Temporal Knowledge Graph (TKG) reasoning involves predicting future facts based on historical information by learning correlations between entities and relations. Recently, many models have been proposed for the TKG reasoning task. However, most existing models cannot efficiently utilize historical information, which can be summarized in two aspects: 1) Many models only consider the historical information in a fixed time range, resulting in a lack of useful information; 2) some models use all the historical facts, thus some noise or invalid facts are introduced during reasoning. In this regard, we propose a novel TKG reasoning model with dynamic memory enhancement (DyMemR). Inspired by human memory, we introduce memory capacity, memory loss, and repetition stimulation to design a human-like memory pool that could remember potentially useful historical facts. To fully leverage the memory pool, we utilize a two-stage training strategy. The first stage is guided by the memory-based encoding module which learns embeddings from memory-based subgraphs generated through the memory pool. The second stage is the memory-based scoring module that emphasizes the historical facts in the memory pool. Finally, we extensively validate the superiority of DyMemR against various state-of-the-art baselines.

Knowledge graphs (KGs) play a pivotal role in AI-related applications. In order to construct or continuously enrich KGs, automatic knowledge construction and update mechanisms are usually utilized, which inevitably bring in plenty of noise, and noise would degrade the performance of downstream applications. Existing KG error detection methods utilize the embeddings of entities and relations, or directly leverage the paths between entities to test the plausibility of triples, while ignore the valuable hierarchical information contained in the paths between entities. Indeed, the paths between a pair of entities conform to a hierarchical structure. Specifically, there may be a number of paths between two entities, and each path is comprised of several relations. The hierarchical structure is able to provide precious information, and is beneficial to leverage the path information in a fine-grained manner. To this end, in this paper, we propose a novel model named KG error detection with HiErarchical pAth stRucture (HEAR for short). Particularly, for a given triple, HEAR first learns path representations with the relations contained in the path, then integrates all path representations, and at last predicts the plausibility of the triple. Finally, we extensively validate the superiority of HEAR against various state-of-the-art baselines.

Knowledge graph embedding (KGE) aims to project both entities and relations in a knowledge graph (KG) into low-dimensional vectors. Indeed, existing KGs suffer from the data imbalance issue, i.e., entities and relations conform to a long-tail distribution, only a small portion of entities and relations occur frequently, while the vast majority of entities and relations only have a few training samples. Existing KGE methods assign equal weights to each entity and relation during the training process. Under this setting, long-tail entities and relations are not fully trained during training, leading to unreliable representations. In this paper, we propose WeightE, which attends differentially to different entities and relations. Specifically, WeightE is able to endow lower weights to frequent entities and relations, and higher weights to infrequent ones. In such manner, WeightE is capable of increasing the weights of long-tail entities and relations, and learning better representations for them. In particular, WeightE tailors bilevel optimization for the KGE task, where the inner level aims to learn reliable entity and relation embeddings, and the outer level attempts to assign appropriate weights for each entity and relation. Moreover, it is worth noting that our technique of applying weights to different entities and relations is general and flexible, which can be applied to a number of existing KGE models. Finally, we extensively validate the superiority of WeightE against various state-of-the-art baselines.

Acoustic cardiography is a completely new technology, it has great advantages in the rapid diagnosis of cardiovascular diseases. The purpose of this study was to investigate the clinical value of the fourth heart sound (S4), cardiac systolic dysfunction index (SDI), and the cardiac cycle time-corrected electromechanical activation time (EMATc) in the prediction of post-percutaneous coronary intervention (PCI) early ventricular remodeling (EVR) in patients with acute myocardial infarction (AMI). We recruited 161 patients with AMI of 72-h post-PCI, including 44 EVR patients with left ventricular ejection fraction (LVEF) < 50% and 117 Non-EVR patients (normal left ventricular systolic function group, LVEF ≥ 50%). EMATc, S4, and SDI were independent risk factors for post-PCI early ventricular remodeling in patients with AMI [S4 (OR 2.860, 95% CI 1.297–6.306, p = 0.009), SDI (OR 4.068, 95% CI 1.800–9.194, p = 0.001), and EMATc (OR 1.928, 95% CI 1.420–2.619, p < 0.001)]. The area under the receiver operating characteristic curve for EMATc was 0.89, with an optimal cutoff point of 12.2, EMATc had a sensitivity of 80% and a specificity of 83%. By contrast, an optimal cutoff point of 100 pg/ml, Serum brain natriuretic peptide had a sensitivity of 46% and a specificity of 83%. Our findings suggest the predictive value of EMATc for the occurrence of EVR in these patients was also identified; EMATc may be a simple, quick, and effective way to diagnose EVR after AMI.

Knowledge Graph (KG) has proven its effectiveness in recommendation systems. Recent knowledge-aware recommendation methods, which utilize graph neural networks and contrastive learning, underestimate two issues: 1) The neglect of modeling the latent relationships between users and entities; 2) The insufficiency of traditional cross-view contrastive learning whose domain is incapable of covering all nodes in a graph. To address these issues, we propose a novel model named Knowledge-aware User Preference Network (KUPN). Specifically, KUPN first constructs the relational preference view containing a new graph named User Preference Graph (UPG) to model the potential relationships between users and entities. Then, we adopt a novel attentive information aggregation to learn the UPG. In addition, we obtain semantic information of users and entities from collaborative knowledge view which consists of KG and Interaction Graph (IG) as supplementary. Finally, we apply a cross-view contrastive learning for complete domains between dynamic relational preference view and collaborative knowledge view. Extensive experiments on three real-world datasets demonstrate the superiority of KUPN against the state-of-the-art methods.

This thesis investigates a novel solar‐assisted heat pump integrated phase change energy storage system. The defrosting performance of this system was studied experimentally and the results were compared with two traditionally used methods: reverse cycle defrosting (RCD) method and hot gas bypass defrosting (HGBD) method. The results show that the phase change energy storage system has superior performance compared with traditional defrosting methods. The indoor temperature drop recorded was relatively small and the defrosting time was 75% of the RCD system and 53% of HGBD system. The phase change energy storage system increased the condensation temperature which consequently increased the temperature difference of heat transfer resulting in higher conductivity in the defrosting progress. Compared with the method of RCD and the method of HGBD, the recovery time of the system was shortened by 90 and 160 seconds, respectively. The system works with low‐temperature heat source and circulating water, which considerably reduces energy consumption, thereby improving the performance of the defrosting system. A further experimental study was also conducted on the heating performance and the results also indicated that the value of COP can reach up to 3.6 in daytime, and the indoor temperature can be stably maintained above 18°C throughout the day. Novelty Statement A new defrosting method for energy storage defrosting is proposed, and the defrosting performance is compared with two common defrosting methods. In addition, the performances of the heating system over the day were experimentally investigated. The experimental results show the system meets the heating needs of the building. Finally, the influence of the outdoor temperature on the exergy efficiency of the system was discussed. It shows that this system can improve the operational stability, the system economy and energy saving.