检索结果-内蒙古大学图书馆

Role of Red Cell Indices in Screening for Beta Thalassemia Trait: an Assessment of the Individual Indices and Application of machine learning algorithm

引用

INDIAN JOURNAL OF HEMATOLOGY AND BLOOD TRANSFUSION 2021年第3期37卷 453-457页

作者： Jahan, Aarzoo Singh, Garima Gupta, Ruchika Sarin, Namrata Singh, Sompal Hindu Rao Hosp Dept Pathol Delhi India ICMR Natl Inst Canc Prevent & Res Div Cytopathol Noida India

Antenatal screening for beta thalassemia trait (BTT) followed by counseling of couples is an efficient way of thalassemia control. Since high performance liquid chromatography (HPLC) is costly, other cost-effective screening methods need to be devised for this purpose. The present study was aimed at evaluating the utility of red cell indices and machine learning algorithms including an artificial neural network (ANN) in detection of BTT among antenatal women. This cross-sectional study included all antenatal women undergoing thalassemia screening at a tertiary care hospital. Complete blood count followed by HPLC was performed. Receiver operating characteristic (ROC) curve analysis was performed for obtaining optimal cutoff for each of the indices with determination of test characteristics for detection of BTT. machine learning algorithms including C4.5 and Naive Bayes (NB) classifier and a back-propagation type ANN including the red cell indices was designed and tested. Over a period of 15 months, 3947 patients underwent thalassemia screening. BTT was diagnosed in 5.98% of women on the basis of HPLC. ROC analysis yielded the maximum accuracy of 63.8%, sensitivity and specificity of 66.2% and 63.7%, respectively for Mean corpuscular hemoglobin concentration (MCHC). The C4.5 and NB classifier had accuracy of 88.56%-82.49% respectively while ANN had an overall accuracy of 85.95%, sensitivity of 83.81%, and specificity of 88.10% in detection of BTT. The present study highlights that none of the red cell parameters standalone is useful for screening for BTT. However, ANN with combination of all the red cell indices had an appreciable sensitivity and specificity for this purpose. Further refinements of the neural network can provide an appropriate tool for use in peripheral settings for thalassemia screening.

关键词： Red cell indices Beta thalassemia trait machine learning algorithm

来源：评论

学校读者我要写书评

暂无评论

An Efficient Unstructured Big Data Analysis Method for Enhancing Performance using machine learning algorithm ocr issue v22

An Efficient Unstructured Big Data Analysis Method for Enhan...

引用

International Conference on Circuit, Power and Computing Technologies (ICCPCT)

作者： Reshmy, A. K. Paulraj, D. Anna Univ Madras 600025 Tamil Nadu India RMD Engn Coll Dept CSE Madras Tamil Nadu India

ISBN: (纸本)9781479970759

In this modern world, data mining technology holds an essential position in all the major Engineering fields. Handling of Unstructured Big Data is an essential task of this era. At present, making the maximum advantage of parallel processing know-hows and the task of rapid examination of huge data steadily and continuously transmitted or received from various sources is becoming popular or conventional. The big data analytics job is fragmented into smaller jobs and ran over tens, hundreds or thousands of product servers by the parallel processing architecture. This helps in maintaining the data center cost efficient and facilitates easy handling of the enormous work in an efficient way. In this paper, proposed solution takes online consumer purchase. The online system has unrivalled bank of data on online consumer purchasing behavior that can be mined from its 100 million customers accounts. They use customer click -stream data and historical purchase data of all those 100 million customers and each user is shown personalized results on customized web pages. For improving Big Data performance the machine learning Method i.e. K -Nearest Neighbour algorithm used to support to take good analysis. Hadoop simulator is used to solve this kind of task.

关键词： Unstructured Big Data machine learning algorithm Parallel Processing Technologies Hadoop Frame Work

来源：评论

学校读者我要写书评

暂无评论

Selection of a machine learning algorithm for OSHA fatalities

Selection of a machine learning algorithm for OSHA fatalitie...

引用

Annual IEEE Technology and Engineering Management Conference (TEMSCON)

作者： Mohammed, Jaby Mahmud, Md Jubaer Illinois State Univ Dept Technol Normal IL 61761 USA

ISBN: (纸本)9781728142241

Traditional programming has already cleared its path to machine learning. With the abundance of data that is available in different applications and fields, it has grown exponentially in the past years. With the available data, machine learning models can predict the output. The different models that have been used have transformed a wide range of real-world applications. Workplace safety is one of the most important factors that make an organization successful. Every organization has a plan that describes what employees should do in order to prevent injury, but still, accidents happen at the workplace. Accident related data is available with the Occupational Safety and Health Administration (OSHA). There are different machine learning algorithms that are used to predict the required output. In this paper, the authors are investigating different machine learning algorithms and their accuracy to the predicted results.

关键词： machine learning OSHA machine learning algorithm fatalities

来源：评论

学校读者我要写书评

暂无评论

machine learning algorithm based on jaw feature points assist complex maxillary and mandibular reconstruction

引用

JOURNAL OF STOMATOLOGY ORAL AND MAXILLOFACIAL SURGERY 2023年第1期124卷 101343页

作者： Han, Jing Liu, Zijia Zhou, Zijie Liu, Yige Zhai, Guangtao Liu, Jiannan Shanghai Jiao Tong Univ Shanghai Peoples Hosp 9 Sch Med Dept Oral & Maxillofacial Head & Neck Oncol Shanghai 200011 Peoples R China Shanghai Jiao Tong Univ Coll Stomatol Shanghai 200011 Peoples R China Natl Clin Res Ctr Oral Dis Shanghai 200011 Peoples R China Shanghai Key Lab Stomatol Shanghai 200011 Peoples R China Shanghai Jiao Tong Univ Sch Elect Informat & Elect Engn Shanghai 200241 Peoples R China

Purposes: Large-scale jaw reconstruction can hardly achieve satisfactory results only by relying on doctors' experience. In this study, we assessed a new approach using a machine learning algorithm based on jaw feature points to assist complex jaw reconstruction in patients with maxillary and mandibular defects. Methods: One hundred and two computed tomography (CT) data on the jaw were collected and 16 skeletal marker points on the jaw were selected. The machine learning algorithm learned the positional relationship between points and built a model, which was used to predict the coordinate position of an unknown point. Then the model was used for a surgical plan in clinical cases. Results: The linear regression model based on machine learning can control the error within 3 mm. In linear models, Lasso has a slight advantage over the others. We used Lasso to predict the missing points for two patients with maxillary and mandibular defect, respectively. The operation was carried out as planned, and the defects were successfully repaired. Conclusions: The restoration of jaw feature points based on a machine learning algorithm is expected to solve large-scale jaw defects without contralateral reference. (c) 2022 Published by Elsevier Masson SAS.

关键词： machine learning algorithm Jaw reconstruction Jaw feature points

来源：评论

学校读者我要写书评

暂无评论

Power Quality Disturbance Detection using machine learning algorithm

Power Quality Disturbance Detection using Machine Learning A...

引用

IEEE International Conference on Advances and Developments in Electrical and Electronics Engineering (ICADEE)

作者： Sekar, Kavaskar Kumar, Sendil S. Karthick, K. Panimalar Engn Coll Dept Elect & Elect Engn Chennai Tamil Nadu India New Prince Bhavani Coll Engn & Technol Dept Elect & Elect Engn Chennai Tamil Nadu India GMR Inst Technol Dept Elect & Elect Engn Tirupati Andhra Pradesh India

ISBN: (纸本)9781728192512

The challenge of Power Quality Disturbances (PQDs) is now admitted as a crucial characteristic of a power system network. For structured power quality, disturbance causes must be recognized and regulated. This is accomplished through detection and classification of different PQDs. This article suggests a methodology to detect and classify PQDs using machine learning algorithm. The features of the signals are extracted through a mathematical morphology filter. These features are input to train one of the machine learning algorithm called Decision Tree (DT) and builds DT model to test and classify PQDs. For the purpose of classification, ten different types of disturbances are considered in this work. The proposed method is demonstrated on a data which is generated through PQD model using MATLAB. The performance of the proposed approach is good in PQD detection with accuracy rate of 99.95%.

关键词： Power Quality Disturbances Mathematical Morphology Decision Tree machine learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Real Time BIG Data Analytic: Security Concern and Challenges with machine learning algorithm

Real Time BIG Data Analytic: Security Concern and Challenges...

引用

Conference on IT in Business, Industry and Government (CSIBIG)

作者： Singh, Jainendra Maharaja Surajmal Inst Dept Comp Sci New Delhi India

ISBN: (纸本)9781479930630;9781479930647

with great power of data comes great responsibility! A big data initiative should not only focus on the volume, velocity or variety of the data, but also on the best way to protect it. Security is usually an afterthought, but Elemental provides the right technology framework to get you the deep visibility and multilayer security any big data project requires. Multilevel protection of your data processing nodes means implementing security controls at the application, operating system and network level while keeping a bird's eye on the entire system using actionable intelligence to deter any malicious activity, emerging threats and vulnerabilities. Advances in machine learning (ML) provide new challenges and solutions to the security problems encountered in applications, technologies and theories. machine learning (ML) techniques have found widespread applications and implementations in security issues. Many ML techniques, approaches, algorithms, methods and tools are extensively used by security experts and researchers to achieve better results and to design robust systems.

关键词： Big Data Analytic machine learning algorithm Security Challenges Mahout Hadoop

来源：评论

学校读者我要写书评

暂无评论

GIS-based machine learning algorithm for flood susceptibility analysis in the Pagla river basin, Eastern India

引用

Natural Hazards Research 2023年第3期3卷 420-436页

作者： Saikh, Nur Islam Mondal, Prolay Department of Geography Raiganj University West Bengal Raiganj 733134 India

The unique characteristics of drainage conditions in the Pagla river basin cause flooding and harm the socioeconomic environment. The main purpose of this study is to investigate the comparative utility of six machine learning algorithms to improve flood susceptibility and ensemble techniques' capability to elucidate the underlying patterns of floods and make a more accurate prediction of flood susceptibilities in the Pagla river basin. In the present scenario, the frequency of flood conditions in this study area becomes high with heavy and sudden rainfall, so it is essential to study flood mitigation and measure. At first, a spatial flood database was built with 200 flood locations and sixteen flood influencing factors, and its process with the help of the Geographic Information System (GIS) environment and build up different models applying the machine learning techniques. It has found different flood susceptibility zone using machine learning-based Artificial Neural Network (ANN), Support Vector machine (SVM), Random Forest (RF), Reduced Error Pruning Tree (REPTree), Logistic Regression (LR), and Bagging helping GIS environment and the model validation using the Receiver Operating Characteristic (ROC) Curve. Afterward, ensemble all the models to gate comparative accuracy of the flood zone. The calculated areas are under the very high flood susceptibility zone 8.69%, 14.92%, 14.17%, 12.98%, 14.65%, 13.24% and 13.41% for ANN, SVM, RF, REPTree, LR and Bagging, respectively. Finally, ROC curve, the Standard Error (SE), and the Confidence Interval (CI) at 95 per cent were used to assess and compare the performance of the models. The obtained results indicate that all models are highly accepted Area Under Curve (AUC) of ROC between 0.889 (LR) to 0.926 (Ensemble). From the estimation of the accuracy of the applied methods using ROC, it is found that the Ensemble model has the higher capability compared to the other applied models in projecting flood susceptibility in t

关键词： Flood susceptibility GIS machine learning algorithm Pagla river Receiver Operating Characteristic

来源：评论

学校读者我要写书评

暂无评论

machine learning algorithm Identifies Patients at High Risk for Early Complications After Intracranial Tumor Surgery: Registry-Based Cohort Study

引用

NEUROSURGERY 2019年第4期85卷 E756-E764页

作者： van Niftrik, Christiaan H. B. van der Wouden, Frank Staartjes, Victor E. Fierstra, Jorn Stienen, Martin N. Akeret, Kevin Seboek, Martina Fedele, Tommaso Sarnthein, Johannes Bozinov, Oliver Krayenbuehl, Niklaus Regli, Luca Serra, Carlo Univ Hosp Zurich Dept Neurosurg Frauenklin Str 10 CH-8091 Zurich Switzerland Univ Hosp Zurich Clin Neurosci Ctr Zurich Switzerland Univ Zurich Zurich Switzerland Univ Calif Los Angeles Dept Geog Los Angeles CA 90024 USA Northwestern Univ Kellogg Sch Management Management & Org Dept Evanston IL USA

INTRODUCTION: Reliable preoperative identification of patients at high risk for early postoperative complications occurring within 24 h (EPC) of intracranial tumor surgery can improve patient safety and postoperative management. Statistical analysis using machine learning algorithms may generate models that predict EPC better than conventional statistical methods. OBJECTIVE: To train such a model and to assess its predictive ability. METHODS: This cohort study included patients from an ongoing prospective patient registry at a single tertiary care center with an intracranial tumor that underwent elective neurosurgery between June 2015 and May 2017. EPC were categorized based on the Clavien-Dindo classification score. Conventional statistical methods and different machine learning algorithms were used to predict EPC using preoperatively available patient, clinical, and surgery-related variables. The performance of each model was derived from examining classification performance metrics on an out-of-sample test dataset. RESULTS: EPC occurred in 174 (26%) of 668 patients included in the analysis. Gradient boosting machine learning algorithms provided the model best predicting the probability of an EPC. The model scored an accuracy of 0.70 (confidence interval [CI] 0.59-0.79) with an area under the curve (AUC) of 0.73 and a sensitivity and specificity of 0.80 (CI 0.58-0.91) and 0.67 (CI 0.53-0.77) on the test set. The conventional statistical model showed inferior predictive power (test set: accuracy: 0.59 (CI 0.47-0.71);AUC: 0.64;sensitivity: 0.76 (CI 0.64-0.85);specificity: 0.53 (CI 0.41-0.64)). CONCLUSION: Using gradient boosting machine learning algorithms, it was possible to create a prediction model superior to conventional statistical methods. While conventional statistical methods favor patients' characteristics, we found the pathology and surgery-related (histology, anatomical localization, surgical access) variables to be better predictors of EPC.

关键词： machine learning algorithm Complication Brain tumor Neurosurgery Neurocritical care Prediction model

来源：评论

学校读者我要写书评

暂无评论

Implementation of machine learning algorithm on factors Effecting Divorce Rate

Implementation of Machine learning Algorithm on factors Effe...

引用

International Conference on Engineering and Emerging Technologies (ICEET)

作者： Sohail, Sana Aziz, Sadia Tahir, Faizan Haqqui, Sufyan Hussain, Ahsan Usman Inst Technol NEDUET Dept Elect Engn Karachi Pakistan Bahria Univ Dept Comp Sci Islamabad Pakistan Dadabhoy Inst Higher Educ Dept Comp Sci Karachi Pakistan

ISBN: (纸本)9781538632055

With the expanding number of marriages the quantity of detachment and separation are additionally expanding. The major factors that prompt separation can be numerous and there are numerous calculations in machine figuring out how to characterize the variables. The quantity of separation can be avoided and diminished on the off chance that we can have a decent information about the fundamental reasons and practices that can lead a connection to its end. In this paper we have taken a sample data set having some major attributes that causes divorce and comprehended it using 3 different classification algorithm and compared their outcomes. On the premise of their outcomes, we have concluded that which algorithm is more effective for the characterization of the data set in this application

关键词： machine learning algorithm Divorce Rate Artificial Intelligence Social Class

来源：评论

学校读者我要写书评

暂无评论

Detection of COVID-19 Infection from Clinical Findings Using machine learning algorithm 1st

Detection of COVID-19 Infection from Clinical Findings Using...

引用

1st international conference Ambient Intelligence in Health Care (ICAIHC)

作者： Durgadevi, Velusamy Arunagiri, Bharath Dhanapal, Vignesh Seeniraj, Yogesh Krishnan Thirugnanam, Shashangan M Kumarasamy Coll Engn Dept Comp Sci & Engn Karur 639113 India

ISBN: (纸本)9789811960703;9789811960680;9789811960673

COVID-19 infection is a transmissible virus causing acute respiratory syndrome spreading worldwide. The number of patients infected by this deadly virus increases steadily, causing a high mortality rate. Hence, it is crucial to diagnose and identify the COVID-19 infection for earlier treatment of the patients. This study has applied four algorithms, namely, Logistic Regression (LR), Nu-Support Vector machine (Nu-SVM), Multi-layer perceptron (MLP) and Naive Bayes (NB) to identify COVID-19 infection. The clinical laboratory findings of 600 individuals were taken from Hospital Isrelita Albert Einstein, Sao Paulo, Brazil, used in this study. We have selected significant features using Random forest-based recursive feature elimination for predicting the infection. Experiments are conducted with 90% training and 10% testing data. The performance result shows that the Nu-SVM algorithm obtained the prediction accuracy of 95% with 100% sensitivity and 94.23% specificity in predicting the infection. To our knowledge, the result achieved by Nu-SVM is the highest in the literature. Hence, the model can be used as a tool for the initial prediction of COVID-19 disease.

关键词： Clinical findings COVID-19 infection machine learning algorithm Nu-support vector machine

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：