The early detection of Alzheimer’s disease (AD) in cognitively healthy individuals remains a major preclinical challenge. EEG is a promising tool that has shown effectiveness in detecting AD risk. Task-related EEG has been rarely used in Alzheimer’s disease research, as most studies have focused on resting-state EEG. An interpretable deep learning framework—Interpretable Convolutional Neural Network (InterpretableCNN)—was utilized to identify AD-related EEG features. EEG data were recorded during three cognitive task conditions, and samples were labeled based on APOE genotype and polygenic risk scores. A 100-fold leave-p%-subjects-out cross-validation (LPSO-CV) was used to evaluate model performance and generalizability. The model achieved an ROC AUC of 60.84% across the tasks and subjects, with a Kappa value of 0.22, indicating fair agreement. Interpretation revealed a consistent focus on theta and alpha activity in the parietal and temporal regions—areas commonly associated with AD pathology. Task-related EEG combined with interpretable deep learning can reveal early AD risk signatures in healthy individuals. InterpretableCNN enhances transparency in feature identification, offering a valuable tool for preclinical screening.

Traditional manual concrete vibration work faces numerous limitations, necessitating the need for efficient automated methods to support this task. This study proposes a path safety optimization method based on safe flight corridors and Euclidean signed distance fields, which is suitable for flexible autonomous movement of vibrating robots between various vibration points. By utilizing a vector method to generate safe flight corridors and optimizing the path with Euclidean signed distance fields, the proposed method reduces the runtime by 80% compared to the original safe flight corridor method and enhances safety by 50%. On embedded systems, the runtime is less than 10 ms. This study is the first to apply the combination of safe flight corridors and Euclidean distance fields for autonomous navigation in concrete vibration tasks, optimizing the original path into a smooth trajectory that stays clear of obstacles. Actual tests of the vibrating robot showed that, compared to traditional methods, the algorithm allows the robot to safely avoid fixed obstacles and moving workers, increasing the execution efficiency of vibration tasks by 60%. Additionally, on-site experiments conducted at three construction sites demonstrated the robustness of the proposed method. The findings of this study advance the automation of concrete vibration work and hold significant implications for the fields of robotics and civil engineering.

3D scanning, measurement, and reconstruction have wide-ranging applications in industrial fields, medical devices, and cultural heritage preservation. This study focuses on the field of 3D measurement and reconstruction, proposing a dual-degree-of-freedom layer-by-layer 3D scanner based on the principle of optical reflection. The scanner employs a laser range sensor to perform layered scanning through a linear motion guide and a translational-rotary platform driven by stepper motors. To improve the computational efficiency of the ICP algorithm, the Newton iteration method is employed to apply global rotation and translation to the sampled point cloud, optimizing the accuracy of point cloud registration. The scanned objects are categorized into three types based on whether the surfaces of their spatial geometries are second-order differentiable. The final matching results show an RMSE range of 0.2–0.7 and a residual variance range of 0.02–0.31, indicating that the RMSE meets the requirements of 3D reconstruction according to international standards. Experimental results demonstrate that the proposed 3D scanner achieves high-precision scanning and reconstruction capabilities, and the surface characteristics of the scanned objects significantly influence the measurement results. The analysis of error distribution provides theoretical guidance for further optimizing device performance and algorithm accuracy.

Accurate measurement and characterization of geometry-dependent forming errors are essential for closed-loop knead forming deformation manufacturing. To improve the forming accuracy under volume conservation, a maximal inscribed constraint-driven radial expansion method (MIC-REM) is proposed for stable shape mapping and geometric compensation. Repeatability and closed-loop compensation experiments were conducted for five representative geometries based on point cloud registration and RMSE evaluation. The results show that the forming error exhibits good repeatability and is mainly dominated by systematic factors rather than random fluctuations. The proposed compensation method reduces geometric errors by 35%--72%, while its effectiveness shows clear geometry dependence, with limited improvement for geometries involving localized large deformation. Further analysis reveals that the forming error is strongly correlated with layer-wise deformation behavior. A process-constrained geometry-dependent error model is established, representing the layer-wise error as a quadratic function of cross-sectional deformation. Under identical process conditions, the model provides a unified formulation across different geometries through parameter variations. This study provides a unified framework for geometric error measurement, modeling, and closed-loop compensation in knead forming, and reveals the geometry-dependent mechanism of forming error.