检索结果-内蒙古大学图书馆

A Deep Learning Method for computing Eigenvalues of the Fractional Schrödinger Operator

Journal of Systems science & Complexity 2024年第2期37卷 391-412页

作者： GUO Yixiao MING Pingbing LSEC Institute of Computational Mathematics and Scientific/Engineering ComputingAcademy of Mathematics and Systems ScienceChinese Academy of SciencesBeijing 100190China School of Mathematical Sciences University of Chinese Academy of SciencesBeijing 100049China

The authors present a novel deep learning method for computing eigenvalues of the fractional Schrödinger *** proposed approach combines a newly developed loss function with an innovative neural network architecture that incorporates prior knowledge of the *** improvements enable the proposed method to handle both high-dimensional problems and problems posed on irregular bounded *** authors successfully compute up to the first 30 eigenvalues for various fractional Schrödinger *** an application,the authors share a conjecture to the fractional order isospectral problem that has not yet been studied.

关键词： Eigenvalue problem deep learning fractional Schrödinger operator isospectral problem

来源：评论

学校读者我要写书评

暂无评论

Utilizing Big Data Analytics for Social Media Insights 5

Utilizing Big Data Analytics for Social Media Insights

引用

5th International Conference on IoT Based Control Networks and Intelligent Systems, ICICNIS 2024

作者： Vedhika Srinidhi, V.S. Sanjana, S. Rozario, Neo Joseph Dewan, Sia Gouthaman, P. School of Computing College of Engineering & Technology SRM Institute of Science and Technology Department of Networking and Communications Kattankulathur603203 India School of Computing Faculty of Engineering & Technology SRM Institute of Science and Technology Department of Networking and Communications Kattankulathur603203 India

ISBN: (纸本)9798331518097

Big Data analytics is a rapidly evolving field that offers profound insights into various sectors by enabling the analysis of massive and diverse datasets. This research paper focuses on the application of Big Data techniques to social media and airline networks, leveraging tools such as sentiment analysis, clustering, and data visualization to extract actionable information. The study analyses Twitter data to uncover public sentiment trends and classifies topics using advanced machine learning techniques. Furthermore, the research explores the use of clustering algorithms within the Hadoop ecosystem to process large-scale datasets efficiently. Insights from airline customer feedback and network planning data demonstrate how Big Data analytics can optimize operational efficiency and enhance customer satisfaction. Key findings include the identification of distinct sentiment patterns in social media data, the efficiency of novel clustering techniques in handling high-volume datasets, and the utility of advanced visualization methods to convey complex data. These results have significant implications for industries ranging from social media platforms to the airline sector, providing valuable tools for enhancing decision-making processes and improving user experiences across diverse domains. The study highlights the potential of Big Data analytics to drive innovation and operational excellence in dynamic environments. © 2024 IEEE.

关键词： Airline networks Big Data analytics Clustering algorithms Data visualization Sentiment analysis Social media

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Relational Approach Toward Stock Price Prediction and Profitability

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第11期5卷 5844-5854页

作者： Patel, Manali Jariwala, Krupa Chattopadhyay, Chiranjoy Sardar Vallabhbhai National Institute of Technology Department of Computer Science and Engineering Surat395007 India FLAME University School of Computing and Data Sciences Pune412115 India

An accurate estimation of future stock prices can help investors maximize their profits. The current advancements in the area of artificial intelligence (AI) have proven prevalent in the financial sector. Besides, stock market prediction is difficult owing to the considerable volatility and unpredictability induced by numerous factors. Recent approaches have considered fundamental, technical, or macroeconomic variables to find hidden complex patterns in financial data. At the macro level, there exists a spillover effect between stock pairs that can explain the variance present in the data and boost the prediction performance. To address this interconnectedness defined by intrasector stocks, we propose a hybrid relational approach to predict the future price of stocks in the American, Indian, and Korean economies. We collected market data of large-, mid-, and small-capitalization peer companies in the same industry as the target firm, considering them as relational features. To ensure efficient feature selection, we have utilized a data-driven approach, i.e., random forest feature permutation (RF2P), to remove noise and instability. A hybrid prediction module consisting of temporal convolution and linear model (TCLM) is proposed that considers irregularities and linear trend components of the financial data. We found that RF2P-TCLM gave the superior performance. To demonstrate the real-world applicability of our approach in terms of profitability, we created a trading method based on the predicted results. This technique generates a higher profit than the existing approaches. © 2024 IEEE.

关键词： Profitability

来源：评论

学校读者我要写书评

暂无评论

SecureML: Machine Learning-Powered Malware Detection 2

SecureML: Machine Learning-Powered Malware Detection

引用

2nd IEEE International Conference on Advances in Information Technology, ICAIT 2024

作者： Awasthi, Animay Ahsan, Mohd Vanusha, D. Delsi Robinsha, S. Department of Computing Technologies School of Computing SRM Institute of Science and Technology Chengalpattu District Tamilnadu Kattankulathur603 203 India Department of Computing Technologies School of Computing Faculty of Engineering and Technology SRM Institute of Science and Technology Chengalpattu District Tamilnadu Kattankulathur603 203 India

ISBN: (纸本)9798350383867

As malware threats become increasingly complex, the development of advanced detection systems is necessary to protect digital assets. SecureML Using Machine Learning presents an innovative approach to combat the escalating threat of malicious software by leveraging machine learning algorithms. This research paper outlines the design, implementation, and evaluation of SecureML, emphasizing its effectiveness in detecting both known and novel malware strains. Through comprehensive feature selection techniques and algorithmic comparison, SecureML identifies crucial features and selects the Random Forest algorithm as the most effective for malware detection, achieving an impressive accuracy rate of 99.40% on the test set. The system's low false positive and false negative rates validate its robustness and reliability in accurately distinguishing between benign and malicious files. SecureML demonstrates significant potential in bolstering cybersecurity defenses and safeguarding digital assets against evolving malware threats. © 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

Real-Time Weapon Detection System for Enhanced Security Monitoring 4

Real-Time Weapon Detection System for Enhanced Security Moni...

引用

4th International Conference on Ubiquitous computing and Intelligent Information Systems, ICUIS 2024

作者： Kuppili, Rohan Agarwal, Khusboo Bhosale, Tanmay Gouthaman, P. School of Computing College of Engineering and Technology Srm Institute of Science and Technology Department of Networking and Communications Kattankulathur603203 India School of Computing Srm Institute of Science and Technology Faculty of Engineering and Technology Department of Networking and Communications Kattankulathur603203 India

ISBN: (纸本)9798331529635

Innovative technology for weapon detection during security monitoring is necessary today due to the rising threats of violence and terror. The paper discusses a detailed design of a weapon detection system intended for application in enhancing security surveillance specifically using a deep learning approach. The system employs YOLOv3 (You Only Look Once, Version 3) mood and adaption aimed at live footage weapon detection. To do this on broader scale, this system incorporates big data tools Hadoop, Docker, Spark and Kafka for reasons of real time processing and effectiveness in high volume data situations. This model is applied on the live footage surveillance of public and private places to determine if the model can detect weapons, to warn relevant authorities in the aim of decreasing response time and averting security breach occurrences. The experiments conducted confirm that the model is capable of performing weapon detection tasks in an indoor environment with changes in illumination conditions with few false alarms. © 2024 IEEE.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Financial Fraud Detection for Credit Card Transactions Using Apache Spark 5

Financial Fraud Detection for Credit Card Transactions Using...

引用

5th International Conference on Sustainable Communication Networks and Application, ICSCNA 2024

作者： Jha, Pratyush Srivastava, Srijan Gandhi, Tanishq Gouthaman, P. School of Computing College of Engineering and Technology SRM Institute of Science and Technology Department of Networking and Communications Kattankulathur603203 India School of Computing SRM Institute of Science and Technology Faculty of Engineering and Technology Department of Networking and Communications Kattankulathur603203 India

ISBN: (纸本)9798331530013

The financial sector's rapid adoption of digital transformation has made identifying fraud a progressively complex challenge, since modern fraudulent activities present significant risks to institutions globally. This paper presents a novel methodology for detecting financial fraud that integrates big data analytics and machine learning techniques within a distributed environment. With an extensive number of actual financial transactions, the system uses Apache Spark for real-time data processing and machine learning algorithms to accurately classify fraudulent transactions. This method effectively addresses two major issues: efficiently processing large data sets and managing the severe class imbalance between fraudulent and non-fraudulent transactions. Collectively, these solutions provide a scalable and resilient framework for improving fraud detection in the digital era. © 2024 IEEE.

关键词： Nearest neighbor search

来源：评论

学校读者我要写书评

暂无评论

Road Damage Detection Using Real Time Video 8th

Road Damage Detection Using Real Time Video

引用

8th IFIP TC 12 International Conference on Computer, Communication and Signal Processing, ICCCSP 2024

作者： Gomathi, G. Niranjana, G. Department of Computer Science and Engineering SRM Institute of Science and Technology Tamil Nadu Kattankulathur India Department of Computing Technologies SRM Institute of Science and Technology Tamil Nadu Kattankulathur India

ISBN: (纸本)9783031736162

This study presents a completely unique deep-learning- powered real-time road damage detection system, paving the way for more secure roads and smarter infrastructure. With the help of convolutional neural networks (CNNs) and an easy to use interface, the system can automatically and clearly identify different types of road damage, such as surface irregularities, detailed fractures, and dangerous potholes. This innovative method surpasses the drawbacks of laborious manual inspections and ushers in a brand new age of advanced road safety and efficient maintenance. A strong CNN model that has been painstakingly trained on an intensive collection of annotated pictures and videos forms the basis of the system. It, as it should be, detects different sorts of damage with an accuracy close to 89%, offering users useful visible information via highlighting particular places on output pictures. However, the creativity doesn’t stop there. The system has a clean-to-use Tkinter graphical consumer interface (GUI) that facilitates engagement. It also has real-time alarm triggers that, without delay, inform the appropriate authorities, ensuring timely restoration and decreasing any safety threats. To make the system work better, it is put through a radical testing process using common evaluation standards along with F1-rating, accuracy, precision, and recall. The findings are clear-cut, which is revolutionary pressure in addition to a useful tool for finding road degradation. Beyond the instantaneous safety advantages, it offers better infrastructure management and optimized useful resource allocation, opening the door to a future in which technology protects our lives and creates more secure, more convenient travel. © IFIP International Federation for Information Processing 2025.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Design and Material Optimization of BLDC Motor Windings using FEM for Motor-Pump Applications using Existing Stator Stamping

Design and Material Optimization of BLDC Motor Windings usin...

引用

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

作者： Richard Pravin, A. Pongiannan, R.K. Srm Institute of Science and Technology Department of Electrical and Electronics Engineering Kattankulathur India Srm Institute of Science and Technology Department of Computing Technologies Kattankulathur India

ISBN: (数字)9798331510022

ISBN: (纸本)9798331510022

This paper covers the design of a 1 Hp, 48 V brushless DC (BLDC) motor-pump utilizing an existing V4 stator stamping. The conceptual BLDC motor design is simulated by choosing different winding configuration and material options, where the number of turns also changed. An analytical approach specifically suited to pumping applications is proposed. Detailed scrutiny of the BLDC motor is carried out based on Finite Element Method (FEM) incorporating sustainable design practices. Simulations of magnetic flux distribution in Infolytica MagNet 7.1 are executed to determine the output characteristics. BLDC motors at 48 V corresponds to an efficiency of 94.06% produced power is 745 W. Torque maximum and speeds corresponded at 7.16 Nm and 3000 rpm whereas cogging torque is 0.74 Nm. The motor's efficiency and stable speed improve overall conversion efficiency by 6% in operational limits, confirming the proposed BLDC motor-pump is energy efficiency. © 2024 IEEE.

关键词： Stators

来源：评论

学校读者我要写书评

暂无评论

Applications of Clustering in Cognitive Radio Networks 15

Applications of Clustering in Cognitive Radio Networks

引用

15th International Conference on Advances in computing, Control, and Telecommunication Technologies, ACT 2024

作者： Joykutty, Anu Maria Baranidharan, B. Rajagiri School of Engineering & Technology Department of Computer Science & Engineering Kochi India SRM Institute of Science & Technology Department of Computing Technologies Chennai India

ISBN: (纸本)9798331300579

With the use of cognitive radio (CR) technology, wireless devices can utilize licensed spectrum when it is unused by the licensed users. CR was developed as a response to the wireless spectrum shortage issue caused by the static spectrum allocation. Using CR technology, the unlicensed users can opportunistically access the spectrum during the absence of usage by the licensed users. Clustering is a widely used technique in Cognitive Radio Networks (CRNs) to efficiently manage network resources, optimize spectrum utilization, and enhance overall network performance. This study focuses on the applications of clustering techniques in the area of CRNs like spectrum management, QoS Support, topology management, energy efficiency, routing etc. © Grenze Scientific Society, 2024.

关键词： Cognitive radio

来源：评论

学校读者我要写书评

暂无评论

Optimizing Vanet Communications: A Bibliometric Analysis of Energy-Efficient Strategies with Deep Learning

Optimizing Vanet Communications: A Bibliometric Analysis of ...

引用

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

作者： Suganya, R. Prakash, B. Srm Institute of Science and Technology Department of Computer Science and Engineering Tamilnadu Kattankulathur India Srm Institute of Science and Technology Department of Computing Technologies Tamilnadu Kattankulathur India

ISBN: (数字)9798331510022

ISBN: (纸本)9798331510022

Vehicular Ad Hoc Networks (VANETs) are important for intelligent transportation systems, permitting vehicles to communicate with one another and nearby infrastructure in order to enhance road safety, traffic management and infotainment services. But the VANET communication is a high energy consumption technology, which may become a big challenge of large-scale power efficiency being in some real scenarios where huge number vehicles are needed to implement such V2I or V2V services sustaining. This paper conducts a analysis of different transmission stratagems for energy-efficient communication strategies among vehicles in VANETs, along with the focus to incorporate deep learning accelerators into an optimized architecture framework for enhancing communication processes. The paper presents an overview of VANET architecture and communication protocols, and then reviews the techniques to save energy in a VANET including efficient mechanisms for Transmission Power Control (TPC), some energy-aware routing protocols, as well as data aggregation realizations. Next, the paper introduces deep learning models that can adaptively optimize VANET transmission by forecasting network states and updating strategies on-the-fly. This analysis emphasizes hybrid solutions where deep learning is combined with traditional communication strategies to improve the energy efficiency apparent on a system level. Finally addresses the current challenges in the field and the need for advanced AI-driven techniques. This bibliometric analysis provides a comprehensive overview of energy-efficient communication strategies in VANETs, offering insights into how deep learning can contribute to the development of more sustainable vehicular networks. © 2024 IEEE.

关键词： Vehicular ad hoc 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：