Search Results (2,912)

The exponential growth of genomic and proteomic data has made computational protein–protein interaction (PPI) prediction indispensable, driving the need for a comprehensive and method-aware evaluation of supervised learning approaches. PPIs are fundamental to understanding cellular processes and disease mechanisms, yet experimental identification remains slow, costly, and difficult to scale. This survey systematically investigates ten supervised learning models—Extreme Learning Machine (ELM), Convolutional Neural Networks (CNNs), Graph Neural Networks (GNNs), Deep Neural Networks (DNNs), Naïve Bayes, Probabilistic Decision Tree, Support Vector Machine (SVM), Least Squares SVM (LS-SVM), K-Nearest Neighbor (KNN), and Weighted K-Nearest Neighbor (WKNN)—through a tri-layered framework that integrates Comparative Quantitative Analysis, Comparative Observational Analysis, and Experimental Evaluations. Beyond conventional accuracy summaries, this work provides critical commentary tied to real-world use, analyzing where techniques succeed or fail in practice—for instance, when instance-based methods bottleneck during inference, when kernel choices influence SVM variance, or when deep architectures trade accuracy for computational cost. The survey also offers concrete deployment guidance, such as calibration insights for WKNN versus KNN under varying feature noise or dataset curation quality, delivering operational perspectives that typical surveys omit. Comparative Quantitative Analysis consolidates metrics such as accuracy, F1-score, and computational time from the existing literature, while Comparative Observational Analysis evaluates interpretability, scalability, dataset suitability, and efficiency. Complementing these, Experimental Evaluations conducted by the authors empirically validate model performance on benchmark datasets. Together, these layers provide a unified and evidence-backed perspective on algorithmic strengths, weaknesses, and practical applicability. Findings show that GNNs and DNNs achieve the highest predictive accuracy due to their ability to capture structural and topological relationships, whereas ELM and Naïve Bayes offer superior efficiency. SVM and LS-SVM maintain robust stability under noisy conditions, and CNNs are well-suited for sequence-based prediction tasks. By combining empirical validation, critical insights, and deployment-focused recommendations, this survey delivers decision-grade guidance that bridges theoretical understanding with real-world implementation, thus clarifying the trade-offs among accuracy, efficiency, and scalability in PPI detection research. Full article

Domain Generation Algorithms (DGAs) pose a persistent threat by enabling malware to dynamically generate numerous command-and-control domains, evading traditional blocklists. While machine learning-based detectors have achieved high accuracy, they operate as statistical pattern matchers and lack the human-like anomaly perception that enables security experts to intuitively recognize unnatural domains. This paper introduces CogNormDGA, a cognitive-driven framework that models normal domain characteristics from a defender’s perspective while also anticipating how attackers might exploit cognitive blind spots. Inspired by dual-process theory, CogNormDGA combines intuitive, pattern-based screening (System 1) with analytical, rule-based evaluation of phonotactic, morphological, and semantic violations (System 2). The cognitive principles of System 1 and System 2 are computationally realized as two distinct pathways: an Attentional Salience Network and a Linguistic Constraint Evaluator, respectively. The framework produces interpretable outputs via attention saliency maps and cognitive violation reports. Extensive experiments on 400,000 domains spanning 33 DGA families demonstrate that CogNormDGA achieves competitive detection performance (F1-score 0.941) while establishing a cognitive-driven detection paradigm that produces human-aligned explanations—a property critical for practical security. It shows promising results on low-entropy and novel DGA families. Human subject studies confirm strong alignment between the model’s internal explanations and expert reasoning. Furthermore, CogNormDGA is particularly effective against low-entropy DGA families that exploit cognitive blind spots. By bridging cognitive science and cybersecurity, our work offers an interpretable and human-aligned approach to threat detection, with promising resilience that requires further validation. Full article

Hydrogels, particularly those based on polymer networks, exhibit complex mechanical behaviors arising from the interplay between network architecture, molecular interactions, and external stimuli. In particular, their viscoelasticity, energy dissipation, and nonlinear mechanical responses arise from the dynamic nature of crosslinking and multiscale relaxation processes. This review provides a comprehensive overview of hydrogel mechanics from a multiscale perspective, covering viscoelastic behavior, relaxation dynamics, energy dissipation mechanisms, nonlinear deformation, and fracture properties. We summarize recent advances in experimental characterization, including bulk rheology and single-molecule force spectroscopy, and discuss how molecular-level interactions, bond kinetics and mechanochemical processes contribute to macroscopic mechanical performance. In addition, theoretical models and constitutive frameworks describing transient and dynamic polymer networks are critically evaluated to bridge microscopic dynamics with bulk responses. Emerging strategies that integrate dynamic bonding and force-responsive elements are also discussed in the context of tailoring mechanical adaptability and functionality. Finally, we outline current challenges and future directions toward the rational design of hydrogels with tunable viscoelasticity, enhanced mechanical robustness, and programmable mechanical functions. Full article

Recent advancements in deep learning have shown considerable potential to enhance radar target detection, particularly in improving detection probability under complex environmental conditions. However, existing deep learning approaches largely operate in the real number domain, neglecting the complex-valued nature of radar data, and often inherit vision-oriented architectures that fail to address radar-specific challenges—such as sparse target echoes, the necessity for phase preservation, and constraints imposed by scanning radar systems. Meanwhile, conventional radar signal processing methods, including CA-CFAR, are limited by their dependence on idealized statistical models and often underperform in dynamic and cluttered electromagnetic environments.To overcome these issues, this paper proposes Radar Transformer for Detection (RaTDet), an end-to-end detection network that integrates complex-valued convolutional neural networks (CNNs) and Transformers. RaTDet fully leverages complex-valued data to preserve critical phase and amplitude information, enabling automated feature learning directly from raw radar signals. The model operates effectively with very few pulses, making it suitable for resource-constrained scenarios, and can serve as a pre-trained foundation model for various radar downstream tasks. Experimental results demonstrate that RaTDet achieves excellent detection performance, characterized by high detection probability (Pd) and low false alarm rate (Pfa), outperforming both traditional signal processing and conventional deep learning methods. This work bridges the gap between deep learning and radar signal processing, offering a flexible and powerful network for next-generation radar systems. Full article

To meet the stringent industrial service requirements of magnesia–chrome refractory bricks, this study adopts a technical approach that synergistically combines precise component ratio optimization with a vacuum-pressure MgSO₄ salt impregnation process to investigate the performance optimization of magnesia–chrome bricks. Samples were prepared by controlled formulation mixing, pressing at 250 MPa, drying at 110 °C, and firing at 1750 °C. Phase composition, microstructure, and physical–mechanical properties were characterized by XRD, SEM, and standard refractory test methods. The optimal additions of chromite powder and Cr₂O₃ micro-powder were determined to be 3 wt.% and 2 wt.%, respectively, which reacted with periclase to form a secondary composite spinel, creating a dense spinel bridge network that connected adjacent grains. Furthermore, when the proportion of sintered magnesia powder (MgO > 97 wt.%) was increased to 11 wt.%, the material achieved efficient densification facilitated by enhancing sintering performance. Based on this optimized formulation, and due to the high elemental compatibility between MgSO₄ and the magnesia–chrome brick matrix as well as the excellent permeability of the solution, the MgSO₄ vacuum-pressure salt impregnation process was subsequently applied. The salt solution filled the open pores and microcracks of the material, forming a crystalline salt micro-pillar reinforcing phase. Consequently, the apparent porosity of the material decreased to 10.98%, the bulk density increased to 3.23 g/cm³, and the cold compressive strength and cold modulus of rupture reached as high as 113.52 MPa and 24.91 MPa, respectively. This study innovatively establishes a new pathway for enhancing the mechanical properties of magnesia–chrome refractory bricks through the synergistic design of component ratio optimization and salt impregnation process. The prepared magnesia–chrome refractory bricks exhibit both excellent mechanical properties and volume stability. Full article

Infrared small target detection (ISTD) plays a crucial role in many real-world applications. However, this task remains highly challenging due to the extremely small target size, low contrast, and complex background interference as infrared small targets often occupy fewer than 80 pixels in a $256\times 256$ image under a commonly used ISTD criterion. Although Segment Anything Model (SAM) shows strong generalization in image segmentation, directly applying SAM to ISTD is suboptimal, primarily due to the significant modality gap between RGB and infrared imagery, as well as the prohibitive cost of full-parameter fine-tuning. To address these challenges, we propose a prompt-free and parameter-efficient fine-tuning framework that adapts SAM for ISTD. To bridge the cross-modality gap while preserving the pretrained prior knowledge of SAM, a lightweight Infrared Adapter (IR-Adapter) is introduced into the image encoder, enabling effective task adaptation with only a small number of trainable parameters. Furthermore, to alleviate the loss of small target information in deep network layers, we design a Multi-Scale Feature Fusion (MSF) module that integrates hierarchical features from different encoder stages. In addition, a Coarse-to-Fine Head (CFH) with dual-branch prediction is proposed to incorporate fine-grained details for more accurate target localization and segmentation. Extensive experiments conducted on two public datasets demonstrate that the proposed method achieves better overall performance than existing representative approaches, yielding higher IoU, nIoU and Pd. Full article

Synthetic Aperture Radar (SAR) images are affected by speckle noise, which limits their application in fine object interpretation and quantitative analysis. Recent deep learning-based single-image SAR despeckling methods have made significant progress in spatial structure modeling but struggle to exploit temporal redundancy in multi-temporal data. Existing multi-temporal despeckling methods usually rely on complex spatiotemporal network structures, which are prone to overfitting or excessive smoothing of details when training samples are limited. To address these challenges, this paper proposes a latent-space-guided multi-temporal SAR despeckling method from the perspective of transfer learning and representation alignment, achieving effective knowledge transfer from single-image SAR despeckling to multi-temporal despeckling tasks. The method treats the single-image SAR despeckling task as a knowledge source domain, using stable latent space representations learned from the pre-trained single-image despeckling model as prior constraints. A latent space regularization mechanism is introduced during the training of the multi-temporal despeckling model, thereby establishing an explicit representation bridge between the 2D spatial model and the 3D spatiotemporal model. With this strategy, the multi-temporal model inherits the structural perception capability of the single-image model under limited training samples, improving speckle suppression while effectively maintaining image detail and structural consistency. Additionally, a pure convolutional network architecture is employed to support variable-length multi-temporal sequence input, enhancing the method’s adaptability under different temporal sampling conditions. Full article

Port competition is increasingly shaped by network structures and differentiated functional roles rather than isolated capacity-based comparisons. This study investigates the structural evolution and functional differentiation of the global container port network from a systems perspective by integrating port-cluster identification with role-based functional evaluation. A CONCOR-based approach is employed to delineate structurally cohesive port clusters, while the rank-sum ratio (RSR) method is used to assess ports’ dominant functional roles, including High-Efficiency core, Bridge-Control, and free-form bridging functions. Based on a comparative analysis of network data for 2014 and 2024, the results reveal a transition from a relatively dispersed and multi-polar configuration toward a more concentrated and hierarchical system. Three recurrent spatial structures are identified, reflecting differentiated patterns of trunk connectivity, corridor organisation, and adaptive network flexibility. Functionally, core hubs have expanded their coverage of mainline services, Bridge-Control ports have become increasingly concentrated at strategic chokepoints and transition zones, and free-form bridging ports have enhanced routing flexibility by linking structurally non-overlapping subnetworks. These findings advance understanding of the evolving structure and interdependence of global port competition and provide insights for system-level coordination, cluster-based governance, and coordinated infrastructure planning. Full article

To examine the complex relationships among physical activity, emotion regulation, psychological stress, and mood states in college students, this study analyzed questionnaire data collected from 494 participants. Network analysis was employed to construct a global association network, compare gender differences, and characterize patterns of directed statistical dependencies via directed acyclic graph (DAG) analysis. The results showed that: (1) the network comprised 25 nodes and 94 non-zero edges, reflecting extensive conditional associations across the four domains; (2) bridge centrality analysis identified cognitive reappraisal, self-related emotions, and anger as key bridge nodes, with cognitive reappraisal exhibiting the highest bridge strength; (3) accuracy and stability analyses yielded a centrality stability coefficient (CS) of 0.749 for strength, indicating adequate network stability; (4) network comparison tests revealed no significant gender differences in overall network structure or global strength, although certain local edge weights differed; (5) DAG analysis suggested that stable directional dependencies were primarily concentrated within individual subsystems, with no marked structural differences observed between male and female groups. In conclusion, physical activity, emotion regulation, psychological stress, and mood states appear to constitute an interconnected psychological adaptation system. Cognitive reappraisal, self-related emotions, and anger likely serve as pivotal bridge nodes warranting priority in future longitudinal research and targeted interventions. Full article

This paper presents a theoretically grounded integration of deterministic Q-learning with relational game theory (QLRG) for efficiently identifying minimal winning coalitions in Online Social Networks (OSNs). We address the fundamental challenge that coalition formation is NP-hard under traditional approaches by leveraging structural properties of relational dependencies and Armstrong’s axioms to transform the problem into one solvable in polynomial time. Our framework reduces the state space from exponential O(2ⁿ) to O(n²) through a sufficient statistic representation based on coalition size, follower reach, and terminal status, while achieving O(n⁴) time complexity under deterministic, static, and sufficiently symmetric influence structures. The QLRG framework introduces three critical innovations: (1) a principled agent selection mechanism derived directly from the Q-function that eliminates heuristic weight tuning; (2) a formal Boost action defined through temporal closure operators that captures influence spread dynamics; and (3) a constrained MDP formulation that enforces relational consistency through action elimination rather than penalty terms. We prove that the Bellman optimality operator forms a contraction mapping, guaranteeing deterministic convergence to optimal policies with established rates of O(1/√k) for decreasing learning rates or linear convergence up to bias for constant rates. To bridge the gap between this idealized model and the asymmetry inherent in real OSNs, we further develop a cluster-based sufficient statistics approach. By partitioning the network into communities with bounded internal variation, we relax the global symmetry requirement while preserving polynomial state space complexity, and obtaining a single within-community swap changes the optimal Q-value by at most ε_i/(1−γ), which is a local Lipschitz continuity result. The implications of this are both theoretical and practical, and they form the bedrock for relaxing the global symmetry assumption in the QLRG framework. Empirical validation on synthetic networks satisfying the symmetry assumption demonstrates that QLRG consistently identifies minimal winning coalitions matching the optimal solutions found by exhaustive search, while operating with polynomial-time complexity. Unlike conventional approaches, our framework simultaneously satisfies four critical properties: deterministic convergence, policy optimality, minimal coalition identification, and computational tractability. The work bridges computational social science and operations research, providing a mathematically rigorous foundation for strategic decision-making in influencer marketing and coalition formation. While the framework requires symmetry assumptions that may only hold approximately in real-world OSNs, it establishes an idealized baseline for future extensions addressing stochasticity, dynamics, and partial observability. This research represents a paradigm shift from empirical improvements to theoretically grounded convergence guarantees for coalition formation problems, demonstrating how structural mathematical insights can transform intractable problems into efficiently solvable ones without sacrificing solution quality. Full article

The large-scale operation of multiple fixed-wing unmanned aerial vehicles (UAVs) in shared airspace requires efficient flight conflict detection and resolution to ensure aviation safety. However, existing research predominantly lacks collaborative optimization of multi-dimensional maneuver recommendations and struggles with dynamic priority allocation in complex multi-UAV scenarios, leaving a critical gap in the field. To bridge this gap, this paper proposes a Complex Network-Based Multi-UAV Conflict Resolution (NCR) method, which first constructs a three-dimensional (3D) flight conflict detection and resolution model for fixed-wing UAVs. The core innovation lies in mapping dynamic multi-UAV conflict scenarios into a flight conflict network, where UAVs serve as nodes and conflict urgencies act as edge weights. By calculating network and node robustness, the method accurately identifies key UAVs requiring immediate maneuver. Subsequently, taking the minimum variation in the velocity vector as the core objective, NCR iteratively searches for optimal resolution recommendations for these key UAVs using an improved fitness function until the conflict network collapses. Simulation and comparative experiments in 3D airspace, including evaluations against serial-based resolution, random-recommendation resolution, and a classical reactive baseline, demonstrate that NCR efficiently resolves multi-UAV conflicts with minimal trajectory deviations and fewer maneuvering UAVs. Furthermore, a macro-micro bi-level validation architecture based on a six-degree-of-freedom (6-DOF) aerodynamic platform is introduced to verify the physical executability of the proposed strategies. Results demonstrate that by incorporating a dynamic aerodynamic compensation margin, the inevitable trajectory tracking deviations caused by system inertia are enveloped within the safety threshold, ensuring absolute flight safety in engineering practice. Notably, as conflict complexity increases, NCR exhibits prominent advantages in reducing velocity variation costs, minimizing the number of maneuvering UAVs, and avoiding unnecessary trajectory deviations. Full article

Artificial Emotional Intelligence (AEI) has gained significant attention for enabling machines to recognize and interpret human affective states through modalities such as speech. While deep learning-based speech emotion recognition (SER) models have achieved promising accuracy levels, their practical deployment in resource-constrained IoT edge environments remains insufficiently explored. In particular, there is a lack of systematic evaluation approaches that jointly consider classification performance, computational efficiency, and deployment feasibility under edge-oriented operational constraints. In this study, I address this gap by proposing a deployment-aware evaluation perspective for SER systems operating under IoT edge constraints. Rather than introducing a new model architecture, I focus on establishing a unified and reproducible evaluation framework that reflects practical deployment considerations for edge-based intelligent systems. Within this framework, three widely used deep learning architectures, convolutional neural networks (CNN), long short-term memory (LSTM), and dense neural networks, are systematically analyzed using the EMODB dataset. The experimental results demonstrate that CNN-based models achieve the most consistent classification performance, with peak validation accuracy reaching approximately 84%, while also providing a favorable balance between recognition performance and computational efficiency. To better reflect deployment-oriented evaluation, the study also considers latency-related behavior and computational characteristics relevant to edge computing environments based on benchmark-driven estimations. The findings highlight the importance of deployment-aware evaluation strategies and provide practical insights for selecting suitable model architectures in edge-oriented speech emotion recognition scenarios. This study contributes to bridging the gap between theoretical deep learning performance and practical feasibility considerations in IoT-based intelligent systems. Full article

This work explores the key capabilities of emerging sensing technologies in the context of Structural Health Monitoring (SHM) of civil infrastructures, aiming to contribute to research on integrated and intelligent systems for more accessible and efficient monitoring solutions. As a case study, it focuses on the analysis of the static and dynamic behavior of the Edgar Cardoso stay-cable bridge during its rehabilitation, using fully customized transducers and equipment. The developed system integrates sensors capable of measuring accelerations, displacements, and temperature, which are connected to an autonomous data acquisition and transmission network. A digital interface was also developed to store, process, and visualize the collected data, enabling remote access for subsequent interpretation and analysis. The main contribution of this research lies in the use of optimized wireless monitoring systems with extended autonomy. This is achieved by employing edge computing techniques to minimize energy consumption during data transmission, as well as by managing the sleep modes of the sensor nodes. At same time, a methodology was proposed for the automatic and real-time estimation of axial forces in cables. This approach relies on the use of innovative edge computing tools, combined with the taut string theory as a simplified modelling framework. The results confirm the effectiveness of the developed system in achieving long-term operation without compromising monitoring performance. In addition, the developed system enabled the identification of the structure’s dynamic properties, particularly natural frequencies. The temperature profiles in critical sections, as well as displacements in the expansion joint were also measured and evaluated. The results demonstrate the potential of customized sensing solutions as effective tools for the management, maintenance, and long-term preservation of strategic infrastructures. Full article

Fear of missing out (FoMO) is a cognitive-affective factor that has been consistently linked to problematic social media use (PSMU), but less is known about whether this association differs across severity-based subgroups or changes over time at the node level. This study examined the cross-sectional and two-wave associations between FoMO and PSMU in Chinese university students. Two-wave data were collected one year apart from 853 participants at Time 1 and 817 participants at Time 2. Partial correlation and regression analyses showed that FoMO was positively associated with PSMU. Latent profile analysis identified broad higher- and lower-level subgroups for both FoMO and PSMU. Node-level network analyses further indicated that FoMO and PSMU nodes were positively interconnected. Most subgroup and two-wave network comparisons suggested that overall network structure was relatively stable. The clearest temporal difference emerged in the global strength of the PSMU network. When differences were observed, they were more evident in the relative prominence of specific nodes, including several bridging nodes, than in broader network organization. Overall, the findings suggest that the FoMO-PSMU association is robust, whereas subgroup- and time-related variation appears limited and is better understood as node-level variation within a broader pattern of structural stability. Full article

Micro- and nanoplastic pollution poses an emerging challenge for aquatic environments, driving the need for efficient and scalable removal strategies. Functional polymeric materials (FPMs) have emerged as a versatile platform to address this issue, owing to their tunable chemical composition, structural diversity, and ability to promote multiple removal mechanisms, including adsorption, filtration, and coagulation/flocculation. This review provides an overview of recent advances in polymer-based strategies for the removal of micro- and nanoplastics, with emphasis on material design, interaction mechanisms, and process performance. A broad range of materials, including natural hydrogels, polysaccharide aerogels, synthetic polymer composites, magnetic hybrids, and metal–organic frameworks (MOFs)–polymer systems, have demonstrated high removal efficiencies through electrostatic interactions, hydrogen bonding, hydrophobic effects, π–π stacking, and physical entrapment. Removal performance is strongly influenced by surface functionalization, porosity, surface area, and polymer network architecture, enabling targeted design for specific particle types and water matrices. Hybrid and multifunctional materials further enhance capacity and reusability, while natural polymers offer sustainable alternatives. Despite these advances, challenges remain in standardization, scalability, long-term stability, fouling resistance, and economic feasibility under realistic environmental conditions. Future research should focus on sustainable, multi-target, and scalable FPMs, integrating hybrid architectures, stimuli-responsive functionalities, and bioinspired design strategies. Particular attention should be given to mechanistic studies under environmentally relevant conditions and the establishment of structure–property design criteria to enable efficient removal of heterogeneous MPs/NPs mixtures. Overall, functional polymeric materials represent a flexible and high-performance platform for mitigating micro- and nanoplastic contamination, although their successful implementation will depend on bridging the gap between laboratory-scale performance and real-world water treatment applications. Full article