Search Results (2,452)

Predicting landslide displacement is important for geological-hazard early warning. In reservoir areas, displacement evolution is affected by rainfall, reservoir water level, vegetation variation, and the intrinsic non-stationarity of the displacement sequence, which makes accurate prediction difficult for conventional single-sequence models. To address this problem, this study proposes a residual-increment-oriented landslide displacement prediction framework that fuses multi-source monitoring variables. The displacement sequence is first processed into trend and periodic-related fluctuation representations, and the residual increment is used as the prediction target. Rainfall, reservoir water level, and the normalized difference vegetation index (NDVI) are incorporated as external monitoring variables. A cross-branch attention mechanism models interactions among heterogeneous feature branches, and a sparse MoE-based fusion module is introduced to adaptively adjust branch contributions under different deformation conditions. The model predicts the displacement residual increment, from which the final displacement is reconstructed. A case study using the Baishui River (Baishuihe) landslide monitoring dataset was conducted, together with additional validation on the related Bazimen Z110 landslide monitoring dataset and comparisons against conventional recurrent, convolutional, statistical, and Transformer-based baselines. The results show that the proposed model achieves lower RMSE and MAE than the compared methods on the tested datasets. These findings suggest that residual-increment modeling, multi-source monitoring variables, and condition-dependent branch fusion can improve short-term displacement prediction for the tested reservoir-area landslide cases. Full article

During startup, ransomware is associated with abnormal fluctuations in underlying hardware resources. Hardware Performance Counters (HPC) can characterize this ultra-early behavior without interference from software-based countermeasures. However, existing studies lack a cross-platform hardware-layer analysis paradigm and typically neglect the first 10 s post-execution. This study selects two platforms—Windows 7 (homogeneous x86) and Windows 10 (Intel performance hybrid architecture with P-core (performance core) and E-core (efficiency core))—and constructs a large-scale dataset (1721 ransomware and 1039 benign samples on Windows 7; 1562 ransomware and 718 benign on Windows 10). On Windows 7, 25 HPC events are monitored. On Windows 10, each event yields two instance-level metrics (P-core and E-core), resulting in 42 instance-level metrics. Using statistical analysis (Pearson correlation, fold change) and feature selection (Random Forest + clustering), four core metrics are independently selected per platform. Windows 7 favors LLC and branch events (increasing trends, fold change ≥ 1.5, e.g., LLC-store_std), while Windows 10 favors P/E-core branch and cache events (decreasing trends, fold change ≤ 0.667, e.g., cpu_atom_branch-load-misses_max). The 10 s window is divided into startup (0–2 s), key generation (2–5 s), and encryption (5–10 s) phases. Results indicate opposite correlation patterns: resource-enhanced disturbance (positive correlation, fold change ≥ 1.5) on Windows 7 versus resource-suppressed disturbance (negative correlation, fold change ≤ 0.667) on Windows 10. Critically, startup-phase HPC events exhibit substantially stronger correlation on Windows 10 (S-level, >85%) compared to Windows 7 (A-level, 70–84%). This difference may be associated with the fine-grained P/E-core separation, which preserves core-type behavioral information that is aggregated and lost on homogeneous platforms. This study contributes a cross-platform correlation framework, observes an architecture-dependent inversion pattern of HPC responses, and suggests that core-type granularity—rather than event quantity—is associated with stronger feature–behavior correlations on heterogeneous architectures, providing preliminary empirical insights for future lightweight detection system design. Full article

GNSS array receivers suffer tracking degradation under array nonidealities such as element-position perturbations, channel amplitude/phase errors, and slowly varying manifold mismatch. Conventional blind anti-jamming suppresses interference, but adaptive weight fluctuations can propagate into the correlator domain, increasing cross-branch correlation, causing Early/Late metric imbalance, and reducing Prompt phase consistency. Existing noncoherent combining methods mainly convert multi-branch correlator outputs into scalar energy metrics for code tracking, leaving the carrier loop’s complex Prompt input insufficiently constrained. To address this problem, we propose a blind adaptive joint code–carrier channel-combining method for nonideal arrays. After first-stage anti-jamming, the method estimates an Early/Late correlator-domain covariance matrix and reuses it as a shared statistical constraint. In the code loop, this matrix drives whitened noncoherent energy combining with closed-loop gain normalization to stabilize the DLL discriminator scale. In the carrier loop, it is combined with a Prompt-derived coherent direction to form a covariance-constrained PLL complex input. Simulations under wideband interference, static array errors, and dynamic mismatch show that the proposed J-WNCC reduces both code-phase error and carrier-phase jitter, improving joint tracking robustness in nonideal array environments. Ablation results further reveal a dominant-effect separation: DLL gain normalization mainly calibrates the whitened code-discriminator scale, whereas coherent Prompt combining mainly reconstructs the complex PLL input. Full article

Malware classification increasingly relies on machine learning models that combine static and dynamic evidence, yet their practical use is often limited by dataset inconsistency, high-dimensional feature spaces, and insufficient transparency. This paper presents an explainable hybrid malware-classification pipeline built on an aligned public dataset in which static and dynamic features are matched at sample level and share the same class space. The framework combines a Random Forest static branch, a calibrated XGBoost dynamic branch, and a weighted late-fusion stage whose branch weights are derived from inner-validation weighted-F1 rather than from test performance. On the corrected no-leak benchmark, static reduction compresses the static space from 771 to 258 features, while sparse-aggressive reduction compresses the dynamic space from 21,918 to 374 features. An early-fusion XGBoost baseline achieves the best multiclass aggregate scores, whereas the validation-weighted calibrated hybrid provides the strongest false-negative-first Benign vs. Malware profile, reaching malware recall 0.9998, benign recall 0.8053, and one false negative on the test set. The study shows that, once leakage is removed and fusion is validation-driven, the preferred hybrid architecture depends on the operational objective rather than on a single aggregate metric. Full article

Background and Clinical Significance: Left ventricular free-wall rupture (LVFWR) is a rare but devastating mechanical complication of acute myocardial infarction (AMI), with reported in-hospital mortality approaching 90% without surgical intervention. Although its incidence has declined in the contemporary primary percutaneous coronary intervention (PCI) era, LVFWR remains an important cause of early post-infarction death, particularly after delayed reperfusion or fibrinolytic therapy. Subacute or contained “oozing” ruptures pose a unique diagnostic challenge because hemodynamic stability and nonspecific symptoms can mask the underlying catastrophe, and standard transthoracic echocardiography may fail to visualize a sealed defect. Contrast-enhanced cardiac computed tomography (CT) has emerged as a valuable adjunct in this setting, enabling early recognition and surgical planning. Case Presentation: We report a case of a 51-year-old male, a heavy smoker, with acute lateral ST-segment elevation myocardial infarction (STEMI) treated with thrombolysis at a referring hospital, followed by percutaneous coronary intervention (PCI) to the obtuse marginal branch. Despite reperfusion, he developed persistent pleuritic chest pain and a small pericardial effusion. Cardiac computed tomography (CT) demonstrated a contained (sealed) lateral-wall oozing-type left ventricular free-wall rupture (LVFWR) with thrombus sealing the defect. A multidisciplinary heart team initially opted for diligent observation with frequent echocardiography. Within the first 24 h, the pericardial effusion increased, and echocardiography showed circumferential effusion with lateral wall thickening and hematoma, prompting emergent sternotomy. Intraoperatively, a large posterolateral infarct with an oozing-type LV free-wall rupture was identified. Surgical repair was performed using interrupted pledgeted sutures, native pericardial patch, BioGlue, and an overlying Teflon patch, with intra-aortic balloon pump (IABP) support. This case demonstrates the complementary diagnostic value of multimodality imaging—echocardiography for serial monitoring of the pericardial effusion and regional wall changes, and cardiac CT for direct characterization of the contained (sealed) defect—and the timely transition from conservative to surgical management in oozing-type rupture. The patient recovered uneventfully and was discharged in stable condition. Conclusions: This case highlights the diagnostic value of multimodality imaging—particularly cardiac CT—in detecting contained (sealed) LVFWR when echocardiography is inconclusive. Early recognition and prompt surgical intervention enabled a successful outcome in this otherwise frequently fatal complication. Full article

Skeleton-based human action recognition (HAR) requires models that preserve the local kinematic structure of the human body while capturing long-range spatiotemporal dependencies under noisy or incomplete joint observations. Traditional Graph Convolutional Networks (GCNs) provide topology-aligned inductive bias but are often limited by local information aggregation from neighboring joints. In contrast, attention-based mechanisms capture global interactions, yet they may attend to spurious correlations when skeletal constraints are weakly enforced. This paper proposes Differential Hyperedge Attention-enhanced GCN (DHA-eGCN), a hybrid architecture that couples structure-aware Differential Hyperedge Attention with multi-scale temporal convolution for spatiotemporal skeleton sequence processing. DHA injects skeletal structure into attention via hop-distance relative positional encoding and hyperedge context tokens generated via joint-to-part pooling. It further employs differential attention to suppress shared noisy correlations and enhance interaction selectivity. To strengthen spatial grounding, an explicit GCN branch is added under partial- or full-depth configurations, where the first four or all ten layers are applied with graph convolutions. The model further employs an ensemble strategy that combines predictions from multiple complementary model instances. Our experiments on NTU RGB+D 60 under the X-Sub and X-View protocols, NTU RGB+D 120 under the X-Sub and X-Set protocols, and Northwestern-UCLA demonstrate that DHA-eGCN consistently outperforms or remains competitive with strong graph-based, transformer-based, and hybrid state-of-the-art methods based on the same four-stream architecture. The best configuration achieves 93.7% and 97.0% on NTU RGB+D 60 X-Sub and X-View, respectively; 90.9% and 91.9% on NTU RGB+D 120 X-Sub and X-Set, respectively; and 97.6% on Northwestern-UCLA. Full article

Small unmanned aerial vehicles are difficult short-range radar targets because their millimeter-wave radar cross-sections often fall between −10 and −25 dBsm. This paper presents a modular analytical and simulation-based benchmark of a cascaded 77 GHz TDM-MIMO FMCW radar with 12 transmitters and 16 receivers, yielding a 192-element virtual ULA over a 40 m instrumented range. The framework is organized around the main counter-UAV sensing functions: range–Doppler processing first evaluates target observability and provides range–Doppler gates; Doppler-dependent TDM phase compensation is then required before virtual-array snapshots are formed for DoA estimation; and a separate long-dwell single-transmitter branch evaluates micro-Doppler separability using handcrafted features and a nearest-centroid Mahalanobis classifier. Four benchmarks are considered: detection under Swerling fluctuation models, residual TDM phase error caused by Doppler quantization, DoA estimation under an idealized far-field snapshot model, and micro-Doppler separability among UAV and bird classes. Under Swerling I, targets with a mean RCS of $-10$ dBsm or larger maintain detection probability above 0.9 throughout the 40 m window, whereas the $-20$ and $-25$ dBsm classes fall below that level at about 28 m and 21 m. In the far-field DoA benchmark, TLS-ESPRIT gives the lowest conditional RMSE and remains about 13–14 dB above the subarray CRLB at moderate SNR; however, these angular results are reference ceilings because the short-range operating region violates the full-aperture far-field condition and because residual TDM phase error can be severe without accurate compensation. In the micro-Doppler benchmark, birds exceed 95% per-class accuracy at 20 dB total SNR, but overall four-class accuracy saturates near 72–75% and UAV-only three-class accuracy near 63%, with most confusion between the micro-quadrotor and fixed-wing classes. This study therefore identifies architecture-specific performance margins and limitations before measured-data field validation, rather than claiming complete deployment-level performance. Full article

Remote sensing object detection remains challenging because objects often appear with large scale variation, dense spatial layouts, and strong interference from complex geographical backgrounds. To address these coupled difficulties, we propose EDM-Net, an end-to-end multi-scale detector that organizes feature processing into three coordinated stages: adaptive extraction, intra-scale interaction, and cross-scale fusion. First, an efficient sparse mixture-of-experts (ES-MoE) module is embedded in the backbone to allocate scale-specific convolutional experts according to scene-level feature responses, providing a more adaptive feature basis than a single static extraction path. Second, a dynamic mixing intra-scale feature interaction (DMIFI) module is introduced into the Transformer encoder. This module combines global self-attention with dynamic spatial mixing, thereby preserving long-range context while reintroducing local two-dimensional inductive bias for dense and small objects. Third, a multi-scale synergistic attention fusion (MSAF) module aligns adjacent feature levels through parallel local and global attention branches and structural re-parameterization, reducing semantic dilution during feature aggregation. Comprehensive experiments on three large-scale remote sensing benchmark datasets, DIOR, NWPU VHR-10, and RSOD, demonstrate that EDM-Net consistently improves over the re-trained RT-DETR-R18 baseline under the same experimental protocol, attaining mAP50 scores of 83.7%, 95.6%, and 95.8% respectively. Additional ablation and scale-specific analyses indicate that the three modules contribute complementary gains, especially for small and densely distributed objects. These results suggest that coordinated extraction, interaction, and fusion can improve remote sensing object detection under complex scale and background conditions. Full article

Paraleyrodes minei is an invasive alien species in China, representing a new record for Yunnan Province and a new sugarcane pest. The mitochondrial genome of P. minei was sequenced using the Illumina NovaSeq 6000 sequencing platform. The genome sequence was assembled and annotated, and its structural characteristics and nucleotide composition were analyzed. A phylogenetic tree of 18 species in the family Aleyrodidae was constructed using maximum likelihood (ML) and Bayesian inference (BI) methods to analyze the phylogenetic relationship of P. minei within the family Aleyrodidae. The results indicated that the mitochondrial genome of P. minei was 18,774 bp in length and contained 13 protein-coding genes (PCGs), 22 transfer RNA (tRNA) genes, 2 ribosomal RNA (rRNA) genes, and 1 non-coding control region. The A+T content of the mitochondrial genome of P. minei was 80.93%, indicating a marked A+T preference. ATN was used as the start codon for the PCGs, and TAA, TAG, TA, and T were used as the stop codons. In the secondary structure of tRNA, the TΨC arm was missing in trnA, trnC, and trnG, and the DHU arm was missing in trnS1 and trnS2, with G-U base mismatches present. The phylogenetic tree revealed that the 18 species of 10 genera in the two subfamilies of the family Aleyrodidae clustered into two major branches: the subfamilies Aleyrodinae and Aleurodicinae. All 10 genera were monophyletic groups; among them, the genus Paraleyrodes and the genus Aleurodicus formed a sister relationship, and both belonged to the subfamily Aleurodicinae. This study represents the first successful sequencing of the mitochondrial genome of P. minei, as well as the first mitochondrial genome of the genus Paraleyrodes, laying the foundation for the control of P. minei and the analysis of phylogenetic relationships among various genera of the family Aleyrodidae. Full article

Combined Vertical–Horizontal Well Patterns (CVHWPs) have been increasingly applied in mature and complex reservoirs, such as the C5 Block. Their application is attractive because they provide extensive reservoir coverage and high development efficiency. However, close well spacing and the three-dimensional configuration of vertical and horizontal wells can induce strong stress-shadow interference. This interference makes fracture propagation difficult to control and may reduce stimulation effectiveness. To address this problem, a multi-well, multi-fracture induced-stress model for CVHWP stimulation was developed in this study. The model was validated using laboratory three-stage fracturing experiments, including two horizontal-well stages and one vertical-well stage, together with field observations. Across three stages, the calculated stress intensity factors at breakdown are closely matched, validating the induced-stress model. When the vertical well was fractured first, the horizontal principal-stress difference at the adjacent horizontal stage increased by 2.01 MPa, which was unfavorable for branched fracture development. In contrast, when the horizontal stage was fractured first, the stress difference decreased by 3.25 MPa at the subsequent horizontal stage and by 3.89 MPa at the vertical-well stage. This sequence is preferable because fractures generated from the vertical well impose a stronger stress perturbation on adjacent horizontal-well fractures than fractures generated from the horizontal well impose on the subsequent vertical-well fracture. Under the tested CVHWP conditions, the horizontal-well fractures tended to form nearly symmetric bi-wing planar fractures, whereas branched fractures were more likely to develop in the vertical well. Therefore, for CVHWP reservoirs with close vertical–horizontal well spacing and significant stress interference, fracturing the horizontal well before the vertical well is recommended to control fracture propagation and promote multiple-fracture formation. Field application of this sequence showed notable production improvement, indicating that the proposed method can provide practical guidance for unconventional well-pattern fracturing design. Full article

A multiphase high-strength steel austempered at 260 °C for 24 h was investigated by quasi-in-situ tensile characterization and EBSD-based crystal plasticity finite element modeling. The experimental observations reveal that local plastic deformation is strongly heterogeneous: von Mises strain concentrates preferentially near bainitic-ferrite packets, phase boundaries, and retained-austenite/martensite–austenite regions, whereas blocky retained austenite contributes to strain accommodation at the early deformation stage. To quantify the underlying stress–strain partitioning, a quasi-two-dimensional representative volume element was reconstructed from EBSD data and implemented in ABAQUS through a user-defined material subroutine. The model contained the real grain morphology, phase distribution, and crystal orientation information of the 24 h austempered specimen. A rate-dependent crystal plasticity constitutive framework with BCC matrix, FCC retained austenite, and transformed martensite branches was calibrated against the macroscopic tensile curve. The simulated tensile response agrees well with the experimental curve before macroscopic instability, and the predicted local fields are consistent with the quasi-in-situ strain maps. The results show that local plastic strain first accumulates in M/A-related regions and phase-boundary-neighboring zones, while high Mises stress migrates dynamically with slip activity and stress-induced martensitic transformation. Retained-austenite transformation increases the local load-bearing capacity, modifies interphase load transfer, and delays the direct linkage of strain-localization bands. The present work clarifies the coupling among retained-austenite stability, TRIP-assisted load redistribution, and microstructural strain partitioning in multiphase high-strength steel, providing a mesoscale basis for microstructure-guided strength–ductility optimization. Full article

In the resistor images used in this study, many defective regions are weak coating-like marks rather than obvious scratches or pits. Their appearance is close to the epoxy background, and some visible defects were missing from the original annotation files. If these labels are used directly, the detector treats the missed defects as background samples during training. We therefore corrected the supervision before changing the feature constraint. An early YOLO26s model was first used to nominate low-overlap boxes, and these candidates were then checked manually. Only confirmed defects were merged into the labels. After this step, a scale-gated prototype consistency term was added during training to reduce the model’s bias toward the dominant tiny-defect group. On the fixed corrected benchmark, mAP50 improved from 28.14% to 63.20%, and Recall increased from 18.42% to 62.20%. In the end-to-end deployment view, where the raw and cleaned validation sets answer different practical questions, mAP50 changed from 43.66% to 63.15%, and Recall changed from 30.01% to 62.24%. For normal-size defects, Recall increased from 26.09% to 56.52%. A prototype-only transfer study on the public MVTec AD benchmark further evaluates whether the feature constraint generalizes when the label-repair stage is not applicable to clean public annotations. Since the prototype term is removed after training, the deployed detector remains the original YOLO26s model without an additional inference branch. Full article

Instance segmentation of surface defects is one of the research hotspots in the field of image segmentation. Due to limitations such as restricted receptive fields or the loss of fine-grained details, traditional neural network models still struggle to achieve sufficiently high-segmentation accuracy for surface defects. To meet the demand for high precision segmentation of surface defects on copper strips and plates in industrial quality inspection, this paper proposes a feature fusion segmentation network, termed DSFFNet. First, a dual-branch structure is designed in DSFFNet to fuse spatial-domain features with discrete cosine transform (DCT)-domain features, thereby obtaining richer feature information. Second, a 2D-DCT frequency feature extraction module is developed to more effectively capture the edge information of targets. Third, a triplet attention mechanism is introduced into the backbone network to form an attention-centric network. Finally, a bidirectional fusion module and a multi-scale fusion network are designed to capture finer-grained feature information. Comparative experiments conducted on the KUST-SEG-Dataset demonstrate that DSFFNet achieves 94.66% ± 1.07% (mask)mAP₅₀ and 95.38% ± 0.06% (box)mAP₅₀, outperforming several classic image segmentation methods. Furthermore, generalization experiments on the public NEU-Seg dataset yield a (mask)mAP₅₀ of 86.27% ± 0.01%. The generalization results indicate that DSFFNet is robust to datasets with similar defect types. Full article

P. massoniana is an important native economic and ecological tree species in southern China, where seasonal drought has emerged as a critical factor limiting its productivity. The SAUR gene family, recognized as core early auxin-responsive genes, plays a crucial role in balancing plant growth, development, and stress adaptation; however, research related to this family in conifers remains limited. Utilizing the chromosome-level genome of P. massoniana, this study identified 73 SAUR genes (PmSAUR1~73) through bioinformatics methods, systematically analyzing the physicochemical properties of the encoded proteins, chromosomal localization, phylogenetic relationships, gene structures, and cis-acting elements. Combined with transcriptome sequencing and molecular experiments, the drought stress response patterns of these genes were further elucidated. The results indicated that PmSAUR genes predominantly encode alkaline proteins, primarily localized in mitochondria and nuclei, with an uneven distribution across nine chromosomes, where tandem duplication serves as the primary mechanism driving family expansion. Phylogenetic analysis classified these genes into seven subfamilies, which include both conserved clades homologous to angiosperms and branches specific to P. massoniana. All members contain the Auxin_inducible conserved domain, with motif1 identified as the core essential motif. Promoter regions were enriched with MeJA (methyl jasmonate)-responsive (56%), ABA-responsive, and drought stress-related cis-elements. Under drought stress, 38 PmSAUR genes exhibited diverse temporal expression patterns. Four key genes (PmSAUR14, PmSAUR28, PmSAUR54, and PmSAUR73), which are localized in the nucleus and exhibit high expression specifically in male cones or roots, were identified. These genes exhibit an expression pattern consistent with an auxin-negative response (i.e., repressed by IAA and induced by drought) and display a distinctive response pattern characterized by drought-induced upregulation coupled with IAA-mediated downregulation. This mechanism may contribute to the drought adaptation strategies of P. massoniana, involving regulatory processes for aboveground reproduction and adaptation of the underground root system. This study represents the first effort to elucidate the evolutionary characteristics and drought response patterns of the SAUR gene family in P. massoniana, thereby addressing the existing research gap regarding the functions of SAUR genes in coniferous trees. Furthermore, it offers candidate gene resources and theoretical support for the molecular breeding of stress resistance in P. massoniana. In addition, two auxin-induced SAUR genes (PmSAUR22 and PmSAUR37) were identified as contrasting examples, but the main focus of this study is on the four auxin-repressed genes. Full article

Large language models (LLMs) are increasingly used in programming education to provide on-demand conceptual clarification, yet how students actually use this feature in mastery learning systems (in which learners must demonstrate conceptual competence before progressing)—and whether clarification interactions relate to subsequent learning—has received limited empirical study. This paper analyzes 732 student remediation episodes (366 students, 43 assignments) to examine how students move through the remediation branch of an LLM-assisted programming course, whether their behavioral pathway choices are associated with subsequent coding challenge efficiency, and what theoretical role the clarification function plays. The results show that 78.0% of remediation episodes follow a pure retesting strategy, with only 22.0% involving any clarification interaction. Clarification is highly concentrated on conceptual questions (84.7%) and occurs mostly in the first remediation round (86.3%). An effect size analysis reveals a large difference in remediation rounds between single immediate and single delayed clarifiers (Cliff’s $\delta =-0.912$), suggesting that the timing of clarification is more strongly associated with remediation efficiency than its occurrence alone. mixed-effect linear models show no significant pathway effects on coding challenge process efficiency (active time and number of code snapshots; all $p>0.05$), a null result that is further examined through code-variability subgroup analyses. We argue that the clarification feature acts as a selective process-support mechanism: its observable value appears to lie in a shorter remediation process rather than in improved subsequent task efficiency, and this association is clearest when clarification occurs early. The findings have practical implications for the design of clarification features in AI-assisted learning systems and for instructional intervention strategies. Full article