检索结果-南通市图书馆

Enhancement of Sentiment Analysis Using Clause and Discourse Connectives

Computers, Materials & Continua 2021年第8期68卷 1983-1999页

作者： Kumari Sheeja Saraswathy sobha lalitha devi AU-KBC Research Centre MIT Campus of Anna UniversityChromepetChennaiIndia

The sentiment of a text depends on the clausal structure of the sentence and the connectives’discourse *** this work,the clause boundary,discourse argument,and syntactic and semantic information of the sentence are used to assign the text’s *** clause boundaries identify the span of the text,and the discourse connectives identify the *** the lexicon-based analysis of traditional sentiment analysis gives the wrong sentiment of the sentence,a deeper-level semantic analysis is required for the correct analysis of ***,in this study,explicit connectives in Malayalam are considered to identify the discourse arguments.A supervised method,conditional random fields,is used to identify the clause boundary and discourse *** the study,1,000 sentiment sentences from Malayalam documents were *** results show that the discourse structure integration considerably improves sentiment analysis performance from the baseline system.

关键词： Natural language processing artificial intelligence sentiment analysis computational linguistics opinion mining machine learning information extraction supervised learning

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Evaluation of cytotoxic and anti-tumor activity of partially purified serine protease isolate from the Indian earthworm Pheretima posthuma

引用

Asian Pacific Journal of Tropical Biomedicine 2013年第11期3卷 896-901页

作者： Mahendra Kumar Verma Francies Xavier Yogendra Kumar Verma Kota sobha Department of Biotechnology R.V.R.& J.C.College of Engineering Department of Microbiology All India Institute of Medical Sciences

Objective:To isolate,partially purify and evaluate the cytotoxic and antitumor activity of a serine protease from the chosen Indian earthworm Pheretima ***:Whole animal extract was prepared and purified its protein constituents by size and charge based chromatographic separation techniques using Sephadex G-50 and DEAE-Cellulose resin *** molecular weight of the protein isolate was determined and analyzed for its cytotoxic property against Vero cells in different dilutions(1:20 and 1:40)and anti-tumor activity by MTT assay(a colorimetric assay)using breast cancer cell line MCF-7,with tamoxifen as ***:One of the protein constituents after purification was characterized as serine protease by Caseinolytic plate diffusion *** molecular weight of this purified isolate was determined,by SDS-PAGE analysis with standard protein ladder,as of 15 *** performed tests suggested that the 15kDa fraction has potent cytotoxic activity and satisfactory antitumor activity as well in ***:Exact molecular mechanism of the cytotoxic and antitumor activities is yet to be explored and currently we are working on ultra-purification and biophysical characterization of this *** investigation into the mechanism(s)of cytotoxic and antitumor activities at molecular level would be useful in treatment of various classes of cancer and viral infections in future.

关键词： Earthworm fibrinolytic enzyme Cytotoxicity Antitumor activity Serine protease Minimum inhibitory concentration

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

A Survey of the Machine Learning Models for Forest Fire Prediction and Detection

引用

International Journal of Communications, Network and System Sciences 2023年第7期16卷 131-150页

作者： Prathibha sobha Shahram Latifi Department of Electrical and Computer Engineering University of Nevada Las Vegas Las Vegas USA

Forest fires are a significant threat to the environment, causing ecological damage, economic losses, and posing a threat to human life. Hence, timely detection and prevention of forest fires are critical to minimizing their impact. In this paper, we review the current state-of-the-art methods in forest fire detection and prevention using predictions based on weather conditions and predictions based on forest fire history. In particular, we discuss different Machine Learning (ML) models that have been used for forest fire detection. Further, we present the challenges faced when implementing the ML-based forest fire detection and prevention systems, such as data availability, model prediction errors and processing speed. Finally, we discuss how recent advances in Deep Learning (DL) can be utilized to improve the performance of current fire detection systems.

关键词： AI Computer Vision Deep Learning Forest Fires ML UAV

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Sero-Prevalence of Paratuberculosis (Johne's Disease) in Cattle Population of South-Western Bangalore Using ELISA Kit

引用

Open Journal of Veterinary Medicine 2012年第4期2卷 196-200页

作者： Anvita Gupta sobha M. Rani Pushpa Agrawal Praveen Kumar Gupta Department of Biotechnology R.V. College of Engineering Bangalore India Department of Seroepidemiology Institute of Animal Health & Veterinary Biologicals Bangalore India

Johne's disease or paratuberculosis is a chronic mycobacterial infection that affects cattle, sheep, goats and other ruminants, adversely, leading to huge economic losses throughout the world. The estimation of sero-prevalence of this disease in the cattle population of south-western Bangalore, Karnataka, using an immunological assay and statistical analyses, was the objective of this study. One of the diagnostic tools used to detect an antigen or an antibody in animal serum or milk is the Enzyme Linked Immuno-Sorbent Assay, which has been widely used in the research and diagnosis of animal and human diseases as its accuracy is of nanogram-picogram/milliltre level. In the present study, indirect-ELISA was used to diagnose and estimate the sero-prevalence of paratuberculosis in cattle showing diarrhoea and/or anaemia, at 5 local dairy farms in south-west Bangalore, India. Out of 350 bovine serum samples, 53 (15.14%) were positive, 55 milk samples out of 300 were found positive (18.33%) for antibody against Johne's disease by indirect ELISA. The positive samples were then confirmed by direct smear examination of dung by Ziehl-Neelsen staining. Statistical analyses were carried out to indicate the seroprevalence of Johne's disease in the cattle population of this region to be 15 ± 10%, taking a confidence interval of 95%. The results emphasize the need to prevent the further spread of infection to other susceptible animals and humans as the causative organism, Mycobacterium avium subsp. paratuberculosis is implicated in Crohn's disease, an irritable bowel syndrome in humans.

关键词： Johne's Disease Mycobacterium avium subsp. paratuberculosis ELISA

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：