检索结果-内蒙古大学图书馆

IEEE Transactions on artificial intelligence 2024年第7期5卷 3743-3756页

作者： Dong, Nanqing Wang, Zhipeng Sun, Jiahao Kampffmeyer, Michael Knottenbelt, William Xing, Eric Shanghai Artificial Intelligence Laboratory Shanghai200232 China Imperial College London Department of Computing LondonSW7 2AZ United Kingdom FLock.io LondonWC2H 9JQ United Kingdom UiT the Arctic University of Norway Department of Physics and Technology Tromso9019 Norway Carnegie Mellon University Machine Learning Department School of Computer Science PittsburghPA15213 United States Mohamed Bin Zayed University of Artificial Intelligence Masdar City Abu Dhabi United Arab Emirates

In the era of deep learning, federated learning (FL) presents a promising approach that allows multiinstitutional data owners, or clients, to collaboratively train machine learning models without compromising data privacy. However, most existing FL approaches rely on a centralized server for global model aggregation, leading to a single point of failure. This makes the system vulnerable to malicious attacks when dealing with dishonest clients. In this work, we address this problem by proposing a secure and reliable FL system based on blockchain and distributed ledger technology. Our system incorporates a peer-to-peer voting mechanism and a reward-and-slash mechanism, which are powered by on-chain smart contracts, to detect and deter malicious behaviors. Both theoretical and empirical analyses are presented to demonstrate the effectiveness of the proposed approach, showing that our framework is robust against malicious client-side behaviors. © 2020 IEEE.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

An Efficient Proposal for Deep learning-Based Diabetes Prediction 2

An Efficient Proposal for Deep Learning-Based Diabetes Predi...

引用

2nd IEEE International Conference on Networks, Multimedia and Information Technology, NMITCON 2024

作者： Baswaraj, D. Raju, Ch V V Narasimha Reddy, Pundru Chandra Shaker Kiran, Ajmeera Shaik, Mohammad Khaja Kumar, D Anil Computer Science and Engineering Vasavi College of Engineering Telangana Hyderabad India Marri Laxman Reddy Institute of Technology and Management Department Information Technology Telangana Hyderabad India Sr University School of Computer Science and Artificial Intelligence Telangana Warangal India Mlr Institute of Technology Computer Science and Engineering Dundigal Telangana Hyderabad India St. Ann's College of Engineering and Technology Artificial Intelligence and Machine Learning Andhra Pradesh Chirala India Pace Institute of Technology and Sciences Electronics and Communication Engineering Andhra Pradesh Ongole India

ISBN: (纸本)9798350372892

As a result of its exponential growth in recent years, diabetes now poses a serious danger on a worldwide scale. As of right now, diabetes is one of the foremost causes of death worldwide. Failure to treat diabetes increases the risk of death from cardiovascular disease, cerebrovascular accident, brain stroke, and a host of other complications. In order to minimize further complications, it is crucial to discover diabetes early so that action can be taken to stop the condition from progressing. Predicting diabetes in its early stages may be possible with the use of cutting-edge machine learning techniques that uncover previously unseen patterns. Using the PIMA dataset and a variety of machine learning algorithms, this study lays forth an approach for diabetes prediction. All four of these functional classifiers - Deep learning (DL), artificial Neural Network (ANN), and Naive Bayes (NB) - achieve accuracy rates between 90% and 98%. With a 98.07% accuracy rate on the PIMA dataset, DL outperforms the other three methods when it comes to diabetes onset. In light of this, the suggested system offers healthcare officials a useful tool for prognosis. Incorporating omics data for illness onset prediction considerably improves the accuracy of the DL technique. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Brain Tumor Detection Using VGG 16 & Efficient Net B3 Model 10

Brain Tumor Detection Using VGG 16 & Efficient Net B3 Model

引用

10th International Conference on Advanced Computing and Communication Systems, ICACCS 2024

作者： Menagadevi, M. Sharmila, S. Thiyagarajan, D. Madian, Nirmala Devaraj, Somasundaram School of Engineering Malla Reddy University Department of Computer Science Engineering Hyderabad India Dr.N.G.P Institute of Technology Department of Biomedical Engineering Coimbatore India School of Engineering Malla Reddy University Department of Artificial intelligence and Machine Learning Hyderabad India Vellore Institute of Technology Vellore India

ISBN: (纸本)9798350384369

A brain tumor is a growth of cells that begins in the brain and develops uncontrollably and unnaturally. Benign, malignant, and pituitary tumors are the different types of brain tumors. The life expectancy of the patients should be increased by appropriate care, careful planning and precise diagnostics. The above knowledge will help in early and accurate Detection of tumor. Magnetic Resonance Imaging (MRI) is generally utilized for diagnosing brain tumors. MRI examination is performed based on injecting contrast agents for enhancing the visibility of tumor. For recognition of brain tumors, machine learning and deep learning algorithms are performed to predictthe brain tumor with high accuracy. In this work modified EfficientN etB3 and VGG16 is proposed to detect the type and location of tumor. Proposed model gives higher prediction accuracy for different types of tumors. VGG 16 gives training accuracy of 95.1 %, testing accuracy of 94.3 % and validation accuracy of 94%. EfficientNetB3 training accuracy of 98.8%, testing accuracy of 98.4% and validation accuracy of 97.8%. EfficientN etB3 have better accuracy for tumor prediction and classification. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Skin Diseases Detection Using LBP and WLD: An Ensembling Approach

引用

SN computer science 2024年第1期5卷 72页

作者： Banerjee, Arnab Sarkar, Somenath Nasipuri, Mita Das, Nibaran Department of Computer Science and Engineering Jadavpur University Jadavpur West Bengal Kolkata 700032 India Department of Computer Science and Engineering (Artificial Intelligence and Machine Learning) Dr. B. C. Roy Engineering College Jemua Road Fuljhore West Bengal Durgapur 713206 India Department of Dermatology Venereology and Leprosy Calcutta School of Tropical Medicine West Bengal Kolkata 700073 India

In all developing and developed countries globally, skin diseases are becoming a prevalent health problem for humans of all age groups. Skin diseases create anxiety, affect mental health, worsen working life, and sometimes cause social isolation. Detecting skin diseases in the early stage is very important because early treatment can be helpful in such cases. There are very few dermatologists in rural and semi-urban areas in a country like India. To overcome the problem, a machine learning technique has been developed to detect three prevalent skin diseases—Leprosy, Tinea versicolor, and Vitiligo from the images of the skin lesions. The proposed approach extracts the texture from the images of the skin regions affected by such diseases using Weber’s local descriptor and Local binary pattern. Then the representations are ensembled to prepare the feature vector. This ensemble technique achieved 91.38% accuracy using a multilevel support vector machine, using the features extracted from different regions of the skin lesions area utilising the centre of gravity based rotation invariant Weber local descriptor and Local binary pattern. Some popular deep learning networks such as MobileNet, ResNet152, GoogLeNet, DenseNet121, and ResNet101 were used to compare the performance of the proposed approach with the deep learning models. ResNet101 achieved 89% accuracy, i.e. best among all the deep learning models used in this study. The proposed ensemble technique outperformed the top performing deep learning model by 2.38%. This technique will be helpful for the early screening of these skin diseases. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： LBP Leprosy Multi-SVM Pattern recognition STM Tinea versicolor Vitiligo WLD WLDRI

来源：评论

学校读者我要写书评

暂无评论

Hybrid Makes Better: Privacy-Preserving Medical Image Classification Based on Federated learning

Hybrid Makes Better: Privacy-Preserving Medical Image Classi...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Wang, Zhi Chi, Haotian Li, Yonggang Zhang, Yuxuan Jiang, Shunrong Du, Xiaojiang Guizani, Mohsen China University of Mining and Technology School of Computer Science Xuzhou221116 China Shanxi University School of Automation and Software Engineering Taiyuan030006 China Stevens Institute of Technology Department of Electrical and Computer Engineering HobokenNJ United States Mohamed Bin Zayed University of Artificial Intelligence Department of Machine Learning Abu Dhabi United Arab Emirates

ISBN: (纸本)9798350351255

The power of machine learning makes it available for medical image classification. However, machine learning requires large medical datasets to improve accuracy, which will involve patients' private information and lead to their privacy leakage. Federated learning is a trending technique to both protect patients' privacy and improve the accuracy of medical image classification. Unfortunately, current research shows that federated learning faces the risk of privacy leakage. In this paper, we propose a privacy-preserving scheme FHDM. Specifically, we construct a local hybrid differential privacy algorithm (LHDP) against patients' privacy leakage. This hybrid algorithm utilizes both Gaussian and Laplace differential privacy without enlarging the privacy budget. We prove that the algorithm applies to the model parameter. Moreover, we design loss optimization and global optimization strategies on the algorithm to achieve higher accuracy in medical image classification. Finally, we validate FHDM in terms of privacy-preserving and model accuracy on real datasets. Experiments show that FHDM effectively protects privacy and improves the average accuracy by 10.0% compared to adopting the LDP-based scheme with the same medical image dataset and privacy budget. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Dynamic Trust Management in IoT Networks using Reputation-Based Systems

Dynamic Trust Management in IoT Networks using Reputation-Ba...

引用

2024 International Conference on Distributed Systems, computer Networks and Cybersecurity, ICDSCNC 2024

作者： Naidu, D J Samatha Jain, Upma Shruthi, S. Rao, K. B. V. Brahma Iqbal, Syed Mohammad Uzair Natrayan, L. Annamacharya Pg College of Computer Studies Department of Master of Computer Applications India Graphic Era Deemed to Be University Department of Computer Science & Engineering Dehradun India Bms Institute of Technology and Management Department of Artificial Intelligence and Machine Learning Bengaluru India Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering India Symbiosis Law School Department of Law Pune India Simats Saveetha School of Engineering Department of Mechanical Engineering India

ISBN: (纸本)9798350375442

The Internet of Things (IoT) enables intelligent data exchange across many kinds of interconnected devices in a diverse and unpredictable physical setting. The Internet of Things (IoT) network used in this study is a cluster-based sensor network that includes a base station and an application server that offers various services in a cloud setting. In this setting, assaults may occur in both device-to-device and user-to-device communication. For pervasive devices with limited resources, the use of conventional encryption techniques to address this problem is not practical. In addition, the majority of current trust-based security solutions either address the user level or the devices level. Therefore, this study aims to tackle environment-specific security concerns at the device and user levels in light of the environment's inherent dynamic and dispersed nature. This research explored the usage of a Trust Based Security Framework (TBSF) and Reputation Based Systems in the Internet of Things (IoT) to accurately describe the actions of devices and users. Fuzzy logic was used to calculate both the device trust and the user trust. A trust-based access control system, secure cluster head selection, and safe routing were all built using these trust values. At first, the security of device-to-device communication was addressed by the design and effective implementation of the Trust Aware Device Access Control System (TADACS). © 2024 IEEE.

关键词： Access control

来源：评论

学校读者我要写书评

暂无评论

Temporal latent variable structural causal model for causal discovery under external interferences

引用

Neurocomputing 2025年 640卷

作者： Cai, Ruichu Huang, Xiaokai Chen, Wei Li, Zijian Hao, Zhifeng School of Computer Science Guangdong University of Technology Guangzhou China Peng Cheng Laboratory Shenzhen China Machine Learning Department Mohamed bin Zayed University of Artificial Intelligence Abu Dhabi United Arab Emirates College of Mathematics and Computer Science Shantou University Shantou China

Inferring causal relationships from observed data is an important task, yet it becomes challenging when the data is subject to various external interferences. Most of these interferences are the additional effects of external factors on observed variables. Since these external factors are often unknown, we introduce latent variables to represent these unobserved factors that affect the observed data. Specifically, to capture the causal strength and adjacency information, we propose a new temporal latent variable structural causal model, incorporating causal strength and adjacency coefficients that represent the causal relationships between variables. Considering that expert knowledge can provide information about unknown interferences in certain scenarios, we develop a method that facilitates the incorporation of prior knowledge into parameters learning based on Variational Inference, to guide the model estimation. Experimental results demonstrate the stability and accuracy of our proposed method. © 2025 Elsevier B.V.

关键词： Variational techniques

来源：评论

学校读者我要写书评

暂无评论

Streamlining Attendance with Fast Face Recognition Model 8

Streamlining Attendance with Fast Face Recognition Model

引用

8th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2024

作者： Sundar, Koushik Ravikumar, S. Jeyalakshmi, J. Eugene Berna, I. Samuel, Prithi Citibank Na Jersey CityNJ United States Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Computer Science & Engineering Chennai India Amrita School of Computing Amrita Vishwa Vidhyapeetham Department of Computer Science and Engineering Chennai India Bannari Amman Institute of Technology Department of Artificial Intelligence and Machine Learning Erode India School of Computing Srm Institute of Science and Technology Department of Computational Intelligence Kattankulathur Campus Chennai India

ISBN: (纸本)9798350376425

Facial recognition technology has become increasingly prevalent in today's world, with applications ranging from mobile phones to banking and workplace security. This research proposes a facial recognition-based solution to replace the manual attendance tracking process, streamlining the process and reducing human error. The proposed system integrates facial recognition, registration forms, and a Redis database to automate attendance tracking. By leveraging the ML search algorithm (similarity approach) and the Insight face Python module, the system can accurately identify individuals within a database. The system's implementation involves two phases: the initial phase focuses on integrating facial recognition, registration forms, and database access. The second phase involves utilizing software such as Streamlit and Dashboard to enhance user experience and visualization. This innovative solution offers a more efficient and accurate alternative to traditional manual attendance tracking methods, improving overall efficiency and reducing administrative burdens. By automating the process, the system contributes to a more streamlined and secure environment. © 2024 IEEE.

关键词： Database systems

来源：评论

学校读者我要写书评

暂无评论

Language Models "Grok" to Copy

arXiv

引用

arXiv 2024年

作者： Lv, Ang Xie, Ruobing Sun, Xingwu Kang, Zhanhui Yan, Rui Gaoling School of Artificial Intelligence Renmin University of China China Machine Learning Platform Department Tencent China School of Computer Science Wuhan University China

We examine the pre-training dynamics of language models, focusing on their ability to copy text from preceding context—a fundamental skill for various LLM applications, including in-context learning (ICL) and retrieval-augmented generation (RAG). We propose a novel perspective that Transformer-based language models develop copying abilities similarly to grokking, which refers to sudden generalization on test set long after the model fit to the training set. Our experiments yield three arguments: (1) The pre-training loss decreases rapidly, while the context copying ability of models initially lags and then abruptly saturates. (2) The speed of developing copying ability is independent of the number of tokens trained, similarly to how grokking speed is unaffected by dataset size as long as the data distribution is preserved. (3) Induction heads, the attention heads responsible for copying, form from shallow to deep layers during training, mirroring the development of circuits in deeper layers during grokking. We contend that the connection between grokking and context copying can provide valuable insights for more effective language model training, ultimately improving in-context performance. For example, we demonstrated that techniques that enhance grokking, such as regularization, either accelerate or enhance the development of context copying. Copyright © 2024, The Authors. All rights reserved.

关键词： Electric transformer testing

来源：评论

学校读者我要写书评

暂无评论

CAUSAL BALANCING FOR DOMAIN GENERALIZATION 11

CAUSAL BALANCING FOR DOMAIN GENERALIZATION

引用

11th International Conference on learning Representations, ICLR 2023

作者： Wang, Xinyi Saxon, Michael Li, Jiachen Zhang, Hongyang Zhang, Kun Wang, William Yang Department of Computer Science University of California Santa Barbara United States David R. Cheriton School of Computer Science University of Waterloo Canada Department of Philosophy Carnegie Mellon University United States Machine Learning Department Mohamed bin Zayed University of Artificial Intelligence United Arab Emirates

While machine learning models rapidly advance the state-of-the-art on various real-world tasks, out-of-domain (OOD) generalization remains a challenging problem given the vulnerability of these models to spurious correlations. We propose a balanced mini-batch sampling strategy to transform a biased data distribution into a spurious-free balanced distribution, based on the invariance of the underlying causal mechanisms for the data generation process. We argue that the Bayes optimal classifiers trained on such balanced distribution are minimax optimal across a diverse enough environment space. We also provide an identifiability guarantee of the latent variable model of the proposed data generation process, when utilizing enough train environments. Experiments are conducted on DomainBed, demonstrating empirically that our method obtains the best performance across 20 baselines reported on the benchmark. © 2023 11th International Conference on learning Representations, ICLR 2023. All rights reserved.

关键词： Optimization

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：