1,167 Hits in 8.4 sec

Handling Data Heterogeneity with Generative Replay in Collaborative Learning for Medical Imaging [article]

Liangqiong Qu, Niranjan Balachandar, Miao Zhang, Daniel Rubin
2022 arXiv   pre-print
In this paper, we present a novel generative replay strategy to address the challenge of data heterogeneity in collaborative learning methods.  ...  Experimental results demonstrate the capability of the proposed method in handling heterogeneous data across institutions.  ...  Acknowledgment This work was supported in part by a grant from the NCI, U01CA242879. References  ... 
arXiv:2106.13208v2 fatcat:usew3aif3ng2rn3chfcm3xjtxu

Decentralized Distributed Learning with Privacy-Preserving Data Synthesis [article]

Matteo Pennisi, Federica Proietto Salanitri, Giovanni Bellitto, Bruno Casella, Marco Aldinucci, Simone Palazzo, Concetto Spampinato
2022 arXiv   pre-print
In the medical field, multi-center collaborations are often sought to yield more generalizable findings by leveraging the heterogeneity of patient and clinical data.  ...  Furthermore, the majority of these approaches, especially those dealing with medical data, relies on a centralized distributed learning strategy that poses robustness, scalability and trust issues.  ...  general, it may not always be available or desirable in collaborative learning scenarios [31] , [37] .  ... 
arXiv:2206.10048v1 fatcat:nga7qndga5fh5j2xsvugtjc2wu

Rethinking Architecture Design for Tackling Data Heterogeneity in Federated Learning [article]

Liangqiong Qu, Yuyin Zhou, Paul Pu Liang, Yingda Xia, Feifei Wang, Ehsan Adeli, Li Fei-Fei, Daniel Rubin
2022 arXiv   pre-print
, especially when dealing with heterogeneous data.  ...  Federated learning is an emerging research paradigm enabling collaborative training of machine learning models among different organizations while keeping data private at each institution.  ...  Acknowledgments This work was supported in part by a grant from the NCI, U01CA242879.  ... 
arXiv:2106.06047v2 fatcat:nlbpw53xxnek5ilys7ga7cwfdy

LIRA: Lifelong Image Restoration from Unknown Blended Distortions [article]

Jianzhao Liu, Jianxin Lin, Xin Li, Wei Zhou, Sen Liu, Zhibo Chen
2020 arXiv   pre-print
To alleviate this problem, we raise the novel lifelong image restoration problem for blended distortions.  ...  branch and continually accumulate new knowledge without interfering with learned knowledge.  ...  medical imaging [10, 8] .  ... 
arXiv:2008.08242v1 fatcat:rqpzd4afgfhbfl6e6trhoj3ire

A Berkeley View of Systems Challenges for AI [article]

Ion Stoica, Dawn Song, Raluca Ada Popa, David Patterson, Michael W. Mahoney, Randy Katz, Anthony D. Joseph, Michael Jordan, Joseph M. Hellerstein, Joseph E. Gonzalez, Ken Goldberg, Ali Ghodsi (+1 others)
2017 arXiv   pre-print
These changes have been made possible by unprecedented levels of data and computation, by methodological advances in machine learning, by innovations in systems software and architectures, and by the broad  ...  With the increasing commoditization of computer vision, speech recognition and machine translation systems and the widespread deployment of learning-based back-end technologies such as digital advertising  ...  With new AI systems continually learning by interacting with dynamic environments, handling data poisoning a acks becomes increasingly important.  ... 
arXiv:1712.05855v1 fatcat:mbg3m2ltqncmxe3z35gnawrgnu

An Efficient CNN-Based Deep Learning Model to Detect Malware Attacks (CNN-DMA) in 5G-IoT Healthcare Applications

Ankita Anand, Shalli Rani, Divya Anand, Hani Moaiteq Aljahdali, Dermot Kerr
2021 Sensors  
An input image of 32 × 32 × 1 is used for the initial convolutional layer.  ...  However, with deep learning techniques, these attacks can be detected, which needs hybrid models.  ...  Data Availability Statement: Not applicable. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/s21196346 pmid:34640666 fatcat:k6hwfxrrfnhyfkavjwy4plqm5q

D4RL: Datasets for Deep Data-Driven Reinforcement Learning [article]

Justin Fu, Aviral Kumar, Ofir Nachum, George Tucker, Sergey Levine
2021 arXiv   pre-print
This serves as a common starting point for the community to identify shortcomings in existing offline RL methods and a collaborative route for progress in this emerging area.  ...  However, existing online RL benchmarks are not tailored towards the offline setting and existing offline RL benchmarks are restricted to data generated by partially-trained agents, making progress in offline  ...  Acknowledgements We would like to thank Abhishek Gupta, Aravind Rajeswaran, Eugene Vinitsky, and Rowan McAllister for providing implementations and assistance in setting up tasks, Michael Janner for informative  ... 
arXiv:2004.07219v4 fatcat:fkjwmgpxjzbyhmwxffdlu62dz4

RL-PDNN: Reinforcement Learning for Privacy-Aware Distributed Neural Networks in IoT Systems

Emna Baccour, Aiman Erbad, Amr Mohamed, Mounir Hamdi, Mohsen Guizani
2021 IEEE Access  
., s t } of data-generating IoT devices (e.g., microphones, cameras and medical sensors), collecting data to be classified by a trained CNN.  ...  More specifically, data-generating devices do not participate in the inference process to save their endowed resources for data collection and execution of the first and last layers.  ...  She was a postdoctoral fellow at Qatar University on a project covering the interconnection networks for massive data centers and then on a project covering video caching and processing in mobile edge  ... 
doi:10.1109/access.2021.3070627 fatcat:ypqpga35nfha7inu7ns37majyq

Merging RFID and Blockchain Technologies to Accelerate Big Data Medical Research Based on Physiological Signals

Xiuqing Chen, Hong Zhu, Deqin Geng, Wei Liu, Rui Yang, Shoudao Li
2020 Journal of Healthcare Engineering  
In order to provide medical data privacy protection and medical decision support, the hybrid systems are presented, and RFID, blockchain, and big data technologies are used to analyse physiological signals  ...  We focus on hybrid systems developed for patient physiological signals for collection, storage protection, and monitoring in critical care and clinical practice.  ...  Data Availability e paper gives an outline about the framework, and internal working and protocols for handling heterogeneous physiological signal data.  ... 
doi:10.1155/2020/2452683 pmid:32351676 pmcid:PMC7178520 fatcat:bhnxlumxtvdfllad3pchu4qzf4

Reinforcement Learning for Intelligent Healthcare Systems: A Comprehensive Survey [article]

Alaa Awad Abdellatif, Naram Mhaisen, Zina Chkirbene, Amr Mohamed, Aiman Erbad, Mohsen Guizani
2021 arXiv   pre-print
Reinforcement Learning (RL) has witnessed an intrinsic breakthrough in solving a variety of complex problems for diverse applications and services.  ...  The rapid increase in the percentage of chronic disease patients along with the recent pandemic pose immediate threats on healthcare expenditure and elevate causes of death.  ...  In [174] , a DRL-based solution is presented to detect abnormalities in medical images.  ... 
arXiv:2108.04087v1 fatcat:ifdpiqwunrawbmpfy6ftjk43g4

Handling of advanced persistent threats and complex incidents in healthcare, transportation and energy ICT infrastructures

Spyridon Papastergiou, Haralambos Mouratidis, Eleni-Maria Kalogeraki
2020 Evolving Systems  
The components of CyberSANE are described along with a description of the CyberSANE data flow.  ...  Publisher's Note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.  ...  In particular, in order to automatically collect and process the medical data, various medical devices and instruments are connected, through wired or wireless communications, with the EHR/EMR systems  ... 
doi:10.1007/s12530-020-09335-4 fatcat:fx76tetjofdkjapu6ymdrabtdq

FedGraph: Federated Graph Learning with Intelligent Sampling [article]

Fahao Chen, Peng Li, Toshiaki Miyazaki, Celimuge Wu
2021 arXiv   pre-print
However, existing work of federated learning mainly focuses on Convolutional Neural Network (CNN), which cannot efficiently handle graph data that are popular in many applications.  ...  In this paper, we propose FedGraph for federated graph learning among multiple computing clients, each of which holds a subgraph.  ...  ACKNOWLEDGMENTS This research was supported in part by The Okawa Foundation for Information and Telecommunications, in part by G-7 Scholarship Foundation, and in part by JSPS KAKENHI grant number 21H03424  ... 
arXiv:2111.01370v1 fatcat:2bfpfdudr5gibb6ukh6d3fhuse

Security Framework for IoT Devices against Cyber-Attacks [article]

Aliya Tabassum, Wadha Lebda
2019 arXiv   pre-print
Internet of Things (IoT) is the interconnection of heterogeneous smart devices through the Internet with diverse application areas.  ...  Along with enhancing existing approaches, a peripheral defence, Intrusion Detection System (IDS), proved efficient in most scenarios.  ...  To prevent unethical approaches for medical devices, a biometric-based two-level secure access control model is developed [46] . In this, the model converts the iris image to iris code.  ... 
arXiv:1912.01712v1 fatcat:mqwzm4f5rrhnvaagwmpz62efpm

Applications of Multi-Agent Deep Reinforcement Learning: Models and Algorithms

Abdikarim Mohamed Ibrahim, Kok-Lim Alvin Yau, Yung-Wey Chong, Celimuge Wu
2021 Applied Sciences  
Multi-agent DRL (MADRL) enables multiple agents to interact with each other and with their operating environment, and learn without the need for external critics (or teachers), thereby solving complex  ...  Recent advancements in deep reinforcement learning (DRL) have led to its application in multi-agent scenarios to solve complex real-world problems, such as network resource allocation and sharing, network  ...  For instance, Nan et al. enable distributed SADRL agents to use historical knowledge to ensure stability (O.1) in [69] , and Arjit et al. detects missing data for improved reliability of medical image  ... 
doi:10.3390/app112210870 fatcat:7ub7vtxppjfgrlpfk2kp7jqmw4

IEEE Access Special Section Editorial: AI-Driven Big Data Processing: Theory, Methodology, and Applications

Zhanyu Ma, Sunwoo Kim, Pascual Martinez-Gomez, Jalil Taghia, Yi-Zhe Song, Huiji Gao
2020 IEEE Access  
heterogeneous data.  ...  For generating realistic samples reliably, different GAN models are evaluated using Frechet Inception Distance scores, and some important tips for handling GAN training in X-ray prohibited item image generation  ...  By comparing with three other modeling methods, the LSTM NN model is validated and tested in various cases with promising performance.  ... 
doi:10.1109/access.2020.3035461 fatcat:rt7ejtponrfexigie4cfpt7gd4
« Previous Showing results 1 — 15 out of 1,167 results