检索结果-内蒙古大学图书馆

9th International Conference on Advanced Computing and Communication Systems, ICACCS 2023

作者： Avupati, Sai Likhitha Harshitha, Abbineni Jeedigunta, Sai Pranavi Sai Chikitha Chowdary, Dirisala Pushpa, B. Gokaraju Rangaraju Institute of Engineering and Technology Computer Science and Engineering Hyderabad India

ISBN: (纸本)9798350397376

Traffic rules are often neglected by people and are taken for granted which results in road accidents and can sometimes end up taking the lives of people or can make them handicapped. Therefore, traffic rules have been introduced for the efficient movement of vehicles, to prevent accidents, and for pedestrian safety. They also help in reducing traffic congestion and decrease the duration of traveling, making transport efficient. With the increase in the number of vehicles moving on roads, it is important to follow the traffic rules to avoid unwanted consequences. But most people tend to violate traffic rules. To enforce the traffic rules at all times, there should be an efficient monitoring system. Thus, in order to identify traffic rule violations accurately, we put forward a project that identifies these violations in real time. In this system, we deal with detecting multiple traffic violations like triple riding, not wearing a helmet, over-speeding, and using a phone while driving with the help of You Only Look Once (YOLOv5) and Haar Cascade. This would be helpful for the traffic police to monitor roads more precisely and take the necessary action against the drivers who violate the traffic rules effectively. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Advances in AI-based genomic data analysis for cancer survival prediction

引用

Multimedia Tools and Applications 2025年第14期84卷 14139-14166页

作者： Deepali Goel, Neelam Padmavati Khandnor University Institute of Engineering and Technology Panjab University Chandigarh160014 India Chandigarh160012 India Department of Computer Science Guru Nanak College Budhlada151502 India

Problem: Cancer is one of the deadliest diseases prevalent in the world. Survivability, early diagnosis, and accurate prognosis are of utmost importance for the therapeutics and clinical management of cancer patients. To achieve accurate and timely prediction of the survival of cancer patients, several machine-learning models based on genomic data have been proposed but a comprehensive review of recent applications in cancer survival prediction is lacking. This paper represents a review of the most recent application of machine learning and deep learning on cancer survival prediction, with a particular focus on the use of genomic data. It specifically targets the most prominent cancer types such as breast cancer, glioblastoma, lung cancer, renal cell cancer, and oral cancer. Methods: A systematic review approach is employed to analyze recent studies on machine learning techniques applied to cancer survival prediction. Emphasis is placed on methodologies utilizing genomic data due to its effectiveness in predicting survival outcomes. Results: This review highlights the efficacy of different machine/deep learning-based techniques in predicting survival outcomes for different cancer types with genomic data. It also provides a summary of the contributions made by different research groups, critically examines the associated challenges, and suggests potential areas for further investigation. Conclusion: Machine learning and deep learning techniques, especially those utilizing genomic data, hold significant promise for accurate cancer survival prediction across diverse cancer types. Despite advancements, challenges such as data heterogeneity and model interpretability still persist. Further research is warranted to address these challenges and develop a comprehensive framework for cancer survival prediction applicable to various cancer types. This review lays the foundation for future investigations in the area of cancer research. © The Author(s), under exclusive licence

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Human-Centered Coordination for Robot-Assisted Equipment Transport

引用

ASME Letters in Dynamic Systems and Control 2025年第2期5卷 021002页

作者： Fernandez, Joshua Cosby, Austin Mazumdar, Anirban Department of Mechanical Engineering Georgia Institute of Technology AtlantaGA30363 United States Department of Computer Science Mississippi State University MS39762 United States

This work explores how to use an unmanned ground vehicle (UGV) to offload the physical burdens of equipment from humans. This work formulates dynamic alignment following and compares it to position-based following techniques. We describe the control strategies of both following methods and implement them in a dynamic simulation and a physical prototype. We test the performance of the two following methods and show that dynamic alignment following can reduce robot positional error and interaction force between the human and the robot. We then analyze the energetics and the performance of the human-UGV team for candidate transportation tasks. The presence of the robot can make some tasks take longer to perform. Nonetheless, the results show that for the candidate tasks, the robot can reduce human average metabolic power and average overall task energy. © 2024 by ASME.

关键词： Ground vehicles

来源：评论

学校读者我要写书评

暂无评论

Intelligent Street Light Management System using Solar Panels 3

Intelligent Street Light Management System using Solar Panel...

引用

3rd IEEE Delhi Section Flagship Conference, DELCON 2024

作者： Venkatraman, Akila Ruchitha, Arutla Sellamuthu, Suseela Shalini, Dappu Reddy, Pulsani Dinesh Gokaraju Rangaraju Institute of Engineering and Technology Department of Information Technology Hyderabad India Vellore Institute of Technology Department of Computer Science & Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798331518592

The conventional street lighting system is used during night time. It consumes more amount of power and there is major energy demand arises. The energy saving methods and lighting control arises to overcome the problem. The smart street light project aims to improve the energy efficiency and urban safety by using sensor- equipped street lights. It can adjust their brightness automatically based on levels of ambient light and the presence of vehicles and pedestrians. Additionally, the project incorporates the central management system implemented by using the ESP 32 module and BLYNK cloud, that allows for remote monitoring and control of street lights. The implementation of this technology can lead to significant cost saving, improves security for the cities and rise the overall quality of life for residents. Vehicle detection system is implemented to control the street lights when vehicle is detected. LED's (Light Emitting Diode) doesn't consume large amount of electricity. By the combination of both LED's and LDR's (Light Dependent Resistor) the intensity of light can be controlled and save more electricity. To make a step towards green energy, solar panels are used to power the street lights. The increased standard of living and growth of cities lead to the complex lighting system with automatic and intelligent control schemes. © 2024 IEEE.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

NetProbe: Deep Learning-Driven DDoS Detection with a Two-Tiered Mitigation Strategy 25

NetProbe: Deep Learning-Driven DDoS Detection with a Two-Tie...

引用

26th International Conference on Distributed Computing and Networking, ICDCN 2025

作者： Jha, Prianshu Singh, Gurpreet Kumar, Amit Agrawal, Dewesh Patel, Yashwant Singh Forough, Javad Department of Computer Science and Engineering Thapar Institute of Engineering and Technology Punjab Patiala India Department of Computing Science Umea University Umeå Sweden

ISBN: (纸本)9798400710629

Web servers are the backbone of modern Internet infrastructure, serving as the primary medium for online information distribution. Despite their critical role, web servers are susceptible to cyber-attacks. While current firewall mechanisms provide some level of protection against cyber threats, the evolving nature of these attacks and emerging vulnerabilities continue to pose significant risks. One of the most prevalent yet lethal attacks known today is DDoS (Distributed Denial of Service) attacks. These growing risks emphasize the urgent need for dynamic and robust threat detection and mitigation systems. This paper presents a comparative analysis of ensemble learning models (e.g., Random Forest, XGBoost, and LightGBM) and neural network-based models (e.g., Graph Neural Networks (GNN), Long Short-Term Memory networks (LSTM) with attention layers, and Gated Recurrent Units (GRU)) for DDoS attack detection and classification. Based on this analysis, we propose a real-time DDoS attack detection system integrated with a mitigation mechanism. The proposed system utilizes a two-tiered mitigation strategy assisted by UFW (Uncomplicated Firewall) and Apache server configuration files to block the incoming and outgoing traffic associated with suspicious IP addresses. The system's overall complexity, integrating both detection and response processes, ensures its efficiency in real-time environments while handling large volumes of traffic. Furthermore, the proposed approach achieves 15% improvement in detection accuracy and 20% reduction in false positives compared to traditional techniques, making it an effective and scalable solution for modern web server security. © 2025 Copyright held by the owner/author(s).

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Deep Learning Approach for Early Detection of Diabetic Retinopathy 3

A Hybrid Deep Learning Approach for Early Detection of Diabe...

引用

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

作者： Mary Vespa, M. Shajeena, J. Shiny, R.M. Gayathri Devi, K. Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Chennai India Srm Institute of Science and Technology Department of Computer Science and Engineering Tiruchirapalli Campus India St Joseph's College of Engineering Department of Computer Science and Engineering Chennai India Rmd Engineering College Department of Artificial Intelligence and Machine Learning Chennai India

ISBN: (数字)9798331509675

ISBN: (纸本)9798331509675

Diabetes is a malnutrition that results from elevated glucose levels. Diabetes eventually results in diabetic retinopathy (DR), a retinal condition that significantly impairs vision. It is an insulin-dependent difficulty that impacts ocular health. The receptive to cells at the back of the individual retina's veins gets injured, which is the cause of it. A favorable prognosis for this condition depends on its early identification. In this paper, the application of Convolutional Neural Network (CNN) with Long Short Term Memory (LSTM) on color fundus images is used for diabetic retinopathy is applied for understanding the task. The goal of the proposed DR identification method is to use deep learning to automatically identify the problem. An hybrid model that was trained and tested to distinguish between healthy and DR-affected fundi was able to achieve an accuracy of roughly 99.07% using fundus images from diabetic patients that were available in MESSIDOR. © 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

Network Optimization of Large-Scale CNNs for Applications in Autonomous Machines 2

Network Optimization of Large-Scale CNNs for Applications in...

引用

2nd International Conference for Innovation in technology, INOCON 2023

作者： Kambhampaty, Harish Rohan Battula, Naga Datha Saikiran Rentala, Salwesh Challa, Sai Charan Anuradha, K. Gokaraju Rangaraju Institute of Engineering and Technology Computer Science & Engineering Hyderabad India

ISBN: (纸本)9798350320923

In the age of automation, a growing number of devices require high dimensional data to increase the reliability of the machines to better predict and classify objects for autonomous decision-making. 3D object detection directly links to environmental interpretation and therefore builds the base for prediction and movement planning for autonomous systems. With greater computing and storage capacities at the edge level, higher-density data can be captured and analyzed, and hence better predictability of natural environments is achieved. Convolutional Neural Networks are becoming increasingly important for object detection and tracking in many autonomous systems due to the improvement of affordable edge-computing devices capable of working with higher-dimensional data, such as LiDAR sensors, in recent years. Although the capabilities of edge-computing devices are growing, the computational requirements for real-time applications are also rising. This paper proposes two types of optimizations to the networks: pruning and quantization. The proposed optimizations are applied to a base model trained on the KITTI dataset, which shows an average inference speed-up of up to 20% while minimizing the loss of performance. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Startup Success and Failure Prediction Algorithm Using k-Means Clustering and Artificial Neural Network

Startup Success and Failure Prediction Algorithm Using k-Mea...

引用

2023 International Conference on Emerging Trends in Networks and computer Communications, ETNCC 2023

作者： Misra, Ajai Kumar Jat, Dharm Singh Mishra, Durgesh Kumar Namibia University of Science and Technology Computer Science Windhoek Namibia Sri Aurobindo Institute of Technology Computer Science and Engineering Indore India

ISBN: (纸本)9798350314878

Startups or new businesses are the growth indicators of a country. Additionally, growing startups are a good opportunity for investors to get high returns in less time and investment amount. In this context, startup success and failure prediction are essential for investors and business administrators. The manual analysis and tracking of a company's growth is challenging for an investor. Therefore, in this paper, a machine learning model has been presented to accurately predict the project of a start-up's success and failure in terms of 'Operating', 'Acquired', 'Closed', and 'IPO'. In this context, the CrunchBase dataset has been used for experimentation. The proposed model includes a modified k-means clustering algorithm and Artificial Neural Network for predicting the start-up's success and failure. Based on the experimental analysis in different scenarios the optimal prediction accuracy of 89% has been recorded. Therefore the proposed model provides acceptable accurate results. © 2023 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Security Concerns in Cloud and Blockchain Solutions 3

Security Concerns in Cloud and Blockchain Solutions

引用

3rd International Conference on Sentiment Analysis and Deep Learning, ICSADL 2024

作者： Bundela, Rajmani Dhanda, Namrata Verma, Rajat Zainab, Kaneez Amity University Uttar Pradesh Department of Computer Science and Engineering India Pranveer Singh Institute of Technology Department of Computer Science and Engineering Kanpur India Shri Ramswaroop College of Engineering and Management Department of Computer Science and Engineering Lucknow India

ISBN: (纸本)9798350396157

Cloud computing and blockchain technology are the two transformative technologies that have created significantly impact in various industries. Cloud computing has revolutionized the way resources and services are delivered over the internet, enabling scalable and cost-effective solutions. On the other hand, blockchain has introduced a safe and decentralized structure for recording transactions and maintaining trust in digital interactions. This research study explores the synergy between cloud computing and blockchain, focusing on their combined potential to increase efficiency, privacy, and data security. The integration of cloud computing and blockchain offers several advantages as the technology makes use of the immutability and cryptographic capabilities of blockchain to provide secure and tamper-proof storage of sensitive data. Furthermore, the decentralized structure of blockchain guarantees that data is not under the control of a single entity, enhancing data ownership and privacy. Smart contracts, and programmable scripts on the blockchain, may streamline and automate a variety of cloud-related activities, cutting out mediators and improving productivity. © 2024 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Federated Multitask Learning for Complaint Identification Using Graph Attention Network

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第3期5卷 1277-1286页

作者： Singh, Apoorva Chandrasekar, Siddarth Sen, Tanmay Saha, Sriparna Department of Computer Science and Engineering Indian Institute of Technology Patna Patna801106 India Department of Electronics and Communication Engineering Iiitdm Kancheepuram600127 India Ericsson Kolkata700135 India

Prior study on automatically identifying complaints on social media has relied on extensive feature engineering in centralized settings, with no consideration for the decentralized, nonidentically independently distributed (Non-IID), and privacyconscious aspect of complaints, which can hinder data collection, distribution, and learning. In this work, we propose a graph attention network (GAT)-based multitask framework that intends to learn two closely related tasks, complaint detection (primary task) and sentiment classification (auxiliary task), simultaneously in federated learning scenarios. We propose the Federated Combination (FedComb) algorithm, a two-sided adaptive optimization technique that simultaneously optimizes global and local models. The proposed methodology outperforms several baselines for the intended task of recognizing complaints in decentralized settings, according to quantitative and qualitative studies on two benchmark datasets. Impact Statement-Automatic complaint identification is crucial to organizations as they provide insights to meet the customers' requirements, including handling and addressing the complaints. Unlike standard technologies developed using data stored in the cloud, a federated learning model allows businesses to learn complaint detection models without sharing their training data spread on their local databases with third-party cloud services. In this work, we propose a GAT-based sentiment-aided complaint identification in federated learning settings. The proposed FedComb algorithm integrates local and global model optimization, making it efficient compared to existing federated algorithms. © 2022 IEEE.

关键词： Deep learning

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：