检索结果-内蒙古大学图书馆

GMTS: GNN-based multi-scale transformer siamese network for remote sensing building change detection

International Journal of Digital Earth 2023年第1期16卷 1685-1706页

作者： Xinyang Song Zhen Hua Jinjiang Li School of Infomation and electronic engineering Shandong Technology and Business UniversityInstitute of Network Technology(ICT)YantaiPeople's Republic of China School of Computer Science and Technology Shandong Technology and Business UniversityYantaiPeople's Republic of China

With the remarkable success of change detection(CD)in remote sensing images in the context of deep learning,many convolutional neural network(CNN)based methods have been *** the current research,to obtain a better context modeling method for remote sensing images and to capture more spatiotemporal characteristics,several attention-based methods and transformer(TR)-based methods have been *** research has also continued to innovate on TR-based methods,and many new methods have been *** of them require a huge number of calculation to achieve good ***,using the TR-based mehtod while maintaining the overhead low is a problem to be ***,we propose a GNN-based multi-scale transformer siamese network for remote sensing image change detection(GMTS)that maintains a low network overhead while effectively modeling context in the spatiotemporal *** also design a novel hybrid backbone to extract *** with the current CNN backbone,our backbone network has a lower overhead and achieves better ***,we use high/low frequency(HiLo)attention to extract more detailed local features and the multi-scale pooling pyramid transformer(MPPT)module to focus on more global features ***,we leverage the context modeling capabilities of TR in the spatiotemporal domain to optimize the extracted *** have a relatively low number of parameters compared to that required by current TR-based methods and achieve a good effect improvement,which provides a good balance between efficiency and performance.

关键词： Remote sensing(RS) change detection(CD) depthwise over-parameterized convolutional(DO-Conv) attention mechanism transformer graph convolution

来源：评论

学校读者我要写书评

暂无评论

Cardiovascular Disease Prediction with Convolutional Neural networks and Hyperparameter Tuning 8th

Cardiovascular Disease Prediction with Convolutional Neural ...

引用

8th International Conference on Information System Design and Intelligent Applications, ISDIA 2024

作者： Hossain, Mohammad Alamgir Metwally, Abdelnasser Abdelwakil Khan, Asif Ali Amin, Sherif Tawfik Hamdan, Alfadil Ahmed Limkar, Suresh Department of Computer Science College of Engineering and Computer Science Jazan University Jazan Saudi Arabia Department ofComputer Science College of Engineering and Computer Science Jazan University Jazan Saudi Arabia Department ofComputer and Network Engineering College of Engineering and Computer Science Jazan University Jazan Saudi Arabia Department of Artificial Intelligence & Data Science AISSMS Institute of Information Technology Maharashtra Pune India

ISBN: (纸本)9789819765805

CVD continues to pose a substantial global health burden, demanding the need for the creation of precise predictive models that can aid in the timely identification and evaluation of risks. This research paper aims to provide a thorough examination of the prediction of CVD by utilizing CNN in aggregation with hyperparameter tuning techniques. This paper examines the effectiveness of three widely recognized CNN architectures, namely ResNet, VGGNet, and Xception CVD. The Tree-structured Parzen Estimator (TPE) is utilized as a method for tuning hyperparameters in order to optimize the CNN models. The study commences with a comprehensive examination of the dataset, encompassing a wide array of cardiovascular CT image data. The chosen CNN architectures serve as the fundamental framework for our predictive models. The selection of these architectures is based on their established track record in effectively addressing image analysis tasks and their capacity to accurately capture complex patterns and features present in medical images. The models undergo training using a dataset in order to acquire knowledge about distinctive features that are linked to various cardiovascular conditions. The experimental findings presented in the study indicate that the utilization of the Xception architecture, in aggregation with TPE for hyperparameter optimization, yields the most favorable predictive accuracy. Specifically, the achieved accuracy rate of 98.26% is notably remarkable. This result highlights the significance of not only choosing advanced CNN architectures but also optimizing their hyperparameters to fully exploit their potential in predicting cardiovascular disease. This establishes it as a promising tool for the early diagnosis and risk assessment of CVD. This study establishes a fundamental basis for future investigations in the advancement of precise and dependable predictive models applicable to various medical imaging contexts. © The Author(s), under exclusive license

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Semantic-Aware Pseudo-Labeling for Unsupervised Meta-Learning

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年第7期47卷 5475-5488页

作者： Ouyang, Tianran Dong, Xingping Ye, Mang Du, Bo Shao, Ling Shen, Jianbing Wuhan University School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan430072 China University of Chinese Academy of Sciences UCAS-Terminus AI Lab Beijing101408 China University of Macau State Key Laboratory of Internet of Things for Smart City Department of Computer and Information Science 314100 China

In unsupervised meta-learning, the clustering-based pseudo-labeling approach is an attractive framework, since it is model-agnostic, allowing it to synergize with supervised algorithms to learn from unlabeled data. However, the pseudo-labels suffer from clustering noise and semantic chaos problems, further impacting the effectiveness of meta-learning. In this paper, we analyze and optimize the pseudo-labeling process, including encoding and clustering, aiming to generate semantic-like pseudo-labels to narrow the gap between unsupervised and supervised meta-learning. First, during the encoding, we observe that the embedding space of existing methods lacks clustering-friendly properties, which is the primary reason for clustering noise. To address this issue, we minimize the inter-to-intra-class similarity ratio to generate clustering-friendly embedding features and validate our approach through comprehensive experiments. Then, during the clustering, we find that the semantic quality of pseudo-labels is not adequately controlled, resulting in semantic chaos of pseudo-labels. We propose a semantic-stability index to measure the semantic quality of pseudo-labels quantitatively. Based on this index, we propose the Semantic-aware Pseudo-label Reassignment mechanism to generate semantic-like pseudo-labels for all samples. Our approach is model-agnostic and can easily be integrated into existing supervised methods. To demonstrate its generalization ability, we integrate it into two representative algorithms: MAML and EP. The results on three main few-shot benchmarks clearly show that the proposed method achieves significant improvement compared to state-of-the-art models. Notably, our approach also outperforms the corresponding supervised method in three tasks. © 1979-2012 IEEE.

关键词： Latent semantic analysis

来源：评论

学校读者我要写书评

暂无评论

Developing Real-World Applications with Algorithmic Intelligence in Reinforcement Learning for Robotics 2

Developing Real-World Applications with Algorithmic Intellig...

引用

2nd IEEE International Conference on Trends in Quantum Computing and Emerging Business Technologies, TQCEBT 2024

作者： Bhanumathi, M. Sangeetha, M. Harin Fernandez, F. Mary Ganesh Ramachandran, A. Saravanan, S.K. Chennai India Department of Computer Engineering University of Technology and Applied Sciences Nizwa Oman Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai India Department of Computer Science Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai India Department of Computers Science and Engineering BigData and Network Security Saveetha School of Engineering Simats Tamil Nadu Chennai India

ISBN: (纸本)9798350384277

In the study, three leading reinforcement learning algorithms Deep Q-network (DQN), Proximal Policy Optimization (PPO) and Asynchronous Advantage Actor - Critic (A3Cc are applied in a number of real-world robotics tasks. The focus of our analysis is on performance indicators, computational efficiencies across multiple environments as well with respect to customer satisfaction rating. The DQN demonstrated good performance, with the success rate of up to 85% in object manipulation tasks and confirmed its reliability under controlled lab conditions where it made only a 5 percent error. PPO excelled in autonomous navigation (82%) and was the most energy-efficient option, requiring just 10 hours for training and using only twelve KWH of power. Compared with A3C, the method performed to a higher level of adaptability and robustness, especially in object manipulation (90% success rate) and dynamic environments (10% error rates applicable for outdoor variable weather conditions). But A3C was also the most automatable, which required 15 hours to train and consumed an astonishing amount of electricity - 18 kWh. Regarding customer satisfaction, PPO performs the best in end-user rating on user interface;A3C shows a preference with engineers due to its advanced features and flexibility. The focus of this study is significant trade-offs between performance, efficiency and user preference in real robotics applications that advocate for individual tailoring selections as well as deployments based on task specifics nature. © 2024 IEEE.

关键词： Customer satisfaction

来源：评论

学校读者我要写书评

暂无评论

Advancements in Object Detection for Accurate and Efficient Visual Recognition Using Machine Learning 2

Advancements in Object Detection for Accurate and Efficient ...

引用

2nd IEEE International Conference on Advances in Information Technology, ICAIT 2024

作者： Fernandez, F. Mary Harin Ramachandran, A. Ganesh Saravanan, S.K. Bhanumathi, M. Sangeetha, M. Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai India Department of Computer Science Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai India Department of Computers Science and Engineering BigData and Network Security Saveetha School of Engineering SIMATS Tamil Nadu Chennai India Chennai India Computer Engineering Department University of Technology and Applied Sciences Nizwa Oman

ISBN: (纸本)9798350383867

Object detection in images and videos is a vital task in computer vision where its application goes beyond the automobile driving and surveillance, to healthcare. The paper introduces an object detection model which is specific and powerful, that is able to recognize visually with machine learning. The framework is constructed on the basis of the recent innovations in deep learning and attentive mechanisms, which not only lead to the best performance in object detection today but also guarantee the widest applicability. Using an extensive experiment which reveals the described model superiority over the current state-of-the-art algorithms by evaluating mAP indices, whereas the latter has a normal complexity. The ablation study uncovers the impact of core parameters including attention mechanisms and semi-supervised techniques, underlining their importance in the growth of detection precision. Moreover, the illustrative comparison of outcomes from detecting objects on the framework calls for attention to the capacity of the networks to objectify in different categories. Our outcome also suggest that although the proposed framework has a human-level performance in task of object detection there is still a scope to enhance their performance above the human level. Summarizing, this work concludes the conversation and can be considered in the progress of research developments of the object detection systems aimed at practical object meeting situations. © 2024 IEEE.

关键词： computer Vision Deep Learning Machine Learning Object Detection Visual Recognition

来源：评论

学校读者我要写书评

暂无评论

Contextualized and Personalized Math Word Problem Generation Using GPT and Authentic Contextual Recognition 12

Contextualized and Personalized Math Word Problem Generation...

引用

12th International Conference on Information and Education Technology, ICIET 2024

作者： Hwang, Wu-Yuin Utami, Ika Qutsiati National Dong Hwa University Graduate Institute Of Network Learning Technology National Central University Department Of Computer Science And Information Engineering Taiwan Graduate Institute Of Network Learning Technology National Central University Taoyuan Taiwan Universitas Airlangga Faculty Of Advanced Technology And Multidiscipline Indonesia

ISBN: (纸本)9798350371772

This paper introduced an interactive system for generating contextualized and personalized mathematic word problems (MWP) from authentic contexts using the Generative Pre-trained Transformers (GPT). Our proposed Automatic Question Generation (AQG) system comprises (1) the authentic contextual information acquisition through image recognition by TensorFlow and augmented reality (AR) measurement through AR Core, (2) a personalized mechanism based on instructional prompts to generate three difficulty levels for learner's different needs, and (3) MWP generation through GPT with authentic contextual information and personalized needs. A quasi-experiment was conducted by recruiting 51 fifth-grade students to evaluate the effectiveness of the proposed AQG on their geometry learning performance. The results revealed that students who learned with the proposed AQG outperformed students who learned with a decontextualized way on geometry learning performances. Therefore, our proposed AQG is useful for promoting mathematic problem-solving activity in an authentic context. © 2024 IEEE.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Opinions Are Not Always Positive: Debiasing Opinion Summarization With Model-Specific and Model-Agnostic Methods 30

Opinions Are Not Always Positive: Debiasing Opinion Summariz...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Zhang, Yanyue Lai, Yilong Wang, Zhenglin Li, Pengfei Zhou, Deyu He, Yulan School of Computer Science and Engineering Key Laboratory of Computer Network and Information Integration Ministry of Education Southeast University China Department of Informatics King's College London United Kingdom The Alan Turing Institute United Kingdom

ISBN: (纸本)9782493814104

As in the existing opinion summary data set, more than 70% are positive texts, the current opinion summarization approaches are reluctant to generate the negative opinion summary given the input of negative opinions. To address such sentiment bias, two approaches are proposed through two perspectives: model-specific and model-agnostic. For the model-specific approach, a variational autoencoder is proposed to disentangle the input representation into sentiment-relevant and sentiment-irrelevant components through adversarial loss. Therefore, the sentiment information in the input is kept and employed for the following decoding which avoids interference of content information with emotional signals. To further avoid relying on some specific opinion summarization frameworks, a model-agnostic approach based on counterfactual data augmentation is proposed. A dataset with a more balanced emotional polarity distribution is constructed using a large pre-trained language model based on some pairwise and mini-edited principles. Experimental results show that the sentiment consistency of the generated summaries is significantly improved using the proposed approaches, while their semantics quality is unaffected. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A New Method for Predefined-Time Synchronization Control of Memristive Cohen-Grossberg Neural networks

A New Method for Predefined-Time Synchronization Control of ...

引用

2023 IEEE International Conference on Memristive Computing and Applications, ICMCA 2023

作者： Liu, Aidi Yu, Wenyue Huang, Lili Guo, Jian Lei, Tengfei Zhao, Hui School of Computer and Information Engineering Qilu Institute of Technology Jinan China School of Computer and Information Engineering Qilu Institute of Technology China Collaborative Innovation Center of Memristive Computing Application School of Computer and Information Engineering Qilu Institute of Technology China School of Information Science and Engineering University of Jinan Shandong Provincial Key Laboratory of Network Based Intelligent Computing Jinan China

ISBN: (纸本)9798350316230

This article mainly conducts a series of research on the synchronization control of Cohen-Grossberg neural networks. Firstly, a memristive Cohen-Grossberg neural network model with time-varying delay was constructed, and an equivalent system was obtained by combining inverse function theory, differential inclusion, and set-valued mapping. Secondly, a new predefined-time stability theorem was proposed, and sufficient conditions were obtained to ensure that the drive-response system achieves predefined-time synchronization by designing appropriate control strategy. The simulation results show that the stability time of the error system can be adjusted by the user, verifying the correctness and of the theory. © 2023 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Predicting the Unseen: A Novel Dataset for Hidden Intention Localization in Pre-abnormal Analysis 24

Predicting the Unseen: A Novel Dataset for Hidden Intention ...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Qi, Zehao Zhang, Ruixu Hu, Xinyi Liu, Wenxuan Wang, Zheng National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Wuhan University Hubei Key Laboratory of Multimedia and Network Communication Engineering School of Computer Science Wuhan China School of Computer Science and Artificial Intelligence Wuhan University of Technology Wuhan China

ISBN: (纸本)9798400706868

Our paper introduces a novel video dataset specifically for Temporal Intention Localization (TIL), aimed at identifying hidden abnormal intention in densely populated and complex environments. Traditional Temporal Action Localization (TAL) frameworks, focusing on overt actions within constrained temporal intervals, often miss subtle pre-abnormal actions that unfold over extended periods. Our dataset comprises 228 videos with 5790 clips, each annotated to capture fine-grained actions within ambiguous temporal boundaries using the Joint-Linear-Assignment methodology. This approach enables detailed analysis of the evolution of abnormal intention over time. To detect subtle, hidden intention, we developed the Intention-Action Fusion module, an creative approach integrating dynamic feature fusion across 11 behavioral subcategories, significantly enhancing the model's ability to discern nuanced intention. This enhancement has led to performance improvements of up to 139% in specific scenarios, dramatically boosting the model's sensitivity and interpretability, crucial for advancing proactive surveillance systems. By pushing the boundaries of technology, our dataset and methodologies foster proactive surveillance systems capable of preemptively identifying potential threats from nuanced behavioral patterns, encouraging further exploration into the complexities of intention beyond observable actions. The dataset is available at https://***/Zzz99999/Hidden-Abnormal-Intention. © 2024 ACM.

关键词： Security systems

来源：评论

学校读者我要写书评

暂无评论

Outbreak prediction of COVID-19 using Recurrent neural network with Gated Recurrent Units

引用

Materials Today: Proceedings 2023年 80卷 3433-3437页

作者： Natarajan, Sathish Kumar, Mohit Gadde, Sai Kiran Kumar Venugopal, Vijay Cognizant Technology Solutions Chennai India Department of Computer Science and Engineering University Institute of Engineering Chandigarh University Punjab Mohali India Senior Data Developer Flagstar Bank Troy Michigan United States Network Consultant Cisco Systems China

Respiratory infections corona virus 2-caused inflammatory disorders are CORONAVIRUS DISEASE 2019 (COVID-19) (SARS-CoV-2). A serious corona virus acute disease arose in 2019. Wuhan, China, was the first location to find the virus in December 2019, which has now been spreading all over the world. Recurrent neural networks, together with the use of LSTMs, fail to provide solutions to numerous issues (RNNs). So this paper has proposed RNN with Gated Recurrent Units for the COVID-19 prediction. This paper utilizes system, which was developed to assist nations (the Czech Republic, the United States, India, and Russia) combat the early stages of a newly emerging infection. For instance, the system tracks confirmed and reported cases, and monitors cures and deaths on a daily basis. This was done to allow the relevant parties to have an early grasp of the disastrous damage the lethal virus will bring. The implemented is an ensemble approach of RNN and GRU that work has computed the RMSE value for the different cases such as infected, cure and death across the four different countries. © 2021

关键词： Viruses

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：