检索结果-内蒙古大学图书馆

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

OpenLORIS-Object: A Robotic Vision dataset and Benchmark for Lifelong Deep Learning

学校读者我要写书评

暂无评论

OpenLORIS-Object: A Robotic Vision Dataset and Benchmark for...

IEEE International Conference on Robotics and Automation (ICRA)

作者： Qi She Fan Feng Xinyue Hao Qihan Yang Chuanlin Lan Vincenzo Lomonaco Xuesong Shi Zhengwei Wang Yao Guo Yimin Zhang Fei Qiao Rosa H. M. Chan Intel Labs Robot Innovation Lab Beijing China Department of Electrical Engineering City University of Hong Kong China Department of Electronic Engineering Tsinghua University China Department of Computer Science and Engineering University of Bologna Bologna Italy Insight Centre for Data Analytics Dublin City University Ireland Imperial College The Hamlyn Centre for Robotic Surgery London UK

ISBN: (数字)9781728173955

ISBN: (纸本)9781728173962

The recent breakthroughs in computer vision have benefited from the availability of large representative datasets (e.g. ImageNet and COCO) for training. Yet, robotic vision poses unique challenges for applying visual algorithms developed from these standard computer vision datasets due to their implicit assumption over non-varying distributions for a fixed set of tasks. Fully retraining models each time a new task becomes available is infeasible due to computational, storage and sometimes privacy issues, while naïve incremental strategies have been shown to suffer from catastrophic forgetting. It is crucial for the robots to operate continuously under open-set and detrimental conditions with adaptive visual perceptual systems, where lifelong learning is a fundamental capability. However, very few datasets and benchmarks are available to evaluate and compare emerging techniques. To fill this gap, we provide a new lifelong robotic vision dataset ("OpenLORIS-Object") collected via RGB-D cameras. The dataset embeds the challenges faced by a robot in the real-life application and provides new benchmarks for validating lifelong object recognition algorithms. Moreover, we have provided a testbed of 9 state-of-the-art lifelong learning algorithms. Each of them involves 48 tasks with 4 evaluation metrics over the OpenLORIS-Object dataset. The results demonstrate that the object recognition task in the ever-changing difficulty environments is far from being solved and the bottlenecks are at the forward/backward transfer designs. Our dataset and benchmark are publicly available at https://***/dataset/object.

关键词： Task analysis Lighting Object recognition Cameras Robot vision systems Clutter

Gated recurrent neural network approach for multilabel emotion detection in microblogs

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Rathnayaka, Prabod Abeysinghe, Supun Samarajeewa, Chamod Manchanayake, Isura Walpola, Malaka J. Nawaratne, Rashmika Bandaragoda, Tharindu Alahakoon, Damminda Department of Computer Science and Engineering University of Moratuwa Sri Lanka Sri Lanka Research Centre for Data Analytics and Cognition La Trobe University Victoria

People express their opinions and emotions freely in social media posts and online reviews that contain valuable feedback for multiple stakeholders such as businesses and political campaigns. Manually extracting opinions and emotions from large volumes of such posts is an impossible task. Therefore, automated processing of these posts to extract opinions and emotions is an important research problem. However, human emotion detection is a challenging task due to the complexity and nuanced nature. To overcome these barriers, researchers have extensively used techniques such as deep learning, distant supervision, and transfer learning. In this paper, we propose a novel Pyramid Attention Network (PAN) based model for emotion detection in microblogs. The main advantage of our approach is that PAN has the capability to evaluate sentences in different perspectives to capture multiple emotions existing in a single text. The proposed model was evaluated on a recently released dataset and the results achieved the state-of-the-art accuracy of 58.9%. Copyright © 2019, The Authors. All rights reserved.

关键词： Recurrent neural networks

Collaborations and influences in new-age musician networks

学校读者我要写书评

暂无评论

AIP Conference Proceedings 2023年第1期2756卷

作者： Jia Hou Chin Kuru Ratnavelu Institute of Actuarial Science and Data Analytics UCSI University UCSI Heights 1 Jalan Puncak Menara Gading Taman Connaught 56000 Cheras Kuala Lumpur Malaysia Department of Mathematical and Actuarial Sciences Lee Kong Chian Faculty of Engineering and Science Universiti Tunku Abdul Rahman Jalan Sungai Long Bandar Sungai Long Cheras 43000 Kajang Selangor Malaysia Institute of Computer Science and Innovation UCSI University UCSI Heights 1 Jalan Puncak Menara Gading Taman Connaught 56000 Cheras Kuala Lumpur Malaysia

Music industry is evolving rapidly over the past decades due to the revolution of digital recordings and distributions. The industry is flooded with innumerable music albums, and production houses are always looking for innovative strategies to present the albums to the listeners. For instance, they rely on recommendation-based systems to get attention from the listeners. Amidst the clouds of genres and tags to differentiate and organize the digital media, listeners have their own music taste and preference. By considering new-age music genre, musician networks are constructed using the data from AllMusic and *** websites. Complex network structural properties such as nodes centralities, degree distribution, and community structure of the musician networks were investigated. The results show distinct differences in terms of defining new-age music and the main styles of new-age music. Furthermore, the musicians collaboration network reveals interesting collaboration trend in the new-age music industry. These observations may provide useful information and ideas in the establishment and improvement of music recommendation websites in near future.

关键词：

Statisfy me: What are my stats?

学校读者我要写书评

暂无评论

Statisfy me: What are my stats?

2018 ISWC Posters and Demonstrations, Industry and Blue Sky Ideas Tracks, ISWC-P and D-Industry-BlueSky 2018

作者： Sejdiu, Gezim Ermilov, Ivan Mami, Mohamed Nadjib Lehmann, Jens Smart Data Analytics University of Bonn Germany Department of Computer Science University of Leipzig Leipzig04109 Germany Fraunhofer IAIS Germany

The increasing adoption of the Linked data format, RDF, over the last two decades has brought new opportunities. It has also raised new challenges though, especially when it comes to managing and processing large amounts of RDF data. In particular, assessing the internal structure of a data set is important, since it enables users to understand the data better. One prominent way of assessment is computing statistics about the instances and schema of a data set. However, computing statistics of large RDF data is computationally expensive. To overcome this challenging situation, we previously built DistLODStats, a framework for parallel calculation of 32 statistical criteria over large RDF datasets, based on Apache Spark. Running DistLODStats is, thus, done via submitting jobs to a Spark cluster. Often times, this process is done manually, either by connecting to the cluster machine or via a dedicated resource manager. This approach is inconvenient as it requires acquiring new software skills as well as the direct interaction of users with the cluster. In order to make the use of DistLODStats easier, we propose in this paper an approach for triggering RDF statistics calculation remotely simply using HTTP requests. DistLODStats is built as a plugin into the larger SANSA Framework and makes use of Apache Livy, a novel lightweight solution for interacting with Spark cluster via a REST Interface. © 2018 CEUR-WS. All rights reserved.

关键词： Statistics

Utilizing players’ playtime records for churn prediction: Mining playtime regularity

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Yang, Wanshan Huang, Ting Zeng, Junlin Chen, Lijun Mishra, Shivakant Liu, Youjian Department of Computer Science University of Colorado Boulder Boulder United States Department of Data Analytics Yoozoo Games Shanghai China Department of Electrical Computer & Energy Engineering University of Colorado Boulder Boulder United States

—In the free online game industry, churn prediction is an important research topic. Reducing the churn rate of a game significantly helps with the success of the game. Churn prediction helps a game operator identify possible churning players and keep them engaged in the game via appropriate operational strategies, marketing strategies, and/or incentives. Playtime related features are some of the widely used universal features for most churn prediction models. In this paper, we consider developing new universal features for churn predictions for long-term players based on players’ playtime. In particular, we measure playtime regularity using the notion of entropy and cross-entropy from information theory. After we calculate the playtime regularity of players from data sets of six free online games of different types. We leverage information from players’ playtime regularity in the form of universal features for churn prediction. Experiments show that our developed features are better at predicting churners compared to baseline features. Thus, the experiment results imply that our proposed features could utilize the information extracted from players’ playtime more effectively than related baseline playtime features. Copyright © 2019, The Authors. All rights reserved.

关键词： data mining

Dynamics of cascades on burstiness-controlled temporal networks

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Unicomb, Samuel Iñiguez, Gerardo Gleeson, James P. Karsai, Márton Université de Lyon ENS de Lyon INRIA CNRS IXXI UMR 5668 Lyon69364 France Department of Network and Data Science Central European University ViennaA-1100 Austria Department of Computer Science Aalto University School of Science AaltoFI-00076 Finland IIMAS Universidad Nacional Autonóma de México Ciudad de México01000 Mexico MACSI and Insight Centre for Data Analytics University of Limerick LimerickV94 T9PX Ireland

Burstiness, the tendency of interaction events to be heterogeneously distributed in time, is critical to information diffusion in physical and social systems. However, an analytical framework capturing the effect of burstiness on generic dynamics is lacking. We develop a master equation formalism to study cascades on temporal networks with burstiness modelled by renewal processes. Supported by numerical and data-driven simulations, we describe the interplay between heterogeneous temporal interactions and models of threshold-driven and epidemic spreading. We find that increasing interevent time variance can both accelerate and decelerate spreading for threshold models, but can only decelerate epidemic spreading. When accounting for the skewness of different interevent time distributions, spreading times collapse onto a universal curve. Our framework uncovers a deep yet subtle connection between generic diffusion mechanisms and underlying temporal network structures that impacts on a broad class of networked phenomena, from spin interactions to epidemic contagion and language dynamics. Copyright © 2020, The Authors. All rights reserved.

关键词： Dynamics

Structured graph learning via Laplacian spectral constraints

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Kumar, Sandeep Ying, Jiaxi Cardoso, José Vinícius de M. Palomar, Daniel P. Department of Industrial Engineering and Data Analytics Hong Kong University of Science and Technology Kowloon Hong Kong Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Kowloon Hong Kong

Learning a graph with a specific structure is essential for interpretability and identification of the relationships among data. It is well known that structured graph learning from observed samples is an NP-hard combinatorial problem. In this paper, we first show that for a set of important graph families it is possible to convert the structural constraints of structure into eigenvalue constraints of the graph Laplacian matrix. Then we introduce a unified graph learning framework, lying at the integration of the spectral properties of the Laplacian matrix with Gaussian graphical modeling that is capable of learning structures of a large class of graph families. The proposed algorithms are provably convergent and practically amenable for large-scale semi-supervised and unsupervised graph based learning tasks. Extensive numerical experiments with both synthetic and real data sets demonstrate the effectiveness of the proposed methods. An R package containing code for all the experimental results is available at https://***/package=spectralGraphTopology. Copyright © 2019, The Authors. All rights reserved.

关键词： Graphic methods

Sub-architecture ensemble pruning in neural architecture search

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Bian, Yijun Song, Qingquan Du, Mengnan Yao, Jun Chen, Huanhuan Hu, Xia The School of Computer Science and Technology University of Science and Technology of China Hefei230027 China The Department of Computer Science and Engineering Texas A&M University College StationTX77840 United States The Data Science and Analytics Department WeBank Shenzhen518000 China

Neural architecture search (NAS) is gaining more and more attention in recent years due to its flexibility and remarkable capability to reduce the burden of neural network design. To achieve better performance, however, the searching process usually costs massive computations that might not be affordable for researchers and practitioners. While recent attempts have employed ensemble learning methods to mitigate the enormous computational cost, however, they neglect a key property of ensemble methods, namely diversity, which leads to collecting more similar sub-architectures with potential redundancy in the final design. To tackle this problem, we propose a pruning method for NAS ensembles called "Sub-Architecture Ensemble Pruning in Neural Architecture Search (SAEP)." It targets to leverage diversity and to achieve sub-ensemble architectures at a smaller size with comparable performance to ensemble architectures that are not pruned. Three possible solutions are proposed to decide which sub-architectures to prune during the searching process. Experimental results exhibit the effectiveness of the proposed method by largely reducing the number of sub-architectures without degrading the performance. Copyright © 2019, The Authors. All rights reserved.

关键词： Network architecture