检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Zhang, Zaixi Liu, Qi Wang, Zhicai Lu, Zepu Hu, Qingyong Anhui Province Key Lab of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China China State Key Laboratory of Cognitive Intelligence Anhui Hefei China Hong Kong University of Science and Technology Hong Kong University of Science and Technology of China China

Deep neural networks (DNNs) are recently shown to be vulnerable to backdoor attacks, where attackers embed hidden backdoors in the DNN model by injecting a few poisoned examples into the training dataset. While extensive efforts have been made to detect and remove backdoors from backdoored DNNs, it is still not clear whether a backdoor-free clean model can be directly obtained from poisoned datasets. In this paper, we first construct a causal graph to model the generation process of poisoned data and find that the backdoor attack acts as the confounder, which brings spurious associations between the input images and target labels, making the model predictions less reliable. Inspired by the causal understanding, we propose the Causality-inspired Backdoor Defense (CBD), to learn deconfounded representations for reliable classification. Specifically, a backdoored model is intentionally trained to capture the confounding effects. The other clean model dedicates to capturing the desired causal effects by minimizing the mutual information with the confounding representations from the backdoored model and employing a sample-wise re-weighting scheme. Extensive experiments on multiple benchmark datasets against 6 state-of-the-art attacks verify that our proposed defense method is effective in reducing backdoor threats while maintaining high accuracy in predicting benign samples. Further analysis shows that CBD can also resist potential adaptive attacks. The code is available at https://***/zaixizhang/CBD. © 2023, CC BY-NC-SA.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Robot and its living space:A roadmap for robot development based on the view of living space

引用

Digital Communications and Networks 2021年第4期7卷 505-517页

作者： Xiaofeng Cai Huansheng Ning Sahraoui Dhelim Rongjuan Zhou Tao Zhang Yang Xu Yueliang Wan School of Computer and Communication Engineering University of Science and Technology Beijing Beijing 100083China Beijing Engineering Research Center for Cyberspace Data Analysis and Applications Beijing 100083China School of Foreign Studies University of Science and Technology Beijing Beijing 100083China Key Lab of Information Network Security Ministry of Public SecurityChina Run Technologies Co. LidBeijing China

Robot’s living space Human-robot relationship Robot humanization Hybrid intelligence Human-robot integrated society Robots,as the creation of humans,became an irreplaceable component in human *** the advancement of technologies,robots have become more and more intelligent and have been widely used in many fields,such as disease diagnosis,customer services,healthcare for the older people,and so *** robots made our lives much more convenient than ever before,they also brought many potential risks and challenges in technology,security,and *** better understand the development of robots,we proposed a concept of a robot’s living space and analyzed the role of robots in our *** this paper,we focus on setting a theoretical framework of the robot’s living space to further understand the human-robot *** research in this paper contains three central ***,we interpret the concept of the robot’s living space and the functions of each ***,we analyze and summarize the relative technologies which support robots living well in each ***,we provide advice and improvement measures based on a discussion of potential problems caused by the developments of *** the trend of robots humanization and human-robot society integration,we should seriously consider how to collaborate with intelligent robots to achieve hybrid *** build a harmonious human-robot integrated society,studying the robot’s living space and its relationship with humans is the prerequisite and roadmap.

关键词： Robot's living space Human-robot relationship Robot humanization Hybrid intelligence Human-robot integrated society

来源：评论

学校读者我要写书评

暂无评论

Dedolomitization establishes flow pathways in Thalassinoides-bearing limestones: a quantitative case study using pore network model and flow simulation

引用

Arabian Journal of Geosciences 2023年第3期16卷 1-16页

作者： da Costa Pedro Calombe, Onilde Wohnrath Tognoli, Francisco Manoel Zolfaghari, Arsalan Silva Santisteban, Tomas VizGEO Sci Data Lab São Leopoldo Brazil Applied Natural Sciences Center (UNESPetro) São Paulo State University Rio Claro Brazil Materials and Structural Analysis Thermo Fisher Scientific Houston USA Oxford Instruments Andor Technology Houston USA

The pore space of rocks acts as a storage for geofluids (oil, gas, water, CO2, contaminants, and metal-enriched solutions) and has been the target of studies approaching fluid flow in different scales. The behavior of fluid phases in porous media has had an increasing interest with the development of high-resolution imaging techniques (e.g., micro- and nano-computed tomography) and scanning microscopy. However, the characterization of the complex pore systems associated with bioturbated limestones is still incipient on the microscale. An integrated approach involving imaging techniques and petrographic analysis was necessary to understand the development of pore connections in dolomitized Thalassinoides galleries. In this study, the porosity distributed inside an intricate network of tubular Thalassinoides burrows is strongly controlled by different diagenetic processes that caused cement precipitation and dissolution of allochem grains and cements through time. High-resolution micro-computed tomography images allowed reconstruction of the 3D pore network model and supported quantitative analysis based on 4831 pores and 2141 throats extracted from the volume of interest. We determined connected pores along axes X, Y, and Z. Only five percent of the pore radii are larger than 5 µm and connected with more than 5 pores. There is a general trend of more connections associated with the large pores. However, the flow pathways have pore connectivity controlled by interactions pore-to-pore in dissolved dolomite crystals. This confirms results from simulations inside the porous zones associated with dolomites. Single-phase flow calculated absolute permeability of 191.9 (X), 0.0 (Y), and 36.76 md (Z). Two-phase flow simulations computed capillary pressures, resistivity indexes, and relative permeabilities curves during primary drainage, imbibition, and secondary drainage to quantify the effectiveness of this biogenically influenced porous conduits.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Correlation Information-based Spatiotemporal Network for Traffic Flow Forecasting

arXiv

引用

arXiv 2022年

作者： Zhu, Weiguo Sun, Yongqi Yi, Xintong Wang, Yan School of Computer and Information Technology Beijing Jiaotong University Beijing100044 China Beijing Key Lab of Traffic Data Analysis and Mining Beijing100044 China

The technology of traffic flow forecasting plays an important role in intelligent transportation systems. Based on graph neural networks and attention mechanisms, most previous works utilize the transformer architecture to discover spatiotemporal dependencies and dynamic relationships. However, they have not considered correlation information among spatiotemporal sequences thoroughly. In this paper, based on the maximal information coefficient, we present two elaborate spatiotemporal representations, spatial correlation information (SCorr) and temporal correlation information (TCorr). Using SCorr, we propose a correlation information-based spatiotemporal network (CorrSTN) that includes a dynamic graph neural network component for integrating correlation information into spatial structure effectively and a multi-head attention component for modeling dynamic temporal dependencies accurately. Utilizing TCorr, we explore the correlation pattern among different periodic data to identify the most relevant data, and then design an efficient data selection scheme to further enhance model performance. The experimental results on the highway traffic flow (PEMS07 and PEMS08) and metro crowd flow (HZME inow and outow) datasets demonstrate that CorrSTN outperforms the state-of-the-art methods in terms of predictive performance. In particu-lar, on the HZME (outow) dataset, our model makes significant improvements compared with the ASTGNN model by 12.7%, 14.4% and 27.4% in the metrics of MAE, RMSE and MAPE, respectively. 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

D2TV: Dual Knowledge Distillation and Target-oriented Vision Modeling for Many-to-Many Multimodal Summarization

arXiv

引用

arXiv 2023年

作者： Liang, Yunlong Meng, Fandong Wang, Jiaan Xu, Jinan Chen, Yufeng Zhou, Jie Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University Beijing China Pattern Recognition Center WeChat AI Tencent Inc China School of Computer Science and Technology Soochow University Suzhou China

Many-to-many multimodal summarization (M3S) task aims to generate summaries in any language with document inputs in any language and the corresponding image sequence, which essentially comprises multimodal monolingual summarization (MMS) and multimodal cross-lingual summarization (MXLS) tasks. Although much work has been devoted to either MMS or MXLS and has obtained increasing attention in recent years, little research pays attention to the M3S task. Besides, existing studies mainly focus on 1) utilizing MMS to enhance MXLS via knowledge distillation without considering the performance of MMS or 2) improving MMS models by filtering summary-unrelated visual features with implicit learning or explicitly complex training objectives. In this paper, we first introduce a general and practical task, i.e., M3S. Further, we propose a dual knowledge distillation and target-oriented vision modeling framework for the M3S task. Specifically, the dual knowledge distillation method guarantees that the knowledge of MMS and MXLS can be transferred to each other and thus mutually prompt both of them. To offer target-oriented visual features, a simple yet effective target-oriented contrastive objective is designed and responsible for discarding needless visual information. Extensive experiments on the many-to-many setting show the effectiveness of the proposed approach. Additionally, we will contribute a many-to-many multimodal summarization (M3Sum) dataset. Copyright © 2023, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

PresRecCD: A Novel Herbal Prescription Recommendation Framework with Cross-Domain Learning and Neural Collaborative Filtering

PresRecCD: A Novel Herbal Prescription Recommendation Framew...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Wansong Zhang Xin Dong Kuo Yang Lei Zhang Xinyu Wang Rouye Huang Runshun Zhang Xuezhong Zhou Department of Artificial Intelligence Institute of Medical Intelligence Beijing Key Lab of Traffic Data Analysis and Mining School of Computer Science & Technology Beijing Jiaotong University Beijing China National Data Center of Traditional Chinese Medicine China Academy of Chinese Medical Sciences Beijing China Guang’Anmen Hospital China Academy of Chinese Medical Sciences Beijing China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Herbal prescriptions hold significant importance in Traditional Chinese Medicine (TCM) diagnosis and treatment, embodying millennia of clinical case summaries and wisdom. Despite numerous proposed methods for herbal prescription recommendation (HPR), significant challenges persist due to the lack of comprehensive clinical data, particularly regarding the relationships between symptoms and herbs. This scarcity poses considerable hurdles for effective HPR modeling. In this study, we introduced a novel herbal prescription recommendation framework with cross-domain learning and neural collaborative filtering (termed PresRecCD). The cross-domain learning mechanism is introduced to learn the noise-reduced cross-domain features of herbs and symptoms in the unified space, alleviating the sparsity of data, and neural collaborative filtering is utilized to carry out prescription recommendations. Comprehensive experiments demonstrate the superiority of the proposed PresRecCD model over the SOTA model. This study contributes to enhancing the performance of the HPR model, ultimately benefiting the efficiency and precision of clinical treatment.

关键词： Learning systems Accuracy Collaborative filtering Biological system modeling Predictive models Bioinformatics Medical diagnostic imaging Context modeling

来源：评论

学校读者我要写书评

暂无评论

Developing Measurement-Informed Methane Emissions Inventory Estimates at Midstream Compressor Stations

ACS ES&T Air

引用

ACS ES&T Air 2025年第3期2卷 358-367页

作者： Arvind P. Ravikumar Hugh Li Shuting Lydia Yang Mackenzie L. Smith Center for Energy and Environmental Systems Analysis (CEESA) The University of Texas at Austin Austin Texas 78712 United States；Energy Emissions Modeling and Data Lab The University of Texas at Austin Austin Texas 78712 United States；Department of Petroleum and Geosystems Engineering The University of Texas at Austin Austin Texas 78712 United States Department of Systems Engineering Harrisburg University of Science and Technology Harrisburg Pennsylvania 17101 United States Center for Energy and Environmental Systems Analysis (CEESA) The University of Texas at Austin Austin Texas 78712 United States；Energy Emissions Modeling and Data Lab The University of Texas at Austin Austin Texas 78712 United States Champion X The Woodlands Texas 77381 United States

Natural gas transmissions and storage compressor stations account for the largest share of anthropogenic methane (CH4) emissions in New York State (NYS). Yet, NYS’s CH4emissions inventory is based on measurements that are a decade old and potentially unlikely to be representative of NYS operations. Here, we present results from a comprehensive, multiscale aerial CH4measurement campaign across all NYS transmission and storage compressor stations. We find a skewed emissions distribution, with 20% of stations accounting for 74% of total CH4emissions. Emissions at engine-driven compressor stations are, on average, 3–4× higher than emissions at turbine-driven compressor stations, thus demonstrating the need for separate emissions factors for engine- and turbine-drive compressor stations. Overall, measurement-informed emissions inventory from midstream transmission and storage compressor stations in NYS is 72% and 69% lower than the current NYS inventory, respectively. We estimate updated emissions factors of 464 [95% CI: 162–920] metric ton (MT) CH4/station/yr and 139 [97, 191] MT CH4/station/yr for engine- and turbine-based transmission compressor stations, respectively. Similarly, we estimate an updated emissions factor of 413 [164, 733] MT CH4/station/yr for engine-based storage compressor stations. These updated emissions factors, along with improved activity data, enable effective reconciliation of NYS inventory with measured *** study reports on the first large-scale measurement of methane emissions from midstream compressor stations in New York and provides a scalable approach to reconcile and update official emission inventories.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Bayesian Graph Neural Network for EEG Classification — A Win-Win on Performance and Interpretability

A Bayesian Graph Neural Network for EEG Classification — A ...

引用

International Conference on data Engineering

作者： Jing Wang Xiaojun Ning Wangjun Shi Youfang Lin School of Computer and Information Technology Beijing Jiaotong University China Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University China CAAC Key Laboratory of Intelligent Passenger Service of Civil Aviation Beijing China

With the deepening of neuroscience research, data mining of brain signals is becoming an emerging topic. Among various brain signals, electroencephalography (EEG) has attracted more and more attention due to its advantages of non-invasiveness, portability, and low cost. EEG modeling and analysis play a vital role in human healthcare. Although many machine learning algorithms have been successfully applied to data mining of EEG signals, few of them achieve a win-win in classification performance and interpretability. In this paper, we propose a Bayesian graph neural network named BayesEEGNet. Considering an electrical impulse between two nodes in the brain as a Poisson process, the countless electrical impulses generated by the brain in a period are represented as an infinite number of connection probability graphs. After coupling and transforming these probability graphs, we interpret the brain’s electrical activity state as the brain’s perceptual state. Benefiting from the joint optimization of Bayesian modules and deep neural networks, our model shows superior classification performance in sleep stage classification and emotion recognition tasks. Meanwhile, our model is able to learn interpretable functional connectivity relationships between EEG channels without any prior knowledge.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-Temporal Relationship Inference in Urban Areas

arXiv

引用

arXiv 2023年

作者： Li, Shuangli Zhou, Jingbo Liu, Ji Xu, Tong Chen, Enhong Xiong, Hui School of Computer Science and Technology University of Science and Technology of China Baidu Research China Business Intelligence Lab Baidu Research China Big Data Lab Baidu Research China School of Computer Science and Technology University of Science and Technology of China State Key Laboratory of Cognitive Intelligence China Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of China State Key Laboratory of Cognitive Intelligence China The Department of Computer Science and Engineering The Hong Kong University of Science and Technology China

Finding multiple temporal relationships among locations can benefit a bunch of urban applications, such as dynamic offline advertising and smart public transport planning. While some efforts have been made on finding static relationships among locations, little attention is focused on studying time-aware location relationships. Indeed, abundant location-based human activities are time-varying and the availability of these data enables a new paradigm for understanding the dynamic relationships in a period among connective locations. To this end, we propose to study a new problem, namely multi-Temporal relationship inference among locations (Trial for short), where the major challenge is how to integrate dynamic and geographical influence under the relationship sparsity constraint. Specifically, we propose a solution to Trial with a graph learning scheme, which includes a spatially evolving graph neural network (SEENet) with two collaborative components: spatially evolving graph convolution module (SEConv) and spatially evolving self-supervised learning strategy (SE-SSL). SEConv performs the intra-time aggregation and inter-time propagation to capture the multifaceted spatially evolving contexts from the view of location message passing. In addition, SE-SSL designs time-aware self-supervised learning tasks in a global-local manner with additional evolving constraint to enhance the location representation © 2023, CC BY.

关键词： Location

来源：评论

学校读者我要写书评

暂无评论

A Downscaled Monthly Solar-Induced Chlorophyll Fluorescence Product at 0.5-Degree Resolution Over East Asia During 1995-2003

A Downscaled Monthly Solar-Induced Chlorophyll Fluorescence ...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Yan Jin Haoyu Fan Yaojie Liu School of Geographic and Biologic Information Nanjing University of Posts and Telecommunications China Smart Health Big Data Analysis and Location Services Engineering Lab of Jiangsu Province China School of Geographic Sciences Nanjing University of Information Science and Technology China

This paper proposes a hybrid downscaling method, named random forest area-to-area regression kriging (RFATARK), to improve the resolution of the Global Ozone Monitoring Experiment (GOME) solar-induced chlorophyll fluorescence (SIF) product over East Asia during 1995-2003. The RFATARK method effectively captures the nonlinear relationships between variables and incorporates spatial variability through residual prediction. Comparative analyses with two alternative downscaling methods demonstrate the superior performance of RFATARK in enhancing the spatial patterns of the downscaled SIF data. The reconstructed 0.5-degree SIF product offers a more detailed representation of the vegetation dynamics and carbon cycle in East Asia. The proposed methodological framework can also be applied to other coarse-resolution SIF products obtained from different satellite sensors, providing valuable datasets for regional vegetation monitoring and carbon cycle modeling.

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：