检索结果-内蒙古大学图书馆

3rd International Conference on Disruptive Technologies, ICDT 2025

作者： Ranjan, Alok Kumar Singh, Avtar School of Computer Science & Engineering Lovely Professional University Punjab Phagwara India School of Computer Science & Engineering Galgotias University UP India

ISBN: (纸本)9798331519582

DDoS attacks are among of the most dangerous forms of attack these days. They are the reason for many security issues in this era all around the globe, particularly in the landscape of SDN where core SDN controlllers are prone to attacks due to their centralized nature. The primary objective of this work is to further the use of machine learning in SDN systems for DDoS attack detection. We performed this research on five machine learning systems, namely Artificial Neural Networks (ANN), Support Vector Classifier (SVC), Decision Tree (DT), and Gradient Boosting Classifier (GBC) a hybrid SVC+GBC model with the aid of the DataSet Sdn. The dataset encompasses standard and attacked data of traffic, around 80 factors are included such as packet and protocol details. One hot encoding and feature selection were some of the data pre-processing methods that were introduced to enhance the models. The evaluation methods were accuracy, F1 score, recall, and precision. Our SVC+GBC hybrid model surpassed all the standalone algorithms, 99.77% accuracy and an F1 Score of 99.76%. To sum up, the use of detection methods based on machine learning can greatly boost the defense of SDN network to DDoS attacks. © 2025 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

DMFCNN-HBO: deep maxout fusion convolutional neural network model enabled with honey badger optimization for DDoS attack detection

引用

International Journal of Information Technology (Singapore) 2025年第4期17卷 2347-2354页

作者： Rakshe, Dhananjay Shripad Jha, Sweta Bhaladhare, Pawan R. School of Computer Science and Engineering Sandip University Maharashtra Nashik India

In recent years, Distributed Denial of Service (DDoS) attacks have developed one of the greatest communal and disrupting threats to network security. These attacks flood focused systems with traffic, establishment them inaccessible to valid users. The growing intricacy and difficulty of DDoS attacks involve improving strong and adaptable detection methods. Existing DDoS detection systems struggle to discriminate between real and fraudulent network traffic, specifically with high traffic volumes and developing attack approaches. In this study, we proposed a novel Deep Maxout Fusion Convolutional Neural Network (DMFCNN) enabled hybridization model for DDoS attack detection. In this study, we collected the data from the CICIDS2017 dataset for DDoS attack detection. Next, we divide the dataset into training and testing sets. Then, we used a preprocessing methodology, including Min–max normalization. Honey Badger Optimization (HBO) is applied for feature selection. The proposed method is compared to the other traditional algorithms. The overall performance is computed in terms of recall (98.75%), accuracy (95.03%), precision (97.26%), and F1-score (98.03%). These results demonstrate the model’s ability to identify different forms of DDoS attacks with high accuracy, improving network security robustness. © Bharati Vidyapeeth's Institute of computer Applications and Management 2025.

关键词： DDoS attack detection Deep maxout fusion convolutional neural network (DMFCNN) Hybridization model Network security

来源：评论

学校读者我要写书评

暂无评论

Towards Maximizing Semantic Coverage for Image-Text Retrieval

Towards Maximizing Semantic Coverage for Image-Text Retrieva...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Xu, Junhao Liu, Zheng Chen, Zhumin Shen, Fei School of Computer Science and Technology Shandong University China School of Computer Science and Technology Shandong University of Finance and Economics China School of Computer Science and Engineering Nanjing University of Science and Technology China

ISBN: (纸本)9798350368741

To establish semantic associations between images and texts, existing Image-Text Retrieval (ITR) methods primarily focus on fixed-scale fragments, which only identify explicit semantic categories. Consequently, semantic coverage is constrained, leading to the omission of certain semantic associations. To enlarge the semantic coverage, we propose the Semantic Coverage-Aware Network (SCA-Net). First, explicit semantic categories are identified by SCA-Net through analyzing the semantic membership of visual and textual fragments, thereby establishing more precise explicit semantic associations. Second, implicit semantic categories are identified by SCA-Net via adaptively aggregating visual and textual fragments across various scales using a co-occurrence-aware router, thereby significantly expanding the semantic coverage and establishing complete semantic associations. Third, image-text similarity is calculated using the attention mechanism over a broader range of semantic coverage. Extensive experiments demonstrate that SCA-Net significantly enhances ITR performance compared to state-of-the-art methods by maximizing semantic coverage. © 2025 IEEE.

关键词： Co-occurrence-aware router Image-text retrieval Semantic association Semantic category Semantic coverage

来源：评论

学校读者我要写书评

暂无评论

Efficient CNN-Based Bone Fracture Detection in X-Ray Radiographs with MobileNetV2 2

Efficient CNN-Based Bone Fracture Detection in X-Ray Radiogr...

引用

2nd IEEE International Conference on Recent Advances in Information Technology for Sustainable Development, ICRAIS 2024

作者： Varun, V. Natarajan, Suresh Kumar Adithya, M. Nagatejas, P. Mithun Chavan, A. Moorthi Hosahalli, Nethra School of Computer Science and Engineering Ramanagara India

ISBN: (纸本)9798350354461

In this study, a deep learning-based approach for detecting bone fractures in X-ray images, utilizing a MobileNetV2 architecture combined with Convolutional Neural Networks (CNNs). Fractures are a prevalent musculoskeletal injury demanding swift and accurate diagnosis for optimal treatment. Our system leverages the Bone Fracture Dataset to train the model in identifying and classifying fractures across diverse anatomical regions. The integration of MobileNetV2, known for its efficiency in mobile and embedded vision applications, with CNNs, allowed us to achieve significant performance improvements while maintaining computational efficiency. In its best performance, the system achieved a success rate of 94.8% on the practice data it was trained on. When tested on entirely new data, it was still able to identify fractures correctly in 93.5% of the cases, demonstrating its efficacy in accurately detecting bone fractures. This approach not only enhances diagnostic accuracy but also reduces the time and effort required for manual evaluation. By automating the initial detection phase, the system endeavors to minimize diagnostic errors and improve patient outcomes, offering a reliable and rapid assessment tool for healthcare professionals. © 2024 IEEE.

关键词： X ray radiography

来源：评论

学校读者我要写书评

暂无评论

CDTR: Semantic Alignment for Video Moment Retrieval Using Concept Decomposition Transformer 39

CDTR: Semantic Alignment for Video Moment Retrieval Using Co...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Ran, Ran Wei, Jiwei Cai, Xiangyi Guan, Xiang Zou, Jie Yang, Yang Shen, Heng Tao School of Computer Science and Engineering University of Electronic Science and Technology of China China School of Computer Science and Technology Tongji University China

ISBN: (纸本)157735897X

Video Moment Retrieval (VMR) involves locating specific moments within a video based on natural language queries. However, existing VMR methods that employ various strategies for cross-modal alignment still face challenges such as limited understanding of fine-grained semantics, semantic overlap, and sparse constraints. To address these limitations, we propose a novel Concept Decomposition Transformer (CDTR) model for VMR. CDTR introduces a semantic concept decomposition module that disentangles video moments and sentence queries into concept representations, reflecting the relevance between various concepts and capturing fine-grained semantics which is crucial for cross-modal matching. These decomposed concept representations are then used as pseudo-labels, determined as positive or negative samples by adaptive concept-specific thresholds. Subsequently, fine-grained concept alignment is performed in video intra-modal and textual-visual cross-modal, aligning different conceptual components within features, enhancing the model’s ability to distinguish fine-grained semantics, and alleviating issues related to semantic overlap and sparse constraints. Comprehensive experiments demonstrate the effectiveness of the CDTR, outperforming state-of-the-art methods on three widely used datasets: QVHighlights, Charades-STA, and TACoS. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Efficient Approach for VM and Database Segmentation of Cloud Resources Over Cloud Computing

引用

SN computer science 2024年第8期5卷 977页

作者： Manoli, Sunil Metipatil, Prabhuraj Raghavendra Nayaka, P. School of Computer Science and Engineering REVA University Bangalore India

Virtual machine (VM) clusters are used in cloud computing models to safeguard resources from failure and provide redundancy. Tasks for cloud users are planned by choosing appropriate resources to carry out the work within the virtual machine cluster. Issues with pre-configuration, downtime, complicated backup procedures, and disaster management plague the current VM clustering methods. High availability resources with dynamic and on-demand configuration are provided by virtual machine infrastructure. To improve efficiency and availability, the suggested technique supports the VM clustering process, which places and allocates virtual machines (VMs) based on the size of the requested task and the bandwidth level based on the migration, the suggested clustering procedure is divided into pre- and post-clustering stages. The task and bandwidth classification procedure groups jobs that can run in a virtual machine cluster with sufficient bandwidth. Depending on the VM’s availability inside the cluster, the bandwidth is mapped to the virtual machine. Several performance metrics, including bucket size, task execution time, VM lifetime, and VM utilization, are used in the VM clustering process. The suggested VM clustering’s primary goal is to map tasks to bandwidth-efficient virtual machines (VMs) in order to achieve high availability and dependability. As opposed to current algorithms, it shortens the time allotted for tasks and their execution. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Bandwidth Cloud computing Database segmentation Virtual machine (VM) VM clustering

来源：评论

学校读者我要写书评

暂无评论

FLBC-IDS: a federated learning and blockchain-based intrusion detection system for secure IoT environments

引用

Multimedia Tools and Applications 2025年第17期84卷 17229-17251页

作者： Govindaram, Anitha A, Jegatheesan Institute of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Tamilnadu Thandalam Chennai India

The development of the Internet of Things (IoT) in multiple sectors has led to substantial security issues due to its decentralized structure and resource limits. To solve these problems, this paper proposes a novel technique called FLBC-IDS, which combines Horizontal Federated Learning (HFL), Hyperledger Blockchain, and EfficientNet to detect intrusions in IoT environments. The FLBC-IDS model uses HFL to enable secure and privacy-preserving model training across numerous IoT devices, resulting in decentralized data privacy and resource efficiency. The model's integration of Hyperledger Blockchain ensures tamper-resistant and transparent recording of model updates and agreements among participating IoT nodes, protecting the system's integrity. Furthermore, EfficientNet improves the model's robustness by effectively obtaining and categorizing features from network traffic data. On the CICIDS-2018 and CICIoT-2023 datasets, the FLBC-IDS model outperforms previous techniques in terms of accuracy, recall, F1-score, and precision. The FLBC-IDS model has an accuracy of 98.89%, recall of 98.044%, F1-score of 98.29%, and precision of 98.44%. The article analyzes the suggested model's merits and limitations, as well as future research directions for real-world deployment of IoT security solutions. Overall, the FLBC-IDS paradigm holds significant promise for improving IoT security and safeguarding IoT settings from infiltration attempts and cyber threats. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Introduction

Signals and Communication Technology

引用

Signals and Communication Technology 2024年 Part F1492卷 3-17页

作者： Tian, Yu-Chu Gao, Jing School of Computer Science Queensland University of Technology BrisbaneQLD Australia College of Computer and Information Engineering Inner Mongolia Agricultural University Hohhot China

The main theme of this book is network analysis and architecture design for network planning. While there are various types of networks, this book specifically focuses on computer networks for data communication. Therefore, it uses the term networks to specifically refer to computer networks unless specified explicitly otherwise. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Smart AI Voice Assistant through Generative Text Transformer and NLP Implementation in Python 4

Smart AI Voice Assistant through Generative Text Transformer...

引用

4th International Conference on Intelligent Technologies, CONIT 2024

作者： Bajpai, Devesh Kiran, Mallela Uday Reddy, Busi Hemanth Natarajan, Suresh Kumar School of Computer Science and Engineering Ramanagara India

ISBN: (纸本)9798350349900

In our project, we employed Natural Language Processing (NLP), Artificial Intelligence (AI), Generative Text Transformer (GTT), and Speech Recognition technologies. Through the utilization of these advanced technologies, we aimed to enhance the capabilities and functionalities of our system. NLP facilitated improved language understanding and interaction, while AI contributed to the overall intelligence and decision-making processes. GTT played a crucial role in generating coherent and contextually relevant text, adding a layer of sophistication to our applications. Additionally, the integration of speech recognition technology enabled seamless interaction through voice commands, enhancing the overall user experience. By leveraging these cutting-edge technologies synergistically, our project aimed to deliver a more intelligent, efficient, and user-friendly system, showcasing the transformative potential of combining NLP, AI, GTT, and speech recognition in an integrated framework. This potent blend transcends mere functionality, aiming to transform user experience and pave the way for intelligent companions seamlessly integrated into our lives. By leveraging the transformative power of this unified framework, we envision a future where technology not only serves us but also empowers and enriches our interactions with the world around us. © 2024 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Stacked autoencoder with weighted loss function for intrusion detection in IoT application

引用

Multimedia Tools and Applications 2024年 1-29页

作者： Gangula, Rekha Vutukuru, Murali Mohan Kumar, M. Ranjeeth Department of Computer Science and Engineering Vaagdevi Engineering College Telangana BollikuntaWarangal506005 India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram AP Guntur522502 India School of Computer Science & amp Artificial Intelligence SR University Anantasagar Telangana Warangal506371 India

The fast increase of network traffic in recent times causes significant detection of intrusions in Internet of Things (IoT) environments. Currently, Deep Learning (DL) models play a crucial role in cyber security for malicious identification and intrusion detection in IoT networks. The existing methods have drawbacks like overfitting, data imbalance, and not completely capturing complex dependencies and relationships among input and features that are significant for intrusion detection. To overcome these limitations, Stacked Autoencoder (SAE) with weighted loss function is proposed for effective Intrusion Detection System (IDS). The SAE includes weighted loss function to minimize the overfitting issue and finally, the One Class-Support Vector Machine (OCSVM) is used in the classification layer to classify the intrusions. The database used for intrusion detection in IoT environment are Bot-IoT and ToN-IoT databases, which undergo pre-processing by using standard scalar and min–max normalization to remove duplicates and inconsistent data in the databases. Then, the optimal features are selected by using firefly optimizer which selects active features values for classification. In the resulting phase, the stacked autoencoder obtains 99.99%, and 99.70% of classification accuracy on the Bot-IoT and ToN-IoT databases, respectively, which are superior while compared to the traditional autoencoder model. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Support vector machines

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：