检索结果-内蒙古大学图书馆

2nd International Conference on Materials science and Mathematics for Advanced technology, MSMAT 2022

作者： Karegoudra, Shilpa Yendapalli, Vamsidhar Department of Computer Science and Engineering Udupi574110 India Department of Computer Science and Engineering GITAM School of Technology Bengaluru GITAM University Karnataka India

Information and Communication technology (ICT) is used in recent industries to advance into a decision-making environment in manufacturing. The objectives of this are efficiency, flexibility, innovation, quality, and cost reduction. Controlling and monitoring the machining operation is an area of interest for most researchers. Drilling is the process of making a hole by using different cutting tools and continuously removing material to create the desired feature. It often rubs against the produced surface during chip evacuation. As a result, the produced roughness is distinct from that of other machining operations like milling or turning. Surface roughness may therefore differ from the one that is predicted theoretically. In this paper, we are studying the various non-contact methods to estimate the surface roughness of the machined surfaces. © 2023 Elsevier Ltd. All rights reserved.

关键词： Cost reduction

来源：评论

学校读者我要写书评

暂无评论

Caching Techniques in Edge Computing and Challenges 3

Caching Techniques in Edge Computing and Challenges

引用

3rd International Conference on Advancement in Electronics and Communication engineering, AECE 2023

作者： Kumar, Sumit Dash, Yajnaseni Galgotias University Department of Computer Science & Engineering Uttar Pradesh India School of Computer Science Engineering and Technology Bennett University Uttar Pradesh India

ISBN: (纸本)9798350330724

Edge computing, a distributed computing concept, brings data processing and storage closer to endpoints or edge devices. Caching methods are crucial in edge computing environments for optimizing performance and minimizing latency and enable faster response times, efficient bandwidth utilization, and enhanced scalability. Edge computing uses caching techniques strategically based on user behaviour studies and access patterns to boost scalability and reduce network congestion. Caching techniques increase the efficacy and performance of edge computing. The parameters that influence efficacy include cache management strategies, network conditions, application features, and data access patterns. This paper presents a brief overview of the caching technologies utilized in edge computing and their challenges. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Advancements in Breast Cancer Diagnosis: Integrating Classifier Algorithms, Neural Network and Ensemble Learning with PCA, VIF for Feature Selection and Dimensionality Reduction 6

Advancements in Breast Cancer Diagnosis: Integrating Classif...

引用

6th International Conference on Electrical engineering and Information and Communication technology, ICEEICT 2024

作者： Rahman, Arifur Zaman, Sakib Parvej, Shahriar Abdul Fattah, H.M. Khulna University of Engineering & Technology Department of Computer Science and Engineering Khulna Bangladesh School of Information University of Arizona TucsonAZ United States

ISBN: (纸本)9798350385779

Breast cancer's global prevalence highlights the need for the development of precise and reliable diagnostic tools. The objective of this study is to contribute to the growing body of knowledge in breast cancer diagnosis, highlighting the potential of a range of classifier algorithms, soft and hard voting ensemble approaches, and neural networks as potent tools in medical applications. These models were utilized to assess the Wisconsin Breast Cancer dataset obtained from UCI Machine Learning repository, consisting of 569 samples and 30 features. Besides, we utilized Principal Component Analysis (PCA) and Variance Inflation Factors (VIF) techniques to perform feature selection and dimensionality reduction on the standardized and original features respectively. After conducting PCA analysis, a variety of classifier models, including k-nearest neighbors (KNN), Lo-gistic Regression (LR), Decision Tree (DT), LightGBM (LGBM), XGBoost (XGB), Random Forest (RF), and Naive Bayes (NB), were employed. Moreover, after the VIF analysis, these classifier models and a Neural Network (NN) model were put into action. Subsequently, the best three and best five classifier algorithms were determined using accuracy metrics, then both soft and hard voting ensemble were executed on these algorithms. The neural network (NN) model underwent training for 500 epochs since beyond that point, the loss curves displayed nearly constant values. This model (NN) were compiled with 'adam' optimizer along with binary crossentropy as loss function. We observed our ensemble strategies demonstrated superior performance in accuracy compared to all existing methods. © 2024 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

EFLSS: An Efficient Federated Learning Security Scheme in Byzantine Attack Scenarios 10

EFLSS: An Efficient Federated Learning Security Scheme in By...

引用

10th IEEE Smart World Congress, SWC 2024

作者： Shen, Gang Fu, Zhiqiang Liu, Shaohua Hubei University of Technology School of Computer Science Wuhan China Naval University of Engineering Department of Management Engineering and Equipment Economics Wuhan China

ISBN: (纸本)9798331520861

Federated Learning (FL), a distributed machine learning approach, aims to protect user privacy by performing model training without centralized data collection. However, FL systems are susceptible to malicious participants uploading incorrect or harmful updates in the face of Byzantine Attacks, leading to model performance degradation or even failure. To address this problem, this paper proposes a new approach that combines an confusion factor and a parameter screening mechanism to securely and efficiently counter Byzantine Attacks. Local gradients are added with confusion factors before uploading to protect the security of local data. In addtion, we propose an improved anomaly detection algorithm that can identify and filter Byzantine nodes during the gradient aggregation phase to ensure the accuracy of the global model. Experimental results show that compared with the traditional FL mechanism, the global model obtained in this scheme has higher accuracy. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Intelligent Techniques for Nutrition Level Prediction in Guava Plants

Intelligent Techniques for Nutrition Level Prediction in Gua...

引用

2024 Asia Pacific Conference on Innovation in technology, APCIT 2024

作者： Nadiger, Rakshith S Suresh, Gautham Shobha Rani, N. Prabhu, Akshatha Sangamesh, M.A. Amrita Vishwa Vidyapeetham School of Computing Department of Computer Science Mysuru India Gitam University Gitam School of Technology Department of Computer Science & Engineering Bengaluru India National Institute of Engineering Department of Chemistry Mysuru India

ISBN: (纸本)9798350361537

Guava, a valuable tropical fruit crop, faces significant defect challenges due to diseases. Manual disease checks are time- consuming and error prone, leading to delayed action. Our research focuses on image processing to quickly and accurately identify guava diseases using deep learning approach with the help of Guava leaf images. This automation minimizes human intervention, enhances accuracy, and aids disease prevention. Early detection of these diseases improves crop quality and sustainability while reducing pesticide use. This Deep learning- driven approach aims to benefit farmers, consumers, and global food security by advancing guava farming practices. By using the YOLOv8 object detection model for 6 classes, we got an accuracy of 87.97%. © 2024 IEEE.

关键词： Agricultural Sustainability Deep Learning Guava Plant Disease Detection Nutrition level prediction YOLOv8

来源：评论

学校读者我要写书评

暂无评论

Moving target detection from the roadside by millimeter-wave radar

Moving target detection from the roadside by millimeter-wave...

引用

2024 International Symposium on Antennas and Propagation, ISAP 2024

作者： Moriyama, Toshifumi Matsumoto, Sora Chang, Yang-Lang Graduate School of Engineering Nagasaki University Nagasaki Japan College of Electrical Engineering and Computer Science National Taipei University of Technology Taipei Taiwan

ISBN: (纸本)9798350364774

In this study, we investigate a traffic monitoring method to detect passing cars, bikes, and humans from roadsides using millimeter-wave radar during road work. Because a road worker is one of the most dangerous occupations, the number of people trying to get this type of job is decreasing. To give a safety work condition and reduce road accidents with respect to the road works, a millimeter-wave radar is one of the candidates for infrastructure sensors that can be expected to offer robust detection performance regardless of the surrounding environment. Then, we applied millimeter-wave radar to traffic monitoring during road work. We examine that the radar detects passing cars, bikes, and humans, and estimates their direction with two corner reflectors from the roadside. These experiments were carried out, and the results are presented in this paper. © 2024 IEEE.

关键词： Roadsides

来源：评论

学校读者我要写书评

暂无评论

Divergent Approaches to Antimicrobial Peptide Classification: A Comparative Evaluation of AI Techniques 7

Divergent Approaches to Antimicrobial Peptide Classification...

引用

7th International Conference on Circuit Power and Computing Technologies, ICCPCT 2024

作者： Rajagopal, Sushma Bharathi Mohan, G. Doss, Srinath Amrita School of Computing Department of Computer Science and Engineering Amrita Vishwa Vidyapeetham Chennai India Botho University Faculty of Engineering and Technology Botswana

ISBN: (纸本)9798350372816

Given the global rise in antibiotic resistance, antimicrobial peptides (AMPs) provide a viable substitute for traditional antibiotics. Through a comparison of transformer-based, deep learning (DL), and machine learning (ML) techniques, this work seeks to classify AMPs. AMP sequences from curated databases were compared with non-AMP sequences obtained from UniProtKB/Swiss-Prot. The study compares performance across many assessment variables to assess how well various algorithms separate AMPs from non-AMPs. Significantly, RoBERTa outperformed DistilBERT (84.43%) in accuracy (86.53%). To provide a thorough knowledge of the algorithms' performance, the research also included a variety of other assessment criteria, including area under the receiver operating characteristic curve (AUC-ROC), recall, F1 score, and accuracy. The performance of the LSTM and GRU models was notable, despite their significantly lower accuracies. Furthermore, conventional machine learning methods such as Naive Bayes and Logistic Regression demonstrated competitive accuracy. This thorough analysis clarifies the benefits and drawbacks of various AMP classification techniques, providing insightful information for next studies on antimicrobial peptides and their potential to fight antibiotic resistance. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Blockchain Based Verification of Educational and Professional Certificates 2

Blockchain Based Verification of Educational and Professiona...

引用

2nd International Conference on Computational Systems and Communication, ICCSC 2023

作者： Singh, Anjali Chauhan, S.P.S. Goel, Amit Kumar Master of Technology in Computer Science and Engineering School of Computing Science and Engineering Galgotias University Greater Noida India School of Computing Science and Engineering Galgotias University Greater Noida India

ISBN: (纸本)9781665493932

Educational Documents and Certificates are a proof of professional achievements for anyone. Without these documents, it is not possible to start your career and hence play a very important role in everyone's professional life. Till date, Colleges, Universities and various educational institutes issue paper based degrees and certificates which are prone to get damaged or may be lost. The other drawback is that this process of issuing of degrees and manual process of verification of those documents by third parties is a time taking and cumbersome process. The employers take a lot of time for verifying these paper based degrees and certificates before they give the job offer. Forgery of paper based documents is also easier and has led to many educational scams. This paper aims to give the solution to the problems mentioned above through Blockchain Implementation. Block chain technology is not only limited to crypto currencies but is also of great applications in various fields like health, supply chain management, finance, etc. It has disrupted the traditional education system. This paper highlights as to how the educational certificates can be verified using the Ethereum platform and smart contracts. The traditional paper certificates would be converted to digital certificates on student's request, their hash value would be calculated using cryptographic hash functions and stored on Blockchain. A unique certificate ID and transaction hash value would be generated which would then be used to verify the certificates through a common platform. © 2023 IEEE.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

Research on the Application of improved AMCL Algorithm in Robot Obstacle Avoidance in Logistics Sorting Scene 7

Research on the Application of improved AMCL Algorithm in Ro...

引用

2024 7th International Conference on Circuits, Systems and Simulation, ICCSS 2024

作者： Shang, Gongyu Gong, Gu Hu, Xiaoting Liu, Xintong Zhu, Hua School of Computer Science and Technology Jiangsu Normal University Xuzhou China School of Mechatronic Engineering China University of Mining and Technology Xuzhou China

Compared with the normal scenes, the positions of obstacles, delivery boxes and sorting stations in the logistics sorting scene are relatively fixed, what’s more, the number of static obstacles in the logistics sorting scene is large. It requires higher navigation accuracy and pose adjustment of the robot. The author proposes an Adaptive Monte Carlo Localization (AMCL) algorithm that integrates the Dynamic Window Approach (DWA) algorithm to improve the accuracy and efficiency of robots in real-time positioning, navigation in static indoor environments, and obstacle avoidance efficiency. Using this method, the data collection of lidar sensor are optimized, reducing positioning calculation. By adjusting the parameters’ value, the adaptive positioning accuracy and real-time positioning rate of the logistics robot are improved. The experimental results show that the Adaptive Monte Carlo Localization integrated with Dynamic Window Approach algorithm is about 13.682 % higher than the normal Adaptive Monte Carlo Localization algorithm in the obstacle avoidance rate, which effectively makes the number of particles collected by lidar more standardized and rational. © 2024 Institute of Physics Publishing. All rights reserved.

关键词： Robots

来源：评论

学校读者我要写书评

暂无评论

A fusion of machine learning and cryptography for fast data encryption through the encoding of high and moderate plaintext information blocks

引用

Multimedia Tools and Applications 2025年第8期84卷 5349-5375页

作者： Shafique, Arslan Mehmood, Abid Alawida, Moatsum Elhadef, Mourad Rehman, Mujeeb Ur School of Biomedical Engineering University of Glasgow Glasgow United Kingdom Department of Computer Sciences Abu Dhabi University Abu Dhabi United Arab Emirates Cyber Technology Institute School of Computer Science and Informatics De Montfort University Leicester United Kingdom

Within the domain of image encryption, an intrinsic trade-off emerges between computational complexity and the integrity of data transmission security. Protecting digital images often requires extensive mathematical operations for robust security. However, this computational burden makes real-time applications unfeasible. The proposed research addresses this challenge by leveraging machine learning algorithms to optimize efficiency while maintaining high security. This methodology involves categorizing image pixel blocks into three classes: high-information, moderate-information, and low-information blocks using a support vector machine (SVM). Encryption is selectively applied to high and moderate information blocks, leaving low-information blocks untouched, significantly reducing computational time. To evaluate the proposed methodology, parameters like precision, recall, and F1-score are used for the machine learning component, and security is assessed using metrics like correlation, peak signal-to-noise ratio, mean square error, entropy, energy, and contrast. The results are exceptional, with accuracy, entropy, correlation, and energy values all at 97.4%, 7.9991, 0.0001, and 0.0153, respectively. Furthermore, this encryption scheme is highly efficient, completed in less than one second, as validated by a MATLAB tool. These findings emphasize the potential for efficient and secure image encryption, crucial for secure data transmission in rea-time applications. © The Author(s) 2024.

关键词： Cryptography

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：