Search Results (3,775)

Potential tropospheric noise is a critical factor that undermines the effectiveness of deformation monitoring in Synthetic Aperture Radar Interferometry (InSAR) technologies. In most scenarios, many point targets within the InSAR deformation monitoring area either do not undergo deformation or exhibit only minimal deformation trends. The phases of densely distributed stable points can effectively respond to spatial tropospheric delays, particularly turbulent atmospheric phases. This study proposes a data-driven InSAR atmospheric correction method by exploring how to use these densely stable InSAR time series to model atmospheric phase delays. Our focus is on selecting stable InSAR time series point targets and evaluating the impact of different densities of stable points on atmospheric correction performance. Analysis of 645 interferograms derived from 217 Sentinel-1A SAR images, spanning from 13 June 2017 to 15 November 2024, demonstrates that the proposed method reduces the Root Mean Square Error (RMSE) by 70%, 59%, and 69% compared to the terrain-related linear approach, the General Atmospheric Correction Online Service, and common scene stacking methods, respectively. In addition, simulation data and leveling data were used to validate the proposed method. This article does not develop an independent InSAR atmospheric correction method. Instead, the proposed approach starts with the InSAR deformation time series, allowing for easy integration into existing InSAR workflows and widely used atmospheric correction strategies. It can serve as a post-processing tool to improve InSAR time series analysis. Full article

Interferometric Synthetic Aperture Radar (InSAR) is an advanced imaging geodesy technique for detecting and characterizing surface deformation with high spatial resolution and broad spatial coverage. However, as an inherently post-event observation method, InSAR suffers from limited capability for near-real-time and short-term updates of deformation time series. In this paper, we proposed a data-driven adaptive framework for deformation prediction based on a hybrid deep learning method to accurately predict the InSAR-derived deformation time series and take the Xi’erguazi−Mawo landslide complex (XMLC) as a case study. The InSAR-derived time series was initially decomposed into trend and periodic components with a two-step decomposition process, which were thereafter modeled separately to enhance the characterization of motion kinematics and prediction accuracy. After retrieving the observations from the multi-temporal InSAR method, two-step signal decomposition was then performed using the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) and Variational Mode Decomposition (VMD). The decomposed trend and periodic components were further evaluated using statistical hypothesis testing to verify their significance and reliability. Compared with the single-decomposition model, the further decomposition leads to an overall improvement in prediction accuracy, i.e., the Mean Absolute Errors (MAEs) and the Root Mean Square Errors (RMSEs) are reduced by 40–49% and 36–42%, respectively. Subsequently, the Radial Basis Function (RBF) neural network and the proposed CNN-BiLSTM-SelfAttention (CBS) models were constructed to predict the trend and periodic variations, respectively. The CNN and self-attention help to extract local features in time series and strengthen the ability to capture global dependencies and key fluctuation patterns. Compared with the single network model in prediction, the MAEs and RMSEs are reduced by 22–57% and 4–33%, respectively. Finally, the two predicted components were integrated to generate the fused deformation prediction results. Ablation experiments and comparative experiments show that the proposed method has superior ability. Through rapid and accurate prediction of InSAR-derived deformation time series, this research could contribute to the early-warning systems of slope instabilities. Full article

This study conducts a landslide deformation assessment in Tianshui, Gansu Province, on the Chinese Loess Plateau, utilizing the Small Baseline Subset InSAR (SBAS-InSAR) method integrated with velocity direction conversion and Z-score clustering. The Chinese Loess Plateau is one of the most landslide-prone regions in China due to frequent rains, strong topographical gradients and severe soil erosion. By constructing subsets of interferograms, SBAS-InSAR can mitigate the influence of decorrelation to a certain extent, making it a highly effective technique for monitoring regional surface deformation and identifying landslides. To overcome the limitations of the satellite’s one-dimensional Line-of-Sight (LOS) measurements and the challenge of distinguishing true landslide signals from noise, two optimization strategies were implemented. First, LOS velocities were projected onto the local steepest slope direction, assuming translational movement parallel to the slope. Second, a Z-score clustering algorithm was employed to aggregate measurement points with consistent kinematic signatures, enhancing identification robustness, with a slight trade-off in spatial completeness. Based on 205 Sentinel-1 Single-Look Complex (SLC) images acquired from 2014 to 2024, the integrated workflow identified 69 “active, very slow” and 63 “active, extremely slow” landslides. These results were validated through high-resolution historical optical imagery. Time series analysis reveals that creep deformation in this region is highly sensitive to seasonal rainfall patterns. This study demonstrates that the SBAS-InSAR post-processing framework provides a cost-effective, millimeter-scale solution for updating landslide inventories and supporting regional risk management and early warning systems in loess-covered terrains, with the exception of densely forested areas. Full article

Accurate mapping of land use and land cover (LULC) is crucial for various applications such as urban planning, environmental management, and sustainable development, particularly in rapidly growing urban areas. African cities such as Yaoundé, Cameroon, are particularly affected by this rapid and often uncontrolled urban growth with complex spatio-temporal dynamics. Effective modeling of LULC indicators in such areas requires robust algorithms for high-resolution images segmentation and classification, as well as reliable data with great spatio-temporal distributions. Among the most suitable data sources for these types of studies, Sentinel-2 image time series, thanks to their high spatial (10 m) and temporal (5 days) resolution, are a valuable source of data for this task. However, for an effective LULC modeling purpose in such dynamic areas, many challenges remain, including spectral confusion between certain classes, seasonal variability, and spatial heterogeneity. This study proposes a hybrid deep learning architecture combining U-Net and Convolutional Long Short-Term Memory (ConvLSTM) layers, allowing the spatial structures and temporal dynamics of the Sentinel-2 series to be exploited jointly. Applied to the Yaoundé region (Cameroon) over the period 2018–2025, the hybrid model significantly outperforms the U-Net and ConvLSTM models alone. It achieves a macro-average F1 score of 0.893, an accuracy of 0.912, and an average IoU of 0.811 on the test set. These segmentation performances reached up to 0.948, 0.953, and 0.910 for precision, F1-score, and IoU, respectively, on the built-up areas class. Moreover, despite its better performance, in terms of complexity, the figures confirm that the hybrid does not significantly penalize evaluation speed. These results demonstrate the relevance of jointly integrating space and time for robust LULC classification from multi-temporal satellite images. Full article

Motion capture experiments can be conducted more easily if marker-based motion (marker-based MoCap) can be captured using an asynchronous multicamera system (Async MCS). However, camera calibration is essential for marker-based MoCap, and a wand calibration method that utilizes timestamp functions has been proposed for Async MCS. However, in practice, many cameras do not provide accurate timestamp functions, limiting the applicability of existing methods in such environments. A wand calibration method for Async MCS that does not rely on timestamp functions is proposed to evaluate the accuracy of estimated camera parameters. In conventional methods, the time offset in image acquisition is obtained from timestamp information, and synchronous coordinates are estimated by interpolating time-series digitized coordinates of wand markers. In this study, the time offset is treated as an optimization variable, which enables camera parameter estimation without using timestamp functions. Consequently, the three-dimensional reconstruction errors of fixed points obtained using the proposed method are significantly smaller (1.445 ± 0.833 and 1.746 ± 0.908 mm) compared to estimations that ignore time offsets. These findings demonstrate that the proposed method enables more accurate camera calibration. Full article

Unmanned aerial vehicles (UAVs) increasingly share low-altitude airspace with birds, making early distinguishing between drones and biological targets critical for safety and security. This work addresses long-range scenarios where objects occupy only a few pixels and appearance-based recognition becomes unreliable. We develop a model-driven simulation pipeline that generates synthetic data with a controlled camera model, atmospheric background and realistic motion of three aerial target types: multicopter, fixed-wing UAV and bird. From these sequences, each track is encoded as a time series of image-plane coordinates and apparent size, and a bidirectional long short-term memory (LSTM) network is trained to classify trajectories as drone-like or bird-like. The model learns characteristic differences in smoothness, turning behavior and velocity fluctuations, and to achieve reliable separation between drone and bird motion patterns on synthetic test data. Motion-trajectory cues alone can support early distinguishing of drones from birds when visual details are scarce, providing a complementary signal to conventional image-based detection. The proposed synthetic data and sequence classification pipeline forms a reproducible testbed that can be extended with real trajectories from radar or video tracking systems and used to prototype and benchmark trajectory-based recognizers for integrated surveillance solutions. The proposed method is designed to generalize naturally to real surveillance systems, as it relies on trajectory-level motion patterns rather than appearance-based features that are sensitive to sensor quality, illumination, or weather conditions. Full article

NFT prices are shaped by heterogeneous signals including visual appearance, textual narratives, transaction trajectories, and on-chain interactions, yet existing studies often model these factors in isolation and rarely unify multimodal alignment, temporal non-stationarity, and heterogeneous relational dependencies in a leakage-safe forecasting setting. We propose MM-Temporal-Graph, a cross-modal temporal graph transformer framework for explainable NFT valuation and information-centric risk forecasting. The model encodes image, text, transaction time series, and blockchain behavioral features, constructs a heterogeneous NFT interaction graph (co-transaction, shared creator, wallet relation, and price co-movement), and jointly performs relation-aware graph attention and global temporal–structural transformer reasoning with an adaptive fusion gate. A contrastive multimodal alignment objective improves robustness under market drift, while a risk-aware regularizer and a multi-source risk index enable early warning and interpretable attribution across modalities, time segments, and relational neighborhoods. On MultiNFT-T, MM-Temporal-Graph improves MAE from 0.162 to 0.153 and R² from 0.823 to 0.841 over the strongest multimodal graph baseline, and achieves 87.4% early risk detection accuracy. These results support accurate, robust, and explainable NFT valuation and proactive risk monitoring in Web3 markets. Full article

Modern industrial equipment is a cyber-physical system (CPS) consisting of physical production components and digital controls. Lowering maintenance costs and increasing availability is important to improve its efficiency. Modern methods, based on solving event prediction problem, in particular, prediction of remaining useful life (RUL), are used as a crucial step in a framework of reliability-centered maintenance to increase efficiency. But modern methods of RUL forecasting fall short when dealing with real-world scenarios, where CPS are described by multidimensional continuous high-frequency data with working cycles with variable duration. To overcome this problem, we propose a new method for fault prediction, which is based on extraction of semantic state vectors (SSVs) from working cycles of equipment. To implement SSV extraction, a new method, based on convolutional autoencoder and extraction of hidden state, is proposed. In this method, working cycles are detected in input data stream, and then they are converted to images, on which an autoencoder is trained. The output of an intermediate layer of an autoencoder is extracted and processed into SSVs. SSVs are then combined into a time series on which RUL is forecasted. After optimization of hyperparameters, the proposed method shows the following results: RMSE = 1.799, MAE = 1.374. These values are significantly more accurate than those obtained using existing methods: RMSE = 14.02 and MAE = 10.71. Therefore, SSV extraction is a viable technique for forecasting RUL. Full article

Background: Diffuse large B cell lymphoma is an aggressive, heterogeneous yet treatable disease. Primary bone lymphoma is a lymphoma involving a single or multiple osseous sites with or without regional nodal involvement. It is exceedingly rare, representing <1% of new non-Hodgkin lymphoma cases per year. Most cases of primary bone lymphoma are diffuse large B cell lymphoma. They infrequently involve the craniofacial bones and mandible; its rarity can lead to delays in diagnosis. Case Series Presentation: Two 64-year-old male patients initially presented to local dentists with concerns of tooth pain and numbness. Both underwent extensive dental procedures including extraction and debridement, with an initial diagnosis of osteomyelitis. They were placed on long-term antibiotics. After months without improvement, further testing was pursued, including imaging and repeat biopsies. The patients were finally diagnosed with primary bone diffuse large B cell lymphoma. From the initial treatment of osteomyelitis, a median time of 8.5 months passed before diagnosis of lymphoma. Treatment with cytotoxic chemotherapy was initiated and both patients achieved remission. Conclusions: As in the two cases presented here, the initial point of entry into the medical system may be a visit to the local dentist. When patients present with periodontal complaints, it is imperative to maintain a broad differential, including lymphoma. This is especially crucial when the patient’s clinical course does not respond to initial treatment. This results in delays of diagnosis and initiation of therapy for a treatable cancer. Full article

This paper proposes a robust convolutional neural network (CNN) architecture for human activity recognition (HAR) using smartphone accelerometer data, evaluated on the WISDM dataset. We introduce two novel pooling mechanisms—Pooling A (Extrema Contrast Pooling (ECP)) and Pooling B (Center Minus Variation (CMV))—that enhance feature discrimination and noise robustness. ECP emphasizes sharp signal transitions through a nonlinear penalty based on the squared range between extrema, while CMV Pooling penalizes local variability by subtracting the standard deviation, improving resilience to noise. Input data are normalized to the [0, 1] range to ensure bounded and interpretable pooled outputs. The proposed framework is evaluated in two separate configurations: (1) a 1D CNN applied to raw tri-axial sensor streams with the proposed pooling layers, and (2) a histogram-based image encoding pipeline that transforms segment-level sensor redundancy into RGB representations for a 2D CNN with fully connected layers. Ablation studies show that histogram encoding provides the largest improvement, while the combination of ECP and CMV further enhances classification performance. Across six activity classes, the 2D CNN system achieves up to 96.84% weighted classification accuracy, outperforming baseline models and traditional average pooling. Under Gaussian, salt-and-pepper, and mixed noise conditions, the proposed pooling layers consistently reduce performance degradation, demonstrating improved stability in real-world sensing environments. These results highlight the benefits of redundancy-aware pooling and histogram-based representations for accurate and robust mobile HAR systems. Full article

This study aimed to evaluate the prediction potential of phenology metrics from two vegetation indices using Sentinel-2 images, the Normalized Difference Vegetation Index (NDVI) and Three Red-Edge Vegetation Index (NDVI3RE), for maize yield prediction. Ground truth maize yield samples were collected near Koška, Croatia, on 13 October 2023, using a Quantimeter yield mapping sensor on Claas Lexion 6900 combine harvester. The phenology analysis was performed based on a time-series of all available Sentinel-2 images during 2023, using the Beck logistic model for determining the start of season (SOS), peak of season (POS), end of season (EOS), greenup, maturity, senescence, and dormancy. A total of fourteen covariates, including vegetation indices at phenology metrics and their occurrence dates, were used for machine learning prediction of maize yield using Random Forest (RF) and Support Vector Machine (SVM) regression. The results suggested that the SVM method based on NDVI phenology metrics produced the highest accuracy for maize yield prediction (R² = 0.935, RMSE = 0.558 t ha⁻¹, MAE = 0.399 t ha⁻¹). Vegetation index values at greenup, dormancy and POS were the most important covariates for the prediction, while day of year (DOY) in which they occurred had only a minor effect on the prediction accuracy. This suggests that, despite its limitations regarding the saturation effect, NDVI outperformed NDVI3RE for maize yield prediction when combined with phenology metrics. Full article

Background: Parasitic skin-related conditions represent a frequent and evolving challenge in human dermatology, as they often mimic other dermatoses, and are increasingly complicated by therapeutic resistance. With this study, we aimed to provide a practical, clinician-oriented overview of our experience, contextualising it within the current literature. Materials and Methods: We conducted a retrospective, single-centre observational study, reporting a case series of 88 patients diagnosed with parasitic or arthropod-related skin infestations at the San Raffaele Hospital Dermatology Unit (Milan) between 2019 and 2024, and integrated a concise narrative review of contemporary evidence on diagnosis, non-invasive imaging and management. For each case, we documented clinical presentation, dermoscopic or reflectance confocal microscopy (RCM) findings, and treatment response. Non-invasive tools (dermoscopy, videodermoscopy, RCM) were used when appropriate. Results: The spectrum of conditions included flea bites, bed bug bites, cutaneous larva migrans, subcutaneous dirofilariasis, Dermanyssus gallinae dermatitis, pediculosis, tick bites (including Lyme disease), myiasis, scabies, and cutaneous leishmaniasis. One case of eosinophilic dermatosis of haematologic malignancy was also considered due to its possible association with arthropod bites. Non-invasive imaging was critical in confirming suspected infestations, particularly in ambiguous cases or when invasive testing was not feasible. Several cases highlighted suspected therapeutic resistance: a paediatric pediculosis and three adult scabies cases required systemic therapy after standard regimens failed, raising concerns over putative resistance to permethrin and pyrethroids. In dirofilariasis, the persistence of filarial elements visualised by RCM justified the extension of antiparasitic therapy despite prior surgical removal. Conclusions: Our findings underline that accurate diagnosis, early intervention, and tailored treatment remain essential for the effective management of cutaneous infestations. The observed vast spectrum of isolated parasites reflects broader health and ecological dynamics, including zoonotic transmission, international mobility, and changing environmental conditions. At the same time, diagnostic delays, inappropriate treatments, and neglected parasitic diseases continue to pose significant risks. To address these challenges, clinicians should remain alert to atypical presentations, and consider a multidisciplinary approach including the consultation with parasitologists and veterinarians, as well as the incorporation of high-resolution imaging and alternative therapeutic strategies into their routine practice. Full article

The growing demand for high-efficiency photovoltaic (PV) technologies has intensified interest in advanced cell architectures, including hybrid passivated back contact (HPBC) solar cells. Conventional solder-based interconnection processes require high thermal budgets, which can induce thermomechanical stress and lead to performance degradation in thin back-contact cell structures. In this study, electrically conductive adhesive (ECA) interconnection is investigated as a low-thermal-budget, solder-free alternative for HPBC solar cells. The curing behavior of an acrylic-based, silver-filled ECA is systematically examined by controlling the upper lamp temperature and the welding time during the interconnection process. Electrical performance is evaluated through current–voltage characterization, fill factor, and series resistance analysis, while interfacial microstructural evolution is examined using scanning electron microscopy. The results identify a well-defined processing window in which adequate curing enables stable electrical contact formation. In contrast, both insufficient curing and excessive curing result in degraded electrical performance. To assess practical applicability, HPBC modules with an industry-relevant size of ~1000 × 1160 mm² are fabricated and evaluated using electroluminescence imaging and I–V measurements. By identifying a robust curing window and demonstrating its successful transfer from string-level interconnections to full-size HPBC modules, this study establishes a practical, low-thermal-budget, solder-free interconnection strategy for advanced back-contact PV architectures. Full article

The photovoltaic (PV) bands on the mid-wave and long-wave infrared (MWIR and LWIR) cold focal plane assemblies of Terra and Aqua MODIS have suffered from gradually increasing electronic crosstalk contamination as both instruments have continued to operate in their extended missions, respectively. This contamination has considerable impact, particularly for the PV LWIR bands, which includes image striping and radiometric bias in the Level-1B (L1B)-calibrated radiance products as well as higher level (and mostly atmospheric but also land and oceanic) products (e.g., cloud phase particle, cloud mask, land and sea surface temperatures). The crosstalk was characterized early in the mission, and test corrections were developed then. Ultimately, the groundwork for a robust electronic crosstalk correction algorithm was developed in 2016 and implemented in MODIS Collection 6.1 (C6.1) back in 2017 for the Terra MODIS PV LWIR bands. It was later introduced in Aqua MODIS C6.1 for the same group of bands in April 2022. Additional improvements were made in MODIS Collection 7 (C7) to better characterize the electronic crosstalk in the PV LWIR bands, and the electronic crosstalk correction algorithm was also extended to select detectors in the MODIS MWIR bands. This work will describe the electronic crosstalk correction algorithm and its application on the MODIS L1B product, the differences in application between C6.1 and C7, as well as additional improvements made to enhance the contamination correction and improve image quality for the Aqua MODIS PV LWIR bands. The electronic crosstalk correction coefficient time series for the MODIS PV bands will be discussed, and some cases will be presented to illustrate how image quality improves on the L1B and Level 2 products after the correction is applied. Lastly, experiences gained regarding the PV bands electronic crosstalk and the strategy used to correct it will be discussed to provide future data users and scientists with an insight as to how to improve on the legacy record that the Terra and Aqua MODIS sensors will leave behind after both spacecrafts are decommissioned. Full article

With the rapid expansion of pulsar survey data driven by advanced radio telescopes such as FAST, automated detection methods have become crucial for the efficient and accurate identification of single-pulse signals. A key challenge in this task is the extreme class imbalance between genuine pulsar pulses and radio frequency interference (RFI), which significantly hampers classifier performance—particularly in low signal-to-noise ratio (S/N) environments. To address this issue and improve detection accuracy, we propose Pulsar-WRecon, a Wasserstein GAN with Gradient Penalty (WGAN-GP)-based framework designed to generate realistic single-pulse profiles. The synthetic samples generated by Pulsar-WRecon are used to augment training data and alleviate class imbalance. Building upon the enhanced dataset, Convolutional Kolmogorov–Arnold Network (CKAN) is further introduced as a novel hybrid model that integrates convolutional layers with KAN-based functional decomposition to better capture complex patterns in pulse signals. On the three-channel pulsar images from the HTRU1 dataset, our method achieves a recall of 97.5% and a precision of 98.5%. On the DM time series image dataset, FAST-DATASET, it achieves a recall of 93.2% and a precision of 92.5%. These results validate that combining generative data augmentation with an improved model architecture can effectively enhance the precision of single-pulse detection in large-scale pulsar surveys, especially in challenging, real-world conditions. Full article