检索结果-内蒙古大学图书馆

Unsupervised Nonlinear Adaptive Manifold Learning for Global and Local information

Tsinghua Science and technology 2021年第2期26卷 163-171页

作者： Jiajun Gao Fanzhang Li Bangjun Wang Helan Liang School of Computer Science and Technology Soochow UniversitySuzhou 215006China Joint International Research Laboratory of Machine Learning and Neuromorphic Computing Provincial Key Laboratory for Computer Information Processing TechnologySoochow UniversitySuzhou 215006China

In this paper,we propose an Unsupervised Nonlinear Adaptive Manifold Learning method(UNAML)that considers both global and local *** this approach,we apply unlabeled training samples to study nonlinear manifold features,while considering global pairwise distances and maintaining local topology *** method aims at minimizing global pairwise data distance errors as well as local structural *** order to enable our UNAML to be more efficient and to extract manifold features from the external source of new data,we add a feature approximate error that can be used to learn a linear ***,we add a feature approximate error that can be used to learn a linear *** addition,we use a method of adaptive neighbor selection to calculate local structural *** paper uses the kernel matrix method to optimize the original *** algorithm proves to be more effective when compared with the experimental results of other feature extraction methods on real face-data sets and object data sets.

关键词： unsupervised manifold learning global and local information,adaptive neighbor selection method kernel matrix

来源：评论

学校读者我要写书评

暂无评论

FreqBlender: Enhancing DeepFake Detection by Blending Frequency Knowledge 38

FreqBlender: Enhancing DeepFake Detection by Blending Freque...

引用

38th Conference on Neural information processing Systems, NeurIPS 2024

作者： Li, Hanzhe Zhou, Jiaran Li, Yuezun Wu, Baoyuan Li, Bin Dong, Junyu School of Computer Science and Technology Ocean University of China China School of Data Science The Chinese University of Hong Kong Shenzhen China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China

Generating synthetic fake faces, known as pseudo-fake faces, is an effective way to improve the generalization of DeepFake detection. Existing methods typically generate these faces by blending real or fake faces in spatial domain. While these methods have shown promise, they overlook the simulation of frequency distribution in pseudo-fake faces, limiting the learning of generic forgery traces in-depth. To address this, this paper introduces FreqBlender, a new method that can generate pseudo-fake faces by blending frequency knowledge. Concretely, we investigate the major frequency components and propose a Frequency Parsing Network to adaptively partition frequency components related to forgery traces. Then we blend this frequency knowledge from fake faces into real faces to generate pseudo-fake faces. Since there is no ground truth for frequency components, we describe a dedicated training strategy by leveraging the inner correlations among different frequency knowledge to instruct the learning process. Experimental results demonstrate the effectiveness of our method in enhancing DeepFake detection, making it a potential plug-and-play strategy for other methods. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Variable-order fractional derivative rutting depth prediction of asphalt pavement based on the RIOHTrack full-scale track

引用

Science China(information Sciences) 2023年第5期66卷 196-214页

作者： Yu WANG Jiaojiao YAN Wei HUANG Leszek RUTKOWSKI Jinde CAO School of Mathematics Southeast University Jiangsu Provincial Key Laboratory of Networked Collective Intelligence Southeast University Intelligent Transportation System Research Center Southeast University Systems Research Institute of the Polish Academy of Sciences Institute of Computer Science AGH University of Science and Technology Information Technology Institute University of Social Sciences Yonsei Frontier Lab Yonsei University

Rutting deformation is typical damage to asphalt pavement and can be quantitatively described as the time-varying mechanical deformation feature of the asphalt mixture during the creep process. First,a nonlinear viscoelastic creep model is established based on the Caputo variable-order fractional *** fractional order in this model is not fixed and is defined as a time-varying function. The time-dependent mechanical properties of asphalt mixtures are efectively reflected. Based on the modified Burgers model, the variable-order function is revised to a linear form. Second, the variable-order fractional Burgers rutting model is obtained by fitting the test data of the RIOHTrack full-scale track. The Levenberg-Marquardt optimization algorithm is used to analyze the test data and the corresponding parameters to obtain more accurate and applicable variable-order fractional rutting mechanics and empirical models for diferent asphalt pavement structures. Finally, according to the classification of the pavement structure, structures III and VI are taken as examples. The rutting prediction and comparison results of several representative pavement structures are obtained to verify that the proposed rutting prediction model can also accurately predict all road sections of RIOHTrack. The new model is also compared with the rutting model of the mechanistic-empirical pavement design guide, the fractional-order Burgers rutting model, and the modified Burgers rutting model. The fitting results are evaluated using the determination coefficient R2. The results show that the variable-order fractional Burgers rutting model proposed in this study exhibits a better fit and is more applicable to describe the rutting deformation of asphalt pavement.

关键词： RIOHTrack full-scale track Caputo fractional derivative variable-order fractional modified Burgers model rutting prediction

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Intelligence Learning Based on Bounded Rationality in IoMT Systems: A Case Study in Parkinson's Disease

引用

IEEE Transactions on Computational Social Systems 2023年第4期10卷 1607-1621页

作者： Zhang, Chao Ding, Juanjuan Zhan, Jianming Sangaiah, Arun Kumar Li, Deyu Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education Shanxi University School of Computer and Information Technology Taiyuan030006 China Hubei Minzu University School of Mathematics and Statistics Enshi445000 China International Graduate Institute of Artificial Intelligence National Yunlin University of Science and Technology Douliou64002 Taiwan Lebanese American University Department of Electrical and Computer Engineering Byblos1102-2801 Lebanon

As a cause of interfering with routine activities, freezing of gait (FOG) is a severe syndrome of Parkinson's disease (PD) and usually performs as an abrupt and momentary inability to effective stepping forward. Advanced wearable acceleration sensors based on socially implemented Internet of medical things (IoMT) devices can remotely provide a platform for recognizing FOG. However, due to the diverse data acquisition modes that appear in classic IoMT devices, the obtained data may contain imprecise, hesitant, and incomplete ones. Meanwhile, the bounded rationality owned by neurologists usually has a big impact on using wearable acceleration sensors to predict illnesses. Therefore, the objective of this article lies in exploring a fuzzy intelligence learning approach based on bounded rationality in IoMT systems and providing a valid scheme for biomedical data analysis. Specifically, a brand-new three-way group decision-making approach by means of TODIM (an acronym in Portuguese for interactive multicriteria decision-making) with incomplete dual hesitant fuzzy (DHF) information and its applications in detecting FOG in PD using IoMT devices are systematically explored. First, taking advantage of DHF sets (DHFSs) when depicting realistic group decision information, the concept of multigranulation (MG) incomplete DHF information systems is built. Second, adjustable MG DHF probabilistic rough sets (PRSs) are further put forward via DHF similarity relations. Third, a three-way group decision-making approach is constructed by virtue of adjustable MG DHF PRSs and TODIM. Finally, the validity, effectiveness, and practicality of the constructed three-way group decision-making approach are investigated by a University of California, Irvine (UCI) dataset with several experimental analyses in the background of FOG detection in PD using IoMT devices. The experimental result indicates that the developed fuzzy intelligence learning approach achieves reasonable diagnostic conclusions

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Interference Suppression and Jitter Elimination Ability-Based Adaption Tracking Guidance for Robotic Fishes

引用

IEEE/CAA Journal of Automatica Sinica 2025年第1期12卷 126-137页

作者： Dongfang Li Jie Huang Rob Law Xin Xu Limin Zhu Edmond Q.Wu IEEE the School of Electrical Engineering and Automation Fuzhou University the Key Laboratory of System Control and Information Processing Ministry of Education the School of Electrical Engineering and Automation Fuzhou University 5G+Industrial Internet Institute Fuzhou University the University of Macau the College of Mechatronics and Automation National University of Defense Technology the School of Mechanical Engineering Shanghai Jiao Tong University the Department of Computer Science and Engineering Shanghai Jiao Tong University

This work presents an adaptive tracking guidance method for robotic fishes. The scheme enables robots to suppress external interference and eliminate motion jitter. An adaptive integral surge line-of-sight guidance rule is designed to eliminate dynamics interference and sideslip issues. Limited-time yaw and surge speed observers are reported to fit disturbance variables in the model. The approximation values can compensate for the system's control input and improve the robots' tracking ***, this work develops a terminal sliding mode controller and third-order differential processor to determine the rotational torque and reduce the robots' run jitter. Then, Lyapunov's theory proves the uniform ultimate boundedness of the proposed method. Simulation and physical experiments confirm that the technology improves the tracking error convergence speed and stability of robotic fishes.

关键词： Adaptive integral surge line-of-sight approximation robotic fish speed observer

来源：评论

学校读者我要写书评

暂无评论

Scheduling Algorithm for Low Energy Consumable Parallel Task Application Based on DVFS 1

引用

7th International Conference on Smart Computing and Communication, SmartCom 2022

作者： Liu, Xun Zhao, Hui College of Computer Science and Technology Wuhan University of Science and Technology Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System Wuhan China Henan University Kaifeng475000 China

ISBN: (数字)9783031281242

ISBN: (纸本)9783031281235

With the continuous improvement of various high-performance computing systems, various data centers had also been fully expanded. Energy consumption and actual performance measurement were very important indicators, which were also key issues in how to judge parallel calls for some tasks in high-performance computer systems. Modern processors were basically equipped with software control functions such as DVFS (Dynamic Voltage Frequency Scaling), in the actual system operation to ensure that the system could ensure the reasonable operation of the system while reducing energy consumption indicators. This paper considered how the designed scheduling algorithm first divides tasks reasonably to ensure that the maximum completion time and energy consumption of the processor were sufficiently reduced when the directed acyclic graph was executed. Then considered making reasonable adjustments to the processor frequency using DVFS technology to adapt to the task while ensuring the critical path of the task. At the end of the article, make sure that the experimental verification algorithm could ensure that the task was completed and could reduce the energy consumption during task execution as much as possible. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Dual Fusion Network for Hyperspectral Semantic Segmentation 12th

Dual Fusion Network for Hyperspectral Semantic Segmentation

引用

12th International Conference on Image and Graphics, ICIG 2023

作者： Ding, Xuan Gu, Shuo Yang, Jian PCA Laboratory Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Jiangsu Key Laboratory of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China

ISBN: (纸本)9783031463075

With the development of imaging technology, it becomes increasingly easy to obtain hyperspectral images (HSI) containing rich spectral information. The application of hyperspectral images in autonomous driving is expected to become a reality. Hyperspectral images have higher dimensions and more information than RGB images, which brings the challenge of training with limited samples. It is not easy to train satisfactory semantic segmentation models directly from hyperspectral images. In this paper, we propose a hyperspectral dual-fusion (hyperDF) network that can fully utilize the pre-training knowledge of the RGB modality to improve the performance of hyperspectral semantic segmentation. Specifically, we generate pseudo-color images from hyperspectral images to simulate RGB signals in order to make better use of the pre-trained RGB semantic segmentation models. The pseudo-color and hyperspectral images are processed in a dual encoder structure and then fused through a channel-wise attention fusion module. Finally, a multi-scale decoder injected with low-level features is used to predict the semantic segmentation results. Experimental results on the Hyperspectral City V2.0 dataset show that our method achieves state-of-the-art results, with a mIoU of 51.68%. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Offloading Algorithm for Edge Computing Tasks Based on Energy Optimization 8

Offloading Algorithm for Edge Computing Tasks Based on Energ...

引用

8th IEEE International Conference on Smart Cloud, SmartCloud 2023

作者： Gao, Xing Gu, Haonan Liu, Fang Hu, Wei Wuhan City College Wuhan China College of Computer Science and Technology Wuhan University of Science and Technology Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan China

ISBN: (纸本)9798350313505

Current research in computation offloading encompasses various aspects, including task partitioning and allocation, resource management, communication, and data management. This paper focuses on developing new algorithms and techniques to enhance the efficiency and effectiveness of the offloading process while addressing challenges arising from dynamic and heterogeneous mobile environments. Researchers are also examining the trade-off between offloading benefits like improved performance and energy efficiency, and the associated overhead costs such as communication and data management. This paper proposes an optimization strategy for computational offloading to enhance the Grey Wolf algorithm. The solution aims to quickly optimize system energy consumption while considering the arithmetic power constraint of the mobile edge computing server and time delay constraints. Simulation experiments demonstrate that the algorithm in this paper significantly outperforms the traditional Grey Wolf and PSO algorithms in terms of both performance and computational speed. ©2023 IEEE.

关键词： information management

来源：评论

学校读者我要写书评

暂无评论

Implicit Learning of Rotational Decoupling Detection Heads Applied to Remote Sensing Object Detection

Implicit Learning of Rotational Decoupling Detection Heads A...

引用

2023 Asia-Pacific Conference on Image processing, Electronics and computers, IPEC 2023

作者： Song, Chengkun Ding, Sheng Chen, Yingying School of Computer Science and Technology Wuhan University of Science and Technology Wuhan China Hubei Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan China Kagoshima University Kagoshima Japan

ISBN: (纸本)9781665457033

Remote sensing image features complicated background, big image size, small object pixels, and variable object direction due to the arbitrary shooting angle. Conventional object detector has poor detection effect on remote sensing image, which is prone to missed detection and false detection. In view of this, an improved YOLOv5 object detection algorithm was proposed for remote sensing image. First, the C3 module was improved. The output feature information of each convolutional module was transmitted to the deep network, so as to preserve more fine-grained feature information and enhance the small object detection capability. The improved downsampling mechanism integrates convolution downsampling with maximum pooling downsampling mechanism in downs amp ling to separate foreground and background information while retaining feature information. A lightweight rotatory decoupling detection head with implicit learning was proposed to address the conflict between regression and classification, thus improving the network detection capability for objects in any direction. In the meantime, an implicit learning matrix was added to guarantee the lightweight detection head and improve the network detection accuracy for multiple tasks. According to experimental results, under the same model size, compared with the original YOLOv5 detection method, the detection accuracy and detection speed of the proposed method were improved by 8% and 15 frames, or 14.7%, respectively on DOTA-v1.5 data set, effectively improving the detection accuracy and speed in remote sensing image detection. The detection accuracy was increased by 3.5% on coco data set in natural scenario. The method herein can still effectively improve the detection accuracy in natural scenario, proving effectiveness of the modified YOLOv5 method. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Seeking a Sense of Meaning and Companionship in Life: Informal Learning on Douyin Among Chinese Older Adults

引用

Proceedings of the ACM on Human-computer Interaction 2025年第2期9卷 1-24页

作者： Qian, Zhigu Fu, Jiaojiao Zhou, Yangfan School of Computer Science Fudan University Shanghai Key Laboratory of Intelligent Information Processing China School of Information Science and Engineering East China University of Science and Technology China

This study examines how Chinese older adults leverage Douyin, a short video platform, for informal learning purposes, analyzing their usage patterns, motivations, and encountered challenges. Although Douyin was not explicitly designed with educational features, it has emerged as a significant informal learning platform for this demographic. Through a qualitative investigation comprising participant observations and semi-structured interviews with 17 participants, we reveal the distinctive learning experience that Douyin facilitates. The platform’s unique combination of short-form videos, live streaming capabilities, and interactive community features creates an engaging learning environment that particularly resonates with older adults. Our findings demonstrate that participants derive substantial social-emotional benefits beyond knowledge acquisition, including strengthened social connections, enhanced companionship, and a reinforced sense of purpose through their Douyin engagement. These social-emotional aspects emerge as crucial factors driving older adults’ selection of Douyin as their preferred learning platform. By providing comprehensive insights into older adults’ engagement with digital platforms for lifelong learning, this research offers valuable implications for HCI, particularly in understanding how technology can be optimized to support the learning needs of older populations. © 2025 Association for Computing Machinery. All rights reserved.

关键词： Social aspects

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：