检索结果-内蒙古大学图书馆

Evaluation of Robust classifier algorithm for Tissue Classification under Various Noise Levels

ETRI JOURNAL 2017年第1期39卷 87-96页

作者： Youn, Su Hyun Shin, Ki Young Choi, Ahnryul Mun, Joung Hwan Sungkyunkwan Univ Dept Biomechatron Engn Suwon South Korea Univ Sci & Technol Dept Energy & Power Convers Engn Daejeon South Korea

Ultrasonic surgical devices are routinely used for surgical procedures. The incision and coagulation of tissue generate a temperature of 40 degrees C-150 degrees C and depend on the controllable output power level of the surgical device. Recently, research on the classification of grasped tissues to automatically control the power level was published. However, this research did not consider the specific characteristics of the surgical device, tissue denaturalization, and so on. Therefore, this research proposes a robust algorithm that simulates noise to resemble real situations and classifies tissue using conventional classifier algorithms. In this research, the bioimpedance spectrum for six tissues (liver, large intestine, kidney, lung, muscle, and fat) is measured, and five classifier algorithms are used. A signal-to-noise ratio of additive white Gaussian noise diversifies the testing sets, and as a result, each classifier's performance exhibits a difference. The k-nearest neighbors algorithm shows the highest classification rate of 92.09% (p < 0.01) and a standard deviation of 1.92%, which confirms high reproducibility.

关键词： Ultrasonic surgical device Power level autocontrol Bioimpedance classifier algorithm Additive white Gaussian noise

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Machine Learning algorithms for 5G Coverage Prediction: Identification of Dominant Feature Parameters and Prediction Accuracy

引用

IEEE ACCESS 2024年 12卷 18939-18956页

作者： Yuliana, Hajiar Iskandar Hendrawan Inst Teknol Bandung Sch Elect Engn & Informat Bandung 40132 Indonesia

5G technology is a key factor in delivering faster and more reliable wireless connectivity. One crucial aspect in 5G network planning is coverage prediction, which enables network providers to optimize infrastructure deployment and deliver high-quality services to customers. This study conducts a comprehensive analysis of machine learning algorithms for 5G coverage prediction, focusing on dominant feature parameters and accuracy. Notably, the Random Forest algorithm demonstrates superior performance with an RMSE of 1.14 dB, MAE of 0.12, and R2 of 0.97. The CNN model, the standout among deep learning algorithms, achieves an RMSE of 0.289, MAE of 0.289, and R2 of 0.78, showcasing high accuracy in 5G coverage prediction. Random Forest models exhibit near-perfect metrics with 98.4% accuracy, precision, recall, and F1-score. Although CNN outperforms other deep learning models, it slightly trails Random Forest in performance. The research highlights that the final Random Forest and CNN models outperform other models and surpass those developed in previous studies. Notably, 2D Distance Tx Rx emerges as the most dominant feature parameter across all algorithms, significantly influencing 5G coverage prediction. The inclusion of horizontal and vertical distances further improves prediction results, surpassing previous studies. The study underscores the relevance of machine learning and deep learning algorithms in predicting 5G coverage and recommends their use in network development and optimization. In conclusion, while the Random Forest algorithm stands out as the optimal choice for 5G coverage prediction, deep learning algorithms, particularly CNN, offer viable alternatives, especially for spatial data derived from satellite images. These accurate predictions facilitate efficient resource allocation by network providers, ensuring high-quality services in the rapidly evolving landscape of 5G technology. A profound understanding of coverage prediction remains pivotal for suc

关键词： Machine learning algorithms Prediction algorithms 5G mobile communication Deep learning Machine learning Predictive models Classification algorithms Performance evaluation 5G coverage prediction classifier algorithm deep learning performance evaluation feature importance

来源：评论

学校读者我要写书评

暂无评论

To explore the optimal solution of different mapping units and classifiers and their application in the susceptibility evaluation of slope geological disasters

引用

ECOLOGICAL INDICATORS 2024年 163卷

作者： Zhang, Shaohan Tan, Shucheng Wang, Haishan Shi, Yiqi Ding, Duanyu Sun, Yongqi Gao, Hongxia Yunnan Univ Inst Int Rivers & Ecosecur Kunming 650500 Yunnan Peoples R China Yunnan Int Joint Lab Crit Mineral Resource Kunming 650500 Yunnan Peoples R China Yunnan Univ Sch Earth Sci Kunming 650500 Yunnan Peoples R China Kunming Univ Sci & Technol Fac Architecture & City Planning Kunming 650500 Yunnan Peoples R China Shilin Scen Area Management Bur Kunming Yunnan Peoples R China

Slope geological disaster is a type of natural disaster that is prevalent in the plateau mountainous area. Its occurrence frequently brings substantial harm to the local human population and living environment. The aim of this research is to investigate the suitability of various mapping units for different classifiers in the process of creating susceptibility zoning maps for slope geological disasters and to evaluate the effectiveness of each model. Concurrently, the susceptibility map produced by the high-accuracy model will assist relevant authorities in conducting disaster management tasks and also serve as a reference for modeling the susceptibility assessment of environmental geological disasters in other mountainous regions. Fuyuan County of China was considered as the research area, based on two different mapping units and four classifiers. Nine factors leading to disasters, such as elevation and topographic relief, were chosen as the evaluation indexes. With the help of the ArcGIS platform, the zoning map of geo-logical disaster susceptibility is drawn. Ultimately, the accuracy of the evaluation results was verified by the receiver operating characteristic curve and the confusion matrix. The findings indicate that all approaches are capable of producing susceptibility maps for geological disasters. However, the outcomes from the four classifiers that utilize slope units are more precise and logical than those that employ grid units. Lithology and the water system emerge as the most significant factors causing disasters in the study area, while the influence of fault zones is found to be minimal. The integration of the slope unit with the random forest classifier achieves the highest accuracy in predictions, maximizing the capabilities of both, and presents a promising application in the susceptibility mapping of slope geological disasters.

关键词： Slope types geological hazard Susceptibility classifier algorithm Mapping unit Fuyuan County

来源：评论

学校读者我要写书评

暂无评论

A hybrid system for Parkinson's disease diagnosis using machine learning techniques

引用

INTERNATIONAL JOURNAL OF SPEECH TECHNOLOGY 2021年第3期25卷 583页

作者： Lamba, Rohit Gulati, Tarun Alharbi, Hadeel Fahad Jain, Anurag Maharishi Markandeshwar Maharishi Markandeshwar Engn Coll Dept Elect & Commun Engn Ambala Haryana India Univ Hail Coll Comp Sci & Engn Hail Saudi Arabia Univ Petr & Energy Studies Sch Comp Sci Virtualizat Dept Dehra Dun Uttarakhand India

Parkinson's disease is a neurodegenerative disorder that progresses slowly and its symptoms appear over time, so its early diagnosis is not easy. A neurologist can diagnose Parkinson's by reviewing the patient's medical history and repeated scans. Besides, body movement analysts can diagnose Parkinson's by analyzing body movement. Recent research work has shown that changes in speech can be used as a measurable indicator for early Parkinson's detection. In this work, the authors propose a speech signal-based hybrid Parkinson's disease diagnosis system for its early diagnosis. To achieve this, the authors have tested several combinations of feature selection approaches and classification algorithms and designed the model with the best combination. To formulate various combinations, three feature selection methods such as mutual information gain, extra tree, and genetic algorithm and three classifiers namely naive bayes, k-nearest-neighbors, and random forest have been used. To analyze the performance of different combinations, the speech dataset available at the UCI (University of California, Irvine) machine learning repository has been used. As the dataset is highly imbalanced so the class balancing problem is overcome by the synthetic minority oversampling technique (SMOTE). The combination of genetic algorithm and random forest classifier has shown the best performance with 95.58% accuracy. Moreover, this result is also better than the recent work found in the literature.

关键词： Parkinson&apos s disease Decision support system Feature selection classifier algorithm Machine learning

来源：评论

学校读者我要写书评

暂无评论

Machine learning-based model for prediction of power consumption in smart grid- smart way towards smart city

引用

EXPERT SYSTEMS 2022年第5期39卷 e12832-e12832页

作者： Tiwari, Shamik Jain, Anurag Ahmed, Nada Mohamed Osman Sid Charu Alkwai, Lulwah M. Dafhalla, Alaa Kamal Yousif Hamad, Sawsan Ali Saad Univ Petr & Energy Studies Sch Comp Sci Dehra Dun 248007 Uttarakhand India Univ Hail Coll Comp Sci & Engn Hail Saudi Arabia Jaypee Inst Informat Technol Dept CSE & IT Noida India

A smart city is an idea that is realized by the computing of a large amount of data collected through sensors, cameras, and other electronic methods to provide services, manage resources and solve daily life problems. The transformation of the conventional grid to a smart grid is one step in the direction towards smart city realization. An electric grid is composed of control stations, generation centres, transformers, communication lines, and distributors, which helps in transferring power from the power station to domestic and commercial consumers. Present electric grids are not smart enough that they can estimate the varying power requirement of the consumer. Also, these conventional grids are not enough robust and scalable. This has become the motivation for shifting from a conventional grid to a smart grid. The smart grid is a kind of power grid, which is robust and adapts itself to the varying needs of the consumer and self-healing in nature. In this way, the transformation from a conventional grid to a smart grid will help the government to make a smart city. The emergence of machine learning has helped in the prediction of the stability of the grid under the dynamically changing requirement of the consumer. Also, the usage of a variety of sensors will help in the collection of real-time consumption data. Through machine learning algorithms, we can gain an insight view of the collected data. This has helped the smart grid to convert into a robust smart grid, as this will help in avoiding the situation of failure. In this work, the authors have applied logistic regression, decision tree, support vector machine, linear discriminant analysis, quadratic discriminant analysis, naive Bayes, random forest, and k-nearest neighbour algorithms to predict the stability of the grid. The authors have used the smart grid stability dataset freely available on Kaggle to train and test the models. It has been found that a model designed using the support vector machine algori

关键词： classifier algorithm machine learning prediction model smart city smart grid

来源：评论

学校读者我要写书评

暂无评论

CICIDS-2017 Dataset Feature Analysis With Information Gain for Anomaly Detection

引用

IEEE ACCESS 2020年 8卷 132911-132921页

作者： Kurniabudi Stiawan, Deris Darmawijoyo Idris, Mohd Yazid Bin Bin Bamhdi, Alwi M. Budiarto, Rahmat Univ Sriwijaya Fac Engn Palembang 30128 Indonesia Univ Dinamika Bangsa Fac Comp Sci Jambi 36138 Indonesia Univ Sriwijaya Fac Comp Sci Palembang 30128 Indonesia Univ Sriwijaya Fac Math & Nat Sci Palembang 30128 Indonesia Univ Teknol Malaysia Fac Engn Sch Comp Johor Baharu 81310 Malaysia Umm Al Qura Univ Coll Comp Dept Comp Sci Al Qunfudhah 21912 Saudi Arabia Albaha Univ Coll Comp Sci & IT Al Aqiq 657797738 Saudi Arabia

Feature selection (FS) is one of the important tasks of data preprocessing in data analytics. The data with a large number of features will affect the computational complexity, increase a huge amount of resource usage and time consumption for data analytics. The objective of this study is to analyze relevant and significant features of huge network traffic to be used to improve the accuracy of traffic anomaly detection and to decrease its execution time. Information Gain is the most feature selection technique used in Intrusion Detection System (IDS) research. This study uses Information Gain, ranking and grouping the features according to the minimum weight values to select relevant and significant features, and then implements Random Forest (RF), Bayes Net (BN), Random Tree (RT), Naive Bayes (NB) and J48 classifier algorithms in experiments on CICIDS-2017 dataset. The experiment results show that the number of relevant and significant features yielded by Information Gain affects significantly the improvement of detection accuracy and execution time. Specifically, the Random Forest algorithm has the highest accuracy of 99.86% using the relevant selected features of 22, whereas the J48 classifier algorithm provides an accuracy of 99.87% using 52 relevant selected features with longer execution time.

关键词： Feature extraction Classification algorithms Anomaly detection Information filters Support vector machines Filtering algorithms Feature selection anomaly detection information gain CICIDS-2017 dataset classifier algorithm

来源：评论

学校读者我要写书评

暂无评论

Exploring the Application of Machine Learning algorithms to the City Public Bus Transport 14

Exploring the Application of Machine Learning Algorithms to ...

引用

14th IEEE International Conference on Big Data Science and Engineering (BigDataSE)

作者： Alicea, Michael McDonald, Arlen P. Tang, Chunyang Yang, Jeong Texas A&M Univ San Antonio Dept Comp & Cyber Secur San Antonio TX 78224 USA

ISBN: (纸本)9781665403962

Supervised machine learning is a method that attempts to emulate experienced-based learning similar to how humans learn. This study leverages supervised machine learning algorithms to determine the most important factors of the on-time performance of a San Antonio's VIA bus system using public data sets collected from the 2019 San Antonio Datathon event. A variety of algorithms are used to create models that are capable of predicting on-time performance to see if a bus route met standards on a given day. The algorithms present in the python libraries Sci Kit Learn and Stats Models. Once an algorithm has proven to be highly accurate at predicting the on-time performance, a further study was conducted into the decision-making process of each algorithm to find out which feature it determined to be most important. By knowing the most important feature of the on-time performance, the study gives insight as to what factors affect the performance of bus routes.

关键词： Machine Learning Bus Transportation Supervised algorithm classifier algorithm City Bus

来源：评论

学校读者我要写书评

暂无评论

21st Century Learning Skills Predictive Model Using PART algorithm 2019

21st Century Learning Skills Predictive Model Using PART Alg...

引用

3rd International Conference on Machine Learning and Soft Computing (ICMLSC)

作者： Aguinaldo, Betchie E. Isabela State Univ Cauayan Isabela Philippines

ISBN: (纸本)9781450366120

The skillset of a graduate is the key to success to perform successfully in their chosen career path, thus, academic institution continuously develops strategic ways to develop and prepare the 21st century Learning skills of the student before they completed the higher education studies. This paper presents the 21st Century Learning Predictive Model in Programming Logic Formulation using PART classifier algorithm. It also aims to determine the significant attributes in the development of dataset for predictive model and generate a predictive model for 21st Century Learning Skills using PART classifier algorithm. Six (6) standardized questionnaire of 21st Century Learning Skills of one hundred eight (180) students were coded and used as a dataset of the study. The result of the customized assessment exam in programming logic formulation was used as response attributes of the datasets. As a result of the study, five (5) rules were generated using PART classifier algorithm. Among the 21st Century Learning skills, Communication is the strongest predicting attributes of successful performance of students in programming logic formulation.

关键词： Data Mining Predictive Model classifier algorithm Employability

来源：评论

学校读者我要写书评

暂无评论

Role of Artificial Intelligence and Machine Learning in Resolving the Issues and Challenges with Prosthetic Knees 4th

Role of Artificial Intelligence and Machine Learning in Reso...

引用

4th International Conference on Information, Communication and Computing Technology (ICICCT)

作者： Salwan, Deepali Kant, Shri Pandian, G. Pt Deen Dayal Upadhyaya Natl Inst Persons Phys Di New Delhi India Sharda Univ Res & Technol Dev Ctr Sch Engn & Technol Dept Comp Sci Greater Noida India

ISBN: (纸本)9789811513848;9789811513831

From the ancient times until today, in the age of Artificial Intelligence, field of prosthetics is where human is continuously striving to do better. Upper limb amputation deprives the person from routine activities, which the amputee never thought was important, on the other hand lower limb amputation restricts the person's physical movements to a great extent. In this article we will highlight the issues and challenges with the active lower limb prosthetic from the socket to the knee, the material, the sensors and the algorithms used for controlling the movement. How each of them plays a pivotal role in providing a comfortable gait which resembles the natural human gait, this article throws light upon where are we in terms of advancement in lower limb prosthetic and the issues and challenges which are still there even with the finest active artificial knee available.

关键词： Prosthetic-knee Artificial-knee Lower limb amputation Microprocessor prosthetic knee Sensors classifier algorithm Sockets and liners

来源：评论

学校读者我要写书评

暂无评论

Employability Predictive Model Evaluator Using PART and JRip classifier 2018

Employability Predictive Model Evaluator Using PART and JRip...

引用

6th International Conference on Information Technology - IoT and Smart City (ICIT)

作者： Gatbonton, Twinkle Mae C. Aguinaldo, Betchie E. Isabela State Univ City Of Ilagan Isabela Philippines Isabela State Univ Cauayan Isabela Philippines

ISBN: (纸本)9781450366298

Employability is the most challenging outcome of higher education institution. It is evident that there are a number of information technology (IT) graduates that failed to address the need of information technology industry, hence, result to job mismatch and high unemployment rate. This presents the Employability Predictive Model Evaluator using PART and JRip classifier algorithm. The study also aims to determine the significant attributes in the development of dataset for predictive model and generate a predictive model for employability of IT graduates using PART and JRip classifier algorithm. The 4-year taken courses of graduates from school year 2013-2016 and employability status extracted from e-Graduate Tracer Survey (eGTS) were used as dataset of the study. The academic courses from the university registrar were clustered based on Commission on Higher Education of the Philippines information technology courses which includes General Education, IT Common Courses, IT Professional Courses, IT Elective Courses and On-the-Job Training Grade. JRip generated two (2) rules while PART generated seven (7) rules, which were used as the logical conditions in the development of Employability Predictive Model Evaluator for IT graduates.

关键词： Data mining predictive model classifier algorithm employability

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：