检索结果-内蒙古大学图书馆

2024 International Conference on Communication, computer Sciences and engineering, IC3SE 2024

作者： Negi, Divya Prakash, Febin Gupta, Anjali Tula's Institute Department Of Computer Science And Engineering Dehradun India Department Of Computer Science And Information Technology Bangalore India Noida Institute Of Engineering And Technology Department Of Electronical And Electronics Engineering Uttar Pradesh Greater Noida India

ISBN: (纸本)9798350366846

Next-generation Internet of Things (IoT) is progressing rapidly due to the introduction of beyond 5G (B5G) and the approaching arrival of 6G, which have improved the dependability, productivity, and profitability of both industrial and personal operations. Nevertheless, data overload is frequently caused by the abundance of wireless sensors in commercial 6G devices. Data mining gathers useful information in order to solve this. Meanwhile, in the 6G architecture, edge computing enables automated equipment operations and intelligent decision-making in real-time. Even so, despite the drawbacks of sensor-based energy sources, the integration of many technologies has led to an increase in energy. Using a multi-agent system (MAS) approach, a system model for industrial wireless sensor networks in 6G applications has been presented in order to combat this. Sensor node clustering locates and forecasts the locations of principal nodes by employing distributed artificial intelligence (DAI). Convolutional neural networks (CNN) and back-propagation neural networks (BPNN) are used in optimisation. Allocating resources to individual nodes efficiently is made possible by the analysis of inter-cluster correlations. The outcomes of the simulation show how well the approach works to reduce resource waste, increase overall energy efficiency, and protect important data. This strategy improves network performance in industrial 6G applications while simultaneously addressing concerns about energy consumption. © 2024 IEEE.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Analysis of Rain Visibility Attenuation on Free Space Optics (FSO) for South African Weather Conditions 4

Analysis of Rain Visibility Attenuation on Free Space Optics...

引用

4th IEEE International Conference on Electrical, computer, and Energy Technologies, ICECET 2024

作者： Mahlobogwane, Zanele Mukubwa, Emmanuel Pillay, Nelendran Tshwane University of Technology Department of Computer Systems Engineering Pretoria South Africa Moi University KipKenya Department of Electrical and Communications Engineering Cheptiret Kenya Durban University of Technology Department of Electronics and Computer Engineering Durban South Africa

ISBN: (纸本)9798350395914

The Free Space Optics (FSO) is a high-speed connectivity system that has the same advantages of speed and bandwidth as that of optic fiber. In comparison to optic fiber, FSO is the preferred choice when it comes to cost and deployment period. However, one of the main challenges with FSO is the changing weather conditions that affect the signal since the transmitted signal is radiated through the atmosphere. This investigation focuses on examining the variables that influence the reduction of visibility at different wavelengths: 750nm, 780nm, 850nm, and 1550nm. The locations of interest concerning visibility and rain data are Pretoria, Upington, Bloemfontein, and Cape Town in the Republic of South Africa. Results indicate that fog attenuates the signal more when compared to rain. Furthermore, signals transmitted at 1550nm will attenuate the signal less when compared to the other wavelengths of interest. © 2024 IEEE.

关键词： Rain

来源：评论

学校读者我要写书评

暂无评论

Evaluation of the Explainable AI-NLP Framework for Text Categorization

Evaluation of the Explainable AI-NLP Framework for Text Cate...

引用

2024 International Conference on Communication, computer Sciences and engineering, IC3SE 2024

作者： Singh, Amar Preet Gupta, Gaurav Soumya, K. Noida Institute Of Engineering And Technology Department Of Electrical & Electronics Engineering Uttar Pradesh Greater Noida India Tula's Institute Department Of Computer Science And Engineering Dehradun India Department Of Computer Science And Information Technology Bangalore India

ISBN: (纸本)9798350366846

Although there has been a decrease in interpretability, significant progress has lately been achieved in developing state-of-the-art models. This assessment provides a thorough analysis of Explainable AI (XAI) within the framework of Natural Language Processing (NLP). This study examines the fundamental classification of descriptions in addition to the many techniques for producing and displaying explanations. The purpose of the survey is to provide a comprehensive study of the many approaches and strategies used to clarify the models' predictions, making it a helpful tool for people who develop NLP models. Additionally, we draw attention to the gaps in the current literature and urge further investigation into potential avenues for this crucial field of study. An experiment is also conducted and the results are discussed in this article. © 2024 IEEE.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Automatic Face Mask Detection Using Deep Learning-Based Mobile-Net Architecture 6

Automatic Face Mask Detection Using Deep Learning-Based Mobi...

引用

6th International Conference on Contemporary Computing and Informatics, IC3I 2023

作者： Kumar, Sandeep Rani, Shilpa Jain, Arpit Kumar, Munish Jaglan, Poonam Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering Vaddeswaram India Neil Gogte Institute of Technology Department of Computer Science and Engineering Hyderabad India MaaSaraswati Institute of Engineering and Technology Department of Electronics &computer Engineering Kalanaur India Panipat Institute of Engineering & Technology Department of Electronics and Communication Engineering Haryana India

ISBN: (纸本)9798350304480

COVID-19 affects public health and economies around the world. Proper wearing of masks plays a vital role in daily life to overcome this epidemic situation. To reduce human contamination, adequate people monitoring is required in public places, i.e., malls, railway stations, bus stands, markets, airports, universities, etc. In highly populated areas, manual inspection of the face mask is not easy, so an automatic face mask detection model helps detect the face mask. This paper proposed mobile Net architecture for face mask detection. This advanced architecture considers the colour image from the standard and its own database for extracting the face feature in-depth to identify the face mask. To validate our work, we used five-fold cross-validation techniques. Finally, the accuracy achieved by the proposed work on two standard databases is 96.4% and 95.7%, showing the outperforming face mask detection results. © 2023 IEEE.

关键词： Covid-19 Deep Learning Face Mask Machine Learning Mask Detection

来源：评论

学校读者我要写书评

暂无评论

A Terse Review of Heart Diseases Estimation Using Machine Learning Practices

A Terse Review of Heart Diseases Estimation Using Machine Le...

引用

2024 International Conference on Communication, computer Sciences and engineering, IC3SE 2024

作者： Pawar, Rahul Dash, Amit Kumar Mittal, Gaurav Department Of Computer Science And Information Technology Bangalore India Noida Institute Of Engineering And Technology Department Of Electronical & Electronics Engineering Uttar Pradesh Greater Noida India Tula's Institute Department Of Computer Science And Engineering Dehradun India

ISBN: (纸本)9798350366846

Heart diseases, a primary cause of global fatalities, represent a growing social matter on a worldwide scale. The integration of machine learning with advancing technology has greatly benefited the medical field, resulting in the provision of seamless solutions characterized by high accuracy, consistency and toughness. These advancements help the patient society through early detection and reduced medical care costs. They also offer the medical fraternity capable, accessible, precise and consistent prediction systems. This paper provides a comprehensive enquiry of machine learning algorithms engaged for the prediction and classification of several cardiovascular diseases, we explore several modalities, including physiological signals, heart sounds and electronic health records, to achieve effective heart disease recognition. We also provide insights into popular machine learning systems, hybrid systems and fuzzy systems in this context. It is noted in this review that Support Vector Machines (SVM) have gained popularity and widespread usage, with neural networks and ensemble techniques following closely behind in terms of their application. All these approaches are compared based on accuracy metrics. © 2024 IEEE.

关键词： Hybrid systems

来源：评论

学校读者我要写书评

暂无评论

Review of the latest techniques that address network fraud detection and proposed architectures 1st

Review of the latest techniques that address network fraud d...

引用

1st International Conference on Applications of AI in 5G and IOT, ICAAI5GI 2024

作者： Indarjit, Elisha Balyan, Vipin Adonis, Marco Department of Electrical Electronics and Computer Engineering Cape Peninsula University of Technology Cape Town Bellville South Africa

ISBN: (纸本)9781032874036

The increase of fraudsters and fraud attacks on the communication network plays a major role in the loss of revenue, network abuse, and degradation of services. Communication and cloud networks belong to separate companies and consist of handover points from one network to another. The scope is to bring communication and cloud networks closer and understand network traffic profiles using the Software-Defined Networking (SDN) concept. The SDN controller will serve to route the extracted tapped data to a central server instead of making use of the live network to route traffic. To apply policies to the traffic and identify which user traffic is a fraud case, and further to send a block signal to the network charging element on the communication network. The flow process will be automated, and to protect the network from fraud attacks, using the SDN controller in a seamless manner and maintaining the performance of the network, The journal article explores traditional fraud detection techniques and will define a new framework for communication and cloud providers to enable the detection and blocking of fraud. The research solution will propose three network architectures for the identification of fraud and integration within communication and cloud networks. The aim of the study is to perform real-time data classification, reporting of fraudulent subscribers, applications, and protocols;real-time analytics, and real-time blocking of data that is classified as fraudulent activity within the mobile data network. The main purpose is to achieve a higher energy/service fraud detection rate than similar work in the field, to provide a solution that integrates within the traditional network, and to further block fraud within the network. © 2025 the Author(s).

关键词： cloud network communication network detection fraud software-defined network

来源：评论

学校读者我要写书评

暂无评论

Food Classification using Machine Learning 1

Food Classification using Machine Learning

引用

1st International Conference on Computational Intelligence for Security, Communication and Sustainable Development, CISCSD 2024

作者： Santhosh Krishna, B.V. Mai, P. Kiran Muthumanickam, S. New Horizon College of Engineering Department of Computer Science and Engineering Bangalore India Rmk College of Engineering and Technology Department of Electronics and Communication Engineering Chennai India

ISBN: (纸本)9798350365405

The use of machine learning techniques in food categorization has received a lot of interest since it has the potential to transform a variety of industries. Food categorization has developed as a critical application of machine learning techniques in recent years, providing potential answers to a variety of problems in the food business, health monitoring, and nutritional evaluation. This paper presents a comprehensive review of methodologies, datasets, and challenges associated with food classification using machine learning. We will have an overview of linear regression. The publicly available datasets are commonly used for training and evaluation purposes, along with challenges such as data imbalance, handling missing values, and limited annotated data. We will perform EDA, finding products by categories and checking missing values and duplicates from the dataset. Finally, we identify future research directions aimed at improving the accuracy, scalability, and real-world applicability of machine learning-based food classification systems. © 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

Smart Travel Solutions Harnessing Artificial Intelligence for Optimal Route Efficiency

Smart Travel Solutions Harnessing Artificial Intelligence fo...

引用

2024 International Conference on System, Computation, Automation and Networking, ICSCAN 2024

作者： Mohanapriya, D. Indumathi, R. Priyatharsini, S. Arounesh, A. Kumar, V.Kishore Kamalan, R. Manakula Vinayagar Institute of Technology Department of Computer Science and Engineering Puducherry India Karpagam Academy of Higher Education Department of Electronics and Communication Engineering Coimbatore India Manakula Vinayagar Institute of Technology Department of Computer Science and Engineering India

ISBN: (纸本)9798331510022

This AI-based route optimizing system has put its focal point on only efficient travel routes based on real-time traffic. It focuses on calculating the shortest distance to source, along with destination and via points, distance, time-based traffic details, in order to arrive at the most optimal route for any journey. Advanced AI techniques in optimizing systems continuously adjust the route according to live traffic patterns so that users may experience the least delay possible. The system integrates with fuel consumption estimations provided the traveler through inputting vehicle mileage, enabling travelers to make better plans for their trips by considering time and fuel efficiency. This would save one time spent traveling, saves fuel, thus saving money while keeping the environment free from pollution. By such smart decisions on making routes, the system increases drivers' overall driving experience, especially in crowded areas or where there is heavy traffic. Since the system is inherently real-time, it's therefore very adaptive to the changing nature of road conditions, thus travel stream lined for the users. © 2024 IEEE.

关键词： Transportation routes

来源：评论

学校读者我要写书评

暂无评论

Performance Enhancement of High-gain STDA Antennas with Reflector for 4G LTE and Sub-6 GHz 5G Applications: Design, Measurement, and Analysis

引用

Progress In Electromagnetics Research C 2024年 139卷 87-94页

作者： Wasim, Mohd Khera, Shelej Islam, Tanvir Malik, Praveen Kumar Asha, Sivaji Das, Sudipta School of Electronics and Electrical Engineering Lovely Professional University Phagwara144411 India Department of Electrical and Computer Engineering University of Houston HoustonTX77204 United States Saveetha Engineering College Saveetha Nagar Thandalam Chennai602105 India Department of Electronics and Communication Engineering IMPS College of Engineering and Technology West Bengal Malda732103 India

The paper focuses on the design, measurement, and performance analysis of a high-gain cross-orthogonal series fed two dipole antenna (STDA) arrays with side-wall reflectors. The antenna is specifically designed for 4G Long Term Evolution (LTE) and sub-6 GHz 5G band applications. The designed antenna is capable of operating at multiple frequencies aiming to support 4G LTE and the sub-6 GHz 5G application bands. To improve the radiation characteristics and prevent coupling effects in the presence of side-wall reflectors, parasitic strip pair directors are included in the antenna design. Furthermore, the performance of the designed STDA is evaluated by forming different array configurations, such as 2 × 1, 2 × 2, and 2 × 3 arrays. The various array configurations are proposed to investigate the effect of the projected array arrangements on the radiation pattern, impedance bandwidth, and gain characteristics. The results of the measurements show that the radiation characteristics of the antenna have been improved significantly. The proposed antenna operates at six distinct frequencies for S11 ≤ 10 dB. The operating frequencies at 1.8, 2.35, and 2.6 GHz can be utilized for LTE and 3.2, 4.2, and 5.2 GHz which can support sub-6 GHz 5G bands. The antenna is characterized by its compact size, measuring around 89 mm × 71 mm, while still achieving high gain of 12.3 dB for single STDA element with parasites and with reflector. These results emphasize the importance of the proposed design, which incorporates parasitic strip pair directors and side-wall reflectors. This design methodology plays a crucial role in enhancing the performance of the prescribed STDA array for both 4G LTE and sub-6 GHz 5G applications. © 2024, Electromagnetics Academy. All rights reserved.

关键词： Dipole antennas

来源：评论

学校读者我要写书评

暂无评论

A Comparison of Machine Learning and Neural Network Algorithms for an Automated Thai Essay Scoring 20

A Comparison of Machine Learning and Neural Network Algorith...

引用

20th International Joint Conference on computer Science and Software engineering, JCSSE 2023

作者： Suriyasat, Suttichai Chanyachatchawan, Sapa Tuaycharoen, Nuengwong Chulalongkorn University Department of Computer Engineering Thailand The National Electronics and Computer Technology Center Thailand

ISBN: (纸本)9798350300505

Thai students have relatively low scores on the reading literacy assessment conducted by PISA. Various studies reported that reading skills could be improved by writing. However, essay scoring is a time-consuming task. An automated essay scoring system can support both teachers and students by reducing the teachers' workload and providing predicted scores as feedback to students. A number of recent studies have focused on automated essay scoring dataset that contains only essays written in English. Little to no research has been done on the automated essay scoring system for the Thai language. The aim of this study is to develop a Thai essay scoring system using machine learning and deep learning models that have been reported to achieve good performance. We also try to improve the performance of our models by adding essay attribute features. The models that were used in this study are logistic regression, kNN, SVM, random forest, gradient boosting, XGBoost, LSTM (bag-of-words), LSTM (w2v), BERT-based, and LSTM+CNN (BERT embedding). The models were evaluated by six metrics, including accuracy, Quadratic weighted kappa, precision, recall, and F1-score along with 10-fold cross-validation. The experimental results show that XGBoost outperforms other models considering the majority of best metric scores in each set. For deep learning models with automatically extracted features from the text, the LSTM with word2vec features model yielded better performance than other deep learning models. © 2023 IEEE.

关键词： Students

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：