Although existing monocular depth estimation methods have made great progress, predicting an accurate absolute depth map from a single image is still challenging due to the limited modeling capacity of networks and the scale ambiguity issue. In this paper, we introduce a fully Visual Attention-based Depth (VADepth) network, where spatial attention and channel attention are applied to all stages. By continuously extracting the dependencies of features along the spatial and channel dimensions over a long distance, VADepth network can effectively preserve important details and suppress interfering features to better perceive the scene structure for more accurate depth estimates. In addition, we utilize geometric priors to form scale constraints for scale-aware model training. Specifically, we construct a novel scale-aware loss using the distance between the camera and a plane fitted by the ground points corresponding to the pixels of the rectangular area in the bottom middle of the image. Experimental results on the KITTI dataset show that this architecture achieves the state-of-the-art performance and our method can directly output absolute depth without post-processing. Moreover, our experiments on the SeasonDepth dataset also demonstrate the robustness of our model to multiple unseen environments.

For an odd prime q and an integer m ≤ q, a binary mq × q2 quasi-cyclic parity-check matrix H(m,q) can be constructed for a class of array LDPC code C(m,q). In this letter, the closed-form formula for the numbers of minimum stopping sets of H(m,q) and minimum codewords of C(m,q) are given for 2 ≤ m ≤ 3 and for (m,q)=(4,5) and (4,7).

Electrocardiogram (ECG) signals are among the significant physiological signals that indicate the essential properties of the human body. In recent years, the measurement of ECG signals has become more portable thanks to the increasing usage of wearable health testing technology. However, the enormous amount of signal data gathered over a long period of time does impose a heavy load on medical professionals. In addition, false alarms might occur due to the potential for the detected signal to become jumbled with noise and motion perturbations. Therefore, analyzing the quality of the measured raw ECG signal automatically is a valuable task. In this paper, we propose a new single-channel ECG signal quality assessment method that combines the Resnet network structure and the principle of self-attention to extract ECG signal features using the principle of similarity between individual QRS heartbeats within a time slice of ten seconds. In addition, an improved self-attention module is introduced into the deep neural network to learn the similarity between features. Finally, the network distinguishes between acceptable and unacceptable ECG segments. The model test results indicate that the F1-score can approach 0.954, which leads to a more accurate assessment of the ECG signal quality.

Semantic segmentation is an important component in understanding the 3D point cloud scene. Whether we can effectively obtain local and global contextual information from points is of great significance in improving the performance of 3D point cloud semantic segmentation. In this paper, we propose a self-attention feature extraction module: the local transformer structure. By stacking the encoder layer composed of this structure, we can extract local features while preserving global connectivity. The structure can automatically learn each point feature from its neighborhoods and is invariant to different point orders. We designed two unique key matrices, each of which focuses on the feature similarities and geometric structure relationships between the points to generate attention weight matrices. Additionally, the cross-skip selection of neighbors is used to obtain larger receptive fields for each point without increasing the number of calculations required, and can therefore better deal with the junction between multiple objects. When the new network was verified on the S3DIS, the mean intersection over union was 69.1%, and the segmentation accuracies on the complex outdoor scene datasets Semantic3D and SemanticKITTI were 94.3% and 87.8%, respectively, which demonstrate the effectiveness of the proposed methods.

The prefixed Varshamov-Tenengolts (VT) codes, which are subsets of VT codes with predetermined prefixes, can be used for error correction over segmented edit channels. In this paper, we investigate the construction and analysis of this class of codes. First, we derive upper bounds on the size of zero-error codes for segmented edit channels with segment-by-segment decoding. Second, we establish a one-to-one correspondence between prefixed VT codes and Levenshtein codes. Based on this relation, we can obtain explicit formulas on the size of prefixed VT codes via the existing results on the size of Levenshtein codes. Third, we construct a new zero-error prefixed VT code and show that the size of the constructed code is strictly larger than that of the existing prefixed VT code for the segmented deletion channel. Finally, an efficient systematic encoding method of prefixed VT codes is proposed for the segmented edit channels.

The performance of classical channel decoding algorithms in resistive random access memory (ReRAM) channels is severely degraded due to the sneak path interference (SPI) caused by the crossbar array structure. In this letter, we first propose a sneak path-aware reliability-based iterative majority-logic decoding (SPR-IMLGD) algorithm for low-density parity-check (LDPC) codes by integrating the sneak path information into reliability metrics. In particular, we introduce the sneak path distance, derived from the associated sneak path probability, which provides a desirable characterization of the presence and extent of sneak paths within a given memory cell. Moreover, we present an enhanced version of the SPR-IMLGD algorithm (ESPR-IMLGD) that further improves the error correction performance. We also optimize the calculation of sneak path distance, ensuring that the SPR-IMLGD and ESPR-IMLGD algorithms have the same level of computational complexity. Simulation results demonstrate that the SPR-IMLGD and ESPR-IMLGD algorithms can achieve better performance with lower computational cost compared with the existing methods.