检索结果-内蒙古大学图书馆

2025 IEEE International Students' Conference on Electrical, Electronics and computer Science, SCEECS 2025

作者： Abinaya, R. Sekar, Rajeev Pai, Tarun Vinod Thippa, Subhash Praveen Joe, I.R. School of Computer Science and Engineering Vellore Institute of Technology Chennai India

ISBN: (纸本)9798331529833

This study presents a highly efficient helmet detection system designed for real-time operation on low-cost edge devices, targeting helmet compliance monitoring in vehicular environments. A novel dataset was created by capturing images from an innovative perspective by positioning the camera above the vehicle's read-view mirror. This provided a unique top-down view that enhances the performance of real-time helmet detection in dynamic traffic conditions. The dataset comprises three defined classes: (2) no face, (1) face without a helmet, and (0) face with a helmet. This reflected the diverse scenarios encountered in real-world situations. A Deep Learning (DL) model was trained and compiled into TensorFlow Lite (TFLite) format which optimizes the model for low-power edge devices with minimal computational resources. The proposed methodology achieved a high classification accuracy of 99.56%. This work not only concentrates on maximizing the computational efficiency of helmet detection on edge devices but also offers a scalable and cost-effective solution for traffic safety monitoring. By integrating advanced deep learning capabilities with affordable hardware, this study provides a valuable tool for automated helmet detection, contributing to the improvement of road safety rules compliance. © 2025 IEEE.

关键词： Magnetic levitation vehicles

来源：评论

学校读者我要写书评

暂无评论

Optimized-Memory and Enhanced-Security Approaches to RSA and ElGamal

Optimized-Memory and Enhanced-Security Approaches to RSA and...

引用

2025 International Conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Kumar, Maheswer Sunil Balaji, Vinithra Sakkarapani, Sandosh School of computer Science and Engineering Vellore Institute of Technology Chennai India

ISBN: (纸本)9798331509828

This paper demonstrates 2 methods, a reduced memory technique, and a reduced memory along with more security techniques in RSA (Rivest-Shamir-Adleman) and ElGamal which are both asymmetric cryptographic algorithms. Regular RSA and ElGamal are known to be performance efficient, but memory wise, they were not efficient. Also, to enhance security of any algorithm, the key size is increased leading to more memory and computation. To solve these challenges, hashing method is used through which, the memory can be reduced without affecting the security or the performance of the algorithms. Along with these hashmaps, we create an array manipulation method, which enhances the security of data in the algorithm by making the cipher text more complex. The above is performed using pipe-lining and use of python. The objective of this research work is to optimize RSA and ElGamal algorithm with respect to memory load and increasing security, without affecting the overall computational overhead of the system. The results aim to contribute to the advancement of these cryptographic techniques and especially resource constrained environments, where memory is an important factor and for more security required procedures. The hashing method optimizes the performance of RSA and ElGamal and their use in transferring large confidential files and the array method enhances the security using a modulus acting as another key. Furthermore, this optimized technique can be applied to other cryptographic solutions © 2025 IEEE.

关键词： Pipe linings

来源：评论

学校读者我要写书评

暂无评论

Multi-Agent hierarchical workflow for autonomous code generation with Large Language Models

Multi-Agent hierarchical workflow for autonomous code genera...

引用

2025 IEEE International Students' Conference on Electrical, Electronics and computer Science, SCEECS 2025

作者： Akilesh, S. Sekar, Rajeev Om Kumar, C.U. Prakalya, D. Suguna, M. Vellore Institute of Technology School of Computer Science and Engineering Chennai India

ISBN: (纸本)9798331529833

This paper presents a multi-agent hierarchical workflow tailored for automating data analysis, code generation, and visualization, focusing specifically on user-provided CSV datasets. The workflow integrates AlphaCodium with LangChain, LangGraph, and GPT, enabling autonomous code generation, unit test development, and debugging. The system operates by analyzing the uploaded dataset, assigning agents that work sequentially: a programmer agent generates code using the Skeleton-Of-Code approach, a unit test agent verifies the code, and an executor agent runs the code. A debugging agent is also included to identify and resolve any issues. The AI agents involved are capable of dynamically accessing online resources, including documentation and references to enhance their decision-making processes. This work attempts to exemplify the application of AI in automating not only code execution but also the planning and validation stages by writing unit tests in the software development process to reflect the increasing role of AI in advancing automation for rapid code generation within the software industry. © 2025 IEEE.

关键词： Software design

来源：评论

学校读者我要写书评

暂无评论

Stereotactic Needle Path Planning for Brain Biopsy Based on Volumetric Segmentation of MRI and Heuristic Approach 5th

Stereotactic Needle Path Planning for Brain Biopsy Based on ...

引用

5th International Conference on Advances in Information Communication technology and Computing, AICTC 2024

作者： Krishnan, Sushil Bhogale, Atharva Gawande, Aarya Jaisankar, N. School of Computer Science and Engineering Vellore Institute of Technology Vellore India

ISBN: (纸本)9789819761050

Any abnormal growth in brain cells refers to brain tumor. With large variety of tumors reported, accurate diagnosis is very essential for appropriate intervention. Traditionally, biopsies are preferred diagnostic tool, where a small piece of tissue or some cells are collected from suspected region and tested in a laboratory. Brain being the control and coordination center, biopsy in brain requires utmost precision and accuracy to avoid any damage to healthy tissues. Stereotactic needle biopsies are specialized minimally invasive technique for collecting the required samples. In such cases precise path planning is very essential. Availability of large medical image datasets and enormous computational capability encourages to train deep learning models that can accurately delineate and identify the tumor’s location, shape, size, and borders within the patient's brain. Volumetric segmentation combined with heuristic path planning algorithm can play a synergistic role in increasing the success rates of brain biopsies. The main objective of the work is to propose a framework for precise needle insertion for brain tumor biopsies. The work proceeds by comparing performances of various model for volumetric segmentation of brain MRI scans and identifying shortest path to the tumor, utilizing the segments obtained. This approach minimizes blood loss and the need for extensive medical intervention. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Biopsy

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-based Classification of Infant Cries for Parental Assistance: A Study using MFCC and CNN Technique 3

Deep Learning-based Classification of Infant Cries for Paren...

引用

3rd International Conference on Electronics and Renewable Systems, ICEARS 2025

作者： Mala, B.M. Darandale, Smitha Sandeep Gitam School of Technology Department of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798331509675

Worldwide Approximate count of 130 million babies were born per annum. Maintaining newborn babies is a great difficulty, mainly for first-time parents. However, intimations from experienced parents, books, and videos help to a certain extent but not significantly because of difficulty understanding the meaning of Infant cries. Researchers have proposed several techniques using machine learning and artificial intelligence. In this work, we try to leverage deep learning-based techniques such as convolutional neural networks (CNN) to identify the infant crying. Infant crying is further classified into four classes (inclusive of pain, hunger, sleepiness, and wet diaper). The MFCC (Mel-Frequency Cepstral Coefficients) technique is used for feature extraction, as it efficiently captures audio characteristics from crying sounds. In this study, will compare the various existing machine learning models with our proposed model. Among the models evaluated, MFCC combined with Convolutional Neural Networks (CNN) achieves the highest accuracy of 95.5%, for classifying the infant cry and reasoning. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

FNRS-MSC: Federated News Recommender System Integrating Multiple Self-Attention and Convolution 24

FNRS-MSC: Federated News Recommender System Integrating Mult...

引用

8th International Conference on computer Science and Artificial Intelligence, CSAI 2024

作者： Li, Weiwei Xia, Xuan School of Computer Science and Engineering Chongqing University of Technology ChongQing China

ISBN: (纸本)9798400718182

News recommendation is an important feature to help users discover news that matches their bias. In response to users’ growing privacy concerns, various recommendation models integrating joint learning have been developed to preserve user privacy. However, these approaches often prioritize protecting user privacy over recommendation performance. This study introduces a federated news recommendation method, FNRS-MSC (Federated News Recommender System Integrating Multiple Self-Attention and Convolution), to address this challenge. The approach is based on a federated learning recommendation model that integrates an attention mechanism in a pre-trained language model (BERT), which is capable of extracting essential features and reducing dimensionality to enhance news representations. In addition, a one-dimensional convolutional layer is integrated for the user encoder in a multiple self-attention model (NRMS) to address the problem of ignoring news features in the user model. Experimental results on two real datasets show that the approach outlined in this study is effective in both protecting user privacy and providing high-quality recommendations. © 2024 Copyright held by the owner/author(s).

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

FLAG: frequency-based local and global network for face forgery detection

引用

Multimedia Tools and Applications 2025年第2期84卷 647-663页

作者： Zhou, Kai Sun, Guanglu Wang, Jun Wang, Jiahui Yu, Linsen School of Computer Science and Technology Harbin University of Science and Technology Harbin150080 China Department of Information Engineering and Mathematics University of Siena Siena53100 Italy

Deepfake detection aims to mitigate the threat of manipulated content by identifying and exposing forgeries. However, previous methods primarily tend to perform poorly when confronted with cross-dataset scenarios. To address the above issue, we propose an innovative hybrid network called the Frequency-based Local and Global (FLAG) network to explore local and global information with the help of frequency-domain cues for better generalization capability. In consideration of the fact that forged faces often exhibit flaws in the frequency domain, we design a Frequency-based Attention Enhancement Module (FAEM) to enhance the aggregation of CNN and Vision Transformer (ViT). In this design, local features from CNN are attentively enhanced by selected frequency coefficients in FAEM, facilitating generalizable global features learning by the ViT module. The effectiveness of the proposed method is validated via numerous experiments and the generalization performance is improved under cross-dataset scenarios. Especially, the proposed method have obtained an AUC of 99.26% and an ACC of 96.56% using intra-dataset experimental results on FaceForensics++ (C23). © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Enhancing Web Security: A Phishing Detection System Integrated with Password Managers 6

Enhancing Web Security: A Phishing Detection System Integrat...

引用

6th International Conference on Mobile Computing and Sustainable Informatics, ICMCSI 2025

作者： Subbulakshmi, T. Meghana, G. Sunkara, S. Ravi Sailendra Shanmukha Sai, V. School of Computer Science and Engineering Vellore Institute of Technology Chennai India

ISBN: (纸本)9798331522667

Phishing attacks have become a widespread and intricate threat, targeting individuals and organizations through deceptive URLs to steal sensitive information such as login credentials and financial data. These attacks exploit human vulnerabilities and frequently employ advanced techniques like URL obfuscation and social engineering to evade traditional security measures. Despite ongoing advancements in cybersecurity, phishing remains a persistent issue due to its adaptability and the continual evolution of attack strategies. This paper introduces a comprehensive phishing detection system that implements both rule-based analysis with machine learning models to address these challenges effectively. The system utilizes YARA rules to detect known phishing patterns and integrates real-time threat intelligence feeds for up-to-date phishing data. Additionally, it employs machine learning algorithms to enhance detection accuracy and adapt to emerging threats. The system is further strengthened by its integration with a password manager, providing real-time URL validation and alerts to users during their online activities. This multi-faceted approach aims to improve the accuracy of phishing detection and offer robust protection against the increasingly advanced methods employed by attackers. © 2025 IEEE.

关键词： Phishing

来源：评论

学校读者我要写书评

暂无评论

Toward Collaborative Intelligence for Meta-Computing-Driven IIoT Based on Vertical Federated Learning With Fast Convergence

引用

IEEE Internet of Things Journal 2025年第10期12卷 13806-13816页

作者： Li, Youqi Liu, Shuangji Meng, Yanchen Qi, Shenyi Qu, Zhe Li, Fan Wang, Yu Beijing Institute of Technology School of Computer Science and Technology Beijing100081 China Central South University School of Computer Science and Engineering Changsha410083 China Temple University Department of Computer and Information Sciences PhiladelphiaPA19122 United States

Industrial Internet of Things (IIoT) is an emerging technology that digitizes industrial production and realizes Industry 4.0. However, it shows that IIoT is difficult to enable sophisticated downstream applications without eliciting all devices to achieve collaborative intelligence. Existing works on IIoT either require the consolidation of various IIoT devices’ data into a single centralized server which has potential privacy breach, or coordinate devices to learn a global model in privacy-preserving federated learning (FL) but assume data across devices has the sample feature space and neglect the heterogeneity of IIoT devices. In this article, we propose Meta-computing-driven vertical FL (VFL) algorithms to achieve collaborative intelligence in IIoT where heterogeneous devices have imperfect data with incomplete features. Specifically, we first provide the modeling of N devices’ VFL to collectively train the submodels and the common model. We present the computing graph to clearly indicate the gradient evaluation. To enable a fast convergence performance, we design a variance-reduced gradient estimator that can be seamlessly integrated into the basic VFL. Finally, we evaluate our proposed VFL by conducting experiments on the MNIST dataset regarding image recognition and the DAWM dataset for detecting anomalies in wafer manufacturing. The experimental results show that our VFL for IIoT is both effective and efficient. © 2014 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

InsightNav - Empowering Desktop Navigation with computer Vision

InsightNav - Empowering Desktop Navigation with Computer Vis...

引用

2025 IEEE International Students' Conference on Electrical, Electronics and computer Science, SCEECS 2025

作者： Sharma, Ayush Kumar Wakchaure, Supriya Bharat Twinkle, Tanya Vignesh, U. Vellore Institute of Technology School of Computer Science and Engineering Chennai India

ISBN: (纸本)9798331529833

InsightNav redefines desktop interaction by harnessing cutting-edge computer vision and AI technologies to deliver a transformative user experience. Beyond its intuitive gesture-based navigation, InsightNav pioneers two groundbreaking features that elevate human-computer interaction. The first, Personalized Desktop Themes Based on Emotion Detection, leverages real-time facial expression analysis to dynamically alter the desktop's visual aesthetics based on the user's mood. This innovation empowers the system to foster emotional well-being, transitioning to serene themes during stress or energizing designs to amplify motivation. The second feature, Voice-Activated Multitasking Snap Layouts, revolutionizes task management by enabling users to orchestrate optimized application layouts through simple voice commands. By uttering phrases like "Focus Mode,"users can seamlessly arrange tools such as browsers, editors, and readers, thereby accelerating productivity and streamlining workflows. Powered by MediaPipe, OpenCV, and Google Speech-to-Text, InsightNav transcends traditional interaction paradigms, offering unparalleled accessibility, efficiency, and personalization. Together, these innovations position InsightNav as a revolutionary tool, setting new benchmarks in adaptive and immersive human-computer interaction. © 2025 IEEE.

关键词： Gesture recognition

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：