Search Results (896)

Reliable gesture interfaces are essential for coordinating distributed robot teams in the field. However, models trained in a single domain often perform poorly when confronted with new users, different sensors, or unfamiliar environments. To address this challenge, we propose a memory-efficient replay-based domain incremental learning (DIL) framework, ReDIaL, that adapts to sequential domain shifts while minimizing catastrophic forgetting. Our approach employs a frozen encoder to create a stable latent space and a clustering-based exemplar replay strategy to retain compact, representative samples from prior domains under strict memory constraints. We evaluate the framework on a multi-domain air-marshalling gesture recognition task, where an in-house dataset serves as the initial training domain and the NATOPS dataset provides 20 cross-user domains for sequential adaptation. During each adaptation step, training data from the current NATOPS subject is interleaved with stored exemplars to retain prior knowledge while accommodating new knowledge variability. Across 21 sequential domains, our approach attains $97.34\%$ accuracy on the domain incremental setting, exceeding pooled fine-tuning ($91.87\%$), incremental fine-tuning ($80.92\%$), and Experience Replay ($94.20\%$) by $+5.47$, $+16.42$, and $+3.14$ percentage points, respectively. Performance also approaches the joint-training upper bound ($98.18\%$), which represents the ideal case where data from all domains are available simultaneously. These results demonstrate that memory-efficient latent exemplar replay provides both strong adaptation and robust retention, enabling practical and trustworthy gesture-based human–robot interaction in dynamic real-world deployments. Full article

Accurate real-time detection of blueberry maturity is vital for automated harvesting. However, existing methods often fail under occlusion, variable lighting, and dense fruit distribution, leading to reduced accuracy and efficiency. To address these challenges, we designed a lightweight deep learning framework that integrates improved feature extraction, attention-based fusion, and progressive transfer learning to enhance robustness and adaptability To overcome these challenges, we propose BMDNet-YOLO, a lightweight model based on an enhanced YOLOv8n. The backbone incorporates a FasterPW module with parallel convolution and point-wise weighting to improve feature extraction efficiency and robustness. A coordinate attention (CA) mechanism in the neck enhances spatial-channel feature selection, while adaptive weighted concatenation ensures efficient multi-scale fusion. The detection head employs a heterogeneous lightweight structure combining group and depthwise separable convolutions to minimize parameter redundancy and boost inference speed. Additionally, a three-stage transfer learning framework (source-domain pretraining, cross-domain adaptation, and target-domain fine-tuning) improves generalization. Experiments on 8,250 field-collected and augmented images show BMDNet-YOLO achieves 95.6% mAP@0.5, 98.27% precision, and 94.36% recall, surpassing existing baselines. This work offers a robust solution for deploying automated blueberry harvesting systems. Full article

The increasing complexity of modern food production demands advanced solutions for quality control (QC), safety monitoring, and process optimization. This review systematically explores recent advancements in machine learning (ML) for QC across six domains: Food Quality Applications; Defect Detection and Visual Inspection Systems; Ingredient Optimization and Nutritional Assessment; Packaging—Sensors and Predictive QC; Supply Chain—Traceability and Transparency and Food Industry Efficiency; and Industry 4.0 Models. Following a PRISMA-based methodology, a structured search of the Scopus database using thematic Boolean keywords identified 124 peer-reviewed publications (2005–2025), from which 25 studies were selected based on predefined inclusion and exclusion criteria, methodological rigor, and innovation. Neural networks dominated the reviewed approaches, with ensemble learning as a secondary method, and supervised learning prevailing across tasks. Emerging trends include hyperspectral imaging, sensor fusion, explainable AI, and blockchain-enabled traceability. Limitations in current research include domain coverage biases, data scarcity, and underexplored unsupervised and hybrid methods. Real-world implementation challenges involve integration with legacy systems, regulatory compliance, scalability, and cost–benefit trade-offs. The novelty of this review lies in combining a transparent PRISMA approach, a six-domain thematic framework, and Industry 4.0/5.0 integration, providing cross-domain insights and a roadmap for robust, transparent, and adaptive QC systems in the food industry. Full article

The proposed study explores the consistency of the geometrical character of surfaces under scaling, rotation and translation. In addition to its mathematical significance, it also exhibits advantages over image processing and economic applications. In this paper, the authors used partition-based principal component analysis similar to two-dimensional Sub-Image Principal Component Analysis (SIMPCA), along with a suitably modified atypical wavelet transform in the classification of 2D images. The proposed framework is further extended to three-dimensional objects using machine learning classifiers. To strengthen fairness, we benchmarked against both Random Forest (RF) and Support Vector Machine (SVM) classifiers using nested cross-validation, showing consistent gains when TIFV is included. In addition, we carried out a robustness analysis by introducing Gaussian noise to the intensity channel, confirming that TIFV degrades much more gracefully compared to traditional descriptors. Experimental results demonstrate that the method achieves improved performance compared to traditional hand-crafted descriptors such as measured values and histogram of oriented gradients. In addition, it is found to be useful that this proposed algorithm is capable of establishing consistency locally, which is never possible without partition. However, a reasonable amount of computational complexity is reduced. We note that comparisons with deep learning baselines are beyond the scope of this study, and our contribution is positioned within the domain of interpretable, affine-invariant descriptors that enhance classical machine learning pipelines. Full article

The Zero Trust Architecture (ZTA) model has emerged as a foundational cybersecurity paradigm that eliminates implicit trust and enforces continuous verification across users, devices, and networks. This study presents a systematic literature review of 74 peer-reviewed articles published between 2016 and 2025, spanning domains such as cloud computing (24 studies), Internet of Things (11), healthcare (7), enterprise and remote work systems (6), industrial and supply chain networks (5), mobile networks (5), artificial intelligence and machine learning (5), blockchain (4), big data and edge computing (3), and other emerging contexts (4). The analysis shows that authentication, authorization, and access control are the most consistently implemented ZTA components, whereas auditing, orchestration, and environmental perception remain underexplored. Across domains, the main challenges include scalability limitations, insufficient lightweight cryptographic solutions for resource-constrained systems, weak orchestration mechanisms, and limited alignment with regulatory frameworks such as GDPR and HIPAA. Cross-domain comparisons reveal that cloud and enterprise systems demonstrate relatively mature implementations, while IoT, blockchain, and big data deployments face persistent performance and compliance barriers. Overall, the findings highlight both the progress and the gaps in ZTA adoption, underscoring the need for lightweight cryptography, context-aware trust engines, automated orchestration, and regulatory integration. This review provides a roadmap for advancing ZTA research and practice, offering implications for researchers, industry practitioners, and policymakers seeking to enhance cybersecurity resilience. Full article

With the rapid evolution of artificial intelligence technologies in power systems, data-driven time-series forecasting has become instrumental in enhancing the stability and reliability of power systems, allowing operators to anticipate demand fluctuations and optimize energy distribution. Despite the notable progress made by current methods, they are still hindered by two major limitations: most existing models are relatively small in architecture, failing to fully leverage the potential of large-scale models, and they are based on fixed nonlinear mapping functions that cannot adequately capture complex patterns, leading to information loss. To this end, an LLM-Empowered Kolmogorov–Arnold frequency learning (LKFL) is proposed for time series forecasting in power systems, which consists of LLM-based prompt representation learning, KAN-based frequency representation learning, and entropy-oriented cross-modal fusion. Specifically, LKFL first transforms multivariable time-series data into text prompts and leverages a pre-trained LLM to extract semantic-rich prompt representations. It then applies Fast Fourier Transform to convert the time-series data into the frequency domain and employs Kolmogorov–Arnold networks (KAN) to capture multi-scale periodic structures and complex frequency characteristics. Finally, LKFL integrates the prompt and frequency representations through an entropy-oriented cross-modal fusion strategy, which minimizes the semantic gap between different modalities and ensures full integration of complementary information. This comprehensive approach enables LKFL to achieve superior forecasting performance in power systems. Extensive evaluations on five benchmarks verify that LKFL sets a new standard for time-series forecasting in power systems compared with baseline methods. Full article

In order to solve the problem of inconsistent data distribution in machine learning, domain adaptation based on feature representation methods extracts features from the source domain, and transfers them to the target domain for classification. The existing feature representation-based methods mainly solve the problem of inconsistent feature distribution between the source domain data and the target domain data, but only a few methods analyze the correlation of cross-domain features between the original space and shared latent space, which reduces the performance of domain adaptation. To this end, we propose a domain adaptation method with a residual module, the main ideas of which are as follows: (1) transfer the source domain data features to the target domain data through the shared latent space to achieve features sharing; (2) build a cross-domain residual learning model using the latent feature space as the residual connection of the original feature space, which improves the propagation efficiency of features; (3) use a regular feature space to sparse feature representation, which can improve the robustness of the model; and (4) give an optimization algorithm, and the experiments on the public visual datasets (Office31, Office-Caltech, Office-Home, PIE, MNIST-UPS, COIL20) results show that our method achieved 92.7% accuracy on Office-Caltech and 83.2% on PIE and achieved the highest recognition accuracy in three datasets, which verify the effectiveness of the method. Full article

Multi-modal sensor fusion has become a cornerstone of robust autonomous driving systems, enabling perception models to integrate complementary cues from cameras, LiDARs, radars, and other modalities. This survey provides a structured overview of recent advances in deep learning-based fusion methods, categorizing them by architectural paradigms (e.g., BEV-centric fusion and cross-modal attention), learning strategies, and task adaptations. We highlight two dominant architectural trends: unified BEV representation and token-level cross-modal alignment, analyzing their design trade-offs and integration challenges. Furthermore, we review a wide range of applications, from object detection and semantic segmentation to behavior prediction and planning. Despite considerable progress, real-world deployment is hindered by issues such as spatio-temporal misalignment, domain shifts, and limited interpretability. We discuss how recent developments, such as diffusion models for generative fusion, Mamba-style recurrent architectures, and large vision–language models, may unlock future directions for scalable and trustworthy perception systems. Extensive comparisons, benchmark analyses, and design insights are provided to guide future research in this rapidly evolving field. Full article

Microplastics pose a growing environmental concern, necessitating accurate and scalable methods for their detection and classification. This study presents a novel deep learning framework that integrates a transformer-based architecture with domain adaptation techniques to classify microplastics using reflectance micro-FTIR spectroscopy. A key challenge addressed in this work is the domain shift between laboratory-prepared reference spectra and environmentally sourced spectra, which can significantly degrade model performance. To overcome this, three domain-adaptation strategies—Domain Adversarial Neural Networks (DANN), Deep Subdomain-Adaptation Networks (DSAN), and Deep CORAL—were evaluated for their ability to enhance cross-domain generalization. Experimental results show that while DANN was unstable, DSAN and Deep CORAL improved target domain accuracy. Deep CORAL achieved 99% accuracy on the source and 94% on the target, offering balanced performance. DSAN reached 95% on the target but reduced source accuracy. Overall, statistical alignment methods outperformed adversarial approaches in transformer-based spectral adaptation. The proposed model was integrated into a reflectance micro-FTIR workflow, accurately identifying PE and PP microplastics from unlabelled spectra. Predictions closely matched expert-validated results, demonstrating practical applicability. This first use of a domain-adaptive transformer in microplastics spectroscopy sets a benchmark for high-throughput, cross-domain analysis. Future work will extend to more polymers and enhance model efficiency for field use. Full article

Slope stability prediction is a critical task in geotechnical engineering, but machine learning (ML) models require large datasets, which are often costly and time-consuming to obtain. This study proposes a domain-driven teacher–student framework to overcome data limitations for predicting the dry factor of safety (FS dry). The teacher model, XGBoost, was trained on the original dataset to capture nonlinear relationships among key site-specific features (unit weight, cohesion, friction angle) and assign pseudo-labels to synthetic samples generated via domain-driven simulations. Six student models, random forest (RF), decision tree (DT), shallow artificial neural network (SNN), linear regression (LR), support vector regression (SVR), and K-nearest neighbors (KNN), were trained on the augmented dataset to approximate the teacher’s predictions. Models were evaluated using a train–test split and five-fold cross-validation. RF achieved the highest predictive accuracy, with an R² of up to 0.9663 and low error metrics (MAE = 0.0233, RMSE = 0.0531), outperforming other student models. Integrating domain knowledge and synthetic data improved prediction reliability despite limited experimental datasets. The framework provides a robust and interpretable tool for slope stability assessment, supporting infrastructure safety in regions with sparse geotechnical data. Future work will expand the dataset with additional field and laboratory tests to further improve model performance. Full article

Continuous Test-Time Adaptation aims to adapt a source model to continuously and dynamically changing target domains. However, previous studies focus on adapting to each target domain independently, treating them as isolated, while ignoring the interplay of interference and promotion between domains, which limits the model’s sustained capability, often causing it to become trapped in local optima. This study highlights this critical issue and identifies two key factors that limit the model’s sustained capability: (1) The update of parameters lacks constraints, where domain-sensitive parameters capture domain-specific knowledge, leading to unstable channel representations and interference from old domain knowledge and hindering the learning of domain-invariant knowledge. (2) The decision boundary lacks constraints, and distribution shifts, which carry significant domain-specific knowledge, cause features to become dispersed and prone to clustering near the decision boundary. This is particularly problematic during the early stages of domain shifts, where features are more likely to cross the boundary. To tackle the two challenges, we propose a Dual Constraints method: First, we constrain updates to domain-sensitive parameters by minimizing the representation changes in domain-sensitive channels, alleviating the interference among domain-specific knowledge and promoting the learning of domain-invariant knowledge. Second, we introduce a constrained virtual decision boundary, which forces features to move away from the original boundary, and with a virtual margin to prevent features from crossing the decision boundary due to domain-specific knowledge interference caused by domain shifts. Extensive benchmark experiments show our framework outperforms competing methods. Full article

The Automatic Checkout (ACO) task aims to accurately generate complete shopping lists from checkout images. Severe product occlusions, numerous categories, and cluttered layouts impose high demands on detection models’ robustness and generalization. To address these challenges, we propose the Edge-Embedded Multi-Feature Fusion Network (E2MF2Net), which jointly optimizes synthetic image generation and feature modeling. We introduce the Hierarchical Mask-Guided Composition (HMGC) strategy to select natural product poses based on mask compactness, incorporating geometric priors and occlusion tolerance to produce photorealistic, structurally coherent synthetic images. Mask-structure supervision further enhances boundary and spatial awareness. Architecturally, the Edge-Embedded Enhancement Module (E3) embeds salient structural cues to explicitly capture boundary details and facilitate cross-layer edge propagation, while the Multi-Feature Fusion Module (MFF) integrates multi-scale semantic cues, improving feature discriminability. Experiments on the RPC dataset demonstrate that E2MF2Net outperforms state-of-the-art methods, achieving checkout accuracy (cAcc) of 98.52%, 97.95%, 96.52%, and 97.62% on Easy, Medium, Hard, and Average mode, respectively. Notably, it improves by 3.63 percentage points in the heavily occluded Hard mode and exhibits strong robustness and adaptability in incremental learning and domain generalization scenarios. Full article

Colorectal cancer (CRC) remains a leading global health challenge, with early and accurate diagnosis crucial for effective treatment. Histopathological evaluation, the current diagnostic gold standard, faces limitations including subjectivity, delayed results, and reliance on well-prepared tissue slides. Mass spectrometry imaging (MSI) offers a complementary approach by providing molecular-level information, but its high dimensionality and the scarcity of labeled data present unique challenges for traditional supervised learning. In this study, we present the first implementation of foundation models for MSI-based cancer classification using desorption electrospray ionization (DESI) data. We evaluate multiple architectures adapted from other domains, including a spectral classification model known as FACT, which leverages audio–language pretraining. Compared to conventional machine learning approaches, these foundation models achieved superior performance, with FACT achieving the highest cross-validated balanced accuracy ($93.27\%\pm 3.25\%$) and AUROC ($98.4\%\pm 0.7\%$). Ablation studies demonstrate that these models retain strong performance even under reduced data conditions, highlighting their potential for generalizable and scalable MSI-based cancer diagnostics. Future work will explore the integration of spatial and multi-modal data to enhance clinical utility. Full article

Under harsh sea states, the dynamic characteristics of ocean mesoscale eddies (OMEs) become significantly more complex, posing substantial challenges to their accurate detection and identification. In this study, we propose an artificial intelligence detection method for OMEs based on the domain adaptation technique to accurately perform pixel-level segmentation and ensure its effectiveness under harsh sea states. The proposed model (LCNN) utilizes large kernel convolution to increase the model’s receptive field and deeply extract eddy features. To deal with the pronounced cross-domain distribution shifts induced by harsh sea states, an adversarial learning framework (ADF) is introduced into LCNN to enforce feature alignment between the source (normal sea states) and target (harsh sea states) domains, which can also significantly improve the segmentation performance in our constructed dataset. The proposed model achieves an accuracy, precision, and Mean Intersection over Union of 1.5%, 6.0%, and 7.2%, respectively, outperforming the existing state-of-the-art technologies. Full article

Background/Objectives: Developing high-performance artificial intelligence (AI) models for rare diseases like malignant bone tumors is limited by scarce annotated data. This study evaluates same-modality cross-domain transfer learning by comparing an AI model pretrained on chest radiographs with a model trained from scratch for detecting malignant bone tumors on knee radiographs. Methods: Two YOLOv5-based detectors differed only in initialization (transfer vs. scratch). Both were trained/validated on institutional data and tested on an independent external set of 743 radiographs (268 malignant, 475 normal). The primary outcome was AUC; prespecified operating points were high-sensitivity (≥0.90), high-specificity (≥0.90), and Youden-optimal. Secondary analyses included PR/F1, calibration (Brier, slope), and decision curve analysis (DCA). Results: AUC was similar (YOLO-TL 0.954 [95% CI 0.937–0.970] vs. YOLO-SC 0.961 [0.948–0.973]; DeLong p = 0.53). At the high-sensitivity point (both sensitivity = 0.903), YOLO-TL achieved higher specificity (0.903 vs. 0.867; McNemar p = 0.037) and PPV (0.840 vs. 0.793; bootstrap p = 0.030), reducing ~17 false positives among 475 negatives. At the high-specificity point (~0.902–0.903 for both), YOLO-TL showed higher sensitivity (0.798 vs. 0.764; p = 0.0077). At the Youden-optimal point, sensitivity favored YOLO-TL (0.914 vs. 0.892; p = 0.041) with a non-significant specificity difference. Conclusions: Transfer learning may not improve overall AUC but can enhance practical performance at clinically crucial thresholds. By maintaining high detection rates while reducing false positives, the transfer learning model offers superior clinical utility. Same-modality cross-domain transfer learning is an efficient strategy for developing robust AI systems for rare diseases, supporting tools more readily acceptable in real-world screening workflows. Full article