检索结果-内蒙古大学图书馆

Global Conference for Advancement in Technology (GCAT)

作者： Poluri Manaswini Sajjad Shaik Shinu M Rajagopal Dept. of Computer Science Engineering Amrita School of Computing Bengaluru Amrita Vishwa Vidyapeetham India

ISBN: (数字)9798350376685

ISBN: (纸本)9798350376692

The integration of cloud and edge computing has the potential to transform how academic resources are accessed and managed. This study focuses on the development of a mobile application that enhances the accessibility of university publications by utilizing both cloud storage and edge computing, ensuring real-time data processing and minimal latency. The methodology includes data scraping from the university website, database creation, and the implementation of a search algorithm using the Flask framework. The results demonstrate significant improvements in the efficiency and accessibility of academic resources, highlighting the practical benefits of combining cloud and edge computing in educational settings.

关键词： Cloud computing Databases Transforms Data processing Real-time systems User experience Mobile applications Resource management Time factors Edge computing

来源：评论

学校读者我要写书评

暂无评论

Cyberbullying Detection on Multiclass Data Using Machine Learning and A Hybrid CNN-BiLSTM Architecture

Cyberbullying Detection on Multiclass Data Using Machine Lea...

引用

Knowledge engineering and Communication Systems (ICKECS), International Conference on

作者： Peddi Gowtham Balaji Priyanka Prakash Katariya S Sruthi Manju Venugopalan Dept. of Computer Science and Engineering Amrita School of Computing Bengaluru Amrita Vishwa Vidyapeetham India

ISBN: (数字)9798350359688

ISBN: (纸本)9798350359695

Cyberbullying has emerged as a significantly concerning online societal issue in the past few years with the proliferation of social media platforms. To address and overcome this pressing communal concern and successfully detect cyberbullying across various categories, this study proposes a novel approach that integrates Convolutional Neural Networks and Bidirectional Long Short-Term Memory Networks, alongside six traditional machine learning techniques, driven by the purpose of enhancing the accuracy and robustness of cyberbullying detection across diverse cultural and textual landscapes. To highlight the multiclass aspect, the model is trained and tested on a dataset containing instances categorized into Age, Religion, Ethnicity, Gender, Other Cyberbullying, and Not Cyberbullying. Through rigorous experimentation, the proposed deep learning model’s proficiency results in a 0.83 accuracy and F measure, showcasing its efficacy in capturing the nuances of various categories. Meanwhile, among the six machine learning models employed, Random Forest emerges as the top performer with values 0.94 and 0.93 for the accuracy and F measure respectively. This comprehensive methodology underscores its ability to effectively discern between the different classes and offers a promising solution to combat cyberbullying across diverse demographics and thematic dimensions.

关键词： Knowledge engineering Deep learning Accuracy Cyberbullying Pressing Robustness Cultural differences

来源：评论

学校读者我要写书评

暂无评论

RLAD: Reinforcement Learning based Anomaly Detection system for IoT devices in smart homes

RLAD: Reinforcement Learning based Anomaly Detection system ...

引用

International Conference on computing and Networking Technology (ICCNT)

作者： Angela Raj Chadha Kethamreddy Karthikeya Reddy S Sountharrajan Dept. of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

In the era of the Internet of Things (IoT), smart homes have become a cornerstone of modern living, offering convenience, energy efficiency, and security. The extensive connectivity within these networks brings forth security challenges, making the detection of anomalies a critical aspect of IoT network security. Anomalies encompass a wide array of unexpected events, from irregular data patterns to communication anomalies, power fluctuations, behavioral deviations, security breaches, and environmental variations. This paper underscores the pivotal role of anomaly detection in securing IoT networks, highlighting its significance in identifying both known threats and emerging risks. Anomaly detection in IoT relies on machine learning and statistical techniques, encompassing data collection, preprocessing, feature extraction, model training, real-time anomaly detection, and responsive actions. Reinforcement Learning(RL), a subset of machine learning, emerges as a formidable tool in enhancing IoT network security. RL models continuously observe and adapt to device behavior, identifying anomalies and security breaches in real-time. RL offers adaptability in rapidly changing IoT environments, proactive responses to anomalies, and the ability to learn and evolve against new threats. RL strengthens network security without compromising individual device data. Our advanced security system that refines its understanding of the smart home environment, collectively learns from anomalies, and bolsters network security. Synergy of IoT and RL is reshaping IoT network security, promising not only seamless device functionality but also the safeguarding of sensitive data and personal spaces.

关键词： Training Adaptation models Accuracy Smart homes Reinforcement learning Network security Real-time systems Internet of Things Anomaly detection Streams

来源：评论

学校读者我要写书评

暂无评论

AI-Enhanced Real-Time Accident Detection with Smart Emergency Response System

AI-Enhanced Real-Time Accident Detection with Smart Emergenc...

引用

Intelligent Signal Processing and Effective Communication Technologies (INSPECT), IEEE International Conference on

作者： Bharathi Mohan G Pranav Reddy Sanikommu Gudi Vishnu Teja Dept. of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai India

ISBN: (数字)9798350379525

ISBN: (纸本)9798350379532

Accidental deaths remain a significant threaten the lives of people worldwide, and recurrently cause severe injuries due to slow reportage and response. The existing methods employed to detect accidental occurrences rely on written reports or structured systems that are usually less reliable, thus slow reporting and high, false alarms rates. This paper proposes a real-time and automated accident detection system which aims at enhancing the identification process by using the deep learning YOLOv5 and YOLOv8. Using the object detection and vehicle tracking, the system can calculate the speed of vehicles and detect collision events, as well as bounding box movements with IoU (Intersection over Union) that let the system track constant collisions past defined thresholds. Contrary to traditional systems, this approach significantly reduces false positive while at the same time increasing detection accuracy. When an accident is found, the system uses geographic results from OpenStreetMap and the Haversine formula to notify the closest emergency services which include hospitals and police stations. Describing its use in real traffic proves that this scalable approach enhances both detection and response time rates. This research makes small advancements towards smarter transportation systems by improving the detection and timely alerting, thereby reducing accident death tolls by quicker responses.

关键词： YOLO Tracking Law enforcement Transportation Signal processing Emergency services Real-time systems Time factors Reliability Accidents

来源：评论

学校读者我要写书评

暂无评论

Implementing Internet Key Exchange with Image-based Key Exchange through Socket Programming

Implementing Internet Key Exchange with Image-based Key Exch...

引用

International Conference for Convergence of Technology (I2CT)

作者： M SreeDeepika N Sri Lekhya Likesh K Shinu M Rajagopal Dept. of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (数字)9798350394474

ISBN: (纸本)9798350394481

The primary objective of our project is to execute the Internet Key Exchange (IKE) protocol, which is commonly utilized for secure key exchange in virtual private networks (VPNs) and other secure connections. Our project is divided into two parts: a server and a client, both of which are written in Python and use socket programming. In order to receive an encrypted symmetric key, the server first creates anRivest, Shamir, Adleman (RSA) key pair, then delivers the client its public key. The symmetric key is contained into an image file and encrypted with the server’s public key. A symmetric key is created on the client side, encrypted using the public key of the server, and hidden inside an image. After then, the server receives this encrypted key image. After the server gets the picture, it uses the decrypted symmetric key to decode another picture, which concludes the key exchange procedure. This creative strategy not only makes use of IKE’s advantages but also investigates a novel technique for key exchange using picture hiding.

关键词： Protocols Sockets Public key Programming Internet Virtual private networks Encryption

来源：评论

学校读者我要写书评

暂无评论

Intent Recognition Leveraging XLM-RoBERTa for Effective NLU

Intent Recognition Leveraging XLM-RoBERTa for Effective NLU

引用

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

作者： K Krishna Jayanth G Bharathi Mohan R Prasanna Kumar M Rithani Department of Computer Science and Engineering (AIE) Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai India

ISBN: (数字)9798350375190

ISBN: (纸本)9798350375206

Natural Language Processing (NLP) systems are vital for precisely interpreting user intentions in order to guarantee efficient communication between people and computers. Intent recognition is a crucial component of natural language processing (NLP), and the XLM-RoBERTa (Cross-lingual Multimodel-Robust Optimized Bidirectional Representation of Transformer Encoder) model is tested in this work by using the ATIS dataset. Findings show that by spotting subtle patterns in the dataset and making use of contextual information, the model improves intent detection with an amazing 98.57% accuracy and efficiency. Together with examining the effects of language variety and dataset size on model performance, the study offers insights into anticipating interpretability and typical problems with intent identification. The study’s practical importance is shown by the creation of a web application designed for real-world situations. The study’s overall findings demonstrate how flexible sophisticated natural language processing (NLP) models, such as XLM-RoBERTa, can be to provide insightful information on intent recognition, enhancing user experiences and propelling NLP research. In order to maximize human-computer communication efficiency and promote innovation in the industry, it emphasizes the significance of incorporating cutting-edge NLP approaches into useful applications.

关键词： Training Industries Technological innovation Accuracy Intent recognition Computational modeling Propulsion

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient and Reliable Federated Learning in Heterogeneous Mobile-Edge computing 19

Energy-Efficient and Reliable Federated Learning in Heteroge...

引用

2022 IEEE SmartWorld, 19th IEEE International Conference on Ubiquitous Intelligence and computing, 2022 IEEE International Conference on Autonomous and Trusted Vehicles Conference, 22nd IEEE International Conference on Scalable computing and Communications, 2022 IEEE International Conference on Digital Twin, 8th IEEE International Conference on Privacy computing and 2022 IEEE International Conference on Metaverse, SmartWorld/UIC/ATC/ScalCom/DigitalTwin/PriComp/Metaverse 2022

作者： Xu, Yan Li, Liying Cong, Peijin Zhou, Junlong Nanjing University of Science and Technology School of Computer Science and Engineering China Institute of Computing Technology Chinese Academy of Sciences State Key Laboratory of Computer Architecture China

ISBN: (纸本)9798350346558

As a decentralized machine learning paradigm, Federated Learning (FL) is an emerging technique to protect user data privacy in Mobile Edge computing (MEC). FL adopts the idea of distributed privacy computing, enabling the terminal devices to train machine learning models required by servers locally and upload model parameters to servers for aggregation. However, in the process of coupling FL with MEC systems, device heterogeneity, malicious use of poisoned data by users and limited system resources will seriously affect FL training accuracy, system reliability and energy efficiency. In this paper, a highly reliable and energy-efficient FL scheme is designed to solve these issues. Specifically, we first propose a calculation method for estimating the reliability of heterogeneous devices. Then, we design a highly reliable device selection scheme based on devices' reliability, computing power, and participation times. Finally, we utilize the slack time in FL training to dynamically adjust the voltage and frequency of devices for reducing the energy consumption of training. Experimental results show that our proposed scheme improves the accuracy by up to 36.45% on average and saves energy by up to 48.63% when compared to the baseline and benchmarking methods. © 2022 IEEE.

关键词： Reliability

来源：评论

学校读者我要写书评

暂无评论

Development of a Comprehensive Learning Management System using Full Stack Technology: A Modern Approach to Educational Platforms

Development of a Comprehensive Learning Management System us...

引用

Data Intelligence and Cognitive Informatics (ICDICI), International Conference on

作者： Supriya M Keshav Rathinavel Divya Radhakrishnan Dept. of Computer Science and Engineering Amrita School of Computing Bengaluru Amrita Vishwa Vidyapeetham India

ISBN: (数字)9798350389609

ISBN: (纸本)9798350389616

Using the advantages of modern web technologies, this project utilizes powerful data modelling characteristics of Prisma and dynamic front-end capacities of *** to design a Learning Management System (LMS). The aim of this project is to create a comprehensive platform that would effectively facilitate the organization of educational resources and assignments, as well as student cooperation, ensuring scalability and performance at the same time. Many software engineering practices are utilized during this project for code maintainability, security, and performance. The full cycle of software development consists of testing and iterative adaptation of the developed systems based on the opinions of end-users. Ultimately, the LMS is improved through thorough testing and feedback from the users in an iterative and progressive process. The findings of this research are pertinent to the future developments of educational technology that will seek to implement modern, full-featured, and user-friendly LMS.

关键词： Learning management systems System dynamics Scalability Organizations Iterative methods Security Reliability Testing Software development management Immersive learning

来源：评论

学校读者我要写书评

暂无评论

Classification of News Category Using Contextual Features

Classification of News Category Using Contextual Features

引用

Knowledge engineering and Communication Systems (ICKECS), International Conference on

作者： M Jahnavi K Chandana Priyanka C Nair K Dheeraj Dept. of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (数字)9798350359688

ISBN: (纸本)9798350359695

This study focuses on the crucial task of news category classification using a dataset consisting of 175,995 instances spanning across 30 distinct categories. The system utilizes a preprocessing pipeline to collect intricate linguistic features. Pre-trained word embeddings such as GloVe, FastText and Word2Vec are utilized to gather semantic information. The dataset is balanced using SMOTE analysis, and semantic information is gathered using pre-trained word embeddings. The study investigates various machine learning algorithms such as K-Nearest Neighbors, Random Forest, XGBoost, Decision Tree, Logistic Regression, Gaussian Naive Bayes, and AdaBoost. The primary emphasis lies in attaining exceptional precision, F1 score, and comprehending the interpretability of the models’ predictions. The study also highlights the need of model interpretability, utilizing LIME. The framework for real-world news classification employs a variety of embeddings, with KNN standing out as particularly effective. It improves precision and efficiency, especially when combined with Word2Vec embeddings, demonstrating machine learning’s potential in a wide range of news categories.

关键词： Logistic regression Accuracy Machine learning algorithms Semantics Pipelines Nearest neighbor methods Predictive models

来源：评论

学校读者我要写书评

暂无评论

Designing of VehiNet Using Convolutional Neural Networks and Deep Learning Techniques

引用

Procedia computer Science 2024年 235卷 1409-1418页

作者： Mahita Kandala Kaushik M Vaishakh Nambiar Vignesh G S Jyotsna C. Tripty Singh Prakash Duraisamy Department of Computer Science and Engineering Amrita School of Computing Bengaluru Amrita Vishwa Vidyapeetam India University of Wisconsin Green Bay Wisconsin USA

Traffic congestion has become a critical issue in metropolitan areas, inflicting significant hardships on individuals on a daily basis. This adverse situation poses multifaceted challenges, including increased air pollution, heightened fuel consumption, and compromised road safety. Deep learning algorithms, encompassing both Convolutional Neural Networks (CNN), and Recurrent Neural Networks (RNN) have showcased remarkable performance in areas such as computer vision, natural language processing, healthcare, finance, and autonomous systems. This research paper proposes a novel methodology to develop a vehicle detection model - VehiNet, which can subsequently be refined to create an automated traffic signal system. The study explores the effectiveness of various CNN, RNN, and deep learning algorithms and techniques in accomplishing this objective. The dataset picked for the study in addition to being compiled from internet resources, was also painstakingly assembled manually using a variety of methods to collect over 2000 photographs from various angles, lighting conditions, and locations within Bengaluru city. The main motive is to apply CNN, RNN, and other Deep Learning classification techniques for object detection and classification of Indian vehicles and see how well these deep learning algorithms and techniques affect prediction efficiency. This research stands out from others and makes its novelty clear thanks to the carefully collected dataset and the detailed analysis of the methodologies.

关键词： Traffic Congestion Vehicle Detection Convolutional Neural Network Recurrent Neural Network Deep Learning Classification

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：