The uncertainty measurement of classified results is especially important in areas requiring limited human resources for higher accuracy. For instance, data-driven algorithms diagnosing diseases need accurate uncertainty score to decide whether additional but limited quantity of experts are needed for rectification. However, few uncertainty models focus on improving the performance of text classification where human resources are involved. To achieve this, we aim at generating accurate uncertainty score by improving the confidence of winning scores. Thus, a model called MSD, which includes three independent components as "mix-up", "self-ensembling", "distinctiveness score", is proposed to improve the accuracy of uncertainty score by reducing the effect of overconfidence of winning score and considering the impact of different categories of uncertainty simultaneously. MSD can be applied with different Deep Neural Networks. Extensive experiments with ablation setting are conducted on four real-world datasets, on which, competitive results are obtained.
Traffic prediction is a challenging task due to the time-varying nature of traffic patterns and the complex spatial dependency of road networks. Adding to the challenge, there are a number of errors introduced in traffic sensor reporting, including bias and noise. However, most of the previous works treat the sensor observations as exact measures ignoring the effect of unknown noise. To model the spatial and temporal dependencies, existing studies combine graph neural networks (GNNs) with other deep learning techniques but their equal weighting of different dependencies limits the models' ability to capture the real dynamics in the traffic network. To deal with the above issues, we propose a novel deep learning framework called Deep Kalman Filtering Network (DKFN) to forecast the network-wide traffic state by modeling the self and neighbor dependencies as two streams, and their predictions are fused under the statistical theory and optimized through the Kalman filtering network. First, the reliability of each stream is evaluated using variances. Then, the Kalman filter is leveraged to properly fuse noisy observations in terms of their reliability. Experimental results reflect the superiority of the proposed method over baseline models on two real-world traffic datasets in the speed prediction task.
Research highlights: Ecological policies must balance ecosystem protection by promoting the sustainable livelihoods of farmers living in or near protected areas; however, the intrinsic motivations of farmers to adopt green production behaviors (GPBs) are poorly understood. Background and objectives: We explored how ecological policies affect the GPBs of farmers in agroforestry. Materials and methods: We conducted questionnaires of farmers in 11 counties of Sichuan Province, China, with abundant protected areas and large-scale agroforestry, after which a structural equation model of farmers’ ecological awareness, policy perception, and GPBs was constructed. Results: (1) Ecological policies can stimulate farmers’ GPBs by improving their ecological awareness, creating positive subjective norms, and inducing the “herd effect”. Increases in protection intensity and scope amplify the pressures on farmers to maintain more than long-term policy consistency. (2) Green production is more time-consuming, laborious, expensive, and difficult to learn compared with traditional production methods, which have somewhat limited GPBs adoption. (3) In the rural “acquaintance society”, information and communication from others have a substantial impact on farmers’ perceptions, attitudes, and behaviors; thus, positive subjective norms from formal and informal channels could promote GPB adoption. Conclusions: Future policies should prioritize environmental education over environmental publicity by helping farmers understand the long-term relationship between ecological protection and economic development, teaching individual environmental responsibility, enhancing positive feedback to farmers who adopt GPBs, actively exploring mechanisms for realizing the value of ecological products, and improving farmers’ management skills and learning ability.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.