Scalability and information personal privacy are vital for training and deploying large-scale deep learning models.Federated learning trains models on exclusive information by aggregating weights from various devices ...Scalability and information personal privacy are vital for training and deploying large-scale deep learning models.Federated learning trains models on exclusive information by aggregating weights from various devices and taking advantage of the device-agnostic environment of web browsers.Nevertheless,relying on a main central server for internet browser-based federated systems can prohibit scalability and interfere with the training process as a result of growing client numbers.Additionally,information relating to the training dataset can possibly be extracted from the distributed weights,potentially reducing the privacy of the local data used for training.In this research paper,we aim to investigate the challenges of scalability and data privacy to increase the efficiency of distributed training models.As a result,we propose a web-federated learning exchange(WebFLex)framework,which intends to improve the decentralization of the federated learning process.WebFLex is additionally developed to secure distributed and scalable federated learning systems that operate in web browsers across heterogeneous devices.Furthermore,WebFLex utilizes peer-to-peer interactions and secure weight exchanges utilizing browser-to-browser web real-time communication(WebRTC),efficiently preventing the need for a main central server.WebFLex has actually been measured in various setups using the MNIST dataset.Experimental results show WebFLex’s ability to improve the scalability of federated learning systems,allowing a smooth increase in the number of participating devices without central data aggregation.In addition,WebFLex can maintain a durable federated learning procedure even when faced with device disconnections and network variability.Additionally,it improves data privacy by utilizing artificial noise,which accomplishes an appropriate balance between accuracy and privacy preservation.展开更多
Quantitative data analysis in single-molecule localization microscopy(SMLM)is crucial for studying cellular functions at the biomolecular level.In the past decade,several quantitative methods were developed for analyz...Quantitative data analysis in single-molecule localization microscopy(SMLM)is crucial for studying cellular functions at the biomolecular level.In the past decade,several quantitative methods were developed for analyzing SMLM data;however,imaging artifacts in SMLM experiments reduce the accuracy of these methods,and these methods were seldom designed as user-friendly tools.Researchers are now trying to overcome these di±culties by developing easyto-use SMLM data analysis software for certain image analysis tasks.But,this kind of software did not pay su±cient attention to the impact of imaging artifacts on the analysis accuracy,and usually contained only one type of analysis task.Therefore,users are still facing di±culties when they want to have the combined use of different types of analysis methods according to the characteristics of their data and their own needs.In this paper,we report an ImageJ plug-in called DecodeSTORM,which not only has a simple GUI for human–computer interaction,but also combines artifact correction with several quantitative analysis methods.DecodeSTORM includes format conversion,channel registration,artifact correction(drift correction and localization¯ltering),quantitative analysis(segmentation and clustering,spatial distribution statistics and colocalization)and visualization.Importantly,these data analysis methods can be combined freely,thus improving the accuracy of quantitative analysis and allowing users to have an optimal combination of methods.We believe DecodeSTORM is a user-friendly and powerful ImageJ plug-in,which provides an easy and accurate data analysis tool for adventurous biologists who are looking for new imaging tools for studying important questions in cell biology.展开更多
基金This work has been funded by King Saud University,Riyadh,Saudi Arabia,through Researchers Supporting Project Number(RSPD2024R857).
文摘Scalability and information personal privacy are vital for training and deploying large-scale deep learning models.Federated learning trains models on exclusive information by aggregating weights from various devices and taking advantage of the device-agnostic environment of web browsers.Nevertheless,relying on a main central server for internet browser-based federated systems can prohibit scalability and interfere with the training process as a result of growing client numbers.Additionally,information relating to the training dataset can possibly be extracted from the distributed weights,potentially reducing the privacy of the local data used for training.In this research paper,we aim to investigate the challenges of scalability and data privacy to increase the efficiency of distributed training models.As a result,we propose a web-federated learning exchange(WebFLex)framework,which intends to improve the decentralization of the federated learning process.WebFLex is additionally developed to secure distributed and scalable federated learning systems that operate in web browsers across heterogeneous devices.Furthermore,WebFLex utilizes peer-to-peer interactions and secure weight exchanges utilizing browser-to-browser web real-time communication(WebRTC),efficiently preventing the need for a main central server.WebFLex has actually been measured in various setups using the MNIST dataset.Experimental results show WebFLex’s ability to improve the scalability of federated learning systems,allowing a smooth increase in the number of participating devices without central data aggregation.In addition,WebFLex can maintain a durable federated learning procedure even when faced with device disconnections and network variability.Additionally,it improves data privacy by utilizing artificial noise,which accomplishes an appropriate balance between accuracy and privacy preservation.
基金supported by the National Natural Science Foundation of China(82160345)Key research and development project of Hainan province(ZDYF2021GXJS017)+2 种基金Key Science and Technology Plan Project of Haikou(2021-016)the Start-up Fund from Hainan University(KYQD(ZR)-20022 and KYQD(ZR)-20077)the Student Innovation and Entrepreneurship Project of Biomedical Engineer-ing School,Hainan University(BMECF2D2021001).
文摘Quantitative data analysis in single-molecule localization microscopy(SMLM)is crucial for studying cellular functions at the biomolecular level.In the past decade,several quantitative methods were developed for analyzing SMLM data;however,imaging artifacts in SMLM experiments reduce the accuracy of these methods,and these methods were seldom designed as user-friendly tools.Researchers are now trying to overcome these di±culties by developing easyto-use SMLM data analysis software for certain image analysis tasks.But,this kind of software did not pay su±cient attention to the impact of imaging artifacts on the analysis accuracy,and usually contained only one type of analysis task.Therefore,users are still facing di±culties when they want to have the combined use of different types of analysis methods according to the characteristics of their data and their own needs.In this paper,we report an ImageJ plug-in called DecodeSTORM,which not only has a simple GUI for human–computer interaction,but also combines artifact correction with several quantitative analysis methods.DecodeSTORM includes format conversion,channel registration,artifact correction(drift correction and localization¯ltering),quantitative analysis(segmentation and clustering,spatial distribution statistics and colocalization)and visualization.Importantly,these data analysis methods can be combined freely,thus improving the accuracy of quantitative analysis and allowing users to have an optimal combination of methods.We believe DecodeSTORM is a user-friendly and powerful ImageJ plug-in,which provides an easy and accurate data analysis tool for adventurous biologists who are looking for new imaging tools for studying important questions in cell biology.
