential to mitigate dynapenia in the paediatric population and enhance movement skill outcomes; however, translating research into practice in primary school settings has been slow due to the expertise and professional learning required for implementation. This review describes the new teacher-supported intervention ‘Kids Innovative Neuromuscular Enhancement & Teacher-supported Instructional Coaching with AI’ (Kinetic AI) and presents evidence supporting its use in primary school settings. The Scale for the Assessment of Narrative Review Articles (SANRA) was used to guide the narrative and conceptual review methodology employed to synthesise peer-reviewed literature on paediatric dynapenia, school-based neuromuscular training, and AI technology-supported instructional models. This synthesis informed the development of a conceptual approach to neuromuscular training delivery in primary schools. The newly developed Kinetic AI conceptual model provides a pathway to embed neuromuscular training within active class breaks, offering adaptive feedback and targeted teacher support to facilitate implementation. This approach has the potential to bridge gaps between research, access, and practice. The Kinetic AI application is designed to support children’s muscular fitness and movement skills through school-based neuromuscular training, while addressing barriers to research translation and teacher expertise. When applied during school breaks, this approach has the potential to reduce the risk of dynapenia and contribute to scalable improvements in paediatric health and wellbeing. Full article

(This article belongs to the Special Issue Children's Exercise Medicine: Bridging Science and Healthy Futures)

58 pages, 5338 KB

Open AccessReview

Human Bioelectromagnetism and the Environment: Introduction to the Problem

by Ganna Nevoit, Maksim Potyazhenko, Ozar Mintser, Gediminas Jarusevicius and Alfonsas Vainoras

Appl. Sci. 2026, 16(8), 3627; https://doi.org/10.3390/app16083627 (registering DOI) - 8 Apr 2026

Abstract

(1) Background: The increasing contribution of anthropogenic electromagnetic radiation has altered the Earth’s electromagnetic landscape and poses a serious problem for electromagnetic ecology and medicine. The aim of this study was to develop a working theoretical framework to describe the current state of interaction between the human body and electromagnetic fields in the external environment and to facilitate transdisciplinary collaboration among scientists in studying and addressing this problem. (2) Methods: Extensive research has been conducted in the literature to provide a comprehensive presentation of data, enabling a working concept of the interaction between the human body and electromagnetic fields in the external environment. (3) Results: General data, theoretical foundations, mechanisms, and results of the interaction of external electromagnetic fields with the human body were presented. (4) Conclusions: There is a proven interaction between the human body and external electromagnetic fields, as the body is part of the Earth’s electromagnetic landscape and has biophysical mechanisms for coupling with it. The increase in anthropogenic electromagnetic radiation is an electromagnetic environmental problem, and this requires further study of the safety issues and the impact of anthropogenic electromagnetic fields on the human body, and a reassessment of their biological impact on the human body, tightening the standards and requirements for electromagnetic safety in places where people live, a moratorium on further deployment of 5G, urgent application of the precautionary principle, and stricter exposure limits, especially for Wireless Communication Electromagnetic Fields. Full article

(This article belongs to the Special Issue Electromagnetic Radiation and Human Environment)

►▼ Show Figures

Figure 1

27 pages, 24387 KB

Open AccessArticle

Green Pepper Harvesting Robot System Based on Multi-Target Tracking with Filtering and Intelligent Scheduling

by Tianyu Liu, Zelong Liu, Jianmin Wang, Dongxin Guo, Yuxuan Tan and Ping Jiang

Horticulturae 2026, 12(4), 464; https://doi.org/10.3390/horticulturae12040464 - 8 Apr 2026

Abstract

To address the challenges of unstable target localization and poor multi-module coordination in automated green pepper harvesting—caused by occlusions from branches and leaves, as well as varying lighting conditions—this paper presents the design and implementation of a modular robotic picking system. At the perception level, the system integrates a YOLOv8 detector with a RealSense D435i camera to identify and locate the calyx–ectocarp junctions of green peppers. An integrated multi-target tracking and filtering framework is proposed, which fuses multi-feature association, trajectory smoothing and coordinate denoising strategies to suppress depth noise and trajectory jitter, thereby enhancing the stability and accuracy of 3D localization. At the control and execution level, a depth-first picking sequence strategy with ID freeze-state management is implemented within a multithreaded software–hardware co-design architecture. This approach avoids task conflicts and duplicate operations while supporting continuous multi-fruit harvesting. Field experiments under natural outdoor lighting and varying occlusion levels demonstrate that the proposed system achieves recognition rates of 91.57% and 80.29% and harvesting success rates of 82.85% and 77.68% for non-occluded and lightly occluded fruits, respectively. The average picking cycle per pepper fruit is 9.8 s. This system provides an effective technical solution for addressing stability control challenges in the automated harvesting process of green peppers. Full article

(This article belongs to the Section Vegetable Production Systems)

►▼ Show Figures

Figure 1

26 pages, 3491 KB

Open AccessArticle

Alternative Energy Source Integration in Medium-Capacity Gas Boiler Plant in Latvian Climate Conditions: Case Study for 6.38 MW Plant Servicing a Residential District

by Jānis Jākobsons, Filips Kukšinovs, Kristina Ļebedeva, Aleksandrs Zajacs and Jeļena Tihana

Energies 2026, 19(8), 1836; https://doi.org/10.3390/en19081836 - 8 Apr 2026

Abstract

One of the main goals of heat and electricity producers in Latvia is to reduce the use of fossil fuels and introduce alternative fuel types that could help in reducing carbon dioxide emissions. This work focuses on addressing the set issue for a medium-capacity automated gas boiler plant, which provides heat for a local residential district. The following solutions were selected for boiler plant optimization: an electric boiler, a heat storage system, and solar collectors. Operating mode simulations were conducted for the electric boiler and solar collectors using Excel and Polysun (Standard) software. Simulations were created based on energy resource demand data obtained from a residential district located in Latvia and local energy resource prices/heat energy tariffs for the year 2024. The results from the simulations were used for technical and economic calculations to determine the payback period of the project. The electric boiler, together with the thermal energy storage tank and solar collectors, can produce 5903.04 MWh/year (~70% of local district heat demand) of thermal energy. This reduces the CO₂ emissions of the boiler plant by at least 1186.51 tCO₂ per year, which, at an emission quota price of 63.80 EUR/tCO₂, allows for savings of 75,699.34 EUR per year (12.82 EUR/MWh heat energy). The project’s discounted payback period is 4.12 years, considering the reduction in the cost of the CO₂ emission quota. The results of this study show that the chosen technologies are straightforward solutions that can be used to optimize existing boiler plants with limited space and can provide financial benefits to heat energy producers. Full article

►▼ Show Figures

Figure 1

21 pages, 2210 KB

Open AccessArticle

From Wildfires to Sustainable Forest Governance: An Analysis of Media Framing and Social Acceptance in the Mediterranean Context

by Marta Esteve-Navarro, José-Vicente Oliver-Villanueva, Celia Yagüe-Hurtado and Guillermo Palau-Salvador

Sustainability 2026, 18(8), 3687; https://doi.org/10.3390/su18083687 - 8 Apr 2026

Abstract

Mediterranean forests are increasingly exposed to climate-related risks, including large wildfires, prolonged droughts and rural abandonment, making sustainable forest management (SFM) a key element for climate adaptation and territorial resilience. However, despite its recognised importance, the social acceptance of SFM remains insufficiently understood, particularly in relation to how public perceptions are shaped by media narratives and information ecosystems. This study addresses this gap by analysing the relationship between media framing and social acceptance of SFM in a Mediterranean context. A mixed-methods approach was applied in the Valencian region (Spain), combining (i) a systematic analysis of conventional and digital media, (ii) a system mapping exercise to identify dominant narratives and communication dynamics, and (iii) a population survey (n = 1070) focused on perceptions of forests, climate change and forest management. The results reveal a high level of environmental concern and climate awareness, coexisting with limited knowledge of SFM and simplified or distorted perceptions of forest dynamics. Media coverage is predominantly reactive and event-driven, strongly focused on wildfire events, while preventive and adaptive forest management practices remain largely invisible. In this context, support for SFM increases significantly when management practices are clearly explained and contextualised, indicating that resistance is more closely related to communication gaps than to ideological opposition. These findings highlight the critical role of media framing and communication processes in shaping the social acceptance of SFM. The study contributes to the literature by integrating media analysis and social perception within a forest governance perspective, and provides empirical insights to support more effective communication strategies and policy design in Mediterranean regions facing increasing climate pressures. Full article

(This article belongs to the Section Sustainable Forestry)

►▼ Show Figures

Figure 1

25 pages, 595 KB

Open AccessArticle

Reimagining SDG 17 in Africa Through the Marshall Plan Paradigm: A Conceptual Framework for Equitable and Sustainable Global Partnerships

by Olusiji Adebola Lasekan, Margot Teresa Godoy Pena and Blessy Sarah Mathew

Sustainability 2026, 18(8), 3688; https://doi.org/10.3390/su18083688 - 8 Apr 2026

Abstract

This study develops a conceptual framework for reimagining Sustainable Development Goal 17 (SDG 17) in Africa through a reinterpretation of the Marshall Plan’s governance logic. The primary focus is to address persistent failures in development partnerships—namely, fragmentation, weak coordination, power asymmetries, and limited institutional capacity—by proposing a structured model of partnership governance. Using a theory-building methodology grounded in historical analysis and documentary evidence, the study applies a systematic adaptation logic in which core governance mechanisms from the Marshall Plan are re-specified to reflect African institutional realities. These mechanisms—coordination, mutual accountability, collective action, state capacity, and trust—are translated into eight operational pillars: co-development, institutional strengthening, structural transformation, regional integration, blended finance, digital public infrastructure, knowledge co-production, and resilience. The framework conceptualizes SDG 17 as a meta-governance system that aligns actors, institutions, and resources across sectors. By moving from historical abstraction to context-sensitive application, the study contributes a coherent, Africa-centered governance model that enhances partnership effectiveness and informs post-2030 development policy. Full article

(This article belongs to the Special Issue Latest Review Papers in Development Goals Towards Sustainability 2026)

►▼ Show Figures

Figure 1

22 pages, 1888 KB

Open AccessArticle

Predictive Fuzzy Proportional–Integral–Derivative Control for Edge-Based Greenhouse Environmental Regulation

by Wenfeng Li, Jianghua Zhao, Yang Liu, Xi Liu, Shu Lou, Hongyao Xu, Chaoyang Wang, Xuankai Zhang and Zhaobo Huang

Agriculture 2026, 16(8), 829; https://doi.org/10.3390/agriculture16080829 (registering DOI) - 8 Apr 2026

Abstract

To address the strong nonlinearity, coupling, and time-delay characteristics in greenhouse environmental regulation, as well as the large overshoot and limited robustness of conventional proportional–integral–derivative (PID) control, while considering the practical constraint that complex intelligent control methods are difficult to deploy directly on low-cost industrial controllers, this study proposes a predictive fuzzy PID control method for greenhouse environments under programmable logic controller (PLC)-based edge deployment. An integrated remote monitoring and control system with a “PLC–human–machine interface (HMI)–cloud–mobile” architecture was also developed. Based on the intelligent greenhouse experimental platform of Yunnan Agricultural University, the proposed method was validated for greenhouse temperature and air humidity regulation through MATLAB simulations, PLC deployment, and on-site operation tests. The results showed that all four control strategies were able to effectively track the setpoints of greenhouse temperature and humidity, while predictive PID and predictive fuzzy PID achieved better overall performance than conventional PID and fuzzy PID. Predictive fuzzy PID performed best in the humidity channel, whereas its performance in the temperature channel was close to that of predictive PID but with more stable disturbance recovery and better overall balance. On-site operation results further showed that, under typical operating conditions, the tracking error of the actual greenhouse temperature relative to the target temperature could be maintained within approximately ±1 °C, while the error of the actual air humidity relative to the target humidity remained within approximately −2% to 3% RH. These results verify the engineering feasibility of the proposed method on resource-constrained industrial PLC platforms. The proposed method can provide a useful reference for the lightweight and intelligent upgrading of small- and medium-sized greenhouse environmental control systems. Full article

(This article belongs to the Special Issue Research on Plant Production in Greenhouse and Plant Factory Systems—2nd Edition)

28 pages, 16466 KB

Open AccessArticle

SAW-YOLOv8l: An Enhanced Sewer Pipe Defect Detection Model for Sustainable Urban Drainage Infrastructure Management

by Linna Hu, Hao Li, Jiahao Guo, Penghao Xue, Weixian Zha, Shihan Sun, Bin Guo and Yanping Kang

Sustainability 2026, 18(8), 3685; https://doi.org/10.3390/su18083685 - 8 Apr 2026

Abstract

Urban underground sewage pipelines often suffer from defects such as cracks, irregular joint misalignment, and stratified sedimentation blockages, which may lead to pipeline bursts, sewage overflow, and water pollution. Timely detection of abnormal defects in sewage pipelines is critical to ensuring public health and environmental sustainability. Vision-based sewage pipeline defect detection plays a crucial role in modern urban wastewater treatment systems. However, it still faces challenges such as limited feature extraction capabilities, insufficient multi-scale defect characterization, and poor positioning stability when dealing with low-contrast images and in environments with severe background interference. To address this issue, this study proposes an enhanced SAW-YOLOv8l model that integrates RT-DETR (real-time detection Transformer) with CNN (convolutional neural network) architecture. First, a C2f_SCA module improves the long-distance feature extraction capability and localization precision. Second, an AIFI-PRBN module enhances global feature correlation through attention-mechanism-based intra-scale feature interaction and reduces computational complexity using lightweight techniques. Finally, an adaptive dynamic weighted loss function based on Wise-IoU (weighted intersection over union) further improves training convergence and robustness by balancing the gradient distribution of samples. Experiments on a mixed dataset comprising Sewer-ML and industrial images demonstrate that the SAW-YOLOv8l model achieved mAP@0.5 of 86.2% and precision of 84.4%, which were improvements of 2.4% and 6.6% respectively over the baseline model, significantly enhancing the detection performance of abnormal defects in sewage pipelines. Full article

(This article belongs to the Special Issue Exploiting Image Processing, Deep Learning, Machine Learning, and Sustainable Artificial Intelligence Applications)

►▼ Show Figures

Figure 1

23 pages, 9554 KB

Open AccessArticle

RegionGraph: Region-Aware Graph-Based Building Reconstruction from Satellite Imagery

by Lei Li, Chenrong Fang, Wei Li, Kan Chen, Baolong Li and Qian Sun

J. Imaging 2026, 12(4), 161; https://doi.org/10.3390/jimaging12040161 - 8 Apr 2026

Abstract

Structural reconstruction helps infer the spatial relationships and object layouts in a scene, which is an essential computer vision task for understanding visual content. However, it remains challenging due to the high complexity of scene structural topologies in real-world environments. To address this challenge, this paper proposes RegionGraph, a novel method for structural reconstruction of buildings from a satellite image. It utilizes a layout region graph construction and graph contraction approach, introducing a primitive (layout region) estimation network named ConPNet for detecting and estimating different structural primitives. By combining structural extraction and rendering synthesis processes, RegionGraph constructs a graph structure with layout regions as nodes and adjacency relationships as edges, and transforms the graph optimization process into a node-merging-based graph contraction problem to obtain the final structural representation. The experiments demonstrated that RegionGraph achieves a 4% improvement in average F1 scores across three types of primitives and exhibits higher regional completeness and structural coherency in the reconstructed structure. Full article

(This article belongs to the Special Issue Progress, Challenges, and Future Trends in Computer Vision and Pattern Recognition)

►▼ Show Figures

Figure 1

26 pages, 2327 KB

Open AccessArticle

Prediction of Ship Estimated Time of Arrival Based on BO-CNN-LSTM Model

by Qiong Chen, Zhipeng Yang, Jiaqi Gao, Yui-yip Lau and Pengfei Zhang

J. Mar. Sci. Eng. 2026, 14(8), 694; https://doi.org/10.3390/jmse14080694 - 8 Apr 2026

Abstract

Accurate prediction of a ship’s Estimated Time of Arrival (ETA) is of great significance for port scheduling, logistics management, and navigation safety. Traditional ETA prediction approaches often rely on manual experience for parameter tuning, which tends to be inefficient and susceptible to subjective factors. To address this issue and improve prediction accuracy, this study proposes a hybrid modeling framework, integrating Bayesian Optimization (BO), Convolutional Neural Networks (CNNs), and Long Short-Term Memory (LSTM) networks. In this approach, Automatic Identification System (AIS) data is leveraged to predict the total voyage duration before departure, thereby deriving the vessel’s ETA. The model, referred to as BO-CNN-LSTM, utilizes BO for automatic hyperparameter tuning, employs CNN for extracting local features, and applies LSTM network to capture temporal dependencies. The model is developed using a dataset of 32,972 distinct voyage records, among which 23,947 are retained as valid samples after data cleaning. Pearson correlation analysis is conducted to select key input variables, including navigation speed, ship type, sailing distance, and deadweight tonnage. Additionally, sailing distance is processed using the Ramer–Douglas–Peucker algorithm. Experimental evaluation indicates that the BO-CNN-LSTM model achieves a coefficient of determination of 0.987, along with a mean absolute error and root mean square error of 6.078 and 8.730, respectively. These results significantly outperform comparison models such as CNN, LSTM, CNN-LSTM, random forest, AdaBoost, and Elman neural networks. Overall, this study validates the effectiveness and superiority of the proposed BO-CNN-LSTM model in ship ETA prediction, providing an efficient and effective prediction solution for intelligent maritime transportation systems. Full article

(This article belongs to the Section Ocean Engineering)

38 pages, 9459 KB

Open AccessArticle

A Multi-Level Street-View Recognition Framework for Quantifying Spatial Interface Characteristics in Historic Commercial Districts

by Yiyuan Yuan, Zhen Yu and Junming Chen

Buildings 2026, 16(8), 1474; https://doi.org/10.3390/buildings16081474 - 8 Apr 2026

Abstract

In the context of urban renewal, the spatial interface of historic commercial districts functions as both a carrier of historical character and a key setting for commercial activity, public life, and local cultural expression. To address the limitations of conventional studies that rely heavily on field observation and qualitative description, this study takes Xiaohe Zhijie in Hangzhou as a case and develops a multi-level street-view recognition framework for the quantitative analysis of spatial interface characteristics. Based on street-view image collection and standardized preprocessing, a sample database was established at the sampling-point scale. Semantic segmentation, automated commercial object detection, and manual interpretation were combined to identify interface elements, including buildings, sky, greenery, pavement, vehicles, pedestrians, and commercial objects, while commercial content was assessed in terms of locality and homogenization. The results show that Xiaohe Zhijie exhibits a building-dominated and relatively enclosed interface pattern, with greenery and pavement forming the basic environmental ground, weak vehicle interference, and localized enhancement of vitality through commercial objects and pedestrian activities. Significant differences were found among street segments in openness, commercial coverage, and local expression. Three interface types were identified: commercial–cultural composite, local life-oriented, and waterfront landscape–cultural composite. The main challenge lies not in commercialization itself, but in stronger visual locality than content locality and increasing homogenization, resulting in a pattern of “localized form but homogenized content.” Full article

(This article belongs to the Special Issue Digital Twins for Information Management in Digitalization, Sustainability, and Resilience: Bridging Heritage and the Modern Built Environment)

►▼ Show Figures

Figure 1

Show export options Show export options

Select all

Export citation of selected articles as:

Error

Oops... you haven't selected anything for export.

Displaying article 1-50 on page 1 of 2000.

Go to page 1 2 3 4 5

Search Results (146,982)

Further Information

Guidelines

MDPI Initiatives

Follow MDPI