检索结果-内蒙古大学图书馆

Distributed Computing and Optimization Techniques (ICDCOT), International Conference on

作者： Adepu Sai Aashrith Vishwaroju Sirichandana Barka Tarun Kumar M A Jabbar Y Sridevi Computer Science and Engineering (AI & ML) Vardhaman College of Engineering Department of English Vardhaman College of Engineering

In an era where the digital realm is indispensable to daily life, Constantly posing a threat, distributed denial of service (DDoS) attacks are capable of disrupting vital online services. Traditional methods of DDoS attack classification often fall short when facing the ever-evolving landscape of attack techniques. This paper unveils a journey through the complexities of enhancing DDoS attack classification with a focus on improving accuracy and adaptability. We embarked on this research by individually training a plethora of machine learning models. However, our preliminary findings highlighted the striking dis-parity in accuracy across different models, highlighting how complex and varied DDoS attacks are. Driven to overcome these constraints, we resorted to the sturdy framework of ensemble learning. Ensemble learning changed the game for accurate DDoS attack classification by effortlessly combining the best features of several base models. To be more precise, we blended two distinct baseline models: K-Nearest Neighbors (KNN) and Random Forest (RF). These models, each with distinct characteristics, combined to form a flexible and adaptive DDoS attack classification system. K-Nearest Neighbors (KNN) uses the proximity of data points to find trends and parallels. Resilience, high-dimensional data processing, and overfitting resistance are all favoured by the Random Forest (RF) ensemble of decision trees. Combining these several methods into a group greatly improved our categorization accuracy. Our research's ability to forecast accuracy using the ensembled model was one of its main results. This prediction accuracy indicates the flexibility and dependability of the classification model in addition to providing a crucial performance standard for assessing system effectiveness. Finally, our explo-ration of the DDoS assault classification demonstrated Ensemble Learning's superiority. The proposed strategy surpassed the existing methodologies, according to experimental

关键词：

来源：评论

学校读者我要写书评

暂无评论

Clustering based Ensemble Machine Learning for Integrated Prediction and Classification of Ecological Zones

Clustering based Ensemble Machine Learning for Integrated Pr...

引用

2024 International Conference on Intelligent Algorithms for Computational Intelligence Systems, IACIS 2024

作者： Alabdeli, Haider Reddy, Francis Vijaykumar Anna Chanti, Yerrolla Aruna, T.M. Das, Abhijeet The Islamic University College of Technical Engineering Department of Computers Techniques Engineering Najaf Iraq Malla Reddy Engineering College for Women Dept of Computer Science and Engineering Secunderabad India Sr University School of Computer Science & Artificial Intelligence Warangal India Nitte Meenakshi Institute of Technology Department of Ai&ml Bengaluru India Department of Civil Engineering Bhubaneswar India

ISBN: (纸本)9798350360660

Accurate classification of ecological zones helps identifying the location of specific ecological features, and analyzing changing conditions. However, existing methods had limitations such as forming different image dimensions and analysing the areas within the images due to high noisy data. To overcome this, the proposed research integrated Density Based Spatial Clustering of Applications with Noise (DBSCAN) with Ensemble Machine Learning (Eml) algorithms using Multilayer Perceptron (mlP), Naïve Bayes (NB), Classification and Regression Tree (CART), and Logistic Regression (LR). To train the model, the Landsat series data which is obtained from Geographical Information System (GIS) is used and then pre-processed using Normalized Difference Vegetation Index (NDVI) to characterize a variety of vegetation properties. The DBSCAN is then used for noisy data to distinguish the densities of data points and to segment data in different fields. The integration of DBSCAN with ml classifiers improved the classification accuracy. The overall experimental results show that the proposed DBSCAN-Eml achieved 98.43% of accuracy and 97.89% of precision when compared with the existing methods Eml based spatial prediction method and Artificial Neural Network Cellular Automata (ANN-CA). © 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

MIGRATE: Cross-Lingual Adaptation of Domain-Specific LLMs through Code-Switching and Embedding Transfer 31

MIGRATE: Cross-Lingual Adaptation of Domain-Specific LLMs th...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Hong, Seongtae Lee, Seungyoon Moon, Hyeonseok Lim, Heuiseok Department of Computer Science and Engineering Korea University Korea Republic of Human-inspired AI Research Korea Republic of

ISBN: (纸本)9798891761964

Large Language Models (LLMs) have rapidly advanced, with domain-specific expert models emerging to handle specialized tasks across various fields. However, the predominant focus on English-centric models demands extensive data, making it challenging to develop comparable models for middle and low-resource languages. To address this limitation, we introduce MIGRATE, a novel method that leverages open-source static embedding models and up to 3 million tokens of code-switching data to facilitate the seamless transfer of embeddings to target languages. MIGRATE enables effective cross-lingual adaptation without requiring large-scale domain-specific corpora in the target language, promoting the accessibility of expert LLMs to a diverse range of linguistic communities. Our experimental results demonstrate that MIGRATE significantly enhances model performance in target languages, outperforming baseline and existing cross-lingual transfer methods. This approach provides a practical and efficient solution for extending the capabilities of domain-specific expert models. © 2025 Association for Computational Linguistics.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Enhancing intrusion detection in IIoT: optimized CNN model with multi-class SMOTE balancing

引用

Neural Computing and Applications 2024年第24期36卷 14643-14659页

作者： Eid, Abdulrahman Mahmoud Soudan, Bassel Nassif, Ali Bou Injadat, MohammadNoor Department of Computer Engineering College of Computing and Informatics University of Sharjah Sharjah United Arab Emirates Department of Data Science and AI Faculty of Information Technology Zarqa University Zarqa Jordan

This work introduces an intrusion detection system (IDS) tailored for industrial internet of things (IIoT) environments based on an optimized convolutional neural network (CNN) model. The model is trained on a dataset that was balanced using a novel multi-class implementation of synthetic minority over-sampling technique (SMOTE) that ensures equal representation of all classes. Additionally, systematic optimization will be used to fine tune the hyperparameters of the CNN model and mitigate the effects of the increased size of the training dataset. Evaluation results will demonstrate substantial improvement in performance when the optimized CNN model is trained on the balanced dataset. The proposed IDS will be evaluated using the IIoT-specific WUSTL-IIOT-2021 dataset, and then its generalization capability will be verified using the non-domain specific UNSW_NB15 dataset. The model’s performance will be evaluated using accuracy, precision, recall, and F1-score metrics. The results will demonstrate that the proposed IDS is highly effective with performance exceeding 99.9% on all performance metrics. The IDS is also highly effective in detecting intrusion for generic IT networks achieving improvements in excess of 30% compared to the default baseline model. The results emphasize the versatility and effectiveness of the proposed IDS model, making it a reliable and adaptable solution for enhancing network security across diverse network environments. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Lung Cancer Prediction using Recurrent Residual Convolutional Neural Network and Long Short Term Memory

Lung Cancer Prediction using Recurrent Residual Convolutiona...

引用

Distributed Computing and Optimization Techniques (ICDCOT), International Conference on

作者： E Shrenitha M Manvith Reddy D Sushanth M A Jabbar Computer Science and Engineering (AI and ML) Vardhaman College of Engineering Shamshabad Hyderabad

Among Cancers lung cancer is one of the most prevailing and death-dealing cancers and the early detection of lung cancer poses a significant challenge due to its often asymptomatic nature, leading to high mortality rates. We introduce a novel method for precise lung cancer detection from CT images, leveraging deep learning techniques. Our approach combines Recurrent Residual Convolutional Neural Networks (RRCNN) like RU-Net and R2U-Net with Long Short-Term Memory (LSTM) networks and VGG16 architecture. Incorporating LSTM and Recurrent Residual Convolutional layers enhances the model's ability to capture temporal dependencies and improve feature representation for segmentation tasks. Additionally, VGG16's strong feature extraction capabilities aid in identifying complex patterns and subtle abnormalities in lung images. Evaluation on the LUNA16 dataset, comprising 888 CT scans with 1186 annotated lung nodules, demonstrates our method's superiority, achieving an impressive 90% accuracy. Our findings underscore the crucial role of temporal information in distinguishing between benign and aggressive lung cancer cases. In conclusion, our study highlights the effectiveness of combining RRCNN, LSTM, and VGG16 for accurate lung cancer detection, offering promising prospects for early diagnosis and improved patient outcome.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Augmented and End-to-End Models for Defect Classification of Structures 18

Augmented and End-to-End Models for Defect Classification of...

引用

18th ACM International Conference on Distributed and Event-Based Systems, DEBS 2024

作者： Kim, Gyu-Il Chung, Kyungyong Department of Computer Science Kyonggi University Suwon Korea Republic of Division of AI Computer Science and Engineering Kyonggi University Suwon Korea Republic of

ISBN: (纸本)9798400704437

This paper proposes an automated defect classification model for the safety diagnosis and maintenance of concrete structures. Traditional manual classification methods are time-consuming and rely on subjective judgment, whereas the proposed model utilizes time-series data obtained from sensors to enable faster and more accurate defect detection through data augmentation and Transformer-based classification. Data augmentation compensates for the imbalance in defect data distribution, and the Transformer effectively interprets the complex temporal patterns of the data, capturing long-range dependencies. This end-to-end model performs an integrated process from data processing to defect classification. Future research will explore the model's generalizability and the potential for integration into real-time monitoring systems. This paper presents a new approach to improving the economic and efficient evaluation of the safety of concrete structures. © 2024 Owner/Author.

关键词： Defects

来源：评论

学校读者我要写书评

暂无评论

Leveraging Augmented Reality,Semantic-Segmentation,and VANETs for Enhanced Driver’s Safety Assistance

引用

computers, Materials & Continua 2024年第1期78卷 1443-1460页

作者： Sitara Afzal Imran Ullah Khan Irfan Mehmood Jong Weon Lee Mixed Reality and Interaction Lab Department of SoftwareSejong UniversitySeoul05006Korea Faculty of Engineering and Digital Technologies School of Computer ScienceAI and ElectronicsUniversity of BradfordBradfordUK

Overtaking is a crucial maneuver in road transportation that requires a clear view of the road ***,limited visibility of ahead vehicles can often make it challenging for drivers to assess the safety of overtaking maneuvers,leading to accidents and *** this paper,we consider atrous convolution,a powerful tool for explicitly adjusting the field-of-view of a filter as well as controlling the resolution of feature responses generated by Deep Convolutional Neural Networks in the context of semantic image *** article explores the potential of seeing-through vehicles as a solution to enhance overtaking ***-through vehicles leverage advanced technologies such as cameras,sensors,and displays to provide drivers with a real-time view of the vehicle ahead,including the areas hidden from their direct line of *** address the problems of safe passing and occlusion by huge vehicles,we designed a see-through vehicle system in this study,we employed a windshield display in the back car together with cameras in both *** server within the back car was used to segment the car,and the segmented portion of the car displayed the video from the front *** see-through system improves the driver’s field of vision and helps him change lanes,cross a large car that is blocking their view,and safely overtake other *** network was trained and tested on the Cityscape dataset using semantic *** transparent technique will instruct the driver on the concealed traffic situation that the front vehicle has *** our findings,we have achieved 97.1% *** article also discusses the challenges and opportunities of implementing see-through vehicles in real-world scenarios,including technical,regulatory,and user acceptance factors.

关键词： Overtaking safety augmented reality VANET V2V deep learning

来源：评论

学校读者我要写书评

暂无评论

Support Vector Regression Based Traffic Prediction Machine Learning Model∗ 8

Support Vector Regression Based Traffic Prediction Machine L...

引用

8th IEEE International Conference on Computational System and Information Technology for Sustainable Solutions, CSITSS 2024

作者： Srivastava, Ansh Singh, Mrigaannkaa Nandi, Somesh Rv College of Engineering Dept. of Computer Science and Engineering Bengaluru India Rv College of Engineering Dept. of Electronics and Communication Bengaluru India Rv College of Engineering Dept. of AI/ML Bengaluru India

ISBN: (纸本)9798331505462

To combat the rising issue of urban traffic congestion, optimization of traffic light timings at intersections is crucial. Traditional methods show stagnancy in managing traffic flow dynamically. This study introduces Support Vector Regression (SVR) as an unconventional solution for traffic signal optimization. The model predicts the traffic conditions and alters the green light to turn on and off accordingly. Utilization of a comprehensive dataset consisting of vehicle distributions and critical flow ratios have been implemented to training a machine learning model. The statistics and performance is checked by usage of Mean Squared Error, R Squared, Mean Absolute Error demonstrating that SVR can effectively enhance traffic signal control. This approach pledges significant improvements in reduction in congestion and streamlined traffic flow. Our findings majorly highlight the capability of the SVR Machine Learning model in improving urban traffic management systems and call for further enhancement and collaboration with experts to address dynamic traffic issues. © 2024 IEEE.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Secure blockchain bidding auction protocol against malicious adversaries

引用

High-Confidence Computing 2024年第3期4卷 58-63页

作者： Xiaobing Dai Jiajing Liu Xin Liu Xiaofen Tu Ruexue Wang Department of Computer and Information Engineering Baotou Vocational&Technical CollegeBaotou 014010China Department of Computer Tianjin Ren’ai CollegeTianjin 301636China School of Information Engineering Inner Mongolia University of Science and TechnologyBaotou 014010China

In recent years,with the development of blockchain,electronic bidding auction has received more and more *** at the possible problems of privacy leakage in the current electronic bidding and auction,this paper proposes an electronic bidding auction system based on blockchain against malicious adversaries,which uses the secure multi-party computation to realize secure bidding auction protocol without any trusted third *** protocol proposed in this paper is an electronic bidding auction scheme based on the threshold elliptic curve *** can be implemented without any third party to complete the bidding auction for some malicious behaviors of the participants,which can solve the problem of resisting malicious adversary *** security of the protocol is proved by the real/ideal model paradigm,and the efficiency of the protocol is *** efficiency of the protocol is verified by simulating experiments,and the protocol has practical value.

关键词： Blockchain Secure multi-party computation Electronic bidding auction Malicious model Real/ideal model paradigm

来源：评论

学校读者我要写书评

暂无评论

Advanced Detection of Cyber-Physical Attacks in Manufacturing Using LSTM-KNN 2

Advanced Detection of Cyber-Physical Attacks in Manufacturin...

引用

2nd IEEE International Conference on Data science and Network Security, ICDSNS 2024

作者： Penchalaiah, N. Kumar, Arvind Chaithrashree, A. Saivaraju, Aravindh Bhoopathy, V. Lamba, Anil Kumar Annamacharya University Department of Ai&ml Boyanapalli Andhra Pradesh Rajampet India Sca Mriirs Haryana Faridabad India Brindavan College of Engineering Department of Computer Science and Engineering Bangalore India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Cse Tamil Nadu Chennai India Sree Rama Engineering College Department of Computer Science and Engineering Tirupathi India Geeta University Department of Computer Science and Engineering Delhi NCR Panipat India

ISBN: (纸本)9798350373110

Cyber Manufacturing System (CMS) is an assembly system that could be used in the future. There will be an increase in cyberattacks like the Stuxnet strike as the number of connected devices continues to grow. Current cyber security measures are inadequate to protect CMSs from new cyber-physical threats. This new security flaw can be better understood with the help of CMS's taxonomy for cyber-physical hazards, which is part of the agency's mandate. Preprocessing, feature selection, and training the model are the three steps that make up this proposed method. The data collected from the sensors show the greatest distance between two nearby locations after any outliers have been removed by preprocessing. Feature selection makes advantage of dimensional reduction derived from geometric feature distribution. When training the model, an LSTM-KNN was used. The average accuracy of the suggested method is 93.46%, which is higher than that of LSTM and KNN. © 2024 IEEE.

关键词： Cyber attacks

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：