检索结果-内蒙古大学图书馆

Applying Parallel Processing to Improve the Computation Speed of K-Nearest Neighbor Algorithm

Applying Parallel Processing to Improve the Computation Spee...

2020 International Conference on data analytics for Business and Industry: Way Towards a Sustainable Economy, ICDABI 2020

作者： Alanezi, Maha A. Alqaddoumi, Abdulla University of Bahrain Collage of Science Big Data Science and Analytics Master Program Sakhir Bahrain University of Bahrain Collage of Information Technology Department of Information System Sakhir Bahrain

ISBN: (纸本)9781728196756

K-Nearest Neighbor (KNN) is a widely used algorithm to gain an accurate and efficient classification. One of the drawbacks of the algorithm is the time required to calculate the distance for each point. In this paper, the aim is to speed up the KNN algorithm with the implementation of multi threads and multiprocessors to reduce the time to execute the algorithm. There are two medical datasets used to apply the KNN algorithm for the comparison of the sequential and parallel performance. The datasets utilized are Heart Test and Breast Cancer Wisconsin (Diagnostic) data Sets. The multiprocessing is used to parallelize the computation of the distance of KNN. The parallel KNN outperforms the sequential version with the speedup increase, leading to reduction in time for both the processes and threads. © 2020 IEEE.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Comparing Naïve Bayes, Decision Tree and Logistic Regression Methods in Fraudulent Credit Card Transactions

Comparing Naïve Bayes, Decision Tree and Logistic Regressio...

引用

2020 International Conference on data analytics for Business and Industry: Way Towards a Sustainable Economy, ICDABI 2020

作者： Alanezi, Maha A. Homeed, Mawra T. Mohamed, Zahra S. Zeki, Ahmed M. University of Bahrain Big Data Science Analytics Master Program Collage of Science Sakhir Bahrain University of Bahrain Collage of Information Technology Department of Information System Sakhir Bahrain

ISBN: (纸本)9781728196756

data mining is utilized to explore banks' data to unravel any hidden scams and detect potential frauds. The aim of this paper is to compare between the Naïve Bayes, Decision Tree and Logistic Regression in fraudulent credit card transactions. Cross-Industry Standard Process for data Mining (CRISP-DM) is followed to achieve the aim of this research. In terms of accuracy, the best classification model was Logistic Regression with 94.6% accuracy, compared with the Decision Tree and Naïve Bayes that showed accuracy of 89.1% and 90.9% respectively. Other measures were also calculated like time needed to build the model among others. © 2020 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

The largest genome-wide association study for breast cancer in Taiwanese Han population

引用

Breast Cancer Research and Treatment 2024年第2期203卷 291-306页

作者： Hsu, Yu-Ching Chen, Hung-Lin Cheng, Chi-Fung Chattopadhyay, Amrita Chen, Pei-Shan Lin, Che-Chen Chiang, Hsiu-Yin Liu, Ting-Yuan Huang, Chi-Hao Kuo, Chin-Chi Chuang, Eric Y. Lu, Tzu-Pin Tsai, Fuu-Jen Bioinformatics Program Taiwan International Graduate Program National Taiwan University Taipei Taiwan Bioinformatics Program Institute of Statistical Science Taiwan International Graduate Program Academia Sinica Taipei Taiwan Institute of Health Data Analytics and Statistics Department of Public Health College of Public Health National Taiwan University Taipei Taiwan Big Data Center China Medical University Hospital Taichung Taiwan Center for Translational Genomic Research Department of Medical Research China Medical University Hospital Taichung Taiwan Million-Person Precision Medicine Initiative Department of Medical Research China Medical University Hospital Taichung Taiwan Division of Breast Surgery Department of Surgery China Medical University Hospital Taichung Taiwan Division of Nephrology Department of Internal Medicine China Medical University Hospital Taichung Taiwan Department of Medical Research China Medical University Hospital Taichung Taiwan Bioinformatics and Biostatistics Core Center of Genomic and Precision Medicine National Taiwan University Taipei Taiwan Graduate Institute of Biomedical Electronics and Bioinformatics National Taiwan University Taipei Taiwan Biomedical Technology and Device Research Laboratories Industrial Technology Research Institute Hsinchu Taiwan Genetic Center Department of Medical Research China Medical University Hospital Taichung Taiwan

Purpose: Breast cancer is a molecularly heterogeneous disease, and multiple genetic variants contribute to its development and prognosis. Most of previous genome-wide association studies (GWASs) and polygenic risk scores (PRSs) analyses focused on studying breast cancers of Caucasian populations, which may not be applicable to other population. Therefore, we conducted the largest breast cancer cohort of Taiwanese population to fill in the knowledge gap. Methods: A total of 152,534 Participants recruited by China Medical University Hospital between 2003 and 2019 were filtered by several patient selection criteria and GWAS quality control steps, resulting in the inclusion of 2496 cases and 9984 controls for this study. We then conducted GWAS for all breast cancers and PRS analyses for all breast cancers and the four breast cancer subtypes, including luminal A, luminal B, basal-like, and HER2-enriched. Results: The GWAS analyses identified 113 SNPs, 50 of which were novel. The PRS models for all breast cancers and the luminal A subtype showed positively correlated trends between the PRS and the risk of developing breast cancer. The odds ratios (95% confidence intervals) for the groups with the highest PRS in all breast cancers and the luminal A subtype were 5.33 (3.79–7.66) and 3.55 (2.13–6.14), respectively. Conclusion: In summary, we explored the association of genetic variants with breast cancer in the largest Taiwanese cohort and developed two PRS models that can predict the risk of developing any breast cancer and the luminal A subtype in Taiwanese women. © 2023, The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature.

关键词： Breast cancer Genome-wide association study Polygenic risk score Taiwanese population

来源：评论

学校读者我要写书评

暂无评论

Exploring the Relation between Blood Tests and Covid-19 Using Machine Learning

Exploring the Relation between Blood Tests and Covid-19 Usin...

引用

data analytics for Business and Industry: Way Towards a Sustainable Economy (ICDABI), International Conference on

作者： Mohamed Almansoor Nabil M. Hewahi Big Data Science & Analytics Program University of Bahrain University of Bahrain

ISBN: (数字)9781728196756

ISBN: (纸本)9781728196763

COVID-19 is a global pandemic that hit the world in 2019-2020 and caused massive losses. Every day, hundreds of thousands of tests are being done on possible infected cases. It usually takes several hours to get the results of virus test in advanced countries, whereas in other countries might take days. The aim of this study is to investigate whether normal blood medical tests help in detecting covid-19 using various machine learning approaches. If true, this would give an indication to people who should undergo the virus test. In this paper we independently use machine learning algorithms including support vector machines, adaptive boosting, random forest and k-nearest neighbors. These algorithms are then merged to form ensemble learning which leads to the classification. The results show that the ensemble learning is having the highest true positive rate of 30%. The obtained results show that normal blood tests do not help much in giving right indications about detecting COVID-19.

关键词： COVID-19 Biological system modeling Machine learning Support vector machines Blood Random forests Predictive models

来源：评论

学校读者我要写书评

暂无评论

Random Forest vs. SVM vs. KNN in classifying Smartphone and Smartwatch sensor data using CRISP-DM

Random Forest vs. SVM vs. KNN in classifying Smartphone and ...

引用

data analytics for Business and Industry: Way Towards a Sustainable Economy (ICDABI), International Conference on

作者： Sadiq Jaffer Saleh Sayed Qasim Ali Ahmed M. Zeki Big Data Science & Analytics Master Program University of Bahrain College of Information Technology University of Bahrain

ISBN: (数字)9781728196756

ISBN: (纸本)9781728196763

Nowadays IoT sensors become one of the major sources of data, starting from home automation going to daily devices. Focusing on handsets that have the most significant contribution factor on data blooming and booming. The problem at hand is data mining methods comparison, for selecting the best method that serves sensor data. Methodology used was CRISP-DM. This paper found Random Forest data mining method to work best under the described circumstances.

关键词： Support vector machines Legged locomotion data mining Business Activity recognition Accelerometers Bibliographies

来源：评论

学校读者我要写书评

暂无评论

Theoretical insight and molecular recognition of fluconazole molecularly imprinted polymers: a combined computational and experimental analysis

引用

RSC advances 2025年第24期15卷 19158-19175页

作者： Untung Gunawan Slamet Ibrahim Atthar Luqman Ivansyah Sophi Damayanti Department of Pharmacy School of Medicine and Health Sciences Atma Jaya Catholic University of Indonesia 14440 Indonesia untung.gunawan@atmajaya.ac.id. Faculty of Pharmacy Universitas Jenderal Achmad Yani Cimahi 40531 Indonesia. Instrumentation and Computational Physics Research Group Department of Physics Faculty of Mathematics and Natural Sciences Institut Teknologi Bandung 40132 Indonesia. Master Program in Computational Science Faculty of Mathematics and Natural Science Institut Teknologi Bandung 40132 Indonesia. Department of Pharmacochemistry School of Pharmacy Institut Teknologi Bandung 40132 Indonesia. University Center of Excellence on Artificial Intelligence for Vision Natural Language Processing & Big Data Analytics (U-CoE Al-VLB) Institut Teknologi Bandung 40132 Indonesia.

Insufficient surveillance and diagnosis result in a minimum of 150 million cases of serious fungal infections reported annually. The WHO has compiled a list of priority pathogens to encourage research and investment in fungal infections and antifungal resistance in late 2022. Among these, is classified as a critical pathogen. Fluconazole is widely recognized as an effective medication for the treatment and prevention of both mucosal and invasive candidiasis. Molecularly imprinted polymer (MIP) could enhance separation selectivity in fluconazole bioanalysis. The objective of this research is to develop an MIP for fluconazole by analyzing interactions identified in prior research and incorporating established improvements for MIP synthesis that cannot be observed through laboratory experimentation. Based on binding affinity, intermolecular hydrogen bonds, complexation energy, and thermodynamic characteristics, 2-acrylamido-1-ethanesulfonic acid was chosen as the optimal monomer. The HOMO-LUMO investigation revealed the localization of the orbitals from the guest to the host. The FMO study indicated that chloroform was the most suitable solvent for complex formation. The QTAIM, NBO, and NCI-RDG analyses identified the hydrogen bond formed between the H51 atom of the monomer and the N33 atom of fluconazole, determined to be the most significant hydrogen bond in the host-guest interaction. The interaction energy from multi-monomer interaction showed that a 1 : 6 ratio is the best ratio in forming a pre-polymerization complex between the template and monomer. Based on the findings of this study, it is anticipated that the computational analysis may be utilized for rational design for the enhancement of prior studies and future laboratory investigations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Comparing Naïve Bayes, Decision Tree and Logistic Regression Methods in Fraudulent Credit Card Transactions

Comparing Naïve Bayes, Decision Tree and Logistic Regressio...

引用

data analytics for Business and Industry: Way Towards a Sustainable Economy (ICDABI), International Conference on

作者： Maha A. Alanezi Mawra T. Homeed Zahra S. Mohamed Ahmed M. Zeki Big Data Science & Analytics Master Program University of Bahrain Sakhir Kingdom of Bahrain Collage of Information Technology University of Bahrain Sakhir Kingdom of Bahrain

ISBN: (数字)9781728196756

ISBN: (纸本)9781728196763

关键词： Support vector machines Business Bayes methods Hidden Markov models Logistics data models Credit cards

来源：评论

学校读者我要写书评

暂无评论

Tweets Sentiment Analysis During COVID-19 Pandemic

Tweets Sentiment Analysis During COVID-19 Pandemic

引用

data analytics for Business and Industry: Way Towards a Sustainable Economy (ICDABI), International Conference on

作者： Maha A. Alanezi Nabil M. Hewahi Big Data Science & Analytics Master Program Collage of Science University of Bahrain Sakhir Kingdom of Bahrain Collage of Information Technology University of Bahrain Sakhir Kingdom of Bahrain

ISBN: (数字)9781728196756

ISBN: (纸本)9781728196763

The aim of this paper is to investigate the impact of social distance on people during COVID-19 pandemic using twitter sentiment analysis through a comparison between the k-means clustering and Mini-Batch k-means clustering approaches. To find the most common frequent words, two datasets have been investigated (WHO and Bahrain ministry of health datasets) to be as data preparation and exploration. Another two datasets (English and Arabic datasets) are used in the clustering of k-means. In this paper, a comparison between k-means and Mini-Batch k-means is performed to find a pattern. The word frequency shows that there are several words related to the pandemic. The sentiment analysis result show that in USA, Australia, Nigeria, Canada, and England, most tweets are neutral. However, the majority of tweets are positive tweets from both Italy and India. In addition, the k-means cluster in the English dataset reveals several cluster trends where COVID-19 pandemic procedures are addressed in cluster 1, and health workers are encouraged in cluster 3.

关键词： COVID-19 Social networking (online) Pandemics Sentiment analysis Blogs Elbow Viruses (medical)

来源：评论

学校读者我要写书评

暂无评论

Prediction of Stock Price and Direction Using Neural Networks: datasets Hybrid Modeling Approach

Prediction of Stock Price and Direction Using Neural Network...

引用

data analytics for Business and Industry: Way Towards a Sustainable Economy (ICDABI), International Conference on

作者： Mohamed Al Aradi Nabil Hewahi Big Data Science & Analytics Master Program Collage of Science Univestity of Bahain Sakhir Kingdom of Bahrain Collage of Information Technology Univestity of Bahain Sakhir Kingdom of Bahrain

ISBN: (数字)9781728196756

ISBN: (纸本)9781728196763

Stock prices prediction is one of the most daunting tasks to achieve for day traders, investors, and data scientists. They are complex functions of a wide array of contributing factors that affects the movement dynamics. Politics, social outlook, the company's sales performance, and socio-economic factors all have an influence of how the stock is perceived globally and thus affecting the price movement based on the supply/demand balance. In this work a Framework is proposed to predict the price and movement direction by using multiple datasets that includes news sentiment, social sentiment, company earnings announcement, and technical indicators. A case study was applied on the Apple Inc. stock using Long short-term Memory Neural Networks (LSTM) and Deep Neural Networks (DNN). Results showed superiority of the LSTM model in both predicting stock value [ 75.4 MSE, +-2.52 PE] and the direction with [70.1% classification accuracy] over the DNN model which suffered from prediction lag and dependency on trend indicators achieving [53.1%] in predicting the direction of the stock.

关键词： Predictive models Machine learning Companies Neural networks Market research data models Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Pruritus and Its Association With Cancer and Mortality in Dermatomyositis and Polymyositis: A Nationwide Cohort Study in Taiwan From 2005 to 2022

引用

Dermatologic Therapy 2025年第1期2025卷

作者： Der-Jr Huang Yu-Hsuan Joni Shao Yi-Hsien Shih Woan-Ruoh Lee Ling-Ya Huang Yu-Min Kuo Quoc Thao Trang Pham Hao-Jui Weng Department of Dermatology Taipei Medical University-Shuang Ho Hospital New Taipei City Taiwan shh.org.tw Graduate Institute of Biomedical Informatics College of Medical Science and Technology Taipei Medical University Taipei Taiwan tmu.edu.tw Clinical Big Data Research Center Taipei Medical University Hospital Taipei Taiwan tmuh.org.tw Health Data Analytics and Statistics Center Office of Data Science Taipei Medical University Taipei Taiwan tmu.edu.tw Department of Dermatology School of Medicine College of Medicine Taipei Medical University Taipei Taiwan tmu.edu.tw Graduate Institute of Medical Sciences College of Medicine Taipei Medical University Taipei Taiwan tmu.edu.tw Division of Allergy Immunology and Rheumatology Department of Internal Medicine National Taiwan University Hospital and National Taiwan University Taipei Taiwan ntu.edu.tw Graduate Institute of Clinical Medicine College of Medicine National Taiwan University Taipei Taiwan ntu.edu.tw International Ph.D. Program in Cell Therapy and Regenerative Medicine College of Medicine Taipei Medical University Taipei Taiwan tmu.edu.tw Department of Dermatology Faculty of Medicine University of Medicine and Pharmacy at Ho Chi Minh City Ho Chi Minh City Vietnam hcmut.edu.vn Graduate Institute of Clinical Medicine College of Medicine Taipei Medical University Taipei Taiwan medcol.mw

Background: Pruritus is the most common initial symptom reported by patients with dermatomyositis (DM) and polymyositis (PM). However, there is limited data regarding the impact of pruritus on cancer and mortality in patients with DM and PM. In this study, we aimed to investigate how pruritus is associated with cancer and mortality in patients with DM and PM. Methods: This nationwide, population-based retrospective cohort study included adult DM and PM patients from Taiwan’s National Health Insurance Research database between 2005 and 2022. Sex- and age-matched pruritic patients, identified by over 6 weeks of antipruritic medication use, and nonpruritic patients were analyzed. The primary outcome was cancer occurrence or all-cause mortality. The association between pruritus and these outcomes was estimated using Cox proportional hazards models. Results: Among 919 matched pairs of pruritic and nonpruritic patients, cancer was observed in 19.96% in the long-term pruritic group (LPG), 14.63% in the short-term pruritic group (SPG), and 10.34% in the non-pruritic group (NPG) ( p < 0.0001). All-cause mortality was documented as 30.37% in the LPG, 29.69% in the SPG, and 37.76% in the NPG ( p < 0.0001). After adjusting for sex, age, and other comorbidities, pruritus was associated with an increased risk of cancer (hazard ratio (HR) 1.708, 95% confidence interval (CI) 1.229–2.374) and a lower risk of all-cause mortality (HR 0.483, 95% CI 0.409–0.569). Conclusion: This population-based study revealed that pruritus appeared to be associated with increased risks of cancer and decreased all-cause mortality. Thus, pruritus may serve as a pragmatic factor for risk stratification and tailored treatment strategies in DM and PM. Cancer screening, particularly for nasopharyngeal and breast cancers in East Asian populations, is recommended for patients with DM or PM, especially those presenting with pruritus. Meanwhile, patients without pruritus may require vigilant management for pote

关键词： cancer dermatomyositis idiopathic inflammatory myopathies mortality polymyositis pruritus

来源：评论

学校读者我要写书评

暂无评论

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

请选择保存的检索档案：

请选择收藏分类：

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

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

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：