Search Results (839)

Phishing attacks are an increasingly common cybersecurity threat and are characterized by deceiving people into giving out their private credentials via emails, websites, and messages. An insight into students’ challenges in recognizing phishing threats can provide valuable information on how AI-based detection systems can be improved to enhance accuracy, reduce false positives, and build user trust in cybersecurity. This study focuses on students’ awareness of phishing attempts and evaluates AI-based phishing detection systems. Questionnaires were circulated amongst students, and responses were evaluated to uncover prevailing patterns and issues. The results indicate that most college students are knowledgeable about phishing methods, but many do not recognize the dangers of phishing. Because of this, AI-based detection systems have potential but also face issues relating to accuracy, false positives, and user faith. This research highlights the importance of bolstering cybersecurity education and ongoing enhancements to AI models to improve phishing detection. Future studies should include a more representative sample, evaluate AI detection systems in real-world settings, and assess longer-term changes in phishing-related awareness. By combining AI-driven solutions with education a safer digital world can created. Full article

Background/Objectives: Electrochemotherapy (ECT) has emerged as a promising locoregional treatment modality for patients with cutaneous and subcutaneous melanoma metastases. While systemic therapies have improved overall disease control, effective local tumor management remains crucial, particularly in oligometastatic or symptomatic disease. This pilot study investigates the role of metabolic imaging with [¹⁸F]FDG PET/CT to assess tumor metabolism in melanoma patients undergoing ECT, building on prior evidence that PET offers valuable functional information beyond anatomical changes detected by conventional imaging. Methods: This retrospective study included 11 patients with histologically confirmed melanoma and cutaneous or subcutaneous metastases treated with ECT. [¹⁸F]FDG PET/CT scans were performed either before ECT, after ECT, or both. Metabolic response was assessed by measuring the tracer uptake (SUV_max) of the ten hottest lesions. Morphological changes were evaluated using CT. Local progression-free survival was determined. Results: A total of 66 lesions were analyzed. Patients with PET/CT only after ECT showed significantly higher SUV_max and lesion size compared to those imaged before treatment (mean SUV_max: 9.9 ± 11.2 vs. 10.3 ± 5.5; p = 0.034). Progression-free survival differed significantly based on pre-ECT SUV_max values (χ² = 3.90; p = 0.048). Among two patients with follow-up imaging, one showed new lesions on CT with only mild FDG uptake, while the other developed newly FDG-avid metastases after ECT. Conclusions: FDG PET/CT provides valuable information on tumor viability and treatment response in melanoma patients undergoing ECT, demonstrated by significant differences in metabolic activity between lesions imaged before and after treatment. The lack of longitudinal intra-individual imaging limits definitive conclusions about the direct metabolic effects of ECT. Full article

Observing building changes in remote sensing images plays a crucial role in monitoring urban development and promoting sustainable urbanization. Mainstream change detection methods have demonstrated promising performance in identifying building changes. However, buildings have large intra-class variance and high similarity with other objects, limiting the generalization ability of models in diverse scenarios. Moreover, most existing methods only detect whether changes have occurred but ignore change types, such as new construction and demolition. To address these issues, we present a building change-type detection network (BCTDNet) based on the Segment Anything Model (SAM) to identify newly constructed and demolished buildings. We first construct a dual-feature interaction encoder that employs SAM to extract image features, which are then refined through trainable multi-scale adapters for learning architectural structures and semantic patterns. Moreover, an interactive attention module bridges SAM with a Convolutional Neural Network, enabling seamless interaction between fine-grained structural information and deep semantic features. Furthermore, we develop a change-aware attribute decoder that integrates building semantics into the change detection process via an extraction decoding network. Subsequently, an attribute-aware strategy is adopted to explicitly generate distinct maps for newly constructed and demolished buildings, thereby establishing clear temporal relationships among different change types. To evaluate BCTDNet’s performance, we construct the JINAN-MCD dataset, which covers Jinan’s urban core area over a six-year period, capturing diverse change scenarios. Moreover, we adapt the WHU-CD dataset into WHU-MCD to include multiple types of changing. Experimental results on both datasets demonstrate the superiority of BCTDNet. On JINAN-MCD, BCTDNet achieves improvements of 12.64% in IoU and 11.95% in F1 compared to suboptimal methods. Similarly, on WHU-MCD, it outperforms second-best approaches by 2.71% in IoU and 1.62% in F1. BCTDNet’s effectiveness and robustness in complex urban scenarios highlight its potential for applications in land-use analysis and urban planning. Full article

Point-type smoke fire detectors have become one of the most commonly used technical means in the fire detection systems of ancient buildings. However, in practical applications, their performance is easily affected by special environmental interference factors. Therefore, in this study, a full-scale experimental scene of an ancient building with a typical flush gable roof structure was taken as the research object, and the differential influence laws of three typical interference sources, namely wind speed, water vapor, and incense burning, on the response times of point-type smoke detectors were quantified. Moreover, the prediction models of the alarm time of the detectors under the three interference conditions were established. The results indicate the following: (1) Within the range of experimental conditions, there is a quantitative relationship between the detector response delay and the type of interference source: the delay time shows a nonlinear positive correlation with the wind speed/water vapor interference gradient, while it exhibits a threshold unimodal change characteristic with the burning incense interference gradient; (2) under interference conditions, the detector response delay varies depending on the type of fire source: the detector has the best detection stability for smoldering smoke from a smoke cake, while it has the lowest detection sensitivity for smoldering smoke from a cotton rope. Moreover, the influence of wind speed interference is weaker than that of water vapor or smoke from burning incense, and the difference is the greatest in the wood block smoldering condition. (3) Construct a detector alarm time prediction model under three types of interference conditions, where the wind speed, water vapor, and burning incense interference conditions conform to third-order polynomial functions, Sigmoid functions, and fourth-order polynomial functions, respectively. Full article

Building change detection and building damage assessment are two essential tasks in post-disaster analysis. Building change detection focuses on identifying changed building areas between bi-temporal images, while building damage assessment involves segmenting all buildings and classifying their damage severity. These tasks play a critical role in disaster response and urban development monitoring. Although supervised learning has significantly advanced building change detection and damage assessment, its reliance on large labeled datasets remains a major limitation. In contrast, self-supervised learning enables the extraction of meaningful data representations without explicit training labels. To address this challenge, we propose a self-supervised learning approach that unifies denoising autoencoders and contrastive learning, enabling effective data representation for building change detection and damage assessment. The proposed architecture integrates a dual denoising autoencoder with a Vision Transformer backbone and contrastive learning strategy, complemented by a Feature Pyramid Network-ResNet dual decoder and an Edge Guidance Module. This design enhances multi-scale feature extraction and enables edge-aware segmentation for accurate predictions. Extensive experiments were conducted on five public datasets, including xBD, LEVIR, LEVIR+, SYSU, and WHU, to evaluate the performance and generalization capabilities of the model. The results demonstrate that the proposed Denoising AutoEncoder-enhanced Dual-Fusion Network (DAEDFN) approach achieves competitive performance compared with fully supervised methods. On the xBD dataset, the largest dataset for building damage assessment, our proposed method achieves an F1 score of 0.892 for building segmentation, outperforming state-of-the-art methods. For building damage severity classification, the model achieves an F1 score of 0.632. On the building change detection datasets, the proposed method achieves F1 scores of 0.837 (LEVIR), 0.817 (LEVIR+), 0.768 (SYSU), and 0.876 (WHU), demonstrating model generalization across diverse scenarios. Despite these promising results, challenges remain in complex urban environments, small-scale changes, and fine-grained boundary detection. These findings highlight the potential of self-supervised learning in building change detection and damage assessment tasks. Full article

Change detection (CD) in remote sensing (RS) is a fundamental task that seeks to identify changes in land cover by analyzing bitemporal images. In recent years, deep learning (DL)-based approaches have demonstrated remarkable success in a wide range of CD applications. However, most existing methods have limitations in detecting building edges and addressing pseudo-changes, and lack the ability to model feature context. In this paper, we introduce DFANet—a Deep Feature Attention Network specifically designed for building CD in RS imagery. First, we devise a spatial-channel attention module to strengthen the network’s capacity to extract change cues from bitemporal feature maps and reduce the occurrence of pseudo-changes. Second, we introduce a GatedConv module to improve the network’s capability for building edge detection. Finally, Transformer is introduced to capture long-range dependencies across bitemporal images, enabling the network to better understand feature change patterns and the relationships between different regions and land cover categories. We carried out comprehensive experiments on two publicly available building CD datasets—LEVIR-CD and WHU-CD. The results demonstrate that DFANet achieves exceptional performance in evaluation metrics such as precision, F1 score, and IoU, consistently outperforming existing state-of-the-art approaches. Full article

Wildfires are becoming an increasingly severe threat to European forests, driven by climate change, land use changes, and socio-economic factors. Integrated solutions for wildfire prevention, early detection, emergency management, and ecological restoration are urgently needed to enhance forest resilience. The Horizon 2020 SILVANUS project developed a comprehensive multi-sectoral platform combining technological innovation, stakeholder engagement, and sustainable forest management strategies. This report analyses the Slovak Republic’s participation in SILVANUS, applying a seven-criterion fit–gap framework (governance, legal, interoperability, staff capacity, ecological suitability, financial feasibility, and stakeholder acceptance) to evaluate the platform’s alignment with national conditions. Notable contributions include stakeholder-supported functional requirements for wildfire prevention, climate-sensitive forest models for long-term adaptation planning, IoT- and UAV-based early fire detection technologies, and decision support systems (DSS) for emergency response and forest-restoration activities. The Slovak pilot sites, particularly in the Podpoľanie region, served as important testbeds for the validation of these tools under real-world conditions. All SILVANUS modules scored ≥12/14 in the fit–gap assessment; early deployment reduced high-risk fuel polygons by 23%, increased stand-level structural diversity by 12%, and raised the national Sustainable Forest Management index by four points. Integrating SILVANUS outcomes into national forestry practices would enable better wildfire risk assessment, improved resilience planning, and more effective public engagement in wildfire management. Opportunities for adoption include capacity-building initiatives, technological deployments in fire-prone areas, and the incorporation of DSS outputs into strategic forest planning. Potential challenges, such as technological investment costs, inter-agency coordination, and public acceptance, are also discussed. Overall, the Slovak Republic’s engagement with SILVANUS demonstrates the value of participatory, technology-driven approaches to sustainable wildfire management and offers a replicable model for other European regions facing similar challenges. Full article

Under the background of global climate change, shallow landslide clusters induced by extreme rainfall are occurring with increasing frequency, causing severe casualties and economic losses. To address this challenge, this study proposes an integrated approach to support both emergency response and long-term mitigation for rainfall-induced shallow landslides. The workflow includes (1) rapid landslide detection based on time-series image fusion and threshold segmentation on the Google Earth Engine (GEE) platform; (2) numerical simulation of landslide runout using the R.avaflow model; (3) landslide susceptibility assessment based on event-driven inventories and machine learning; and (4) delineation of high-risk slopes by integrating simulation outputs, susceptibility results, and exposed elements. Applied to Qugaona Township in Zhouqu County, Bailong River Basin, the framework identified 747 landslides. The R.avaflow simulations captured the spatial extent and depositional features of landslides, assisting post-disaster operations. The Gradient Boosting-based susceptibility model achieved an accuracy of 0.870, with 8.0% of the area classified as highly susceptible. In Cangan Village, high-risk slopes were delineated, with 31.08%, 17.85%, and 22.42% of slopes potentially affecting buildings, farmland, and roads, respectively. The study recommends engineering interventions for these areas. Compared with traditional methods, this approach demonstrates greater applicability and provides a more comprehensive basis for managing rainfall-induced landslide hazards. Full article

This paper focuses on optimizing sensor placement in structures for load monitoring applications. Such applications rely on sensor data to track changes in the structure. Monitoring accuracy relies on proper sensor placement. The goal is to maximize load monitoring accuracy under multiple loading scenarios while the number of sensors is kept smaller than the number of load cases. Building on prior work in which machine learning models predicted loads using only sensor readings without information on load location, this study continues that approach. It demonstrates that prediction models perform better when sensor networks are optimized. The novelty lies in a newly formulated objective function, allowing for optimization of sensor number, positions, and orientations across multiple load cases and measurement types. The goal is to minimize the differences between maximal responses of the structure and detected responses by the sensors (for all possible load cases). The method is validated on a numerical model of a composite structure with 1–3 sensors under seven different load cases. Load predictions from sensors in optimized locations are compared to predictions from measurements of randomly positioned sensors. Statistical comparison proved that the developed methods and algorithms allow us to significantly reduce the prediction errors. Full article

In this work, we investigate the fundamental usability of fluorescent DNA-templated silver nanoclusters (DNA-AgNCs) as sensors for Point-of Care-Testing (PoCT) applications. We developed a microfluidic platform for the generation of droplets containing DNA-AgNCs in defined, different chemical environments. The droplets are read out fluorescently at two different emission wavelengths. For the pre-evaluation for the usage of biologically relevant matrices with DNA-AgNCs, the response of two different DNA-AgNCs to a variation in pH and sodium chloride concentration was acquired. Our compact and simple setup can detect DNA-AgNCs well below 100 nM and allows the characterization of the fluorescence response of DNA-based biohybrid nanosensors to changes in the chemical environment within short measurement times. The model DNA-AgNCs remain fluorescent throughout the physiologically relevant chloride concentrations and up to 150 mM. Upon shifts in pH, the DNA-AgNCs showed a complex fluorescence intensity response. The model DNA-AgNCs differ strongly in their response characteristics to the applied changes in their environments. With our work, we show the feasibility of the use of DNA-AgNCs as sensors in a simple microfluidic setup that can be used as a building block for PoCT applications while highlighting challenges in their adaption for use with biologically relevant matrices. Full article

Environmental monitoring systems often operate continuously, measuring various parameters, including carbon dioxide levels (CO₂), relative humidity (RH), temperature (T), and other factors that affect environmental conditions. Such systems are often referred to as smart systems because they can autonomously monitor and respond to environmental conditions and can be integrated both indoors and outdoors to detect, for example, structural anomalies. However, these systems typically have high energy consumption, data overload, and large equipment sizes, which makes them difficult to install in constrained spaces. Therefore, three challenges remain unresolved: efficient energy use, accurate data measurement, and compact installation. To address these limitations, this study proposes a two-to-one threshold sampling approach, where the CO₂ measurement is activated when the specified T and $RH$ change thresholds are exceeded. This event-driven method avoids redundant data collection, minimizes power consumption, and is suitable for resource-constrained embedded systems. The proposed approach was implemented on a low-power, small-form and self-made multivariate sensor based on the PIC16LF19156 microcontroller. In contrast, a commercial monitoring system and sensor modules based on the Arduino Uno were used for comparison. As a result, by activating only key points in the T and $RH$ signals, the number of CO₂ measurements was significantly reduced without loss of essential signal characteristics. Signal reconstruction from the reduced points demonstrated high accuracy, with a mean absolute error (MAE) of 0.0089 and root mean squared error (RMSE) of 0.0117. Despite reducing the number of CO₂ measurements by approximately 41.9%, the essential characteristics of the signal were saved, highlighting the efficiency of the proposed approach. Despite its effectiveness in controlled conditions (in buildings, indoors), environmental factors such as the presence of people, ventilation systems, and room layout can significantly alter the dynamics of CO₂ concentrations, which may limit the implementation of this approach. Future studies will focus on the study of adaptive threshold mechanisms and context-dependent models that can adjust to changing conditions. This approach will expand the scope of application of the proposed two-to-one sampling technique in various practical situations. Full article

With the widespread application of deep learning in Earth observation, remote sensing image-based building change detection has achieved numerous groundbreaking advancements. However, differences across time periods caused by temporal variations in land cover, as well as the complex spatial structures in remote sensing scenes, significantly constrain the performance of change detection. To address these challenges, a change detection algorithm based on spatio-spectral information aggregation is proposed, which consists of two key modules: the Cross-Scale Heterogeneous Convolution module (CSHConv) and the Spatio-Spectral Information Fusion module (SSIF). CSHConv mitigates information loss caused by scale heterogeneity, thereby enhancing the effective utilization of multi-scale features. Meanwhile, SSIF models spatial and spectral information jointly, capturing interactions across different spatial scales and spectral domains. This investigation is illustrated with a case study conducted with the real-world dataset QL-CD (Qinling change detection), acquired in the Qinling region of China. The work includes the construction of QL-CD, which includes 12,724 pairs of images captured by the Gaofen-1 satellite. Experimental results demonstrate that the proposed approach outperforms a wide range of state-of-the-art algorithms. Full article

Photogrammetry can be a valuable tool for understanding landscape evolution and natural hazards such as landslides. However, factors such as vegetation cover, shadows, and unstable ground can limit its effectiveness. Using photos across time to monitor an area with unstable or changing ground conditions results in fewer tie points between images across time, and often leads to low comparative accuracy if single-epoch (i.e., classical) photogrammetric processing approaches are used. This paper presents a study evaluating the co-alignment approach applied to fixed terrestrial timelapse photos at an active landslide site. The study explores the comparative accuracy of reconstructed surface models and the location and behavior of tie points over time in relation to increasing levels of global change due to landslide activity and rockfall. Building upon previous work, this study demonstrates that high comparative accuracy can be achieved with a relatively low number of inter-epoch tie points, highlighting the importance of their distribution across stable ground, rather than the total quantity. High comparative accuracy was achieved with as few as 0.03 percent of the overall co-alignment tie points being inter-epoch tie points. These results show that co-alignment is an effective approach for conducting change detection, even with large degrees of global changes between surveys. This study is specific to the context of geoscience applications like landslide monitoring, but its findings should be relevant for any application where significant changes occur between surveys. Full article

Background/Objectives: Diabetic retinopathy (DR) remains one of the primary causes of preventable vision impairment worldwide, particularly among individuals with long-standing diabetes. The progressive damage of retinal microvasculature can lead to irreversible blindness if not detected and managed at an early stage. Therefore, the development of reliable, non-invasive, and automated screening tools has become increasingly vital in modern ophthalmology. With the evolution of medical imaging technologies, Optical Coherence Tomography (OCT) has emerged as a valuable modality for capturing high-resolution cross-sectional images of retinal structures. In parallel, machine learning has shown considerable promise in supporting early disease recognition by uncovering complex and often imperceptible patterns in image data. Methods: This study introduces a novel framework for the early detection of DR through multifractal analysis of OCT images. Multifractal features, extracted using a box-counting approach, provide quantitative descriptors that reflect the structural irregularities of retinal tissue associated with pathological changes. Results: A comparative evaluation of several machine learning algorithms was conducted to assess classification performance. Among them, the Multi-Layer Perceptron (MLP) achieved the highest predictive accuracy, with a score of $98.02\%$, along with precision, recall, and F1-score values of $98.24\%$, $97.80\%$, and $98.01\%$, respectively. Conclusions: These results highlight the strength of combining OCT imaging with multifractal geometry and deep learning methods to build robust and scalable systems for DR screening. The proposed approach could contribute significantly to improving early diagnosis, clinical decision-making, and patient outcomes in diabetic eye care. Full article

Due to the complex structure of high-rise space buildings, traditional point fire detectors are not effective in terms of detection range and installation difficulty. Although linear beam smoke detectors are widely adopted, they still face problems such as low accuracy and false alarms caused by interference. To address these limitations, we constructed a 120 m experimental platform for analyzing smoke–light interactions. Through systematic investigation of spectral scattering phenomena, optimal operational wavelengths were identified for beam-type detection. By improving the gated recurrent unit (GRU) neural network, an algorithm combining dual-wavelength information fusion and an attention mechanism was designed. The algorithm integrates dual-wavelength information and introduces the cross-attention mechanism into the GRU network to achieve collaborative modeling of microscale scattering characteristics and macroscale concentration changes of smoke particles. The alarm strategy based on time series accumulation effectively reduces false alarms caused by instantaneous interference. The experiment shows that our method is significantly better than traditional algorithms in terms of accuracy (96.8%), false positive rate (2.1%), and response time (6.7 s). Full article