Search Results (7,924)

Synthetic aperture radar (SAR) ship detection faces three persistent challenges: coherent speckle noise that obscures target boundaries, heterogeneous background clutter in coastal and harbor scenes, and ship targets whose spatial extent varies by more than an order of magnitude within the same image. To address these issues jointly, this paper proposes MSA-DET, an improved SAR ship detection network built upon YOLOv11. In the backbone, a Multi-Scale Cross-axis Attention module (MSCAttention) runs horizontal and vertical axial attention branches in parallel across multiple receptive-field scales, sharpening feature representations for ship targets that vary widely in size and orientation. In the neck, the standard C3k2 block is redesigned as C3k2_SSA by embedding sparse self-attention, which selectively focuses on the most discriminative spatial tokens while suppressing speckle interference and reducing computational overhead. An Adaptive Spatial Feature Fusion detection head (ASFF) replaces fixed pyramid-level aggregation with learned per-pixel blending weights, resolving gradient conflicts across scales and improving localization consistency for both small and large ships. On the HRSID dataset, MSA-DET achieves an mAP@0.5:0.95 of 63.6% and mAP@0.5 of 88.1%, representing gains of 4.0% and 1.6% over the YOLOv11n baseline; on SSDD, it reaches 69.6% and 97.7%, surpassing the baseline by 7.2% and 2.1%, respectively. These results demonstrate that coordinated multi-stage redesign—rather than isolated module substitution—is an effective strategy for SAR-oriented ship detection. The accuracy gains are accompanied by a moderate increase in model size (8.9 M parameters versus 2.6 M for YOLOv11n) and computational cost (9.6 G FLOPs versus 6.3 G), a trade-off that is justified by the substantial improvement in detection quality. Full article

Person re-identification (re-ID) aims to match pedestrian images across disjoint camera views. Existing multi-source unsupervised domain adaptation (UDA) re-ID methods still face two critical issues: they fail to effectively balance domain-invariant feature learning and domain-specific style preservation and cannot adequately model the implicit correlations among diverse source domains, resulting in limited cross-domain generalization performance. To address these challenges, this paper proposes a novel multi-source UDA re-ID framework equipped with a Mixture of Experts feature extraction (MEFE) network and a Graph-Based Relation (GBR) module. Specifically, the MEFE network integrates mixed Instance and Batch Normalization (MIBN) to extract robust domain-invariant features, while the embedded domain-specific style information (DSI) module compensates for lost domain-specific style details at the feature level. Furthermore, the cascaded Graph Attention and Graph Convolution Networks (GATs/GCNs) in the GBR module adaptively explore implicit feature correlations and achieve effective multi-source feature fusion. Center maximum mean discrepancy loss is adopted to further reduce cross-domain distribution discrepancies. Extensive experiments on large-scale datasets demonstrate that the proposed method achieves state-of-the-art performance and substantially outperforms mainstream UDA re-ID approaches. Full article

African soils face increasing levels of metal pollution due to industrialization, artisanal mining activities, improper waste management, and enhanced agricultural productivity. However, unlike many organic pollutants, heavy metals do not degrade naturally and therefore persist in environmental systems for prolonged periods. Heavy metals accumulate over many decades in the soil and bioaccumulate through the food chain causing severe health complications such as cancer, kidney problems, and neurological impairment. This paper reviews the current literature on the origin, prevalence, and behavior of the main pollutants Pb, Cd, Cr, As, Hg, and Cu. The major phytoremediation methods including phytoextraction, rhizofiltration, phytostabilization, and phytovolatilization are highlighted alongside in planta screening methods for hyperaccumulating plants including Berkheya coddii (Ni) and Haumaniastrum robertii (Co). The paper evaluates various enhancement techniques such as the use of chelators, Rhizobium inoculations, and genetic modifications. The significance of these approaches in tropical and subtropical climates is discussed. The paper suggests a holistic framework involving empirical kinetic modeling, geospatial machine learning (random forest, kriging), and molecular omics in prediction modeling. Major hurdles in such predictions include lack of field-based verification of the models, biotechnology safety of genetically modified (GM) organisms, and inadequate regulations. Future perspectives emphasize community-driven phytomining, biomass recycling, and resilient phytoremediation solutions. Full article

Visual impairment affects approximately 2.2 billion people worldwide, yet existing assistive technologies remain fragmented and prohibitively expensive. This paper presents Munir, an integrated multimodal assistive system designed to enhance human–computer interaction through a combination of a mobile application and Bluetooth-enabled smart glasses. Munir leverages a hybrid machine learning architecture to provide inclusive, real-time support for daily living activities. The system integrates ten core capabilities—including face recognition, optical character recognition, and scene description—all accessible through a unified bilingual (Arabic/English) voice interface. By employing on-device processing for biometric tasks, Munir ensures user privacy and trust while maintaining high responsiveness. End-to-end system evaluation on the SCface dataset achieves a 96.69% recognition rate with 0% False Accept Rate. At an estimated first-year total cost of $806, Munir demonstrates a 4–5× cost advantage over commercial alternatives, providing a scalable and affordable multimodal solution for global digital inclusion. Full article

Drainage pipe defect detection is essential for maintaining the normal operation of urban infrastructure. In recent years, deep learning-based object detection methods have provided an effective technical solution for drainage pipe defect recognition. Among them, YOLO-series models have demonstrated strong potential in visual detection tasks due to their end-to-end architecture and high inference efficiency. However, directly applying baseline YOLO models may still face challenges such as limited detection accuracy, relatively high model complexity, and insufficient adaptability for lightweight deployment scenarios. To address these issues, this paper proposes a lightweight drainage pipe defect detection method based on an improved YOLO11 network. Rather than treating detection enhancement and model compression as two separate procedures, the proposed method integrates feature enhancement, adaptive pruning, and distillation-based recovery into a unified lightweight detection framework. Specifically, an improved SimAM attention mechanism is introduced into the backbone and integrated with the C3k2 module to construct the C3K2_SWS module, aiming to enhance the representation capability of critical defect features. In the neck network, a focused diffusion pyramid network with a dimension-aware selective fusion structure, termed FDPN-DASI, is designed to strengthen multi-scale feature interactions. In addition, an adaptive-threshold focal loss (ATFL) is introduced to improve the learning capability for hard samples. For efficient deployment, the LAMP pruning algorithm is further improved, and an entropy-guided entropy-adaptive magnitude-based pruning method (EA-LAMP) is proposed to enable adaptive allocation of pruning ratios across different network layers. Moreover, BCKD knowledge distillation is applied after pruning to mitigate the accuracy degradation caused by model compression. Experimental results indicate that the proposed lightweight YOLO11-SFA+EA+BCKD framework achieves a precision of 92.4%, a recall of 88.5%, and an mAP50 of 93.3%, while maintaining a compact model size of 1.6 M parameters and 4.5 G FLOPs. Compared with the baseline model, the proposed method improves precision, recall, and mAP50 by 5.9%, 5.0%, and 4.7%, respectively, while reducing the number of parameters, FLOPs, and model size by 1.0 M, 1.8 G, and 2.1 M, respectively. These results suggest that the proposed framework can improve detection performance while reducing model complexity under the current experimental setting, indicating its potential for lightweight drainage pipe defect detection tasks. Full article

Identity verification across pre-operative and post-operative facial images remains a challenging task, particularly following eyelid surgery, where localized periocular changes can disrupt conventional face recognition systems. This research introduces a novel verification framework using an ensemble-based autoencoder-initialized Siamese eye-region periocular verification network designed to remain resilient to surgically induced appearance variation. The proposed approach integrates anatomy-guided periocular normalization with a Siamese deep metric learning architecture, initialized via unsupervised autoencoder pretraining, enabling the model to acquire periocular-specific representations before supervised learning. Robustness in this data-limited clinical setting is enhanced through a combination of constrained periocular augmentation, dropout-based regularization, L2 weight decay, validation-guided checkpoint selection, staged hard-negative mining, validation-weighted multi-seed ensemble learning, and bootstrap-based threshold calibration. Experimental evaluation demonstrates recognition rates of 96.08% on the test set. These results indicate that the proposed framework maintains discriminative periocular identity representations under post-surgical appearance variation while remaining robust in a limited-data clinical setting. Full article

We developed a laboratory-based setup to perform behavioral tests of the effect of the neonicotinoid insecticide Thiacloprid in the CALYPSO^® formulation on bumblebees. This setup simulates essential components of navigation and pollination under natural conditions. The behavioral components are exploration, exploratory learning, learning of a rewarded local cue in the context of a specific panorama, and retrieving the memory for this association. The walking bumblebees navigated under their own motivation between a fully functional colony and a training/test arena. They explored the arena and learned the association of a rewarded local cue in the context of a panorama. The rule of association was that the local cue was bound to a particular part of the panorama irrespective of where it appeared in its spatial relation to the entrance gate through which the animal came from the colony. Extinction tests were performed for two conditions, match and mismatch. The match condition resembled the training condition. In the mismatch condition the local cue appeared in a different part of the panorama. Solving this task requires the learning and remembering of a rule under variable conditions, mimicking the cognitive requirements faced by bumblebees under natural conditions. The control animals solved this task, whereas animals treated with Thiacloprid 400 ng CALYPSO^® diluted in 4 µL per animal were significantly compromised, as shown by several parameters of the walking trajectories under the match and mismatch conditions. No dose–response functions were established, but a volume of 800 ng CALYPSO^® diluted in 8 µL per animal did not show any significant differences from a volume of 4 µL CALYPSO^®. The setup and the experimental paradigm are suitable for routine quantitative tests on the effects of insecticides on the cognitive faculties of insects during navigation and pollination. Full article

Accurate solar irradiance forecasting is important for efficient planning of solar energy systems, renewable energy integration, and data-driven energy management in smart cities. This becomes more essential in regions with limited measured data availability and varying climatic conditions, where reliable forecasting can support urban energy planning and smart grid operation. Pakistan faces a scarcity of available solar data and has varying climatic conditions, which makes it ideal for such a study. This study utilizes nine geographically diverse stations to develop a benchmark framework for direct one-step-ahead hourly solar irradiance forecasting. The dataset was subjected to data preprocessing, feature engineering, and multi-model evaluation. A staged approach was adopted for feature selection, starting from a base model comprising three input variables: extraterrestrial radiation, solar zenith angle, and relative humidity. Features were added in an incremental order, which resulted in an optimized four-variable input set through the addition of a lagged clearness index to the base model. The forecasting models evaluated in this study, using these input variables, were ANN, NAR, NARX, LSTM, GRU, SARIMA, and Prophet. Deep learning models outperformed the other considered approaches, with LSTM showing the best overall benchmark performance with an average RMSE of 92.93 W/m², MAE of 66.56 W/m², and R-Squared of 0.872. The performance trends were broadly consistent across the evaluated stations, indicating stable behaviour within the adopted dataset and experimental setup. The study shows that a compact and physically interpretable input feature set, used with recurrent deep learning models, provides an effective solution for hourly solar irradiance forecasting, especially in locations with varying climatic conditions. The proposed benchmark can support smart city applications related to distributed solar generation, energy-aware urban planning, and intelligent operation of renewable-rich power systems. Full article

The growth of Intelligent Transportation Systems (ITS) has made high-quality perception data from multi-sensor setups essential. Pairing millimeter-wave (mmW) radar with a monocular camera is a common way to recover three-dimensional information about the environment, but aligning the two is difficult because sparse radar point clouds and dense camera images differ sharply in how they sense a scene. The problem grows more severe in roadside infrastructure, where the high mounting elevation introduces perspective distortion that vehicle-mounted systems rarely face. This paper presents a systematic review, conducted under the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, of radar-camera extrinsic calibration for fixed roadside infrastructure, organizing existing work into a taxonomy that separates traditional two-stage pipelines from recent end-to-end learning frameworks. Because methods designed specifically for roadside units remain scarce, the review also covers vehicle- and robot-mounted methods whose static-sensor formulation carries over to fixed roadside deployment. For the two-stage pipeline, the analysis covers target-based and targetless correspondence registration along with the optimization techniques and algorithmic assumptions behind parameter estimation. The end-to-end learning literature shows a clear shift toward self-supervised and fusion-based models, some of which report real-time performance. The review also compares the metrics and procedures used to quantify calibration accuracy. Progress is evident, but robustness in cluttered urban environments remains an open challenge, and the paper closes by outlining future directions, arguing that standardized roadside benchmarks are needed before scalable, targetless calibration can mature. Full article

With the increasing complexity of unmanned aerial vehicle (UAV) missions in complex obstacle environments, cooperative hunting of maneuvering ground targets by UAV swarms has become an important problem for multi-agent autonomous decision-making. This paper focuses on a simulated three-UAV hunting scenario in a two-dimensional obstructed environment, where UAVs must search for, approach, encircle, and continuously track a target while avoiding static obstacles under local observation. To address the problem of multi-UAV cooperative hunting of dynamic targets in complex obstacle environments, this paper proposes a curriculum learning (CL)-based Multi-Agent Proximal Policy Optimization algorithm, termed CL-MAPPO. Specifically, a three-stage progressive training curriculum is designed to overcome the challenges of low exploration efficiency, slow environmental adaptation, and difficult convergence of cooperative hunting policies faced by multi-agent deep reinforcement learning in hunting tasks, thereby gradually enhancing the cooperative hunting capability of UAVs in complex environments. Curriculum I employs fixed obstacles and a stationary target position to train the UAVs’ basic obstacle avoidance and target search abilities. Curriculum II introduces randomly generated obstacles and target positions to improve the UAVs’ adaptability to varying environments. Curriculum III further incorporates a dynamic target, prompting the UAVs to learn effective hunting strategies against maneuvering targets. The simulation experiment includes ablation experiments against MAPPO without curriculum learning and comparative simulations against MADDPG and MADQN, using reward convergence curves and trajectory visualizations to evaluate the training results. The results show that, under the same training episodes in the ablation experiment, CL-MAPPO reaches a higher and more stable reward level than vanilla MAPPO, indicating improved learning efficiency without increasing model complexity. In the comparative experiment, the CL-MAPPO algorithm achieved a higher success rate in cooperative hunting. These simulation experiments verify the effectiveness and superiority of the CL-MAPPO algorithm in multi-agent cooperative hunting tasks. Full article

Combinatorial optimization is a key component in critical decision problems such as routing, scheduling, network design, and graph optimization. Although combinatorial optimization methods, including exact algorithms, approximation methods, constraint programming, mixed integer programming, and metaheuristics, are widely available, they often face obstacles, such as limited scalability and adaptability in various applications. In this study, a systematic critical review of machine learning for combinatorial optimization is provided to characterize the usage and evaluation of learning-based approaches. A detailed analysis is used to infer and determine findings and limitations. The paper emphasizes how machine learning for computational optimization has changed over time, moving from end-to-end neural solvers to hybrid systems. Learning components are essential for directing, speeding up, or enhancing traditional solver backbones such as constraint programming and metaheuristics in hybrid systems. The review also critically examines current limits that impact performance in general, including scalability, deployment readiness, generalization, and benchmark consistency. Even though using large language models for problem formulation and heuristic synthesis has potential, more work needs to be done to ensure reliable validation. As a conclusion, this article examines recent studies’ findings, emphasizes the growing trend toward hybrid learning-driven optimization frameworks, and underlines important methodological limits and unresolved issues. Full article

Existing drug–target interaction (DTI) prediction methods still face challenges caused by sparse interaction data, complex multi-source relationships, and imbalanced information contributions among different nodes. In this study, we propose NAFF-DTI, a node-level adaptive feature fusion network based on multi-view graphs. The model uniformly represents drug similarity, target similarity, and known drug–target interactions as multiple relational views, and learns node representations through graph encoding and cross-view representation learning. To more effectively utilize heterogeneous relational information, NAFF-DTI introduces cross-view feature discrepancy modeling and a node-level adaptive fusion mechanism to dynamically adjust the contribution of different views according to node structural characteristics. Experimental results show that NAFF-DTI achieves the best AUC and AUPR on all five benchmark datasets. Compared with the strongest baseline for each dataset and metric, NAFF-DTI achieves average relative improvements of 3.81% in AUC and 3.23% in AUPR. It can also improve the utilization of multi-source information, maintain relatively stable prediction under different data distributions, and prioritize biologically plausible candidate drug–target associations from the unannotated candidate space. These results indicate that NAFF-DTI can provide computational support for DTI candidate prioritization and repurposing-oriented hypothesis generation. Full article

Traditional Network Intrusion Detection Systems (NIDSs) face persistent challenges in detecting zero-day attacks due to concept drift, high false-positive rates, and limited adaptability. This research introduces a Cognitive Network Intrusion Detection System (CNIDS) whose central novelty is that effective zero-day handling does not arise from any single mechanism but from the interaction between continual representation learning, persistent vector memory, and human-aligned feedback. By reframing zero-day resilience as a continuous learning process rather than a static detection task, CNIDS emphasizes adaptive operational behavior over raw automated accuracy. The proposed framework integrates Continual Pre-Training (CPT) to align representations with evolving traffic, Supervised Fine-Tuning (SFT) to preserve precision on known attacks, and a Human-in-the-Loop Reinforcement Signal (HRS) that converts low-confidence alerts into structured learning updates. These components are unified through a vector database that functions as long-term episodic memory, enabling similarity-based reasoning and cross-dataset generalization. Ablation results show that disabling any component degrades zero-day adaptation: removing CPT increases drift sensitivity, removing vector memory prevents knowledge retention, and removing human feedback collapses learning to static inference. Using a class-exclusion zero-day protocol on NSL-KDD, UNSW-NB15, and CICIDS2017, CNIDS raises zero-day detection from 0% to 18.2% while maintaining precision above 80% and stabilizing false positives. Full article

Rapid detection of foodborne pathogenic and spoilage microorganisms is critical for ensuring food safety and quality in liquid matrices. While Raman tweezers spectroscopy (RTS) enables label-free single-cell analysis, its application in high-throughput inline inspection faces a fundamental bottleneck: high flow rates required for efficiency induce severe motion blur and low signal-to-noise ratios (SNR), which blind automated control systems and destabilize optical trapping. To overcome this, we present a Spatiotemporal Video-Enhanced Raman Tweezers (SVERT) system integrating a deceleration-optimized microfluidic chip with a deep learning-based visual feedback loop. We propose a Local–Global Unified Denoising Network (LGU-Net) tailored to recover high-fidelity bacterial structures from low-SNR video streams, achieving a deterministic processing latency of ~0.49 ms. Experimental results demonstrate that SVERT improves the optical trapping success rate from 21.27% ± 2% to 91.47% ± 1.8% compared to raw video input, enabling a four-fold increase in spectral acquisition efficiency. Leveraging the acquired high-quality dataset, we achieved a classification accuracy of 96.74% across four bacterial species of relevance to food safety and quality. Crucially, we validated the system’s practical robustness by successfully isolating and tracking trace E. coli in an unpurified commercial beverage. This capability to effectively mitigate natural background interference demonstrates the system’s promising potential to be expanded for broader applications in liquid food safety screening. Full article

Precision feeding is an important foundation for improving production efficiency in aquaculture, reducing feed waste, mitigating water pollution, and promoting the intelligent development of aquaculture. Conventional feeding practices remain heavily dependent on operator experience and are typically executed at predetermined times or fixed ration levels. Such approaches frequently result in extensive feeding management, poor adaptability, low feed utilization efficiency, and delayed responses to environmental changes. Advances in machine vision, the Internet of Things, machine learning, deep learning, and automatic control have progressively shifted aquaculture feeding research beyond standalone automatic feeders toward integrated systems encompassing demand perception, intelligent decision-making, precise control, and equipment coordination. This paper reviews the state of the art in precision feeding technologies and equipment in aquaculture. At the technical level, it summarizes advances in feeding demand perception, intelligent feeding decision-making, and precise control and execution. At the equipment level, it reviews the main types, design features, and field application status of precision feeding equipment in intensive aquaculture, pond aquaculture, and offshore aquaculture scenarios. Despite the considerable progress achieved, the practical deployment of precision feeding still faces several limitations. Environmental disturbances, water turbidity, illumination variation, and sensor drift may compromise the reliability of feeding demand perception. Existing decision-making models frequently exhibit limited generalizability across species, growth stages, and aquaculture scenarios. Moreover, insufficient integration of sensing, decision-making, and execution restricts the development of fully closed-loop feeding systems. High initial investment, maintenance costs, and the shortage of skilled personnel further constrain the adoption of precision feeding equipment, particularly in resource-limited regions. On this basis, the main challenges including sensing accuracy, model practicability, closed-loop control, equipment reliability, and standardization, are examined. Future development trends are also discussed, covering multi-source information fusion, synergy between mechanistic models and data-driven methods, system-level closed-loop control, equipment modularization, and industrial application. This review is expected to provide a reference for subsequent research and engineering applications. Full article