检索结果-内蒙古大学图书馆

1st IEEE International Conference on Computing and Data science, ICCDS 2024

作者： Eapen, Maya Mercy, H. Beulah Jayakumari, R. Lavanya Mala, A. Indumathi, S. Pooja, S. Jerusalem College oif Engineering Dept. of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350365337

The Smart Device Cockpit collects data from IoT enabled household appliances like Air conditioner, refrigerators, microwave ovens, and washing machines. Once transmitted to the Smart Device Cockpit portal, the data undergoes analysis and is then presented in the form of both usage data and error data. This platform facilitates a thorough comprehension of the utilization patterns of these household devices and offers insights into any possible errors or malfunctions that may occur. In essence, the Smart Device Cockpit serves as a powerful tool for homeowners to not only monitor and manage their smart appliances but also to make informed decisions about usage optimization and timely maintenance. © 2024 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Cyberbullying Detection using Deep Learning Algorithms 3

Cyberbullying Detection using Deep Learning Algorithms

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Nirmala Devi, K. Jayanthi, P. Rajasekar, Vani Rathinasamy, Rahul Dhandapani, Pradeep Rasil Risam, F. Dept. of Computer Science Kongu Engineering College Erode India

ISBN: (纸本)9798331527549

Social media's widespread use has made it easier for people to communicate openly, but it has also fuelled the growth of cyberbullying, which has seriously harmed victims' emotional and mental health. The intricacy of human language and the variety of abusive behaviours make it difficult to detect cyberbullying. To solve this problem, numerous studies have used deep learning (DL) and machine learning (ML) algorithms over time. However, deep learning (DL) algorithms have transformed text analysis by automatically extracting features and comprehending contextual dependencies in language, while machine learning (ML) techniques are limited in their ability to handle complex and contextual linguistic patterns. Building upon this framework, this study investigates the use of transformer-based models—more especially, BERT—for the detection of cyberbullying. Out of the proposed models, DistlBERT gives the best accuracy, precision, recall, and F1-score of 98.87%,98.87%, 98.87 and 98.86% respectively. © 2025 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

WebTrek Learner : AI Integrated Cloud Based Learning Platform

WebTrek Learner : AI Integrated Cloud Based Learning Platfor...

引用

2024 IEEE International Conference on Computing, Semiconductor, Mechatronics, Intelligent Systems and Communications, COSMIC 2024

作者： Bhandari, Arjun Harisha, A. Rishav, Kumar Shifana, Mariyam Sameer, Jazil Sahyadri College of Engineering and Management Dept. of Computer Science and Engineering Mangalore India

ISBN: (纸本)9798331517892

In an era defined by the rapid proliferation of digital technology and connectivity, the need for virtual education has never been more critical. This article, referred to hereon as 'WebTrek Learner,' is a forward-thinking initiative aimed at catering quality virtual education through a dynamic and engaging approach of gaming. To further enhance the learning experience, WebTrek Learner incorporates cutting-edge LLM based AI technology to curate internal insights and content based on glossary documents. Cloud based a gaming platform enables lightweight experience to all potential learners. © 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

Earth Pit Monitoring System for Petrol Pumps 5

Earth Pit Monitoring System for Petrol Pumps

引用

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

作者： Guruprasad, Sunitha Nikitha, Amulya Rebello, Glen Noronha, Calisha Madtha, Elena St Joseph Engineering College Dept. of Computer Science & Engineering Mangaluru India

ISBN: (纸本)9798331518097

The oil industry is constantly seeking ways to monitor their facilities and equipment in a systematic way with as little human intervention as possible. Currently, monitoring of earth pits is done manually. The Hindustan Petroleum Corporation Limited (HPCL) Earth Pit Monitoring App is a mobile application that aims to enable HPCL staff to securely log in and monitor their petroleum storage sites and earthing pits. This app will make it easier to monitor all aspects of their operations, including vendors and petrol pump dealers, with timely alerts for any necessary maintenance checks. The research conducted on the modern type of earthing will be beneficial for the petroleum outlets as maintenance time and cost would be reduced due to its durability. Field research at HPCL Petroleum Outlets were conducted to observe the state of earth pits and the method of earthing used. Chemical earthing is a method of grounding electrical equipment by pouring a mixture of bentonite and graphite around a copper or iron rod driven into the ground, creating a low-resistance path for electrical charge to dissipate into the earth. It is used in areas with high soil resistance and where traditional earthing methods are not feasible. Comparison between the GI Earthing used currently, and the Chemical Earthing was drawn by comparing resistance values under different conditions. © 2024 IEEE.

关键词： Gasoline

来源：评论

学校读者我要写书评

暂无评论

Detection and Categorization of Conflict Flows Within SDN Environments using Machine Learning Approach 2

Detection and Categorization of Conflict Flows Within SDN En...

引用

2nd International Conference on Emerging Trends in Information Technology and engineering, ic-ETITE 2024

作者： Kousalya, S. Sundararajan, Kanthimathi Vasudevan, I. Jaichitra Sheela, L. Jaba Thyagarajan, Sarunya Panimalar Engineering College M.E. Computer Science and Engineering Tamil Nadu Chennai India Panimalar Engineering College B.E. Computer Science and Engineering Tamil Nadu Chennai India Panimalar Engineering College Dept of Computer Science and Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350328202

Software-Defined Networking (SDN) is known for its remarkable versatility and adaptability. SDN applications encompass a wide range of network management and control functionalities, including load balancing, access control, and routing. However, SDN can encounter issues stemming from conflicting traffic patterns that may degrade network performance in relation of efficiency and optimization. These conflicts arise when factors such as priority and action settings are adjusted. Furthermore, IP spoofing, commonly employed for anonymity and amplification, frequently leads to widespread distributed denial-of-service (DDoS) attacks. We've established a sufficient condition based on the duration and frequency of DDoS attacks. Notably, our sophisticated attack method generates legitimate traffic within the SIP network using reflection techniques. 'As a result, it has the ability to bypass security measures such as blacklists, IP blocking, rate limiting based on packet counts or session/transaction volumes, and automated systems designed to detect unnatural message generation. These security mechanisms are commonly employed in advanced security setups, but the system or technique in question can effectively avoid detection or restriction when interacting with digital environments.' © 2024 IEEE.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Affordable Navigation Aid: A Smart Walking Stick for the Visually Impaired 6

Affordable Navigation Aid: A Smart Walking Stick for the Vis...

引用

6th IEEE International Conference on Recent Advances in Intelligent Computational Systems, RAICS 2024

作者： Muhammed Suhair, K. Malayil, Shanid Deepak, A.V. Faslu Rahman, T.P. Abdul Kabeer, Marwan Pookatil Mea Engineering College Dept: Computer Science Perinthalmanna India

ISBN: (纸本)9798350381689

An innovative effort to improve mobility and freedom is the Low-Cost Smart Walking Stick, which is intended for those with vision impairments. This inventive walking stick offers an effective navigation solution for a variety of locations by integrating affordable technologies like the ESP8266, ultrasonic sensor, buzzer, and vibrator. Users are greatly enhanced by being instantly notified about barriers, changes in topography, and potential risks through real-time notifications and haptic feedback. With the help of this affordable smart walking stick, people who are blind or visually impaired can now confidently and independently traverse their daily lives. It is a major technological advancement. © 2024 IEEE.

关键词： Ultrasonic sensors

来源：评论

学校读者我要写书评

暂无评论

Compact Raspberry PI Server with Integrated UPS 5

Compact Raspberry PI Server with Integrated UPS

引用

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

作者： Hemachandran, A. Nithyabharathi, S. IFET College of Engineering Dept. Computer Science Engineering Tamilnadu Villupuram India

ISBN: (纸本)9798331530013

This paper designs and implements a compact server system based on the Raspberry Pi 4B and tailored to specific low-end and budget-constrained environments, such as home offices and small businesses, through the integration of an uninterruptible power supply (UPS) in the system to ensure continuous operation during periods of power failure. Important features include VPN for secure remote access, an ad blocker to increase the efficiency of browsing, a private NAS system with data management in a secured and easily accessible manner, and video streaming capabilities to meet multimedia requirements. Real-time performance monitoring comes through with an OLED display. The paper reflects an integrated approach combining hardware and software components which stress system flexibility, low costs, and reliability. This compact server system allows an efficient, user-friendly, and flexible server infrastructure at small scale by providing a cost-effective alternative to traditional server solutions. © 2024 IEEE.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Transfer Learning based Deep Learning Model for the Identification of Facial Expression 3

Transfer Learning based Deep Learning Model for the Identifi...

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Ekambaram, Gothai Rakkiannan, Thamilselvan Natesan, P. Jayakkavin, E. Dept of Computer Technology Kongu Engineering College Tamilnadu Perundurai India Dept Computer Science and Engineering Kongu Engineering College Tamilnadu Perundurai India Dept of Artificial Intelligence Kongu Engineering College Tamilnadu Perundurai India Kongu Engineering College Tamilnadu Perundurai India

ISBN: (纸本)9798331527549

The changes that occur on a person's face to communicate their internal emotional states, intentions, or social cues are known as facial expressions. The human face is a crucial tool for communicating with other sand determining their emotional states from their facial expressions. Because it is essential in human interaction, real-time facial expression analysis has become a research topic. Face reading is used in various areas, such as social interaction, emotional intelligence, computer vision, biometric security, and social intelligence. This work focuses on an overview of the various facial expression recognition methods and their advantages and disadvantages. The body's natural response to internal and external stimuli is emotional. Whether it's a common emotion, stress, anger, etc., it can cause serious harm to health. Both psychological and physiological manifestations of these responses emotions and facial expressions appear. The model is used to analyse real-time snapshots of the user's face and detect the existence of stressful information as well as convolutional neural network capable of recognizing emotions, and facial emotions, a proof of concept for the emotion detector was developed. The classification model was developed via transfer learning and fine-tuning. For deep learning process, two classifier designs were taken into account. Following a numberoftests, it was shown that a classifier built using a Separable Conv2D convolutional layer and LeakyReLU as activation method CNN performed the best in categorising emotions. The results are encouraging, and the proposed emotion detection system is minimallyintrusive as it only needs a webcam to monitor the user's facial expressions. © 2025 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Disaster Management Based on Biodiversity Conservation Using Remote Sensing Data Analysis Using Machine Learning Model

引用

Remote Sensing in Earth Systems sciences 2025年第1期8卷 191-199页

作者： Pokkuluri, Kiran Sree Mounika, Talla Devi, N. Durga Kishore, D. Ratna Balakiruthiga, B. Krishna, B. Murali Department of Computer Science and Engineering Shri Vishnu Engineering College for Women Telangana Bhimavaram India Department of CSE-DS Mallareddy College of Engineering Hyderabad India Department of Computer Science and Engineering Aditya University Andhra Pradesh Surampalem India Dept of Information Technology Lakireddy Balireddy College of Engineering Mylavram Vijayawada India Department of Networking and Communications College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur India Department of Computer Science and Engineering MLR Institute of Technology Hyderabad India

Artificial intelligence (AI) applications in forestry as well as wildlife domains have become more feasible due to the advancements in data science and digital and satellite technologies. However, there is a serious global threat to biodiversity due to the rapid expansion of urban, agricultural, and development initiatives. Therefore, the effective monitoring, management, and preservation of biodiversity as well as forest resources may be facilitated by integration of cutting-edge methods like AI in disciplines of forests as well as biodiversity. This study suggests a novel approach to disaster management based on biodiversity protection that makes use of machine learning models and remote sensing image analysis. In this case, the data for disaster management has been gathered and processed for normalisation and smoothing. The processed image features have been segmented using active contour Gaussian Q- histogram equalisation model and feature extracted using probabilistic Bayesian fuzzy transfer NN. Experimental analysis is carried out based on parameters like random accuracy, average precision, sensitivity, AUC, and normalized co-efficient. The proposed technique attained average precision was 95%, sensitivity was 97%, random accuracy was 98%, and normalized coefficient was 94%, AUC of 96%. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2025.

关键词： Biodiversity conservation Disaster management Machine learning model Q- histogram equalisation Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Optimizing Job Search: A Multi-Model Approach with DRNN-BES, Collaborative Filtering, and LLM-NER Resume Analysis 3

Optimizing Job Search: A Multi-Model Approach with DRNN-BES,...

引用

3rd IEEE International Conference on Blockchain and Distributed Systems Security, ICBDS 2024

作者： Jayakumar, Naveenkumar Patil, Netra Pokal, Roshankumar S. Dev, Rudra Pratap Nair, Sidharth Vellore Institute of Technology School of Computer Science and Engineering Vellore India College of Engineering Dept. of Computer Engineering Pune India

ISBN: (纸本)9798350354348

This research introduces an innovative job recommendation platform designed to optimize the job search process through advanced technology integration. The platform features a sophisticated Resume Analyzer leveraging NLP and ML to meticulously extract candidate information. Coupled with a Recommendation System that employs mixture models such as DRNN-BES and collaborative filtering, it delivers personalized job suggestions tailored to individual profiles. Additionally, the system utilizes state-of-the-art web scraping technologies to continuously update its database with diverse and current job listings from various online sources, ensuring a wide range of opportunities are accessible. This integration of technologies not only refines job-matching precision but also significantly improves the efficiency of connecting job seekers with appropriate opportunities. Initial experimental results underscore the enhanced effectiveness and accuracy of our recommendation system, particularly when incorporating user behavioral data into the collaborative filtering algorithm. This paper demonstrates the transformative potential of integrating AI into job seeking, offering a scalable, unbiased, and time-efficient approach to modern employment challenges. © 2024 IEEE.

关键词： Collaborative filtering

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：