Introduction: This study—drawing upon data from a questionnaire—examined 503 Chinese university students’ metacognitive strategies in writing (MSW). The focus was on Chinese student writers who are learning English as a foreign language (EFL).Methods: The examination was conducted through a survey on MSW and a writing test administered at the end of the semester. We employed exploratory factor analysis (EFA) and confirmatory factor analysis (CFA) for data analysis. Multiple regression analysis was also adopted for understanding the predictive effects of strategies on writing performance.Results: The findings provided validity to MSW, including person, task, strategies, planning, monitoring, and evaluating. The different components of MSW were reported to significantly affect the participants’ writing performance. The findings highlight that EFL student writers were aware of metacognitive writing strategies. The MSW survey could be used to assess EFL students’ metacognitive writing strategies and develop curricula in writing strategy training.Conclusion: Writing instruction can direct learners’ ability to acquire metacognitive writing strategies, particularly those of planning, monitoring, and evaluating, to build their awareness as agents in EFL writing. Relevant pedagogical implications are discussed.
1 November 2021 in Computer Methods and Programs in Biomedicine
The ability to learn incrementally is critical to the long-term operation of AI systems. Benefiting from the power of few-shot class-incremental learning (FSCIL), deep learning models can continuously recognize new classes with only a few samples. The difficulty is that limited instances of new classes will lead to overfitting and exacerbate the catastrophic forgetting of the old classes. Most previous works alleviate the above problems by imposing strong constraints on the model structure or parameters, but ignoring embedding network transferability and classifier adaptation (CA), failing to guarantee the efficient utilization of visual features and establishing relationships between old and new classes. In this paper, we propose a simple and novel approach from two perspectives: embedding bias and classifier bias. The method learns an embedding augmented (EA) network with cross-class transfer and class-specific discriminative abilities based on self-supervised learning and modulated attention to alleviate embedding bias. Based on the adaptive incremental classifier learning scheme to realize incremental learning capability, guiding the adaptive update of prototypes and feature embeddings to alleviate classifier bias. We conduct extensive experiments on two popular natural image datasets and two medical datasets. The experiments show that our method is significantly better than the baseline and achieves state-of-the-art results.
The current intelligent auxiliary diagnosis models all follow the closed-set recognition setting. After the model is deployed online, the input data is often not completely controlled. Diagnosing an untrained disease as a known category would lead to serious medical malpractice. Therefore, realizing the open-set recognition is significant to the safe operation of the intelligent auxiliary diagnosis model. Currently, most open-set recognition models are studied for natural images, and it is very challenging to obtain clear and concise decision boundaries between known and unknown classes when applied to fine-grained medical images. We propose an open-set recognition network for medical images based on fine-grained data mixture and spatial position constraint loss (FGM-SPCL) in this work. Considering the fine graininess of medical images and the diversity of unknown samples, we propose a fine-grained data mixture (FGM) method to simulate unknown data by performing a mixing operation on known data to expand the coverage of unknown data difficulty levels. In order to obtain a concise and clear decision boundary, we propose a spatial position constraint loss (SPCL) to control the position distribution of prototypes and samples in the feature space and maximize the distance between known classes and unknown classes. We validate on a private ophthalmic OCT dataset, and extensive experiments and analyses demonstrate that FGM-SPCL outperforms state-of-the-art models.