Search Results (1,828)

Grid-based 3D object detection methods effectively leverage mature point cloud processing techniques and convolutional neural networks for feature extraction and object localization. However, unlike the 2D object detection domain, the unique characteristics of point cloud data being unevenly and sparsely distributed in space necessitate that detection networks possess a certain level of spatial structural perception. Learning spatial information such as point cloud density and distribution patterns can significantly benefit 3D detection networks. This paper proposes a Spatial-aware Network for 3D object detection (SpaA). Based on the 3D sparse convolution network, we designed a Variable Sparse Convolution network (VS-Conv) capable of perceiving the importance of locations. To address the issue of set abstraction operations completely ignoring spatial structure during local feature aggregation, we proposed a Spatial-aware Density-based Local Aggregation (SDLA) method. Experiments demonstrate that enhancing the spatial-awareness capability of detection networks is crucial for complex 3D object detection. Detection results on the KITTI dataset validate the effectiveness of our method. The test set results of SpaA achieved 3D AP values of 82.20%, 44.04%, and 70.34% for the Car, Pedestrian, and Cyclist categories, respectively, and a competitive 3D mAP of 67.23%, outperforming several published methods. Full article

Granular modeling has emerged as an interpretable framework for nonlinear system representation by constructing clusters of meaningful data units within the input and output domains. Unlike conventional neuro-fuzzy models that yield crisp outputs, granular models generate fuzzy-set-based outputs, preserving uncertainty information. However, traditional granular architectures rely on linear aggregation mechanisms, limiting their expressive power and structural adaptability. This paper proposes a novel framework termed Logic-Based Fuzzy Granular Networks (LFGNs), in which conventional granular models are enhanced through the incorporation of fuzzy logical neurons implementing AND–OR operations. The proposed logic-based structure enables nonlinear interactions among induced granules while maintaining interpretability. To further improve predictive performance, LFGNs are embedded into a boosting framework, forming a boosted LFGN in which each LFGN acts as a weak learner. Extensive simulation studies on benchmark datasets indicate that the proposed approach outperforms conventional granular models and the existing boosting method in terms of regression accuracy. The integration of logical neurons, boosting, and fuzzy granular models provides a unified and robust granular modeling framework. Full article

Background/Objectives: Tablet development requires simultaneous optimization of multiple quality attributes under limited experimental budgets, yet formulation–property relationships are highly nonlinear in mixture systems. To support pre-formulation decision-making prior to extensive tablet prototyping, this study proposes an AI framework that organizes formulation and process data together with raw-material property records into a reusable database, and enriches conventional composition/process features with physically motivated mixture descriptors derived from raw-material properties and formulation/process settings. Methods: Mixture-level scalar descriptors are constructed by composition-weighted aggregation of material properties, and particle size distribution (PSD) is incorporated via a compact set of summary statistics computed from composition-weighted mixture PSDs. Three feature sets are compared: (i) Materials + Processes (MP), (ii) MP with scalar Descriptors (MPD), and (iii) MPD with PSD summaries (MPDD). Five target properties are modeled: hardness, disintegration time, flow function, cohesion, and thickness. We train and evaluate Random Forest, Extra Trees Regressor, Lasso, Partial Least Squares, Support Vector Regression, and a multi-branch neural network that processes the three feature blocks separately and concatenates them for prediction. For interpolation assessment, repeated Train/Dev/Test splitting (5:3:2) across multiple random seeds is used, and the effect of feature augmentation is quantified by paired RMSE improvements with bootstrap confidence intervals and paired Wilcoxon signed-rank tests. To assess robustness under practical formulation updates, rolling-origin time-series splits are employed and Applicability Domain indicators are computed to characterize out-of-distribution coverage. Results: Across interpolation evaluations, mixture-descriptor augmentation (MPD/MPDD) improves hardness and disintegration time in most settings, whereas gains for flow function are smaller and cohesion/thickness show mixed effects under limited sample sizes. Conclusions: Under extrapolation-oriented evaluation, the descriptors can improve hardness but may degrade disintegration-time prediction under covariate shift, emphasizing the need for careful descriptor selection and dimensionality control when deploying pre-formulation predictors. Full article

As a key task in remote sensing analysis, semantic segmentation of remote sensing images (RSI) underpins many practical applications. Despite its importance, obtaining dense pixel-wise annotations remains labor-intensive and time-consuming. Unsupervised domain adaptation (UDA) offers a promising solution by utilizing knowledge from labeled source domains for unlabeled target domains, yet its effectiveness is often compromised by significant distribution shifts arising from variations in imaging conditions. To address this challenge, we propose a depth-aware adaptation network (DAAN), a novel two-branch network that explicitly leverages complementary depth information from a digital surface model (DSM) to enhance cross-domain remote sensing segmentation. Unlike conventional UDA methods that primarily focus on semantic features, DAAN incorporates depth data to build a more generalized feature space. This network introduces three key components: an adaptive feature aggregator (AFA) for progressive semantic-depth feature fusion, a gated prediction selection unit (GPSU) that selectively integrates predictions to mitigate the impact of noisy depth measurements, and misalignment-focused residual refinement (MFRR) module that emphasizes poorly aligned target regions during training. Experiments on the ISPRS and GAMUS datasets demonstrate the effectiveness of the proposed method. In particular, DAAN achieves an mIoU of 50.53% and an F1 score of 65.75% for cross-domain segmentation on ISPRS to GAMUS, outperforming models without depth information by 9.17% and 8.99%, respectively. These results demonstrate the advantage of integrating auxiliary geometric information to improve model generalization on unlabeled remote sensing datasets, contributing to higher mapping accuracy, more reliable automated analysis, and enhanced decision-making support. Full article

We investigate wheat lodging segmentation from UAV RGB imagery acquired over real production fields rather than controlled experimental sites. Besides pixel-level accuracy, our evaluation also emphasizes robustness under heterogeneous farmland conditions and deployment-oriented efficiency. We propose CASGNet, an edge-oriented segmentation network with a content-aware spatial gating mechanism that reweights intermediate features according to local structural variation. Instead of uniformly aggregating features, the module suppresses responses in homogeneous regions while preserving activation in structurally complex areas. In practice, this improves the continuity of irregular lodging shapes and reduces spurious responses in relatively homogeneous backgrounds. The dataset spans 46 farms across Jiaozuo, Jiyuan, and Luoyang, covering progressively fragmented farmland. Under a stricter mission-level data-isolation protocol, CASGNet achieves 94.4% mIoU and 90.38% IoU for the lodging class on the combined dataset. Under sequential regional adaptation, performance remains relatively stable in continuous parcels, and degradation is less severe than most compact baselines in highly fragmented landscapes. On Jetson Nano, CASGNet achieves 1.94 FPS embedded inference under the 5 W mode. Smaller networks achieve higher speed but show reduced structural continuity in complex scenes. The results indicate that CASGNet provides a favorable balance between structural fidelity and computational cost, while its robustness remains constrained by scene complexity. Full article

The increasing deployment of Internet of Things (IoT) devices introduces significant security challenges, while privacy concerns limit centralized data aggregation for intrusion detection. Federated learning (FL) offers a decentralized alternative, yet the interaction between feature representation, model architecture, and data heterogeneity remains insufficiently understood in IoT malware detection. This study provides a controlled comparative analysis of centralized and federated learning, optionally using amino acid encoding, under IID and Non-IID conditions using a 10,000-sample subset of the CTU–IoT–Malware–Capture dataset. First, we evaluate raw tabular features versus amino acid-based feature encoding, followed by a lightweight multi-layer perceptron (2882 parameters) versus a deeper residual network (70,532 parameters), across binary and multi-class classification tasks. In the binary setting, centralized training achieved up to 98.6% accuracy, while federated IID training reached 98.6%, with differences within statistical variance. Under Non-IID conditions, performance decreased modestly (0.1–0.5 percentage points), and accuracy was consistently lower when using encoded features compared with raw features. The degradation is smaller in deeper architectures and may offer improved stability under highly skewed federated conditions. In the four-class setting, the complex network achieved up to 97.8% accuracy with raw features, while amino acid encoding achieves up to 93.3%. The results show that federated learning can achieve performance comparable to centralized training under moderate heterogeneity, that lightweight architectures are sufficient for low-dimensional IoT traffic features, and that feature compression via amino acid encoding does not inherently mitigate Non-IID effects. These findings clarify the relative impact of representation, heterogeneity, and architectural capacity in practical FL-based IoT intrusion detection systems. Full article

Vehicular ad hoc networks (VANETs) operating in dense urban environments are characterized by highly dynamic topology, fluctuating traffic conditions, and stringent latency requirements, which significantly complicate reliable data routing and packet forwarding. To address these challenges, this paper proposes an Intelligent Fuzzy Protocol (IFP) for adaptive vehicle-to-vehicle data routing under uncertain and rapidly changing traffic scenarios. The proposed protocol integrates fuzzy logic decision making with the real-time vehicular context, including vehicle velocity, traffic congestion level, distance to road junctions, and data urgency, to dynamically select appropriate forwarding actions. IFP employs a structured fuzzy inference engine comprising fuzzification, rule evaluation, inference aggregation, and centroid-based defuzzification to determine routing and forwarding decisions in a decentralized manner. To further enhance performance robustness, the fuzzy membership parameters and rule weights are optimized using metaheuristic techniques, namely, genetic algorithms (GAs) and particle swarm optimization (PSO). Extensive simulations are conducted using NS-3 coupled with SUMO under realistic urban mobility scenarios and varying network densities. The simulation results demonstrate that IFP significantly outperforms conventional routing approaches in terms of end-to-end delay, packet delivery ratio, and routing overhead. In particular, the optimized IFP variants achieve notable reductions in latency and improvements in delivery reliability under high-congestion conditions, while maintaining low computational and communication overhead. These findings confirm that IFP offers an interpretable, scalable, and energy-aware routing solution suitable for large-scale intelligent transportation systems and next-generation vehicular networks. Full article

Wi-Fi networks used in smart grids are essential for enabling communication between smart meters and data aggregation units. A key challenge, however, is the ability to hide the existence and traffic patterns of these communications, so that sensitive information exchanges cannot be easily detected or intercepted. Unfortunately, most existing solutions do not provide support for traffic prioritization and steganographic channel encryption. In this paper, we propose a novel covert channel with Quality of Service (QoS) and encryption support for smart grid environments based on the IEEE 802.11 standard. We introduce an original steganographic approach that leverages the backoff mechanism, the Enhanced Distributed Channel Access (EDCA) function, frame aggregation, and the StegoPaddingCipher algorithm. This design ensures QoS-aware traffic handling while enhancing security through encryption of the transmitted covert data. The proposed protocol was implemented and evaluated using the ns-3 simulator, where it achieved excellent performance results. The system maintained high efficiency even under heavily saturated network conditions with additional background traffic generated by other nodes. The proposed covert channel offers an innovative and secure method for transmitting substantial volumes of QoS-related data within smart grid environments. Full article

Federated learning (FL) enables collaborative model training across distributed devices and robotic systems while preserving data privacy, making it well-suited for swarm robotics and edge-device-powered intelligence. However, FL remains vulnerable to adversarial behaviors such as data and model poisoning, particularly in real-world deployments where detection methods must operate under strict computational and communication constraints. This paper presents a practical, real-world federated learning framework that enhances robustness to adversarial agents in a ROS2-based edge-device swarm environment. The proposed system integrates the Federated Averaging (FedAvg) algorithm with a lightweight average cosine similarity-based filtering method to detect and suppress harmful model updates during aggregation. Unlike prior work that primarily evaluates poisoning defenses in simulated environments, this framework is implemented and evaluated on physical hardware, consisting of a laptop-based aggregator and multiple Raspberry Pi worker nodes. A convolutional neural network (CNN) based on the MobileNetV3-Small architecture is trained on the MNIST dataset, with one worker executing a sign-flipping model poisoning attack. Experimental results show that FedAvg alone fails to maintain meaningful model accuracy under adversarial conditions, resulting in near-random classification performance with a final global model accuracy of 11% and a loss of 2.3. In contrast, the integration of cosine similarity filtering demonstrates effective detection of sign-flipping model poisoning in the evaluated ROS2 swarm experiment, allowing the global model to maintain model accuracy of around 90% and loss around 0.37, which is close to baseline accuracy of 93% of the FedAvg algorithm only under no attack with a very minimal increase in loss, despite the presence of an attacker. The proposed method also maintains a false positive rate (FPR) of around 0.01 and a false negative rate (FNR) of around 0.10 of the global model in the presence of an attacker, which is a minimal difference from the baseline FedAvg-only results of around 0.008 for FPR and 0.07 for FNR. Additionally, the proposed method of FedAvg + cosine similarity filtering maintains computational statistics similar to baseline FedAvg with no attacker. Baseline results show an average runtime of about 34 min, while our proposed method shows an average runtime of about 35 min. Also, the average size of the global model being shared among workers remains consistent at around 7.15 megabytes, showing little to no increase in message payload sizes between baseline results and our proposed method. These results demonstrate that computationally lightweight cosine similarity-based detection methods can be effectively deployed in real-world, resource-constrained robotic swarm environments, providing a practical path toward improving robustness in real-world federated learning deployments beyond simulation-based evaluation. Full article

To address the challenges posed by the strong uncertainty of high-proportion renewable energy sources (RES) to the secure and stable operation of distributed real-time power dispatch (D-RTPD) in new-type power systems, this paper proposes an integrated solution combining a neighborhood feature aggregation-based graph attention network (NFA-GAT) and multi-agent deep deterministic policy gradient (MADDPG). First, the D-RTPD problem is modeled as a decentralized partially observable Markov decision process (Dec-POMDP), which effectively captures the stochastic game characteristics of multi-regional agents and the partial observability of grid states. Second, the NFA-GAT is designed to enhance agents’ perception of grid operating states: by introducing a spatial discount factor, it realizes rational aggregation of multi-order neighborhood information while modeling the attenuation of electrical quantity influence with topological distance. Third, a prior-guided mechanism is integrated into the MADDPG framework to eliminate constraint-violating actions by setting their actor logits to negative infinity, improving training efficiency and strategy reliability. Simulation validations on the IEEE 118-bus test system (75.2% RES installed capacity ratio) show that the proposed method achieves efficient training convergence. Compared with the multi-layer perceptron (MLP) structure, it attains higher cumulative reward values and scenario win rates. When compared with traditional model-driven (ADMM) and data-driven (Q-MIX) methods, the proposed method balances solution efficiency, operational safety (98.7% maximum line load rate, zero power flow violation rate), and economic performance ($12,845 daily dispatch cost), providing a reliable technical support for D-RTPD under high-proportion RES integration. Full article

Wireless medical sensor networks (WMSNs) enable continuous patient monitoring by transmitting sensitive physiological data over open wireless links. Given the resource-constrained nature and large-scale deployment of such networks, authentication mechanisms must be both lightweight and privacy-preserving. Moreover, due to the frequent turnover of patients and devices in hospital environments, timely member revocation is crucial to prevent discharged or compromised entities from injecting forged reports that could mislead medical diagnosis. Although existing pairing-free certificateless aggregate authentication schemes are efficient, they often suffer from critical security and privacy vulnerabilities. Recently, an efficient certificateless authentication scheme with revocation has been proposed. However, our analysis reveals that the scheme presents the following security vulnerabilities: (i) member witnesses can be recovered from public information, (ii) revocation checks can be bypassed via identity grafting attack, and (iii) user identities can be linked due to the long-term use of static pseudonyms. To address these issues, we propose a security-enhanced certificateless aggregate authentication protocol with revocation for WMSNs. Our design enforces strong identity–membership binding to resist grafting attacks, employs a non-interactive zero-knowledge membership proof to preserve witness secrecy, and adopts dynamic pseudonym rotation to achieve unlinkability. We provide formal security proofs and comprehensive performance comparisons. The results indicate that, at the same security level, our protocol achieves more efficient signature verification while maintaining communication overhead comparable to existing schemes. In addition, the overhead introduced by our revocation mechanism remains constant, making it well suited for large-scale WMSNs deployments with frequent membership changes. Full article

Electrical imaging logging images play a crucial role in petroleum exploration; however, in practical applications, blank strips frequently appear due to instrument malfunctions or data transmission failures, severely compromising geological interpretation and hydrocarbon evaluation. Existing image inpainting methods have limited adaptability to blank strips at different depth scales and exhibit blurred high-resolution geological textures. To address these issues, this paper proposes a blank strip filling method that integrates Arbitrary Kernel Convolution (AKConv) with the Aggregated Contextual-Transformations Generative Adversarial Network (AOT-GAN). Specifically, the adaptive sampling mechanism of AKConv is incorporated into the generator network of AOT-GAN, enabling the model—to effectively capture long-range contextual information and adaptively handle blank strips of varying scales and shapes through multi-scale feature fusion. Experimental results on real oilfield datasets demonstrate that the proposed method achieves significant improvements in PSNR, SSIM, and MAE, exhibiting superior structural preservation and texture sharpness—especially in restoring deep and large-scale blank strips. Furthermore, visual comparisons confirm the method’s superior performance in recovering key geological features, such as bedding continuity and fracture structures, thus providing an effective approach for electrical imaging logging image restoration. Full article

Despite recent advances in artificial intelligence for agriculture, reliable crop recommendation remains constrained by limited access to soil diagnostics, insufficient integration of environmental context, and the absence of transparent, quantitative evaluation frameworks. This study addresses the research question: How can we integrate multiple indicators to generate accurate, explainable, and context-sensitive crop recommendations? To this end, we propose a multimodal decision-support framework that combines image-based soil texture classification with geospatial, and climatic information. A convolutional neural network was trained on a curated dataset of 3250 soil images aggregated from four publicly available sources, covering four primary soil texture classes, alongside tabular soil and nutrient data. The model was evaluated using 5-fold stratified cross-validation, achieving an average classification accuracy of 99.30% (standard deviation ≈ 0.66), and was further validated on an independent hold-out test set to assess generalization performance. To enhance practical applicability, the framework incorporates elevation, rainfall, temperature, and major soil nutrients, and employs a large language model to generate user-oriented, interpretable justifications for each recommendation. Crop recommendations were quantitatively evaluated using a novel Agronomic Suitability Score (ASS), which measures alignment across soil compatibility, climatic suitability, seasonal alignment, and elevation tolerance. Across six geographically diverse case studies, the framework achieved mean ASS values ranging from 3.76 to 4.96, with five regions exceeding 4.45, demonstrating strong agronomic validity, robustness, and scalability. A Streamlit-based application further illustrates the system’s ability to deliver accessible, location-aware, and explainable agronomic guidance. The results indicate that the proposed approach constitutes a scalable decision-support tool with significant potential for sustainable agriculture and food security initiatives. Full article

The detection of surface defects on smartphone components is a critical step in quality assurance for industrial manufacturing. However, existing deep learning-based methods struggle with the extreme variations in defect morphology and scale, while labeled training data remains scarce due to the high cost of expert annotation. To address these challenges, we propose a twofold solution. First, we introduce MSAdaNet, a Multi-Scale Adaptive Defect Detection Network, which integrates three novel modules: a Parallel Multi-Scale Feature Aggregation (PMSFA) backbone, a Focusing Diffusion Pyramid Network (FDPN) neck, and a Scale-Adaptive Shared Detection (SASD) head. Second, to combat data scarcity, we propose a novel data generation pipeline, creating the synthetic Smartphone Camera Bezel Dataset (SCBD) of 4936 images. Extensive experiments on both real-world and synthetic datasets validate our approach. On the challenging public SSGD, MSAdaNet achieves a state-of-the-art mAP@0.5 of 54.8%, outperforming prominent frameworks and improving upon the strong YOLOv11m baseline by +10.6 points in mAP@0.5 and +18.3 points in recall. Furthermore, on our synthetic SCBD, the model achieves an impressive 94.0% mAP@0.5, confirming the quality of our data generation pipeline and the robustness of our architecture across different data distributions. Ablation studies systematically confirm the significant contribution of each proposed module, validating MSAdaNet as an effective and efficient solution for industrial defect detection. Full article

Unmanned Aerial Vehicle (UAV) swarms operating in contested environments face a critical “semantic gap” between raw, high-velocity network traffic and high-level mission security constraints, compounded by the risk of privacy leakage during collaborative learning. Existing deep learning (DL)-based Network Intrusion Detection Systems (NIDSs) suffer from opacity, prohibitive resource consumption, and vulnerability to gradient leakage attacks in federated settings, while traditional rule-based systems fail to handle encrypted payloads and evolving attack patterns. To bridge this gap, we present NeSySwarm-IDS (Neuro-Symbolic Swarm Intrusion Detection System), an end-to-end differentiable neuro-symbolic framework that simultaneously achieves high accuracy, strong privacy guarantees, and built-in interpretability under resource constraints. NeSySwarm-IDS integrates an extremely lightweight 1D convolutional neural network with a differentiable Łukasiewicz fuzzy logic reasoner incorporating attack-specific rules. By aggregating only low-dimensional logic rule weights with calibrated differential privacy noise, we drastically reduce communication overhead while providing $(ϵ,\delta )$-DP guarantees with negligible utility loss. Extensive experiments on the UAV-NIDD dataset and our self-collected dataset demonstrate that NeSySwarm-IDS achieves near-perfect detection accuracy, significantly outperforming traditional machine learning baselines despite using limited training data. A detailed case study on GPS spoofing confirms the interpretability of our approach, providing axiomatic explanations suitable for autonomous mission verification. These results establish that end-to-end neuro-symbolic learning can effectively bridge the semantic gap in UAV swarm security while ensuring privacy and interpretability, offering a practical pathway for deploying trustworthy AI in contested environments. Full article