The coronavirus disease 2019 (COVID-19) breaking out in late December 2019 is gradually being controlled in China, but it is still spreading rapidly in many other countries and regions worldwide. It is urgent to conduct prediction research on the development and spread of the epidemic. In this article, a hybrid artificial-intelligence (AI) model is proposed for COVID-19 prediction. First, as traditional epidemic models treat all individuals with coronavirus as having the same infection rate, an improved susceptible-infected (ISI) model is proposed to estimate the variety of the infection rates for analyzing the transmission laws and development trend. Second, considering the effects of prevention and control measures and the increase of the public's prevention awareness, the natural language processing (NLP) module and the long short-term memory (LSTM) network are embedded into the ISI model to build the hybrid AI model for COVID-19 prediction. The experimental results on the epidemic data of several typical provinces and cities in China show that individuals with coronavirus have a higher infection rate within the third to eighth days after they were infected, which is more in line with the actual transmission laws of the epidemic. Moreover, compared with the traditional epidemic models, the proposed hybrid AI model can significantly reduce the errors of the prediction results and obtain the mean absolute percentage errors (MAPEs) with 0.52%, 0.38%, 0.05%, and 0.86% for the next six days in Wuhan, Beijing, Shanghai, and countrywide, respectively. Index Terms-Coronavirus disease 2019 (COVID-19) prediction, epidemic model, hybrid artificial-intelligence (AI) model, natural language processing (NLP).

Chinese spelling correction (CSC) is a task to detect and correct spelling errors in texts. CSC is essentially a linguistic problem, thus the ability of language understanding is crucial to this task. In this paper, we propose a Pre-trained masked Language mOdel with Misspelled knowledgE (PLOME) for CSC, which jointly learns how to understand language and correct spelling errors. To this end, PLOME masks the chosen tokens with similar characters according to a confusion set rather than the fixed token "[MASK]" as in BERT. Besides character prediction, PLOME also introduces pronunciation prediction to learn the misspelled knowledge on phonic level. Moreover, phonological and visual similarity knowledge is important to this task. PLOME utilizes GRU networks to model such knowledge based on characters' phonics and strokes. Experiments are conducted on widely used benchmarks. Our method achieves superior performance against state-of-the-art approaches by a remarkable margin. We release the source code and pre-trained model for further use by the community 1 .

This paper presents a novel framework, MGNER, for Multi-Grained Named Entity Recognition where multiple entities or entity mentions in a sentence could be nonoverlapping or totally nested. Different from traditional approaches regarding NER as a sequential labeling task and annotate entities consecutively, MGNER detects and recognizes entities on multiple granularities: it is able to recognize named entities without explicitly assuming non-overlapping or totally nested structures. MGNER consists of a Detector that examines all possible word segments and a Classifier that categorizes entities. In addition, contextual information and a self-attention mechanism are utilized throughout the framework to improve the NER performance. Experimental results show that MGNER outperforms current state-of-the-art baselines up to 4.4% in terms of the F1 score among nested/non-overlapping NER tasks.

BackgroundTea is one of the most consumed beverages worldwide. The healthy effects of tea are attributed to a wealthy of different chemical components from tea. Thousands of studies on the chemical constituents of tea had been reported. However, data from these individual reports have not been collected into a single database. The lack of a curated database of related information limits research in this field, and thus a cohesive database system should necessarily be constructed for data deposit and further application.DescriptionThe Tea Metabolome database (TMDB), a manually curated and web-accessible database, was developed to provide detailed, searchable descriptions of small molecular compounds found in Camellia spp. esp. in the plant Camellia sinensis and compounds in its manufactured products (different kinds of tea infusion). TMDB is currently the most complete and comprehensive curated collection of tea compounds data in the world. It contains records for more than 1393 constituents found in tea with information gathered from 364 published books, journal articles, and electronic databases. It also contains experimental 1H NMR and 13C NMR data collected from the purified reference compounds or collected from other database resources such as HMDB. TMDB interface allows users to retrieve tea compounds entries by keyword search using compound name, formula, occurrence, and CAS register number. Each entry in the TMDB contains an average of 24 separate data fields including its original plant species, compound structure, formula, molecular weight, name, CAS registry number, compound types, compound uses including healthy benefits, reference literatures, NMR, MS data, and the corresponding ID from databases such as HMDB and Pubmed. Users can also contribute novel regulatory entries by using a web-based submission page. The TMDB database is freely accessible from the URL of http://pcsb.ahau.edu.cn:8080/TCDB/index.jsp. The TMDB is designed to address the broad needs of tea biochemists, natural products chemists, nutritionists, and members of tea related research community.ConclusionThe TMDB database provides a solid platform for collection, standardization, and searching of compounds information found in tea. As such this database will be a comprehensive repository for tea biochemistry and tea health research community.

While offering high-precision control of neural circuits, optogenetics is hampered by the necessity to implant fiber-optic waveguides in order to deliver photons to genetically engineered light-gated neurons in the brain. Unlike laser light, X-rays freely pass biological barriers. Here we show that radioluminescent Gd2(WO4)3:Eu nanoparticles, which absorb external X-rays energy and then downconvert it into optical photons with wavelengths of ∼610 nm, can be used for the transcranial stimulation of cortical neurons expressing red-shifted, ∼590–630 nm, channelrhodopsin ReaChR, thereby promoting optogenetic neural control to the practical implementation of minimally invasive wireless deep brain stimulation.