检索结果-内蒙古大学图书馆

2023 International Conference on Sustainable Computing and Smart Systems, ICSCSS 2023

作者： Theertani, Malluri Reddy Valeti, Neha Solanki, Darshini Kumar, Kakelli Anil Vellore Institute of Technology Vellore Computer Science and Engineering Vellore India Vellore Institute of Technology Vellore Sr. School of Computer Science Engineering Vellore India

ISBN: (纸本)9798350333602

Cloud computing has recently experienced rapid expansion, making it a major target for cybercrimes. Though cloud computing has many advantages, there are also substantial security issues related to confidentiality, integrity, privacy, and availability. Being a relatively new discipline, cloud forensics faces numerous challenges and issues with interpreting and analyzing data. Forensic investigators and law enforcement confront numerous difficulties in data collection, data protection, and evidence access. Several sophisticated models have been proposed in recent years aiming to accelerate the entire investigation process or address several issues that arise frequently in forensic investigations. This review paper seeks to comprehend the significance of various machine learning models which would help cloud forensics advance significantly. It also provides a detail information on cloud forensics as well as the research trends that have been going on in this field over the past few years. A detailed comparative analysis of different approaches of machine learning on development of cloud forensics has been presented in this research study. © 2023 IEEE.

关键词： Data acquisition

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

An efficient cloud based face recognition system for e-health secured login using steerable pyramid transform and local directional pattern

引用

Journal of Ambient Intelligence and Humanized Computing 2024年第1期15卷 1017-1027页

作者： Dosaj, Ayush Satapathy, Suresh Chandra Soundrapandiyan, Rajkumar Kaur, Mannat Hannoon, Naeem School of Computer Science and Engineering Vellore Institute of Technology Vellore India School of Computer Science and Engineering Kalinga Institute of Industrial Technology Deemed to be University Odisha Bhubaneswar India Faculty of Electrical Engineering Universiti Teknologi MARA Shah Alam Malaysia

This paper proposes a face recognition system based on steerable pyramid transform (SPT) and local directional pattern (LDP) for e-health secured login in cloud domain. In an e-health login, patients periodically forget their self-made login username and password. This face recognition system can replace the traditional login system. In the proposed system, SPT can decompose a face image into several sub-bands of different scales and orientations, and LDP can encode the sub-bands in binary texture pattern. The LDP binary pattern was obtained by computing the edge response values in all eight directions at each pixel position and generating a code from the relative strength magnitude. Therefore, SPT–LDP design represents a face image in a robust way which includes multiple information sources from different scales and orientations. The proposed system is tested on standard benchmark facial recognition technology (FERET) and extended Yale-B databases. Further, the efficiency of the proposed system is proved by comparing recognition rates with other existing descriptor based methods. From the experimental results it is observed that the proposed system achieves 99.79% recognition in fb set, 90.72% in fc set, 84.97% in dup I set, and 87.69% in dup II set for FERET database and 100% in sub2 set, 100% in sub3 set, 96% in sub4 set and 95% in sub5 set for extended Yale-B database which is better than the existing methods. © Springer-Verlag GmbH Germany, part of Springer Nature 2018.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Personalized Mental Health Assistance: Integrating Emotion Prediction with GPT-Based Chatbot

Personalized Mental Health Assistance: Integrating Emotion P...

引用

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

作者： Kifayathullah, Muhammad Sekar, Rajeev Abinaya, R. Vijayaprabakaran, K. Vellore Institute of Technology School of Computer Science and Engineering Chennai India

ISBN: (纸本)9798331529833

Mental health is a fundamental aspect of overall wellbeing, despite its importance, it remains one of the most neglected issues. By integrating Artificial Intelligence with Natural Language Processing into this domain helps to bridge the gaps and challenges. The proposed methodology provides easier access to mental health support by integrating emotion prediction, using the Bi-LSTM Model, with GPT-based chatbots. This system is designed to analyse user inputs, estimating the likelihood of various emotional states such as Anxiety, Depression, Stress, and Suicidal thoughts. These emotional probabilities are then used to inform and guide the responses generated by the GPT model, ensuring that the interactions are more relevant and supportive. Additionally, our approach focuses on providing personalized mental health care using sentiment analysis and prompt engineering. By understanding and interpreting users' emotional states, the chatbot can dynamically adjust its interactions to better meet the needs of everyone, thus improving the quality of mental health support. © 2025 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Exploring the Microcosm: A Comprehensive Survey of Micro Sensor Applications Across Multidisciplinary Research

Exploring the Microcosm: A Comprehensive Survey of Micro ...

引用

International Conference on Power engineering and Intelligent Systems, PEIS 2024

作者： Nandhini, R. Radha, R. School of Computer Science and Engineering Vellore Institute of Technology Chennai India

ISBN: (纸本)9789819767090

The main aim of this survey is to provide wider insight about the use of MEMS (Micro-Electro-Mechanical-System) technology in various interdisciplinary fields. The areas include IoT (Internet-Of-Things) for smart automations, agricultural field for performing precision farming. Automotive sector to predict failures, environmental aspects to detect factors affecting ecosystem, food control to measure the quality. Healthcare for identifying the disease in prior stages, robotics to carry out multiple operations. Machine Learning algorithms play vital role in classifying and extracting the necessary feature from the raw data. Deep Learning techniques like ANN (Artificial Neural Network) is employed for estimation of optimal input and output parameters. CNN (Convolutional Neural Network) for representing the designed structure in binary pixelated image form. The various types of sensors, energy harvesters, transducers and actuators which are designed using MEMS technology and their predominant role in recent advancements has been discussed in brief. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Automotive industry

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

EAMR-Net: A multiscale effective spatial and cross-channel attention network for retinal vessel segmentation

引用

Mathematical Biosciences and engineering 2024年第3期21卷 4742-4761页

作者： Prethija, G. Katiravan, Jeevaa School of Computer Science and Engineering Vellore Institute of Technology Chennai600127 India Department of Information Technology Velammal Engineering College Chennai600066 India

Delineation of retinal vessels in fundus images is essential for detecting a range of eye disorders. An automated technique for vessel segmentation can assist clinicians and enhance the efficiency of the diagnostic process. Traditional methods fail to extract multiscale information, discard unnecessary information, and delineate thin vessels. In this paper, a novel residual U-Net architecture that incorporates multi-scale feature learning and effective attention is proposed to delineate the retinal vessels precisely. Since drop block regularization performs better than drop out in preventing overfitting, drop block was used in this study. A multi-scale feature learning module was added instead of a skip connection to learn multi-scale features. A novel effective attention block was proposed and integrated with the decoder block to obtain precise spatial and channel information. Experimental findings indicated that the proposed model exhibited outstanding performance in retinal vessel delineation. The sensitivities achieved for DRIVE, STARE, and CHASE_DB datasets were 0.8293, 0.8151 and 0.8084, respectively. © 2024the Author(s).

关键词： Drops

来源：评论

学校读者我要写书评

暂无评论

Crop Recommendation and Irrigation System Using Machine Learning with Integrated IoT Devices 1

引用

8th International Conference on Data Management, Analytics and Innovation, ICDMAI 2024

作者： Khan, Mohammad Umair Dangi, Nikhil Kumar, Ankit Saproo, Vishwas Agrawal, Harsh Gaffar, H. Abdul School of Computer Science and Engineering Vellore Institute of Technology Vellore India School of Information Technology and Engineering Vellore Institute of Technology Tamil Nadu Vellore632014 India

ISBN: (数字)9789819732425

ISBN: (纸本)9789819732418

In agriculture, timely and efficient irrigation is crucial to achieving maximum crop yield. However, traditional irrigation methods are often inefficient and wasteful, leading to water scarcity and abbreviated crop productivity. To solve these problems, we suggest an intelligent irrigation system that combines IoT devices and machine learning techniques to suggest the best crop for a particular area and deliver the best irrigation based on real-time weather data and soil moisture levels. The system accumulates data on soil nutrients, temperature, and sultriness utilizing IoT sensors and uses XGBoost, a popular machine learning algorithm, to recommend the most lucrative crop predicated on historical data. The system additionally incorporates authentic-time weather data from APIs and water level sensors to provide customized irrigation for each crop. Our system aims to improve crop productivity, minimize water waste, and avail farmers to make data-driven decisions to maximize their profits © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Crops

来源：评论

学校读者我要写书评

暂无评论

SmokerBeacon: Hybrid Real-Time Smoking Detection Using Object Detection and Gas Sensor

SmokerBeacon: Hybrid Real-Time Smoking Detection Using Objec...

引用

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

作者： Harshavardhan, S. Upender, Patri Ganesh, N. Giftsy, Sharon Vellore Institute of Technology School of Computer Science and Engineering Chennai India Vellore Institute of Technology School of Electronics Engineering Chennai India

ISBN: (纸本)9798331529833

Enforcing smoking bans in public areas remains a challenge due to limitations in conventional monitoring methods. This paper introduces SmokerBeacon, an innovative system for real-time detection of smoking activities in restricted zones. SmokerBeacon uses gas sensors and advanced image classification - YOLO to identify smoking activities. The system catego-rizes detection scenarios into three types: (i) instances where smoking actions are detected by YOLO without corresponding signals from gas sensors, (ii) cases where YOLO fails to detect smoking actions despite gas sensors detecting smoking-related substances, and (iii) situations where both smoking activities and corroborating signals from gas sensors confirm smoking. Each scenario triggers specific actions to improve enforcement and foster healthier environments. By generating timely alerts and enabling proactive intervention, SmokerBeacon mitigates risks associated with smoking in prohibited areas, leveraging IoT technology. © 2025 IEEE.

关键词： Chemical sensors

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Helmet Detection for In-Vehicle Compliance Monitoring on Low-Cost Edge Devices

Deep Learning-Based Helmet Detection for In-Vehicle Complian...

引用

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

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：