Two-Way Concept-Cognitive Learning via Concept Movement Viewpoint

Xu, Weihua; Guo, Doudou; Qian, Yuhua; Zheng, Keyin; Ding, Weiping

doi:10.1109/tnnls.2023.3235800

Cited by 49 publications

(2 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In a critical period of rural revitalization, this work has important theoretical implications and practical significance that allows for the exploration of issues around sustainable development. This paper uses cognitive learning theory [21] to define social responsibility for family grain farmers and explores sustainable development from the perspective of social functions.…”

Section: Introductionmentioning

confidence: 99%

Perceptions of Social Responsibility, Resource Integration Ability and Sustainable Development of Family Grain Farms – Evidence from China

Duan,

Luo

2023

Pol. J. Environ. Stud.

View full text Add to dashboard Cite

The purpose of this paper is to analyze the influencing factors of sustainable development of family grain farms in China. According to related investigation, there is a real problem of lack of social responsibility of grain family farms in China, which restricts their sustainable development. Therefore, based on a sample of 301 family grain farms in China, this paper used multi-classification ordered logit model and mediation effect model to investigate the relationship between perceptions of social responsibility, resource integration ability, and sustainable development of family grain farms. Various studies show that stronger perceptions of social responsibility related to more sustainable development; greater resource integration ability related to more sustainable development; and resource integration ability mediated the relationships between perceptions of social responsibility and sustainable development. Conclusions suggest that improving perceptions of social responsibility, increasing support for improving resource integration ability and giving full play to the mediating role of resource integration ability is needed to bolster the sustainable development of family grain farms.

show abstract

Section: Introductionmentioning

confidence: 99%

Perceptions of Social Responsibility, Resource Integration Ability and Sustainable Development of Family Grain Farms – Evidence from China

Duan,

Luo

2023

Pol. J. Environ. Stud.

View full text Add to dashboard Cite

show abstract

“…Concretely, FCA is often considered as a very useful method for CL by organizing different concepts with the relationships of generalization and specialization [14]. Based on FCA, numerous related learning algorithms were proposed to meet different requirements, such as an automatic ontology generation method for ontology construction [37], social networks [38], [39], two-way CCL [40], and fuzzy CL model for concept generation [19]. However, it is a very time-consuming process to construct a concept lattice from a given information system due to the number of concepts in the structure growing constantly and exponentially, which means that it is unfeasible to employ FCA directly for CL.…”

Section: Introductionmentioning

confidence: 99%

Stream Concept-cognitive Computing System for Streaming Data Learning

2023

Preprint

View full text Add to dashboard Cite

People can often acquire knowledge dynamically and rapidly from different types of data, yet existing incremental learning algorithms are still computationally time consuming and most of stream learning methods are mainly designed for streaming data while ignoring other types of data. Hence, this paper proposes a novel dynamic concept learning (CL) algorithm by imitating human cognitive learning processes from the perspective of brain logical cognition, which is named stream concept-cognitive computing system (streamC3S). For streamC3S, it mainly consists of three aspects: the concept space, CL process, and model update process. Moreover, considering the concept drift frequently occurs in the streaming data over time, an extended version of streamC3S (namely, streamC3SE) is also proposed in this work. Specifically, we first show the related theories for streamC3S and streamC3SE on the basis of the concept space. Then an overall framework and its corresponding algorithm are shown. Finally, experimental results on various types of datasets, including the standard machine learning datasets, streaming datasets, image datasets, and two traffic data streams, validate the effectiveness of our streamC3S and streamC3SE compared to the state-of-the-art incremental learning and stream learning algorithms.

show abstract