检索结果-内蒙古大学图书馆

41st International Conference on Machine Learning, ICML 2024

作者： Miao, Rui Zhou, Kaixiong Wang, Yili Liu, Ninghao Wang, Ying Wang, Xin School of Artificial Intelligence Jilin University China Institute for Medical Engineering Science Massachusetts Institute of Technology United States School of Computing University of Georgia United States College of Computer Science and Technology Jilin University China

Graph neural networks (GNNs) have exhibited prominent performance in learning graph-structured data. Considering node classification task, based on the i.i.d assumption among node labels, the traditional supervised learning simply sums up cross-entropy losses of the independent training nodes and applies the average loss to optimize GNNs' weights. But different from other data formats, the nodes are naturally connected. It is found that the independent distribution modeling of node labels restricts GNNs' capability to generalize over the entire graph and defend adversarial attacks. In this work, we propose a new framework, termed joint-cluster supervised learning, to model the joint distribution of each node with its corresponding cluster. We learn the joint distribution of node and cluster labels conditioned on their representations, and train GNNs with the obtained joint loss. In this way, the data-label reference signals extracted from the local cluster explicitly strengthen the discrimination ability on the target node. The extensive experiments demonstrate that our joint-cluster supervised learning can effectively bolster GNNs' node classification accuracy. Furthermore, being benefited from the reference signals which may be free from spiteful interference, our learning paradigm significantly protects the node classification from being affected by the adversarial attack. Copyright 2024 by the author(s)

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

A classifier design for micro bubble generators based on deep learning technique

引用

Materials Today: Proceedings 2023年 80卷 2684-2696页

作者： Qaddoori, Ayman S. Saud, Jamila H. Hamad, F.A. Informatics Institute for Postgraduate Studies Iraqi Commission for Computer and Informatics Baghdad Iraq College of Science Mustansiriyah University Baghdad Iraq School of computing Engineering and Digital Technology Teesside University Middlesbrough United Kingdom

This paper aims to study the sizes of bubbles generated by the micro-bubble generator device (MBGs) in the water because of its impact on the dissolved oxygen percentage in the water and we find this in aquaculture where oxygen is important for marine life and in many applications. Where we have designed a classifier for micro-bubbles of different sizes and the effectiveness of the device has been proven in generating bubbles whose size ranges from 20 to 50 and calculating their numbers in the image by converting the image from (RGB) to (HSV), it has proven its effectiveness in maintaining lighting and neglecting color information Which is not important in identifying bubbles in the image, as well as increasing the processing speed, and then finding edges in the image, using canny edge detection, which has proven its great effectiveness in finding weak and strong edges. Where we then used the (Circular Hough Transform) algorithm to identify the tiny bubbles in the image, calculate their average diameter and numbers in the image, and find the overlapping bubbles between them by using (Two Thresholds) one for the edge and the other for the center of the bubble and then making (Segmentation) for these bubbles and inserting them on (Gaussian Normal Distribution) Do not neglect the dark bubbles, because in most cases they are unreal bubbles and may be distortions in the image or reflections in the lighting. And then make (zero paddings) for the extracted images to make them equal in size and avoid the distortion that will happen in the image if another method is used to make all bubbles of equal dimensions to prepare them for classification. And then we calculated the (mean square error) of the resulting bubble images to avoid repeating the same bubble in (datasets). The efficiency of the classifier was calculated by using deep learning technology. Where we built a (Convolution Neural Network) consisting of (15) layers and then we trained these layers on the images resul

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Experimental Evaluation of AI Powered Vehicle Toll Collection System Based on RFID and Internet of Things (IoT) Assistance

Experimental Evaluation of AI Powered Vehicle Toll Collectio...

引用

2024 International Conference on Innovative computing, Intelligent Communication and Smart Electrical Systems, ICSES 2024

作者： Pulikanti, Jyothi Jayaraj, R. Purushotham, S. Devi, V. Saranya Antony, A.Santhi Mary Chitra, M.P. Qis College of Engineering and Technology Department of Aimlds Andhra Pradesh Ongole India School of Computing Srm Institute of Science and Technology Department of Data Science and Buisness Systems Kattankulathur Chennai India Sona College of Technology Department of Eee Salem India Qis College of Engineering and Technology Department of Ece AndhraPradesh Ongole India Loyola-ICAM College of Engineering and Technology Department of Eee Nungambakkam Loyola Campus Chennai India Panimalar Engineering College Department of Electronics and Communication Engineering Chennai India

ISBN: (纸本)9798331543617

This paper presents the experimental evaluation of an AI-powered vehicle toll collection system, utilizing RFID technology and IoT integration. The system was designed to automate toll collection, reducing transaction time and improving accuracy while minimizing human intervention. The methodology involved RFID-based vehicle identification, real-time data transfer via IoT, and automatic toll deductions from prepaid accounts. The system was evaluated based on transaction speed, accuracy, user satisfaction, and system reliability. Results show that the automated system significantly reduced average transaction times from 32.5 seconds (manual) to 10 seconds (automated) during peak hours. Additionally, the system demonstrated a 100% accuracy rate in detecting unregistered vehicles and low-balance scenarios. User satisfaction was high, with an average rating of 4.6 out of 5. System reliability was also excellent, achieving an average uptime of 99.5% across multiple toll booth locations. The AI-powered toll collection system proved to be highly efficient in automating toll processes, reducing congestion, and improving the user experience. These findings suggest that such systems can effectively modernize toll management, contributing to time savings, reduced operational costs, and enhanced security. © 2024 IEEE.

关键词： Radio frequency identification (RFID)

来源：评论

学校读者我要写书评

暂无评论

Fuzz-classification(p,l)-Angel:An enhanced hybrid artificial intelligence based fuzzy logic for multiple sensitive attributes against privacy breaches

引用

Digital Communications and Networks 2023年第5期9卷 1131-1140页

作者： Tehsin Kanwal Hasina Attaullah Adeel Anjum Abid Khan Gwanggil Jeon Department of Computer Science COMSATS University IslamabadPakistan Department of Information Technology Quaid-e-Azam University IslamabadPakistan College of Science and Engineering School of Computing and MathsUniversity of DerbyDE221GBUK Department of Embedded Systems Engineering Incheon National UniversitySouth Korea

The inability of traditional privacy-preserving models to protect multiple datasets based on sensitive attributes has prompted researchers to propose models such as SLOMS,SLAMSA,(p,k)-Angelization,and(p,l)-Angelization,but these were found to be insufficient in terms of robust privacy and performance.(p,l)-Angelization was successful against different privacy disclosures,but it was not *** the best of our knowledge,no robust privacy model based on fuzzy logic has been proposed to protect the privacy of sensitive attributes with multiple *** this paper,we suggest an improved version of(p,l)-Angelization based on a hybrid AI approach and privacy-preserving approach like ***-classification(p,l)-Angel uses artificial intelligence based fuzzy logic for classification,a high-dimensional segmentation technique for segmenting quasi-identifiers and multiple sensitive *** demonstrate the feasibility of the proposed solution by modelling and analyzing privacy violations using High-Level Petri *** results of the experiment demonstrate that the proposed approach produces better results in terms of efficiency and utility.

关键词： Generalization Fuzzy-logic MSA Privacy disclosures Membership function (p,l)-Angelization QT HLPN

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Approach for Analysis and Characterization of COVID-19

引用

Computers, Materials & Continua 2022年第1期70卷 451-468页

作者： Indrajeet Kumar Sultan S.Alshamrani Abhishek Kumar Jyoti Rawat Kamred Udham Singh Mamoon Rashid Ahmed Saeed AlGhamdi School of Computing Graphic Era Hill UniversityDehradun(UK)India Department of Information Technology College of Computer and Information TechnologyTaif UniversityTaif21944Saudi Arabia School of Computer Science&IT JAIN(to be Deemed University)BangaloreIndia School of Computing Dehradun Institute of TechnologyUttarakhandIndia Department of Computer Engineering Faculty of Science and TechnologyVishwakarma UniversityPuneIndia Department of Computer Engineering College of Computer and Information TechnologyTaif UniversityTaif21944Saudi Arabia

Early diagnosis of a pandemic disease like COVID-19 can help deal with a dire situation and help radiologists and other experts manage human resources more *** a recent pandemic,laboratories perform diagnostics manually,which requires a lot of time and expertise of the laboratorial technicians to yield accurate ***,the cost of kits is high,and well-equipped labs are needed to perform this ***,other means of diagnosis is highly *** is one of the existing methods that finds its use in the diagnosis of *** radiography observes change in Computed Tomography(CT)chest images of patients,developing a deep learning-based method to extract graphical features which are used for automated diagnosis of the disease ahead of laboratory-based *** proposed work suggests an Artificial Intelligence(AI)based technique for rapid diagnosis of COVID-19 from given volumetric chest CT images of patients by extracting its visual features and then using these features in the deep learning *** proposed convolutional neural network aims to classify the infectious and non-infectious SARS-COV2 *** proposed network utilizes 746 chests scanned CT images of 349 images belonging to COVID-19 positive cases,while 397 belong to negative cases of *** experiment resulted in an accuracy of 98.4%,sensitivity of 98.5%,specificity of 98.3%,precision of 97.1%,and F1-score of 97.8%.The additional parameters of classification error,mean absolute error(MAE),root-mean-square error(RMSE),and Matthew’s correlation coefficient(MCC)are used to evaluate our proposed *** obtained result shows the outstanding performance for the classification of infectious and non-infectious for COVID-19 cases.

关键词： Coronavirus covid-19 respiratory infection computed tomography deep neural network

来源：评论

学校读者我要写书评

暂无评论

CurricularVPR: Curricular Contrastive Loss for Visual Place Recognition

CurricularVPR: Curricular Contrastive Loss for Visual Place ...

引用

2024 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2024

作者： Zhang, Dongshuo Chen, Nanhua Wu, Meiqing Lam, Siew-Kei Nanyang Technological University College of Computing and Data Science 50 Nanyang Ave 639798 Singapore Beijing Institute of Technology School of Aerospace Engineering Beijing100081 China

ISBN: (纸本)9798350377705

Visual Place Recognition (VPR) techniques commonly utilize Contrastive Losses (CL) to train models that generate compact and discriminative global descriptors for images. These models often result in poor performance due to one of the following reasons during training: 1) loss functions that focus primarily on easier samples, 2) reliance on time-consuming hard sample mining methods to identify informative supervisory samples, which hinders effective learning from large-scale datasets. To enhance both learning efficiency and effectiveness, we propose a Curricular Contrastive Loss (CCL) and use graded similarity labels as a measure of sample difficulty. Inspired by human learning that begin with easier concepts and progressively tackle more challenging ones, our CCL dynamically emphasizes easier samples during the initial training stages to achieve rapid convergence. The learning gradually focuses on harder samples in later training stages to bolster robustness of the models under challenging conditions. Our proposed method has been extensively evaluated on popular datasets, and the results demonstrate its superior performance compared to the CL and Generalized CL functions. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Harnessing an AI-Driven Analytics Model to Optimize Training and Treatment in Physical Education for Sports Injury Prevention 24

Harnessing an AI-Driven Analytics Model to Optimize Training...

引用

8th International Conference on Education and Multimedia technology, ICEMT 2024

作者： Mishra, Nilamadhab Habal, Beau Gray M. Garcia, Precious S. Garcia, Manuel B. School of Computing Science & Engineering VIT Bhopal University India College of Computer Studies and Multimedia Arts FEU Institute of Technology Philippines College of Nursing Jose Rizal University Philippines Educational Innovation and Technology Hub FEU Institute of Technology Philippines

ISBN: (纸本)9798400717611

In the competitive area of sports, injuries not only jeopardize athletes' careers but also lead to substantial setbacks for teams and organizations. Addressing this critical issue, our study introduces an artificial intelligence (AI)-driven model that enhances injury management through the strategic implementation of rest periods during athletes' recovery phases. By leveraging data analytics to monitor athletes' health continuously, this model offers sports managers a predictive tool for a proactive and preventative approach to injury management. Our research analyzes athletes' performance and health data across various sports disciplines by employing advanced machine learning techniques to identify patterns related to training regimes, treatment strategies, and the consequent risk and severity of injuries. Our findings underscore the utility of AI in generating actionable insights, thereby enabling more informed decision-making that centers on athletes' well-being. Notably, they demonstrate the model's success in predicting injury risks with high accuracy, subsequently informing tailored intervention strategies that significantly reduce the incidence of injuries. Furthermore, our study highlights how AI technologies can revolutionize training environments by enhancing safety and improving the efficacy of injury prevention and rehabilitation strategies. By advocating for the adoption of AI and technology in sports science, our study not only contributes to enhancing athlete care but also paves the way for future research to optimize athlete performance and health. Overall, this research highlights the role of AI-driven analysis in advancing sports medicine by offering a blueprint for coaches, sports medicine professionals, and athletes alike to navigate the complexities of injury prevention and management. © 2024 Copyright held by the owner/author(s).

关键词： Sports medicine

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning Method for Detecting Behavior-Based Malware 5

A Machine Learning Method for Detecting Behavior-Based Malwa...

引用

5th International Conference on Inventive Research in computing Applications, ICIRCA 2023

作者： Venkatarao, Javvaji Deeban Chakravarthy, V. Ramya, Singaraju Siva Prasad, V. Cherukuvada, Srikanth Soujanya, Annaram Sree Vidyanikethan Engineering College Dept. of Computer Science and Engineering Tirupati517 102 India Srm Institute of Science and Technology Department of Computing Technologies Chennai India School of Computing Srm Institute of Science and Technology Department of Computing Technologies Chennai India Mohan Babu University Dept. of Ai&ml Tirupati India School of Computing Srm Institute of Scienceand Technology Department of Networking and Communications Chennai India Cvr College of Engineering Department of Computer Science and Engineering Telangana India

ISBN: (纸本)9798350321425

While malware has posed a danger to businesses for years, advances in malware detection have lagged. Malware can cause damage to a system by starting unneeded services, which increases the system's workload and prevents it from operating smoothly. Malware detection can be done in one of two ways: the traditional signature-based approach or the more modern behavior-based approach. When malware is activated on a system, it conducts specific actions, such as launching malicious OS services or downloading malicious files from the web, that characterize its behaviour. The described technique detects malicious software based on its actions. The suggested model in this paper combines Support Vector Machine and Principal Component Analysis. © 2023 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

A Denoising Convolutional Auto Encoder with Bi-LSTM for Corrupted ECG Signals Reduction 2

A Denoising Convolutional Auto Encoder with Bi-LSTM for Corr...

引用

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

作者： Alsalami, Zaid Satish, E.G. Ponnibala, M. Rajalakshmi, J. Sushama, C. College of Technical Engineering The Islamic University Department of Computers Techniques Engineering Najaf Iraq Nitte Meenakshi Institute of Technology Dept. of Computer Science and Engineering Bengaluru India Velalar College of Engineering and Technology Erode India School of Computing Mohan Babu University Dept. of Cse Tirupati India

ISBN: (纸本)9798350373110

The IoT based scheme e-health uses some measurable device for to monitor the health condition of our body. The long-term measurable system like cardiovascular, electrocardiogram (ECG) are significant methods to diagnose the patient's diseases. The drawbacks of this measurable system such as high computational cost, consume more time for training and ECG signals contained some noise and corrupted signals. To addresses this kind of problem, the Denoising Convolution Auto Encoder (DCAE) with Bidirectional Long Short-Term Memory (Bi-LSTM) method is implemented. The DCAE contains encoder and decoder part to convert the ECG corrupted signals into compressed form. Bi-LSTM attached to encoder part that carries the input signals and trains that. Bi-LSTM carries double layers, which makes the training process easily. This proposed method tested on MIT-BIH databases. The advantages of this method, auto encoder easily convert the corrupted signals without using any parameters and reduce computation cost. Bi-LSTM reducing the training process, time consumption and it consisted of double layers, which increase the compression process of signals fastly. The developed DCAE-Bi-LSTM gives better output rate of 97.85% which is better than other existing methods like CNN-LSTM and SVM. © 2024 IEEE.

关键词： Signal denoising

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Cipher for Balancing Security Trade-Off in Smart Healthcare Application 6th

A Lightweight Cipher for Balancing Security Trade-Off in Sma...

引用

6th International Conference on Innovative computing and Communication, ICICC 2023

作者： Sandhya Sarma, K.N. Chandra Blessie, E. Lamkuche, Hemraj Shobharam Nehru College of Management Thirumalayampalayam India Coimbatore Institute of Technology Coimbatore India School of Computing Science and Engineering VIT Bhopal University Kothrikalan Sehore466114 India

ISBN: (纸本)9789819940707

IoT is a dynamic, emerging sector characterized by using existing Internet infrastructure to connect devices and data centers worldwide. The internet of healthcare things (IoHT) is a subclass of IoT that includes high-tech medical equipment that plays a crucial role in data monitoring, processing, storage, and transfer. It has novel challenges in data security. Several cryptographic techniques have been devised to safeguard the system against data misuse, alteration, and node tempering. Such cryptographic algorithms are inadequate because of the device's diminutive size, limited computing power, memory, and power resources. A lightweight cryptographic scheme based on symmetric cryptosystems powered by the Feistel structure is required to secure such a system. A lightweight cryptosystem is proposed in this paper for the security of the e-healthcare system. The proposed algorithm encompasses a compact S-box function, less round and addition substitution, and an XOR operation to generate encrypted information from plaintext. Additionally, a secure authentication mechanism based on the previously mentioned method is suggested for secure communication in the healthcare system. The cryptanalysis process and result state that our proposed system resists several cryptanalytic attacks which include brute force, avalanche effect, linear cryptanalysis, and biclique attack when compared with standard AES algorithm. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2024.

关键词： Internet of things

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：