检索结果-内蒙古大学图书馆

8th International Conference on Intelligent Computing and Signal Processing, ICSP 2023

作者： Qi, Meibin Zhou, Dade Li, Kunyuan HeFei University of Technology School of Computer Science and Information Engineering Anhui Hefei China

ISBN: (纸本)9798350302455

Radar radiation source sorting and identification methods based on in-depth learning have received considerable attention in recent years, but there are time and resource constraints in practice. To solve this problem, this paper presents a method of radar radiation source signal sorting based on meta-learning. Data samples for signal sorting are generated by acquiring the three-dimensional entropy, image coefficient, high-order cumulants, bandwidth and carrier frequency characteristics of the signal. A signal classification model based on adaptive channel attention is constructed. Model-Agnostic Meta-Learning (MAML) meta-learning mechanism is used to enhance the generalization performance of the model to meet the task requirements of radar signal sorting under small sample conditions. The experimental results show that this method can effectively improve the low recognition rate of small sample radar radiation source signals, and achieve a good classification accuracy under the condition of a small sample of training data. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Direct Monocular Visual Odometry Based on Lidar Vision Fusion∗ 5

Direct Monocular Visual Odometry Based on Lidar Vision Fusio...

引用

5th World Robot Conference Symposium on Advanced Robotics and Automation, WRC SARA 2023

作者： Fang, Baofu Pan, Qing Wang, Hao Hefei University of Technology School of Computer Science and Information Engineering Hefei230601 China

ISBN: (纸本)9798350307320

Lidar-assisted visual odometry is a widely used method for pose estimation. However, existing lidar-visual odometry methods suffer from depth association errors, and single-point feature-based methods have insufficient accuracy and are prone to tracking failures, leading to inaccurate pose estimation. In this paper, we proposed a direct monocular visual odometry method based on lidar visual fusion. Firstly, high-gradient pixels of the lidar point cloud projection are extracted, and an initial pose estimation is performed by minimizing photometric errors, avoiding inaccurate feature-depth associations. Then, the point-line features in keyframes are combined and associated with the current frame for pose refinement, and the line features are also matched using the minimization of photometric errors. The evaluations on the KITTI Odometry and Nuscene datasets, and compared to lidar odometry and similar lidar-assisted visual odometry methods, show that our method achieves better pose estimation accuracy and robustness in the majority of scenarios. © 2023 IEEE.

关键词： Optical radar

来源：评论

学校读者我要写书评

暂无评论

From Static to Dynamic: Adapting Landmark-Aware Image Models for Facial Expression Recognition in Videos

引用

IEEE Transactions on Affective Computing 2024年第2期16卷 624-638页

作者： Chen, Yin Li, Jia Shan, Shiguang Wang, Meng Hong, Richang Hefei University of Technology School of Computer Science and Information Engineering Hefei230601 China Institute of Computing Technology Chinese Academy of Sciences Key Laboratory of Intelligent Information Processing Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China

Dynamic facial expression recognition (DFER) in the wild is still hindered by data limitations, e.g., insufficient quantity and diversity of pose, occlusion and illumination, as well as the inherent ambiguity of facial expressions. In contrast, static facial expression recognition (SFER) currently shows much higher performance and can benefit from more abundant high-quality training data. Moreover, the appearance features and dynamic dependencies of DFER remain largely unexplored. Recognizing the potential in leveraging SFER knowledge for DFER, we introduce a novel Static-to-Dynamic model (S2D) that leverages existing SFER knowledge and dynamic information implicitly encoded in extracted facial landmark-aware features, thereby significantly improving DFER performance. Firstly, we build and train an image model for SFER, which incorporates a standard Vision Transformer (ViT) and Multi-View Complementary Prompters (MCPs) only. Then, we obtain our video model (i.e., S2D), for DFER, by inserting Temporal-Modeling Adapters (TMAs) into the image model. MCPs enhance facial expression features with landmark-aware features inferred by an off-the-shelf facial landmark detector. And the TMAs capture and model the relationships of dynamic changes in facial expressions, effectively extending the pre-trained image model for videos. Notably, MCPs and TMAs only increase a fraction of trainable parameters (less than +10%) to the original image model. Moreover, we present a novel Emotion-Anchors (i.e., reference samples for each emotion category) based Self-Distillation Loss to reduce the detrimental influence of ambiguous emotion labels, further enhancing our S2D. Experiments conducted on popular SFER and DFER datasets show that we have achieved a new state of the art. © 2010-2012 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Polarization‑entangled photon‑pair source with van der Waals 3R‑WS_(2) crystal

引用

eLight 2024年第1期4卷 99-106页

作者： Jiangang Feng Yun‑Kun Wu Ruihuan Duan Jun Wang Weijin Chen Jiazhang Qin Zheng Liu Guang‑Can Guo Xi‑Feng Ren Cheng‑Wei Qiu Department of Electrical and Computer Engineering National University of SingaporeSingapore 117583Singapore CAS Key Laboratory of Quantum Information University of Science and Technology of ChinaHefei 230026China CAS Center for Excellence in Quantum Information and Quantum Physics University of Science and Technology of ChinaHefei 230026China Hefei National Laboratory University of Science and Technology of ChinaHefei 230088China School of Materials Science and Engineering Nanyang Technological UniversitySingapore 639798Singapore Department of Optical Science and Engineering and Shanghai Frontiers Science Research Base of Intelligent Optoelectronics and PerceptionFudan UniversityShanghai 200433China

Ultracompact entangled photon sources are pivotal to miniaturized quantum photonic *** der Waals(vdW)nonlinear crystals promise efficient photon-pair generation and on-chip monolithic integration with nanophotonic ***,it remains challenging to generate maximally entangled Bell states of photon pairs with high purity,generation rate,and fidelity required for practical ***,we realize a polarization-entangled photon-pair source based on spontaneous parametric down conversion in an ultrathin rhombohedral tungsten disulfide(3R-WS2)*** vdW entangled photonic source exhibits a high photon-pair purity with a coincidenceto-accidental ratio of above 800,a generation rate of 31 Hz,and two maximally polarization-entangled Bell states with fidelities exceeding 0.93 and entanglement degree over *** results stem from scalable optical nonlinearity,enhanced second-order susceptibility by electronic transitions,and a well-defined symmetry-enabled selection rule inherent in *** polarization entangled photon source can be integrated with photonic structures for generating more complex entangled states,thus paving an avenue for advanced quantum photonic systems toward computation and metrology.

关键词： purity maximal Polarization

来源：评论

学校读者我要写书评

暂无评论

EELMCDA: Combining evolutionary ensemble learning with matrix feature decomposition for predicting circRNA-disease associations

EELMCDA: Combining evolutionary ensemble learning with matri...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Wang, Zheng Wang, Lei You, Zhu-Hong Wang, Lei Li, Yang Wang, Zhenyu Xi'an University of Technology School of Computer Science and Engineering Xi'an710048 China Northwestern Polytechnical University School of Computer Science Xi'an710048 China China University of Mining and Technology School of Computer Science and Technology Xuzhou221116 China Hefei University of Technology School of Computer Science and Information Engineering Hefei230601 China Lanzhou University of Technology School of Electrical Engineering and Information Engineering Lanzhou730050 China

ISBN: (纸本)9798350386226

Recent studies have indicated that circular RNAs (circRNAs) play a significant role in the diagnosis and treatment of disease. However, the prediction of associations between circRNAs and diseases using conventional biological methods is constrained by numerous factors. In this study, we proposed a novel computational model called EELMCDA that combines evolutionary ensemble learning (EEL) approach and matrix feature decomposition method to predict potential circRNA-disease associations. The model firstly integrates circRNA function information, disease semantic information, and circRNA and disease gaussian interaction profile kernel (GIPK) information into an integrated matrix and constructed the corresponding feature matrix, then uses the matrix feature decomposition algorithm to obtain its important feature, and finally adopted evolutionary ensemble learning module to predict circRNA-disease associations. The average accuracy of the EELMCDA model by 5-fold cross-validation on CircR2Disease, CircAtlasv2.0, Circ2Disease, and CircRNADisease datasets were 92.40%, 92.90%, 88.91%, and 90.74%, respectively. Moreover, in case studies, the 21 of the top 30 circRNA-disease pairs with the highest EELMCDA scores were validated in recent literatures. These results further demonstrate the effectiveness of EELMCDA in predicting circRNA-disease associations. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Unseen Codec Spoof Speech Detection Based on Channel-Robust Feature 23

Unseen Codec Spoof Speech Detection Based on Channel-Robust ...

引用

3rd International Conference on Artificial Intelligence, Automation and Algorithms, AI2A 2023

作者： Zhu, Yupeng Zhao, Zuxing Li, Fan Chen, Yanxiang School of Computer Science and Information Engineering Hefei University of Technology Hefei Anhui China

ISBN: (纸本)9798400707605

For speech anti-spoofing, the ability of countermeasures (CMs) to cope with unseen attacks has been under scrutiny. Since the previous LA attack was mainly for ASV, which required that the spoofed speech be clean enough to be parsed properly by the ASV and that the unseen scenario be limited to the types of synthesis algorithms. With the development of DeepFake, spoofed speech is more often used to spread fake information so that the unseen codecs channel effects needs to be considered. Based on this, we propose a channel-robust spoof detection method based on the wav2vec2.0 and a channel augmentation adversarial (AUG-ADV) strategy. Our method was experimented on the FMFCC-A dataset and achieves the best results with several evaluation metrics. © 2023 ACM.

关键词： unseen codec anti-spoofing channel-robust DeepFake

来源：评论

学校读者我要写书评

暂无评论

Junction matters in hydraulic circuit bio-design of microfluidics

引用

Bio-Design and Manufacturing 2023年第1期6卷 38-50页

作者： Yao Lin Dongliang He Zerui Wu Yurou Yao Zhanhao Zhang Yuheng Qiu Shan Wei Guangzhu Shang Xingyue Lei Ping Wu Weiping Ding Liqun He Department of Thermal Science and Energy Engineering University of Science and Technology of ChinaHefei 230027China School of Chemistry and Materials Science University of Science and Technology of ChinaHefei 230027China GeneMind Biosciences Company Limited Shenzhen 518023China Department of Electronic Engineering and Information Science University of Science and Technology of ChinaHefei 230027China

Microfluidic channels are at micrometer scales;thus,their fluid flows are laminar,resulting in the linear dependence of pressure drop on flow rate in the length of the *** ratio of the pressure drop to flow rate,referred to as resistance,depends on channel size and dynamic ***,a microfluidic chip is analogous to an electric circuit in design,but the design is adjusted to optimize channel ***,whereas voltage loss is negligible at the nodes of an electric circuit,hydraulic pressure drops at the nodes of microfluidic chips by a magnitude are comparable to the pressure drops in the straight ***,we prove by experiment that one must fully consider the pressure drops at nodes so as to accurately design a precise microfluidic *** the process,we numerically calculated the pressure drops at hydraulic nodes and list their resistances in the range of flows as *** resorted to machine learning to fit the calculated results for complex ***,we obtained a library of node resistances for common junctions and used them to design three established chips that work for single-cell analysis and for precision allocation of solutes(in gradient and averaging concentration microfluidic networks).Endothelial cells were stimulated by generating concentrations of adriamycin hydrochloride from the last two microfluidic networks,and we analyzed the response of endothelial *** results indicate that consideration of junction resistances in design calculation brings experimental results closer to the design values than *** approach may therefore contribute to providing a platform for the precise design of organ chips.

关键词： Junctions Hydraulics Microfluidic chip design

来源：评论

学校读者我要写书评

暂无评论

Comprehensive research facility for negative ion source neutral beam injection at CRAFT:design and first

引用

Plasma science and technology 2025年第4期27卷 1-11页

作者： Jianglong WEI Yahong XIE Yuanlai XIE Caichao JIANG Yuanzhe ZHAO Yongjian XU Yuming GU Wei YI Wei LIU Lyuyang BU Dezhi YAN Zhimin LIU Sheng LIU Junjun PAN Shiyong CHEN Ling YU Qinglong CUI Shihua SONG Yuqing CHEN Ji WANG Ling LIU Shengmin PAN Bin GUO Zhigang ZHU Na WANG Junwei XIE Yuwen YANG Tengsai ZHU Lixin YANG Yufan LI Ning TANG Qianxu WANG Huihui HONG Bo LIU Yuqian LI Yang LI Yu GU Xufeng PENG Shanhu LIU Yong WU Xiancai MENG Chundong HU Lizhen LIANG Institute of Plasma Physics Hefei Institutes of Physical ScienceChinese Academy of SciencesHefei 230031People’s Republic of China Science Island Branch of Graduate School University of Science and Technology of ChinaHefei 230026People’s Republic of China School of Nuclear Science and Engineering East China University of TechnologyNanchang 330013People’s Republic of China School of Electrical Engineering University of South ChinaHengyang 421001People’s Republic of China School of Science Shandong Jianzhu UniversityJinan 250101People’s Republic of China School of Electronic and Information Engineering Anhui Jianzhu UniversityHefei 230022People’s Republic of China Institute of Energy Hefei Comprehensive National Science CenterHefei 230031People’s Republic of China

Neutral beam injection(NBI)has been proven as a reliable heating and current drive method for fusion *** the high-energy NBI system(particle energy>150 ke V)of large-scale fusion devices,the negative ion source neutral beam injection(NNBI)system is inevitable,which can obtain an acceptable neutralization efficiency(>55%).But the NNBI system is very complex and *** explore and master the key NNBI technology for future fusion reactor in China,an NNBI test facility is under development in the framework of the Comprehensive Research Facility for Fusion technology(CRAFT).The initial goal of CRAFT NNBI facility is to achieve a 2 MW hydrogen neutral beam at the energy of 200–400 ke V for lasting 100 *** the first operation of the CRAFT NNBI facility,a negative ion source with dual RF drivers was developed and *** using the 50 keV accelerator,the long-pulse and highcurrent extractions of negative hydrogen ions have been achieved and the typical values were 55.4 keV,7.3 A(~123 A/m^(2)),105 s and 55.0 keV,14.7 A(~248 A/m^(2)),30 s,*** using the 200 keV accelerator,the megawatt-class negative hydrogen beam has also been achieved(135.9 keV,8.9 A,8 s).The whole process of the gas neutralization of negative ion beam,electric removal of residual ions,and beam transport have been demonstrated experimentally.

关键词： beam acceleration magnetic confinement fusion negative ion source neutral beam injection(Some figures may appear in colour only in the online journal)

来源：评论

学校读者我要写书评

暂无评论

Polarization image defogging based on detail recovery generative adversarial network 3

Polarization image defogging based on detail recovery genera...

引用

3rd International Conference on Signal Image Processing and Communication, ICSIPC 2023

作者： Yang, Cheng Li, Yang School of Computer Science and Information Engineering Hefei University of Technology AnHui Hefei China

ISBN: (纸本)9781510670945

Most of the existing polarization image based defogging methods use a priori and assumptions to recover images, and although these methods have made great progress, the a priori or assumptions are not always reliable in practical scenarios, which limits the performance of defogging methods. In this paper, we design a two branch network to learn image features;the defogging network uses the fusion module to adaptively assign weights to different path features to ensure the defogging effect while focusing on the haze region;the detail recovery network uses convolutional layers and smoothly expanding convolution to expand the perceptual field and fully obtain local and global feature information;finally, the features obtained from the detail recovery network and the defogging network are fused to improve the defogging Finally, the features obtained from detail recovery network and defogging network are fused to improve the defogging effect. The experimental results show that this method can reconstruct clear images in foggy environment with 2db improvement in PSNR and 0.016 improvement in SSIM, and the quality of reconstructed images is better than existing algorithms. © 2023 SPIE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Cat Swarm Algorithm Generated Based on Genetic Programming Framework Applied in Digital Watermarking

引用

computers, Materials & Continua 2025年第5期83卷 3135-3163页

作者： Shu-Chuan Chu Libin Fu Jeng-Shyang Pan Xingsi Xue Min Liu School of Artificial Intelligence Nanjing University of Information Science and TechnologyNanjing210000China College of Computer Science and Engineering Shandong University of Science and TechnologyQingdao266000China Department of Information Management Chaoyang University of TechnologyTaichung40601TaiwanChina School of Information Science and Engineering Fujian University of TechnologyFuzhou350000China Key Laboratory of Hydrometeorological Disaster Mechanism and Warning of Ministry of Water Resource Nanjing University of Information Science and TechnologyNanjing210000China

Evolutionary algorithms have been extensively utilized in practical ***,manually designed population updating formulas are inherently prone to the subjective influence of the *** programming(GP),characterized by its tree-based solution structure,is a widely adopted technique for optimizing the structure of mathematical models tailored to real-world *** paper introduces a GP-based framework(GPEAs)for the autonomous generation of update formulas,aiming to reduce human *** modifications to tree-based GP have been instigated,encompassing adjustments to its initialization process and fundamental update operations such as crossover and mutation within the *** designing suitable function sets and terminal sets tailored to the selected evolutionary algorithm,and ultimately derive an improved update *** Cat Swarm Optimization Algorithm(CSO)is chosen as a case study,and the GP-EAs is employed to regenerate the speed update formulas of the *** validate the feasibility of the GP-EAs,the comprehensive performance of the enhanced algorithm(GP-CSO)was evaluated on the CEC2017 benchmark ***,GP-CSO is applied to deduce suitable embedding factors,thereby improving the robustness of the digital watermarking *** experimental results indicate that the update formulas generated through training with GP-EAs possess excellent performance scalability and practical application proficiency.

关键词： Cat swarm algorithm genetic programming digital watermarking update mode mode generation framework

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：