检索结果-内蒙古大学图书馆

2023 CAA Symposium on Fault Detection, Supervision and Safety for Technical Processes, SAFEPROCESS 2023

作者： Zhang, Bangcheng Song, Jingyuan Li, Bo Gao, Zhi Changchun Institute of Engineering Changchun University of Technology School of Mechatronics Changchun China Jilin Emergency Management Institute Changchun Institute of Engineering Changchun China Changchun Institute of Engineering School of Computer Science and Computing Changchun China Changchun University of Technology School of Applied Technology Changchun China

ISBN: (纸本)9798350337754

In industrial production, rolling element bearings are key rotating components in a wide range of applications. By predicting rolling element bearings, the failure of bearings as well as problems can be detected in time and preventive measures can be taken to improve production efficiency before the failure occurs. For the prediction problem of rolling element bearing, a hybrid model of rolling bearing prediction based on variable mode decomposition optimized by sparrow search algorithm and bidirectional recurrent neural network of convolutional neural network based on attention mechanism is proposed. Firstly, the initial signal is preprocessed with data using variational modal decomposition. Secondly, the signal with threshold value more than 0.5 is selected as the input of convolutional neural network to perform feature extraction. Then, the bidirectional recurrent neural network structure is used to perform the degradation prediction of rolling bearings. Finally, the proposed method is validated using the XJTU-SY dataset and compared with gated recurrent unit, bidirectional recurrent neural network, bidirectional recurrent neural network based on attention and attention-based convolutional neural network, bidirectional recurrent neural network combination model. The experimental results show that the used model has about 30% higher prediction accuracy than the above four models and has some application val. © 2023 IEEE.

关键词： Roller bearings

来源：评论

学校读者我要写书评

暂无评论

IOT Network Feature Based Intrusion Detection Techniques- Review

IOT Network Feature Based Intrusion Detection Techniques- Re...

引用

2022 IEEE International Conference on Current Development in engineering and Technology, CCET 2022

作者： Chaudhary, Diwakar Kumar Yadav, Pritaj Gupta, Sanjeev Jha, Kanchan Ravindranath Tagore University Computer Science and Engineering Bhopal India School of Advance Computing Sage University Bhopal India

ISBN: (纸本)9781665454155

Communication networks become mobile and dynamic with the usage of portable wireless devices. The Internet of Things network's flexibility creates a risky environment for a variety of applications. Therefore, there is a significant possibility of an attack in such a network. In order to secure various types of networks, researchers' work in the subject of intrusion detection has been described in this paper. The architecture of the IDS was discussed as per networks with its types. Models proposed by the authors were detailed with techniques used for the detection of intrusion in different environments. The further paper has listed compared various techniques and listed strengths with limitations. Finally, evaluation parameters were listed to compare models of intrusion detection systems. © 2022 IEEE.

关键词： Intrusion detection

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis using VADER: Unveiling Customer Sentiment and Predicting Buying Behavior in the Airline Industry

Sentiment Analysis using VADER: Unveiling Customer Sentiment...

引用

Women in Innovation, Technology & Entrepreneurship (ICWITE), IEEE International Conference for

作者： R Annamalai Shaik Atheeq Rasool Deena S K Venkatraman Soundaram Y Computer Science and Engineering Amrita Vishwa Vidyapeetham School of Computing Chennai India Department of CSE Annamalai University Chidambaram Chennai India Computer Science and Engineering Amrita Vishwa Vidyapeetham School of Computing Chennai Computer Science and Engineering St.Peter’s Institute of Higher Education and Research

This study focuses on leveraging sentiment analysis using VADER (Valence Aware Dictionary and Sentiment Reasoner) to analyze customer reviews and predict buying behavior in the airline industry, with a specific focus on British Airways. The study aims to enhance customer experience and provide valuable insights for the airline company. The study begins by applying web scraping techniques to collect customer reviews from the Airline Quality website. The collected unstructured data is then processed and cleaned for further analysis. VADER sentiment analysis is utilized to determine the sentiment of each customer review, classifying them as positive, negative, or neutral. This analysis provides valuable insights into customer sentiment towards British Airways, enabling the airline to identify areas of improvement and address customer concerns. Furthermore, the study involves creating a classification model to predict customer buying behavior. Various features such as flight routes, booking origins, trip types, number of passengers, and customer preferences are considered to build the model. Random Forest Classifier, XGBoost Classifier, Logistic Regression and KNN algorithms are employed to train and evaluate the models. By accurately predicting buying behavior, British Airways can tailor their services and offerings to meet customer expectations, resulting in improved customer satisfaction and increased bookings. The findings and insights from this study provide British Airways with valuable information to optimize their operations, enhance customer experience, and stay competitive in the airline industry. By understanding customer sentiment and predicting buying behavior, the airline can make data-driven decisions to attract and retain customers, ultimately leading to improved business performance and success.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Exploring the Cut-Off Between Energy Balance and Delay in In-Network Data Aggregation (I-NDA) for Wireless Sensor Networks

Exploring the Cut-Off Between Energy Balance and Delay in In...

引用

Disruptive Technologies (ICDT), International Conference on

作者： Anuj Kumar Krishna Kant Agrawal School of Computing Science & Engineering Galgotias University Greater Noida India Department of Computer Science Engineering Ajay Kumar Garg Engineering College Ghaziabad School of Computing Science & Engineering Galgotias University Greater Noida Yamuna Expressway Gautam buddh Nagar India

In WSN, data aggregation is an important part of the data collection process. It is used to reduce network traffic and reduce energy consumption. However, this process comes with a cut-off between energy balance and delay. This cut-off is due to the competing interests of the nodes in the network: the sensors require energy to transmit data, while the sinks require low delays in data collection. In order to maintain energy balance and reduce delay, the system must select suitable methods of data aggregation that are both energy-efficient and low-delay. To reduce energy consumption, the system can use energy-conserving data aggregation protocols, such as clustering and tree-structured routing. To reduce delay, they system can use low-delay data aggregation techniques, such as time synchronization and distributed aggregation. By understanding the cut-off between energy balance and delay in I-NDA, it is possible to make informed decisions on the selection of suitable protocols and techniques to ensure energy-efficiency and low-delay data collection. It is important to select the right set of protocols and techniques to balance the efficiency and delay parameters.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Telecommunications Customer Retention: A Deep Learning Approach Using LSTM for Predictive Churn Analysis

Enhancing Telecommunications Customer Retention: A Deep Lear...

引用

Data science and Network Security (ICDSNS), International Conference on

作者： M Ranjith Kumar Priyanga S Janani Srinivasan Anusha Veda Chatiyode Jerome Santiago Dharminder Chaudhary School of Computer Science and Engineering Vellore Institute of Technology Chennai India Dept. of Computer Science & Engg Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai India Dept. of Computer Science & Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai India

ISBN: (数字)9798350373110

ISBN: (纸本)9798350373127

The telecommunications industry has a significant challenge in customer churn, especially for companies aiming for sustainable growth in a competitive market. To overcome this issue, we suggested a method utilizing Long Short-Term Memory (LSTM) networks, a deep learning strategy that has revolutionized predictive modeling. We used 4250 customer profiles, each containing 19 features including consumption data and plan options, to train and test the LSTM model. Data preprocessing included encoding categorical variables, normalizing numerical features, and eliminating irrelevant variables to maintain data integrity and authenticity. The LSTM model was fine-tuned to recognize significant patterns rather than simply memorizing data. We also incorporated an additional layer to assess diverse information types, which improved the model's ability to process sequential data effectively. The proposed model achieved a prediction accuracy of 95.3% in identifying potential customer churn, demonstrating its effectiveness in predicting when customers might leave their telecommunications provider. These results demonstrate how LSTM networks can reduce customer attrition in the telecom industry, making them a valuable tool for companies aiming to retain customers and maintain growth in a competitive market. The study's findings pave the way for innovative applications of deep learning techniques in customer retention strategies across diverse industries. This breakthrough has the potential to transform business approaches to customer relationship management and loyalty programs.

关键词： Industries Deep learning Accuracy Data preprocessing Companies Predictive models Data models Telecommunications Numerical models Long short term memory

来源：评论

学校读者我要写书评

暂无评论

YOLO: Redefining Real-Time Object Detection Accuracy and Efficiency 3

YOLO: Redefining Real-Time Object Detection Accuracy and Eff...

引用

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

作者： Verma, Shivam Gopikishan Maurya, Sudhanshu Pant, Himanshu Yadav, Ajay Kumar Thomas Varghese, Sneha Garg, Rachit Symbiosis Institute of Technology Nagpur Campus Pune India Graphic Era Hill University School of Computing Uttarakhand India United Institute of Management Department of Computer Application Uttar Pradesh Prayagraj India Lovely Professional University School of Computer Science and Engineering Phagwara India

ISBN: (纸本)9798350384598

Image classification, also known as object detection, is an advanced form of computer vision in which a network can predict objects in an image and point them out as bounding boxes. Classifying and recognizing objects in an image is just one aspect of object detection because it also involves localizing these objects and attracting bounding boxes around them. Since object detection involves image and video analysis, it has been of critical interest to researchers over the past few years. The previous object recognition method relies on manually created features and traditional and trainable algorithms. By using the YOLO (You Only Look Once) process, this research aims to perform real-time object detection. Regarding speed and performance, the YOLO algorithm is much more efficient than the existing model. Unlike existing algorithms that do not scan the entire image in single forward propagation, YOLO uses a neural network to predict binding boxes for the whole image. In comparison with existing algorithms, YOLO performs faster. © 2024 IEEE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

AI-Enhanced Cloud Security Framework for IoT Networks Using a Predictive Analytics Approach 3

AI-Enhanced Cloud Security Framework for IoT Networks Using ...

引用

3rd International Conference for Advancement in Technology, ICONAT 2024

作者： Ramesh Naidu, P. Dankan Gowda, V. Gujar, Shantanu Sudhir Shaikh, Salman Firoz Shandilya, Saurabh Sudhakar Reddy, N. Nitte Meenakshi Institute of Technology Department of Computer Science and Engineering Karnataka Bangalore560064 India BMS Institute of Technology and Management Department of Electronics and Communication Engineering Karnataka Bangalore India Rochester Institute of Technology Golisano College of Computing and Information Sciences Department of CyberSecurity RochesterNY14623 United States Rochester Institute of Technology Golisano College of Computing and Information Sciences Department of Computer Science RochesterNY14623 United States Poornima College of Engineering Department of Advance Computing Rajasthan Jaipur India Mohan Babu University School of Engineering Department of ECE Tirupati India

ISBN: (纸本)9798350354171

The use of IoT with cloud computing has seen a massive improvement when it comes to data processing as well as connectivity. However, this has its own set of security problems like violation of access, leakage of information and issues with respect to scaling up. These challenges are fundamental and complex, and so this paper seeks to introduce an AI-cloud security framework that incorporates the use of predictive analytical functions. It is used to provide a real-time measure of security threats in IoT networks with a view of safeguarding both the data and the devices used. The values of precision and recall were 95 percent and 90 percent, respectively, with an overall anomaly detection rate higher than the previous threat detection methods. The framework also unveiled overall improvements in response time and false positive rates over the conventional methods. Such findings suggest that implementing AI and predictive analytics into cloud security frameworks for IoT networks are highly conceivable. Concerning future work, the research underlines the need for security solutions that can adapt to IoT's increasing connectivity requirements in numerous applications and would open the path for the next developments in IoT protection frameworks. © 2024 IEEE.

关键词： Cloud security

来源：评论

学校读者我要写书评

暂无评论

Distributed time-varying formation control with uncertainties based on an event-triggered mechanism

引用

science China(Information sciences) 2021年第3期64卷 167-176页

作者： Xiaoduo LI Yumeng BAI Xiwang DONG Qingdong LI Zhang REN Science and Technology on Aircraft Control Laboratory School of Automation Science and Electrical EngineeringBeihang University Department of Electrical and Computer Engineering University of Wisconsin-Madison Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University

This paper investigates the distributed time-varying formation(TVF) problems for general linear multi-agent systems(MASs) subject to matched bounded uncertainties based on an adaptive event-triggered mechanism. A TVF protocol was designed with an event-triggered mechanism by introducing adaptive weights into the formation control protocol and triggering condition, and the large chattering phenomenon was avoided by the σ-modification adaptive law. According to the Lyapunov stability theory, proof has been established that the MASs in the presence of uncertainties can realize the expected formation that satisfies the given feasible condition. Finally, an example is provided to verify the effectiveness of the proposed algorithm.

关键词： formation control multi-agent systems event-triggered adaptive control

来源：评论

学校读者我要写书评

暂无评论

5G-SRNG: 5G Spectrogram-based Random Number Generation for Devices with Low Entropy Sources

5G-SRNG: 5G Spectrogram-based Random Number Generation for D...

引用

2023 IEEE International Conference on Omni-Layer Intelligent Systems, COINS 2023

作者： Catak, Ferhat Ozgur Catak, Evren Elezaj, Ogerta University of Stavanger Electrical Engineering and Computer Science Stavanger Norway Independent Researcher Stavanger Norway School of Computing and Digital Technology Birmingham City University Birmingham United Kingdom

ISBN: (纸本)9798350346473

Random number generation (RNG) is a crucial element in security protocols, and its performance and reliability are critical for the safety and integrity of digital systems. This is especially true in 5G networks with many devices with low entropy sources. This paper proposes 5G-SRNG, an end-to-end random number generation solution for devices with low entropy sources in 5G networks. Compared to traditional RNG methods, the 5G-SRNG relies on hardware or software random number generators, using 5G spectral information, such as from spectrum-sensing or a spectrum-aware feedback mechanism, as a source of entropy. The proposed algorithm is experimentally verified, and its performance is analysed by simulating a realistic 5G network environment. Results show that 5G-SRNG outperforms existing RNG in all aspects, including randomness, partial correlation and power, making it suitable for 5G network deployments. © 2023 IEEE.

关键词： Random number generation

来源：评论

学校读者我要写书评

暂无评论

Enhancing Intrusion Prevention with Explainable Convolutional Neural Networks: Recent Developments and Promising Applications 8

Enhancing Intrusion Prevention with Explainable Convolutiona...

引用

8th International Conference on Communication and Electronics Systems, ICCES 2023

作者： Chitnis, Ajay Chandre, Pankaj Pathan, Shafi DevOps Architect Hcl Technologies Uk Limited Pune India Mit Art Design & Technology University Mit School of Computing Department of Computer Science & Engineering Pune India

ISBN: (纸本)9798350396638

The proliferation of cyberattacks in recent years has led to an increased demand for effective intrusion prevention systems (IPS). Convolutional Neural Networks (CNNs) have shown promise in improving the accuracy of IPS, but their lack of interpretability hinders their wider adoption. Explainable AI (XAI) techniques have emerged to address this issue, allowing users to understand the reasoning behind a model's predictions. This survey paper provides an overview of recent developments in enhancing IPS with XAI techniques in CNNs. This study reviews state-of-the-art research on integrating interpretability into CNN models, including methods such as attention mechanisms, saliency maps, and LIME. Also, this study discusses about the promising applications of CNN-based IPS with XAI, including network traffic analysis, malware detection, and anomaly detection. Finally, we highlight some of the challenges and opportunities for future research in this area, including the need for standardized evaluation metrics and the potential for combining XAI techniques with other AI methods such as reinforcement learning. Overall, this survey paper aims to provide a comprehensive understanding of the recent advances in using CNNs with XAI for enhancing IPS, and to identify promising directions for future research in this field. © 2023 IEEE.

关键词： Convolutional neural networks

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：