检索结果-内蒙古大学图书馆

Analysis of COVID-19 Datasets Using Statistical Modelling and Machine Learning Techniques to Predict the Disease

SN computer Science 2024年第1期5卷 181页

作者： Nramban Kannan, Senthil Kumar Kolla, Bhanu Prakash Sengan, Sudhakar Muthusamy, Rajendiran Manikandan, Raja Patel, Kanubhai K. Dadheech, Pankaj Department of Computer Science and Engineering School of Computing Institute of Science and Technology (Deemed to Be University) Vel Tech Rangarajan Dr. Sagunthala R&D Tamil Nadu Chennai 600062 India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram Guntur 522302 India Department of Computer Science and Engineering PSN College of Engineering and Technology Tamil Nadu Tirunelveli 627152 India Department of Computer Science and Engineering Panimalar Engineering College Chennai 600123 India Department of Electronics and Communication Engineering K. Ramakrishnan College of Technology Tamil Nadu Trichy 621112 India Charotar University of Science and Technology Gujarat 388421 India Department of Computer Science and Engineering Management and Gramothan (SKIT) Swami Keshvanand Institute of Technology Rajasthan Jaipur 302017 India

Sustainable development is crucial for a prosperous future, but epidemic diseases like Coronavirus Disease 2019 (COVID-19) pose real and complex challenges. The global pandemic, declared by the WHO on March 11, 2020, has led to significant loss of life and challenges in public health, economy, food systems, and social life. This research article aims to develop a Machine Learning (ML) model to predict a patient’s COVID-19 diagnosis, as early diagnosis is fundamental for controlling the spread of COVID-19. An investigation of the literature and a research study is conducted to find suitable mathematical methods and measure how they impact prediction models. This paper analyses COVID-19 pandemic deaths, confirmed cases, and recovered individuals using Time Series Analysis (TSA) to study the disease's impacts and understand the TAS. A forecasting model can predict future COVID cases by analyzing trends in time-series and connecting global changes with government restrictions. Since higher predictive accuracy is the limitation of ensemble learning algorithms, better ML approaches are proposed here. Autocorrelation plots clearly showed the results executed for the considered objectives. The hybrid ARIMA algorithm proposed in this work proved adequate results. © 2024, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Analysis and visualization Autocorrelation COVID-19 Machine learning Time-series analysis Time-series forecasting

来源：评论

学校读者我要写书评

暂无评论

Age-Based Automatic Voice Conversion Using Blood Relation for Voice Impaired

引用

computers, Materials & Continua 2022年第2期70卷 4027-4051页

作者： Palli Padmini C.Paramasivam G.Jyothish Lal Sadeen Alharbi Kaustav Bhowmick Department of Electronics&Communication Engineering Amrita School of EngineeringBengaluruAmrita Vishwa VidyapeethamIndia Center for Computational Engineering and Networking(CEN) Amrita School of EngineeringCoimbatoreAmrita Vishwa VidyapeethamIndia Department of Software Engineering College of Computer and Information SciencesKing Saud UniversityRiyadhSaudi Arabia Department of Electronics and Communication Engineering PES UniversityBengaluruIndia

The present work presents a statistical method to translate human voices across age groups,based on commonalities in voices of blood *** age-translated voices have been naturalized extracting the blood relation features e.g.,pitch,duration,energy,using Mel Frequency Cepstrum Coefficients(MFCC),for social compatibility of the *** system has been demonstrated using standard English and an Indian *** voice samples for resynthesis were derived from 12 families,with member ages ranging from 8–80 *** voice-age translation,performed using the Pitch synchronous overlap and add(PSOLA)approach,by modulation of extracted voice features,was validated by perception *** translated and resynthesized voices were correlated using Linde,Buzo,Gray(LBG),and Kekre’s Fast Codebook generation(KFCG)*** translated voice targets,a strong(θ>∼93%andθ>∼96%)correlation was found with blood relatives,whereas,a weak(θ<∼78%andθ<∼80%)correlation range was found between different families and different gender from same *** study further subcategorized the sampling and synthesis of the voices into similar or dissimilar gender groups,using a support vector machine(SVM)choosing between available voice ***,∼96%,∼93%,and∼94%accuracies were obtained in the identification of the gender of the voice sample,the age group samples,and the correlation between the original and converted voice samples,*** results obtained were close to the natural voice sample features and are envisaged to facilitate a near-natural voice for speech-impaired easily.

关键词： Blood relations KFCG LBG MFCC vector quantization correlation speech samples same-gender dissimilar gender voice conversion PSOLA SVM

来源：评论

学校读者我要写书评

暂无评论

Enhancing Skin Cancer Detection Through Automated Classification Using Convolutional Neural Networks 1

引用

7th International Conference on Intelligent Computing and Optimization, ICO 2023

作者： Hossain, Md Jakir Bhuiyan, M. D. Wahidul Islam Raisa, Sadia Afrin Tomal, Minhazul Amin Jennifer, Sanjeda Sara Reza, Ahmed Wasif Siddique, Nazmul Department of Computer Science and Engineering East West University Dhaka Bangladesh School of Computing Engineering and Intelligent Systems Ulster University Londonderry United Kingdom

ISBN: (数字)9783031733185

ISBN: (纸本)9783031733178

Skin cancer presents a significant public health concern, necessitating early detection and intervention to mitigate life-threatening consequences. Despite its prevalence, skin cancer is not always given the attention it deserves. In this paper, we propose an automated procedure for distinguishing skin cancers using several neural network algorithms. We used the MobileNet architecture whose accuracy is not very high and this is why we have also used other algorithms such as Sequential CNN (Convolution Neural Network), VGG16, and Xception to improve the accuracy of our model. By comparing these algorithms, we found that the Sequential CNN performed best with an accuracy of 94%. The proposed model utilizes the Sequential CNN algorithm to achieve a high level of accuracy, which is of utmost importance for the early detection of skin cancer. The high accuracy of the proposed model makes it a promising tool for detecting skin cancer early. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

An Innovative Method in Classifying and predicting the accuracy of intrusion detection on cybercrime by comparing Decision Tree with Support Vector Machine

An Innovative Method in Classifying and predicting the accur...

引用

2022 International Conference on Business Analytics for Technology and Security, ICBATS 2022

作者： Kumar, Marri Ranjith Malathi, K. Saveetha University Saveetha School of Engineering Department of Computer Science and Engineering Chennai India Saveetha School of Engineering Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9781665409209

Classifying and predicting the accuracy of intrusion detection on cybercrime by comparing machine learning methods such as Innovative Decision Tree (DT) with Support Vector Machine (SVM). By comparing the Decision Tree (N=20) and the Support Vector Machine algorithm (N=20) two classes of machine learning classifiers were used to determine the accuracy. The decision Tree (99.19%) has the highest accuracy than the SVM (98.5615%) and the independent T-test was carried out (=.507) and shows that it is statistically insignificant (p>0.05) with a confidence value of 95%. by comparing Innovative Decision Tree and Support Vector Machine. The Decision Tree is more productive than the Support Vector Machine for recognizing intruders with substantially checked, according to the significant analysis. © 2022 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Oil Spill Classification using Machine Learning 18

Oil Spill Classification using Machine Learning

引用

18th INDIAcom;11th International Conference on Computing for Sustainable Global Development, INDIACom 2024

作者： Ravulakollu, Kiran Kumar Dewan, Ritu Verma, Kimmi Garg, Setu Mishra, Sunil Kumar Sharan, Bhagwati Woxsen University School of Technology Hyderabad India Galgotias College of Engineering & Technology Department of Computer Science and Engineering Uttar Pradesh India Delhi Technical Campus Greater Noida India Its Engineering College Ece Department Greater Noida India Accurate Institute of Management and Technology Greater Noida India Srm University-AP School of Engineering and Sciences Department of Computer Science and Engineering Guntur India

ISBN: (纸本)9789380544519

An Oil Spill is the accidental discharge of liquid petroleum hydrocarbons into the environment. It is one of the major causes of marine and terrestrial pollution which affects marine ecosystems, marine animals most importantly, the economic system and human society. The study on this will help save lives, protect sensitive ecosystems, and minimize the economic impact of oil spills. This paper provides an overview of oil spill classification techniques using ML approaches, along with their advantages and limitations and recent advancements in the field. The classification techniques that are considered in this article are Random Forest Classifier, Decision Tree Classifier, K-Nearest Neighbors (KNN), Artificial Neural Networks (ANN), Support Vector Machines (SVM), and Ensemble Learning Techniques such as Stacking. The outputs of each classification algorithm are analyzed and compared to determine the most effective method for classifying oil spills. © 2024 Bharati Vidyapeeth, New Delhi.

关键词： Decision tree Ensemble learning K-NN Oil Spill Random Forest Support Vector Machine (SVM)

来源：评论

学校读者我要写书评

暂无评论

Linear magnetoelectric electro-optical effect

引用

Physical Review B 2024年第11期110卷 115421页

作者： D. J. P. de Sousa C. O. Ascencio Tony Low Department of Electrical and Computer Engineering School of Physics and Astronomy

In this work, we derive a generalized constitutive relation describing the current response to external electromagnetic fields in electrically biased quantum materials. While our semiclassical Boltzmann approach reveals the existence of electro-optical effects induced by the Berry curvature dipole of Bloch electrons, we also find a wealth of alternative electro-optical effects originating from the interplay between Berry curvature and magnetic moment. In particular, our symmetry analysis indicates the existence of a magnetoelectric electro-optical effect, derived from the simultaneous presence of Berry curvature and magnetic moment, which requires either time-reversal or inversion symmetry breaking. The revealed conductivity coefficients are explicitly written and we derive the tensor shape describing such alternative electromagnetic responses for chiral materials pertaining to space groups 152 and 198.

关键词： Berry curvature Electro-optic effects Magnetoelectric effect Optoelectronics Magnetic moment Bloch wave theory Boltzmann theory

来源：评论

学校读者我要写书评

暂无评论

Ensemble Learning based Categorical Boosting for Customer Lifetime Value Prediction in Businesses 1

Ensemble Learning based Categorical Boosting for Customer Li...

引用

1st International Conference on Intelligent Systems and Computational Networks, ICISCN 2025

作者： Monica, K.M. Habelalmateen, Mohammed I. Shashidhara, K.S. Buckshumiyan, A. Muthukumaran, K. Vellore Institute of Technology School of Computer Science and Engineering Chennai India The Islamic University College of Technical Engineering Department of Computers Techniques Engineering Najaf Iraq Nitte Meenakshi Institute of Technology Department of Electronics and Communication Engineering Bengaluru India New Prince Shri Bhavani College of Engineering and Technology Department of Mechanical Engineering Chennai India Dhanalakshmi Srinivasan College of Engineering and Technology Department of Bio Medical Engineering Mamallapuram India

ISBN: (纸本)9798331529246

Nowadays, Customer Lifetime Value (CLV) prediction is becoming critical task for businesses to identify high-value customers and optimize the marketing strategies. However, the existing Deep Neural Networks (DNN) failed to predict CLV in business due to the dynamic and heterogeneous nature of customer behaviour. Hence, this research proposes an Ensemble Learning based Categorical Boosting (EL-CatBoost) to provide decision-making and strategic planning for businesses. Initially, the data is collected from online retail customer churn dataset and fed into preprocessing with K-Nearest Neighbor (KNN) imputation. The preprocessing technique effectively handles the missing values in the data by replacing the missing value with nearest similar one. Then, the Latent Semantic Analysis (LSA) is employed to extract semantic, sentiment, and contextual features from the preprocessed data. Finally, the proposed EL-CatBoost is employed to predict the CLV by capturing the complex relationships within the features. From the results, the proposed EL-CatBoost achieved better results in terms of terms of Rate of Investment (ROI) with 10-day prediction (ROI-10) of 0.1803 and ROI with 20-day prediction (ROI-20) of 0.3795 when compared with the existing Temporal Structural User Representation (TSUR) network. © 2025 IEEE.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

Risk ranking of rig up operation activities using multi-criteria decision-making methods based on fuzzy environment

Journal of Engineering Research (Kuwait)

引用

Journal of engineering Research (Kuwait) 2024年第1期12卷 289-298页

作者： Ali, Syed Imran Lalji, Shaine Mohammadali Ali, Syed Muhammad Zia, Yassar Kamal Husain, Nusrat Yousaf, Nimra Balobaid, Awatef Salem Yahya, Ashraf Awan, Zahoor Department of Petroleum Engineering NED University Of Engineering & Technology Karachi 75270 Pakistan NED Academy NED University of Engineering &Technology Karachi 75270 Pakistan Department of Electronics & Power Engineering Pakistan Navy Engineering College National University of Sciences and Technology (NUST) Islamabad 44000 Pakistan School of Geography and Environment University of Oxford United Kingdom Department of Computer Science Computer Science and Information Technology College Jazan University Jazan 45142 Saudi Arabia Department of Food Engineering NED University Of Engineering & Technology Karachi 75270 Pakistan

The main aim of this research study is to determine the risk ranking of 29 failure modes of rig-up operations using a well-known and highly effective MCDM method i.e. Fuzzy Technique for Order of Preference by Similarity to Ideal Solution (FTOPSIS). This method takes into account the four criteria which comprise human impact, property damage, environmental effect and company reputation as risk criteria. Three Experts in the field were invited to present the risk ranking of the relative importance of criteria and criteria performance of each risk (as failure mode) by utilizing linguistic variables which are then integrated in triangular fuzzy numbers for further analysis using the Fuzzy TOPSIS method. The evaluation concluded that FM20 (Collision between the offshore platform and boats) is the most dangerous risk with a coefficient of closeness (CCi) equal to 0.992 while the risk level of FM26 (foggy weather) was found least having a coefficient of closeness (CCi) of 0. Subsequently, sensitivity analysis of ranks concluded that FM1 (H2S inaccurate monitoring) is the most sensitive alternative with standard deviation and frequency of rank change was 5.16 and 15 respectively whereas FM20 (Collision between offshore platform and boats) is observed to be the least sensitive alternative. Fuzzy TOPSIS results were found in excellent correlations with the other reliable MCDM methods which include Fuzzy VIKOR (VIseKriterijumska Optimizacija I Kompromisno Resenje) and Fuzzy COPRAS (COmplex PRoportional ASsessment) yielding correlation of around 1. This study proves to be a landmark in the petroleum industry and significantly contributes to verifying safe practices, by taking appropriate actions in minimizing the risk level associated with different activities during rig-up operations. © 2024 The Authors

关键词： Failure mode Fuzzy technique for order of preference by similarity to ideal solution (FTOPSIS) Multi-criteria decision-making rig-up operations Risk ranking

来源：评论

学校读者我要写书评

暂无评论

A comprehensive review on breast cancer prediction using deep neural network

A comprehensive review on breast cancer prediction using dee...

引用

International Conference on Artificial Intelligence, Blockchain, Computing and Security, ICABCS 2023

作者： Singh, Aditee Jain, Anuraj Mishra, Anmol Rawat, Sur Singh Mahesh, G. Singh, Gambhir Department of Computer Science and Engineering JSS Academy of Technical Education Noida India School of Computing Sciences and Engineering Galgotias University Greater Noida India

ISBN: (纸本)9781032669663

Breast cancer is the largest and most prevalent cancer type among women, according to the World Health Organization (WHO). Breast cancer affects millions of women annually and is the most common cancer disease in women. It also accounts for the majority of women’s cancer-related deaths. Lung cancer is the primary cause of cancer-related death, followed by breast cancer. Early detection is essential for survival and the elimination of this issue. There are two methods one is Early diagnosis and other is screening which are available for earlier detection of breast cancer. Early diagnostic initiatives based on knowledge of early signs and symptoms and timely referral to diagnosis Based on the attributes that the data provides, several machine learning algorithms are utilised to determine whether a tumour is benign or malignant. The proposed work can be used to forecast the results of many techniques, and based on the need, the appropriate technique can be applied. © 2024, CRC Press/Balkema. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Integrated dominating and hit set-inspired unequal clusteringbased data aggregation in wireless sensor networks

引用

International Journal of Intelligent Computing and Cybernetics 2022年第4期15卷 642-655页

作者： G.Vennira Selvi V.Muthukumaran A.C.Kaladevi S.Satheesh Kumar B.Swapna Department of Computer Science and Engineering Global Institute of Engineering and TechnologyVelloreIndia Department of Mathematics School of Applied SciencesREVA UniversityBangaloreIndia Department of Computer Science and Engineering Sona College of TechnologySalemIndia Department of Computer Science School of Applied SciencesREVA UniversityBangaloreIndia Department of Electronics and Communication Engineering Dr MGR Educational and Research InstituteChennaiIndia

Purpose-In wireless sensor networks,improving the network lifetime is considered as the prime objective that needs to be significantly addressed during data *** the traditional data aggregation techniques,cluster-based dominating set algorithms are identified as more effective in aggregating data through cluster ***,the existing cluster-based dominating set algorithms suffer from a major drawback of energy deficiency when a large number of communicating nodes need to collaborate for transferring the aggregated ***,due to this reason,the energy of each communicating node is gradually decreased and the network lifetime is also *** increase the lifetime of the network,the proposed algorithm uses two sets:Dominating set and hit ***/methodology/approach-The proposed algorithm uses two sets:Dominating set and hit *** dominating set constructs an unequal clustering,and the hit set minimizes the number of communicating nodes by selecting the optimized cluster head for transferring the aggregated data to the base *** simulation results also infer that the proposed optimized unequal clustering algorithm(OUCA)is greater in improving the network lifetime to a maximum amount of 22%than the existing cluster head selection approach considered for ***-In this paper,lifetime of the network is prolonged by constructing an unequal cluster using the dominating set and electing an optimized cluster head using hit *** dominator set chooses the dominator based on the remaining energy and its node degree of each *** optimized cluster head is chosen by the hit set to minimize the number of communicating nodes in the *** proposed algorithm effectively constructs the clusters with a minimum number of communicating nodes using the dominating and hit *** simulation result confirms that the proposed algorithm prolonging the lifetime of the network efficiently when compared with the existing algorithms.

关键词： Unequal clustering Hit set Dominating set Network lifetime

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：