A Metric Approach to Hot Topics in Biomedicine via Keyword Co-occurrence

Purpose:To reveal the research hotpots and relationship among three research hot topics in b iomedicine,namely CRISPR,iPS(induced Pluripotent Stem)cell and Synthetic biology.Design/methodology/approach:We set up their keyword co-occurrence networks with using three indicators and information visualization for metric analysis.Findings:The results reveal the main research hotspots in the three topics are different,but the overlapping keywords in the three topics indicate that they are mutually integrated and interacted each other.Research limitations:All analyses use keywords,without any other forms.Practical implications:We try to find the information distribution and structure of these three hot topics for revealing their research status and interactions,and for promoting biomedical developments.Originality/value:We chose the core keywords in three research hot topics in biomedicine by using h-index.

Keyword Co-occurrence Analysis of Research on Innovation Ecosystem Studies

The aim of the paper is to identify and explore leading thematic areas within the research field related to innovation ecosystem.Based on data from the Web of Science database,the keywords frequency and its co-occurrence frequency pair were analyzed,and the theory of mapping knowledge domains was used to visualize the keywords co-occurrence network in innovation ecosystem to make further research of the heated issues.The findings indicate that the research scope involved in innovation ecosystem research is broad,and research content focus on micro and macro levels.According to the results of keywords co-occurrence analysis of different stages,innovation,network,knowledge,strategy,open innovation,value creation are the most important issues to innovation ecosystem research,given their position and role in the research network.The paper generates the added value mainly from the point of view of theory development.

Effect of land use on soil nematode community composition and co-occurrence network relationship

Land use influences soil biota community composition and diversity,and then belowground ecosystem processes and functions.To characterize the effect of land use on soil biota,soil nematode communities in crop land,forest land and fallow land were investigated in six regions of northern China.Generic richness,diversity,abundance and biomass of soil nematodes was the lowest in crop land.The richness and diversity of soil nematodes were 28.8and 15.1%higher in fallow land than in crop land,respectively.No significant differences in soil nematode indices were found between forest land and fallow land,but their network keystone genera composition was different.Among the keystone genera,50%of forest land genera were omnivores-predators and 36%of fallow land genera were bacterivores.The proportion of fungivores in forest land was 20.8%lower than in fallow land.The network complexity and the stability were lower in crop land than forest land and fallow land.Soil pH,NH_(4)^(+)-N and NO_(3)^(–)-N were the major factors influencing the soil nematode community in crop land while soil organic carbon and moisture were the major factors in forest land.Soil nematode communities in crop land influenced by artificial management practices were more dependent on the soil environment than communities in forest land and fallow land.Land use induced soil environment variation and altered network relationships by influencing trophic group proportions among keystone nematode genera.

Machine learning prediction model for gray-level co-occurrence matrix features of synchronous liver metastasis in colorectal cancer

BACKGROUND Synchronous liver metastasis(SLM)is a significant contributor to morbidity in colorectal cancer(CRC).There are no effective predictive device integration algorithms to predict adverse SLM events during the diagnosis of CRC.AIM To explore the risk factors for SLM in CRC and construct a visual prediction model based on gray-level co-occurrence matrix(GLCM)features collected from magnetic resonance imaging(MRI).METHODS Our study retrospectively enrolled 392 patients with CRC from Yichang Central People’s Hospital from January 2015 to May 2023.Patients were randomly divided into a training and validation group(3:7).The clinical parameters and GLCM features extracted from MRI were included as candidate variables.The prediction model was constructed using a generalized linear regression model,random forest model(RFM),and artificial neural network model.Receiver operating characteristic curves and decision curves were used to evaluate the prediction model.RESULTS Among the 392 patients,48 had SLM(12.24%).We obtained fourteen GLCM imaging data for variable screening of SLM prediction models.Inverse difference,mean sum,sum entropy,sum variance,sum of squares,energy,and difference variance were listed as candidate variables,and the prediction efficiency(area under the curve)of the subsequent RFM in the training set and internal validation set was 0.917[95%confidence interval(95%CI):0.866-0.968]and 0.09(95%CI:0.858-0.960),respectively.CONCLUSION A predictive model combining GLCM image features with machine learning can predict SLM in CRC.This model can assist clinicians in making timely and personalized clinical decisions.

基于Word2Vec和LDA主题模型的中国省级五年规划“文化政策”文本研究

运用Word2Vec和LDA相结合的主题模型分析技术,对我国31个省份三个时期五年规划文本中文化政策部分进行主题识别,从时间和空间两个维度进行“文化政策”主题挖掘和演化分析。研究发现,“文化政策”主题在发展趋势、重点转移、政策导向、技术应用等方面随时间推移呈现不同演化趋势;四大区域受经济发展水平、文化资源禀赋、政策导向影响,在企业角色强调程度、地区特色旅游发展以及国家级项目和竞争力方面存在地域差异。

Python实现Excel文档转换到Word文档的自动化方法

通过研究开发了一种基于Python语言,实现Excel数据自动转换成Word文档并实现排版功能的方法,为科研工作者、数据分析师或报告撰写人员提供一个方便快捷的工具,帮助他们更高效地完成Excel数据转换成Word并实现排版的任务。

Inversion tillage with straw incorporation affects the patterns of soil microbial co-occurrence and multi-nutrient cycling in a Hapli-Udic Cambisol

Inversion tillage with straw amendment is widely applied in northeastern China, and it can substantially increase the storage of carbon and improve multiple subsoil functions. Soil microorganisms are believed to be the key to this process,but research into their role in subsoil amelioration is limited. Therefore, a field experiment was conducted in 2018 in a region in northeastern China with Hapli-Udic Cambisol using four treatments: conventional tillage(CT, tillage to a depth of 15 cm with no straw incorporation), straw incorporation with conventional tillage(SCT, tillage to a depth of 15 cm),inversion tillage(IT, tillage to a depth of 35 cm) and straw incorporation with inversion tillage(SIT, tillage to a depth of 35 cm). The soils were managed by inversion to a depth of 15 or 35 cm every year after harvest. The results indicated that SIT improved soil multi-nutrient cycling variables and increased the availability of key nutrients such as soil organic carbon, total nitrogen, available nitrogen, available phosphorus and available potassium in both the topsoil and subsoil.In contrast to CT and SCT, SIT created a looser microbial network structure but with highly centralized clusters by reducing the topological properties of average connectivity and node number, and by increasing the average path length and the modularity. A Random Forest analysis found that the average path length and the clustering coefficient were the main determinants of soil multi-nutrient cycling. These findings suggested that SIT can be an effective option for improving soil multi-nutrient cycling and the structure of microbial networks, and they provide crucial information about the microbial strategies that drive the decomposition of straw in Hapli-Udic Cambisol.

基于Word2Vec和决策树的故障定位技术

利用Word2Vec方法对Java源代码进行深层语义编码,生成文件级和行级的语义向量,并将其用作输入数据来训练决策树模型,以实现精确的文件级别和行级别故障定位,优化故障检测过程,构建一个综合文件级别与行级别分析的高效故障定位框架.实验结果表明:该模型在各项目中的故障定位准确率均高于83%.

Temporal characteristics of algae-denitrifying bacteria co-occurrence patterns and denitrifier assembly in epiphytic biofilms on submerged macrophytes in Caohai Lake,SW China

Denitrifying bacteria in epiphytic biofilms play a crucial role in nitrogen cycle in aquatic habitats.However,little is known about the connection between algae and denitrifying bacteria and their assembly processes in epiphytic biofilms.Epiphytic biofilms were collected from submerged macrophytes(Patamogeton lucens and Najas marina L.)in the Caohai Lake,Guizhou,SW China,from July to November 2020 to:(1)investigate the impact of abiotic and biotic variables on denitrifying bacterial communities;(2)investigate the temporal variation of the algae-denitrifying bacteria co-occurrence networks;and(3)determine the contribution of deterministic and stochastic processes to the formation of denitrifying bacterial communities.Abiotic and biotic factors influenced the variation in the denitrifying bacterial community,as shown in the Mantel test.The co-occurrence network analysis unveiled intricate interactions among algae to denitrifying bacteria.Denitrifying bacterial community co-occurrence network complexity(larger average degrees representing stronger network complexity)increased continuously from July to September and decreased in October before increasing in November.The co-occurrence network complexity of the algae and nirS-encoding denitrifying bacteria tended to increase from July to November.The co-occurrence network complexity of the algal and denitrifying bacterial communities was modified by ammonia nitrogen(NH_(4)^(+)-N)and total phosphorus(TP),pH,and water temperature(WT),according to the ordinary least-squares(OLS)model.The modified stochasticity ratio(MST)results reveal that deterministic selection dominated the assembly of denitrifying bacterial communities.The influence of environmental variables to denitrifying bacterial communities,as well as characteristics of algal-bacterial co-occurrence networks and the assembly process of denitrifying bacterial communities,were discovered in epiphytic biofilms in this study.The findings could aid in the appropriate understanding and use of epiphytic biofilms denitrification function,as well as the enhancement of water quality.

Environment drives the co-occurrence of bacteria and microeukaryotes in a typical subtropical bay

The co-occurrence of bacteria and microeukaryote species is a ubiquitous ecological phenomenon,but there is limited cross-domain research in aquatic environments.We conducted a network statistical analysis and visualization of microbial cross-domain co-occurrence patterns based on DNA sampling of a typical subtropical bay during four seasons,using high-throughput sequencing of both 18S rRNA and 16S rRNA genes.First,we found obvious relationships between network stability and network complexity indices.For example,increased cooperation and modularity were found to weaken the stability of cross-domain networks.Secondly,we found that bacterial operational taxonomic units(OTUs)were the most important contributors to network complexity and stability as they occupied more nodes,constituted more keystone OTUs,built more connections,more importantly,ignoring bacteria led to greater variation in network robustness.Gammaproteobacteria,Alphaproteobacteria,Bacteroidetes,and Actinobacteria were the most ecologically important groups.Finally,we found that the environmental drivers most associated with cross-domain networks varied across seasons(in detail,the network in January was primarily constrained by temperature and salinity,the network in April was primarily constrained by depth and temperature,the network in July was mainly affected by depth,temperature,and salinity,depth was the most important factor affecting the network in October)and that environmental influence was stronger on bacteria than on microeukaryotes.

Community composition,co-occurrence,and environmental drivers of bacterioplankton community in surface and 50-m water layers in the subarctic North Pacific

The Western Subarctic Gyre(WSG)is one of the two gyre-systems in the subarctic North Pacific known for high nutrient and low-chlorophyll waters.However,the bacterioplankton in marine water of this area,either in terms of the taxonomic composition or functional structure,remains relatively unexplored.A total of 22 sampling sites from two water layers(surface water,SW and 50-m layer water,FW)were collected in this area.The physiochemical parameters of waters,Synechococcus,and bacterial density,as well as the bacterioplankton community composition and distribution pattern,were analyzed.The nutrient concentrations of DIN,DIP,and DSi,Chl-a concentration,and the average abundance of heterobacteria in FW were higher than those in SW.However,temperature and the average abundance of Synechococcus and pico-eukaryotes were higher in SW.A total of 3269 OTUs were assigned,and 2123OTUs were commonly shared;moreover,similar alpha diversity patterns were observed in both SW and FW.The bacterioplankton community showed significantly obvious correlation with salinity,DIP,DIN,and Chl a in both SW and FW.Proteobacteria,Cyanobacteria,Bacteroidota,Actinobacteriota,and Firmicutes were the main phyla while Synechococcus_CC9902,Psychrobacter,and Sulfitobacter were the dominant genera in each sampling site.Most correlations that happened between the OTUs in the cooccurrence network were positive and inter-module.Higher edges and graph density were found in SW,indicating that more correlations occurred,and the community was more complex in SW.This study provided novel knowledge on the bacterioplankton community structure and the correlation characteristics in WSG.

基于LDA和Word2Vec模型的学位论文评阅意见主题挖掘与分析

选取某高校部分硕士学位论文评阅意见为研究对象,使用自然语言处理和机器学习技术进行自动化的硕士学位论文评阅意见主题挖掘与分析。首先,采用LDA(latent dirichlet allocation)模型对评阅数据进行主题建模,提取文本中的潜在主题,并将评阅意见转化为主题分布向量;其次,结合Word2Vec模型将评阅意见的关键词转化为向量表达;最后,采用TextRank方法提取关键词,以揭示评阅专家的关注核心主题。实验结果表明,所提方法能为高校管理人员提供切实有效的分析工具,有助于他们更好地分析总结评阅意见,同时也为硕士研究生撰写高质量学位论文提供有益借鉴。

基于LDA-Word2vec的图书情报领域机器学习研究主题演化与热点主题识别

[目的/意义]在人工智能技术及应用快速发展与深刻变革背景下,机器学习领域不断出现新的研究主题和方法,深度学习和强化学习技术持续发展。因此,有必要探索不同领域机器学习研究主题演化过程,并识别出热点与新兴主题。[方法/过程]本文以图书情报领域中2011—2022年Web of Science数据库中的机器学习研究论文为例,融合LDA和Word2vec方法进行主题建模和主题演化分析,引入主题强度、主题影响力、主题关注度与主题新颖性指标识别热点主题与新兴热点主题。[结果/结论]研究结果表明,(1)Word2vec语义处理能力与LDA主题演化能力的结合能够更加准确地识别研究主题,直观展示研究主题的分阶段演化规律;(2)图书情报领域的机器学习研究主题主要分为自然语言处理与文本分析、数据挖掘与分析、信息与知识服务三大类范畴。各类主题之间的关联性较强,且具有主题关联演化特征;(3)设计的主题强度、主题影响力和主题关注度指标及综合指标能够较好地识别出2011—2014年、2015—2018年和2019—2022年3个不同周期阶段的热点主题。

基于Word VBA辅助技术文件编制的数字化协同建设的探索

文件编制是设计研发人员日常工作的重要组成部分,其中技术文件的编制涉及大量文件结构和起草规则的应用,基于相关标准中关于文件的编写要求,文章利用WordVBA编程技术辅助技术文件编写工作中的格式编排,实现了Word文档标准格式技术文件的自动化编制,从而保障文件编制符合标准格式要求,有效提高了工作效率。

结合Word2vec和BiLSTM的民航非计划事件分析方法

安全是民航业的核心主题。针对目前民航非计划事件分析严重依赖专家经验及分析效率低下的问题,文章提出一种结合Word2vec和双向长短期记忆(bidirectional long short-term memory,BiLSTM)神经网络模型的民航非计划事件分析方法。首先采用Word2vec模型针对事件文本语料进行词向量训练,缩小空间向量维度;然后通过BiLSTM模型自动提取特征,获取事件文本的完整序列信息和上下文特征向量;最后采用softmax函数对民航非计划事件进行分类。实验结果表明,所提出的方法分类效果更好,能达到更优的准确率和F 1值,对不平衡数据样本同样具有较稳定的分类性能,证明了该方法在民航非计划事件分析上的适用性和有效性。

基于LSTM+Word2vec的微博评论情感分析

微博作为当今热门的社交平台,其中蕴含着许多具有强烈主观性的用户评论文本。为挖掘微博评论文本中潜在的信息,针对传统的情感分析模型中存在的语义缺失以及过度依赖人工标注等问题,提出一种基于LSTM+Word2vec的深度学习情感分析模型。采用Word2vec中的连续词袋模型(continuous bag of words,CBOW),利用语境的上下文结构及语义关系将每个词语映射为向量空间,增强词向量之间的稠密度;采用长短时记忆神经网络模型实现对文本上下文序列的线性抓取,最后输出分类预测的结果。实验结果的准确率可达95.9%,通过对照实验得到情感词典、RNN、SVM三种模型的准确率分别为52.3%、92.7%、85.7%,对比发现基于LSTM+Word2vec的深度学习情感分析模型的准确率更高,具有一定的鲁棒性和泛化性,对用户个性化推送和网络舆情监控具有重要意义。

关于Word2Vec文本分类效果若干影响因素的分析

Word2Vec向量模型参数众多,在不同情景下分类效果不一,分析其影响因素很有必要。从Word2Vec模型基本原理出发,分析讨论了预训练语料、词向量预训练参数以及分类模型参数三大因素对模型分类效果的影响。结果表明限定域预料效果好于广域预料;预训练参数中向量维度越大,效果越好,窗口大小存在最优值,分类算法影响不大;分类模型参数中学习率、激活函数、批次大小对模型分类效果影响较大,训练轮次相对较小。

标准电子文件转WORD校验方法

随着标准电子文件在各个领域的广泛应用,文件格式的转换及其后续校验工作变得日益重要。本研究聚焦于探讨标准文档格式转换为Word格式的过程中所面临的挑战,并提出了一个全面的校验流程,以确保转换的准确性和高效性。阐述了标准电子文件在石油等领域的广泛应用以及转换为Word格式的必要性,强调了校验过程的重要性,旨在确保转换后的文件与原始文件在错误率万分之五以内的一致性。

基于K-means与Word2vec的哺乳文胸评论主题挖掘研究

目的为了了解消费者在网络平台购买哺乳文胸时的关注侧重点,文章从在线评论中抽取有效关键词构建哺乳文胸主题,并通过计算主题的重要程度协助商家了解消费者关注重点方向。方法选用TF-IDF关键词抽取算法,结合K-means和Word2vec进行语义聚类、主题识别、主题词挖掘及主题重要度计算。结果哺乳文胸评论文本聚类后的主题重要程度排名是:产品品质(45.47%)、产品外观(35.83%)、产品服务(18.79%)。结论通过该方法能够有效的识别和构建哺乳文胸主题及主题词,同时,通过主题的重要程度,能够了解消费者对于网络平台购买哺乳文胸时关注的重点方向,为哺乳内衣企业进行产品改善及生产等提供理论参考。

Sentiment Analysis Using E-Commerce Review Keyword-Generated Image with a Hybrid Machine Learning-Based Model

In the context of the accelerated pace of daily life and the development of e-commerce,online shopping is a mainstreamway for consumers to access products and services.To understand their emotional expressions in facing different shopping experience scenarios,this paper presents a sentiment analysis method that combines the ecommerce reviewkeyword-generated imagewith a hybrid machine learning-basedmodel,inwhich theWord2Vec-TextRank is used to extract keywords that act as the inputs for generating the related images by generative Artificial Intelligence(AI).Subsequently,a hybrid Convolutional Neural Network and Support Vector Machine(CNNSVM)model is applied for sentiment classification of those keyword-generated images.For method validation,the data randomly comprised of 5000 reviews from Amazon have been analyzed.With superior keyword extraction capability,the proposedmethod achieves impressive results on sentiment classification with a remarkable accuracy of up to 97.13%.Such performance demonstrates its advantages by using the text-to-image approach,providing a unique perspective for sentiment analysis in the e-commerce review data compared to the existing works.Thus,the proposed method enhances the reliability and insights of customer feedback surveys,which would also establish a novel direction in similar cases,such as social media monitoring and market trend research.