检索结果-内蒙古大学图书馆

6th International Conference on Inventive Computation Technologies, ICICT 2023

作者： Veena, K. Meena, K. Mercy Theresa, M. Hemalatha, C. Rajalakshmi, D. Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai600119 India Department of Computer Science and Engineering GITAM School of Technology GITAM Bangalore561203 India Department of Data Science and Business Systems School of Computing College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Chennai603203 India Computer Science and Engineering Sri Sairam Institute of Technology Chennai India

ISBN: (纸本)9798350398496

Network security is a critical issue in modern technology. Honey pot-based intrusion detection methods provide an additional layer of security and enhance network performance by analyzing hacker behaviour and detecting unauthorized clients. IP validation and vulnerability detection are used to ensure authorized customer access and prevent illegal client activity. A voice recognition system detects malicious attacks in stage two. If authorized, packets are passed to the server, otherwise, they are delivered to honeypot servers. Using Naive Bayes algorithm, the detection rate is 85.06% with an accuracy of 98.18% and a false alarm rate of 0.15 seconds. © 2023 IEEE.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Customer Churn Prediction System using Deep Learning Techniques

Customer Churn Prediction System using Deep Learning Techniq...

引用

IEEE International Conference on Emerging & Sustainable Technologies for Power & ICT in a Developing Society (NIGERCON)

作者： Tope-Oke Adebusola Modupeola Olatokun Wole Michael Abdulazeez Olayinka Olatokun Babalola Gbemisola Obamiyi Stephen Eyitayo Abiola Oluwatoyin Oguntimilehin Abiodun Department of Computing Afe Babalola University Ekiti State Nigeria Department of Data and Information Science University of Ibadan Oyo State

ISBN: (数字)9798331542559

ISBN: (纸本)9798331542566

Modern business operations necessitate churn prediction systems, particularly in industries with subscription-based services and recurring revenue streams. This study proposes a deep learning-based customer churn prediction system for e-commerce, aiming to identify and retain at-risk customers. Addressing the limitations of previous studies—such as sparse representation of industry-specific challenges and limited exploration of deep learning models and feature engineering—the study utilizes the cell2cell dataset to build predictive models. Techniques like principal component analysis, correlation matrices, and random forest classifiers, alongside Python tools, were employed for data preparation and feature selection. Advanced deep learning methods, including recurrent neural networks (RNNs) and long short-term memory (LSTM) networks, were used to improve prediction accuracy and capture temporal relationships in customer behavior. Performance was evaluated using metrics like accuracy, precision, recall, F1 score, and AUC score. Results indicated that RNN achieved accuracy and AUC scores of 0.7108 and 0.6107, respectively, while LSTM achieved scores of 0.7106 and 0.6026. The study recommends future research to employ deep learning and advanced feature engineering approaches to enhance churn prediction systems.

关键词： Deep learning Accuracy Recurrent neural networks Sparse approximation Predictive models Electronic commerce Sparse matrices Churn Long short term memory Streams

来源：评论

学校读者我要写书评

暂无评论

Logical Relation Modeling and Mining in Hyperbolic Space for Recommendation 40

Logical Relation Modeling and Mining in Hyperbolic Space for...

引用

40th IEEE International Conference on data Engineering, ICDE 2024

作者： Tan, Yanchao Lv, Hang Zhou, Zihao Guo, Wenzhong Xiong, Bo Liu, Weiming Chen, Chaochao Wang, Shiping Yang, Carl College of Computer and Data Science Fuzhou University Fuzhou China Engineering Research Center of Big Data Intelligence Ministry of Education Fuzhou China Fujian Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou China Institute for Artificial Intelligence University of Stuttgart Stuttgart Germany College of Computer Science Zhejiang University Hangzhou China Emory University Department of Computer Science Atlanta United States

ISBN: (纸本)9798350317152

The sparse interactions between users and items have aggravated the difficulty of their representations in recommender systems. Existing methods leverage tags to alleviate the sparsity problem but ignore prevalent logical relations among items and tags (e.g., membership, hierarchy, and exclusion), which can be leveraged to enhance the accuracy of modeling user preferences and conducting recommendations. To this end, we propose to extract logical relations among item tags from existing tag taxonomies and exploit the individual strengths of the Poincaré and the Lorentz models in hyperbolic space for logical relation modeling towards enhanced recommendations. Moreover, we find that the logical relations directly extracted from existing tag taxonomies can be inaccurate and coarse. Therefore, we further devise innovative consistency-based and granularity-based weighting mechanisms based on user behavior patterns for data-driven logical relation mining that can be jointly optimized along with recommendations in an end-to-end fashion. Extensive experiments on four real-world benchmark datasets show drastic performance gains brought by our proposed framework, which constantly achieves an average of 8.25% improvement over state-of-the-art competitors regarding both Recall and NDCG metrics. Insightful case studies further demonstrate that our automatically refined logical relations are highly accurate and interpretable. © 2024 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Enhancing Effective Learning Capability of SOAR Agent based Episodic Memory

Enhancing Effective Learning Capability of SOAR Agent based ...

引用

2023 International Conference on Artificial Intelligence and Smart Communication, AISC 2023

作者： Kaswan, Kuldeep Singh Naruka, Mahaveer Singh Dhatterwal, Jagjit Singh Galgotias University School of Computing Science and Engineering Greater Noida India G L Bajaj Institute of Technology and Management Greater Noida India Koneru Lakshmaiah Education Foundation Department of Artificial Intelligence & Data Science AP Vaddeswaram India

ISBN: (纸本)9798350322309

In order to increase the agent's intelligence, the fundamental goal of the research paper is to learn from its experiences. In order to solve a problem, learning is accomplished with the aid of episodic memory, which stores previous experiences as episodes. This study illustrates the improvement in intelligence with the use of the application of an example in soar. Working memory elements (WMEs), which are episodes (past experiences) in the form, are discussed in this paper as a means of enhancing intelligence. The purpose of this work is to demonstrate that knowledge always leads to performance improvement, meaning that as an agent studies more, performance will extend. © 2023 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

ECC-Based Encryption with ECDSA for Medical Images

ECC-Based Encryption with ECDSA for Medical Images

引用

IEEE International Conference on Emerging & Sustainable Technologies for Power & ICT in a Developing Society (NIGERCON)

作者： Olanike Christianah Akinduyite Samuel Jemirin Tolani Grace Oluwatoki Bukola Badeji-Ajisafe Abiodun Oguntimilehin Adebayo Olusola Adetunmbi Stephen E. Obamiyi Josephine Mebawondu Oluwatoyin Okebule Department of Computing Afe Babalola University Ado-Ekiti Nigeria Department of Data Science Federal University of Technology Akure Nigeria

ISBN: (数字)9798331542559

ISBN: (纸本)9798331542566

The work aims to develop a user-friendly encryption and decryption using Elliptic Curve Cryptography. The Elliptic Curve Digital Signature Algorithm (ECDSA) is used to perform cryptographic functions such as key generation, encryption, and decryption on medical images. Three categories of images used are Magnetic Resonance Imaging (MRI) Scans, Computed Tomography (CT) Scans, and X-ray Scans. These images are encrypted and decrypted individually using the Elliptic Curve Digital Signature Algorithm (ECDSA). Experiments are carried out to test the accuracy of the images based on the Peak Signal-Noise Ratio (PSNR), Encryption time, and Decryption time. The original and decrypted images are compared using the Peak Signal-Noise Ratio (PSNR) to determine the difference between the original image and the decrypted image. Comparing the result, the Elliptic Curve Digital Signature Algorithm achieved a higher PSNR values compared to the accuracy of other cryptography systems. The Encryption and decryption times of the images averaged 0.007 seconds in overall compared to the 1,261 seconds average achieved using a different cryptography system. The analysis of the results showed how well the ECDSA algorithm protects the accuracy of medical image data when decrypted and also shows accuracy of Elliptic Curve Digital Signature Algorithm (ECDSA) over other methods.

关键词： Accuracy PSNR Elliptic curves Magnetic resonance imaging Computed tomography Elliptic curve cryptography Encryption Digital signatures X-ray imaging Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Cloud-Based Road Safety for Real-Time Vehicle Rash Driving Alerts with Random Forest Algorithm 3

Cloud-Based Road Safety for Real-Time Vehicle Rash Driving A...

引用

3rd International Conference for Innovation in Technology, INOCON 2024

作者： Presitha Aarthi, M. Reddy, Chilukala Mahender Anbarasi, A. Mohankumar, N. Ishwarya, M.V. Murugan, S. Shree Sathyam College of Engineering and Technology Department of Computer Science and Engineering Tamil Nadu Salem India Gitam University Department of Computer Science and Engineering Telangana Hyderabad India Srm Institute of Science and Technology School of Computing Department of Computing Technologies Chennai Tamil Nadu Kattankulathur India B.V. Raju Institute of Technology Department of Electronics and Communication Engineering Telangana Hyderabad India Agni College of Technology Artificial Intelligence and Data Science Department Tamil Nadu Chennai India Saveetha University Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Biomedical Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350381931

The cloud-based road safety technology introduced in this research improves real-time vehicle behavior monitoring and warns for rash driving. It uses cloud computing to gather and interpret data from onboard car sensors and other traffic monitoring equipment. Powerful machine learning technology the Random Forest (RF) algorithm analyses this data intelligently. The RF algorithm is trained on a varied array of driving metrics to detect rash driving tendencies. Real-time data streams may be processed efficiently and scalable on the cloud, enabling speedy decision-making for rash driving detection. A network sends alerts to authorities and nearby vehicles. The system is adaptable to different road conditions, resistant to sensor data noise, and able to enhance rash driving detection accuracy via model updates. Cloud architecture makes the system available worldwide. With its focus on real-time notifications utilizing the RF algorithm, this cloud-based road safety system may reduce the hazards of reckless driving and avoid accidents. © 2024 IEEE.

关键词： Cloud computing architecture

来源：评论

学校读者我要写书评

暂无评论

Real-Time Decision-Making Techniques using Artificial Intelligence and Cloud computing

Real-Time Decision-Making Techniques using Artificial Intell...

引用

2023 International Conference on Disruptive Technologies, ICDT 2023

作者： Kaswan, Kuldeep Singh Dhatterwal, Jagjit Singh Kumar, Naresh Awasthi, Shashank Chauhan, Sansar Singh Galgotias University School of Computing Science & Engineering UP Greater Noida India Koneru Lakshmaiah Education Foundation Department of Artificial Intelligence and Data Science AP Vaddeswaram India Gl Bajaj Institute of Technology & Management Greater Noida India

ISBN: (纸本)9798350323887

scientific research will increasingly rely on AI and the cloud in the future;our suggested solution will allow us to use these technologies to solve a number of problems (CC). We have outlined the different issues that may be addressed via the combined efforts of cloud computing and AI and discussed how to implement such an approach. One of the most powerful exploration techniques is, for example, using cloud-based artificial intelligence algorithms to increase productivity. Drive to create apps, manufactured in the cloud, beyond the fundamental automation pro, requires the ability to predict scenarios and make continuous decisions online. In this paper, we describe a programming language for intelligent computing that will enable machines to reason and make choices for themselves, in real time. © 2023 IEEE.

关键词： Cloud computing

来源：评论

学校读者我要写书评

暂无评论

Violence Detection System using MobileNetV2

Violence Detection System using MobileNetV2

引用

Applied Artificial Intelligence and computing (ICAAIC), International Conference on

作者： Rahul Kumar Aniket Gupta D Rajeswari Department of Data Science and Business Systems School of computing College of Engineering and technology SRM Institute of Science and Technology Kattankulathur Chennai India

ISBN: (数字)9798350375190

ISBN: (纸本)9798350375206

The number of cases of violence and fights has been increasing around the world. With the use of CCTV, such incidents can be recorded but the detection of Violence is a major issue around the globe, and it plays a vital role in the safety and security of the area. It helps in effective surveillance and law enforcement. The effectiveness of any violence detection system depends on the speed and accuracy with which it detects the events and how it performs over different types of videos of varied sizes and formats. In the proposed algorithm, the dataset used contains videos of different types and scenarios to help the model understand and train better. To improve the overall effectiveness of the model, Lightweight CNN MobileNetV2 has been used along with that Bidirectional LSTM (BiLSTM) has been used. The accuracy rate of the proposed model is 98%.

关键词： Analytical models Accuracy Computational modeling Surveillance Bidirectional control Feature extraction Security

来源：评论

学校读者我要写书评

暂无评论

Multi-fidelity physics constrained neural networks for dynamical systems

arXiv

引用

arXiv 2024年

作者： Zhou, Hao Cheng, Sibo Arcucci, Rossella Department of Earth Science & Engineering Imperial College London United Kingdom Data Science Institute Department of Computing Imperial College London United Kingdom

Physics-constrained neural networks are commonly employed to enhance prediction robustness compared to purely data-driven models, achieved through the inclusion of physical constraint losses during the model training process. However, one of the major challenges of physics-constrained neural networks consists of the training complexity especially for high-dimensional systems. In fact, conventional physics-constrained models rely on singular-fidelity data necessitating the assessment of physical constraints within high-dimensional fields, which introduces computational difficulties. Furthermore, due to the fixed input size of the neural networks, employing multi-fidelity training data can also be cumbersome. In this paper, we propose the Multi-Scale Physics-Constrained Neural Network (MSPCNN), which offers a novel methodology for incorporating data with different levels of fidelity into a unified latent space through a customized multi-fidelity autoencoder. Additionally, multiple decoders are concurrently trained to map latent representations of inputs into various fidelity physical spaces. As a result, during the training of predictive models, physical constraints can be evaluated within low-fidelity spaces, yielding a trade-off between training efficiency and accuracy. In addition, unlike conventional methods, MSPCNN also manages to employ multi-fidelity data to train the predictive model. We assess the performance of MSPCNN in two fluid dynamics problems, namely a two-dimensional Burgers’ system and a shallow water system. Numerical results clearly demonstrate the enhancement of prediction accuracy and noise robustness when introducing physical constraints in low-fidelity fields. On the other hand, as expected, the training complexity can be significantly reduced by computing physical constraint loss in the low-fidelity field rather than the high-fidelity one. © 2024, CC BY-NC-ND.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Neuroimaging Precision: Crafting a Stacked VGG19-Logistic Fusion for Breakthrough Early Detection of Alzheimer's

Neuroimaging Precision: Crafting a Stacked VGG19-Logistic Fu...

引用

International Conference on science Technology Engineering and Management (ICONSTEM)

作者： G. Anbu Selvi T. Karthick Department of Computer Science and Engineering SRMIST Kattankulathur Chennai India Department of Data Science and Business Systems SRMIST Kattankulathur School of Computing Chennai India

ISBN: (数字)9798350365092

ISBN: (纸本)9798350365108

Several medical investigations have demonstrated that Alzheimer's disease (AD) manifests itself long before the formal diagnosis of dementia. These studies have led to the identification of numerous ideal biomarkers associated with Alzheimer's symptoms. Consequently, the imperative for early diagnosis has become evident, necessitating a high-performance computational tool capable of efficiently processing vast amounts of data. Early detection of AD not only offers valuable insights into the condition's progression but also presents a significant opportunity to benefit from timely and effective treatment. This ground-breaking study pioneers an innovative approach to the early detection and diagnosis of AD by crafting a sophisticated model SVGGL, which blends the power of stacked VGG19 neural networks with the interpretability of logistic regression. Leveraging neuro-imaging data, specifically the insights provided MRI, and our model aims to discern subtle structural and functional alterations in the brains of individuals at risk for or in the early stages of AD. The combination of feature extraction from stacked VGG19 models and subsequent logistic regression classification yields a precise and efficient classifier with an outstanding accuracy of 98.24%. With such a high degree of accuracy, the model can reliably differentiate among healthy people and those with Alzheimer's, opening the door to potential early intervention and individualized treatment plans. The study not only sheds light on the intricate neuro pathological landscape of AD but also propels us toward a future where cutting-edge technology and data-driven insights, exemplified by our high-accuracy model, converge to tackle the challenges posed by this prevalent neurodegenerative disorder.

关键词： Neuroimaging Logistic regression Accuracy Computational modeling Brain modeling Feature extraction data models

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：