检索结果-内蒙古大学图书馆

A human-in-the-loop method for pulmonary nodule detection in CT scans

Visual Intelligence 2024年第1期2卷 227-239页

作者： Qingjie Zeng Yutong Xie Zilin Lu Yong Xia National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science and EngineeringNorthwestern Polytechnical UniversityXi’an 710072China Australian Institute for Machine Learning The University of AdelaideAdelaide SA 5000Australia

Automated pulmonary nodule detection using computed tomography scans is vital in the early diagnosis of lung *** extensive well-performed methods have been proposed for this task,they suffer from the domain shift issue between training and test *** domain adaptation(UDA)methods provide a promising means to mitigate the domain variance;however,their performance is still limited since no target domain supervision is *** make the pulmonary nodule detection algorithm more applicable in clinical practice and further boost the performance across domains,we propose a human-in-the-loop method in a semi-supervised fashion to enhance the model generalization ability when transferred from source domain to target ***,we first train a detector model on source domain,and then the pre-trained detector is utilized with our proposed uncertainty-guided sample selection scheme(USSS)to find a few target domain samples worth annotating most and obtain their human ***,the annotated and the rest unlabeled target domain samples are used together to refine the pre-trained model via our proposed zoom-in and zoom-out constraint(ZZC)*** evaluate our method on the Nodule Analysis 2016(LUNA16)and TianChi *** results show that our method surpasses recent competitive methods on source domain and also achieves surprising performance on target domain.

关键词： Pulmonary nodule detection Human-in-the-loop Semi-supervised learning Domain adaptation

来源：评论

学校读者我要写书评

暂无评论

External Reliable Information-enhanced Multimodal Contrastive Learning for Fake News Detection 39

External Reliable Information-enhanced Multimodal Contrastiv...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Cao, Biwei Wu, Qihang Cao, Jiuxin Liu, Bo Gui, Jie School of Cyber Science and Engineering Southeast University Nanjing211189 China Key Laboratory of Computer Network and Information of Ministry of Education of China Nanjing211189 China Purple Mountain Laboratories Nanjing210000 China School of Computer Science and Engineering Southeast University Nanjing211189 China Engineering Research Center of Blockchain Application Supervision And Management Southeast University Ministry of Education China

ISBN: (纸本)157735897X

With the rapid development of the Internet, the information dissemination paradigm has changed and the efficiency has been improved greatly. While this also brings the quick spread of fake news and leads to negative impacts on cyberspace. Currently, the information presentation formats have evolved gradually, with the news formats shifting from texts to multimodal contents. As a result, detecting multimodal fake news has become one of the research hotspots. However, multimodal fake news detection research field still faces two main challenges: the inability to fully and effectively utilize multimodal information for detection, and the low credibility or static nature of the introduced external information, which limits dynamic updates. To bridge the gaps, we propose ERIC-FND, an external reliable information-enhanced multimodal contrastive learning framework for fake news detection. ERIC-FND strengthens the representation of news contents by entity-enriched external information enhancement method. It also enriches the multimodal news information via multimodal semantic interaction method where the multimodal constrative learning is employed to make different modality representations learn from each other. Moreover, an adaptive fusion method is taken to integrate the news representations from different dimensions for the eventual classification. Experiments are done on two commonly used datasets in different languages, X (Twitter) and Weibo. Experiment results demonstrate that our proposed model ERIC-FND outperforms existing state-of-the-art fake news detection methods under the same settings. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Industrial IoT Smart Manufacturing Systems based on Cloud Computing Energy Efficiency Analysis using Machine Learning Algorithms 3

Industrial IoT Smart Manufacturing Systems based on Cloud Co...

引用

3rd International Conference on Electronics and Renewable Systems, ICEARS 2025

作者： Chinnasamy, P. Khan, Patan Feridoz Sasikala, C. Swathi, Mavalluru Kumar, M. Prema Yadav, Ajay Kumar Kalasalingam Academy of Research and Education School of Computing Department of Computer Science and Engineering Tamilnadu India Mohan Babu University School of Computing Department of Computer Science and Engineering Andhra Pradesh Tirupati India Dept of Cse Andhra Pradesh Ananthapuramu India Audisankara College of Engineering and Technology Andhra Pradesh India Dept. of Ece Andhra Pradesh Bhimavaram India United Institute of Management Department of Computer Application Prayagraj India

ISBN: (纸本)9798331509675

With open connectivity and emergent computing, the Industrial Internet of Things (IIoT) combined with cloud computing resources provides significant breakthroughs in the field of industrial automation. These developments lead to the evolution of supplemental services, which improve automation in the production and industrial sectors. This research proposes novel technique in smart manufacturing system based on cloud computing with IIoT in energy efficiency using machine learning. Here the smart manufacturing process has been analysed based on IIoT with cloud computing network, where the energy efficiency is analysed using virtual machine-based reinforcement markov chain based linear regression. Experimental analysis has been carried out in terms of latency, energy efficiency, task response time, accuracy. proposed technique obtained 97% of Latency, 95% of Energy efficiency, 98% of Accuracy, 94% of Task response time. © 2025 IEEE.

关键词： Smart manufacturing

来源：评论

学校读者我要写书评

暂无评论

Hyperparameter Optimization of Software Quality Model Using Improvised Genetic Algorithm and EEM 1

Hyperparameter Optimization of Software Quality Model Using ...

引用

1st IEEE International Conference on Advances in Computing, Communication and Networking, ICAC2N 2024

作者： Singh, Rakhi Sharma, Vishnu Kaushik, Neeraj Malhotra, Ritu Rauthan, Hemlata Delhi Institute of Higher Education Department of Computer Application Greater Noida India ITS Engineering College Department Of Computer Science and Engineering Greater Noida India Galgotias College of Engineering and Tehnology Department of Computer Applications Greater Noida India GNIOT Institute of Professional Studies Department of Computer Applications Greater Noida India Delhi Institute of Higher Education Department of Computer Applications Greater Noida India

ISBN: (纸本)9798350356816

Software quality analysis has become one of the topmost concerns in the modern world and requires the massive attention of developers and testers during software development. Software quality analysis is a multidimensional notion and one attribute may not describe the software product's overall quality. Software developer's objective is to build a software product that attains the highest quality which depends on multifarious attributes namely functional suitability, maintainability, etc. However, analysis of software product quality is challenging in both the development and maintenance phases. This research is aimed at hyperparameter optimization of the software quality model using an improvised genetic algorithm and an enhanced ensemble model (EEM) approach. In this research, there has been shown the optimal possibility of software quality model hyperparameter optimization using the modified architecture of genetic algorithm along with EEM. To validate the performance of this suggested approach, PROMISE Repository datasets have been utilized. As a result, this proposed approach achieves all performance metrics very optimal. The evaluated values of accuracy, precision, recall, and F1- score are 99.45%, 98.83%, 97.28%, and 99.37%, respectively. In the future, this approach may be integrated with modified architectures of software quality models for automated software product quality analysis. © 2024 IEEE.

关键词： Software quality

来源：评论

学校读者我要写书评

暂无评论

Supervised and Unsupervised Coupled Generative Adversarial Networks in Multivariate Time Series 4

Supervised and Unsupervised Coupled Generative Adversarial N...

引用

4th International Conference on Information science, Parallel and Distributed Systems, ISPDS 2023

作者： Wang, Qinfen Li, Yifei Xia, Yong School of Computer Science and Engineering Northwestern Polytechnical University Natl. Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Xi'an710072 China

ISBN: (纸本)9798350337181

Generative adversarial networks (GAN) have been successful in demonstrating the efficiency of generative time series. In this paper, we proposed a novel end-to-end supervised and unsupervised coupled generative adversarial networks (SUC-GAN) framework that consists of a gated recurrent unit (GRU) for generating multivariate time series. We test SUC-GAN on three datasets (i.e. Sines, Energy, Stocks) to investigate the efficacy and properties. The preliminary results show the potential power of supervised, unsupervised, and coupled learning for data generation. © 2023 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Efficient net-based deep learning: A deep-fake image detection

Efficient net-based deep learning: A deep-fake image detecti...

引用

Communication, Control and Intelligent Systems (CCIS)

作者： Rohan Singh Dilip Kumar Sharma Praphula Kumar Jain Department of Computer Science and Engineering GLA University Mathura Department of Computer Engineering and Application GLA University Mathura Department of Computer Science and Engineering MITS Gwalior MP

ISBN: (数字)9798331528201

ISBN: (纸本)9798331528218

With the substantial volume of social media data generated daily and the concurrent emergence of powerful multimedia modification techniques, detecting manipulations in photographs and videos has become an important task. This study examines the strength of a deep learning-based efficient net model for detecting manipulation in multimedia images. This study examines the publicly accessible benchmark dataset DFDC to prove its efficiency. We also highlighted the real-world challenges and emerging trends to combat deep-fakes. The research experiment resulted in and confirmed the efficiency of Efficient-Net as it performed well in both the training and testing stages, exhibiting more accuracy and reduced loss. The test accuracy varies between 50 and 95, with epochs spanning from 0 to 10.

关键词： Training Deep learning Accuracy Social networking (online) Image edge detection Streaming media Market research Feature extraction Spatial databases Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Effective Intrusion Detection Model Using Raptor Optimized Deep Convolutional Neural Network

Effective Intrusion Detection Model Using Raptor Optimized D...

引用

2023 IEEE Guwahati Subsection Conference, GCON 2023

作者： Mahanta, Kshyamasagar Maringanti, Hima Bindu Bhale, Pradeepkumar Maharaja Sriram Chandra Bhanja Deo University Department of Computer Application Odisha Mayurbhanj757003 India Indian Institute of Technology Department of Computer Science and Engineering Guwahati Guwahati781039 India

ISBN: (纸本)9798350337785

Malicious behavior in the system must be recognized for ensure security because the occurrence of the intrusions can threaten the valuable data and threatens the quality of the network. An important area of research in network security is network intrusion detection. In recent years the intrusion detection model faced several problems due to low accuracy, data imbalance, lack of optimization and so on. To overcome this issue, in this research, a raptor-optimized deep CNN is used to develop the intrusion detection model, where the occurrence of intrusions is effectively detected. The deep CNN classifier effectively learns the features, and the enabling of the raptor optimization optimizes the weights and bias parameters to enhance the performance of the deep CNN classifier. The raptor optimization improves the classifier convergence time and global search capability, and the enabling of Synthetic Minority Oversampling Technique (SMOTE) resolved the issues of data imbalance, which reduced the complexity of the system. By evaluating the parameters of accuracy, sensitivity, and specificity, the research's superiority is demonstrated, and the suggested raptor-optimized deep CNN classifier achieved values of 96.51%, 90.23%, and 97.71% for dataset 1. The proposed raptor optimization also achieved values of 95.39%, 95.83%, and 95.15% for dataset 2, which is highly efficient compared to other existing methods. © 2023 IEEE.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

An end-to-end repair-based joint training framework for weakly supervised pavement crack segmentation

引用

Multimedia Tools and applications 2025年第16期84卷 16281-16299页

作者： Zhou, Hui Tao, Huanjie Duan, Qianyue Hu, Zhenwu Deng, Yishi School of Computer Science Northwestern Polytechnical University Xi’an710129 China School of Cyberspace Security Northwestern Polytechnical University Xi’an710129 China Engineering Research Center of Embedded System Integration Ministry of Education Xi’an710129 China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Xi’an710129 China

Weakly supervised pavement crack segmentation aims to assign each pixel of pavement surface images a category label (crack or non-crack) using limited annotation information. Most existing methods adopt the multi-stage approach based on the class activation map (CAM), which outputs from a pre-trained crack classification model, to generate the pixel-level pseudo labels, and then train a segmentation model using these pseudo labels. However, these methods have two notable drawbacks: (i) CAM focuses primarily on the most discriminative regions of the image, potentially resulting in an incomplete estimation of crack regions, and (ii) the process of obtaining pixel-level pseudo labels from CAM is complex and may introduce noise. To avoid these issues, we propose an end-to-end repair-based joint training framework for weakly supervised pavement crack segmentation. Specifically, to better guide the model to pay more attention to the repair process of crack regions, we introduce the segmentation loss, which assigns different weights for crack regions and background regions, through the Residual Project Network. Additionally, to alleviate the impact of the domain gap between synthetic and real datasets, we introduce the consistency loss through the joint training paradigm of unpaired data that incorporates both crack and non-crack images into the training process simultaneously. Furthermore, to enable the model to effectively extract local features and reduce the model's computational complexity, we introduce the Lightweight Multi-head Self-attention module. The experiment results on the CRACK500 Dataset, the CFD Dataset, and the AEL Dataset demonstrate that our model achieves better performance than some existing weakly supervised pavement segmentation methods. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Repair

来源：评论

学校读者我要写书评

暂无评论

Instance by Instance: An Iterative Framework for Multi-Instance 3D Registration

引用

IEEE/CAA Journal of Automatica Sinica 2025年第6期12卷 1117-1128页

作者： Yang, Jiaqi Cao, Xinyue Zhang, Xiyu Cheng, Yuxin Qi, Zhaoshuai Quan, Siwen School of Computer Science Northwestern Polytechnical University National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Xi'an710072 China School of Electronic and Control Engineering Chang'an University Xi'an710064 China Shenzhen University MNR Key Laboratory for Geo-Environmental Monitoring of Great Bay Area Shenzhen518060 China

Multi-instance registration is a challenging problem in computer vision and robotics, where multiple instances of an object need to be registered in a standard coordinate system. Pioneers followed a non-extensible one-shot framework, which prioritizes the registration of simple and isolated instances, often struggling to accurately register challenging or occluded instances. To address these challenges, we propose the first iterative framework for multi-instance 3D registration (MI-3DReg) in this work, termed instance-by-instance (IBI). It successively registers instances while systematically reducing outliers, starting from the easiest and progressing to more challenging ones. This enhances the likelihood of effectively registering instances that may have been initially overlooked, allowing for successful registration in subsequent iterations. Under the IBI framework, we further propose a sparse-to-dense correspondence-based multi-instance registration method (IBI-S2DC) to enhance the robustness of MI-3DReg. Experiments on both synthetic and real datasets have demonstrated the effectiveness of IBI and suggested the new state-of-the-art performance with IBI-S2DC, e.g., our mean registration F1 score is 12.02%/12.35% higher than the existing state-of-the-art on the synthetic/real datasets. © 2014 Chinese Association of Automation.

关键词： 3D modeling

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Driven X-ray Classification for Pneumonia Detection Using CNN

Deep Learning Driven X-ray Classification for Pneumonia Dete...

引用

Communication, Control and Intelligent Systems (CCIS)

作者： Sarvagya Saxena Siddhartha Khandelwal Sneha Chaudhary Priyanka Gupta Computer Science Engineering GLA University Vrindavan India Computer Science Engineering GLA University Mathura India Computer Engineering & Application GLA University Mathura India

ISBN: (数字)9798331528201

ISBN: (纸本)9798331528218

Major deaths (55% or 1.5 million) of LRI (Lower Respiratory Infections) are caused due to Pneumococcal pneumonia. LRI is the 5th highest cause of demise as mentioned by the Global Burden of Disease Study 2015. Health organization suffers from a lack of Physicians. A Physician handles so many cases which leads to misdiagnoses. To resolve all these issues we came up with an easy-to-handle, and implemented in health organizations, the CNN model. The main aim of this model is to help the healthcare professionals by providing them with a tool which will help them detect Pneumococcal pneumonia. With the help of this tool, the work strain of a doctor can be reduced. This model is developed without any pre-trained model and for better accuracy, an immense dataset is used. All the X-ray images were pre processed before being introduced to the neural network. Different layers have been used to make the model more precise and make it adaptable for X-ray images under different conditions. The aim is to combine deep learning concepts with healthcare to make a positive and meaningful impact in the healthcare industry.

关键词： Deep learning Adaptation models Pneumonia Accuracy Computational modeling Neural networks Medical services Organizations X-ray imaging Strain

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：