检索结果-内蒙古大学图书馆

2021 IEEE International Conference on Multimedia and Expo, ICME 2021

作者： Dong, Junhao Xie, Xiaohua School of Computer Science and Engineering Sun Yat-sen University China Guangdong Key Laboratory of Information Security Technology China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

ISBN: (纸本)9781665438643

As a deep learning-based application, DeepFake can generate malicious images or videos through replacing the face of a source image with the target face, which poses a significant threat to social media. In this paper, we propose a scheme to prevent such tampering by exploring adversarial examples against DeepFake. Specifically, adversarial examples are produced by adding tailored distortion to source images. The added distortion is imperceptible to human vision but can mislead the generation of face-swapped images effectively. We present three novel adversarial attacks against DeepFake autoencoders from perspectives of adversarial transferability and latent representation. Our first method synthesizes universal perturbation, which is image-agnostic. By contrast, the latter two methods directly perform the preciser perturbation specific to a source image. Extensive experiments demonstrate the effectiveness of our adversarial examples against DeepFake in terms of both reference and non-reference image quality assessment. © 2021 IEEE

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

PanGu Drug Model: learn a molecule like a human

引用

Science China(Life Sciences) 2023年第4期66卷 879-882页

作者： Xinyuan Lin Chi Xu Zhaoping Xiong Xinfeng Zhang Ningxi Ni Bolin Ni Jianlong Chang Ruiqing Pan Zidong Wang Fan Yu Qi Tian Hualiang Jiang Mingyue Zheng Nan Qiao Laboratory of Health Intelligence Huawei Cloud Computing Technologies Co.LtdGuizhou 550025China Shanghai Institute for Advanced Immunochemical Studies and School of Life Science and TechnologyShanghaiTech UniversityShanghai 200031China Drug Discovery and Design Center State Key Laboratory of Drug ResearchShanghai Institute of Materia MedicaChinese Academy of SciencesShanghai 201203China

Dear Editor,Recent achievements in large-scale pre-trained models like GPT-3 and PanGu-α have demonstrated astounding performances in many downstream tasks of natural language processing (NLP),confirming AI to be user-oriented for even industrial *** learning has been recognized as the most promising technology for pharmaceuticals,a powerful molecule pre-trained model that could economize researchers’tons of *** the strategic application of AI capabilities to the drug discovery field,we pre-trained a model called PanGu Drug Model with 1.7 billion small molecules from ZINC20 (Irwin et al.,2020),DrugSpaceX(Yang et al.,2021),and UniChem (Chambers et al.,2013).

关键词： fir trained strategic

来源：评论

学校读者我要写书评

暂无评论

Revealing distribution discrepancy by sampling transfer in unlabeled data 24

Revealing distribution discrepancy by sampling transfer in u...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Zhilin Zhao Longbing Cao Xuhui Fan Wei-Shi Zheng School of Computing Macquarie University Australia and School of Computer Science and Engineering Sun Yat-sen University China School of Computing Macquarie University Australia School of Computer Science and Engineering Sun Yat-sen University China and Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

ISBN: (纸本)9798331314385

There are increasing cases where the class labels of test samples are unavailable, creating a significant need and challenge in measuring the discrepancy between training and test distributions. This distribution discrepancy complicates the assessment of whether the hypothesis selected by an algorithm on training samples remains applicable to test samples. We present a novel approach called Importance Divergence (I-Div) to address the challenge of test label unavailability, enabling distribution discrepancy evaluation using only training samples. I-Div transfers the sampling patterns from the test distribution to the training distribution by estimating density and likelihood ratios. Specifically, the density ratio, informed by the selected hypothesis, is obtained by minimizing the Kullback-Leibler divergence between the actual and estimated input distributions. Simultaneously, the likelihood ratio is adjusted according to the density ratio by reducing the generalization error of the distribution discrepancy as transformed through the two ratios. Experimentally, I-Div accurately quantifies the distribution discrepancy, as evidenced by a wide range of complex data scenarios and tasks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Single-Wavelength Laminar Optical Tomography for In Vivo Microvascular Three-Dimensional Imaging

Single-Wavelength Laminar Optical Tomography for In Vivo Mic...

引用

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

作者： Han Cui Dewei Han Wenquan Liu Xinping Deng Zhixuan Xin Guanglin Li CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institute of Advanced Technology Chinese Academy of Sciences (CAS) Shenzhen China

ISBN: (数字)9798350371499

ISBN: (纸本)9798350371505

Laminar Optical Tomography (LOT) is a promising non-invasive technique for three-dimensional imaging of complex biological structures, combining high resolution and deep penetration. In this study, a LOT system was assembled using a 520nm continuous-wave laser, exploiting the contrast mechanism provided by the unique optical absorption coefficient of hemoglobin at this wavelength for microvascular imaging. The system utilizes raster scanning to illuminate the target tissue's surface, capturing backscattered light intensity with a multi-channel Photomultiplier Tubes. The inverse problem of light propagation within the tissue is solved to reconstruct a three-dimensional image of microvasculature. Phantom and in-vivo rat ear results demonstrate the system's ability to image micro vessels with diameters of several hundred micrometers within the tissue. The implemented LOT system, known for its simplicity and cost-effectiveness, showcases its potential for applications in microvascular physiological and pathological research, as well as clinical diagnostics.

关键词： Micrometers Surface reconstruction Biomedical optical imaging Three-dimensional displays Surface waves Tissue engineering Tomography Optical imaging Image reconstruction Tumors

来源：评论

学校读者我要写书评

暂无评论

Fabrication of large-scale monocrystalline silicon metasurfaces on flexible substrates 4

Fabrication of large-scale monocrystalline silicon metasurfa...

引用

4th Optics Frontier Conference, OFS 2024

作者： Liu, Chen Zhang, Yuehao Zhai, Yiheng Li, Guangyuan Wang, Shaojun School of Optoelectronic Science and Engineering Collaborative Innovation Center of Suzhou Nano Science and Technology Soochow University Suzhou215006 China Key Lab of Advanced Optical Manufacturing Technologies of Jiangsu Province Key Lab of Modern Optical Technologies of Education Ministry of China Soochow University Suzhou215006 China CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China

ISBN: (纸本)9781510682269

Flexible photonic devices based on metasurfaces exhibit characteristics such as ultra-thinness and light weight, enabling versatile applications across various surfaces, particularly in smart wearable devices, visible light communication, and conformal optics, etc. Among existing methods, direct flip transfer and stamp-assisted transfer are the two most prevalent processes. However, metasurfaces produced by these methods are typically embedded within a flexible substrate, constraining the dielectric environment of the metasurface. Moreover, conventional approaches often utilize materials like metal or amorphous silicon for nanoantennas, leading to unnecessary optical losses. In contrast, monocrystalline silicon offers a larger scattering cross-section and lower absorption loss, promising superior performance for photonic devices[1-5]. Herein, we propose a method for fabricating reconfigurable, flexible centimeter-scale monocrystalline silicon metasurfaces. The process involves a polymer membrane containing monocrystalline silicon metasurface, followed by transferring the polymer onto a stretchable substrate (PDMS) utilizing water tension. The monocrystalline silicon nanoparticle arrays are affixed to the PDMS substrate via van der Waals force, with the surrounding area directly exposed to air. Further, photonic devices with upper and lower refractive index matching can be achieved by pouring PDMS. By adjusting the mechanical stretching of the photonic device, dynamic control of the light field can be realized. © 2024 SPIE.

关键词： Photonic devices

来源：评论

学校读者我要写书评

暂无评论

Latency Localization of Auditory Brainstem Response by Different Deep Learning Methods

Latency Localization of Auditory Brainstem Response by Diffe...

引用

2023 IEEE International Conference on Real-Time computing and Robotics, RCAR 2023

作者： Ji, Junyu Wang, Xin Jia, Desheng Zhao, Chunrui He, Yuchao Ahmad, Ijaz Zhu, Mingxing Pan, Hongguang Chen, Shixiong Li, Guanglin University of Chinese Academy of Sciences Shenzhen College of Advanced Technology Shenzhen518055 China Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen518055 China Shenzhen Children's Hospital Department of Otolaryngology Shenzhen518033 China Chinese Academy of Sciences Cas Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institute of Advanced Technology Shenzhen518055 China Harbin Institute of Technology School of Electronics and Information Engineering Shenzhen518055 China

ISBN: (纸本)9798350327182

Auditory brainstem response (ABR) is an evoked potential generated by the auditory brainstem nuclei in response to auditory stimuli. Hearing loss or impairment in the auditory pathway can be objectively reflected by extracting the latencies of the peaks of characteristic waves (especially wave V) in the clinic. The commonly used clinical method of peak localization is the manual labeling approach by subjective visualization. However, this method is time-consuming and highly dependent on the experience of the clinician. In this study, three different types of neural networks were proposed to realize the automatic intelligent recognition of the wave V position. Firstly, during the data preprocessing, the ABR data of humans was clipped and normalized. Then three types of neural networks, namely DNN, CNN, and RNN, were proposed for the latency localization of wave V. The performances of these three networks were further evaluated under different sound pressure levels and different error scales. The results showed that DNN was the best network for localizing the wave V position. The highest overall accuracy rate was 91.70% and the error scale was 0.1ms. This study showed that the proposed automatic method with neural networks can greatly reduce the workload of medical personnel in finding the ABR latencies and can assist doctors in further diagnosis. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Vehicle Trajectories Prediction via Nearest Neighbor Historical Behavior

Vehicle Trajectories Prediction via Nearest Neighbor Histori...

引用

2023 IEEE International Conference on Robotics and Biomimetics, ROBIO 2023

作者： Wang, Wanting Zhang, Qieshi Li, Xuesong Tang, Jian Liu, Dong Cheng, Jun Chinese Academy of Sciences Cas Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institute of Advanced Technology Shenzhen China University of Chinese Academy of Sciences Shenzhen College of Advanced Technology Beijing China The Chinese University of Hong Kong Hong Kong Co. Ltd China

ISBN: (纸本)9798350325706

Trajectory prediction is crucial in enabling autonomous driving systems to make informed decisions, plan appropriate paths, and enhance traffic safety and efficiency. It remains an immensely challenging task due to complex interaction between vehicles, the difficulty of extracting traffic rules information, and the dynamic changes in traffic flow. Existing methods model the interactions among vehicles or extract traffic flow density features, but overlook the effects of neighboring vehicles' movements and interactions, which contain traffic rules and the influence of surrounding traffic conditions. To achieve this, we propose a new method taking into account neighboring vehicles' dynamic behaviors and history, allowing for a more comprehensive understanding of the traffic environment. Firstly, a novel dual-stream nearest vehicle attention mechanism method is proposed that leverages the historical state and position of the neighbors' vehicle and captures its features. Secondly, in order to effectively encode these features, we recombine them by the multi-head attention mechanism. Lastly, in order to fusion these features and other inputs, we extract and combine the relationships between them by a self-attention mechanism. Our approach not only outperforms other methods in evaluation metrics but also demonstrates excellent results in real-world scenarios. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multimodal Action Quality Assessment

arXiv

引用

arXiv 2024年

作者： Zeng, Ling-An Zheng, Wei-Shi The School of Artificial Intelligence Sun Yat-sen University Guangzhou China The School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Guangdong Province Key Laboratory of Information Security China The Key Laboratory of Machine Intelligence and Advanced Computing Sun Yat-sen University Ministry of Education China

Action quality assessment (AQA) is to assess how well an action is performed. Previous works perform modelling by only the use of visual information, ignoring audio information. We argue that although AQA is highly dependent on visual information, the audio is useful complementary information for improving the score regression accuracy, especially for sports with background music, such as figure skating and rhythmic gymnastics. To leverage multimodal information for AQA, i.e., RGB, optical flow and audio information, we propose a Progressive Adaptive Multimodal Fusion Network (PAMFN) that separately models modality-specific information and mixed-modality information. Our model consists of with three modality-specific branches that independently explore modality-specific information and a mixed-modality branch that progressively aggregates the modality-specific information from the modality-specific branches. To build the bridge between modality-specific branches and the mixed-modality branch, three novel modules are proposed. First, a Modality-specific Feature Decoder module is designed to selectively transfer modality-specific information to the mixed-modality branch. Second, when exploring the interaction between modality-specific information, we argue that using an invariant multimodal fusion policy may lead to suboptimal results, so as to take the potential diversity in different parts of an action into consideration. Therefore, an Adaptive Fusion Module is proposed to learn adaptive multimodal fusion policies in different parts of an action. This module consists of several FusionNets for exploring different multimodal fusion strategies and a PolicyNet for deciding which FusionNets are enabled. Third, a module called Cross-modal Feature Decoder is designed to transfer cross-modal features generated by Adaptive Fusion Module to the mixed-modality branch. Our extensive experiments validate the efficacy of the proposed method, and our method achieves state-of-the-a

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Interpretable Drug Response Prediction through Molecule Structure-aware and Knowledge-Guided Visible Neural Network

Interpretable Drug Response Prediction through Molecule Stru...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Jiancong Xie Zhe Zhang Youyou Li Jiahua Rao Yuedong Yang School of Computer Science and Engineering Sun Yat-sen University China Department of Chemistry University of Chicago Illinois USA Key Laboratory of Machine Intelligence and Advanced Computing of MOE Sun Yat-sen University China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Precise prediction of anti-cancer drug responses has become a crucial obstruction in anti-cancer drug design and clinical applications. In recent years, various deep learning methods have been applied to drug response prediction and become more accurate. However, they are still criticized as being non-transparent. To offer reliable drug response prediction in real-world applications, there is still a pressing demand to develop a model with high predictive performance as well as interpretability. In this study, we propose DrugVNN, an end-to-end interpretable drug response prediction framework, which extracts gene features of cell lines through a knowledge-guided visible neural network (VNN) and learns drug representation through a node-edge communicative message passing network (CMPNN). Additionally, between these two networks, a novel drug-aware gene attention gate is designed to direct the drug representation to VNN to simulate the effects of drugs. By evaluating on the GDSC dataset, DrugVNN achieved state-of-the-art performance. Moreover, DrugVNN can identify active genes and relevant signaling pathways for specific drug-cell line pairs with supporting evidence in the literature, implying the interpretability of our model.

关键词： Drugs Deep learning Message passing Biological system modeling Neural networks Pressing Predictive models Logic gates Feature extraction Reliability

来源：评论

学校读者我要写书评

暂无评论

Accurate Prediction of Knee Joint Angles Using a Hybrid CNN-LSTM-Attention Network from Surface Electromyography

Accurate Prediction of Knee Joint Angles Using a Hybrid CNN-...

引用

2024 IEEE International Conference on Robotics and Biomimetics, ROBIO 2024

作者： Wang, Zhuo Chen, Hui Yang, Fangliang Wang, Xiangyang Wu, Xinyu Chen, Chunjie Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen518055 China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen518055 China University of Chinese Academy of Sciences Beijing100049 China

ISBN: (纸本)9781665481090

In various fields such as robotics, rehabilitation, biomechanics, human-machine interfaces, and clinical research, human motion prediction has extensive applications. A hybrid networks model based on Convolutional Neural Network-Long Short-Term Memory-Attention (CNN-LSTM-Attention) was employed in this paper to extract features from the high-dimensional space and time series of surface electromyography (sEMG) data for continuous prediction of knee angles. Five able-bodied subjects participated in the study, walking at a self-selected pace while six surface electromyography (sEMG) signals from muscles involved in knee flexion and extension, along with knee angles, were synchronously recorded. The performance was assessed using the root mean square error (RMSE), Pearson Correlation Coefficient (r), and coefficient of determination (R2) between estimated and measured knee joint angles. Compared to the CNN, LSTM, and CNN-LSTM algorithms, the adopted method estimated knee angles more accurately, achieving an average RMSE, ρ, and R2 of 3.09± 0.90,\ 0.9911 ± 0.0052, and 0.9817± 0.0108, respectively. As the advance time increased, the accuracy of knee joint angle estimation decreased, particularly when the advance time reached 100 ms, at which point the RMSE is 4.83 degress. In addition, the computing time of the prediction model was less than 1 ms, which was shorter than the advance time 100 ms it could predict, thereby facilitating real-time computation in practical environments. Compared to previous studies, the proposed method excelled at extracting features directly from raw signals, avoiding the need for handcrafted feature extraction. Consequently, the model effectively achieved continuous and accurate predictions of joint motion angles and demonstrated potential to reduce latency in the human-machine interface. © 2024 IEEE.

关键词： Clinical research

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：