Search Results (443)

Semantic change detection (SCD) effectively captures ground object transition information within change regions, delivering more comprehensive and detailed results than binary change detection (BCD) tasks. The existing multi-task SCD models enable parallel processing of segmentation and BCD of bi-temporal remote sensing images, but they still have shortcomings in feature mining, interaction, and cross-task transfer. To address these limitations, a multi-branch feature interaction network (MBFI-Net) is proposed. MBFI-Net designs parallel encoding branches with attention mechanisms that enhance semantic change perception by jointly modeling global contextual patterns and local details. In addition, MBFI-Net proposes bi-temporal feature interaction (BTFI) and cross-task feature transfer (CTFT) modules to improve feature diversity and representativeness, and combines with prior logical relationship constraints to improve SCD performance. Comparative and ablation studies on the SECOND and Landsat-SCD datasets highlight the superiority and robustness of MBFI-Net, which achieves SeKs of 0.2117 and 0.5543, respectively. Furthermore, MBFI-Net strikes a balance between SCD results and model complexity and has superior detection performance for semantic change categories with a small proportion. Full article

While face recognition systems are increasingly deployed in critical domains, they remain vulnerable to presentation attacks and exhibit significant demographic bias, particularly affecting African populations. This paper presents a fairness-aware Presentation Attack Detection (PAD) system using Local Binary Patterns (LBPs) with novel ethnicity-aware processing techniques specifically designed for African contexts. Our approach introduces three key technical innovations: (1) adaptive preprocessing with differentiated Contrast-Limited Adaptive Histogram Equalization (CLAHE) parameters and gamma correction optimized for different skin tones, (2) group-specific decision threshold optimization using Equal Error Rate (EER) minimization for each ethnic group, and (3) three novel statistical methods for PAD fairness evaluation such as Coefficient of Variation analysis, McNemar’s significance testing, and bootstrap confidence intervals representing the first application of these techniques in Presentation Attack Detection. Comprehensive evaluation on the Chinese Academy of Sciences Institute of Automation-SURF Cross-ethnicity Face Anti-spoofing dataset (CASIA-SURF CeFA) dataset demonstrates significant bias reduction achievements: a 75.6% reduction in the accuracy gap between African and East Asian subjects (from 3.07% to 0.75%), elimination of statistically significant bias across all ethnic group comparisons, and strong overall performance, with 95.12% accuracy and 98.55% AUC. Our work establishes a comprehensive methodology for measuring and mitigating demographic bias in PAD systems while maintaining security effectiveness, contributing both technical innovations and statistical frameworks for inclusive biometric security research. Full article

The thematic processing of pseudocolor composite images, especially those created from remote sensing data, is of considerable interest. The set of spectral classes comprising such images is typically described by a nominal scale, meaning the absence of any predetermined relationships between the classes. However, in many cases, images of this type may contain elements of a regular spatial order, one variant of which is a gradient structure. Gradient structures are characterized by a certain regular spatial ordering of spectral classes. Recognizing gradient patterns in the structure of pseudocolor composite images opens up new possibilities for deeper thematic images processing. This article describes an algorithm for analyzing the spatial structure of a pseudocolor composite image to identify gradient patterns. In this process, the initial nominal scale of spectral classes is transformed into a rank scale of the gradient legend. The algorithm is based on the analysis of Moore neighborhoods for each image pixel. This creates an array of the prevalence of all types of local binary patterns (the pixel’s nearest neighbors). All possible variants of the spectral class rank scale composition are then considered. The rank scale variant that describes the largest proportion of image pixels within its gradient order is used as a final result. The user can independently define the criteria for the significance of the gradient order in the analyzed image, focusing either on the overall statistics of the proportion of pixels consistent with the spatial structure of the selected gradient or on the statistics of a selected key image region. The proposed algorithm is illustrated using analysis of test examples. Full article

Based on niche theory, this study pioneered the application of the niche state-role model, suitability model, subgroup model, and overlap model in evaluating small-town communities, integrating both their endowment attributes and relational attributes. Taking Pingshan County, Hebei Province, China, as a case study, it revealed the evolution patterns of suburban small-town communities from 2000 to 2020. The results indicated significant changes in the comprehensive niche indices and rankings of small-town communities, though top-ranking towns remained relatively stable. Niche indices varied from dimensions, primarily manifesting a binary opposition between natural and humanistic factors. The overall suitability of small-town communities showed little change, but internal disparities gradually narrowed. The niche subgroups of small-town communities displayed a gradient distribution pattern: ecological functions significantly strengthened in the west of the county; population and economy functions continuously intensified in southeastern towns; while central-region towns maintained intermediate levels. Regarding niche overlap based on population and economy flows, the overall competitive intensity of small-town communities weakened, but competition among central region towns intensified. Regarding niche overlap based on ecology flows, the overall competitive intensity strengthened, with particularly notable changes in the central and eastern regions. Moreover, the spatial evolution of county-level small towns exhibited scale-dependent differences: while the macro-scale pattern remained relatively stable, the micro-scale pattern underwent significant changes, with the driving force gradually shifting from local endowments to factor flows. Full article

Visual emotion recognition in unconstrained environments remains challenging, as single-stream deep learning models often fail to capture the localized facial cues and contextual information necessary for accurate classification. This study introduces a hierarchical multi-level feature fusion framework that systematically combines low-level micro-textural features (Local Binary Patterns), mid-level facial cues (Facial Action Units), and high-level scene semantics (Places365) with ResNet-50 global embeddings. Evaluated on the large-scale EmoSet-3.3M dataset, which contains 3.3 million images across eight emotion categories, the framework demonstrates marked performance gains with the best configuration (LBP-FAUs-Places365-ResNet). The proposed framework achieves 74% accuracy and a macro-averaged F1-score of 0.75 under its best configuration (LBP-FAUs-Places365-ResNet), representing a five-percentage-point improvement over the ResNet-50 baseline. The approach excels at distinguishing high-intensity emotions, maintaining efficient inference (2.2 ms per image, 29 M parameters), and analysis confirms that integrating facial muscle activations with scene context enables nuanced emotional differentiation. These results validate that hierarchical feature integration significantly advances robust, human-aligned visual emotion recognition, making it suitable for real-world Human–Computer Interaction (HCI) and affective computing applications. Full article

Background: Artificial intelligence (AI) emerges as a powerful tool to assist breast cancer screening; however, its integration into different mammographic modalities remains insufficiently explored. Digital Mammography (DM) is widely accessible but presents limitations in dense breast tissue, whereas Contrast-Enhanced Spectral Mammography (CESM) provides functional information that enhances lesion visualization. Understanding how deep learning models behave across these modalities, and determining whether their decision-making patterns remain consistent, is essential for equitable clinical adoption. Methods: This study evaluates three convolutional neural network (CNN) architectures, ResNet-18, DenseNet-121, and EfficientNet-B0, for binary classification of breast lesions using DM and CESM images from the public CDD-CESM dataset (2006 images, three diagnostic classes). The models are trained separately on DM and CESM using three classification tasks: Normal vs. Benign, Benign vs. Malignant, and Normal vs. Malignant. A 3-fold cross-validation scheme and an independent test set are employed. Training uses transfer learning with ImageNet weights, weighted binary cross-entropy (BCE) loss, and SHapley Additive exPlanations (SHAP) analysis to visualize pixel-level relevance of model decisions. Results: CESM yields higher performance in the Normal vs. Benign and Benign vs. Malignant tasks, whereas DM achieves the highest discriminative ability in the Normal vs. Malignant comparison (EfficientNet-B0: AUC = 97%, Accuracy = 93.15%), surpassing the corresponding CESM results (AUC = 93%, Accuracy = 85.66%). SHAP attribution maps reveal anatomically coherent decision patterns in both modalities, with CESM producing sharper and more localized relevance regions due to contrast uptake, while DM exhibits broader yet spatially aligned attention. Across architectures, EfficientNet-B0 demonstrates the most stable performance and interpretability. Conclusions: CESM enhances subtle lesion discrimination through functional contrast, whereas DM, despite its simpler acquisition and wider availability, provides highly accurate and explainable outcomes when combined with modern CNNs. The consistent SHAP-based relevance observed across modalities indicates that both preserve clinically meaningful information. To the best of our knowledge, this study is the first to directly compare DM and CESM under identical preprocessing, training, and evaluation conditions using explainable deep learning models. Full article

This paper presents a proof-of-concept for a natural-language-based closed-loop controller that regulates the temperature of a simple single-input single-output (SISO) thermal process. The key idea is to express a relay-with-hysteresis policy in plain English and let a local large language model (LLM) interpret sensor readings and output a binary actuation command at each sampling step. Beyond interface convenience, we demonstrate that natural language can serve as a valid medium for modeling physical reality and executing deterministic reasoning in control loops. We implement a compact plant model and compare two controllers: a conventional coded relay and an LLM-driven controller prompted with the same logic and constrained to a single-token output. The workflow integrates schema validation, retries, and a safe fallback, while a stepwise evaluator checks agreement with the baseline. In a long-horizon (1000-step) simulation, the language controller reproduces the hysteresis behavior with matching switching patterns. Furthermore, sensitivity and ablation studies demonstrate the system’s robustness to measurement noise and the LLM’s ability to correctly execute the hysteresis policy, thereby preserving the theoretical robustness inherent to this control law. This work demonstrates that, for slow thermal dynamics, natural-language policies can achieve comparable performance to classical relay systems while providing a transparent, human-readable interface and facilitating rapid iteration. Full article

Epileptic seizure (ES) detection is critical for improving clinical outcomes in epilepsy management. While intracranial EEG (iEEG) provides high-quality neural recordings, existing detection methods often rely on large amounts of data, involve high computational complexity, or fail to generalize in low-data settings. In this paper, we propose a lightweight, data-efficient, and high-performance approach for ES detection based on hyperdimensional computing (HDC). Our method first extracts local binary patterns (LBPs) from each iEEG channel to capture temporal–spatial dynamics. These binary sequences are then mapped into a high-dimensional space via HDC for robust representation, followed by a binary Naive Bayes classifier to distinguish ictal and inter-ictal states. The proposed design enables fast inference, low memory requirements, and suitability for hardware implementation. We evaluate the method on the SWEC-ETHZ iEEG short-term dataset. In one-shot learning, it achieves 100% sensitivity and specificity for most patients. In few-shot learning, it maintains 98.88% sensitivity and 93.09% specificity on average. The average latency is 4.31 s, demonstrating that it is much better than state-of-the-art methods. These results demonstrate the method’s potential for efficient, low-resource, and high-performance ES detection. Full article

Cashew apples, a byproduct of the cashew nut industry with an estimated global production of 38 million tonnes, are rich in several essential nutrients and are widely processed into juice, syrup, wine, pickles, and other value-added products. However, their morphological and physicochemical properties vary significantly across varieties, complicating in-field characterization, maturity assessment, and biochemical analysis. These challenges originate from the reliance on costly chemicals, skilled manpower, limited time, and sophisticated equipment. This study employed a user-developed computer vision-based ImageJ 1.x batch processing plugin to assess 15 physicochemical properties across six diverse cashew apple varieties from the images of slices and whole samples. Five methodologies—color grid, surface morphology, gray level co-occurrence matrix, local binary pattern, and color indices—generated image-based metrics rapidly ($2.87\pm 0.79$ s/image). The correlation of wet chemistry with image-based parameters, linear modeling, and wet chemistry parameters prediction with an independent dataset were successfully performed, and the successfully modeled properties include acidity, antioxidants, carbohydrates, carotenoids, crude fat, flavonoids, pH, phenolics, proteins, tannins, vitamin C, and total soluble solids. The results demonstrated the feasibility of predicting 11 out of 15 physicochemical properties of cashew apples ($R^2>0.5$). This methodology offers a faster, safer, and cost-effective alternative to wet chemistry and can be extended to other horticultural crops. Full article

The local rules of elementary cellular automata (ECA) with one-dimensional three-cell neighborhoods are represented by eight-bit binary numbers that encode deterministic update rules. This class of systems is also commonly referred to as the Wolfram cellular automata. These automata are widely utilized to investigate self-organization phenomena and the dynamics of complex systems. In this work, we employ numerical simulations and computational methods to investigate the asymptotic density and dynamical evolution mechanisms in Wolfram automata. We explore alternative initial conditions under which certain Wolfram rules generate similar fractal patterns over time, even when starting from a single active site. Our results reveal the relationship between the asymptotic density and the initial density of selected rules. Furthermore, we apply both supervised and unsupervised learning methods to identify the configurations associated with different Wolfram rules. The supervised learning methods effectively identify the configurations of various Wolfram rules, while unsupervised methods like principal component analysis and autoencoders can approximately cluster configurations of different Wolfram rules into distinct groups, yielding results that align well with simulated density outputs. Machine learning methods offer significant advantages in identifying different Wolfram rules, as they can effectively distinguish highly similar configurations that are challenging to differentiate manually. Full article

Background/Objectives: Toolmark analysis on cartridge cases offers critical insights in forensic ballistics, as the impressions left on cartridge cases by firearm components—such as the firing pin, breech face, and annulus—carry distinctive patterns and act as unique identifiers that can be used for firearm linkage. This study aims to develop a systematic and interpretable feature extraction pipeline for these regions to support future automation and comparison studies in forensic cartridge case analysis. Methods: A dataset of 20 high-resolution cartridge case images was prepared, and each region of interest (firing pin impression, breech face, and annulus) was manually annotated using the LabelMe tool. ImageJ and Python-based scripts were employed for feature extraction, capturing geometric descriptors (area, perimeter, circularity, and eccentricity) and texture-based features (Local Binary Patterns and Haralick statistics). In total, 61 quantitative features were derived from the annotated regions. Similarity between cartridge cases was evaluated using Euclidean distance metrics after normalization. Results: The extracted and calibrated region-wise geometric and texture features demonstrated distinct variation patterns across firing pin, breech face, and annulus regions. Pairwise similarity analysis revealed measurable intra-class differences, indicating the discriminative potential of the extracted features even within cartridges likely fired from the same firearm. Conclusions: This study provides a foundational, region-wise quantitative framework for analysing cartridge case impressions. The extracted dataset and similarity outcomes establish a baseline for subsequent research on firearm identification and model-based classification in forensic ballistics. Full article

The rise in trusted machine learning has prompted concerns about the security, reliability and controllability of deep learning, especially when it is applied to sensitive areas involving life and health safety. To thoroughly analyze potential attacks and promote innovation in security technologies for DNNs, this paper conducts research on adversarial attacks against medical images and proposes a medical image attack method that focuses on lesion areas and has good transferability, named LatAtk. First, based on the image segmentation algorithm, LatAtk divides the target image into an attackable area (lesion area) and a non-attackable area and injects perturbations into the attackable area to disrupt the attention of the DNNs. Second, a class activation loss function based on gradient-weighted class activation mapping is proposed. By obtaining the importance of features in images, the features that play a positive role in model decision-making are further disturbed, making LatAtk highly transferable. Third, a texture feature loss function based on local binary patterns is proposed as a constraint to reduce the damage to non-semantic features, effectively preserving texture features of target images and improving the concealment of adversarial samples. Experimental results show that LatAtk has superior aggressiveness, transferability and concealment compared to advanced baselines. Full article

As an advanced form of community development, Future Communities (Weilai Shequ) is a policy-led urban initiative launched in Zhejiang, China, that prioritizes human-centered development. However, it is currently confronted with an inherent contradiction: the expansion of technological rationality is encroaching upon humanistic values. Centering on the core “technology–human” relationship, this study is dedicated to exploring development measures for Future Community that synergistically integrate technological empowerment and humanistic care. Using natural language processing techniques (LDA topic modeling), we conducted an exploration and analysis of the thematic characteristics and evolution of 40 policy documents related to future communities issued by the central and local governments of China from 2014 to 2024. The study identifies six core topics: Quality Enhancement, Technical Foundation, Intelligent Operations and Maintenance, Green and Low-Carbon, All-Age Friendliness, and Community Services. Analysis revealed that each theme embodies a dual connotation of both technological and humanistic dimensions. Furthermore, the study revealed that the evolution of policy semantics follows a three-stage developmental pattern: technology dominance and nascent human-centered values; human-centered rise and technology empowerment; and human-centered deepening and technological embeddedness. Based on the above findings, and grounded in a phenomenological perspective, this study integrates Alexander’s human-centered architectural philosophy with Ihde’s theory of technological mediation to propose a future community construction pathway jointly driven by “technological mediation” and “human presence.” Theoretically, this research transcends the binary narrative of technology versus humanism. In practice, it provides policymakers with tools to avoid technological pitfalls. It establishes fundamental principles for planners and designers to implement humanistic values, ultimately aiming to realize, at the community level, the vision of technology serving humanity’s aspiration for a better life. Full article

Structural Health Monitoring (SHM) systems increasingly require efficient and scalable methods for identifying structural damage under dynamic loading. Traditional learning-based SHM models often rely on high-dimensional features or deep architectures, which may be computationally intensive and difficult to deploy in real-time applications, especially in scenarios with limited resources or bandwidth constraints. In this work, we propose a lightweight classification framework based on Hyperdimensional Computing (HDC) to detect structural damage using vibration-induced features, aiming to reduce complexity while maintaining detection performance. The proposed method encodes a rich feature set, including time-domain, frequency-domain, and autoregressive (AR) model features into high-dimensional binary vectors through a sliding window approach, capturing temporal variations and local patterns within the signal. A supervised HDC classifier is trained to distinguish between healthy and damaged structural states using these compact encodings. The framework enables fast learning and low memory usage, making it particularly suitable for edge-level SHM applications where real-time processing is required. To evaluate the feasibility and effectiveness of the proposed method, experiments are conducted on vibration data collected from controlled lateral impact tests on a concrete-filled steel tubular structure. The results validate the method ability to detect the damage-induced variations in modal frequencies and highlight its potential as a compact, robust, and efficient solution for future SHM systems based on modal data. Full article

This study aims to evaluate the ability of an artificial intelligence (AI) model developed for use in the field of orthodontics to accurately and reliably classify skeletal maturation stages of individuals using hand–wrist radiographs. A total of 809 grayscale hand–wrist radiographs (250 × 250 px; pre-peak n = 400, peak n = 100, post-peak n = 309) were analyzed using four complementary image-based feature extraction methods: Local Binary Pattern (LBP), Histogram of Oriented Gradients (HOG), Zernike Moments (ZM), and Intensity Histogram (IH). These methods generated 2355 features per image, of which 2099 were retained after variance thresholding. The most informative 1250 features were selected using the ANOVA F-test and classified with a stacking-based machine learning (ML) architecture composed of Light Gradient Boosting Machine (LightGBM) and Logistic Regression (LR) as base learners, and Random Forest (RF) as the meta-learner. Across all evaluation folds, the average performance of the model was Accuracy = 83.42%, Precision = 84.48%, Recall = 83.42%, and F1 = 83.50%. The proposed model achieved 87.5% accuracy, 87.8% precision, 87.5% recall, and an F1-score of 87.6% in 10-fold cross-validation, with a macro-average area under the ROC curve (AUC) of 0.96. The pre-peak stage, corresponding to the period of maximum growth velocity, was identified with 92.5% accuracy. These findings indicate that integrating handcrafted radiographic features with ensemble learning can enhance diagnostic precision, reduce observer variability, and accelerate evaluation. The model provides an interpretable and clinically applicable AI-based decision-support tool for skeletal maturity assessment in orthodontic practice. Full article