检索结果-内蒙古大学图书馆

3rd IEEE International Conference on Distributed Computing and Electrical Circuits and Electronics, ICDCECE 2024

作者： Sudhakar, K. Husain, Saif O. Babu, D. Raja Kumar, M. Ashok Dineshkumar, R. Nitte Meenakshi Institute Of Technology Dept. Of Ai & Ds Bengaluru India College Of Technical Engineering The Islamic University Department Of Computers Techniques Engineering Najaf Iraq Sr University Department Of Electrical And Electronics Engineering Warangal India Skyline University Nigeria Department Of Computer Science Software Engineering And Cyber Security Kano State Nigeria Saveetha School Of Engineering Saveetha Institute Of Medical And Technical Sciences Saveetha University Department Of Electronics And Communication Engineering Chennai India

ISBN: (纸本)9798350318609

The Internet of Things (IoT) connects numerous intelligent devices providing security features that interact with default settings accessed through applications. Additionally, Deep Learning (DL)-based mechanisms was involved for malware detection to identify and mitigate attacks. The Adaptive Synthetic Sampling (ADASYN) technique addresses class imbalances, especially when splitter class instances are distributed data in complex patterns. The proposed Self-Attention based Long Short-Term Memory (LSTM) classification method facilitates the handling of long-range dependencies in transferred data sequences offering high flexibility and adaptability to varying input lengths. For feature selection Particle Swarm Optimization (PSO) is utilized iteratively optimizes a solution in a high-dimensional space although it may have a low convergence rate due to its iterative process. The obtained results demonstrate the proposed Self-Attention based LSTM model achieves better accuracy reaching 98.05% on the NSL-KDD dataset and 99.01 % on the UNSW-NB15 dataset. These results ensure accurate classification compared to other existing methods, such as Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN). © 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

Enhancing Cybersecurity using Machine Learning Strategies for Phishing Defense

Enhancing Cybersecurity using Machine Learning Strategies fo...

引用

International Conference on Communication and Electronics Systems (ICCES)

作者： C. Jamunadevi S. Pandikumar Naveen N S. Prasath Dhivyashree S Department of Computer Technology PG Kongu Engineering College Perundurai Erode Department of MCA Acharya Institute of technology Bangalore Department of IT Excel Engineering College Komarapalayam Department of Computer Science VET Institute of Arts and Science (Co-education) college Thindal MSc (Software Systems) Kongu Engineering College Perundurai Erode

ISBN: (数字)9798350377972

ISBN: (纸本)9798350377989

Cybersecurity experts continue to be concerned about phishing attacks because it causes a real risk to people, businesses, and economies all around the world. Phishing attacks cause a critical threat to global cybersecurity, necessitating effective classification methods for phishing URL operations. So, this work aims to categorize phishing URL operations into distinct types: deceptive, spear, whaling, and pharming. Leveraging machine learning techniques including logistic regression, support vector machine, Naive Bayes, decision tree, K-NN, and Perceptron, evaluate their efficacy in accurately identifying and classifying phishing attacks. The findings underscore the importance of these models in providing cybersecurity professionals with actionable insights into the diverse tactics employed by malicious actors. Among the evaluated models, logistic regression emerges as the preferred choice, demonstrating superior performance in accurately categorizing phishing URLs. This work contributes to enhancing cybersecurity defenses by offering a comprehensive framework for understanding and mitigating the impact of phishing attacks on digital ecosystems.

关键词： Uniform resource locators Support vector machines Logistic regression Phishing Biological system modeling Ecosystems Machine learning Decision trees computer crime Business

来源：评论

学校读者我要写书评

暂无评论

Separating Spectral and Spatial Feature Aggregation for Demosaicking

Separating Spectral and Spatial Feature Aggregation for Demo...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Xuanchen Li Bo Zhao Yan Niu Li Cheng Haoyuan Shi Zitong An College of Software Jilin University Changchun China College of Computer Science and Technology Jilin University Changchun China Department of Electrical and Computer Engineering University of Alberta Canada

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Existing demosaicking neural models typically follow the same design principles as those adopted by the rest image restoration tasks; yet one unique & often overlooked problem with demosaicking is it also suffers from the moiré artifact. This observation inspires us to examine the key reason that moiré happens only to demosaicking instead of other image restoration tasks. In this process, We identify the spectral inconsistency concealed in the input of demosaicking neural networks; our findings also clarify the failure of the traditional dense spatiospectral feature aggregation in mitigating spectral inconsistency. Based on the analysis, a new solution is proposed to address moiré while preserving fine image details. In particular, we decouple the traditionally used spatio-spectral feature aggregation into comprehensive spectral aggregation and local spatial aggregation. Throughout a diverse range of experiments with quantitative and qualitative results, our approach is shown capable of significantly reducing artifacts such as moiré and over-smoothness, as well as drastically boosting state-of-the-art performance without increasing computational cost.

关键词： Image color analysis Neural networks Transformers Boosting Image restoration Computational efficiency High frequency

来源：评论

学校读者我要写书评

暂无评论

SecureMed: A Blockchain-Based Privacy-Preserving Framework for Internet of Medical Things

引用

Wireless Communications and Mobile Computing 2023年第1期2023卷

作者： Rafique, Wajid Khan, Maqbool Khan, Salabat Ally, Juma Said Department of Computer Science and Operations Research University of Montreal Canada Department of IT and Computer Science PAF-IAST Pakistan College of Computer Science and Software Engineering Shenzhen University China Department of Electronics and Telecommunication Engineering Mbeya University of Science and Technology Tanzania United Republic of

The Internet of Medical Things (IoMT) connects a huge amount of smart sensors with the Internet for healthcare service provisioning. IoMT's privacy-preserving becomes a challenge considering the life-saving data collected and transferred through IoMT. Traditional privacy protection techniques use centralized management strategies, which lead to a single point of failure, lack of trust, state modification, information disclosure, and identity theft. Edge computing enables local computation of IoMT data, which reduces traffic to the cloud and also helps in accomplishing latency-sensitive healthcare applications and services. This paper proposes a novel framework (i.e., SecureMed) that uses blockchain-based distributed authentication implemented at the edge cloudlets to enforce privacy protection. In SecureMed, IoMT devices interact with edge cloudlets using smart contracts. It uses trusted edge nodes to implement an authentication algorithm that uses public/private key matching to authenticate IoMT. Experimental evaluation performed using the Pythereum blockchain shows that SecureMed outperforms the traditional blockchain scheme based on latency, bandwidth consumption, deployment time, scalability, and accuracy. Therefore, it can be used to protect the edge-enabled IoMT from privacy attacks and to ensure end-to-end healthcare service provisioning. © 2023 Wajid Rafique et al.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Adapt PointFormer: 3D Point Cloud Analysis via Adapting 2D Visual Transformers

arXiv

引用

arXiv 2024年

作者： Li, Mengke Li, Da Yang, Guoqing Cheung, Yiu-Ming Huang, Hui Shenzhen China VCC College of Computer Science and Software Engineering Shenzhen University Shenzhen China Department of Computer Science Hong Kong Baptist University Hong Kong

Pre-trained large-scale models have exhibited remarkable efficacy in computer vision, particularly for 2D image analysis. However, when it comes to 3D point clouds, the constrained accessibility of data, in contrast to the vast repositories of images, poses a challenge for the development of 3D pre-trained models. This paper therefore attempts to directly leverage pre-trained models with 2D prior knowledge to accomplish the tasks for 3D point cloud analysis. Accordingly, we propose the Adaptive PointFormer (APF), which fine-tunes pre-trained 2D models with only a modest number of parameters to directly process point clouds, obviating the need for mapping to images. Specifically, we convert raw point clouds into point embeddings for aligning dimensions with image tokens. Given the inherent disorder in point clouds, in contrast to the structured nature of images, we then sequence the point embeddings to optimize the utilization of 2D attention priors. To calibrate attention across 3D and 2D domains and reduce computational overhead, a trainable PointFormer with a limited number of parameters is subsequently concatenated to a frozen pre-trained image model. Extensive experiments on various benchmarks demonstrate the effectiveness of the proposed APF. The source code and more details are available at https://***/research/2024/PointFormer. Copyright © 2024, The Authors. All rights reserved.

关键词： 3D modeling

来源：评论

学校读者我要写书评

暂无评论

Learning-Aided Evolutionary Search and Selection for Scaling-up Constrained Multiobjective Optimization

引用

IEEE Transactions on Evolutionary Computation 2024年 1-1页

作者： Liu, Songbai Wang, Zeyi Lin, Qiuzhen Li, Jianqiang Tan, Kay Chen College of Computer Science and Software Engineering Shenzhen University Shenzhen China Department of Computing The Hong Kong Polytechnic University Hong Kong Hong Kong

The existing constrained multiobjective evolutionary algorithms (CMOEAs) still have great room for improvement in balancing populations convergence, diversity and feasibility on complex constrained multiobjective optimization problems (CMOPs). Besides, their effectiveness deteriorates dramatically when facing the CMOPs with scaling-up objective space or search space. We are thus motivated to design a learning-aided CMOEA with promising problem-solving ability and scalability for various CMOPs. In the proposed solver, two learning models are respectively trained online on constrained-ignored task and feasibility-first task, which are then used to learn the two improvement-based vectors for enhancing the search by differential evolution. In addition, the union population of parent and child solutions is divided into multiple subsets with a hierarchical clustering based on cosine similarity. A comprehensive indicator, considering objective-based performance and constraint violation degree of a solution, is developed to select the representative solution from each cluster. The effectiveness of the proposed optimizer is verified by solving the CMOPs with various irregular Pareto fronts, the number of objectives ranging from 2 to 15, and the dimensionality of search space scaling up to 1000. IEEE

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Electrocoagulation-based AZO DYE (P4R) Removal Rate Prediction Model using Deep Learning

Electrocoagulation-based AZO DYE (P4R) Removal Rate Predicti...

引用

2023 International Symposium on Green Technologies and Applications, ISGTA 2023

作者： Akoulih, Meryem Tigani, Smail Byoud, Fouzia Rharib, Meryem El Saadane, Rachid Pierre, Samuel Chehri, Abdellah Ghachtouli, Sanae El IME Lab Faculty of Science Hassan 2 University Casablanca20250 Morocco Research and Development Unit Accsellium LLC Fez Morocco Electrical Engineering Department SIRC-LaGeS Hassania School of Public Labors Casablanca20250 Morocco Department of Computer and Software Engineering Polytechnique Montréal MontréalQC Canada Department of Mathematics and Computer Science Royal Military College of Canada KingstonON11 K7K 7B4 Canada

This article presents a study on the effectiveness of electrocoagulation (EC) for the removal of azo dyes from wastewater. The analysis was performed using a combination of statistical methods, including density estimation, correlation analysis, and deep learning for electrocoagulation performance prediction. The results showed that electrocoagulation was able to effectively remove azo dyes from the wastewater, considering the energy consumption and the mass of flocs being important factors in the process. Deep Learning (DL) is used to build our predictive model using the datasets collected during the experimentation stage. Overall, the findings suggest that electrocoagulation is a promising technique for the treatment of wastewater containing azo dyes, and that the use of statistical and machine learning methods can aid in the optimization of the process. © 2024 The Authors. Published by ELSEVIER B.V.

关键词： Azo dyes

来源：评论

学校读者我要写书评

暂无评论

Towards Multi-Objective High-Dimensional Feature Selection via Evolutionary Multitasking

arXiv

引用

arXiv 2024年

作者： Feng, Yinglan Feng, Liang Liu, Songbai Kwong, Sam Tan, Kay Chen Department of Computer Science City University of Hong Kong Hong Kong College of Computer Science Chongqing University China College of Computer Science and Software Engineering Shenzhen University China Department of Computing The Hong Kong Polytechnic University Hong Kong

Evolutionary Multitasking (EMT) paradigm, an emerging research topic in evolutionary computation, has been successfully applied in solving high-dimensional feature selection (FS) problems recently. However, existing EMT-based FS methods suffer from several limitations, such as a single mode of multitask generation, conducting the same generic evolutionary search for all tasks, relying on implicit transfer mechanisms through sole solution encodings, and employing single-objective transformation, which result in inadequate knowledge acquisition, exploitation, and transfer. To this end, this paper develops a novel EMT framework for multiobjective high-dimensional feature selection problems, namely MO-FSEMT. In particular, multiple auxiliary tasks are constructed by distinct formulation methods to provide diverse search spaces and information representations and then simultaneously addressed with the original task through a multi-slover-based multitask optimization scheme. Each task has an independent population with task-specific representations and is solved using separate evolutionary solvers with different biases and search preferences. A task-specific knowledge transfer mechanism is designed to leverage the advantage information of each task, enabling the discovery and effective transmission of high-quality solutions during the search process. Comprehensive experimental results demonstrate that our MO-FSEMT framework can achieve overall superior performance compared to the state-of-the-art FS methods on 26 datasets. Moreover, the ablation studies verify the contributions of different components of the proposed MO-FSEMT. Copyright © 2024, The Authors. All rights reserved.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Intrusion Detection Mechanism Using Deep Learning

Intrusion Detection Mechanism Using Deep Learning

引用

IoT Based Control Networks and Intelligent Systems (ICICNIS), International Conference on

作者： P. Ananthi K. Nirmaladevi Naveen Kumar S Department of Computer Technology-PG Kongu Engineering College Erode Tamilnadu Department of Computer Applications Madanapalle Institute of Technology & Science M.Sc Software Systems Kongu Engineering College Erode India

ISBN: (数字)9798331518097

ISBN: (纸本)9798331518103

In today's connected and data-driven world, networks and digital systems need to be protected from malicious attacks. The effectiveness of conventional Intrusion Detection Systems (IDS) in recognizing and impeding novel threats and intricate methodologies has its limits. This study introduces a new method for improving network security by using deep learning techniques in the design and development of an intrusion detection system (IDS). The suggested Intrusion Detection System uses deep learning techniques, specifically Long Short Term Memory (LSTM) and Convolutional Neural Networks (CNNs), to identify and react to known and new security threats. Data can be taught to be encoded into a lower-dimensional representation and then decoded back into its original form using autoencoders (AEs). Autoencoders are a cutting-edge intrusion detection system that can lower false positives and raise overall detection accuracy because of their capacity to automatically learn from and adjust to the ever-changing threat landscape. They enhance computer networks capacity to spot irregularities and possible security threats. With the deep learning model obtaining a high accuracy of 99% in real-world threat detection, the results show that deep learning is effective in developing intrusion detection systems.

关键词： Deep learning Accuracy Autoencoders Intrusion detection Network security Threat assessment Real-time systems computer security Optimization Long short term memory

来源：评论

学校读者我要写书评

暂无评论

A Composite Retinal Fundus and OCT Dataset to Grade Macular and Glaucomatous Disorders 2

A Composite Retinal Fundus and OCT Dataset to Grade Macular ...

引用

2nd International Conference on Digital Futures and Transformative Technologies, ICoDT2 2022

作者： Hassan, Taimur Raja, Hina Hassan, Bilal Akram, Muhammad Usman Dias, Jorge Werghi, Naoufel Khalifa University C2PS and Kucars Department of Electrical Engineering and Computer Science Abu Dhabi United Arab Emirates College of EME Nust Biomisa Lab Department of Computer and Software Engineering Rawalpindi Pakistan Khalifa University Kucars Department of Electrical Engineering and Computer Science Abu Dhabi United Arab Emirates

ISBN: (纸本)9781665498197

Retinopathy represents a group of retinal diseases that causes severe visual impairments and even blindness. Many researchers have publicly released datasets containing fundus or optical coherence tomography (OCT) scans to screen retinal diseases like macular edema (ME) and age-related macular degeneration (AMD). These datasets also contain clinical markings to analyze the retinal layers and retinal lesions within normal and abnormal pathologies. However, to the best of our knowledge, no dataset provides the clinically graded fundus and OCT images reflecting the geographic AMD, neovascular AMD, acute central serous retinopathy (CSR), chronic CSR, centrally involved DME (ci-DME), and glaucomatous pathologies. Furthermore, the majority of the publicly available OCT datasets are acquired through Spectralis Machines, which limits the thorough evaluation of autonomous frameworks to screen retinal pathologies irrespective of the scanner specifications. To overcome these challenges, we present a novel dataset containing composite fundus and OCT scans of each patient, along with detailed annotations for extracting the retinal layers and retinal lesions. Also, contrary to its competitors, the proposed dataset is acquired through Topcon 3D OCT 2000 machine that can be utilized for training (or evaluating) any autonomous frameworks to give the lesion-aware screening and severity grading of the above-mentioned retinal diseases as per the clinical standards. Moreover, in this paper, we are also releasing the retinal annotation software alongside the proposed dataset. This software can help clinicians in quickly marking both fundus and OCT scans, which can be saved later on in any image format. Overall, the proposed dataset contains 9,268 OCT scans and 180 fundus scans from 105 subjects depicting healthy, ci-DME, geographic AMD, neovascular AMD, acute CSR, chronic CSR, and glaucomic pathologies. © 2022 IEEE.

关键词： Optical tomography

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：