检索结果-内蒙古大学图书馆

Learning from suspected target: Bootstrapping performance for breast cancer detection in mammography

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Xiao, Li Zhu, Cheng Liu, Junjun Luo, Chunlong Liu, Peifang Zhao, Yi Key Laboratory of Intelligent Information Processing Advanced Computer Research Center Institute of Computing Technology Chinese Academy of Sciences Beijing China Tianjin Medical University Cancer Institute Hospital

Deep learning object detection algorithm has been widely used in medical image analysis. Currently all the object detection tasks are based on the data annotated with object classes and their bounding boxes. On the other hand, medical images such as mammography usually contain normal regions or objects that are similar to the lesion region, and may be misclassified in the testing stage if they are not taken care of. In this paper, we address such problem by introducing a novel top likelihood loss together with a new sampling procedure to select and train the suspected target regions, as well as proposing a similarity loss to further identify suspected targets from targets. Mean average precision (mAP) according to the predicted targets and specificity, sensitivity, accuracy, AUC values according to classification of patients are adopted for performance comparisons. We firstly test our proposed method on a private dense mammogram dataset. Results show that our proposed method greatly reduce the false positive rate and the specificity is increased by 0.25 on detecting mass type cancer. It is worth mention that dense breast typically has a higher risk for developing breast cancers and also are harder for cancer detection in diagnosis, and our method outperforms a reported result from performance of radiologists. Our method is also validated on the public Digital Database for Screening Mammography (DDSM) dataset, brings significant improvement on mass type cancer detection and outperforms the most state-of-the-art work. Copyright © 2020, The Authors. All rights reserved.

关键词： Object recognition

Humanoid Robot Control Based on Deep Learning 12th

学校读者我要写书评

暂无评论

Humanoid Robot Control Based on Deep Learning

12th International Conference on e-Learning and Games, Edutainment 2018

作者： Guo, Bin Yi, Pengfei Zhou, Dongsheng Wei, Xiaopeng Key Laboratory of Advanced Design and Intelligent Computing Dalian University Ministry of Education Dalian116622 China College of Computer Science and Technology Dalian University of Technology Dalian1160243 China

ISBN: (纸本)9783030237110

The direct control of humanoid robot by human motion is an important aspect of current research. Most of these methods are based on additional equipments, such as Kinect, which are usually not equipped on robot. In order to avoid using these external equipments, we explored a robot controlling method only using the low-resolution camera on robot. Firstly, a stacked hourglass network is employed to obtain the accurate 2D heatmap containing positions of human joints from RGB image captured by camera on robot. Then, 3D human poses including coordinates of human body joints are estimated from 2D heatmaps by a method aiming to reconstruct 3D human poses from 2D poses. Finally, the rotation angles of robot are computed according to these 3D coordinates and are transmitted to the robot to reconstruct the original human pose. Using the NAO robot as an example, the experimental results show that the humanoid robot can imitate motions of different human actors in different scenes well while applying our method. © 2019, Springer Nature Switzerland AG.

关键词： Anthropomorphic robots

ASPCNet: A Deep Adaptive Spatial Pattern Capsule Network for Hyperspectral Image Classification

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wang, Jinping Tan, Xiaojun Lai, Jianhuang Li, Jun Xiang, Canqun School of Intelligent Systems Engineering Sun Yat-sen University Guangzhou510006 China Key Laboratory of Machine Intelligence and Advanced Computing School of Computer Science and Engineering Sun Yatsen University Ministry of Education Guangzhou510006 China Zhuhai519082 China College of Electronics and Information Engineering Shenzhen University Shenzhen518060 China

Previous studies have shown the great potential of capsule networks for the spatial contextual feature extraction from hyperspectral images (HSIs). However, the sampling locations of the convolutional kernels of capsules are fixed and cannot be adaptively changed according to the inconsistent semantic information of HSIs. Based on this observation, this paper proposes an adaptive spatial pattern capsule network (ASPCNet) architecture by developing an adaptive spatial pattern (ASP) unit, that can rotate the sampling location of convolutional kernels on the basis of an enlarged receptive field. Note that this unit can learn more discriminative representations of HSIs with fewer parameters. Specifically, two cascaded ASP-based convolution operations (ASPConvs) are applied to input images to learn relatively high-level semantic features, transmitting hierarchical structures among capsules more accurately than the use of the most fundamental features. Furthermore, the semantic features are fed into ASP-based conv-capsule operations (ASPCaps) to explore the shapes of objects among the capsules in an adaptive manner, further exploring the potential of capsule networks. Finally, the class labels of image patches centered on test samples can be determined according to the fully connected capsule layer. Experiments on three public datasets demonstrate that ASPCNet can yield competitive performance with higher accuracies than state-of-the-art methods. Copyright © 2021, The Authors. All rights reserved.

关键词： Spectroscopy

Detection of Deepfake videos using long distance attention

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Lu, Wei Liu, Lingyi Luo, Junwei Zhao, Xianfeng Zhou, Yicong Huang, Jiwu School of Computer Science and Engineering Guangdong Province Key Laboratory of Information Security Technology Ministry of Education Key Laboratory of Machine Intelligence and Advanced Computing Sun Yat-sen University Guangzhou510006 China State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences Beijing100195 China School of Cyber Security University of Chinese Academy of Sciences Beijing100195 China Department of Computer and Information Science University of Macau 999078 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen Key Laboratory of Media Security Shenzhen University Shenzhen518060 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518055 China

With the rapid progress of deepfake techniques in recent years, facial video forgery can generate highly deceptive video contents and bring severe security threats. And detection of such forgery videos is much more urgent and challenging. Most existing detection methods treat the problem as a vanilla binary classification problem. In this paper, the problem is treated as a special fine-grained classification problem since the differences between fake and real faces are very subtle. It is observed that most existing face forgery methods left some common artifacts in the spatial domain and time domain, including generative defects in the spatial domain and inter-frame inconsistencies in the time domain. And a spatial-temporal model is proposed which has two components for capturing spatial and temporal forgery traces in global perspective respectively. The two components are designed using a novel long distance attention mechanism. The one component of the spatial domain is used to capture artifacts in a single frame, and the other component of the time domain is used to capture artifacts in consecutive frames. They generate attention maps in the form of patches. The attention method has a broader vision which contributes to better assembling global information and extracting local statistic information. Finally, the attention maps are used to guide the network to focus on pivotal parts of the face, just like other fine-grained classification methods. The experimental results on different public datasets demonstrate that the proposed method achieves the state-of-the-art performance, and the proposed long distance attention method can effectively capture pivotal parts for face forgery. Copyright © 2021, The Authors. All rights reserved.

关键词： Time domain analysis

Fractional Modeling and Dynamic Analysis of Two Kinds of Viscoelastic Thin Plates with Gaussian White Noise

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Deng, Jinna Liu, Qiumei Yang, Aimin Chen, Yiming College of Science North China University of Science and Technology Tangshan063210 China Hebei Key Laboratory of Data Science and Application North China University of Science and Technology Tangshan063210 China The Key Laboratory of Engineering Computing in Tangshan City North China University of Science and Technology Tangshan063210 China Tangshan Intelligent Industry and Image Processing Technology Innovation Center North China University of Science and Technology Tangshan063210 China Hebei Engineering Research Center for the Intelligentization of Iron Ore Optimization and Ironmaking Raw Materials Preparation Processes North China University of Science and Technology Tangshan063210 China School of Science Yanshan University Qinhuangdao066004 China LE STUDIUM Loire Valley Institute for Advanced Studies Orléans & Tours Orléans45000 France

According to fractional order model, the governing equation of viscoelastic plate is established. Using the properties of the shifted Bernstein polynomials, the fractional order equation of viscoelastic plate is resolved, the conversion of fractional differential equations to algebraic equations, and operator matrices represented by Kronecker products are solved in the domain. The convergence study validates the algorithm's efficacy and precision in solving differential equations. The displacement of viscoelastic metal thin plate under different external loads (uniform distribution and linear distribution), the effect of white Gaussian noise on the thin metal plate displacement, the effect of different boundary conditions on thin metal plate displacement under harmonic load are studied, the displacements of metal and polymer plates under different loads are contrasted and stress and strain relationship of two kinds of plates are discussed. Based on the outcomes, it can be concluded that the shift Bernstein polynomial approach is useful for numerically simulating viscoelastic plates. © 2023, The Authors. All rights reserved.

关键词： Gaussian noise (electronic)

A knowledge acquisition automatizing framework from literature exemplified by Na + activation energy prediction of NASICON solid-state electrolyte

学校读者我要写书评

暂无评论

Energy Storage Materials 2025年 80卷

作者： Yue Liu Dahui Liu Zhengwei Yang Xianyuan Ge Wenxuan Yao Jie Wu Maxim Avdeev Siqi Shi State Key Laboratory of Materials for Advanced Nuclear Energy & School of Computer Engineering and Science Shanghai University Shanghai 200444 China Shanghai Engineering Research Center of Intelligent Computing System Shanghai 200444 China Australian Nuclear Science and Technology Organisation Sydney 2232 Australia School of Chemistry The University of Sydney Sydney 2006 Australia State Key Laboratory of Materials for Advanced Nuclear Energy & School of Materials Science and Engineering Shanghai University Shanghai 200444 China Materials Genome Institute Shanghai University Shanghai 200444 China

Materials science literature contains vast amount of structure-activity relationship knowledge crucial for materials discovery and design. However, automatic extraction of domain knowledge from literature remains challenging due to its unstructured and heterogeneous format. Herein, we propose a framework for automating knowledge acquisition, which involves a materials entity-aware relational extraction model (MatRE) to mine triples, an approach to construct a knowledge graph (KG) for the detection of associations among triples, as well as inference and representation of structure-activity relationships in a machine learning (ML)-compatible format. We demonstrate its application in predicting sodium ion activation energy for the NASICON solid-state electrolyte (SSE) system. MatRE trained on a NASICON SSE dataset, achieves an F1-score of 0.80, and is used to extract 260,475 entity–relation triples from 1,808 scientific publications. Furthermore, embedding 24 knowledge bullets from the KG into data pre-processing and feature engineering stages improves the performance and interpretability of six common ML models by up to 25.7%. This work offers key insights into automatic knowledge acquisition from literature and heralds a new paradigm for AI-assisted materials genome engineering driven by both data and knowledge.

关键词：

Global-and-Local Collaborative Learning for Co-Salient Object Detection

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Cong, Runmin Yang, Ning Li, Chongyi Fu, Huazhu Zhao, Yao Huang, Qingming Kwong, Sam The Institute of Information Science Beijing Jiaotong University Beijing100044 China The Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing100044 China The Department of Computer Science City University of Hong Kong Hong Kong The School of Computer Science and Engineering Nanyang Technological University Singapore A*STAR Singapore The School of Computer Science and Technology University of Chinese Academy of Sciences Beijing101408 China University of Chinese Academy of Sciences Beijing101408 China The Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Peng Cheng Laboratory Shenzhen518055 China The City University of Hong Kong Shenzhen Research Institute Shenzhen51800 China

The goal of co-salient object detection (CoSOD) is to discover salient objects that commonly appear in a query group containing two or more relevant images. Therefore, how to effectively extract inter-image correspondence is crucial for the CoSOD task. In this paper, we propose a global-and-local collaborative learning architecture, which includes a global correspondence modeling (GCM) and a local correspondence modeling (LCM) to capture comprehensive inter-image corresponding relationship among different images from the global and local perspectives. Firstly, we treat different images as different time slices and use 3D convolution to integrate all intra features intuitively, which can more fully extract the global group semantics. Secondly, we design a pairwise correlation transformation (PCT) to explore similarity correspondence between pairwise images and combine the multiple local pairwise correspondences to generate the local inter-image relationship. Thirdly, the inter-image relationships of the GCM and LCM are integrated through a global-and-local correspondence aggregation (GLA) module to explore more comprehensive inter-image collaboration cues. Finally, the intra- and inter-features are adaptively integrated by an intra-and-inter weighting fusion (AEWF) module to learn co-saliency features and predict the co-saliency map. The proposed GLNet is evaluated on three prevailing CoSOD benchmark datasets, demonstrating that our model trained on a small dataset (about 3k images) still outperforms eleven state-of-the-art competitors trained on some large datasets (about 8k̴200k images). © 2022, CC BY-NC-SA.

关键词： Convolution

Missing Data Recovery for Human Mocap Data Based on A-LSTM and LS Constraint

学校读者我要写书评

暂无评论

Missing Data Recovery for Human Mocap Data Based on A-LSTM a...

IEEE International Conference on Signal and Image Processing (ICSIP)

作者： Lu Ji Rui Liu Dongsheng Zhou Qiang Zhang Xiaopeng Wei Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education School of Software Engineering Dalian University Dalian China School of Computer Science and Technology Dalian University of Technology Dalian China

ISBN: (数字)9781728168968

ISBN: (纸本)9781728168975

Human mocap (motion capture) data has been widely used in many fields. However, influenced by the occlusion and falling, missing of markers is inevitable in optical motion capture system. According to the temporal and spatial characteristics of mocap data, a missing data recovery method based on attention-based LSTM network (A-LSTM) and least-squares (LS) constraint is proposed in this paper. First, the LSTM is chosen as the basic network to estimate the position of the missing markers, in which an attention mechanism is introduced to learn the temporal continuity of human mocap data. Then, a space affine transformation based on least-squares fitting is adopted as the spatial constraint to refine the estimated positions, after which the restored error can be reduced significantly. Experiments show that the proposed A-LSTM+LS method is robust to the length of missing gap and the number of missing markers. Under the same conditions, our method achieves smaller restore error than the state of the art.

关键词： Legged locomotion Deep learning Image recognition Correlation Fitting Neural networks Image restoration

Near-Space Communications: the Last Piece of 6G Space-Air-Ground-Sea Integrated Network Puzzle

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Liu, Hongshan Qin, Tong Gao, Zhen Mao, Tianqi Ying, Keke Wan, Ziwei Qiao, Li Na, Rui Li, Zhongxiang Hu, Chun Mei, Yikun Li, Tuan Wen, Guanghui Chen, Lei Wu, Zhonghuai Liu, Ruiqi Chen, Gaojie Wang, Shuo Zheng, Dezhi School of Information and Electronics Beijing Institute of Technology Beijing100081 China MIIT Key Laboratory of Complex-Field Intelligent Sensing Beijing Institute of Technology Beijing100081 China Advanced Research Institute of Multidisciplinary Sciences 100081 Beijing Institute of Technology Beijing China Yangtze Delta Region Academy of Beijing Institute of Technology Beijing Institute of Technology Jiaxing314000 China Advanced Research Institute of Multidisciplinary Science Beijing Institute of Technology Jinan250307 China Department of Mathematics Southeast University Nanjing210096 China Advanced Research Institute of Multidisciplinary Science Beijing Institute of Technology Beijing100081 China Beijing Key Laboratory for Precision Optoelectronic Measurement Instrument and Technology School of Optics and Photonics Beijing Institute of Technology Beijing100081 China Wireless and Computing Research Institute ZTE Corporation Beijing100029 China 5GIC & 6GIC Institute for Communication Systems University of Surrey GuildfordGU2 7XH United Kingdom China Academy of Space Technology Beijing100094 China

This article presents a comprehensive study on the emerging near-space communications (NS-COM) within the context of space-air-ground-sea integrated network (SAGSIN). Specifically, we firstly explore the recent technical developments of NS-COM, followed by the discussions about motivations behind integrating NS-COM into SAGSIN. To further demonstrate the necessity of NS-COM, a comparative analysis between the NS-COM network and other counterparts in SAGSIN is conducted, covering aspects of deployment, coverage, channel characteristics and unique problems of NS-COM network. Afterwards, the technical aspects of NS-COM, including channel modeling, random access, channel estimation, array-based beam management and joint network optimization, are examined in detail. Furthermore, we explore the potential applications of NS-COM, such as structural expansion in SAGSIN communication, civil aviation communication, remote and urgent communication, weather monitoring and carbon neutrality. Finally, some promising research avenues are identified, including stratospheric satellite (StratoSat) -to-ground direct links for mobile terminals, reconfigurable multiple-input multiple-output (MIMO) and holographic MIMO, federated learning in NS-COM networks, maritime communication, electromagnetic spectrum sensing and adversarial game, integrated sensing and communications, StratoSat-based radar detection and imaging, NS-COM assisted enhanced global navigation system, NS-COM assisted intelligent unmanned system and free space optical (FSO) communication. Overall, this paper highlights that the NS-COM plays an indispensable role in the SAGSIN puzzle, providing substantial performance and coverage enhancement to the traditional SAGSIN architecture. Copyright © 2023, The Authors. All rights reserved.

关键词： Navigation systems