Background: Idiopathic pulmonary fibrosis (IPF) is a type of interstitial lung disease characterized by unknown causes and a poor prognosis. Recent research indicates that age-related mechanisms, such as cellular senescence, may play a role in the development of this condition. However, the relationship between cellular senescence and clinical outcomes in IPF remains uncertain. Methods: Data from the GSE70867 database were meticulously analyzed in this study. The research employed differential expression analysis, as well as univariate and multivariate Cox regression analysis, to pinpoint senescence-related genes (SRGs) linked to prognosis and construct a prognostic risk model. The model’s clinical relevance and its connection to potential biological processes were systematically assessed in training and testing datasets. Additionally, the expression location of prognosis-related SRGs was identified through immunohistochemical staining, and the correlation between SRGs and immune cell infiltration was deduced using the GSE28221 dataset. Result: The prognostic risk model was constructed based on five SRGs (cellular communication network factor 1, CYR61, stratifin, SFN, megakaryocyte-associated tyrosine kinase, MATK, C-X-C motif chemokine ligand 1, CXCL1, LIM domain, and actin binding 1, LIMA1). Both Kaplan-Meier (KM) curves (p = 0.005) and time-dependent receiver operating characteristic (ROC) analysis affirmed the predictive accuracy of this model in testing datasets, with respective areas under the ROC curve at 1-, 2-, and 3-years being 0.721, 0.802, and 0.739. Furthermore, qRT-RCR analysis and immunohistochemical staining verify the differential expression of SRGs in IPF samples and controls. Moreover, patients in the high-risk group contained higher infiltration levels of neutrophils, eosinophils, and M1 macrophages in BALF, which appeared to be independent indicators of poor prognosis in IPF patients. Conclusion: Our research reveals the effectiveness of the 5 SRGs model in BALF for risk stratification and prognosis prediction in IPF patients, providing new insights into the immune infiltration of IPF progression. Full article

Polyaniline has been utilized in various applications, yet its widespread adoption has often been impeded by challenges. Composite systems have been proposed as a means of mitigating some of these limitations, and anthranilic acid (2-aminobenzoic acid) has emerged as a possible moderator for use in co-polymer systems. It offers improved solubility and retention of electroactivity in neutral and alkaline media, and, significantly, it can also bestow chemical functionality through its carboxylic acid substituent, which can greatly ease post-polymer modification. The benefits of using anthranilic acid (as a homopolymer or copolymer) have been demonstrated in applications including corrosion protection, memory devices, photovoltaics, and biosensors. Moreover, this polymer has been used as a versatile framework for the sequestration of metal ions for water treatment, and, critically, these same mechanisms serve as a facile route for the production of catalytic metallic nanoparticles. However, the widespread adoption of polyanthranilic acid has been limited, and the aim of the present narrative review is to revisit the early promise of anthranilic acid and assess its potential future use within modern smart materials. A critical evaluation of its properties is presented, and its versatility as both a monomer and a polymer across a spectrum of applications is highlighted. Full article

Background: Fungal keratitis is an ophthalmic emergency that can cause visual impairment and blindness. We reviewed the epidemiology and clinical features of fungal keratitis in a tropical Australian setting. Objectives: To document the clinical and microbiological characteristics of fungal keratitis in an Australian tropical setting. Methods: A retrospective cohort study of patients with fungal keratitis from October 2014 to December 2022 was conducted at Royal Darwin Hospital, Northern Territory, Australia. We reviewed all patients with culture-proven fungal keratitis and their outcomes. Results: There were 31 patients identified. Aboriginal and Torres Strait Islander (ATSI) patients were of a significantly younger median age (28 years) compared to non-ATSI patients (42 years), and they also presented later to health care. Contact lens use and ocular trauma were the most common predisposing factors. Most patients presented with a corneal infiltrate and corneal epithelial defect, and the central visual axis was affected in 54% of patients. Curvularia spp. and Fusarium spp. were the commonest causative fungi (39% and 30% respectively). Conclusions: Our series is different and reveals a wider range of fungal species identified over the 7 years of the study, in particular, a range of Curvularia spp. were detected. Access to eye health services in rural and remote settings is important, particularly for ATSI patients, as morbidity remains high. Full article

Ternary blended cements, made with silica fume and limestone, provide significant benefits such as improved compressive strength, chloride penetration resistance, sulfates attack, etc. Furthermore, they could be considered low-carbon cements, and they contribute to reducing the depletion of natural resources in reference to water usage, fossil fuel consumption, and mining. Limestone (10%, 15%, and 20%) with different fineness and coarse silica fume (3%, 5%, and 7%) was used to produce ternary cements. The average size of coarse silica fume used was 238 μm. For the first time, the carbonation resistance of ternary Portland cements made with silica fume and limestone has been assessed. The carbonation resistance was assessed by natural carbonation testing. The presence of coarse silica fume and limestone in the blended cement led to pore refinement of the cement-based materials by the filling effect and the C-S-H gel formation. Accordingly, the carbonation resistance of these new ternary cements was less poor than expected for blended cements. Full article

Visual selection plays a fundamental role in various aspects of animal behavior, such as colony formation, maintenance, defense, and courtship. This study investigated the effect of bionic robot fish color on carp behavior based on physiological characteristics that were observed during behavioral experiments. Through computer image processing and analysis of light attenuation, we observed changes in the number and positioning of carp with bionic robotic fish of different colors (white, red, blue, green, and yellow). The results indicated that (1) the attenuation coefficient of visible light in freshwater was red > yellow > green > blue; (2) the order of the average change in the number of carp responding to different colors of robotic fish was white > red > green > yellow > blue, and carp were more sensitive and responsive to white and red robotic fish; and (3) the order of the distances between different colors of robotic fish and carp was white < yellow < blue < green < red, and white and yellow robotic fish were more attractive to carp. Therefore, the use of white or yellow robotic fish for relevant operations can reduce disturbance to fish schools. Full article

(1) Introduction: Digitalis use in patients with severe heart failure is controversial. We assessed the effects of digitalis therapy on mortality in a large, observational study in recipients of cardiac resynchronization therapy (CRT). (2) Methods: Consecutive patients receiving a CRT-defibrillator in three European tertiary referral centers were enrolled and followed-up for a mean 37 months ± 28 months. Digitalis use was assessed at the time of CRT implantation. A multivariate Cox-regression model and propensity score matching were used to determine all-cause mortality as the primary endpoint. CRT-response (defined as improvement of ≥1 NYHA class), echocardiographic improvement (defined as improvement of LVEF of ≥ 5%) and incidence of ICD shocks and rehospitalization were assessed as secondary endpoints in a subgroup of patients. (3) Results: The study comprised 552 CRT-recipients with standard indications, including 219 patients (40%) treated with digitalis. Compared to patients without digitalis, they had more often atrial fibrillation, poorer LVEF and a higher NYHA class (all p ≤ 0.002). Crude analysis of all-cause mortality demonstrated a similar relative risk of death for patients with and without digitalis (HR = 1.14; 95% CI 0.88–1.5; p = 0.40). After adjustment for independent predictors of mortality, digitalis therapy did not alter the risk for death (adjusted HR = 1.04; 95% CI 0.75–1.45; p = 0.82). Furthermore, in comparison to 286 propensity-score-matched patients, mortality was not affected by digitalis intake (propensity-adjusted HR = 1.11; 95% CI 0.72–1.70; p = 0.64). A CRT-response was predominant in digitalis non-users, concerning both improvement of HF symptoms and LVEF (NYHA p < 0.01; LVEF p < 0.01), while patients on digitalis had more often ventricular tachyarrhythmias requiring ICD shock (p = 0.01); although, rehospitalization for cardiac reasons was significantly lower among digitalis users compared to digitalis non-users (HR = 0.58; 95% C. I. 0.40–0.85; p = 0.01). (4) Conclusions: Digitalis therapy had no effect on mortality, but was associated with a reduced response to CRT and increased susceptibility to ventricular arrhythmias requiring ICD shock treatment. Although, digitalis administration positively altered the likelihood for cardiac rehospitalization during follow-up. Full article

The present study aimed to systematically investigate the underlying differences in flesh quality between wild and farmed Monopterus albus. Fifteen healthy M. albus per group with an average body weight of 45 g were sampled to analyze muscle parameters by biochemical indicators, histomorphology, and molecular biology. Compared with the wild fish, the farmed M. albus in flesh had lower crude protein, collagen, lysine, histidine, total amino acids, SFA, n-3 PUFA contents, and n-3/n-6 ratio (p < 0.05), and higher moisture, crude lipid, crude ash, MUFA, n-6PUFA, and total PUFA contents (p < 0.05). The thawing loss, drip loss, steaming loss, and boiling loss in the farmed group were significantly higher, and hardness, springiness, cohesiveness, gumminess, chewiness, and resilience were significantly lower than those in the wild group (p < 0.05). In addition, higher muscle fiber density and lower muscle fiber diameter were observed in wild M. albus (p < 0.05). In muscle transcriptome profiling, differentially expressed genes and enriched pathways are primarily associated with muscle development, protein synthesis, catabolism, lipid metabolism, and immunity. To the best of our knowledge, this is the first investigation that compares the flesh quality between wild and farmed M. albus in terms of biochemistry, histology, and molecular biology levels. Overall, wild M. albus had a higher nutritional value and texture quality than farmed M. albus. Full article

The classifier is an essential tool for the development of contemporary engineering technology. The application of classifiers is to categorize mixed-sized particles into multi-stage uniform particle sizes. In current studies, the particles in the classifier obtain their initial velocity when feeding. The classification effect is impacted by the inability to precisely control the initial state of the particles. To solve this problem, a pusher feed classifier was designed in this study, and a numerical simulation was performed to investigate its flow field characteristics and classification performance using the RNG-DPM method. A pusher is utilized to achieve particle feeding without initial velocity and to precisely control the initial state of the particles in the classification flow field. A newly developed two-way air inlet structure is designed to provide a superimposed flow field and enable the five-stage classification. Our results show that this pusher feed classifier has the best classification effect when the vertical airflow velocity is 10 m/s and the horizontal airflow velocity is 3 m/s. Meanwhile, the classification size ratio (CSR) from outlet 1 to outlet 5 was 1.24, 0.55, 0.45, 0.39, and 0.15, respectively. Full article

Dendritic cells (DCs) are a heterogeneous group of antigen-presenting cells crucial for fostering allograft tolerance while simultaneously supporting host defense against infections and cancer. Within the tumor microenvironment, DCs can either mount an immune response against cancer cells or foster immunotolerance, presenting a dual role. In immunocompromised individuals, posttransplant malignancies pose a significant health concern, with DCs serving as vital players in immune responses against cancer cells. Both recipient- and donor-derived DCs play a critical role in the rejection process, infiltrating the transplanted organ and sustaining T-cell responses. The use of immunosuppressive drugs represents the predominant approach to control this immunological barrier in transplanted organs. Evidence has shed light on the immunopharmacology of these drugs and novel strategies for manipulating DCs to promote allograft survival. Therefore, comprehending the mechanisms underlying this intricate microenvironment and the effects of immunosuppressive therapy on DCs is crucial for developing targeted therapies to reduce graft failure rates. This review will delve into the fundamental immunobiology of DCs and provide a detailed exploration of their clinical significance concerning alloimmune responses and posttransplant malignancies. Full article

Due to the rising annual incidence of lung cancer (LC), new treatment strategies are needed. While various options exist, many, if not all, remain suboptimal. Several studies have shown cryoablation to be a promising approach. Yet, a lack of basic information pertaining to LC response to freezing and requirement for percutaneous access has limited clinical use. In this study, we investigated the A549 lung carcinoma cell line response to freezing. The data show that a single 5 min freeze to −15 °C did not affect cell viability, whereas −20 °C and −25 °C result in a significant reduction in viability 1 day post freeze to <10%. These populations, however, were able to recover in culture. Application of a repeat (double) freeze resulted in complete cell death at −25 °C. Studies investigating the impact of adjunctive gemcitabine (75 nM) pretreatment in combination with freezing were then conducted. Exposure to gemcitabine alone resulted in minimal cell death. The combination of gemcitabine pretreatment and a −20 °C single freeze as well as combination treatment with a −15 °C repeat freeze both resulted in complete cell death. This suggests that gemcitabine pretreatment may be synergistically effective when combined with freezing. Studies into the modes of cell death associated with the increased cell death revealed the increased involvement of necroptosis in combination treatment. In summary, these results suggest that repeat freezing to −20 °C to −25 °C results in a high degree of LC destruction. Further, the data suggest that the combination of gemcitabine pretreatment and freezing resulted in a shift of the minimum lethal temperature for LC from −25 °C to −15 °C. These findings, in combination with previous reports, suggest that cryoablation alone or in combination with chemotherapy may provide an improved path for the treatment of LC. Full article

Abnormal skin healing resulting in chronic wounds or hypertrophic scarring remains a major healthcare burden. Here, the antifibrotic angiotensin II type 2 receptor (AT2R) signaling pathway was modulated to determine its impact on cutaneous wound healing. Balb/c mice received two splinted full-thickness wounds. Topical treatments with the selective AT2R agonist compound 21 (C21) and/or selective antagonist PD123319 or saline vehicle were administered until sacrifice on post-wounding days 7 or 10. The rate of wound re-epithelialization was accelerated by PD123319 and combination treatments. In vitro, C21 significantly reduced human fibroblast migration. C21 increased both collagen and vascular densities at days 7 and 10 post-wounding and collagen I:III ratio at day 10, while PD123319 and combination treatments decreased them. Genes associated with regeneration and repair were upregulated by C21, while PD123319 treatment increased the expression of genes associated with inflammation and immune cell chemotaxis. C21 treatment reduced wound total leukocyte and neutrophil staining densities, while PD123319 increased these and macrophage densities. Overall, AT2R activation with C21 yields wounds that mature more quickly with structural, cellular, and gene expression profiles more closely approximating unwounded skin. These findings support AT2R signal modulation as a potential therapeutic target to improve skin quality during wound healing. Full article

Long-chain polyunsaturated omega-3 fatty acids (n-3 PUFAs), particularly docosahexaenoic acid (DHA) and eicosapentaenoic acid (EPA), are recommended as beneficial dietary supplements for enhancing cognitive function. Although fish oil (FO) is renowned for its abundant n-3 PUFA content, combining FO with other natural products is considered as a viable option to support the sustainable development of FO products. This review aims to provide comprehensive insights into the advanced effects of combining FO or its components of DHA and EPA with natural products on protecting cognitive function. In two double-blind random control trials, no advanced effects were observed for adding curcumin to FO on cerebral function protection. However, 16 week’s treatment of FO combined with vitamin E did not yield any advanced effects in cognitive factor scores. Several preclinical studies have demonstrated that combinations of FO with natural products can exhibit advanced effects in addressing pathological components in cognitive impairment, including neuroinflammation, oxidative stress, and neuronal survival. In conclusion, evidence from clinical trials for beneficial use of FO and natural ingredients combination is lacking. Greater cohesion is needed between preclinical and clinical data to substantiate the efficacy of FO and natural product combinations in preventing or slowing the progression of cognitive decline. Full article

This paper aims to study the asymptotic properties of nonoscillatory solutions (eventually positive or negative) of a class of third-order canonical neutral differential equations. We use Riccati substitution to reduce the order of the considered equation, and then we use the Philos function class to obtain new criteria of the Kamenev type, which guarantees that all nonoscillatory solutions converge to zero. This approach is characterized by the possibility of applying its conditions to a wider area of equations. This is not the only aspect that distinguishes our results; we also use improved relationships between the solution and the corresponding function, which in turn is reflected in a direct improvement of the criteria. The findings in this article extend and generalize previous findings in the literature and also improve some of these findings. Full article

Our study examines how dengue fever incidence is associated with spatial (demographic and socioeconomic) alongside temporal (environmental) factors at multiple scales in the city of Ibagué, located in the Andean region of Colombia. We used the dengue incidence in Ibagué from 2013 to 2018 to examine the associations with climate, socioeconomic, and demographic factors from the national census and satellite imagery at four levels of local spatial aggregation. We used geographically weighted regression (GWR) to identify the relevant socioeconomic and demographic predictors, and we then integrated them with environmental variables into hierarchical models using integrated nested Laplace approximation (INLA) to analyze the spatio-temporal interactions. Our findings show a significant effect of spatial variables across the different levels of aggregation, including human population density, gas and sewage connection, percentage of woman and children, and percentage of population with a higher education degree. Lagged temporal variables displayed consistent patterns across all levels of spatial aggregation, with higher temperatures and lower precipitation at short lags showing an increase in the relative risk (RR). A comparative evaluation of the models at different levels of aggregation revealed that, while higher aggregation levels often yield a better overall model fit, finer levels offer more detailed insights into the localized impacts of socioeconomic and demographic variables on dengue incidence. Our results underscore the importance of considering macro and micro-level factors in epidemiological modeling, and they highlight the potential for targeted public health interventions based on localized risk factor analyses. Notably, the intermediate levels emerged as the most informative, thereby balancing spatial heterogeneity and case distribution density, as well as providing a robust framework for understanding the spatial determinants of dengue. Full article

Studying the ecological niches of species and their responses to climate change can provide better conservation strategies for these species. Myrothamnaceae is endemic to Africa, comprising only two species that belong to Myrothamnus (M. flabellifolius and M. moschatus). These closely related species exhibit allopatric distributions, positioning them as ideal materials for studying the species ecological adaptation. This study explores the ecological niche differentiation between M. flabellifolius and M. moschatus and their response capabilities to future climate change. The results indicate that M. flabellifolius and M. moschatus have undergone niche differentiation. The main drivers of niche differences are the minimum temperature of the coldest month (Bio6) for M. flabellifolius, precipitation of the driest month (Bio14), and precipitation of the coldest quarter (Bio19) for M. moschatus. M. flabellifolius demonstrated a stronger adaptation to environments characterized by lower precipitation, relatively lower temperatures, and greater annual temperature variations compared to M. moschatus. Under future climate scenarios (SSP5-8.5, 2081–2100 years), the results show that approximately 85% of the total suitable habitat for M. flabellifolius will be lost, with an 85% reduction in high-suitability areas and almost complete loss of the original mid-low suitability areas. Concurrently, about 29% of the total suitable habitat for M. moschatus will be lost, with a 34% reduction in high suitability areas and roughly 60% of the original mid-low suitability areas becoming unsuitable. This suggests that M. flabellifolius will face greater threats under future climate change. This study contributes novel insight into niche differentiation in Myrothamnaceae and provides useful information for the conservation of this distinctive African lineage. Full article

The circular hollow steel-reinforced concrete (HSRC) column consists of an inner circular hollow steel tube and outer circular hollow reinforced concrete (RC). This design provides several advantages, including being lightweight, having a wide sectional profile, and having a high flexural stiffness. This paper aims to investigate the behavior of the circular HSRC columns under axial compression through testing and finite element (FE) modeling. An FE model was established to simulate the circular HSRC columns under axial compression, which was validated against the test data. Additionally, the load distribution and the interface stress between the outer hollow RC and inner steel tube were analyzed. Subsequently, a systematic parametric analysis was conducted on the diameter (d) and thickness (t) of the steel tube; slenderness ratio (λ); strength of concrete (f_cu); yield strength of steel tube (f_sy), longitudinal rebar (f_ly), and stirrup (f_gy); as well as the stirrup spacing (s). The critical influencing factors of the circular HSRC columns under axial compression were identified. f_cu, λ, d, f_ly, and f_sy dramatically influence the bearing capacity, and the stiffness is notably affected by λ and f_cu. Finally, three simplified design methods were summarized and evaluated for calculating the bearing capacity of the circular HSRC columns under axial compression. Full article

In this study, a novel composite solder, Sn-3.5Ag-10.0Co, was tailored for transient liquid phase (TLP) bonding in electric vehicle power module integration. Employing a meticulous two-step joining process, the solder joint was transformed into a robust microstructure characterized by two high-melting point intermetallic compounds, Ni₃Sn₄ and (Co,Ni)Sn₂. After 1 h of TLP bonding, the Sn-3.5Ag-10.0Co paste transformed into the IMCs, but voids persisted between them, particularly between (Co,Ni)Sn₂ and Ni₃Sn₄. Voids significantly reduced after 2 h of bonding, with full coalescence of the joint microstructure observed. The joint continued to be densified after 3 h of TLP bonding, but voids tended to accumulate at the joint center. Failure analysis revealed crack propagation through Ni₃Sn₄/(Co,Ni)Sn₂ interfaces and internal voids. The engineered Sn-Ag-Co TLP joint exhibited superior shear strength retention even at an elevated temperature of 200 °C, contrasting with the significant reduction observed in the Sn-3.5Ag control specimen due to remaining Sn. Full article

Several attacks have been proposed against autonomous vehicles and their subsystems that are powered by machine learning (ML). Road sign recognition models are especially heavily tested under various adversarial ML attack settings, and they have proven to be vulnerable. Despite the increasing research on adversarial ML attacks against road sign recognition models, there is little to no focus on defending against these attacks. In this paper, we propose the first defense method specifically designed for autonomous vehicles to detect adversarial ML attacks targeting road sign recognition models, which is called ViLAS (Vision-Language Model for Adversarial Traffic Sign Detection). The proposed defense method is based on a custom, fast, lightweight, and salable vision-language model (VLM) and is compatible with any existing traffic sign recognition system. Thanks to the orthogonal information coming from the class label text data through the language model, ViLAS leverages image context in addition to visual data for highly effective attack detection performance. In our extensive experiments, we show that our method consistently detects various attacks against different target models with high true positive rates while satisfying very low false positive rates. When tested against four state-of-the-art attacks targeting four popular action recognition models, our proposed detector achieves an average AUC of 0.94. This result achieves a 25.3% improvement over a state-of-the-art defense method proposed for generic image attack detection, which attains an average AUC of 0.75. We also show that our custom VLM is more suitable for an autonomous vehicle compared to the popular off-the-shelf VLM and CLIP in terms of speed (4.4 vs. 9.3 milliseconds), space complexity (0.36 vs. 1.6 GB), and performance (0.94 vs. 0.43 average AUC). Full article

In the field of underwater acoustics, the signal-to-noise ratio (SNR) is generally low, and the underwater environment is complex and variable, making target azimuth estimation highly challenging. Traditional model-based subspace methods exhibit significant performance degradation when dealing with coherent sources, low SNR, and small snapshot data. To overcome these limitations, an improved model based on SubspaceNet, called PConv-GAM Residual SubspaceNet (PGR-SubspaceNet), is proposed. This model embeds the global attention mechanism (GAM) into residual blocks that fuse PConv convolution, making it possible to capture richer cross-channel and positional information. This enhancement helps the model learn signal features in complex underwater conditions. Simulation results demonstrate that the underwater target azimuth estimation method based on PGR-SubspaceNet exhibits lower root mean square periodic error (RMSPE) values when handling different numbers of narrowband coherent sources. Under low SNR and limited snapshot conditions, its RMSPE values are significantly better than those of traditional methods and SubspaceNet-based enhanced subspace methods. PGR-SubspaceNet extracts more features, further improving the accuracy of direction-of-arrival estimation. Preliminary experiments in a pool validate the effectiveness and feasibility of the underwater target azimuth estimation method based on PGR-SubspaceNet. Full article

Early detection of plant nutrient deficiency is crucial for agricultural productivity. This study investigated the performance and interpretability of Convolutional Neural Networks (CNNs) for this task. Using the rice and banana datasets, we compared three CNN architectures (CNN, VGG-16, Inception-V3). Inception-V3 achieved the highest accuracy (93% for rice and banana), but simpler models such as VGG-16 might be easier to understand. To address this trade-off, we employed Explainable AI (XAI) techniques (SHAP and Grad-CAM) to gain insights into model decision-making. This study emphasises the importance of both accuracy and interpretability in agricultural AI and demonstrates the value of XAI for building trust in these models. Full article

The construction of new towns is one of the main measures to evacuate urban populations and promote regional coordination and urban–rural integration in China. Mining the spatio-temporal pattern of new town hot spots based on multivariate data and analyzing the influencing factors of new town construction hot spots can provide a strategic basis for new town construction, but few researchers have extracted and analyzed the influencing factors of new town internal hot spots and their classification. In order to define the key points of Wuhan’s new town construction and promote the construction of new cities in an orderly and efficient manner, this paper first constructs a space-time cube based on the luminous remote sensing data from 2010 to 2019, extracts hot spots and emerging hot spots in Wuhan New City, selects 14 influencing factor indicators such as population density, and uses bivariate Moran’s index to analyze the influencing factors of hot spots, indicating that the number of bus stops and vegetation coverage rate are the most significant. Secondly, the disorderly multivariate logistic regression model is used to analyze the influencing factors of emerging hot spots. The results show that population density, vegetation coverage, road density, distance to water bodies, and distance to train stations are the most significant factors. Finally, based on the analysis results, some relevant suggestions for the construction of Wuhan New City are proposed, providing theoretical support for the planning and policy guidance of new cities, and offering reference for the construction of new towns in other cities, promoting the construction of high-quality cities. Full article

Building land-use type classification using earth observation data is essential for urban planning and emergency management. Municipalities usually do not hold a detailed record of building land-use types in their jurisdictions, and there is a significant need for a detailed classification of this data. Earth observation data can be beneficial in this regard, because of their availability and requiring a reduced amount of fieldwork. In this work, we imported Google Street View (GSV), light detection and ranging-derived (LiDAR-derived) features, and orthophoto images to deep learning (DL) models. The DL models were trained on building land-use type data for the Greater Toronto Area (GTA). The data was created using building land-use type labels from OpenStreetMap (OSM) and web scraping. Then, we classified buildings into apartment, house, industrial, institutional, mixed residential/commercial, office building, retail, and other. Three DL-derived classification maps from GSV, LiDAR, and orthophoto images were combined at the decision level using the proposed ranking classes based on the F1 score method. For comparison, the classifiers were combined using fuzzy fusion as well. The results of two independent case studies, Vancouver and Fort Worth, showed that the proposed fusion method could achieve an overall accuracy of 75%, up to 8% higher than the previous study using CNNs and the same ground truth data. Also, the results showed that while mixed residential/commercial buildings were correctly detected using GSV images, the DL models confused many houses in the GTA with mixed residential/commercial because of their similar appearance in GSV images. Full article