김예진 교수

Sparseness of user-to-item rating data is one of the major factors that deteriorate the quality of recommender system. To handle the sparsity problem, several recommendation techniques have been proposed that additionally consider auxiliary information to improve rating prediction accuracy. In particular, when rating data is sparse, document modeling-based approaches have improved the accuracy by additionally utilizing textual data such as reviews, abstracts, or synopses. However, due to the inh

The purpose of this study was to identify personality factor-associated predictors of smartphone addiction predisposition (SAP). Participants were 2,573 men and 2,281 women (n = 4,854) aged 20-49 years (Mean ± SD: 33.47 ± 7.52); participants completed the following questionnaires: the Korean Smartphone Addiction Proneness Scale (K-SAPS) for adults, the Behavioral Inhibition System/Behavioral Activation System questionnaire (BIS/BAS), the Dickman Dysfunctional Impulsivity Instrument (DDII), and t

L-ascorbic acid (vitamin C) is one of the well-known anti-viral agents, especially to influenza virus. Since the in vivo anti-viral effect is still controversial, we investigated whether vitamin C could regulate influenza virus infection in vivo by using Gulo (-/-) mice, which cannot synthesize vitamin C like humans. First, we found that vitamin C-insufficient Gulo (-/-) mice expired within 1 week after intranasal inoculation of influenza virus (H3N2/Hongkong). Viral titers in the lung of vitami

Tensor factorization models offer an effective approach to convert massive electronic health records into meaningful clinical concepts (phenotypes) for data analysis. These models need a large amount of diverse samples to avoid population bias. An open challenge is how to derive phenotypes jointly across multiple hospitals, in which direct patient-level data sharing is not possible (e.g., due to institutional policies). In this paper, we developed a novel solution to enable federated tensor fact

These findings indicate that β-sitosterol ameliorates HFD-induced colitis by inhibiting the binding of LPS to toll-like receptor 4 in the NF-κB pathway.

Biopolymeric microparticles have been widely used for long-term release formulations of short half-life chemicals or synthetic peptides. Characterization of the drug release from microparticles is important to ensure product quality and desired pharmacological effect. However, there is no official method for long-term release parenteral dosage forms. Much work has been done to develop methods for in vitro drug release testing, generally grouped into three major categories: sample and separate, d

Sequential recommendation is a task that learns a temporal dynamic of a user behavior in sequential data and predicts items that a user would like afterward. However, diversity has been rarely emphasized in the context of sequential recommendation. Sequential and diverse recommendation must learn temporal preference on diverse items as well as on general items. Thus, we propose a sequential and diverse recommendation model that predicts a ranked list containing general items and also diverse ite

Deep learning has been actively investigated for various applications such as image classification, computer vision, and regression tasks, and it has shown state-of-the-art performance. In diffuse optical tomography (DOT), the accurate estimation of the bulk optical properties of a medium is paramount because it directly affects the overall image quality. In this work, we exploit deep learning to propose a novel, to the best of our knowledge, convolutional neural network (CNN)-based approach to

In the large-scale cohort of young and middle-aged individuals with NAFLD, BMI was positively associated with worsening of noninvasive fibrosis marker regardless of metabolic health status. Excess adiposity per se, even without accompanying metabolic health status, may contribute to fibrosis progression in NAFLD.

Interleukin (IL)-22 is a potent mediator of inflammatory responses. The IL-22 receptor consists of the IL-22Rα and IL-10Rβ subunits. Previous studies have shown that IL-22Rα expression is restricted to non-hematopoietic cells in the skin, pancreas, intestine, liver, lung, and kidney. Although IL-22 is involved in the development of inflammatory responses, there have been no reports of its role in brain inflammation. Here, we used RT-PCR, Western blotting, flow cytometry, immunohistochemical, and

Recent studies show that IL-22, a cytokine produced by activated CD4+ T cells and NK cells, plays a pathogenic role in acute and chronic skin diseases. While IL-22 is produced by immune cells, the expression of IL-22Rα, the functional subunit of IL-22R, is mostly restricted to non-hematopoietic cells in organs such as the skin and pancreas. Although it is well known that ultraviolet B (UVB) radiation induces skin inflammation, there have been no reports regarding the effect of UVB on the express