Electrocardiogram (ECG) signals have wide-ranging applications in various fields, and thus it is crucial to identify clean ECG signals under different sensors and collection scenarios. Despite the availability of a variety of deep learning algorithms for ECG quality assessment, these methods still lack generalization across different datasets, hindering their widespread use. In this paper, an effective model named Swin Denoising AutoEncoder (SwinDAE) is proposed. Specifically, SwinDAE uses a DAE as the basic architecture, and incorporates a 1D Swin Transformer during the feature learning stage of the encoder and decoder. SwinDAE was first pre-trained on the public PTB-XL dataset after data augmentation, with the supervision of signal reconstruction loss and quality assessment loss. Specially, the waveform component localization loss is proposed in this paper and used for joint supervision, guiding the model to learn key information of signals. The model was then fine-tuned on the finely annotated BUT QDB dataset for quality assessment. SwinDAE achieved 0.02-0.13 mean F1 score improvement on the BUT QDB dataset compared to multiple deep learning methods, and demonstrated applicability on two other datasets. The proposed SwinDAE shows strong generalization ability on different datasets, and surpasses other state-of-the-art deep learning methods on multiple evaluation metrics. In addition, the statistical analysis for SwinDAE prove the significance of the performance and the rationality of the prediction. SwinDAE can learn the commonality between high-quality ECG signals, exhibiting excellent performance in the application of cross-sensors and cross-collection scenarios.

As one of the fundamental sectors to measure the carbon emission levels in a certain region, building carbon emission plays an important role in determining low-carbon development plans. Most of the carbon emission estimation research mainly focuses on the establishment of bottom-up GHG inventory and the implication of policy-driven approaches, there are still many theoretical gaps in the usage of remote sensing data to predict building carbon emission. This paper presents a comprehensive study to discuss the performance of different regression models using various open nighttime light (NTL) data sources. The Noord Brabant province was employed as a case study to verify the feasibility of using different estimation models at various spatial scales (city-level, district-level, and neighborhood-level). Among all regression models, the geographically weighted regression (GWR) has been proven to better reflect the relationship between building carbon emissions and the NTL index. For practical applications, the carbon intensity (CI) and annual nighttime light index (ANLI) are a pair of optimal sets to establish a reliable estimation model. It exhibits higher utility value at the city-level due to the fewer interferences caused by non-building lighting sources. The results of this comparative study provide a new reference to support the establishment of carbon inventory. By illustrating the differences among various estimation models, the applicable scope of using open remote sensing data to estimate building carbon emissions can be further defined. The conclusion may provide more detailed instructions during the process of developing low-carbon cities.

Existing topic models that aim to discover relationships between topics typically focus on two types of relations: undirected correlation and hierarchy with a tree structure. However, these approaches are limited in their ability to capture complicated dependencies between topics, such as causality, where topics may depend on multiple other topics. To address this limitation, we propose a novel Dependency-Aware Neural Topic Model (DepNTM). This model takes the dependency relationships between topics as a generative process, where each topic is generated by other topics based on their dependencies. Specifically, we utilize a Structural Causal Model within a variational autoencoder (VAE) framework to learn the topic dependencies in a Directed Acyclic Graph (DAG). To further map the latent topics with comprehensible semantic information and ensure interpretability, we use labels of documents as the supervision signal. We conduct experiments on two public real-world corpora from the arXiv system and Stack Overflow website. The experimental results show that DepNTM outperforms nine state-of-the-art (SOTA) topic models in terms of perplexity (reduced by 9% on avg. vs. SOTA baselines), topic quality (improved by 58%) in most cases. We further conduct abundant analytical experiments to demonstrate the reliability of DepNTM.

Maintenance and production scheduling are interactive activities that should be considered simultaneously to maintain production systems’ reliability and high production delivery rate. This study investigates a problem of joint maintenance and production scheduling in a multi-stage hybrid flow shop experiencing machine deterioration processes. To address the structural dependency among production stages and machines, a decentralized partially observable Markov decision process (Dec-POMDP) is considered. However, the large state and action space pose a challenge for existing reinforcement learning methods to provide satisfactory solutions. To overcome this problem, the study proposes a counterfactual attention multi-agent reinforcement learning (CAMARL) solution framework that comprises three functional modules: The attention mechanism module, which adaptively shrinks the dimension of the state space; the action abstraction representation module that deals with the high-dimension of the action space; and the coordination control unit, which accelerates the exploration for the optimal production policy. Numerical experiments demonstrate the effectiveness of the proposed method by comparing it with seven benchmarks under different production scenarios.