检索结果-内蒙古大学图书馆

5th IEEE International Conference for Emerging Technology, INCET 2024

作者： Tiwari, Utkarsh Jahanve, P. Reddy Karna, Siwani Anand, M. Pati, Peeta Basa Prakash, Bhanu K.N. Department of Computer Science and Engineering Amrita School of Computing Bengaluru Amrita Vishwa Vidyapeetham India Bioinformatics Institute A*STAR Singapore

ISBN: (纸本)9798350361155

Parkinson's disease (PD) is a progressive neurological disorder that mainly affects people over the age of sixty. Currently, there is no such cure for PD. However, Treatments are available to help relieve the symptoms related to PD. A rating tool called MDS-UPDRS III is used to gauge the severity and progression and stages of disease severity are measured by the Hoehn and Yahr (NHY) staging system. This study performs a comparative analysis of the effectiveness of various machine learning models such as AdaBoost, XGBoost, Gradient Boosting Classifier (GBC), Decision Trees (DT), K-Nearest Neighbor (KNN), Logistic regression (LR), and Gaussian Naïve Bayes (GNB) on a dataset containing a variety of PD-related features obtained from 2861 persons. Local Interpretable Model-agnostic Explanations (LIME) is employed to perform the analysis of the strength of each feature toward the outcome prediction for various classification tasks. It is observed that the AdaBoost classifier delivers superior performance of 93.2% accuracy and 84.2% F1-Score for the dataset. © 2024 IEEE.

关键词： Adaptive boosting

来源：评论

学校读者我要写书评

暂无评论

SVM Versus KNN: Prediction of Best Image Classifier

SVM Versus KNN: Prediction of Best Image Classifier

引用

International Conference on Intelligent Systems and Sustainable Computing, ICISSC 2022

作者： Marri, Sreekar Praneeth Nikith, Boda Venkata Keerthan, Nagandla Krishna Sai Jayan, Sarada Department of Computer Science Engineering Amrita School of Engineering Bengaluru India Department of Mathematics Amrita Vishwa Vidyapeetham Coimbatore India

ISBN: (纸本)9789819947164

Image classification is the most accurate way to anticipate a classifier’s accuracy. Categorization approaches include logistic regression, K-nearest neighbors, Naive Bayes, decision trees, and support vector machines. Artificial neural networks and convolutional neural networks can also be used for classification. The best classification algorithm is predicted using K-nearest neighbors (KNN) and support vector machines (SVM). The "Cats versus Dogs" dataset and the "Human and Animals" dataset are used to test the accuracy in this research. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

IoT-Enabled WBAN and Machine Learning for Emotion Recognition 4

IoT-Enabled WBAN and Machine Learning for Emotion Recognitio...

引用

4th International Conference on Technological Advancements in Computational sciences, ICTACS 2024

作者： Mathur, Hritesh Panwar, Harsh Karki, Rahul Jangra, Vivek Yadav, Ramnaresh Kapoor, Anjali Amity University Department of Information Technology Noida India School of Computer Science and Engineering Galgotias University Greater Noida India

ISBN: (纸本)9798350387490

All industries, including computer science and health care and customer service are in dire need of efficient recognition of human feelings. This work is a script for a novel approach to affect recognition which involves both vocal emotion analysis and face emotion detection. Voice sentiment analysis project used machine learning technique to identify the prospects of emotional content in voice data. The model also assists in the classification of emotions with reference to the speech emotional states based on added features of MFCC and chroma. On the other hand, face emotion recognition project by applying deep learning algorithms identifies emotions by face expressions. With the help of convolutional, neural networks (CNNs) determining the happiness, sadness, and anger it analyses the facial features correctly. Combining all of these results in a coherent system that allows for the recognition of feelings through voice and or facial signals. Consequently, as demonstrated in the experimental results provided hereinafter, the accuracy of the presented system in correctly identifying human emotions is significantly higher than when using single models on their own. Therefore this combination creates space for other uses such as healthcare marketing among other fields hence improving user experience while at the same time providing unforeseen analysis of human conduct during an interaction with intelligent devices. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A connectivity index based on adjacent vertices in cubic fuzzy graph with an application

引用

Journal of Intelligent and Fuzzy Systems 2024年第4期46卷 11025-11040页

作者： Guan, Hao Sadati, Seyed Hossein Talebi, Ali Asghar Shafi, Jana Khan, Aysha Institute of Computing Science and Technology Guangzhou University Guangzhou China School of Computer Science of Information Technology Qiannan Normal University for Nationalities Duyun China Department of Mathematics University of Mazandaran Babolsar Iran Department of Computer Engineering and Information College of Engineering in Wadi Alddawasir Prince Sattam Bin Abdulaziz University Wadi Alddawasir Saudi Arabia Department of Mathematics Prince Sattam Bin Abdulaziz University Al-Kharj Saudi Arabia

A cubic fuzzy graph is a type of fuzzy graph that simultaneously supports two different fuzzy memberships. The study of connectivity in cubic fuzzy graph is an interesting and challenging topic. This research generalized the neighborhood connectivity index in a cubic fuzzy graph with the aim of investigating the connection status of nodes with respect to adjacent vertices. In this survey, the neighborhood connectivity index was introduced in the form of two numerical and distance values. Some characteristics of the neighborhood connectivity index were investigated in cubic fuzzy cycles, saturated cubic fuzzy cycle, complete cubic fuzzy graph and complementary cubic fuzzy graph. The method of constructing a cubic fuzzy graph with arbitrary neighborhood connectivity index was the other point in this research. The results showed that the neighborhood connectivity index depends on the potential of nodes and the number of neighboring nodes. This research was conducted on the Central Bank's data regarding inter-bank relations and its results were compared in terms of neighborhood connectivity index. © 2024-IOS Press. All rights reserved.

关键词： Graph theory

来源：评论

学校读者我要写书评

暂无评论

Wavelength-multiplexed orbital angular momentum meta-holography

引用

PhotoniX 2024年第1期5卷 276-289页

作者： Jaehyuck Jang Seong-Won Moon Joohoon Kim Jungho Mun Stefan A.Maier Haoran Ren Junsuk Rho Department of Chemical Engineering Pohang University of Science and Technology(POSTECH)Pohang 37673Republic of Korea Department of Materials Science and Engineering Stanford UniversityStanfordCA 94305USA Department of Mechanical Engineering Pohang University of Science and Technology(POSTECH)Pohang 37673Republic of Korea School of Electrical and Computer Engineering Purdue UniversityWest LafayetteIN 47907USA School of Physics and Astronomy Monash UniversityMelbourneVIC 3800Australia Department of Physics Imperial College LondonLondon SW72AZUK Department of Electrical Engineering Pohang University of Science and Technology(POSTECH)Pohang 37673Republic of Korea POSCO-POSTECH-RIST Convergence Research Center for Flat Optics and Metaphotonics Pohang 37673Republic of Korea National Institute of Nanomaterials Technology(NINT) Pohang 37673Republic of Korea

The field of high-bandwidth holography has been extensively studied over the past *** angular momentum(OAM)holography,which utilizes vortex beams with theoretically unbounded OAM modes as information carriers,showcases the large capacitance of hologram ***,OAM holography has been limited to a single wavelength,restricting its potential for full-color holography and *** this study,we propose wavelength and OAM multiplexed holography that utilizes the multiple dimensions of light—wavelength and OAM—to provide a multi-color platform that expands the information capacity of holographic storage *** proposed wavelength-OAM multiplexed holography is physically realized by a metasurface,the state-of-the-art optical element consisting of an array of artificially engineered *** silicon meta-atoms,the constituents of the metasurface,are engineered to possess wavelength selectivity by tailoring the dispersion of polarization *** meta-atoms are used to encode the calculated OAM-preserved phase maps based on our *** sampling grid of the phase map is rotated by 45°,which effectively suppress higher-order diffraction,providing a great strategy for achieving large field-of-view(FOV)*** successfully demonstrate six holographic images that are selectively reconstructed under the illumination of light with specific wavelengths(λ=450,635 nm)and topological charges(l=-2,0,2),without high-order *** work suggests that ultrathin meta-holograms can potentially realize ultrahigh-bandwidth full-color holography and holographic video displays with large FOV.

关键词： Metasurface Meta-holography Wavelength-multiplexed holography OAM holography

来源：评论

学校读者我要写书评

暂无评论

Distributed Cloud Simulation Architecture Combining Virtual and Real Environment

Distributed Cloud Simulation Architecture Combining Virtual ...

引用

2024 International Conference on Interactive Intelligent Systems and Techniques, IIST 2024

作者： Hu, Jiangang Mao, Yukun Li, Junjie Ye, Mengya Chen, Li Wan, Zhangbo Peng, Yuhuai Zhiyuan Research Institute Strategic Research Department Hangzhou China Northeastern University School of Computer Science and Engineering Shenyang China

ISBN: (纸本)9798350374421

With the deep integration of advanced manufacturing technology and the new generation of information technology, human-machine collaborative intelligent manufacturing has emerged as the core technology driving the development of the industrial sector. However, the human-machine collaborative intelligent manufacturing equipment exhibits high complexity and uncertainty in faults. The data silos that exist between equipment, personnel, systems, and platforms contribute to decreased productivity. Furthermore, the prolonged and costly technician training cycles add further obstacles. Therefore, a virtual-real integrated cloud simulation architecture is constructed using LVC (Live, Virtual, Constructive) simulation technology combined with a distributed computing framework. This architecture aims to achieve intelligent human-machine collaboration and real-time virtual-real interaction in industrial production. Real time monitoring of equipment and the entire production process through cloud simulation technology to optimize production processes and efficiency. The architecture supports simulation services such as intelligent task scheduling, human-machine collaborative manufacturing, adaptive flexible manufacturing, and production equipment precision and performance evaluation. The current architecture has just been proposed as a theoretical innovation for intelligent manufacturing cloud simulation solutions, but it has yet to be put into practice. © 2024 IEEE.

关键词： Smart manufacturing

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Driven Control and Optimization of Dual Band-Notched UWB Circular Monopole Antenna 12

Machine Learning-Driven Control and Optimization of Dual Ban...

引用

12th International Conference on Internet of Everything, Microwave, Embedded, Communication and Networks, IEMECON 2024

作者： Nikpoosh, Alireza Kapur, Aryaman Barón, Alejandra Palomo Soni, Gaurav Kumar Yadav, Dinesh School of Mathematics & Computer Science Iran University of Science and Technology Tehran Iran Department of Computer Science and Engineering Manipal University Jaipur Rajasthan Jaipur India Polytechnic University of Madrid-ETSIAE Madrid Spain Department of ECE Manipal University Jaipur Rajasthan Jaipur India

ISBN: (纸本)9798350387315

As communication technologies continue to advance rapidly, there is a growing need for antennas that provide high performance while minimizing interference from other systems. This paper explores optimizing and controlling the performance of a dual band-notched Ultra-Wideband (UWB) circular monopole antenna with parasitic resonators using machine learning techniques. Building upon a previously proposed antenna design, we first employ various machine learning models—such as Gaussian Process Regression, Support Vector Regression, and Gradient-Boosted Trees—to precisely control band notches within specific frequency ranges, thereby preventing interference with any narrow-band systems in close vicinity. Following this, we leverage a new method for evaluating the performance of UWB antennas with band-notched characteristics and use similar models to optimize the antenna’s physical properties and enhance radiation characteristics. Validated through simulations in CST Studio Suite, the optimized antenna demonstrates significantly improved return loss, and our approach allows for accurate prediction of the physical properties required to achieve desired band notches within the 4–8 GHz and 6–9 GHz ranges, corresponding to each parasitic resonator. © 2024 IEEE.

关键词： Monopole antennas

来源：评论

学校读者我要写书评

暂无评论

Predicting Groundwater Quality with Advanced Deep Learning Models: Improving Environmental Management by Addressing Pollution Issues and Obtaining More Accurate Forecasts 8

Predicting Groundwater Quality with Advanced Deep Learning M...

引用

8th International Conference on Electronics, Communication and Aerospace Technology, ICECA 2024

作者： Selvakumarasamy, K. Mahaveerakannan, R. Kumar, D. N.S Ravi Balamanigandan, R. Kumar, T. Rajesh Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Electronics and Communication Engineering Chennai602105 India Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Computer Science and Engineering Tamil Nadu Chennai India Sathyabama Institute of Science and Technology School of Electronics Engineering Chennai India

ISBN: (纸本)9798350367904

To ensure clean water for consumption in the future, it is imperative to understand the pollutants and the quality of the existing groundwater. Controlling water pollution and enhancing water management both depend on the ability to predict the water's purity with high accuracy. Previous studies have shown that when it comes to deep learning models, extreme gradient boosting (XGBoost) performs better in terms of accuracy and precision than random forest (RF). This study explores the field of water quality assessment by creating a novel method that combines state-of-the-art deep learning algorithms such as artificial neural networks (ANN), long short-term memory (LSTM), bidirectional LSTM (Bi-LSTM), gated recurrent units (GRU), convolutional neural networks (CNN), recurrent neural networks (RNN), and backpropagation neural networks (BPNN). Utilising deep learning techniques to enhance the index's prediction capacity and accuracy, as well as computing WQI utilising comprehensive water quality metrics, are our main research objectives. Through the use of deep learning models in conjunction with WQI, we hope to uncover patterns and connections in information on water quality that are not visible through conventional means. Plans for groundwater development will benefit from the study's findings, which will also enhance DL applications for better groundwater quality. © 2024 IEEE.

关键词： ANN Bi-LSTM BPNN CNN Deep learning algorithm Forecast for Water Standards GRU LSTM RNN WAWQI

来源：评论

学校读者我要写书评

暂无评论

Enhanced License Plate Detection using YOLOv8n: An Approach for Efficient Vehicle Identification 3

Enhanced License Plate Detection using YOLOv8n: An Approach ...

引用

3rd IEEE World Conference on Applied Intelligence and Computing, AIC 2024

作者： Chandok, Vishesh Maurya, Sudhanshu Mirza, Kashish Kumar Yadav, Ajay Thomas Varghese, Sneha Garg, Rachit Symbiosis Institute of Technology Nagpur Campus Pune India Graphic Era Hill University Department of Computer Science & Engineering Uttarakhand Bhimtal Campus India United Institute of Management Department of Computer Application Prayagraj India Lovely Professional University School of Computer Science and Engineering Phagwara India

ISBN: (纸本)9798350384598

An essential feature of the intelligent transportation system is the automatic detection and recognition of license plate information. The e-payment systems for parking and toll collection in traffic control security could be utilized with this application. Numerous algorithms have been created for License Plate Recognition (LPR) and Identification, each with pros and cons depending on the circumstances. computer vision has increased in terms of techniques and developments since deep learning emerged and became popular in several artificial intelligence domains. It is one of the most efficient ways to monitor traffic signals, tax paid for parking, and police monitoring through Automatic LPR. Although it, as a technology, is widely used and developed, much more must be done to improve the system's accuracy. The current science community has excelled in efficiency and problem-solving in recent years. Along with the You Only Look Once (YOLO), targeted at the object detection area and applied to this study, our primary goal is to summarize and analyze several methods and advancements in LPR in the deep learning age. © 2024 IEEE.

关键词： Traffic signals

来源：评论

学校读者我要写书评

暂无评论

Exploratory Data Analysis using Autoviz for Machine Learning Classification Problem

Exploratory Data Analysis using Autoviz for Machine Learning...

引用

2024 International Conference on Emerging Innovations and Advanced Computing, INNOCOMP 2024

作者： Guru Prasad, M.S. Praveen Gujjar, J. Kotiyal, Arnav Prasanna Kumar, H.R. Devadas, Raghavendra M Jahan, Afsar Department of Computer Science and Engg. Dehradun India Faculty of Management Studies Bengaluru India Visvesvaraya Technological University PESITM Dept. of Information Science & Engg. Shivamogga India Gitam School of Technology Department of Computer Science and Engineering Gitam University Bengaluru India Department of Computer Application Dehradun India

ISBN: (纸本)9798350376470

As the field of machine learning continues to advance, the importance of effective exploratory data analysis (EDA) cannot be overstated, especially in the context of classification problems. This research paper introduces an innovative and automated approach to exploratory data analysis using Autoviz, a powerful Python library designed to streamline the visualization process for machine learning datasets. The study aims to demonstrate the efficacy of Autoviz in meaningful insights, facilitating feature understanding, and supporting data preprocessing for classification tasks. Furthermore, the paper discusses how Autoviz assists in feature selection by highlighting the relevance and importance of each feature about the target variable. This feature-centric analysis contributes to optimizing machine learning models by guiding the selection of relevant input features, thereby improving model accuracy and interpretability. Autoviz is a Python library designed to automate the exploratory data analysis (EDA) process for machine learning tasks. It is specifically tailored to generate a variety of visualizations that aid in understanding the structure and characteristics of a dataset. The results indicate that Autoviz significantly reduces the time and effort required for exploratory data analysis while maintaining the quality and depth of insights obtained. The differences between Autoviz and Pycaret is discussed in this paper. It has been observed that AutoViz automates the process of exploring and analyzing data, while PyCaret is designed for the comparison, construction, and tuning of machine learning models. © 2024 IEEE.

关键词： Adversarial machine learning

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：