Search

Accurate prediction of future events brings great benefits and reduces losses for society in many domains, such as civil unrest, pandemics, and crimes. Knowledge graph is a general language for describing and modeling complex systems. Different types of events continually occur, which are often related to historical and concurrent events. In this paper, we formalize the future event prediction as a temporal knowledge graph reasoning problem. Most existing studies either conduct reasoning on static knowledge graphs or assume knowledges graphs of all timestamps are available during the training process. As a result, they cannot effectively reason over temporal knowledge graphs and predict events happening in the future. To address this problem, some recent works learn to infer future events based on historical event-based temporal knowledge graphs. However, these methods do not comprehensively consider the latent patterns and influences behind historical events and concurrent events simultaneously. This paper proposes a new graph representation learning model, namely Recurrent Event Graph ATtention Network (RE-GAT), based on a novel historical and concurrent events attention-aware mechanism by modeling the event knowledge graph sequence recurrently. More specifically, our RE-GAT uses an attention-based historical events embedding module to encode past events, and employs an attentionbased concurrent events embedding module to model the associations of events at the same timestamp. A translation-based decoder module and a learning objective are developed to optimize the embeddings of entities and relations. We evaluate our proposed method on four benchmark datasets. Extensive experimental results demonstrate the superiority of our RE-GAT model comparing to various baselines, which proves that our method can more accurately predict what events are going to happen. [ABSTRACT FROM AUTHOR]

The shortage of water resources promotes the development of water saving irrigation in arid land. Regulated deficit irrigation (RDI), as one of the water-saving irrigation technologies through applying a certain amount of water stress to the crops to promote the distribution of the photosynthate of crops to the needs of the tissues and organs, can save water and may increase yield. Our study evaluated the effect of the RDI on the sugar beet (Beta vulgaris L. cv. Beta356). Seven irrigation treatments were applied based on the growth stages of sugar beet (canopy development, storage root development, and sugar accumulation) and water deficit levels (30, 50, and 70% of field capacity [FC]). The yield, quality, sugar yield, irrigation water use efficiency (IWUE), and agronomic physiological traits of sugar beet were evaluated. Moderate water deficit (50% of FC) during canopy development increased sugar yield by 27% compared with the control (70% of FC during the whole growth stages). Severe (30% of FC) water deficit increased sugar yield by 45% during storage root development, and by 55% during sugar accumulation. The RDI during canopy development and storage root development inhibited leaf growth but did not affect yield. Malondialdehyde content and relative conductivity increased significantly when soil water content dropped to the irrigation threshold levels (i.e., 30% and 50% of FC) before rehydration during canopy development. After rehydration, there were significant increases in peroxidase activity and proline content (indicators of antioxidant defense and osmotic stress). Our results indicated that RDI increased yield at 30% and 50% of FC during three growth stages (canopy development, storage root development, and sugar accumulation) of sugar beet, which reduced irrigation water requirements. RDI could be applied as a strategic action for crop sustainability and water saving in arid land. [ABSTRACT FROM AUTHOR]

Compressed sensing (CS) is a new theory. With regard to the sparse signal, an exact reconstruction can be obtained with sufficient CS measurements. Nevertheless, in practical applications, the transform coefficients of many signals usually have weak sparsity and suffer from a variety of noise disturbances. What's worse, most existing classical algorithms are not able to effectively solve this issue. So we proposed an efficient algorithm based on smoothed ℓ0 norm for sparse signal reconstruction. The direct ℓ0 norm problem is NP hard, but it is unrealistic to directly solve the ℓ0 norm problem for the reconstruction of the sparse signal. To select a suitable sequence of smoothed function and solve the ℓ0 norm optimization problem effectively, we come up with a generalized approximate function model as the objective function to calculate the original signal. The proposed model preserves sharper edges, which is better than any other existing norm based algorithm. As a result, following this model, extensive simulations show that the proposed algorithm is superior to the similar algorithms used for solving the same problem. [ABSTRACT FROM AUTHOR]

Nanoparticles of the CeO2-ZrO2-La2O3 solid solution were prepared by the W/O microemulsion method. Ceria-zirconia-lanthana (Ce/Zr/La = 1/1/0.06, mol) sample calcined at 1000 °C for 4 h has higher surface area (126 m²/g) and excellent thermal stability. Its particle size is 5-10nm. The presence of lanthana in the sample can improve obviously the thermal stability of the CeO2-ZrO2 solid solution. [ABSTRACT FROM AUTHOR]