Search

Traditional document clustering algorithms classify data by measuring the similarity between documents. But they can??t mine users' subjective intention of clustering results according to a small amount of supervision information given by users. With the development of the diversified application scenarios, the clustering results of the same dataset under the guidance of different users?? intentions may not be unique. How to obtain the clustering results following users' intentions is one of the problems in the current research. Besides, there is a small amount of supervision information given by users. How to learn the clustering intention of users to the greatest extent according to a small amount of supervision information is another problem. Therefore, a semi-supervised deep document clustering model with supplemented intention (SDDCS) is proposed. According to the supervision information given by the user, SDDCS constructs an intention matrix to mine the user's intention. The unknown elements in the intention matrix are supplemented according to the matrix factorization and supplement algorithm, so as to learn the users' intention to the greatest extent. The supplementary intention matrix is used to guide the document clustering process, and the user's intention is taken as one of the clustering bases. Finally, the clustering results in line with the user's intention are obtained. Experiments on four public document datasets show that the clustering performance of SDDCS is higher, and its effectiveness is proven.

The intention expresses the user’s preference for document structure division. Intention-guided document structure division is an important task in the field of text mining. To achieve this goal, deep semi-supervised document clustering provides a promising solution to personalized document clustering. However, traditional deep semi-supervised clustering models suffer from the problem of the limited number of constraints which is insufficient for intention-guided document clustering. Moreover, documents normally have various emphases on their representations to reflect different structural opinions. In this paper, we proposed an intention-guided deep semi-supervised document clustering model, namely IGSC, to divide document structure based on a small amount of user-provided supervised information. IGSC designs a deep metric learning network to solve the above problems. The deep metric learner explores the user’s global intention and outputs an intention matrix. The intention is explored from the small amount user provided pairwise constraints and is used to guide the representation learning. Moreover, IGSC uses the intention matrix to guide the clustering process, to get the clustering results that best meet the user’s intention. This paper compares IGSC with a number of document clustering models on four real-world text datasets, namely Reu-10k, BBC, ACM, and Abstract. The results show that IGSC evidently improves the clustering performance and outperforms the best result of benchmark models with 7% on average. The comparison with other models and the visualization results can demonstrate that IGSC is effective.

This paper summarizes the current situation of self-management of patients with hematological malignancies, the concept, classification and management strategies of e-health technology, and points out its existing problems and the direction of future research, in order to provide reference for the self-management of patients with hematological malignancies in China. (本研究从血液恶性肿瘤患者自我管理现状、电子健康技术的概念、分类、管理策略等方面进行综述, 分析利弊, 探讨未来研究的方向, 旨在为国内血液恶性肿瘤患者的自我管理提供借鉴和参考。)

The gastrointestinal tract is the largest organ connecting the human body and the outside world. The gastrointestinal mucosa is not only an important barrier connecting the internal body and the outside world, but also plays a key role in maintaining normal functions of the gastrointestinal tract. The injuries of gastrointestinal mucosal barrier are the common pathogenesis mechanisms in the occurrence and development of gastrointestinal diseases. However, there is still a lack of deep and systematic understanding of gastrointestinal mucosa, especially small intestinal mucosa. In clinical practice, more attentions have been paid to the role of injury factors, but the importance of mucosal protection is ignored. In order to improve the understanding of gastrointestinal mucosa protection and standardize the clinical application of gastrointestinal mucosal protective agents, the Gastrointestinal Hormone and Mucosal Barrier Group, Chinese Society of Gastroenterology, Chinese Medical Association formulated the first expert consensus on gastrointestinal mucosal protection in China, which was offi- cially published at the end of 2021. This paper interprets the background, process and main content of this consensus, so as to raise awareness among medical staff, and standardize clinical diagnosis and treatment.

Humic-like substances (HULIS) are complex macromolecules in water-soluble organic compounds (WSOCs) containing multiple functional groups, and transition metal ions (TMs) are ubiquitous in atmospheric particles. In this study, potential physical and chemical interactions between HULIS and four TM species, including Cu 2+ , Mn 2+ , Ni 2+ , and Zn 2+ , were analyzed by optical method under acidic, weakly acidic, and neutral conditions. The results showed that Cu 2+ , Mn 2+ , and Zn 2+ only slightly enhanced mass absorption efficiency (MAE 365) of HULIS in winter and had indiscernible effects on the absorption Ångström exponent (AAE) of HULIS in both seasons under all acidity conditions. All four TMs had fluorescence quenching effects on winter HULIS, and only Cu 2+ had similar effects on summer HULIS, with the highest quenching coefficients found under weakly acidic conditions in both seasons. The 1 H-nuclear magnetic resonance (1 H-NMR) and Fourier-transform infrared (FTIR) spectra revealed that Cu 2+ mainly bound with aromatic species and tightened the molecule structures of HULIS. The parallel factor analysis (PARAFAC) results extracted four components of HULIS, including low-oxidized humic-like substances (C1), N-containing compounds (C2), highly oxidized humic-like substances (C3), and the mixing residuals (C4), from the fluorescence spectra in both winter and summer. The spectral characteristic of HULIS with Cu 2+ additions under three acidity conditions indicated that electron-donating groups of HULIS mainly corresponded to C1 and C3, with Cu 2+ binding with HULIS by replacing protons, while electron-withdrawing groups of HULIS could correspond to C2, with its connection with Cu 2+ through electrostatic adsorption or colliding-induced energy transfer. [ABSTRACT FROM AUTHOR]

Electrochemical oxidation is an efficient and pollution-free technology that belongs to the advanced oxidation process. The anode with excellent characteristics is a key factor that affects the electrocatalytic oxidation system. To explore the difference of performance between the PbO2 electrode and RuO2-IrO2 electrode, the morphology, microstructure, and other electrochemical properties were tested respectively. The scanning electron microscopy (SEM) shows that the PbO2 film is a typical pyramid shape with a compact structure while many cracks appear on RuO2-IrO2 film. The PbO2 and RuO2-IrO2 crystallize sizes are 22.7 nm and 31.3 nm, respectively. The oxygen evolution overpotential of the PbO2 electrode is 1.33 V (vs. SCE) a little lower than the RuO2-IrO2 electrode of 1.41 V (vs. SCE). The phenol and crystal violet (CV) are applied as the target contaminants to check the electrocatalytic performance of the two electrodes. The experiment results show that the RuO2-IrO2 electrode is fit for the degradation of crystal violet and the PbO2 electrode is fit for the degradation of phenol. The better electrocatalytic performance on the degradation of crystal violet by RuO2-IrO2 electrode can be attributed to the higher oxygen evolution overpotential. [ABSTRACT FROM AUTHOR]

The financial risk of enterprises is crucial to business managers and investors, and the establishment of the independent director system is intended to address the financial risk generated internally by enterprises. However, in recent years, the system of independent directors has increasingly been criticized, and its impact on corporate financial risk is also being questioned. Herein, through empirical research methods, we have studied the relationship between independent directors and financial risk. We found that the opinions of independent directors, their professional backgrounds, and the size of the board of directors have a significant impact on financial risk. This could provide a reference for optimizing the system of independent directors.