To confront college students’ new reading patterns and the continuous decline in academic library borrowing rates, we conducted empirical research on promoting multisensory reading as a way to attract students’ attention, and to stimulate interest in, and promote the practice of, reading through a library program called “Reading Today Listening Everyday” (RTLE) on a library’s WeChat public account. The program involved 48 librarians and 105 students who were recruited into different groups to co-create, edit and release multisensory tweets every workday. Multisensory contents including text-based content, audio-based content and emotional resonance were presented to evoke readers’ visual, audio, and emotional senses to induce more reading practice. Using the Context, Input, Process and Product (CIPP) evaluation method, the multisensory presentation in RTLE program was proven to be effective in promoting library reading with a high number of tweeted page views and an increased borrowing rate for recommended books. In 2020, 269 issues accompanied by 269 audio frequencies garnered 80,268 page views, depending on the caliber of the reading promoter out of the 48 librarians and 52 student anchors behind it. The 484 RTLE-recommended books were borrowed 113 times in 2020, which was a rate 1.46 times higher than in 2019 (77 times). The analysis of the relationship between tweet views and borrowing rates for recommended books indicates that more page views indicate greater reader interest, leading to increased borrowing. From readers’ feedback and comments, the gain afforded by multisensory reading can improve higher-level reading trends such as the number of reading interests, enjoyment, engagement, etc.
Corneal ulcer is the most common symptom of corneal disease, which is one of the main causes of corneal blindness. The accurate classification of corneal ulcer has important clinical importance for the diagnosis and treatment of the disease. To achieve this, we propose a deep learning method based on multi-scale information fusion and label smoothing strategy. Firstly, the proposed method utilizes the densely connected network (DenseNet121) as backbone for feature extraction. Secondly, to fully integrate the shallow local information and the deep global information and improve the classification accuracy, we develop a multi-scale information fusion network (MIF-Net), which uses multi-scale information for joint learning. Finally, to reduce the influence of the inter-class similarity and intra-class diversity on the feature representation, the learning strategy of label smoothing is introduced. Compared with other state-of-the-art classification networks, the proposed MIF-Net with label smoothing achieves high classification performance, which reaches 87.07 and 83.84% for weighted-average recall (W_R) on the general ulcer pattern and specific ulcer pattern, respectively. The proposed method holds promise for corneal ulcer classification in fluorescein staining slit lamp images, which can assist ophthalmologists in the objective and accurate diagnosis of corneal ulcer.
Frontiers in Neuroscience
Causal Self-Supervised Learning in AI: Advancing Perception Science