Search Results (6)

Fine-grained insect pest classification presents a particularly demanding visual recognition challenge due to severe class imbalance, pronounced intra-class morphological variability across developmental stages, and high inter-class visual similarity among taxonomically related species. Existing deep learning approaches typically rely on a single feature representation extracted from a single network depth, overlooking complementary discriminative cues distributed across multiple abstraction levels. Furthermore, classical attention mechanisms perform spatial weighting deterministically, without explicitly modeling the underlying statistical structure of the feature space, which is inherently multimodal on long-tailed benchmarks such as IP102. This study proposes a Multi-Scale Gaussian Mixture Model-Gated Mixture of Experts (GMM-MoE) architecture that operates as a plug-in module insertable into any convolutional backbone, evaluated here on DenseNet-121 at three distinct feature depths. The proposed module computes analytic GMM posterior responsibilities in closed form, softly assigning each spatial location to dedicated convolutional expert sub-networks. At the same time, a conditional prior mechanism π(x) adapts the routing strategy to individual image content rather than relying on fixed priors. The architecture is evaluated on the IP102 benchmark (102 pest classes, ~75,000 images) under a two-stage training protocol. Ablation experiments confirm that increasing the number of experts consistently improves accuracy across all three routing depths, and that multi-scale fusion surpasses any single-scale configuration. The proposed model achieves a mean top-1 accuracy of 74.12% (±0.25%, 95% CI) across three independent runs on the IP102 test set. To the best of our knowledge, this is the first work to employ GMM posterior responsibilities as a spatial routing mechanism within a multi-scale CNN feature hierarchy for fine-grained insect pest classification, establishing a principled probabilistic alternative to deterministic attention weighting in visual recognition systems. Full article

Modeling contextual relationships among key features is crucial for improving object detection, yet existing relation-based methods rely on fixed feature selection and shared transformations, limiting their ability to capture diverse feature interactions in complex scenes. To address this, we propose MoE-RelationNet++, a relation enhancement framework based on a Mixture-of-Experts (MoE) mechanism. Unlike fixed selection and shared transformations, the proposed MoE enhancement module adopts a conditional computation paradigm: a dynamic router adaptively assigns features to specialized experts, enabling heterogeneous relationship modeling and overcoming the representational bottlenecks inherent in traditional shared mappings. Furthermore, to alleviate its computational burden and reduce redundant inputs, a lightweight key selector using depthwise separable convolution is introduced to adaptively identify informative features. To ensure robust relation modeling and prevent noisy or unreliable feature interactions from degrading the experts, an energy verification mechanism is employed to evaluate feature reliability and refine the overall process. Extensive experiments on MS COCO show consistent improvements across multiple detectors, increasing AP by 4.2, 3.2, 3.3, and 3.1 points for RetinaNet, FCOS, ATSS, and Faster R-CNN, respectively. Additionally, the method achieves a 1.5 AP gain on the VisDrone-DET2019 benchmark. These results demonstrate that MoE-RelationNet++ effectively captures heterogeneous relations via conditional expert routing, overcoming the representational limitations of fixed transformations. Moreover, it can be seamlessly integrated into various detection frameworks as an add-on enhancement module, consistently improving their performance without modifying the base architecture. Full article

Bundle recommendation has gained significant attention, but it faces two key challenges: sparse interaction data and complex UB, UI, and BI relations. Recent work uses multi-view contrastive learning, yet current frameworks rely on fixed-weight fusion that ignores view-specific importance and suffers from gradient suppression on sparse data. We propose TriadCBR, a tri-view adaptive contrastive learning architecture for bundle recommendation. It uses a simplified GCN to learn view-specific representations and a Mixture-of-Experts (MoE) module to generate personalized fusion weights, addressing the limitations of fixed-weight fusion. TriadCBR further incorporates a fine-grained contrastive module integrating InfoNCE, DCL, and Barlow Twins. This combination effectively mitigates gradient vanishing from invalid negatives and minimizes cross-view feature redundancy. To handle data sparsity, we design a Difficulty-Aware BPR (DA-BPR) with curriculum augmentation to dynamically refine the ranking trajectory. Extensive experiments on Youshu, iFashion, and NetEase demonstrate that TriadCBR achieves statistically significant improvements, boosting Recall and NDCG by an average of 3.61%, with 9 of 12 metric–dataset combinations reaching statistical significance, over state-of-the-art baselines, validating the robustness of its dynamic fusion and adaptive optimization. Full article

Traditional lie detection technologies, such as the polygraph and event-related potential (ERP)-based approaches, often face limitations in real-world applicability due to their sensitivity to psychological states and the complex, nonlinear nature of electroencephalogram (EEG) signals. In this study, we propose SparseMambaNet, a novel neural architecture that integrates the recently developed Bi-Mamba model with a Sparsely Activated Mixture of Experts (MoE) structure to effectively model the intricate spatio-temporal dynamics of EEG data. By leveraging the near-linear computational complexity of Mamba and the bidirectional contextual modeling of Bi-Mamba, the proposed framework efficiently processes long EEG sequences while maximizing representational power through the selective activation of expert networks tailored to diverse input characteristics. Experiments were conducted with 46 healthy subjects using a simulated criminal scenario based on the Comparison Question Technique (CQT) with monetary incentives to induce realistic psychological tension. We extracted nine statistical and neural complexity features, including Hjorth parameters, Sample Entropy, and Spectral Entropy. The results demonstrated that Sample entropy and Hjorth parameters achieved exceptional classification performance, recording F1 scores of 0.9963 and 0.9935, respectively. Statistical analyses further revealed that the post-response “answer” interval provided significantly higher discriminative power compared to the “question” interval. Furthermore, channel-level analysis identified core neural loci for deception in the frontal and fronto-central regions, specifically at channels E54 and E63. These findings suggest that SparseMambaNet offers a highly efficient and precise solution for EEG-based lie detection, providing a robust foundation for the development of personalized brain–computer interface (BCI) systems in forensic and clinical settings. Full article

The goal of the present study was to use machine learning to identify how gender, age, ethnicity, screen time, internalizing problems, self-regulation, and FoMO were related to problematic smartphone use in a sample of Canadian adolescents during the COVID-19 pandemic. Participants were N = 2527 (1269 boys; M_age = 15.17 years, SD = 1.48 years) high school students from the Lower Mainland of British Columbia, Canada. Data on problematic smartphone use, screen time, internalizing problems (e.g., depression, anxiety, and stress), self-regulation, and FoMO were collected via an online questionnaire. Several different machine learning algorithms were used to train the statistical model of predictive variables in predicting problematic smartphone use. The results indicated that Shrinkage algorithms (lasso, ridge, and elastic net regression) performed better than other algorithms. Moreover, FoMO, emotional, and cognitive self-regulation made the largest relative contribution to predicting problematic smartphone use. These findings highlight the importance of FoMO and self-regulation in understanding problematic smartphone use. Full article

The results of microstructure and mechanical properties evaluation of a Stellite 6 (Co-6) alloy deposited on X22CrMoV12-1 substrate by the laser-engineered net shaping (LENS^TM) technology are presented in this paper. The Stellite 6 alloy is widely used in industry due to its excellent wear resistance at elevated temperatures and corrosive environments. Specific properties of this alloy are useful in many applications, e.g., as protective coatings in steam turbine components. In this area, the main problems are related to the fabrication of coatings on complex-shaped parts, the low metallurgical quality of obtained coatings, and its insufficient adhesion to a substrate. The results of recently performed investigations proved that the LENS technology is one of the most effective manufacturing techniques of the Co-6 alloy coatings (especially deposited on complex-shaped turbine parts). The microstructural and phase analyses of obtained Stellite 6 coatings were carried out by light microscopy techniques and X-ray diffraction analysis. A chemical homogeneity of Co-6 based layers and a fluctuation of chemical composition in coating–substrate zone after the laser deposition were analyzed using an energy dispersive X-ray spectrometer coupled with scanning electron microscopy. The room temperature strength and ductility of the LENS processed layers were determined in static bending tests. Full article