HiMul-LGG: A hierarchical decision fusion-based local-global graph neural network for multimodal emotion recognition in conversation.

Emotion recognition in conversation (ERC) is a vital task that requires deciphering human emotions through analysis of contextual and multimodal information. However, extant research on ERC concentrates predominantly on investigating multimodal fusion while overlooking the model's constraints in dealing with unimodal representation discrepancy and speaker dependencies. To address the aforementioned problems, this paper proposes a Hierarchical decision fusion-based Local-Global Graph Neural Network for multimodal ERC (HiMul-LGG). HiMul-LGG employs a hierarchical decision fusion strategy to ensure feature alignment across modalities. Moreover, HiMul-LGG also adopts a local-global graph neural network architecture to reinforce inter-modality and intra-modality speaker dependency. Additionally, HiMul-LGG utilizes a cross-modal multi-head attention mechanism to promote interplay between modalities. We evaluate HiMul-LGG on two emotion recognition datasets, IEMOCAP and MELD, where HiMul-LGG outperforms existing methods. The results of the ablation study also imply the effectiveness of the proposed hierarchical decision fusion strategy and local-global structure of Graph construction.

Effects of constructing farmland with large amounts of iron tailings as soil reconstruction materials on soil properties and crop growth.

With continuous population growth and farmland decrease, the food security is seriously threatened. Farmland reclamation has been used as a means of raising the agricultural productivity and improving the ecological environment. However, the lack of reclaimed soil represents a serious problem. To verify the feasibility and effect of using large amounts of iron tailings to construct farmland, ten treatments (T1-T10) were designed to represent different soil profiles of regional normal farmland and constructed profiles using iron tailings. All treatments involving an iron tailings layer below topsoil exhibited higher soil water contents. The field capacity under T3 (20-cm iron tailings layer below cinnamon soil (b)) was 19.20% higher than that under T7 (20-cm red clay layer below cinnamon soil (b)), and the field capacity under T5 (20-cm iron tailings layer below cinnamon soil (a)) was 2.26% higher than that under T9 (20-cm red clay layer below cinnamon soil (a)). The soil water contents under T3 and T5 were almost the same as those under T7 and T9, respectively. The water-holding capacity of the 30-cm iron tailings layer (T6) was better than that of the 20-cm iron tailings layer (T2). Additionally, none of the treatments caused salt injury to maize. The maize height and stem thickness under the treatments employing iron tailings layers below topsoil were significantly greater than those in normal farmland; the maize height and stem thickness under T3 were 136.82% and 32.02% greater, respectively, than those under T7, and the values under T5 were 9.13% and 9.56% greater, respectively, than those under T9. The maize yields matched or even surpassed those in normal farmland, namely, the maize yield under T5 was equal to that under T9, and the maize yield under T3 was 12.69% higher than that under T7. In general, the application of an iron tailings layer below topsoil to construct farmland is a feasible and environmentally friendly way to realize sustainable farmland utilization and is beneficial to soil quality and crop yield improvement. Collectively, these results provide insight into the efficient utilization of iron tailings and environmental protection.

Effects of urban sprawl on arthropod communities in peri-urban farmed landscape in Shenbei New District, Shenyang, Liaoning Province, China.

Peri-urban farmland provides a diversity of ecological services. However, it is experiencing increasing pressures from urban sprawl. While the effects of land use associated with farming on arthropod assemblages has received increasing attention, most of this research has been conducted by comparing conventional and organic cropping systems. The present study identifies the effects of urban sprawl and the role of non-cropped habitat in defining arthropod diversity in peri-urban farmed landscapes. Multi-scale arthropod data from 30 sampling plots were used with linear-mixed models to elucidate the effects of distance from urban areas (0-13 km; 13-25 km and >25 km, zones I, II, and III, respectively) on arthropods. Results showed that urban sprawl, disturbed farm landscapes, and disturbance in non-cropped habitats had negative effects on arthropods, the latter requiring arthropods to re-establish annually from surrounding landscapes via dispersal. While arthropod species richness showed no obvious changes, arthropod abundance was lowest in zone II. Generally, patch density (PD), Shannon diversity index (SHDI), and aggregate index (AI) of non-cropped habitat were major drivers of changes in arthropod populations. This study contributes to identifying the effects of urban sprawl on arthropod diversity and documenting the multiple functions of farm landscapes in peri-urban regions.