scholarly journals Personalized Federated Learning for ECG Classification Based on Feature Alignment

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Renjie Tang ◽  
Junzhou Luo ◽  
Junbo Qian ◽  
Jiahui Jin
Keyword(s):  
Data Privacy ◽  
Medical Information ◽  
Global Model ◽  
Local Model ◽  
Local Alignment ◽  
Global Alignment ◽  
Local Data ◽  
Discriminative Ability ◽  
Private Data ◽  
Feature Alignment

Electrocardiogram (ECG) data classification is a hot research area for its application in medical information processing. However, insufficient data, privacy preserve, and local deployment are still challenging difficulties. To address these problems, a novel personalized federated learning method for ECG classification is proposed in this paper. First, a global model is trained with federated learning framework on multiple local data clients. Then, we use the global model and private data to train the local model. To reduce the feature inconsistency between global and private local data and for better fitting the private local data, a novel ”feature alignment” module is devised to guarantee the uniformity, which contains two parts, global alignment and local alignment, respectively. For global alignment, the graph metric of batch data is used to constrain the dissimilarity between features generated by the global model and local model. For local alignment, triplet loss is adopted to increase discriminative ability for local private data. Comprehensive experiments on our collected dataset are evaluated. The results show that the proposed method can be better adapted to local data and exhibit superior ability of generalization.

scholarly journals Privacy-Preserving Predictive Modeling: Harmonization of Contextual Embeddings From Different Sources (Preprint)

2017 ◽  
Author(s):  
Yingxiang Huang ◽  
Junghye Lee ◽  
Shuang Wang ◽  
Jimeng Sun ◽  
Hongfang Liu ◽  
...  
Keyword(s):  
Medical Information ◽  
Original Data ◽  
Global Model ◽  
Local Models ◽  
Multiple Sources ◽  
Model Combining ◽  
Novel Approach ◽  
Private Data ◽  
Wide Range ◽  
Medical Concepts

BACKGROUND Data sharing has been a big challenge in biomedical informatics because of privacy concerns. Contextual embedding models have demonstrated a very strong representative capability to describe medical concepts (and their context), and they have shown promise as an alternative way to support deep-learning applications without the need to disclose original data. However, contextual embedding models acquired from individual hospitals cannot be directly combined because their embedding spaces are different, and naive pooling renders combined embeddings useless. OBJECTIVE The aim of this study was to present a novel approach to address these issues and to promote sharing representation without sharing data. Without sacrificing privacy, we also aimed to build a global model from representations learned from local private data and synchronize information from multiple sources. METHODS We propose a methodology that harmonizes different local contextual embeddings into a global model. We used Word2Vec to generate contextual embeddings from each source and Procrustes to fuse different vector models into one common space by using a list of corresponding pairs as anchor points. We performed prediction analysis with harmonized embeddings. RESULTS We used sequential medical events extracted from the Medical Information Mart for Intensive Care III database to evaluate the proposed methodology in predicting the next likely diagnosis of a new patient using either structured data or unstructured data. Under different experimental scenarios, we confirmed that the global model built from harmonized local models achieves a more accurate prediction than local models and global models built from naive pooling. CONCLUSIONS Such aggregation of local models using our unique harmonization can serve as the proxy for a global model, combining information from a wide range of institutions and information sources. It allows information unique to a certain hospital to become available to other sites, increasing the fluidity of information flow in health care.

Privacy-preserving Collaborative Training for Medical Image Analysis Based on Multi-Blockchain

2020 ◽  
Vol 23 ◽  
Author(s):  
Wanlu Zhang ◽  
Qigang Wang ◽  
Mei Li
Keyword(s):  
Medical Image ◽  
Data Privacy ◽  
Medical Image Analysis ◽  
Auxiliary Information ◽  
Training Process ◽  
Private Data ◽  
Medical Institutions ◽  
Model Training ◽  
Collaborative Training ◽  
Similar Task

Background: As artificial intelligence and big data analysis develop rapidly, data privacy, especially patient medical data privacy, is getting more and more attention. Objective: To strengthen the protection of private data while ensuring the model training process, this article introduces a multi-Blockchain-based decentralized collaborative machine learning training method for medical image analysis. In this way, researchers from different medical institutions are able to collaborate to train models without exchanging sensitive patient data. Method: Partial parameter update method is applied to prevent indirect privacy leakage during model propagation. With the peer-to-peer communication in the multi-Blockchain system, a machine learning task can leverage auxiliary information from another similar task in another Blockchain. In addition, after the collaborative training process, personalized models of different medical institutions will be trained. Results: The experimental results show that our method achieves similar performance with the centralized model-training method by collecting data sets of all participants and prevents private data leakage at the same time. Transferring auxiliary information from similar task on another Blockchain has also been proven to effectively accelerate model convergence and improve model accuracy, especially in the scenario of absence of data. Personalization training process further improves model performance. Conclusion: Our approach can effectively help researchers from different organizations to achieve collaborative training without disclosing their private data.

scholarly journals Federated Learning in a Medical Context: A Systematic Literature Review

2021 ◽  
Vol 21 (2) ◽  
pp. 1-31
Author(s):  
Bjarne Pfitzner ◽  
Nico Steckhan ◽  
Bert Arnrich
Keyword(s):  
Machine Learning ◽  
Literature Review ◽  
Systematic Literature Review ◽  
Data Privacy ◽  
Research Area ◽  
Learning Models ◽  
Related Data ◽  
Private Data ◽  
Large Databases ◽  
Machine Learning Models

Data privacy is a very important issue. Especially in fields like medicine, it is paramount to abide by the existing privacy regulations to preserve patients’ anonymity. However, data is required for research and training machine learning models that could help gain insight into complex correlations or personalised treatments that may otherwise stay undiscovered. Those models generally scale with the amount of data available, but the current situation often prohibits building large databases across sites. So it would be beneficial to be able to combine similar or related data from different sites all over the world while still preserving data privacy. Federated learning has been proposed as a solution for this, because it relies on the sharing of machine learning models, instead of the raw data itself. That means private data never leaves the site or device it was collected on. Federated learning is an emerging research area, and many domains have been identified for the application of those methods. This systematic literature review provides an extensive look at the concept of and research into federated learning and its applicability for confidential healthcare datasets.

scholarly journals FedPSO: Federated Learning Using Particle Swarm Optimization to Reduce Communication Costs

Sensors ◽  
2021 ◽  
Vol 21 (2) ◽  
pp. 600
Author(s):  
Sunghwan Park ◽  
Yeryoung Suh ◽  
Jaewoo Lee
Keyword(s):  
Particle Swarm Optimization ◽  
Data Privacy ◽  
Particle Swarm ◽  
Global Model ◽  
Network Communication ◽  
Improve Performance ◽  
Communication Performance ◽  
Swarm Optimization ◽  
Model Update ◽  
Network Environments

Federated learning is a learning method that collects only learned models on a server to ensure data privacy. This method does not collect data on the server but instead proceeds with data directly from distributed clients. Because federated learning clients often have limited communication bandwidth, communication between servers and clients should be optimized to improve performance. Federated learning clients often use Wi-Fi and have to communicate in unstable network environments. However, as existing federated learning aggregation algorithms transmit and receive a large amount of weights, accuracy is significantly reduced in unstable network environments. In this study, we propose the algorithm using particle swarm optimization algorithm instead of FedAvg, which updates the global model by collecting weights of learned models that were mainly used in federated learning. The algorithm is named as federated particle swarm optimization (FedPSO), and we increase its robustness in unstable network environments by transmitting score values rather than large weights. Thus, we propose a FedPSO, a global model update algorithm with improved network communication performance, by changing the form of the data that clients transmit to servers. This study showed that applying FedPSO significantly reduced the amount of data used in network communication and improved the accuracy of the global model by an average of 9.47%. Moreover, it showed an improvement in loss of accuracy by approximately 4% in experiments on an unstable network.

scholarly journals Modeling of the buckstay system of membrane-walls in watertube boiler construction

2014 ◽  
Vol 18 (suppl.1) ◽  
pp. 59-72 ◽  
Author(s):  
Hasan Nagiar ◽  
Tasko Maneski ◽  
Vesna Milosevic-Mitic ◽  
Branka Gacesa ◽  
Nina Andjelic
Keyword(s):  
Finite Element ◽  
Orthotropic Plate ◽  
Global Model ◽  
Local Model ◽  
Thermal Loads ◽  
Water Tube ◽  
Bending Load ◽  
Specific Geometry ◽  
Structural Parts ◽  
Help Model

Membrane walls are very important structural parts of water-tube boiler construction. Based on their specific geometry, one special type of finite element was defined to help model the global boiler construction. That is the element of reduced orthotropic plate with two thicknesses and two elasticity matrixes, for membrane and bending load separately. A global model of the boiler construction showed that the high value of stress is concentrated in plates of the buckstay system in boiler corners. Validation of the new finite element was done on the local model of the part of membrane wall and buckstay. A very precise model of tubes and flanges was compared to the model formed on the element of a reduced orthotropic plate. Pressure and thermal loads were discussed. Obtained results indicated that the defined finite element was quite favorable in the design and reconstruction of the boiler substructures such as a buckstay system.

Local model of a scientific collaboration in physics network compared with the global model

2010 ◽  
Vol 389 (23) ◽  
pp. 5530-5537 ◽  
Author(s):  
A.A. Roohi ◽  
A.H. Shirazi ◽  
A. Kargaran ◽  
G.R. Jafari
Keyword(s):  
Scientific Collaboration ◽  
Global Model ◽  
Local Model

scholarly journals Federated Learning in Big Data Application and Sharing

2020 ◽  
Author(s):  
Jing Yang ◽  
Quan Zhang ◽  
Kunpeng Liu ◽  
Peng Jin ◽  
Guoyi Zhao
Keyword(s):  
Big Data ◽  
Data Privacy ◽  
The State ◽  
Ideal Model ◽  
Local Data ◽  
Data Safety ◽  
Big Data Applications ◽  
Data Application ◽  
Big Data Application ◽  
Uniform Model

In recent years, electricity big data has extensive applications in the grid companies across the provinces. However, certain problems are encountered including, the inability to generate an ideal model using the isolated data possessed by each company, and the priority concerns for data privacy and safety during big data application and sharing. In this pursuit, the present research envisaged the application of federated learning to protect the local data, and to build a uniform model for different companies affiliated to the State Grid. Federated learning can serve as an essential means for realizing the grid-wide promotion of the achievements of big data applications, while ensuring the data safety.

scholarly journals Enhanced Integrity Checking for Preserve Data Owner and User Level Privacy Using Dual Cryptography Approach

2019 ◽  
pp. 138-146
Author(s):  
Poovizhi. M ◽  
Raja. G
Keyword(s):  
Data Storage ◽  
Data Privacy ◽  
Capital Expenditure ◽  
Data Access ◽  
Third Party ◽  
Configurable Computing ◽  
Local Data ◽  
Cloud Data ◽  
On Demand ◽  
Integrity Checking

Using Cloud Storage, users can tenuously store their data and enjoy the on-demand great quality applications and facilities from a shared pool of configurable computing resources, without the problem of local data storage and maintenance. However, the fact that users no longer have physical possession of the outsourced data makes the data integrity protection in Cloud Computing a formidable task, especially for users with constrained dividing resources. From users’ perspective, including both individuals and IT systems, storing data remotely into the cloud in a flexible on-demand manner brings tempting benefits: relief of the burden for storage management, universal data access with independent geographical locations, and avoidance of capital expenditure on hardware, software, and personnel maintenances, etc. To securely introduce an effective Sanitizer and third party auditor (TPA), the following two fundamental requirements have to be met: 1) TPA should be able to capably audit the cloud data storage without demanding the local copy of data, and introduce no additional on-line burden to the cloud user; 2) The third party auditing process should take in no new vulnerabilities towards user data privacy. In this project, utilize and uniquely combine the public auditing protocols with double encryption approach to achieve the privacy-preserving public cloud data auditing system, which meets all integrity checking without any leakage of data. To support efficient handling of multiple auditing tasks, we further explore the technique of online signature to extend our main result into a multi-user setting, where TPA can perform multiple auditing tasks simultaneously. We can implement double encryption algorithm to encrypt the data twice and stored cloud server in Electronic Health Record applications.

Blockchain Technology - Based Solutions for IOT Security

2022 ◽  
pp. 53-63
Author(s):  
Israa Al_Barazanchi ◽  
Aparna Murthy ◽  
Ahmad AbdulQadir Al Rababah ◽  
Ghadeer Khader ◽  
Haider Rasheed Abdulshaheed ◽  
...  
Keyword(s):  
Data Privacy ◽  
Smart Contracts ◽  
Iot Security ◽  
Security Issues ◽  
Iot Applications ◽  
Blockchain Technology ◽  
Private Data ◽  
Long Time ◽  
It Applications

Blockchain innovation has picked up expanding consideration from investigating and industry over the later a long time. It permits actualizing in its environment the smart-contracts innovation which is utilized to robotize and execute deals between clients. Blockchain is proposed nowadays as the unused specialized foundation for a few sorts of IT applications. Blockchain would aid avoid the duplication of information because it right now does with Bitcoin and other cryptocurrencies. Since of the numerous hundreds of thousands of servers putting away the Bitcoin record, it’s impossible to assault and alter. An aggressor would need to change the record of 51 percent of all the servers, at the precise same time. The budgetary fetched of such an assault would distantly exceed the potential picks up. The same cannot be said for our private data that lives on single servers possessed by Google and Amazon. In this paper, we outline major Blockchain technology that based as solutions for IOT security. We survey and categorize prevalent security issues with respect to IoT data privacy, in expansion to conventions utilized for organizing, communication, and administration. We diagram security necessities for IoT together with the existing scenarios for using blockchain in IoT applications.

Privacy Preserving Machine Learning and Deep Learning Techniques

2020 ◽  
pp. 222-235
Author(s):  
Divya Asok ◽  
Chitra P. ◽  
Bharathiraja Muthurajan
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Data Privacy ◽  
Differential Privacy ◽  
Digital Data ◽  
Sensitive Data ◽  
Security Issues ◽  
Private Data ◽  
Learning Techniques ◽  
Machine Learning Applications

In the past years, the usage of internet and quantity of digital data generated by large organizations, firms, and governments have paved the way for the researchers to focus on security issues of private data. This collected data is usually related to a definite necessity. For example, in the medical field, health record systems are used for the exchange of medical data. In addition to services based on users' current location, many potential services rely on users' location history or their spatial-temporal provenance. However, most of the collected data contain data identifying individual which is sensitive. With the increase of machine learning applications around every corner of the society, it could significantly contribute to the preservation of privacy of both individuals and institutions. This chapter gives a wider perspective on the current literature on privacy ML and deep learning techniques, along with the non-cryptographic differential privacy approach for ensuring sensitive data privacy.

Sign in / Sign up

Export Citation Format

Share Document