Two-dimensional (2D) materials with reconfigurable properties show potential in neuromorphic hardware applications. However, most 2D materials-based neuromorphic hardware is volatile, which needs large energy to accomplish perception functions. Here, we report on nonvolatile floating gate photo-memory devices based on ReS2/h-BN/SnS2 van der Waals heterostructures. The devices exhibit a large memory window of ∼60 V, a high program/erase current ratio of ∼107 with excellent retention characteristics, a low off-state current of 7.4 × 10−13 A, and a high detectivity of 1.98 × 1013 cm Hz1/2 W−1, allowing for multi-bit information storage. For the multi-level storage capacity, 27 photo-memory states are obtained by pulsed laser illumination. Moreover, a neuromorphic computing network is also constructed based on the photo-memory devices with a maximum recognition accuracy of up to 90%. This work paves the way for miniaturization and high-density integration of future optoelectronics for neuromorphic hardware applications.

Medical image segmentation plays an important role in the computer-aided screening of many diseases. Different from popular deep learning-based segmentation methods that mainly focus on the whole target, recent studies pay more attention to target contour by making use of the distance transform of the object boundary. In this paper, to learn both the object content and the boundary information, we incorporate a regression task that estimates a distance map of target contour into a CNN-based segmentation network. The segmentation task and the regression task share most parts of the backbone network. Moreover, we introduce a channel information exchange module that dynamically exchanges feature maps between the segmentation and the regression tasks. The proposed information exchange module is parameter-free and controlled by the batch normalization scaling factor. In addition, the output feature maps of the two tasks are further integrated to provide fused segmentation results.We evaluate our method on three popular datasets, including the 2D ultrasound thyroid nodule segmentation dataset, the 3D MRI left atrial segmentation dataset and 2017 MM-WHS whole heart segmentation Challenge datasets. Experimental results show that our method achieves promising performance compared to the state-of-the-art approaches.

Automated analysis of long-term Holter recordings is important for efficient arrhythmia screening, but most deep learning approaches rely on raw electrocardiographic waveforms. Heart-rate scatter plots provide a compact visual representation of rhythm dynamics and may support image-based preliminary screening. In this retrospective single-centre study, we developed a deep learning framework for multi-label arrhythmia classification from Holter scatter plot images and evaluated clinically oriented label-specific thresholding. Six hundred de-identified patients, with one Holter record per patient, were included. Expert-reviewed rhythm conclusions were mapped to 15 rhythm labels for model development and evaluation. ResNet18-based models were trained using predefined scatter plot crops. The primary dual-branch model trained with weighted binary cross-entropy achieved macro-F1 = 0.738 (95% CI, 0.666–0.774), micro-F1 = 0.808 (0.777–0.838), macro-AUROC = 0.919 (0.895–0.941) and macro-AUPRC = 0.805 (0.758–0.858) using a fixed threshold of 0.5. Clinically oriented thresholds increased mean specificity from 0.844 (0.822–0.865) to 0.885 (0.860–0.909), but reduced macro-F1 to 0.693 (0.628–0.726). Strong discrimination was observed for atrial fibrillation, atrial flutter, premature atrial contraction and premature ventricular contraction. These findings suggest that scatter plot-based deep learning may provide an efficient preliminary screening approach for Holter analysis, although multicentre external validation is required before clinical implementation.

Efficient motion planning with the error tolerance is crucial for dynamic robotic tasks, particularly robotic table tennis. This task demands simultaneous high efficiency and error tolerance. First, the incoming ball’s high speed allows only tens of milliseconds for motion planning. Second, two types of errors, namely, ball-paddle motion uncertainty and joint limit violation, must be tolerated to ensure a high success rate of planning (SRP) and striking. This article proposes an advanced joint planning framework designed for high efficiency and error tolerance. To tolerate the error of ball-paddle motion uncertainty, this work introduces a joint classification criterion according to the joint motion characteristics. To tolerate the error of joint limit violation, based on the classification criterion, this study also develops a robust reference trajectory generation scheme, named error-tolerant-variable-sigmoid-based motion template (ETVSMT), to fully consider the motion capabilities of different joints. The ETVSMT approach utilizes the variable-sigmoid-based motion template (VSMT) as the backbone and designs its basic and remedial portions to tolerate the error of hard joint limit violation. The implementation of the ETVSMT scheme results in an average SRP of 98% and a ball-striking success rate of up to 90%, with execution time on an Intel Xeon CPU as low as 15 ms. Furthermore, the proposed method ensures the outgoing ball lands on the opposite side of the table with an average landing error of 19.62 cm and a net-passing height error of 12.68 cm. The proposed method can also benefit other dynamic tasks like human–robot interaction to improve the planning efficiency.

Hand gesture recognition plays an important role in computer vision with broad applications in human–computer interaction, intelligent perception, and contactless interaction systems. However, existing detection-based methods mainly rely on hand appearance features, which are often insufficient for distinguishing gesture categories with similar local hand shapes but different hand–head spatial configurations. To address this issue, a multi-scale dual-head hand gesture detection framework based on YOLOv5s is proposed. The framework introduces an auxiliary detection branch to explicitly detect hand and head regions, and the corresponding multi-scale feature representations are fused to incorporate hand–head spatial contextual information into gesture recognition. Furthermore, Spatial Pyramid Pooling (SPP) and a Convolutional Block Attention Module (CBAM) are employed to enhance multi-scale contextual representation and feature discrimination before final gesture prediction. To evaluate the proposed framework, experiments were conducted on a HaGRID-based Dataset, a UAV-Gesture Dataset, and a self-collected real-world zero-shot dataset. Experimental results demonstrate that the proposed framework consistently improves detection performance over the YOLOv5s baseline while maintaining relatively lightweight model complexity and real-time inference capability. In addition, ablation studies verify the effectiveness of the proposed dual-head architecture, multi-scale feature fusion, SPP, and CBAM, while cross-dataset and zero-shot evaluations further demonstrate the applicability of the proposed framework across different gesture datasets and unseen real-world scenarios.