检索结果-内蒙古大学图书馆

Conditional selection with CNN augmented transformer for multimodal affective analysis

CAAI Transactions on Intelligence Technology 2024年第4期9卷 917-931页

作者： Jianwen Wang Shiping Wang Shunxin Xiao Renjie Lin Mianxiong Dong Wenzhong Guo College of Computer and Data Science Fuzhou UniversityFuzhouChina College of Computer and Cyber Security Fujian Normal UniversityFuzhouChina Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou UniversityFuzhouChina Digital Fujian Institute of Big Data Security Technology Fujian Normal UniversityFuzhouChina Department of Sciences and Informatics Muroran Institute of TechnologyMuroranJapan

Attention mechanism has been a successful method for multimodal affective analysis in recent years. Despite the advances, several significant challenges remain in fusing language and its nonverbal context information. One is to generate sparse attention coefficients associated with acoustic and visual modalities, which helps locate critical emotional se-mantics. The other is fusing complementary cross‐modal representation to construct optimal salient feature combinations of multiple modalities. A Conditional Transformer Fusion Network is proposed to handle these problems. Firstly, the authors equip the transformer module with CNN layers to enhance the detection of subtle signal patterns in nonverbal sequences. Secondly, sentiment words are utilised as context conditions to guide the computation of cross‐modal attention. As a result, the located nonverbal fea-tures are not only salient but also complementary to sentiment words directly. Experi-mental results show that the authors’ method achieves state‐of‐the‐art performance on several multimodal affective analysis datasets.

关键词： affective computing data fusion information fusion multimodal approaches

来源：评论

学校读者我要写书评

暂无评论

Redundant Data Detection and Deletion to Meet Privacy Protection Requirements in Blockchain-Based Edge Computing Environment

引用

China Communications 2024年第3期21卷 149-159页

作者： Zhang Lejun Peng Minghui Su Shen Wang Weizheng Jin Zilong Su Yansen Chen Huiling Guo Ran Sergey Gataullin Cyberspace Institute Advanced Technology Guangzhou UniversityGuangzhou 510006China College of Information Engineering Yangzhou UniversityYangzhou 225127China School Math&Computer Science Quanzhou Normal UniversityQuanzhou 362000China Computer Science Department City University of Hong KongHong Kong 999077China School of Computer and Software Nanjing University of Information Science and TechnologyNanjing 21004China Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and TechnologyAnhui UniversityHefei 230601China Department of Computer Science and Artificial Intelligence Wenzhou UniversityWenzhou 325035China Guangzhou University Library Guangzhou UniversityGuangzhou 510006China Central Economic and Mathematics Institute Russian Academy of Sciences MIREA-Russian Technological University Moscow RegionRussia

With the rapid development of information technology,IoT devices play a huge role in physiological health data *** exponential growth of medical data requires us to reasonably allocate storage space for cloud servers and edge *** storage capacity of edge nodes close to users is *** should store hotspot data in edge nodes as much as possible,so as to ensure response timeliness and access hit rate;However,the current scheme cannot guarantee that every sub-message in a complete data stored by the edge node meets the requirements of hot data;How to complete the detection and deletion of redundant data in edge nodes under the premise of protecting user privacy and data dynamic integrity has become a challenging *** paper proposes a redundant data detection method that meets the privacy protection *** scanning the cipher text,it is determined whether each sub-message of the data in the edge node meets the requirements of the hot *** has the same effect as zero-knowledge proof,and it will not reveal the privacy of *** addition,for redundant sub-data that does not meet the requirements of hot data,our paper proposes a redundant data deletion scheme that meets the dynamic integrity of the *** use Content Extraction Signature(CES)to generate the remaining hot data signature after the redundant data is *** feasibility of the scheme is proved through safety analysis and efficiency analysis.

关键词： blockchain data integrity edge computing privacy protection redundant data

来源：评论

学校读者我要写书评

暂无评论

Exploring the Significance of Feature Analysis in AI/ML Modeling 21

Exploring the Significance of Feature Analysis in AI/ML Mode...

引用

21st OITS International Conference on Information Technology, OCIT 2023

作者： Rout, Smriti Mallick, Rishikant Kumar Sahu, Santosh Siksha'O'anusandhan Department of Computer Science Bhubaneswar India Kalinga Institute of Industrial Technology Department of Computer Science Bhubaneswar India Oil and Natural Gas Corporation Geodata Processing and Interpretation Center Dehradun India

ISBN: (纸本)9798350358230

Feature selection (FS) is one of the important tasks of data preprocessing in data analytics. The data with a large number of features will affect the computational complexity, and increase a huge amount of resource usage and time consumption for data analytics. In the era of burgeoning data, the need to streamline datasets for analysis while maintaining predictive accuracy has become paramount. This study presents an investigation into the efficacy of feature selection techniques in reducing the dimensionality of datasets while preserving predictive accuracy. Our primary objective is to curate a subset of relevant attributes from an original dataset and ascertain if the predictive performance remains comparable to the full dataset. Through systematic experimentation and analysis, we aim to illustrate the advantages of this feature selection approach for enhancing the efficiency of datasets. In this study, we will explore various feature selection methods and assess their impact on both computational efficiency and model accuracy. By examining the reduced dataset's ability to produce results akin to those of the complete dataset, we aim to demonstrate the potential benefits of feature selection in optimizing data analysis processes. Our findings are expected to shed light on the practical utility of feature selection techniques and provide insights into their relevance for future data-driven endeavors. This research represents a crucial step towards harnessing the power of reduced, yet effective, datasets in data science and machine learning applications. © 2023 IEEE.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Controlled Causal Hallucinations Can Estimate Phantom Nodes in Multiexpert Mixtures of Fuzzy Cognitive Maps

arXiv

引用

arXiv 2024年

作者： Panda, Akash Kumar Kosko, Bart Signal and Image Processing Institute Department of Electrical and Computer Engineering University of Southern California United States

An adaptive multiexpert mixture of feedback causal models can approximate missing or phantom nodes in large-scale causal models. The result gives a scalable form of big knowledge. The mixed model approximates a sampled dynamical system by approximating its main limit-cycle equilibria. Each expert first draws a fuzzy cognitive map (FCM) with at least one missing causal node or variable. FCMs are directed signed partial-causality cyclic graphs. They mix naturally through convex combination to produce a new causal feedback FCM. Supervised learning helps each expert FCM estimate its phantom node by comparing the FCM's partial equilibrium with the complete multi-node equilibrium. Such phantom-node estimation allows partial control over these causal hallucinations and helps approximate the future trajectory of the dynamical system. But the approximation can be computationally heavy. Mixing the tuned expert FCMs gives a practical way to find several phantom nodes and thereby better approximate the feedback system's true equilibrium behavior. Copyright © 2024, The Authors. All rights reserved.

关键词： Phantoms

来源：评论

学校读者我要写书评

暂无评论

The Role of Generative AI in Deepfake Detection: A Systematic Literature Review

The Role of Generative AI in Deepfake Detection: A Systemati...

引用

International Conference on Smart Business and technology, ICSBT 2024

作者： Acim, Btissam Kharmoum, Nassim Lagmiri, Souad Najoua Ziti, Soumia Department of Computer Science Intelligent Processing & Security of Systems Faculty of Sciences Mohammed V University in Rabat Rabat Morocco Rabat Morocco IT Networking Security and Management Laboratory Higher Institute of Management Administration and Computer Engineering Rabat Morocco

ISBN: (纸本)9783031866975

There is a possibility that deepfakes will increase a great deal of false information in a very realistic way, but it seems that today such technology appears to be extremely dangerous. While generative Artificial Intelligence (AI) does expand possibilities and give an opportunity to achieve terrific outcomes and has innumerable potential uses. This systematic literature review focuses on the role of generative AI in the improvement of deepfake detection technologies, providing a comparison between different methods and assessing their effectiveness. By analyzing recent studies, it depicts the techniques employed most frequently in deepfake detection, such as the ones concentrating on the intricacies between the visual and auditory elements, the temporal domains, as well as any minor signs of alteration. Due to the fact that generative AI is rapidly improving, the methods that are used to detect its use are often inadequate, which calls for more studies on the subject matter. Besides, by combining audio and visual elements when performing the analysis, calling it as a method that can be useful in focusing the detection growth potential with diverse and unstructured data. Also, this study evaluates the advantages and limitations of the techniques existing today and demonstrates their relative effectiveness in controlled and real conditions. Clarifying that measures aimed at detecting AI generated content should be preoccupied with a technique that is able to keep pace with changes in generative AI. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Federated Multi-Phase Curriculum Learning to Synchronously Correlate User Heterogeneity

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第5期5卷 2026-2039页

作者： Wang, Mingjie Guo, Jianxiong Jia, Weijia BNU-HKBU United International College Guangdong Key Lab of AI and Multi-Modal Data Processing Department of Computer Science Zhuhai519087 China Beijing Normal University Advanced Institute of Natural Sciences Zhuhai519087 China BNU-HKBU United International College Guangdong Key Lab of AI and Multi-Modal Data Processing Zhuhai519087 China

Federated learning (FL) is a decentralized learning method used to train machine learning algorithms. In FL, a global model iteratively collects the parameters of local models without accessing their local data. However, a significant challenge in FL is handling the heterogeneity of local data distribution, which often results in a drifted global model that is difficult to converge. To address this issue, current methods employ different strategies, such as knowledge distillation, weighted model aggregation, and multitask learning. These approaches are referred to as asynchronous FL, as they align user models either locally or posthoc, where model drift has already occurred or has been underestimated. In this article, we propose an active and synchronous correlation approach to address the challenge of user heterogeneity in FL. Specifically, our approach aims to approximate FL as standard deep learning by actively and synchronously scheduling user learning pace in each round with a dynamic multiphase curriculum. A global curriculum is formed by an autoregressive autoencoder that integrates all user curricula on the server. This global curriculum is then divided into multiple phases and broadcast to users to measure and align the domain-agnostic learning pace. Empirical studies demonstrate that our approach outperforms existing asynchronous approaches in terms of generalization performance, even in the presence of severe user heterogeneity. © 2023 IEEE.

关键词： Curricula

来源：评论

学校读者我要写书评

暂无评论

Assessing Self-supervised xLSTM-UNet Architectures for Head and Neck Tumor Segmentation in MR-Guided Applications 1st

Assessing Self-supervised xLSTM-UNet Architectures for Head ...

引用

1st Challenge on Head and Neck Tumor Segmentation for MRI-Guided Applications, HNTS-MRG 2024, Held in Conjunction with 27th International Conference on Medical image Computing and computer-Assisted Intervention, MICCAI 2024

作者： Qayyum, Abdul Mazher, Moona Niederer, Steven A. National Heart and Lung Institute Faculty of Medicine Imperial College London London United Kingdom Centre for Medical Image Computing Department of Computer Science University College London London United Kingdom

ISBN: (纸本)9783031832734

Radiation therapy (RT) plays a pivotal role in treating head and neck cancer (HNC), with MRI-guided approaches offering superior soft tissue con- trast and daily adaptive capabilities that significantly enhance treatment preci- sion while minimizing side effects. To optimize MRI-guided adaptive RT for HNC, we propose a novel two-stage model for Head and Neck Tumor Segmenta- tion. In the first stage, we leverage a Self-Supervised 3D Student-Teacher Learn- ing Framework, specifically utilizing the DINOv2 architecture, to learn effec- tive representations from a limited unlabeled dataset. This approach effectively addresses the challenge posed by the scarcity of annotated data, enabling the model to generalize better in tumor identification and segmentation. In the second stage, we fine-tune an xLSTM-based UNet model that is specifically designed to capture both spatial and sequential features of tumor progression. This hybrid architecture improves segmentation accuracy by integrating temporal dependen- cies, making it particularly well-suited for MRI-guided adaptive RT planning in HNC. The model’s performance is rigorously evaluated on a diverse set of HNC cases, demonstrating significant improvements over state-of-the-art deep learning models in accurately segmenting tumor structures. Our proposed solu- tion achieved an impressive mean aggregated Dice Coefficient of 0.81 for pre- RT segments and 0.65 for mid-RT segments, underscoring its effectiveness in automated segmentation tasks. This work advances the field of HNC imaging by providing a robust, generalizable solution for automated Head and Neck Tumor Segmentation, ultimately enhancing the quality of care for patients undergo- ing RT. Our team name is DeepLearnAI (CEMRG). The code for this work is available at https://***/RespectKnowledge/SSL-based-DINOv2_Vision- LSTM_Head-and-Neck-Tumor_Segmentation. © The Author(s) 2025.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

A Two-Stage Self-Supervised Learning Framework for Automated Whole Heart Segmentation in CT and MRI: Addressing Challenges in Cardiac Imaging 1st

A Two-Stage Self-Supervised Learning Framework for Automated...

引用

1st MICCAI Challenge Comprehensive Analysis and Computing of Real-World Medical images, CARE 2024 Held in Conjunction with 27th International Conference on Medical image Computing and computer-Assisted Intervention, MICCAI 2024

作者： Qayyum, Abdul Mazher, Moona Niederer, Steven A. Faculty of Medicine National Heart and Lung Institute Imperial College London London United Kingdom Centre for Medical Image Computing Department of Computer Science University College London London United Kingdom

ISBN: (纸本)9783031870088

Cardiovascular diseases (CVDs) are the leading cause of death worldwide, highlighting the need for precise diagnostic and therapeutic strategies. Whole heart segmentation (WHS) from medical images is vital for understanding cardiac anatomy, assessing disease progression, and guiding treatments. However, WHS poses significant challenges due to the dynamic shape changes of the heart during the cardiac cycle, motion artifacts, low contrast-to-noise ratio, and variability from multi-center data. Additionally, CT and MRI modalities each present unique difficulties: CT provides high spatial resolution but poor soft-tissue contrast, while MRI offers excellent soft-tissue contrast but is prone to artifacts. To address these challenges, we propose a two-stage method. In the first stage, the DINOv2 framework leverages a 3D Vision-LSTM (xLSTM) model for self-supervised learning on the limited, unlabeled WHS++ dataset to overcome the scarcity of annotated data. In the second stage, we fine-tune the model for segmentation by freezing the encoder and optimizing the decoder. Our approach is rigorously evaluated on the WHS++ dataset for both CT and MRI modalities, demonstrating superior performance compared to state-of-the-art deep learning models in accurately segmenting cardiac structures. Our proposed solution achieved an average Dice Coefficient of 0.9414 using CT and 0.8891 using MRI dataset. This work advances the field of cardiac imaging by providing a robust, generalizable solution for automated whole heart segmentation. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： computerized tomography

来源：评论

学校读者我要写书评

暂无评论

Simulated Data for SAR Tomographic Reconstruction in Urban Areas

Simulated Data for SAR Tomographic Reconstruction in Urban A...

引用

2023 International Conference on Earth Observation and Geo-Spatial Information, ICEOGI 2023

作者： Daoud, Ishak Belhadj-Aissa, Saoussen Hocine, Faiza Kourgli, Assia University of Science and Technology Image Processing and Radiation Lab Department of Telecommunication Houari Boumediene Algiers Algeria California Institute of Technology Jet Propulsion Laboratory PasadenaCA United States

ISBN: (纸本)9798350396720

The evaluation of SAR tomographic reconstruction models requires an examination of their robustness with respect to various parameters. Typically, a simple simulation of reflectivity profiles with different scatters at different elevations and SNRs is used to evaluate the robustness of any reconstruction model. However, these simulation setups do not account for most of the geometric acquisition variables present in the reconstruction of real data. Most of the data used for SAR tomographic reconstruction in urban areas are acquired using high-resolution X-band sensors because of their weak penetration, which aids in recovering the geometry of the target. In this work, we propose simulating an urban area acquisition scene that considers the primary acquisition parameters of high-resolution X-band sensors. By doing so, one can simulate various measurements for different building shapes and elevations, providing a more comprehensive evaluation of the reconstruction methods. In this simulation, the geometry of SAR tomography is respected by considering different geometry distortions such as layover, foreshortening, and shadowing. The simulation is evaluated by implementing different reconstruction methods to the simulated data. Results obtained show that sparse reconstruction methods such as 11 and 12 norms and SL1MMER are more suitable to evaluate the reconstruction due to the high-resolution acquisitions. On the other hand, we used other conventional reconstruction models such as SVD-Weiner and MUSIC for assessment purposes. © 2023 IEEE.

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

AutoSketch: Automatic Sketch-Oriented Compiler for Query-driven Network Telemetry 21

AutoSketch: Automatic Sketch-Oriented Compiler for Query-dri...

引用

21st USENIX Symposium on Networked Systems Design and Implementation, NSDI 2024

作者： Sun, Haifeng Huang, Qun Sun, Jinbo Wang, Wei Li, Jiaheng Li, Fuliang Bao, Yungang Yao, Xin Zhang, Gong National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University China Institute of Computing Technology CAS China Northeastern University China Huawei Theory Department

ISBN: (纸本)9781939133397

Recent network telemetry witnesses tremendous progress in two directions: query-driven telemetry that targets expressiveness as the primary goal, and sketch-based algorithms that address resource-accuracy trade-offs. In this paper, we propose AutoSketch that aims to integrate the advantages of both classes. In a nutshell, AutoSketch automatically compiles high-level operators into sketch instances that can be readily deployed with low resource usage and incur limited accuracy drop. However, there remains a gap between the expressiveness of high-level operators and the underlying realization of sketch algorithms. AutoSketch bridges this gap in three aspects. First, AutoSketch extends its interface derived from existing query-driven telemetry such that users can specify the desired telemetry accuracy. The specified accuracy intent will be utilized to guide the compiling procedure. Second, AutoSketch leverages various techniques, such as syntax analysis and performance estimation, to construct efficient sketch instances. Finally, AutoSketch automatically searches for the most suitable parameter configurations that fulfill the accuracy intent with minimum resource usage. Our experiments demonstrate that AutoSketch can achieve high expressiveness, high accuracy, and low resource usage compared to state-of-the-art telemetry solutions. © 2024 Proceedings of the 21st USENIX Symposium on Networked Systems Design and Implementation, NSDI 2024. All rights reserved.

关键词： Economic and social effects

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：