检索结果-内蒙古大学图书馆

2021 International Conference on data analytics for Business and Industry, ICDABI 2021

作者： Mohammed, Abdulrahim Hewahi, Nabil College of Science University of Bahrain Big Data Science and Analytics Program Sakhir Bahrain College of Information Technology University of Bahrain Department of Computer Science Sakhir Bahrain

ISBN: (纸本)9781665416566

Pipeline networks are crucial for process industries transportation and business operation. These vital elements, however, are highly exposed to material degradation due to corrosion that seriously impedes operational profitability, reliability, and safety. Industries usually monitor pipeline corrosion rate by gauging pipe wall thickness. Predicting pipe wall thickness helps industries to identify locations with high corrosion rate at an early stage and take necessary actions. The aim of this research is to predict pipe wall thickness at different locations using different machine learning algorithms including Support Vector Machine (SVM), Random Forest (RF), k-Nearest Neighbor (KNN), fully connected Artificial Neural Network (ANN), and Long Short-Term Memory (LSTM). The data processed and analyzed in this study included six different process variables as well as pipe wall thickness at three different locations in a downstream oil and gas industry. The study findings demonstrated that LSTM with test Root Mean Squared Errors (RMSEs) of 0.019 mm, 0.015 mm, and 0.017 mm for the three selected locations, outperformed the other methods applied and successfully identified the pipe wall thickness pattern. © 2021 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of Diverse Intrusion Detection Methods using Machine Learning Techniques 12

A Comparative Study of Diverse Intrusion Detection Methods u...

引用

12th International Conference on computer Communication and Informatics, ICCCI 2022

作者： Kathiresan, V. Karthik, S. Divya, P. Rajan, D. Palanivel Marwadi University Computer Engineering- Ai and Big Data Analytics Gujarat Rajkot India S. N. S College of Technology Department of CSE Tamil Nadu Coimbatore India Bannari Amman Institute of Technology Department of Computer Science and Engineering Tamil Nadu Erode India Cmr Engineering College Department of Computer Science and Engineering Telangana Hyderabad India

ISBN: (纸本)9781665480352

Establishing robust and efficient intrusion detection systems (IDS) and Intrusion prevention systems (IPS) are inevitable in today's security world. The major role of IDS is detecting the anomaly in network traffic using effective methods. Machine learning techniques take a vital role in intrusion detection based on anomaly detection. This paper deals with the survey on machine learning techniques used in intrusion detection. The classification algorithms of machine learning like logistic regression, naïve Bayes, KNN, Decision Tree, Random Forest, and SVM are suitable for intrusion detection. This paper analyses the behaviour and properties of the machine learning-based classification techniques which is used for intrusion detection application. © 2022 IEEE.

关键词： Intrusion detection

来源：评论

学校读者我要写书评

暂无评论

Incentivized Federated Learning and Unlearning

引用

IEEE Transactions on Mobile Computing 2025年

作者： Ding, Ningning Sun, Zhenyu Wei, Ermin Berry, Randall Data Science and Analytics Thrust Internet of Things Thrust Information Hub Guangzhou511453 China Northwestern University Department of Electrical and Computer Engineering EvanstonIL60208 United States Northwestern University Electrical and Computer Engineering Department Industrial Engineering and Management Sciences Department EvanstonIL60208 United States

To protect users' right to be forgotten in federated learning, federated unlearning aims at eliminating the impact of leaving users' data on the global learned model. The current research in federated unlearning mainly concentrates on developing effective and efficient unlearning techniques. However, the issue of incentivizing valuable users to remain engaged and preventing their data from being unlearned is still under-explored, yet important to the unlearned model performance. This paper focuses on the incentive issue and develops an incentive mechanism for federated learning and unlearning. We first characterize the leaving users' impact on the global model accuracy and the required communication rounds for unlearning. Building on these results, we propose a four-stage game to capture the interaction and information updates during the learning and unlearning process. A key contribution is to summarize users' multi-dimensional private information into one-dimensional metrics to guide the incentive design. Interestingly, we prove that allowing federated unlearning can result in reduced payoffs for both the server and users, compared to a scenario without unlearning. Numerical results demonstrate the necessity of unlearning incentives for retaining valuable leaving users, and also show that our proposed mechanisms decrease the server's cost by up to 53.91% compared to state-of-the-art benchmarks. © 2002-2012 IEEE.

关键词： federated learning federated unlearning incentive mechanism

来源：评论

学校读者我要写书评

暂无评论

Overview of Shared-task on Abusive Comment Detection in Tamil and Telugu 3

Overview of Shared-task on Abusive Comment Detection in Tami...

引用

3rd Workshop on Speech and Language Technologies for Dravidian Languages, DravidianLangTech 2023

作者： Priyadharshini, Ruba Chakravarthi, Bharathi Raja Subramanian, Malliga Navaneethakrishnan, Subalalitha Chinnaudayar Shanmugavadivel, Kogilavani Premjith, B. Murugappan, Abirami Kumaresan, Prasanna Kumar Prashanth, Karnati Sai Reddy, Mangamuru Sai Rishith Chandu, Janakiram Gandhigram Rural Institute-Deemed to be University India Insight SFI Research Centre for Data Analytics School of Computer Science University of Galway Ireland Kongu Engineering College Tamil Nadu India SRM Institute of Science and Technology Kattankulathur Chennai India Amrita School of Artificial Intelligence Amrita Vishwa Vidyapeetham India Department of Information Science and Technology Anna University India

ISBN: (纸本)9789544520854

This paper discusses the submissions to the shared task on abusive comment detection in Tamil and Telugu codemixed social media text conducted as part of the third Workshop on Speech and Language Technologies for Dravidian Languages at RANLP 2023. The task encourages researchers to develop models to detect the contents containing abusive information in Tamil and Telugu codemixed social media text. The task has three subtasks - abusive comment detection in Tamil, Tamil-English and Telugu-English. The dataset for all the tasks was developed by collecting comments from YouTube. The submitted models were evaluated using macro F1-score, and prepared the rank list accordingly. © DravidianLangTech 2023 - 3rd Workshop on Speech and Language Technologies for Dravidian Languages, associated with 14th International Conference on Recent Advances in Natural Language Processing, RANLP 2023 - Proceedings.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Fourth-Order Paired-Explicit Runge-Kutta Methods

arXiv

引用

arXiv 2024年

作者： Doehring, Daniel Christmann, Lars Schlottke-Lakemper, Michael Gassner, Gregor J. Torrilhon, Manuel RWTH Aachen University Germany University of Stuttgart Germany Center for Advanced Analytics and Predictive Sciences University of Augsburg Germany Department of Mathematics and Computer Science Center for Data and Simulation Science University of Cologne Germany

In this paper, we extend the Paired-Explicit Runge-Kutta schemes by Vermeire et. al. [1, 2] to fourth-order of consistency. Based on the order conditions for partitioned Runge-Kutta methods we motivate a specific form of the Butcher arrays which leads to a family of fourth-order accurate methods. The employed form of the Butcher arrays results in a special structure of the stability polynomials, which needs to be adhered to for an efficient optimization of the domain of absolute stability. We demonstrate that the constructed fourth-order Paired-Explicit Runge-Kutta methods satisfy linear stability, internal consistency, designed order of convergence, and conservation of linear invariants. At the same time, these schemes are seamlessly coupled for codes employing a method-of-lines approach, in particular without any modifications of the spatial discretization. We apply the multirate Paired-Explicit Runge-Kutta (P-ERK) schemes to inviscid and viscous problems with locally varying wave speeds, which may be induced by non-uniform grids or multiscale properties of the governing partial differential equation. Compared to state-of-the-art optimized standalone methods, the multirate P-ERK schemes allow significant reductions in right-hand-side evaluations and wall-clock time, ranging from 40% up to factors greater than *** Codes 65L06, 65M20, 7604 © 2024, CC BY.

关键词： Runge Kutta methods

来源：评论

学校读者我要写书评

暂无评论

Enhancing Intrusion Detection Systems Using Ensemble Machine Learning Techniques

Enhancing Intrusion Detection Systems Using Ensemble Machine...

引用

IEEE International Conference on Emerging & Sustainable Technologies for Power & ICT in a Developing Society (NIGERCON)

作者： Isaac Adedoyin Oyebade Isaac Oluwafemi Elesemoyo Mercy Oka Ebute Abidemi Emmanuel Adeniyi Joseph Bamidele Awotunde Akpan Caleb Solomon Agbotiname Lucky Imoize Kehinde Amudat Odulana Department of Computer Science Bowen University Iwo Nigeria Department of Computer Engineering Elizade University Ilara-Mokin Nigeria Department of Accounting Anderson School of Management University of New Mexico USA Department of Computer Science University of Ilorin Ilorin Nigeria Department of Electrical and Electronics Engineering University of Lagos Akoka Lagos Nigeria School of Physics Engineering and Computer Science (Data Science and Analytics) University of Hertfordshire

ISBN: (数字)9798331542559

ISBN: (纸本)9798331542566

Intrusion detection systems are an essential part of the current cybersecurity environment, and IDS devices are intended to scan the activity of the network and systems to identify possible improper actions or violations. IDSs work in analyzing the traffic of networks and the traffic of networks and the behavior of systems, distinguishing suspicious information and signs of violation of legal access. This capability is critical for protecting information systems’ characteristics, such as integrity, confidentiality, and availability. Useful data was collected from Kaggle data archives, and several base models such as K-Nearest Neighbor, Random Forest, Logistic Regression, and Decision Tree classifier will be used. Their predictions are combined using a Voting Classifier. The models are trained and evaluated based on accuracy, precision, recall, and F1-Score. Results show that the Voting classifier achieved an accuracy of 99.78%, with a precision of 99.67% and recall of 99.92% for intrusion detection. The Logistic Regression and K-Nearest Neighbor models achieved accuracies of 95.37% and 99.52%, respectively, while having a precision of 94.93% and 99.51%, respectively. The Decision Tree and Random Forest models achieved accuracies of 99.76% and 99.86%, respectively, while having a precision of 99.75% and 99.83%, respectively. These findings suggest ensemble techniques significantly enhance intrusion detection, making networks safer.

关键词： Logistic regression Accuracy Sensitivity Intrusion detection Telecommunication traffic Nearest neighbor methods Classification algorithms Decision trees Object recognition Random forests

来源：评论

学校读者我要写书评

暂无评论

LearningFlow: Automated Policy Learning Workflow for Urban Driving with Large Language Models

arXiv

引用

arXiv 2025年

作者： Peng, Zengqi Wang, Yubin Han, Xu Zheng, Lei Ma, Jun Robotics and Autonomous Systems Thrust The Hong Kong University of Science and Technology Guangzhou China Data Science and Analytics Thrust The Hong Kong University of Science and Technology Guangzhou China Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology China

Recent advancements in reinforcement learning (RL) demonstrate the significant potential in autonomous driving. Despite this promise, challenges such as the manual design of reward functions and low sample efficiency in complex environments continue to impede the development of safe and effective driving policies. To tackle these issues, we introduce LearningFlow, an innovative automated policy learning workflow tailored to urban driving. This framework leverages the collaboration of multiple large language model (LLM) agents throughout the RL training process. LearningFlow includes a curriculum sequence generation process and a reward generation process, which work in tandem to guide the RL policy by generating tailored training curricula and reward functions. Particularly, each process is supported by an analysis agent that evaluates training progress and provides critical insights to the generation agent. Through the collaborative efforts of these LLM agents, LearningFlow automates policy learning across a series of complex driving tasks, and it significantly reduces the reliance on manual reward function design while enhancing sample efficiency. Comprehensive experiments are conducted in the high-fidelity CARLA simulator, along with comparisons with other existing methods, to demonstrate the efficacy of our proposed approach. The results demonstrate that LearningFlow excels in generating rewards and curricula. It also achieves superior performance and robust generalization across various driving tasks, as well as commendable adaptation to different RL algorithms. Copyright © 2025, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Novel Development of Artificial Intelligence Enabled Learning Methodology for Human Depression Prediction Scheme

A Novel Development of Artificial Intelligence Enabled Learn...

引用

2024 International Conference on Intelligent Systems for Cybersecurity, ISCS 2024

作者： Ramkumar, G. Priyadharshini, R. Selvi, K. Kalaiselvi, K. Rathika, S. Kanagavalli, N. Saveetha University Department of Ece Tamil Nadu Chennai India Vel Tech Rangarajan Dr. Sagunthala R and D Institute of Science and Technology Department of Computer Science and Engineering Tamil Nadu Chennai India R.M.K Engineering College Department of Information Technology Tamil Nadu Chennai India Saveetha College of Liberal Arts and Sciences Saveetha Institute of Medical and Technical Sciences Department of Data Analytics Tamil Nadu Chennai India Prince Shri Venkateshwara Padmavathy Engineering College Department of Master of Business Administration Tamil Nadu Chennai India Rajalakshmi Institute of Technology Department of Computer Science and Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350375237

Human Depression Prediction is essential for several reasons, primarily centered around improving mental health outcomes and providing timely interventions. Firstly, early detection of depression allows for prompt and targeted interventions, enabling individuals to receive appropriate support and treatment before their condition worsens. The Human Depression Prediction Scheme (HDPS) introduces an innovative method for predicting depression by synergizing the capabilities of deep learning through the LeNet architecture with the optimization prowess of the Grey Wolf Optimization (GWO) algorithm. The proposed scheme achieves a commendable accuracy of 95%, attesting to its effectiveness in discerning depressive tendencies. Notably, the HDPS is implemented in Google Colab, emphasizing its accessibility and ease of use. This integration of advanced technologies and optimization techniques positions HDPS as a promising tool for early detection of depression, offering both high accuracy and practical implementation in a widely accessible computing environment. © 2024 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Uniform Consistency of Generalized Fréchet Means

arXiv

引用

arXiv 2024年

作者： Aveni, Andrea Mukherjee, Sayan Department of Statistical Science Duke University United States Center for Scalable Data Analytics and Artificial Intelligence Department of Computer Science Universität Liepzig Germany Max Planck Institute for Mathematics in the Natural Sciences Duke University Departments of Statistical Science Mathematics Computer Science and Biostatistics & Bioinformatics United States

We study a generalization of the Fréchet mean on metric spaces, which we call φ-means. Our generalization is indexed by a convex function φ. We find necessary and sufficient conditions for φ-means to be finite and provide a tight bound for the diameter of the intrinsic mean set. We also provide sufficient conditions under which all the φ-means coincide in a single point. Then, we prove the consistency of the sample φ-mean to its population analogue. We also find conditions under which classes of φ-means converge uniformly, providing a Glivenko-Cantelli result. Finally, we illustrate applications of our results and provide algorithms for the computation of φ-*** Codes 0F05, 60F15, 60D05, 62E20, 62F10, 58K05 © 2024, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Exploring Classification Models for Video Source Device Identification: A Study of CNN-SVM and Softmax Classifier

Exploring Classification Models for Video Source Device Iden...

引用

International Symposium on Networks, computers and Communications (ISNCC)

作者： Najmath Ottakath Younes Akbari Somaya Al-Maadeed Ahmed Bouridane Fouad Khelifi Department of Computer Science and Engineering Qatar University Doha Qatar Center for Data Analytics and Cybernetics University of Sharjah Sharjah UAE Department of Computer and Information Sciences Northumbria University Newcastle UK

Video Source device identification plays a crucial role in video forensics as the proliferation of video capturing devices has given rise to crimes with videos that are challenging to trace. Reliance on metadata extraction is insufficient as it can be corrupted or manipulated to conceal the source of the crime. Another technique employed for source identification is noise pattern extraction, which generates a unique identification for the video camera. However, this method is susceptible to capture faults and can produce diverse noise patterns for each video. In addressing these challenges, there is a need to identify distinctive features that are consistent across all videos captured by the same camera. This has led to the adoption of computer vision techniques utilizing machine learning and deep learning. Classifiers play a crucial role in machine learning and data analysis, as they are responsible for categorizing or predicting results based on input data. Our experiments show that the subject is sensitive to classifiers and developing a good classifier or classifier-level fusions can improve results in practice for all datasets.

关键词：

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：