Window Size Research Articles

ATP_mCNN: Predicting ATP binding sites through pretrained language models and multi-window neural networks.

Adenosine triphosphate plays a vital role in providing energy and enabling key cellular processes through interactions with binding proteins. The increasing amount of protein sequence data necessitates computational methods for identifying binding sites. However, experimental identification of adenosine triphosphate-binding residues remains challenging. To address the challenge, we developed a multi-window convolutional neural network architecture taking pre-trained protein language model embeddings as input features. In particular, multiple parallel convolutional layers scan for motifs localized to different window sizes. Max pooling extracts salient features concatenated across windows into a final multi-scale representation for residue-level classification. On benchmark datasets, our model achieves an area under the ROC curve of 0.95, significantly improving on prior sequence-based models and outperforming convolutional neural network baselines. This demonstrates the utility of pre-trained language models and multi-window convolutional neural networks for advanced sequence-based prediction of adenosine triphosphate-binding residues. Our approach provides a promising new direction for elucidating binding mechanisms and interactions from primary structure.

JTF-SqueezeNet: A SqueezeNet network based on joint time-frequency data representation for egg-laying detection in individually caged ducks.

Accurate individual egg-laying detection is crucial for eliminating low-yielding breeder ducks and improving production efficiency. However, existing methods are often expensive and require strict environmental conditions. This study proposes a data processing method based on wearable sensors and joint time-frequency representation (TFR), aimed at accurately identifying egg-laying in ducks. First, the sensors continuously monitor the ducks' activity and collect corresponding X-axis acceleration data. Next, a sliding window combined with Short-Time Fourier Transform (STFT) is applied to convert the continuous data into spectrograms within consecutive windows. SqueezeNet is then used to detect spectrograms containing key features of the egg-laying process, marking these as egg-laying state windows. Finally, Kalman filtering was used to continuously predict the detected egg-laying status, allowing for the precise determination of the egg-laying period. The best detection performance was achieved by applying the 10-fold cross-validation to a dataset of 59,135 spectrograms, using a window size of 50 min and a step size of 3 min. This configuration yielded an accuracy of 95.73 % for detecting egg-laying status, with an inference time of only 2.1511 milliseconds per window. The accuracy for identifying the egg-laying period reached 92.19 %, with a precision of 93.57 % and a recall rate of 91.95 %. Additionally, we explored the scalability of the joint time-frequency representation to reduce the computational complexity of the model.

Assessing the impact of natural ventilation on indoor air quality and CO2 concentration in residential apartments

This study investigates the impact of natural ventilation on indoor air quality (IAQ) and CO₂ concentration in residential buildings in Dhaka, Bangladesh, focusing on kitchen environments. Poor IAQ, particularly elevated CO₂ levels, poses significant health risks, including respiratory issues and cognitive impairments. In Dhaka, inadequate ventilation exacerbates these issues, especially in kitchens where cooking activities generate pollutants like CO₂ and particulate matter. The study aims to assess how variations in window size and ventilation influence CO₂ levels in kitchens and compare CO₂ concentrations before and after cooking. Additionally, it explores natural ventilation strategies to enhance IAQ in residential apartments. Using an experimental approach, CO₂ levels were monitored in various kitchens and living rooms over a one-week period, employing HOBO CO₂ sensors and temperature-humidity loggers. Cooking activities like grilling, frying, and boiling were analyzed to determine the effect on CO₂ concentrations. Results showed that CO₂ levels significantly increased during cooking, with kitchens exhibiting the highest concentrations. Notably, open windows contributed to lower CO₂ levels, particularly in living rooms and dining areas, emphasizing the role of natural ventilation. However, kitchens still experienced substantial CO₂ buildup, indicating the need for additional ventilation solutions. The study concludes that while open windows improve IAQ, enhanced ventilation systems and strategic airflow management are essential to reduce CO₂ levels and ensure healthier living environments in residential buildings.

Effect of window openings on indoor air quality and CO₂ concentration in classrooms: A Case Study of Primary School, Dhaka

Abstract. This study investigates the impact of window openings on indoor air quality (IAQ) and CO₂ levels in school classrooms in Dhaka, focusing on natural ventilation strategies to improve the learning environment. The importance of effective window design in controlling CO₂ concentrations and enhancing ventilation is critical, particularly in tropical climates like Dhaka's, where indoor air quality is often compromised due to inadequate ventilation. The study aims to explore the effect of window size and ventilation on CO₂ levels, comparing classrooms with different window configurations to identify the best strategies for improving IAQ. Over a period of two measurement campaigns, the study monitored CO₂ levels, indoor temperature, and relative humidity in two elementary schools, revealing that limited window openings, particularly when windows were 75% closed, resulted in significantly higher CO₂ concentrations. The analysis showed a direct correlation between reduced ventilation and increased CO₂ levels, with concentrations peaking at 2560 ppm, well above the recommended threshold of 1000 ppm. Factors like room design, occupancy density, and window placement contributed to variations in CO₂ levels across classrooms. The study emphasizes the need for optimized window openings to promote natural ventilation and reduce CO₂ concentrations, suggesting that opening windows beyond 50% can significantly improve IAQ. Regular monitoring, maintenance, and the implementation of effective ventilation strategies are essential to maintaining healthy indoor air quality in schools, ensuring a conducive learning environment for students. This research highlights the critical role of building design and ventilation systems in enhancing IAQ in educational settings.

Canopy Segmentation of Overlapping Fruit Trees Based on Unmanned Aerial Vehicle LiDAR

Utilizing LiDAR sensors mounted on unmanned aerial vehicles (UAVs) to acquire three-dimensional data of fruit orchards and extract precise information about individual trees can greatly facilitate unmanned management. To address the issue of low accuracy in traditional watershed segmentation methods based on canopy height models, this paper proposes an enhanced method to extract individual tree crowns in fruit orchards, enabling the improved detection of overlapping crown features. Firstly, a distribution curve of single-row or single-column treetops is fitted based on the detected treetops using variable window size. Subsequently, a cubic spatial region extending infinitely along the Z-axis is generated with equal width around this curve, and all crown points falling within this region are extracted and then projected onto the central plane. The projecting contour of the crowns on the plane is then fitted using Gaussian functions. Treetops are detected by identifying peak points on the curve fitted by Gaussian functions. Finally, the watershed algorithm is applied to segment fruit tree crowns. The results demonstrate that in citrus orchards with pronounced crown overlap, this novel method significantly reduces the number of undetected trees with a precision of 97.04%, and the F1 score representing the detection accuracy for fruit trees reaches 98.01%. Comparisons between the traditional method and the Gaussian fitting–watershed fusion algorithm across orchards exhibiting varying degrees of crown overlap reveal that the fusion algorithm achieves high segmentation accuracy when dealing with overlapping crowns characterized by significant height variations.

Hybrid generative adversarial network based on frequency and spatial domain for histopathological image synthesis

BackgroundDue to the complexity and cost of preparing histopathological slides, deep learning-based methods have been developed to generate high-quality histological images. However, existing approaches primarily focus on spatial domain information, neglecting the periodic information in the frequency domain and the complementary relationship between the two domains. In this paper, we proposed a generative adversarial network that employs a cross-attention mechanism to extract and fuse features across spatial and frequency domains. The method optimizes frequency domain features using spatial domain guidance and refines spatial features with frequency domain information, preserving key details while eliminating redundancy to generate high-quality histological images.ResultsOur model incorporates a variable-window mixed attention module to dynamically adjust attention window sizes, capturing both local details and global context. A spectral filtering module enhances the extraction of repetitive textures and periodic structures, while a cross-attention fusion module dynamically weights features from both domains, focusing on the most critical information to produce realistic and detailed images.ConclusionsThe proposed method achieves efficient spatial-frequency domain fusion, significantly improving image generation quality. Experiments on the Patch Camelyon dataset show superior performance over eight state-of-the-art models across five metrics. This approach advances automated histopathological image generation with potential for clinical applications.

Ultrasound-Guided Vacuum-Assisted Excision (VAE) in Breast Lesion Management: An Experimental Comparative Study of Two Different VAE Devices Across Various Aspiration Levels and Window Sizes

Background/Objectives: Vacuum-assisted excision (VAE) is a minimally invasive technique for breast tumor treatment, offering precision, comfort, and quick recovery. It is widely used for benign breast lesions and is playing an increasingly important role in the therapeutic management of non-surgical patients or patients who refuse surgery. Optimal outcomes require an understanding of device features to tailor treatment to each lesion. The Mammotome® Elite 10G operates in a fixed mode, while the Mammotome® Revolve EX 8G offers multiple aspiration levels and aperture windows for greater versatility. This study analyzed the specimen features (weight and length), comparing the weight obtained from two different VAE systems to aid the appropriate selection of a device based on the clinical setting. It also determined the number of specimens needed to achieve the 4 g diagnostic threshold. Methods: The Mammotome® Elite 10G and the Mammotome® Revolve EX were evaluated under controlled conditions. For Mammotome® Revolve EX, combinations of five aspiration levels and three aperture lengths (12 mm, 18 mm, and 25 mm) were tested. Twelve samples were collected from a chicken breast phantom for each setting. Specimen weights and the minimum excisions required to reach the 4 g threshold were analyzed. Results: The mean weight per sample for the Mammotome® Elite 10G was 0.16 ± 0.04 g. For the Mammotome® Revolve EX, the weights increased with aperture size and aspiration level, ranging from a minimum of 0.132 ± 0.028 g (a window length of 12 mm and aspiration level 1) to a maximum of 0.407 ± 0.055 g (a window length of 25 mm and aspiration level 5). The 25 mm window at aspiration level 5 achieved the 4 g threshold in as few as 10 samples. By comparison, the Mammotome® Elite required up to 26 samples. Conclusions: Compared to the Mammotome Elite, Mammotome® Revolve EX offers superior versatility and efficiency, reducing patient discomfort by minimizing the required samples. Its technical advantages make it a valuable tool for both diagnostic and therapeutic applications.

Convolutional neural networks for sea surface data assimilation in operational ocean models: test case in the Gulf of Mexico

Abstract. Deep learning models have demonstrated remarkable success in fields such as language processing and computer vision, routinely employed for tasks like language translation, image classification, and anomaly detection. Recent advancements in ocean sciences, particularly in data assimilation (DA), suggest that machine learning can emulate dynamical models, replace traditional DA steps to expedite processes, or serve as hybrid surrogate models to enhance forecasts. However, these studies often rely on ocean models of intermediate complexity, which involve significant simplifications that present challenges when transitioning to full-scale operational ocean models. This work explores the application of convolutional neural networks (CNNs) in data assimilation within the context of the HYbrid Coordinate Ocean Model (HYCOM) in the Gulf of Mexico. The CNNs are trained to correct model errors from a 2-year, high-resolution (1/25°) HYCOM dataset, assimilated using the Tendral Statistical Interpolation System (T-SIS). The CNNs are trained to replicate the increments generated by the T-SIS data assimilation package, aiming to correct model forecasts of sea surface temperature (SST) and sea surface height (SSH). The inputs to the CNNs include real satellite observations of SST from the Group for High Resolution Sea Surface Temperature (GHRSST), along-track altimeter SSH observations (ADT), the model background state (previous forecast), and the innovations (differences between observations and background). We assess the performance of the CNNs across five controlled experiments, designed to provide insights into their application in environments governed by full primitive equations, real observations, and complex topographies. The experiments focus on evaluating (1) the architecture and complexity of the CNNs, (2) the type and quantity of observations, (3) the type and number of assimilated fields, (4) the impact of training window size, and (5) the influence of coastal boundaries. Our findings reveal significant correlations between the chosen training window size – a factor not commonly examined – and the CNNs' ability to assimilate observations effectively. We also establish a clear link between the CNNs' architecture and complexity and their overall performance. This research uses artificial intelligence to enhance ocean forecasting in the Gulf of Mexico. By using convolutional neural networks, the study improves predictions of sea temperatures and heights by integrating real satellite data with existing models. Through five comprehensive experiments, the team found that the amount of training data and the design of the neural networks significantly affect accuracy. These insights pave the way for faster, more reliable ocean models, benefiting environmental monitoring and maritime operations.

Hybrid recurrent neural network using custom activation function for COVID-19 short term time series prediction

Introduction: The nonlinear behaviour of activation functions is vital in Artificial Neural Networks (ANNs) for exploring the complex relationship between the input and output features. However, these are probably going to encounter vanishing gradient problems due to small gradients that lead to training instability, expensive exponent operations, and slow convergence. Objectives: The primary objective of this study is to develop Taylor expansion of the second order to realize the hyperbolic tangent and sigmoid functions. In particular, long short term memory network make extensive use of these functions as well as gating mechanism to control the flow of information and gradients. Both the custom functions can reduce the vanishing gradient issues in recurrent neural networks. Methods: Taylor expansion hyperbolic tangent and sigmoid activation functions based parallel heterogeneous Long Short Term Memory Network integrated with Bayesian hyperparameter Optimization is being proposed for coronavirus multi step time series prediction. a Min-Max Normalization is applied, which produces scaled data in the range (0, 1). The normalized dataset is partitioned into training and testing datasets, with 80% and 20%, respectively. Furthermore, both train and test datasets are prepared as input and target series using a window size of 5-7.The further proposed model is tuned with key hyperparameters such as the number of neurons, learning rate, dropout, and type of optimizer. The remaining model parameters are epochs, batch size, and loss, which are 200, 32, and mean square error, respectively. Results: The proposed model efficacy is evaluated on coronavirus daily cumulative cases, cumulative deaths, daily new cases, and total recovery cases in India. The Analysis reveals that the current model achieves remarkable performance in terms of Mean Absolute Percentage Error (MAPE), Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Coefficient of determination (R2 Score) when compared to existing models. Conclusions: The study reveals that the proposed framework with the Taylor approximation activation function produces more consistency in prediction than the default activation functions, including Tanh and sigmoid. In spite of that, gradients of Taylor Tanh and sigmoid activation function traits indicate a decline in the possibility of vanishing issue.

The Differentiation of Extra Virgin Olive Oil from Other Olive Oil Categories Based on FTIR Spectroscopy and Random Forest

The great interest in the rapid and reliable differentiation of extra virgin olive oil from other olive oil categories is directly related to its unique sensory characteristics and high market prices. The aim of the present study was to investigate the potential of FTIR as a rapid and non-invasive technique to discriminate extra virgin olive oil (EVOO) from other olive oil categories (virgin olive oil, ordinary, and lampante) based on the acquired spectral profile of olive oil. Spectral data were collected, pre-processed, and correlated by Random Forest (RF) analysis with the sensory category (EVOO vs. other) of olive oil samples, as defined by sensory analysis undertaken previously by trained panelists. The results showed that the application of Savitzky–Golay (S-G) smoothing with a second derivative (d = 2), second- and third-order polynomial (p = 2, p = 3), and window size (w) of 12 and 13 points achieved the highest accuracy (0.91) between the two classes of samples. Characteristic spectral bands of triacylglycerols related to the carbonyl groups present in triacylglycerols (C=O) located near 1744 cm−1 (specific features: 1739, 1748, and 1751 cm−1), the fingerprinting area 1250–1000 cm−1 (specific features: 1088, 1094, 1116, 1123, 1124, 1158, 1162, 1236, 1240, and 1247 cm−1), which correspond to CH bending, and 1680 cm−1, which is associated with unsaturated aldehydes were observed to constitute the main basis of the discrimination of EVOO from the “other” class. The ability of the model to achieve high classification accuracy demonstrates the robustness of the FTIR spectral data combined with advanced machine learning techniques. Due to the lower cost and more rapid analysis time afforded by FTIR, this method provides promising perspectives for industrial olive oil classification.

Clinical Relatedness and Stability of vigiVec Semantic Vector Representations of AdverseEvents and Drugs in Pharmacovigilance.

Individual case reports are essential to identify and assess previously unknown adverse effects of medicines. On these reports, information on adverse events (AEs) and drugs are encoded in hierarchical terminologies. Encoding differences may hinder the retrieval and analysis of clinically related reports relevant to a topic of interest. Recent studies have explored the use of data-driven semantic vector representations to support analysis of pharmacovigilance data. This study aims to evaluate the stability and clinical relatedness of vigiVec, a semantic vector representation for codes of AEs and drugs. vigiVec is a published adaptation to pharmacovigilance of the publicly available Word2Vec model, applied to structured data instead of free text. It provides vector representations for MedDRA® Preferred Terms and WHODrug Global active ingredients, learned from reporting patterns in VigiBase, the WHO global database of adverse event reports for medicines and vaccines. For this study, a 20-dimensional Skip-gram architecture with window size 250 was used. Our evaluation focused on nearest neighbors identified by the cosine similarity of vigiVec vector representations. Clinical relatedness was measured through term intruder detection, whereby a medical doctor was tasked to identify a randomly selected term-the intruder-includedamong the four nearest neighbors to a specific AE or drug. Stability was measured as the average overlap in the ten nearest neighbors for each AE or drug, in repeated fittings of vigiVec. Among the ten nearest neighbors, 1.8 AEs on average belonged to the same MedDRA High Level Term (HLT; e.g., coagulopathies), and 1.3 drugs belonged to the same Anatomical Therapeutic Chemical level 3 (ATC-3; e.g., opioids). In the intruder detection task, when neighbors and intruders were both chosen from the same HLT, the intruder detection rate was 46%. When selected from different HLTs, it was 79%. Byrandom chance, we should expect 20%(1 in 5). Corresponding rates for drugs were 42% in same ATC-3 and 65% in different ATC-3. The stability of nearest neighbors was 80% for AEs and 64% for drugs. Nearest neighbors identified with vigiVec are stable and show high level of clinical relatedness. They are often from different parts of the existing hierarchies and complement these.

Quality control of DEMs using check surfaces

ABSTRACT This paper proposes the use of check surfaces or ‘patches’ for the assessment of Digital Elevation Model (DEM) elevations and derived variables (e.g. slope and aspect). We work with grid-type DEMs, and the patches are implemented through square windows of different sizes. Since the data included in a patch are autocorrelated, a trial is performed under controlled conditions of simulation, and then the same simulation method is applied to a DEM data set. Using the Kolmogorov–Smirnov statistic, the observed distribution functions of the results for different sample sizes (20, 50, 100) and different patch sizes (3 × 3, 5 × 5, 9 × 9, 11 × 11, 15 × 15, 19 × 19) and for a sample of points are compared against the true population distribution function. The trial based on autocorrelated synthetic data created following a geostatistical model (exponential law) outputs a clear result regarding the influence of intra-patch autocorrelation. The lower this autocorrelation is, the better the patch performs in terms of sampling efficiency. The same simulation process applied to synthetic data has also been applied to the case of a DEM product. The results obtained allow us to establish an equivalence between sample size when using control patches and control points. The main result of this study is that it allows us to understand the behaviour of samples based on patches and offers us a guide for determining the size of patch-based samples. The most relevant contribution of this proposal is that it opens the possibility of analysing variables derived from elevation data, such as slope and aspect.

Action Recognition in Basketball with Inertial Measurement Unit-Supported Vest.

In this study, an action recognition system was developed to identify fundamental basketball movements using a single Inertial Measurement Unit (IMU) sensor embedded in a wearable vest. This study aims to enhance basketball training by providing a high-performance, low-cost solution that minimizes discomfort for athletes. Data were collected from 21 collegiate basketball players, and movements such as dribbling, passing, shooting, layup, and standing still were recorded. The collected IMU data underwent preprocessing and feature extraction, followed by the application of machine learning algorithms including KNN, decision tree, Random Forest, AdaBoost, and XGBoost. Among these, the XGBoost algorithm with a window size of 250 and a 75% overlap yielded the highest accuracy of 96.6%. The system demonstrated superior performance compared to other single-sensor systems, achieving an overall classification accuracy of 96.9%. This research contributes to the field by presenting a new dataset of basketball movements, comparing the effectiveness of various feature extraction and machine learning methods, and offering a scalable, efficient, and accurate action recognition system for basketball.

Anatomical investigation of safety determining factors for keyhole drilling trajectories for robotic cochlear implant surgery.

Cochlear implants (CI) are the most successful bioprosthesis in medicine probably due to the tonotopic anatomy of the auditory pathway and of course the brain plasticity. Correct placement of the CI arrays, respecting the inner ear anatomy are therefore important. The ideal trajectory to insert a cochlear implant array is defined by an entrance through the round window membrane and continues as long as possible parallel to the basal turn of the cochlea. Image-guided surgery can directly drill with a robotic arm through the mastoid and execute an exact drilling of this precalculated most ideal trajectory. Here, we aim to identify critical anatomical structures determining the safest keyhole drilling trajectory by comparing easy and difficult CI surgeries performed with the HEARO Procedure: a robotic tool for image-guided surgery. Cone-beam computed tomography images of patients who underwent robot-assisted cochlear implantation surgery (RACIS) were included. Three of 25 cases had to be converted to conventional surgery because of the current safety mitigations based on anatomical distance. Radiological images in DICOM format were transferred to dedicated software (OTOPLAN® Cascination GMHB Bern Switzerland) for analyses. Surgical segmentation and previously planned trajectories were analyzed for these 25 cases by comparing cochlear sizes, facial recess sizes, round window sizes, and trajectory angles. In addition, facial recess angle, and cochlear orientation angles were measured with RadiAnt DICOM Viewer (Medixant, Pozan, Poland). Facial recess size, facial recess angle, and distance between the facial nerve and safe trajectory were smaller in patient who converted from robotic surgery to conventional. A significant positive correlation existed between basal turn angle and in-plane angle (p = 0.001, r = 0.859). In addition, there was a significant negative correlation between the basal turn length and the last electrode insertion depth degree (p = 0.007, r = 0.545). In our robotic surgery cases, we demonstrate that the limiting factors of anatomical relationships are constituted by the dimensions of the facial recess and the cochlear orientation. The findings of this study are considered to be a reference for future studies in achieving collision-free trajectory planning in robotic-assisted cochlear implant surgery.

Classifying Food Items During an Eating Occasion: A Machine Learning Approach with Slope Dynamics for Windowed Kinetic Data.

Wearable devices equipped with a range of sensors have emerged as promising tools for monitoring and improving individuals' health and lifestyle. Contribute to the investigation and development of effective and reliable methods for dietary monitoring based on raw kinetic data generated by wearable devices. This study uses resources from the NOTION study. A total of 20 healthy subjects (9 women and 11 men, aged 20-31 years) were equipped with two commercial smartwatches during four eating occasions under semi-naturalistic conditions. All meals were video-recorded, and acceleration data were extracted and analyzed. Food recognition on these features was performed using random forest (RF) models with 5-fold cross-validation. The performance of the classifiers was expressed in out-of-bag sensitivity and specificity. Acceleration along the x-axis and power show the highest and lowest rates of median variable importance, respectively. Increasing the window size from 1 to 5 s leads to a gain in performance for almost all food items. The RF classifier reaches the highest performance in identifying meatballs (89.4% sensitivity and 81.6% specificity) and the lowest in identifying sandwiches (74.6% sensitivity and 72.5% specificity). Monitoring food items using simple wristband-mounted wearable devices is feasible and accurate for some foods while unsatisfactory for others. Machine learning tools are necessary to deal with the complexity of signals gathered by the devices, and research is ongoing to improve accuracy further and work on large-scale and real-time implementation and testing.

A Novel Methodology for Performance Evaluation in Advanced Quality Control

Current global conditions and challenges in industrial manufacturing, marked by dynamism, competition, and the need for responsible resource management, have increased the demand for sustainable manufacturing practices. The integration of Industry 4.0 and the recent development of Industry 5.0 have added dynamism, which has generated profound implications for quality control and process monitoring, focusing mainly on recognising control patterns within the manufacturing environment. This study introduces a novel methodology for evaluating the performance of pattern classification models used in advanced quality control. Our approach incorporates robust performance metrics, early detection, window size, network hyperparameters, and concurrent patterns within a simulated monitoring environment. Unlike previous research, our evaluation methodology addresses the sensitivity of classification models to various factors, emphasising the critical balance between early detection and minimising false alarms. The findings reveal that window size significantly impacts the model’s sensitivity to pattern changes, highlighting that measuring early detection alone is impractical in real-world applications. Furthermore, optimal hyperparameter selection enhances the model’s practical applicability.

The degree of parallel/serial processing affects stimulus-driven and memory-driven attentional capture: Evidence for the attentional window account.

The issue of whether a salient stimulus in the visual field captures attention in a stimulus-driven manner has been debated for several decades. The attentional window account proposed to resolve this issue by claiming that a salient stimulus captures attention and interferes with target processing only when an attentional window is set wide enough to encompass both the target and the salient distractor. By contrast, when a small attentional window is serially shifted among individual stimuli to find a target, no capture is found. Research findings both support and challenge this attentional window account. However, in these studies, the attentional window size was improperly estimated, necessitating a re-evaluation of the account. Here, using a recently developed visual search paradigm, we investigated whether visual stimuli were processed in a parallel or a serial manner. We found significant attentional capture when multiple stimuli were processed in parallel within a large attentional window. By contrast, when a small window had to be serially shifted, no capture was found. We conclude that the attentional window account can be a useful framework to resolve the widespread debate regarding stimulus-driven attentional capture.

Multiscale Sensitivity Analysis of Landscape Fragmentation in Plantation Forests on the Loess Plateau

ABSTRACTEffectively quantifying plantation forest fragmentation is crucial for vegetation restoration and management on the Loess Plateau. Forest area density (FAD) effectively measures fragmentation, with multiscale sensitivity analysis essential for determining the appropriate window scale threshold. This study uses plantation forest data from different geomorphological types (hilly gully and plateau gully region) of the Loess Plateau. Various window sizes are applied to evaluate the FAD threshold curve and its derivative for determining a stable fragmentation threshold, while a structural equation model is employed to analyze the drivers of forest fragmentation. The results are as follows: (1) FAD variability decreases with increasing window size, leveling off after reaching the threshold. (2) Thresholds vary by forest type and county. (3) Two principal components explain 81.27% of the window stabilization threshold variation, with strong correlations between similar fragmentation types. (4) Fragmentation slowed between 2000 and 2022, with hilly gully region more fragmented than plateau gully region. (5) Stand structure mitigates fragmentation, with topographic and climate change influences showing heterogeneity. “Core” maintain stability, while “Islet” drive fragmentation. This study emphasizes the importance of scale‐specific analysis and adaptive management strategies in mitigating forest fragmentation. This study supports optimizing ecological restoration and targeted conservation strategies, promoting sustainable forest management on the Loess Plateau.

Sliding-Window Dissimilarity Cross-Attention for Near-Real-Time Building Change Detection

A near-real-time change detection network can consistently identify unauthorized construction activities over a wide area, empowering authorities to enforce regulations efficiently. Furthermore, it can promptly assess building damage, enabling expedited rescue efforts. The extensive adoption of deep learning in change detection has prompted a predominant emphasis on enhancing detection performance, primarily through the expansion of the depth and width of networks, overlooking considerations regarding inference time and computational cost. To accurately represent the spatio-temporal semantic correlations between pre-change and post-change images, we create an innovative transformer attention mechanism named Sliding-Window Dissimilarity Cross-Attention (SWDCA), which detects spatio-temporal semantic discrepancies by explicitly modeling the dissimilarity of bi-temporal tokens, departing from the mono-temporal similarity attention typically used in conventional transformers. In order to fulfill the near-real-time requirement, SWDCA employs a sliding-window scheme to limit the range of the cross-attention mechanism within a predetermined window/dilated window size. This approach not only excludes distant and irrelevant information but also reduces computational cost. Furthermore, we develop a lightweight Siamese backbone for extracting building and environmental features. Subsequently, we integrate an SWDCA module into this backbone, forming an efficient change detection network. Quantitative evaluations and visual analyses of thorough experiments verify that our method achieves top-tier accuracy on two building change detection datasets of remote sensing imagery, while also achieving a real-time inference speed of 33.2 FPS on a mobile GPU.

Optical Quantification of Wind‐Wave Breaking and Regional Variations in Different Offshore Seas Using Landsat‐8 OLI Images

AbstractOceanic whitecaps, as indicators of increased air–sea exchange, can be effectively captured by Landsat‐8 Operational Land Imager (OLI) images with a 30‐m spatial resolution. This study used a new adaptive iterative triangle algorithm, which was applied to 400 OLI images synchronized with National Data Buoy Center‐measured wind speeds, covering the different offshore areas of the United States over the last ten years to automatically extract whitecap‐affected pixels. By integrating radiative transfer equations, we calculated the whitecap coverage (W), determined that a 4 km window size is optimal for calculating W, and established a whitecap coverage‐sea surface wind speed model. A sliding window method was used to achieve high‐resolution (100 m) large‐area sea surface wind speed estimations. More importantly, this study provides new insights into the impact of different wind and wave conditions on W and regional variations in the whitecap coverage‐sea surface wind speed model from an optical satellite perspective, which can effectively quantify the wind‐wave breaking and distinguish the regional variations of them in different offshore seas. By comparing with 10‐m resolution data from the Sentinel‐2 Multi‐Spectral Instrument, we further clarified the impact of spatial resolution on the selection of methods for calculating W, revealing scale effects in optical remote sensing of whitecap detection and proposing corresponding W calculation strategies. These results demonstrate the potential of high‐resolution optical remote sensing for monitoring whitecaps, estimating sea surface winds and studying air–sea interactions.