Search Results (2)

We present a novel deep learning framework for high-resolution semantic segmentation, designed to interpret complex visual environments such as cities, rural areas, and natural landscapes. Our method integrates conic geometric embeddings, which is a mathematical approach for capturing spatial relationships, with belief-aware learning, a strategy that adapts model predictions when input data are uncertain or change over time. A multi-scale refinement process further improves boundary accuracy and detail preservation. The proposed model, built on a hybrid Vision Transformer (ViT) backbone and trained end-to-end using adaptive optimization, is evaluated on four benchmark datasets including EDEN, OpenEarthMap, Cityscapes, and iSAID. It achieves 88.94% Accuracy and $R^2$ of 0.859 on EDEN, while surpassing 85.3% Accuracy on Cityscapes. Ablation studies demonstrate that removing Conic Output Embeddings causes drops in Accuracy of up to 2.77% and increases in RMSE, emphasizing their contribution to frequency-aware generalization across diverse conditions. On OpenEarthMap, our model achieves a mean IoU of 73.21%, outperforming previous baselines by 2.9%, and on iSAID, it reaches 80.75% mIoU with improved boundary adherence. Beyond technical performance, the framework enables practical applications such as automated landscape analysis, urban growth monitoring, and sustainable environmental planning. Its consistent results across three independent runs demonstrate both robustness and reproducibility, offering a reliable tool for large-scale geospatial and environmental modeling. Full article

Melt turbulence during mold filling is detrimental to the quality of sand castings. In this research study, the authors present a novel method of embedding Internet of Things (IoT) sensors to monitor real-time melt flow velocity in sand molds during metal casting. Cavities are incorporated in sand molds to position the sensors with precise registration. Capacitive and magnetic sensors are embedded in the cavities where melt flow velocity is calculated by using an oscillator, the frequency of which is sensitive to changes in the close field permittivity, and change in magnetic flux, respectively. Their efficiency is investigated by integrating the sensors into 3D sand-printing (3DSP) molds for conical-helix and straight sprue configurations to measure flow velocities for aluminum alloy 319. Experimental melt flow velocities are within 5% of estimations from computational simulations. A major benefit of 3DSP is the geometrical freedom for complex gating systems necessary to reduce turbulence and access to mold volume for sensor integration during 3DSP processing. Findings from this study establish the opportunity of embedding IoT sensors in sand molds to monitor metal velocity in order to validate simulation results (2–5% error), compare gating systems performance, and improve foundry practice of manual pouring as a quality control system. Full article