检索结果-内蒙古大学图书馆

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Tingyao Li Bin Sheng Dept. Computer Science and Engineering Shanghai Jiao Tong University Shanghai China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Retinal diseases are leading causes of blindness globally. In real-world clinical practice, a patient may suffer from multiple retinal diseases, and these diseases are often under a long-tailed distribution, which poses significant challenges for accurate diagnosis. In this work, we propose a novel contrastive learning(CL)-based framework for multi-label retinal disease recognition. It consists of two parallel branches, a multi-label supervised contrastive learning branch and a classifier branch. The positive sets are created by the extent of proportional label overlap between samples and the anchor in calculating contrastive loss. For minority information enhancement, we design a hybrid-proxy model to generate class-dependent proxies, which are updated alongside the network. We capture rich relations samples, proxies, and labels by introducing the hybrid sample-proxy contrastive loss. Taking both label co-occurrence and data imbalance into consideration, we further utilize Distribution Balanced (DB) binary cross-entropy loss to guide the classifier branch learning. Experimental results on four public retinal disease datasets have demonstrated the superiority and effectiveness of our method.

关键词： Representation learning Heavily-tailed distribution Accuracy Contrastive learning Tail Blindness Retina Bioinformatics Diseases

来源：评论

学校读者我要写书评

暂无评论

Reconnaissance Detection in Decentralised IoT System using Model-Contrastive Federated Learning

Reconnaissance Detection in Decentralised IoT System using M...

引用

International Symposium on Advanced Networks and Telecommunication Systems (ANTS)

作者： Rajdeep Kumar Dutta Bishal Chhetry Rakesh Matam Ferdous Ahmed Barbhuiya Dept. of Computer Science and Engineering Indian Institute of Information Technology Guwahati India

ISBN: (数字)9798350391725

ISBN: (纸本)9798350391732

The detection of reconnaissance attacks is crucial for safeguarding Internet of Things (IoT) environments, which are inherently more vulnerable and resource-constrained compared to traditional computing systems. Traditional centralised detection methods face significant challenges, such as privacy concerns and limited scalability due to the need to aggregate raw data on a central server. These issues become particularly pronounced in IoT environments where devices are diverse and geographically distributed. To address these challenges, we propose ReconGuard, a novel approach leveraging Model Contrastive Federated Learning (MCFL). ReconGuard enables collaborative training across multiple IoT devices without the necessity of sharing raw data, thereby preserving user privacy and enhancing data security. The approach integrates contrastive learning techniques, which improve the model’s ability to discriminate between benign and malicious activities by contrasting positive (similar) and negative (dissimilar) data pairs. Our experimental results demonstrate that the ReconGuard-based detection system provides a scalable and privacy-preserving solution for identifying reconnaissance activities. These activities are often the initial step in more severe cyber threats, such as botnet attacks, which can lead to significant disruption and damage. By effectively detecting reconnaissance activities, ReconGuard enhances the overall cybersecurity framework of IoT environments. This research presents a viable and innovative method for improving cybersecurity in IoT systems, addressing the critical need for scalable, efficient, and privacy-preserving intrusion detection solutions. The use of MCFL in ReconGuard not only mitigates the challenges of data centralisation but also leverages the distributed nature of IoT networks to enhance robustness against cyber threats.

关键词： Training Data privacy Federated learning Scalability Reconnaissance Data models Telecommunications Internet of Things Servers Faces

来源：评论

学校读者我要写书评

暂无评论

Prediction of Alzheimer's Disease using Deep Learning Algorithms

Prediction of Alzheimer's Disease using Deep Learning Algori...

引用

Applied Artificial Intelligence and Computing (ICAAIC), International Conference on

作者： P Praveen Koleti Srilatha Masabathini Sathvika Edulapuram Nishitha Madduri Nikhil Dept. of Computer Science and Artificial Intelligence SR University Warangal India Dept. of Computer Science Engineering SR Engineering College Warangal India

Throughout the world, at least five crore individuals are thought to have the disease of Alzheimer. This Alzheimer's disease is the most well-known and prevalent kind of dementia (AD). Since the modest but significant advancements in Alzheimer's disease (AD) treatment, the diagnostic emphasis has progressively switched to the precise identification of the disease's earliest stage. In numerous attempts at clinical classification, the difficulty of differentiating pre-clinical AD from changes associated with normal aging or developed AD has been recognized. Alzheimer's disease is a neurological and brain disorder that eventually makes it difficult to do even the most fundamental tasks. It gradually destroys memory and thinking skills. It is a neurological degenerative disorder that causes both brain cell shrinkage and degeneration. The most typical reason of dementia is a gradual loss of cognitive ability, behavioral, and social abilities, limiting their capacity to operate independently. It causes both brain cell shrinkage and degeneration. As people live longer, there are more concerns about aging. Damage to brain cells can be avoided with an early diagnosis of this disease. Early detection can considerably slow or stop the growth of this disease because there is no cure for it. To stop the progression of Alzheimer's disease, early detection is essential. As a result, experts can initiate preventive care as soon as possible. They call for prompt and precise Alzheimer's disease detection in its initial and most elusive stages. The only accurate approach for diagnosis is magnetic resonance imaging (MRI) brain imaging, although exams like the Mini-Mental State Examination (Fol stein 1975), or MMSE, are routinely used for earlier diagnosis. The main objective of this research work is to devise a technique for accurately identifying and staging diseases in magnetic resonance imaging (MRI). Deep learning excels at analyzing images and predicting diseases. A growing body o

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of Deep Image Retrieval Models Leveraging Deep Features

A Comparative Study of Deep Image Retrieval Models Leveragin...

引用

Electrical Electronics and Computing Technologies (ICEECT), International Conference on

作者： Ashish Jain Sudeep Varshney Dept. of Computer Science and Engineering SET Sharda University Greater Noida India

ISBN: (数字)9798350378092

ISBN: (纸本)9798350378108

This review investigates how deep learning methods can be utilized for efficient image retrieval based on content. Obtaining accurate images from vast digital collections poses significant challenges, motivating research in CBIR. The effectiveness of these methods varies depending on the dataset’s type and size, with certain algorithms excelling with specific dataset characteristics. An extensive and well-structured review of successful image retrieval techniques is given in this paper. Our primary objective is to evaluate various deep learning models applied by researchers and compare their performance based on the outcome of evaluation matrices. These models encompass CNNs, DBNs, and other deep architectures tailored for image retrieval tasks. By synthesizing insights from this review, researchers can make informed decisions regarding model selection and potentially enhance retrieval performance by leveraging advanced deep learning features. The importance of deep features in image retrieval is the ability to capture complex visual patterns and semantic information that cannot be easily extracted by traditional handcrafted features. With the increasing volume of online images, Image retrieval using deep learning has become crucial for applications like object recognition, image retrieval, and image search engines.

关键词： Deep learning computers Visualization Reviews Image retrieval Semantics Search engines Feature extraction Object recognition Data mining

来源：评论

学校读者我要写书评

暂无评论

Enhancing Synthetic Reduced Nearest-Neighbor with Two-Layer Neural Networks: A Step Forward in Image Classification

Enhancing Synthetic Reduced Nearest-Neighbor with Two-Layer ...

引用

IEEE Workshop on Signal Processing Systems (SIPS)

作者： Azar Alizadeh Mukesh Singhal dept. Electrical Engineering and Computer Science nUniversity of California Merced Merced USA

ISBN: (数字)9798350373752

ISBN: (纸本)9798350373769

Synthetic Reduced Nearest Neighbor (SRNN) models, operating exclusively on synthetic samples or prototypes, represent a significant stride in the field of nearest-neighbor algorithms. Central to this innovation is enhancing the inter-pretability and optimization of the model, achieved through specialized techniques. This study introduces a novel Two-Layer Neural-SRNN model for classification tasks, diverging from traditional Expectation Maximization (EM) methodologies. The TLN-SRNN model significantly advances efficiency and scalability, outperforming traditional methods in speed while maintaining accuracy. Our empirical findings highlight the model's rapid convergence and robust performance across diverse datasets, establishing it as a notable innovation in the field of machine learning.

关键词： Technological innovation Scalability Neural networks Signal processing algorithms Prototypes Machine learning Signal processing Optimization Image classification Convergence

来源：评论

学校读者我要写书评

暂无评论

Inferring Message Flows From System Communication Traces

arXiv

引用

arXiv 2024年

作者： Nadimi, Bardia Zheng, Hao Dept. Computer Science and Engineering University of South Florida Tampa United States

This paper proposes a novel method for automatically inferring message flow specifications from the communication traces of a system-on-chip (SoC) design that captures messages exchanged among the components during a system execution. The inferred message flows characterize the communication and coordination of components in a system design for realizing various system functions, and they are essential for SoC validation and debugging. The proposed method relieves the burden of manual development and maintenance of such specifications on human designers. Our method also uses a new accuracy metric, acceptance ratio, to evaluate the quality of the mined specifications instead of the specification size often used in the previous work, enabling more accurate specifications to be mined. Furthermore, this paper introduces the concept of essential causalities to enhance the accuracy of the message flow mining and accelerate the mining process. The effectiveness of the proposed method is evaluated on both synthetic traces and traces generated from executing several system models in GEM5. In both cases, the proposed method achieves superior accuracies compared to a previous approach. Additionally, this paper includes some practical use cases. Copyright © 2024, The Authors. All rights reserved.

关键词： System-on-chip

来源：评论

学校读者我要写书评

暂无评论

Enhancements to ODXT SSE Scheme: Algorithm Optimization and Leakage Suppression

Enhancements to ODXT SSE Scheme: Algorithm Optimization and ...

引用

Distributed Systems, computer Networks and Cybersecurity (ICDSCNC), International Conference on

作者： Prathit Aswar Syed Taqi Ali Dept. of Computer Science and Engineering Visvesvaraya National Institute of Technology Nagpur India

ISBN: (数字)9798350375442

ISBN: (纸本)9798350375459

A Dynamic SSE (Searchable symmetric encryption) scheme should support updates and keyword searches with outsourced symmetrically encrypted data while minimizing the amount of data revealed to the untrusted server. For this purpose, literature in this field has identified two critical security properties, i.e. forward and backward *** this work, we build upon the previously developed "Oblivious Dynamic Cross Tags" (ODXT) scheme for conjunctive keyword searches, featuring forward and backward privacy. The objective is to improve flexibility in the update operation of the given scheme, solve the open problem of s-term leakage, and perform leakage analysis of the improved scheme. We propose flexODXT, to reduce the time required for individual keyword update operations to a constant instead of linear complexity, and we propose suppODXT, to reduce the s-term leakage, an open problem found in ODXT.

关键词： Privacy Heuristic algorithms Keyword search Distributed databases computer networks Encryption Servers computer security Secure storage Optimization

来源：评论

学校读者我要写书评

暂无评论

A Factor Based Multiple Imputation Approach to Handle Class Imbalance

引用

Procedia computer science 2023年 218卷 103-112页

作者： Pranita Baro Malaya Dutta Borah Dept. of Computer Science and Engineering National Institute of Technology Silchar Silchar-788010 India

Class imbalance and incompleteness are the two most serious problems faced in data science and machine learning when working on real-life datasets. Both of these cases have severe implications on the ability of classification algorithms to make accurate predictions. When a dataset used for training classifiers is both imbalanced as well as incomplete, the traditional approach is to address the missing data first and then handle class imbalance but it could lead to some issues such as overfitting as well as amplification of some errors due to random duplication. In this paper, an alternate factor-based multiple imputation oversampling method (FB-MIO) is proposed to handle class imbalance as well as missing values in the training dataset at the same time. First, a new factor is presented to evaluate the density of missing values belonging to the majority class with respect to the minority class in a particular region. With the help of this factor, an oscillator is developed to guide how imputation based oversampling should be carried out. Then the training set is divided into multiple smaller subsets and used the oscillator to determine whether missing values for the majority class belonging to that subsets should be imputed or not. This would help in preventing exaggerated duplication when not needed. Experiments were carried out on 27 imbalanced datasets after random addition of missing value and the F1 and AUROC scores of FB-MIO were compared to other dataset level resampling methods such as SMOTE, ADASYN, B-SMOTE etc. The effectiveness of the proposed method has been validated after experiments on benchmark datasets and the comparative results are presented in the form of average rank and number of wins.

关键词： class imbalance overfitting oversampling imputation missing value

来源：评论

学校读者我要写书评

暂无评论

Imaging – based Detection of Bone Injuries using Hybrid Models

Imaging – based Detection of Bone Injuries using Hybrid Mod...

引用

International Conference on ent Computing and Control Systems (ICICCS)

作者： Vineela Madireddy Bhagya Lakshmi Medam Sai Vardhan Reddy Manne Navaneeth Yadav Madhugani Dept. Computer Science and Engineering -AI&ML Vignan Institute of Technology and Science Nalgonda India

ISBN: (数字)9798331512088

ISBN: (纸本)9798331512095

Bone fractures are among the most common physical injuries, affecting individuals across all age groups and requiring prompt and precise diagnosis. However, radiologists often face challenges in accurate fracture identification due to variations in image quality and complexity. The present work investigates a robust system for the automatic detection and classification of fractures in X-radiation (X-ray) images. The proposed model integrates Convolutional Neural Networks (CNN) and MobileNet with a hybrid approach that combines MobileNet and Random Forest to improve classification accuracy. The system is designed to be user-friendly, incorporating modules for registration, data processing, and real-time classification of fractures into 11 distinct types, including avulsion fracture, impacted fracture, longitudinal fracture, comminuted fracture, greenstick fracture, oblique fracture, pathological fracture, spiral fracture, and others. Experimental results demonstrate that the hybrid model significantly enhance diagnostic accuracy, underscoring its potential application in medical settings.

关键词： Pathology Accuracy Spirals Computational modeling Bones Real-time systems Convolutional neural networks X-ray imaging Random forests Injuries

来源：评论

学校读者我要写书评

暂无评论

Integrating Artificial Intelligence and Educational Technology for Inclusive and Ethical Education Practices

Integrating Artificial Intelligence and Educational Technolo...

引用

Intelligent Data Communication Technologies and Internet of Things (IDCIoT), International Conference on

作者： Lathika Ilayaraja Yukthika S S Subramani Prabakaran S. Pavithra Dept. of Computer Science and Engineering Chennai Institute of Technology Chennai Tamil Nadu India

ISBN: (数字)9798331527549

ISBN: (纸本)9798331527556

AI and EdTech are transforming education by making it more accessible, personalized, and assessable, even in low and middle income countries (LMICs) facing resource constraints. However, challenges come with unequal access, issues in data privacy, and bias in AI model creations. As AI continues to become more popular, the issue of whether the work made by the students will be original. This paper focuses on the impact of artificial intelligence on learning in both its ethical and practical dimensions while highlighting the themes of inclusivity, fairness, and authenticity. Guidelines and policies for responsible AI in integration will be proposed further, alongside teacher training. Results should depict that this moral framework, policies, and teacher education should aid in ensuring that the implications of AI are positive and fruitful for learning. Ideal AI guidelines would foster an educational system that is inclusive, transparent, and considers uniqueness and innovation.

关键词： Training Ethics Technological innovation Large language models Education Educational technology Learning (artificial intelligence) Internet of Things Artificial intelligence Guidelines

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：