检索结果-内蒙古大学图书馆

Structured probabilistic end-to-end learning from crowds 29

学校读者我要写书评

暂无评论

Structured probabilistic end-to-end learning from crowds

29th International Joint Conference on Artificial Intelligence, IJCAI 2020

作者： Chen, Zhijun Wang, Huimin Sun, Hailong Chen, Pengpeng Han, Tao Liu, Xudong Yang, Jie SKLSDE Lab School of Computer Science and Engineering Beihang University China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University China Web Information Systems Delft University of Technology Netherlands

ISBN: (纸本)9780999241165

End-to-end learning from crowds has recently been introduced as an EM-free approach to training deep neural networks directly from noisy crowdsourced annotations. It models the relationship between true labels and annotations with a specific type of neural layer, termed as the crowd layer, which can be trained using pure backpropagation. Parameters of the crowd layer, however, can hardly be interpreted as annotator reliability, as compared with the more principled probabilistic approach. The lack of probabilistic interpretation further prevents extensions of the approach to account for important factors of annotation processes, e.g., instance difficulty. This paper presents SpeeLFC, a structured probabilistic model that incorporates the constraints of probability axioms for parameters of the crowd layer, which allows to explicitly model annotator reliability while benefiting from the end-to-end training of neural networks. Moreover, we propose SpeeLFC-D, which further takes into account instance difficulty. Extensive validation on real-world datasets shows that our methods improve the state-of-the-art. © 2020 Inst. Sci. inf., Univ. Defence in Belgrade. All rights reserved.

关键词： Deep neural networks

Heterogeneous influence of individuals’ behavior on mask efficacy in gathering environments

学校读者我要写书评

暂无评论

Frontiers of engineering Management 2022年第4期9卷 550-562页

作者： Haochen SUN Xiaofan LIU Zhanwei DU Ye WU Haifeng ZHANG Xiaoke XU College of Information and Communication Engineering Dalian Minzu UniversityDalian 116600China Web Mining Laboratory Department of Media and CommunicationCity University of Hong KongHong KongChina WHO Collaborating Centre for Infectious Disease Epidemiology and Control School of Public HealthLi Ka Shing Faculty of MedicineThe University of Hong KongHong KongChina Laboratory of Data Discovery for Health Hong Kong Science and Technology ParkHong KongChina Computational Communication Research Center Beijing Normal University(Zhuhai)Zhuhai 519087China School of Journalism and Communication Beijing Normal UniversityBeijing 100875China Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Mathematical ScienceAnhui UniversityHefei 230601China

Wearing masks is an easy way to operate and popular measure for preventing *** masks can slow down the spread of viruses,their efficacy in gathering environments involving heterogeneous person-to-person contacts remains ***,we aim to investigate the epidemic prevention effect of masks in different real-life gathering *** study uses four real interpersonal contact datasets to construct four empirical networks to represent four gathering *** transmission of COVID-19 is simulated using the Monte Carlo simulation *** heterogeneity of individuals can cause mask efficacy in a specific gathering environment to be different from the baseline efficacy in general ***,the heterogeneity of gathering environments causes the epidemic prevention effect of masks to *** masks can greatly reduce the probability of clustered epidemics and the infection scale in primary schools,high schools,and ***,the use of masks alone in primary schools and hospitals cannot control *** high schools with social distancing between classes and in workplaces where the interpersonal contact is relatively sparse,masks can meet the need for *** the heterogeneity of individual behavior,if individuals who are more active in terms of interpersonal contact are prioritized for mask-wearing,the epidemic prevention effect of masks can be ***,asymptomatic infection has varying effects on the prevention effect of masks in different *** effect can be weakened or eliminated by increasing the usage rate of masks in high schools and ***,the effect on primary schools and hospitals cannot be *** study contributes to the accurate evaluation of mask efficacy in various gathering environments to provide scientific guidance for epidemic prevention.

关键词： COVID-19 masks behavioral heterogeneity asymptomatic infection

NEW: A Generic Learning Model for Tie Strength Prediction in Networks

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Liu, Zhen Li, Hu Wang, Chao Web Sciences Center School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China Big Data Research Center School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China School of Electrical Engineering ChongQing University Chongqing China

Tie strength prediction, sometimes named weight prediction, is vital in exploring the diversity of connectivity pattern emerged in networks. Due to the fundamental significance, it has drawn much attention in the field of network analysis and mining. Some related works appeared in recent years have significantly advanced our understanding of how to predict the strong and weak ties in the social networks. However, most of the proposed approaches are scenario-aware methods heavily depending on some special contexts and even exclusively used in social networks. As a result, they are less applicable to various kinds of *** contrast to the prior studies, here we propose a new computational framework called Neighborhood Estimating Weight (NEW) which is purely driven by the basic structure information of the network and has the flexibility for adapting to diverse types of networks. In NEW, we design a novel index, i.e., connection inclination, to generate the representative features of the network, which is capable of capturing the actual distribution of the tie strength. In order to obtain the optimized prediction results, we also propose a parameterized regression model which approximately has a linear time complexity and thus is readily extended to the implementation in large-scale networks. The experimental results on six real-world networks demonstrate Copyright © 2020, The Authors. All rights reserved.

关键词： Forecasting

Spectral-spatial anomaly detection of hyperspectral data based on improved isolation forest

学校读者我要写书评

暂无评论

TechRxiv

TechRxiv 2021年

作者： Song, Xiangyu Aryal, Sunil Ting, Kai Ming Liu, Zhen He, Bin Changchun130033 China The University of Chinese Academy of Sciences Beijing100049 China The School of Information Technology Deakin University 75 Pigdons Rd Waurn Ponds VIC3216 Australia National Key Laboratory for Novel Software Technology Nanjing University Nanjing210023 China Big Data Research Center and Web Sciences Center School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu611731 China

Anomaly detection in hyperspectral image is affected by redundant bands and the limited utilization capacity of spectral-spatial information. In this article, we propose a novel Improved Isolation Forest (IIF) algorithm based on the assumption that anomaly pixels are more susceptible to isolation than the background pixels. The proposed IIF is a modified version of the Isolation Forest (iForest) algorithm, which addresses the poor performance of iForest in detecting local anomalies and anomaly detection in high-dimensional data. Further, we propose a spectral-spatial anomaly detector based on IIF (SSIIFD) to make full use of global and local information, as well as spectral and spatial information. To be specific, first, we apply the Gabor filter to extract spatial features, which are then employed as input to the Relative Mass Isolation Forest (ReMass-iForest) detector to obtain the spatial anomaly score. Next, original images are divided into several homogeneous regions via the Entropy Rate Segmentation (ERS) algorithm, and the preprocessed images are then employed as input to the proposed IIF detector to obtain the spectral anomaly score. Finally, we fuse the spatial and spectral anomaly scores by combining them linearly to predict anomaly pixels. The experimental results on four real hyperspectral data sets demonstrate that the proposed detector outperforms other state-of-the-art methods. © 2021, CC BY.

关键词： Anomaly detection

AI Models Close to your Chest: Robust Federated Learning Strategies for Multi-site CT

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Lee, Edward H. Kelly, Brendan Altinmakas, Emre Dogan, Hakan Mohammadzadeh, Maryam Colak, Errol Fu, Steve Choudhury, Olivia Ratan, Ujjwal Kitamura, Felipe Chaves, Hernan Zheng, Jimmy Said, Mourad Reis, Eduardo Lim, Jaekwang Yokoo, Patrícia Mitchell, Courtney Houshmand, Golnaz Ghassemi, Marzyeh Killeen, Ronan Qiu, Wendy Hayden, Joel Rafiee, Farnaz Klochko, Chad Bevins, Nicholas Sazgara, Faeze Wong, S. Simon Moseley, Michael Halabi, Safwan Yeom, Kristen W. School of Medicine Stanford University United States Insight Centre for Data Analytics University College Dublin Ireland Icahn School of Medicine at Mount Sinai United States Koç University School of Medicine Turkey Division of Neuroradiology Amiralam Hospital Tehran University of Medical Sciences Iran Unity Health Toronto St. Michael’s Hospital University of Toronto Canada Amazon Web Services United States Universidade Federal de São Paulo Brazil Fleni Argentina Radiology Department Centre International Carthage Médicale Monastir Tunisia Hospital Israelita Albert Einstein SP São Paulo Brazil Department of Radiology Kyungpook National University Hospital Korea Republic of Department of Radiology St. Joseph’s Hospital and Medical Center United States Rajaie Cardiovascular Medical and Research Center Iran University of Medical Sciences Iran Dept. of Electrical Engineering and Computer Science at MIT United States Department of Radiology Henry Ford Health System DetroitMI United States Department of Radiology Guilan University of Medical Sciences Iran Department of Electrical Engineering Stanford University United States Ann & Robert H. Lurie Children's Hospital of Chicago United States

While it is well known that population differences from genetics, sex, race, and environmental factors contribute to disease, AI studies in medicine have largely focused on locoregional patient cohorts with less diverse data sources. Such limitation stems from barriers to large-scale data share and ethical concerns over data privacy. Federated learning (FL) is one potential pathway for AI development that enables learning across hospitals without data share. In this study, we show the results of various FL strategies on one of the largest and most diverse COVID-19 chest CT datasets: 21 participating hospitals across five continents that comprise >10,000 patients with >1 million images. We also propose an FL strategy that leverages synthetically generated data to overcome class and size imbalances. We also describe the sources of data heterogeneity in the context of FL, and show how even among the correctly labeled populations, disparities can arise due to these biases. Copyright © 2023, The Authors. All rights reserved.

关键词： Hospitals

Crank Call Detection Models Based on Call data of Telephone Subscribers

学校读者我要写书评

暂无评论

Journal of Physics: Conference Series 2020年第1期1673卷

作者： Wenbo Xie Zhen Liu Yan Fu Big Data Research Center University of Electronic Science and Technology of China Chengdu 611731 People's Republic of China Web Sciences Center School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu 611731 People's Republic of China

data explosion makes our life much more convenient than ever. For example, people always get timely news from Apps, and get interesting recommendations when shopping online. However, these conveniences come by probing people's private data, such as account information, search history, and chat records. Thus, if the management of data is not as secure as it supposes to be, many problems, e.g., crank calls, will arise and cause big troubles in people's lives. Although many security Apps have been developed to help mobile phone users stay away from crank calls, the users need to update Apps frequently due to their user-labels-based blacklist. These feedback-based systems depend on a large number of user actions that have significant lag. In this paper, we propose two crank call detection models to help operators mark crank callers based on the call data of telephone subscribers, in which the features are organized by different ways. One is a composited classification model, and the other is a convolutional neural network model based on the time-sliced data. The experiments show that the model applying convolutional neural network gets better accuracies in detecting crank calls.

关键词：

Zero-determinant Strategies for Three-player in Finitely Repeated Games

学校读者我要写书评

暂无评论

Zero-determinant Strategies for Three-player in Finitely Rep...

第37届中国控制会议

作者： Jianzhang Chen Zhihai Rong College of Computer and Information Sciences Fujian Agriculture and Forestry University CompleX Lab Web Sciences CenterUniversity of Electronic Science and Technology of China Big Data Research Center University of Electronic Science and Technology of China School of Computer Science and Engineering University of Electronic Science and Technology of China

Zero-determinant strategies are a new class of probabilistic and conditional strategies, where a player can use a linear relationship between his own payoff and the opponents payoff to determine his opponents expected payoff or extort his opponents unilaterally. This paper will analysis a model of zero-determinant strategies for three players in the finitely repeated public goods game（with a discount factor δ satisfying 0 ＜ δ ＜ 1）. Via analyzing these strategies for three players in the game, including equalizer strategies, extortion strategies and generous strategies, it finds that a player also has an ability to pin the expected total payoff of all other players in a unilateral way as the two-player model by equalizer strategies and can set a ratio between his payoff and the total payoff of all other players by the extortion strategies, and the expected payoffs of three players can obtain the same payoff when they cooperate in the first round by using generous strategies. This provides potential clues to design efficient cooperation protocol in multi-agent systems.

关键词： Zero-determinant Strategies Finitely Repeated Games Direct reciprocity Discount factor

A model for meme popularity growth in social networking systems based on biological principle and human interest dynamics

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Wang, Le-Zhi Zhao, Zhi-Dan Jiang, Jun-Jie Guo, Bing-Hui Wang, Xiao Huang, Zi-Gang Lai, Ying-Cheng School of Electrical Computer and Energy Engineering Arizona State University TempeAZ85287 United States Web Sciences Center Big Data Research Center University of Electronic Science and Technology of China Chengdu610054 China School of Mathematics Beihang University Beijing100191 China School of Biological and Health Systems Engineering Arizona State University TempeAZ85287 United States School of Life Science and Technology Xi'An Jiaotong University Xi'an710049 China Institute of Computational Physics and Complex Systems Lanzhou University Lanzhou Gansu730000 China Department of Physics Arizona State University TempeAZ85287 United States

We analyze five big data sets from a variety of online social networking (OSN) systems and find that the growth dynamics of meme popularity exhibit characteristically different behaviors. For example, there is linear growth associated with online recommendation and sharing platforms, a plateaued (or an \S"-shape) type of growth behavior in a web service devoted to helping users to collect bookmarks, and an exponential increase on the largest and most popular microblogging website in China. Does a universal mechanism with a common set of dynamical rules exist, which can explain these empirically observed, distinct growth behaviors? We provide an affirmative answer in this paper. In particular, inspired by biomimicry to take advantage of cell population growth dynamics in microbial ecology, we construct a base growth model for meme popularity in OSNs. We then take into account human factors by incorporating a general model of human interest dynamics into the base model. The final hybrid model contains a small number of free parameters that can be estimated purely from data. We demonstrate that our model is universal in the sense that, with a few parameters estimated from data, it can successfully predict the distinct meme growth dynamics. Our study represents a successful effort to exploit principles in biology to understand online social behaviors by incorporating the traditional microbial growth model into meme popularity. Our model can be used to gain insights into critical issues such as classification, robustness, optimization, and control of OSN systems. Copyright © 2019, The Authors. All rights reserved.

关键词： Social networking (online)

The effect of non-Markovian recovery on reversible failure propagation on networks

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Lin, Zhaohua Feng, Mi Tang, Ming Liu, Zonghua Hui, Pak Ming Lai, Ying-Cheng Department of Physics East China Normal University Shanghai200062 China School of Information Science Technology East China Normal University Shanghai200241 China Web Sciences Center University of Electronic Science and Technology of China Chengdu611731 China Big Data Research Center University of Electronic Science and Technology of China Chengdu611731 China Shanghai Key Laboratory of Multidimensional Information Processing East China Normal University Shanghai200241 China Department of Physics Chinese University of Hong Kong Shatin Hong Kong School of Electrical Computer and Energy Engineering Arizona State University TempeAZ85287 United States

Compared with the classical irreversible failure propagation, the spontaneous recovery model can better depict the failure propagation on network systems such as financial and transportation networks. In this paper, we study how the non-Markovian recovery process influences cascading failure dynamics in the spontaneous recovery systems. To this end, we compare two kinds of failure-recovery models: the non-Markovian recovery (NMR) model and the corresponding Markovian recovery (MR) model. We first develop a Pairwise approximation theory for the MR and NMR models, which can predict the time evolution, steady state, and hysteresis behaviour of failure-recovery systems more accurately than the classical mean-field (MF) method. We find that although the non-Markovian recovery mechanism does not essentially affect the steady state and hysteresis behaviour of failure-recovery systems, the two models exhibit distinct evolution processes. When investigating the effect of initial conditions on the phase transition and hysteresis behavior, we find in the hysteresis region, the NMR model exhibits a non-monotonic growth characteristic: with the increase of initial failed nodes, the steady state staying in relative low-failure phase first turns into relative high-failure phase, and then into relative low-failure phase again. We then use the MF theory to explain the phenomenon qualitatively and point out when considering non-Markovian dynamics, we should study the steady state not only from the perspective of the variation of parameters, but also from the initial conditions. Copyright © 2019, The Authors. All rights reserved.

关键词： Hysteresis