检索结果-内蒙古大学图书馆

International Joint Conference on Neural networks (IJCNN)

作者： Yurun Bi Xingang Wang Qingao Wang Jinxiao Yang Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Medical Visual Question Answering (Med-VQA) is a sophisticated multimodal technology within the medical domain that utilizes natural language processing and artificial intelligence techniques. It serves as a tool in the medical field to provide information and answers, aiming to correctly respond to medical questions related to specific professional medical images. The primary goal is to assist patients in understanding their physical condition and provide decision support for healthcare professionals. While Generalized Visual Question Answering has seen significant advancements, challenges persist in the medical domain. Firstly, medical data has inherent limitations, such as the scarcity of annotated medical datasets and the complexity of medical images (including factors like noise, artifacts, and low contrast). Secondly, in terms of cross-modal fusion, there exists an intricate relationship between medical images and textual information. The complexity of the relationship between medical images and medical text, as well as the incorporation of global contextual details, pose challenges. To address these issues, this paper proposes the Feature-Enhanced network with Conditional Mixing. This innovative approach aims to overcome the scarcity and complexity of medical images without the need for additional datasets. Simultaneously, to tackle the challenge of cross-modal fusion and information interaction and to address the complex relationship between medical images and text, we propose the Cross-Adaptive Fusion network. Experimental results conducted on the VQA-RAD dataset demonstrate noticeable improvements in accuracy compared to mainstream Med-VQA models.

关键词： Visualization Accuracy Noise Neural networks Medical services Question answering (information retrieval) data models

来源：评论

学校读者我要写书评

暂无评论

Quantum Light Generation Based on GaN Microring toward Fully On-Chip Source

引用

Physical Review Letters 2024年第13期132卷 133603-133603页

作者： Hong Zeng Zhao-Qin He Yun-Ru Fan Yue Luo Chen Lyu Jin-Peng Wu Yun-Bo Li Sheng Liu Dong Wang De-Chao Zhang Juan-Juan Zeng Guang-Wei Deng You Wang Hai-Zhi Song Zhen Wang Li-Xing You Kai Guo Chang-Zheng Sun Yi Luo Guang-Can Guo Qiang Zhou Institute of Fundamental and Frontier Sciences University of Electronic Science and Technology of China Chengdu 611731 China Key Laboratory of Quantum Physics and Photonic Quantum Information Ministry of Education University of Electronic Science and Technology of China Chengdu 611731 China Department of Electronic Engineering Tsinghua University Beijing 100084 China Department of Fundamental Network Technology China Mobile Research Institute Beijing 100053 China Center for Quantum Internet Tianfu Jiangxi Laboratory Chengdu 641419 China Southwest Institute of Technical Physics Chengdu 610041 China National Key Laboratory of Materials for Integrated Circuits Shanghai Institute of Microsystem and Information Technology Chinese Academy of Sciences Shanghai 200050 China Institute of Systems Engineering AMS Beijing 100141 China CAS Key Laboratory of Quantum Information University of Science and Technology of China Hefei 230026 China

An integrated quantum light source is increasingly desirable in large-scale quantum information processing. Despite recent remarkable advances, a new material platform is constantly being explored for the fully on-chip integration of quantum light generation, active and passive manipulation, and detection. Here, for the first time, we demonstrate a gallium nitride (GaN) microring based quantum light generation in the telecom C-band, which has potential toward the monolithic integration of quantum light source. In our demonstration, the GaN microring has a free spectral range of 330 GHz and a near-zero anomalous dispersion region of over 100 nm. The generation of energy-time entangled photon pair is demonstrated with a typical raw two-photon interference visibility of 95.5±6.5%, which is further configured to generate a heralded single photon with a typical heralded second-order autocorrelation gH(2)(0) of 0.045±0.001. Our results pave the way for developing a chip-scale quantum photonic circuit.

关键词： Quantum entanglement Semiconductor quantum optics

来源：评论

学校读者我要写书评

暂无评论

Adversarial Camouflage for Node Injection Attack on Graphs

arXiv

引用

arXiv 2022年

作者： Tao, Shuchang Cao, Qi Shen, Huawei Wu, Yunfan Hou, Liang Sun, Fei Cheng, Xueqi Data Intelligence System Research Center Institute of Computing Technology Chinese Academy of Sciences Beijing China CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China

Node injection attacks on Graph Neural networks (GNNs) have received increasing attention recently, due to their ability to degrade GNN performance with high attack success rates. However, our study indicates that these attacks often fail in practical scenarios, since defense/detection methods can easily identify and remove the injected nodes. To address this, we devote to camouflage node injection attack, making injected nodes appear normal and imperceptible to defense/detection methods. Unfortunately, the non-Euclidean structure of graph data and the lack of intuitive prior present great challenges to the formalization, implementation, and evaluation of camouflage. In this paper, we first propose and define camouflage as distribution similarity between ego networks of injected nodes and normal nodes. Then for implementation, we propose an adversarial CAmouflage framework for Node injection Attack, namely CANA, to improve attack performance under defense/detection methods in practical scenarios. A novel camouflage metric is further designed under the guide of distribution similarity. Extensive experiments demonstrate that CANA can significantly improve the attack performance under defense/detection methods with higher camouflage or imperceptibility. This work urges us to raise awareness of the security vulnerabilities of GNNs in practical applications. Copyright © 2022, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Onion: Dependency-Aware Reliable Communication Protocol for Magnetic MIMO WPT System 27

Onion: Dependency-Aware Reliable Communication Protocol for ...

引用

27th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2021

作者： Liang, Xiaolun Zhou, Hao Zhou, Wangqiu Cui, Xiang Liu, Zhi Li, Xiang-Yang LINKE Lab School of Computer Science and Technology University of Science and Technology of China China The CAS Key Laboratory of Wireless-Optical Communications University of Science and Technology of China China The University of Electro-Communications Department of Computer and Network Engineering Tokyo182-8585 Japan

ISBN: (纸本)9781665408783

Magnetic wireless power transfer (WPT) has received widespread attention from both academia and industry, and magnetic resonance coupling (MRC) based WPT systems have a longer charging distance to support the scenarios with multiple transmitters (TXs) and multiple receivers (RXs). In such systems, an in-band reliable TX-RX communication protocol is essential to guarantee to charge performance. In this paper, we devise Onion, a dependency-aware in-band communication protocol for MIMO MRC-WPT systems. Technically, we extend the well-known EPCglobal C1G2 protocol in Radio Frequency Identification (RFID) fielded and make it suitable for mutual inductance based communication links in MRC-WPT systems. Furthermore, we craft an innovative onion-style layer-dependency based communication mechanism to utilize the positive impact of the relay phenomenon. We design and implement the Onion prototype and conduct extensive experiments to evaluate it. The experiment results demonstrate the effectiveness of the proposed protocol, which increases the communication success ratio by an average of 40% as compared to the dependency-unaware scheme. © 2021 IEEE.

关键词： Energy transfer

来源：评论

学校读者我要写书评

暂无评论

Observational study of the physical and chemical characteristics of the winter radiation fog in the tropical rainforest in Xishuangbanna, China

引用

science China Earth sciences 2021年第11期64卷 1982-1995页

作者： Yuan WANG Shengjie NIU Chunsong LU Jingjing LV Jing ZHANG Hongwei ZHANG Sirui ZHANG Naifu SHAO Wei SUN Yuchen JIN Qinghai SONG Collaborative Innovation Center on Forecast and Evaluation of Meteorological Disasters and Key Laboratory for Aerosol-Cloud-Precipitation of China Meteorological AdministrationNanjing University of Information Science&Technology(NUIST)Nanjing 210044China College of Safety Science and Engineering Nanjing Tech UniversityNanjing 210009China Key Laboratory of Tropical Forest Ecology(TFE) Xishuangbanna Tropical Botanical GardenChinese Academy of Sciences(CAS)Menglun 666303China Henan Meteorological Observation and Data Center Zhengzhou 450003China

We conducted a three-month field experiment focusing on the physical and chemical characteristics of fog in a tropical rainforest in Xishuangbanna,Southwest China,in the winter of *** general,the fog would form at midnight and persist because of the increased long-wave radiative cooling combined with the high relative humidity,gentle breeze,and a relatively low aerosol number concentration in the forest;the fog would dissipate before noon due to the increasing turbulence near the *** diurnal cycle is typical for radiation *** microphysical fog properties included a relatively low number concentration of the fog droplet,large droplet size,high liquid water content,narrow droplet number-size distribution,and high *** chemical properties showed that the fog water was slightly alkaline with low electrical conductivity,whereas the highest proportions of anions and cations therein were Cl^(−)and Ca^(2+),respectively;the chemical components were enriched in small fog *** addition,we indirectly calculated the fog supersaturation according to theκ-Köhler *** found that condensation broadens the droplet number-size distribution at relatively low supersaturation,which is positively correlated with the fog-droplet number concentration and negatively correlated with the droplet mean-volume diameter;this affects the key microphysical processes of fog.

关键词： Radiation fog Formation and disappearance mechanisms Physical and chemical characteristics Supersaturation Tropical rainforest

来源：评论

学校读者我要写书评

暂无评论

Research on Zenith Tropospheric Delay Model Based on TCN Improving HGPT2 Model

Research on Zenith Tropospheric Delay Model Based on TCN Imp...

引用

第十四届中国卫星导航年会

作者： Dengao Li Danyang Shi Jumin Zhao Fanming Wu Liangquan Yan Ran Feng Xinfang Zhang Jinhua Zhao College of Data Science Taiyuan University of Technology Key Laboratory of Big Data Fusion Analysis and Application of Shanxi Province Intelligent Perception Engineering Technology Center of Shanxi Shanxi Province Engineering Technology Research Center of Spatial Information Network College of Information and Computer Taiyuan University of Technology

The zenith tropospheric delay（ZTD） obtained by global navigation satellite system（GNSS） atmospheric sounding is a pivotal data source for water vapor monitoring. Meteorological changes in Antarctica play an important role in analysis of the global climate, but factors such as complex climatic conditions can limit the collection of meteorological data needed for ZTD retrieval. Therefore, it is necessary to establish high-precision ZTD models that do not rely on measured meteorological data. The existing global pressure and temperature 3（GPT3） model has limited ability to capture complex weather variations and cannot obtain high-precision GPT3TD. To address the above issues, this research proposes a high-precision ZTD model through using temporal convolutional network（TCN） for improving the hourly global pressure and temperature 2（HGPT2） model. The HGTP2 model based on Fourier analysis and the time-segmentation concept can consider the linear trend of climate variations, simultaneously the TCN is introduced to simulate the long-term temporal dependence of HGPT2TD, so as to achieve the goal of obtaining high-precision ZTD without relying on measured meteorological data. The experimental results show that the precision of TCNTD obtained from the proposed model is higher than GPT3TD and HGPT2TD when using the GNSSTD observations obtained from 35 stations in Antarctica as a reference, and the improvement of the model is obvious.

关键词： GNSS ZTD GPT3 HGPT2 TCN

来源：评论

学校读者我要写书评

暂无评论

Membership Inference Attacks via Dynamic Adversarial Perturbations Reduction

Membership Inference Attacks via Dynamic Adversarial Perturb...

引用

IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)

作者： Zehua Ding Youliang Tian Guorong Wang Jinbo Xiong Jianfeng Ma State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang China Fujian Provincial Key Laboratory of Network Security and Cryptology College of Computer and Cyber Security Fujian Normal University Fuzhou China School of Cyber Engineering Xidian University Xian China

ISBN: (数字)9798331506209

ISBN: (纸本)9798331506216

Existing membership inference attacks (MIAs) based on adversarial attacks typically introduce excessively large adversarial perturbations to change the model predictions. However, such methods are not only likely to obscure the characteristic memory of the model regarding member data but also blur the subtle characteristic differences between member and non-member data. To address this issue, we propose a novel dynamic adversarial perturbation reduction MIA (DAPR-MIA), which aims to enhance the ability to identify the membership of samples by reducing the perturbation strength. Specifically, DAPR-MIA first conducts a fine-grained analysis of the gradient components of conventional adversarial examples, assessing the impact of each element on the model decision to generate a sensitivity mask. This mask identifies dimensions within adversarial examples that significantly influence model predictions, referred to as sensitive dimensions. Then, by dynamically reducing the perturbation size in these sensitive dimensions, DAPR-MIA gradually approaches the minimum perturbation required to change the prediction result of samples, maximizing the retention of membership features within the sample. Finally, the deviation of the prediction results between the original sample and the adversarial example after perturbation attenuation on the target model is measured to infer whether the sample belongs to a member data. Experimental results show that DAPR-MIA significantly outperforms existing methods on multiple datasets and deep models, demonstrating state-of-the-art attack accuracy.

关键词： Privacy Sensitivity Perturbation methods Computational modeling Predictive models Attenuation measurement Attenuation data models Robustness Security

来源：评论

学校读者我要写书评

暂无评论

Remaining Useful Life Prediction of Lithium Battery via Neural network Ensemble 16

Remaining Useful Life Prediction of Lithium Battery via Neur...

引用

16th IEEE International Conference on Intelligent Systems and Knowledge Engineering, ISKE 2021

作者： Zhang, Hengshan Wu, Di Wang, Zhongmin Chen, Yanping Xu, Jiaxuan Xi'an University of Posts and Telecommunications School of Computer Science and Technology Xi'an710000 China Shanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi'an710000 China

ISBN: (纸本)9781665405539

Accurately predicting the Remaining Useful Life (RUL) of lithium-ion batteries is critical for accelerating the technology development. The neural network via data driven can avoid manual feature extraction and release the difficulty of model construction. However, diverse aging mechanisms, significant device variability and dynamic operating conditions have remained major challenges. The single neural network cannot tackle these challenges efficiently. In this paper, the RUL prediction of lithium battery via neural network ensemble is developed to improve the accuracy and generalization of the prediction model. The predicting results of multiple neural networks are considered as the base vectors, and the liner combination on the base vectors are conducted to obtain the ensemble RUL prediction of lithium-ion battery. The experiment is performed on the MIT-Stanford University lithium battery accelerated degradation dataset, and the experimental results show that the developed method has achieved better generalization and higher accuracy comparing with the other methods. © 2021 IEEE.

关键词： Lithium-ion batteries

来源：评论

学校读者我要写书评

暂无评论

Prediction of Ionospheric TEC based on BLS-LSTM-GRU Hybrid model

Prediction of Ionospheric TEC based on BLS-LSTM-GRU Hybrid m...

引用

第十四届中国卫星导航年会

作者： Dengao Li Xinfang Zhang Jumin Zhao Fanming Wu Ran Feng Jinhua Zhao Danyang Shi College of Data Science Taiyuan University of Technology Key Laboratory of Big Data Fusion Analysis and Application of Shanxi Province Intelligent Perception Engineering Technology Center of Shanxi Shanxi Province Engineering Technology Research Center of Spatial Information Network College of Information and Computer Taiyuan University of Technology

In satellite communications, global navigation satellite systems(GNSS) and other important space activities, the value of total electron content(TEC)in the ionosphere directly affects the size of ionospheric delay. Achieving accurate prediction of ionospheric total electron content through modeling can effectively improve the reliability and accuracy of GNSS positioning. Considering the high prediction accuracy of long short-term memory neural network(LSTM)and the fast training speed of gated recurrent unit network(GRU), but it is easy to fall into the local optimum, while the width learning system(BLS) can effectively avoid this drawback. Therefore, this paper proposes a model for predicting the total electron content of the ionosphere, which consists of a broad learning system, an LSTM network and a GRU networks. Six parameters of TEC, geomagnetic index Dst, Kp, Ap, solar activity index F10.7, and hour(HD)are selected as input features from the observed data to predict the variation of the total ionospheric electron content. The results generate prediction maps of the total ionospheric electron content and are compared with empirical models and conventional neural network models at different times and solar activity conditions. The experimental results show that the root mean square error(RMSE)of the prediction results of this BLSLSTM-GRU model is decreased by 23.07%,17.48% and 9.46%compared with the IRI-2016, NeQuick and CNN-LSTM prediction models, respectively, with higher prediction accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Graph Representation Learning for Microarchitecture Design Space Exploration

Graph Representation Learning for Microarchitecture Design S...

引用

Design Automation Conference

作者： Xiaoling Yi Jialin Lu Xiankui Xiong Dong Xu Li Shang Fan Yang State Key Laboratory of Integrated Chips and Systems Fudan University Shanghai China School of Microelectronics Fudan University Shanghai China ZTE Corporation China State Key Laboratory of Mobile Network and Mobile Multimedia Technology China China and Shanghai Key Laboratory of Data Science School of Computer Science Fudan University Shanghai China

Design optimization of modern microprocessors is a complex task due to the exponential growth of the design space. This work presents GRL-DSE, an automatic microarchitecture search framework based on graph embeddings. GRL-DSE uses graph representation learning to build a compact and continuous embedding space. Multi-objective Bayesian optimization using an ensemble surrogate model conducts microarchitecture design space exploration in the graph embedding space to efficiently and holistically optimize performance-power-area (PPA) objectives. Experimental studies on RISC-V BOOM show that GRLDSE outperforms previous techniques by 74.59% on Pareto front quality and outperforms manual designs in terms of PPA.

关键词：

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：