检索结果-内蒙古大学图书馆

International Conference on Computing, engineering, and Design (ICCED)

作者： Rahmat Hidayat Achmad Solichin Adhitia Erfina Sudin Saepudin Muhamad Muslih Mohd Zainuri Saringat Master of Computer Science Budi Luhur University Jakarta Indonesia Information Systems Study Program Nusa Putra University Sukabumi Indonesia Department of Software Engineering Faculty of Computer Science and Information Technology Tun Hussein Onn Malaysia University

ISBN: (数字)9798331529376

ISBN: (纸本)9798331529383

The Plasmodium parasite, which causes malaria, is an acute fever illness that infects people when a female Anopheles mosquito bites them. It is predicted that malaria would claim 619,000 lives in 2021, with 96% of those deaths occurring in the African continent. We can achieve this by using a microscope to examine thick and thin blood smears. The proficiency of a microscope examiner is crucial for doing microscopic examinations. Consider how time-consuming, ineffective, and costly it would be to examine thousands of malaria cases. Consequently, Creating an automated method for detecting malaria parasites is the aim of this study. We employ a MobileNetV2 pretrained model with CNN technology. Because it has been trained on dozens or even millions of data points, this pretrained model is incredibly light but dependable. There are two main benefits of automatic malaria parasite detection: firstly, it can offer a more accurate diagnosis, particularly in locations with limited resources; secondly, it lowers diagnostic expenses. The optimizer utilizes Adam Weight, the criteria uses NLLLoss, and the model is trained using 32 for batch_size. In the fourteenth epoch, we obtained the maximum accuracy score of 96.26% based on the training data. The outcomes of the predictions demonstrate how excellent this score is. EfficienceNet, DenseNet, AlexNet, and other pretrained models are among the alternatives that scientists are advised to try training with.

关键词： Training Adaptation models Accuracy Costs Malaria Microscopy Data visualization Training data Cost function Data models

来源：评论

学校读者我要写书评

暂无评论

MUSE: A Multi-Feature Semantic Fusion Method for ROS Node Search Based on Knowledge Graph

MUSE: A Multi-Feature Semantic Fusion Method for ROS Node Se...

引用

Asia-Pacific Conference on software engineering

作者： Yuxin Zhao Xinjun Mao Tanghaoran Zhang Zhang Zhang College of Computer National University of Defense Technology Changsha China Key Laboratory of Software Engineering for Complex Systems National University of Defense Technology Changsha China

Reusing ROS components, specifically ROS Nodes, is crucial for improving the efficiency and quality of robotic software development. However, developers face challenges in finding the desired ROS Nodes for reuse due to scattered organization of ROS Nodes and the ambiguity in their ROS Node name. To address these challenges, this paper proposes a MUlti-feature SEmantic fusion method (MUSE) that leverages a domain-specific ROS knowledge graph for searching ROS Nodes. Firstly, a large dataset is constructed, comprising code files and textual descriptions related to ROS Nodes obtained from GitHub and ROS Wiki. Secondly, an in-depth analysis of user queries regarding the reuse of ROS Nodes is conducted, leading to the selection of multiple features that provide a comprehensive representation of ROS Node semantics, including Function, Hardware, Input, and Output. Subsequently, a knowledge graph of ROS Nodes is developed based on the dataset, incorporating the selected features. This knowledge graph effectively organizes scattered knowledge and resolves the issue of diverse mentions through entity disambiguation and resolution. To eliminate the semantic gap between the descriptions of features mentioned in user queries and the entities in the knowledge graph, a pretrained transformer-based model was used to measure the multi-feature semantic similarity between user queries and ROS Nodes knowledge. Finally, we employ a linear regression model to integrate the multi-feature knowledge between user queries and ROS Nodes knowledge. The proposed method has shown a 20% improvement in performance on NDCG@1 compared to other ROS Node search methods. Further evaluations highlight the effectiveness of each feature incorporated in the knowledge graph, as well as the significance of each parameter within the regression model. These findings underscore the robustness of this research in optimizing the reuse of ROS Nodes and facilitating the development of robotics software.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Reinforcement Learning Approach for Robust Supervisory Control of Uavs Under Disturbances

SSRN

引用

SSRN 2023年

作者： Ahmed, Ibrahim Quinones-Grueiro, Marcos Biswas, Gautam Electrical and Computer Engineering Institute for Software Integrated Systems Vanderbilt University 1025 16th Ave S NashvilleTN37212 United States Computer Science Institute for Software Integrated Systems Vanderbilt University 1025 16th Ave S NashvilleTN37212 United States

In this work, we present an approach to supervisory reinforcement learning control for unmanned aerial vehicles (UAVs). UAVs are dynamic systems where control decisions in response to disturbances in the environment have to be made in the order of milliseconds. We formulate a supervisory control architecture that interleaves with extant embedded control and demonstrates robustness to environmental disturbances in the form of adverse wind conditions. We run case studies with a Tarot T-18 Octorotor to demonstrate the effectiveness of our approach and compare it against a classic cascade control architecture used in most vehicles. While the results show the performance difference is marginal for nominal operations, substantial performance improvement is obtained with the supervisory RL approach under unseen wind conditions. © 2023, 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

Smart Advertising Based on Customer Preferences and Manage the Supermarket 4

Smart Advertising Based on Customer Preferences and Manage t...

引用

4th International Conference on Advancements in Computing, ICAC 2022

作者： Eishan Dinuka, W.H.A. Wickramasinghe, A.Y.S.W. Weerasinghe, W.S.H. Karunaratne, K.P.G. Liyanapathirana, Chethana Rupasinghe, Lakmal Department of Computer Science and Software Engineering Faculty of Computing Sri Lanka Institute of Information Technology Malabe Sri Lanka Department of Information Technology Faculty of Computing Sri Lanka Institute of Information Technology Malabe Sri Lanka Department of Computer Systems Engineering Faculty of Computing Sri Lanka Institute of Information Technology Malabe Sri Lanka

ISBN: (纸本)9798350398090

As a developing country, Sri Lanka needs to go along with cutting-edge technologies. In the beginning phase of this digital advertising, multiple advertisements were displayed on the users' feeds, including advertisements despite their preferences. This was a terrible user experience for the users. However, smart advertising based on customer preferences can manage the flow of advertisements on the feed as per the users' preferences. This same technique can be used in handling advertisements while shopping at supermarkets. These advertisements can be directed based on demographic characteristics like face and gender and previous customer transactions. Additionally, providing the nearest supermarket they can reach based on their current location. Queue management is the next most crucial facility that needs to be provided to a supermarket. However, the manual system of queue management is not effective. But with a modernized queue management system, overcrowded supermarkets can be managed effectively. This proposed system also considers providing a chatbot service to manage customer inquiries in a reliable strategy. In this system, we mainly used the Keras model called VGGFace for face detection, the Conventional Neural Network and Keras-based model for gender detection, the TensorFlow model called Single Shot MultiBox Detection MobileNet for queue and crowd detection, the Apriori algorithm base model for predicting the buying pattern, a Keras-based model for Artificial Intelligence chatbot and finally, google map Application Programming Interface for the nearest supermarket finding are models and technology. This system was developed to manage a supermarket properly. © 2022 IEEE.

关键词： Sales

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

computer-Vision-Based Non-Contact Paste Concentration Measurement*

Computer-Vision-Based Non-Contact Paste Concentration Measur...

引用

Automation in Manufacturing, Transportation and Logistics (ICaMaL), International Conference on

作者： Tailin Liang Zhaolin Yuan State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beihang University Beijing China Department of Industrial and Systems Engineering Research Institute of Advanced Manufacturing The Hong Kong Polytechnic University Hong Kong China

ISBN: (数字)9798350378658

ISBN: (纸本)9798350378665

For monitoring the paste concentration, existing techniques, such as ultrasonic concentration meters and neutron meters, suffer from radiation hazards and low precision in high concentrations. This paper proposes a novel non-contact concentration measurement method based on deep learning. With the dataset collected by preparing the paste with different concentrations and taking photographs from the paste surface, a convolutional neural network is trained to extract the features from images and predict the concentration. The experiments indicate that the measurement accuracy is close to 88.79 % for the manual stirring paste dataset and 91.42 % for the automatic stirring paste dataset, which are sufficient in industrial applications. As a substitution of traditional concentration measurement instruments, the proposed vision-based concentration measurement method is non-contact and its accuracy is sufficient in industrial applications.

关键词： Meters Deep learning Accuracy Ultrasonic variables measurement Transportation Manuals Feature extraction Surface texture Convolutional neural networks Surface treatment

来源：评论

学校读者我要写书评

暂无评论

An Efficient Community-based Approach for the Influence Maximization Problem in Social Networks 10

An Efficient Community-based Approach for the Influence Maxi...

引用

10th IEEE International Conference on Intelligent Computing and Information systems, ICICIS 2021

作者： Samir, Ahmed M. Rady, Sherine Gharib, Tarek F. Kafrelsheikh University Faculty of Computer and Information Sciences Software Engineering Department Kafrelsheikh Egypt Ain Shams University Faculty of Computer and Information Sciences Information Systems Department Cairo Egypt

ISBN: (纸本)9781665440769

The problem of detecting top influential users in social networks is known as the influence maximization problem. Top social network influencers play a significant role in different fields like virtual marketing, politics, and public health. There are various techniques and methods implemented to identify the top influential users for maximizing the influence within social networks. There exist, however, a real challenge to effectively reach those top influential users with both high accuracy and less computational time. This paper proposes an efficient approach for the problem of influence maximization based on communities' identification. A proposed approach LCS includes three stages: firstly, the application of the Louvain community detection algorithm to detect the different communities of the social network graph. Secondly, executing the CRANK algorithm to rank and sort the generated communities-based CRANK main four metrics. Finally, the selection of the top seed nodes from the sorted communities using degree centrality. Experimental results conducted on three social network datasets, under an Independent Cascade model for verification, show the effectiveness of the proposed approach compared to the centrality-based heuristics. Additionally, comparable results are achieved against greedy algorithms with far less time complexity. © 2021 IEEE.

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

Novel Approach for Enhancing Mental Well-Being Through Machine Learning Techniques

Novel Approach for Enhancing Mental Well-Being Through Machi...

引用

Advancements in Computing (ICAC), International Conference on

作者： O.V.D.E Roshani H.M.K.J.J Ayuwardhana P.H.M.S Rodrigo R.U Hewageegana Harinda Fernando Dilshan I. de Silva Department of Computer Science and Software Engineering Faculty of Computing Sri Lanka Institute of Information Technology Malabe Sri Lanka Department of Computer Systems Engineering Faculty of Computing Sri Lanka Institute of Information Technology Malabe Sri Lanka

Frequently, individuals undergo specific episodes of mental health challenges throughout their lifetime. But the COVID pandemic has triggered a surge in mental health disorders arising from isolation, monotonous routines, demanding workloads, financial disparities, and disruptions to daily schedules. Furthermore, the global pandemic has induced constant anxiety and stress. Beyond the pandemic, the competition and intense pressure of the modern world impact mental health. Access to advanced mental health solutions and the necessary familiarity remain limited for most of the population. Given the integration of technology into daily life, diverse remedies, including mobile and web applications, have emerged to tackle the escalating challenge of mental health disorders. This study proposes an accessible and cost-effective approach that employs machine learning to detect stress levels and discern user emotions from journal entries and facial expressions while integrating self-journaling, video recommendations, and visual content generation to stimulate positive emotions and relieve stress.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DomainDemo: a dataset of domain-sharing activities among different demographic groups on Twitter

arXiv

引用

arXiv 2025年

作者： Yang, Kai-Cheng Goel, Pranav Quintana-Mathé, Alexi Horgan, Luke McCabe, Stefan D. Grinberg, Nir Joseph, Kenneth Lazer, David Network Science Institute Northeastern University BostonMA United States Department of Software and Information Systems Engineering Ben-Gurion University of the Negev Be’er-Sheva Israel Computer Science and Engineering Department University at Buffalo BuffaloNY United States

Social media play a pivotal role in disseminating web content, particularly during elections, yet our understanding of the association between demographic factors and political discourse online remains limited. Here, we introduce a unique dataset, DomainDemo, linking domains shared on Twitter (X) with the demographic characteristics of associated users, including age, gender, race, political affiliation, and geolocation, from 2011 to 2022. This new resource was derived from a panel of over 1.5 million Twitter users matched against their U.S. voter registration records, facilitating a better understanding of a decade of information flows on one of the most prominent social media platforms and trends in political and public discourse among registered U.S. voters from different sociodemographic groups. By aggregating user demographic information onto the domains, we derive five metrics that provide critical insights into over 129,000 websites. In particular, the localness and partisan audience metrics quantify the domains’ geographical reach and ideological orientation, respectively. These metrics show substantial agreement with existing classifications, suggesting the effectiveness and reliability of DomainDemo’s approach. © 2025, CC BY.

关键词： Tweets

来源：评论

学校读者我要写书评

暂无评论

Runtime Backdoor Detection for Federated Learning via Representational Dissimilarity Analysis

arXiv

引用

arXiv 2025年

作者： Zhang, Xiyue Xue, Xiaoyong Du, Xiaoning Xie, Xiaofei Liu, Yang Sun, Meng School of Computer Science University of Bristol United Kingdom Department of Information and Computing Science School of Mathematical Science Peking University China Department of Software Systems and Cybersecurity Monash University Australia School of Computing and Information Systems Singapore Management University Singapore School of Computer Science and Engineering Nanyang Technological University Singapore

Federated learning (FL), as a powerful learning paradigm, trains a shared model by aggregating model updates from distributed clients. However, the decoupling of model learning from local data makes FL highly vulnerable to backdoor attacks, where a single compromised client can poison the shared model. While recent progress has been made in backdoor detection, existing methods face challenges with detection accuracy and runtime effectiveness, particularly when dealing with complex model architectures. In this work, we propose a novel approach to detecting malicious clients in an accurate, stable, and efficient manner. Our method utilizes a sampling-based network representation method to quantify dissimilarities between clients, identifying model deviations caused by backdoor injections. We also propose an iterative algorithm to progressively detect and exclude malicious clients as outliers based on these dissimilarity measurements. Evaluations across a range of benchmark tasks demonstrate that our approach outperforms state-of-the-art methods in detection accuracy and defense effectiveness. When deployed for runtime protection, our approach effectively eliminates backdoor injections with marginal overheads. © 2025, CC BY.

关键词： Federated learning

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：