Federated Learning(FL)with mobile computing and the Internet of Things(IoT)is an effective cooperative learning approach.However,several technical challenges still need to be addressed.For instance,dividing the training process among several devices may impact the performance of Machine Learning(ML)algorithms,often significantly degrading prediction accuracy compared to centralized learning.One of the primary reasons for such performance degradation is that each device can access only a small fraction of data(that it generates),which limits the efficacy of the local ML model constructed on that device.The performance degradation could be exacerbated when the participating devices produce different classes of events,which is known as the class balance problem.Moreover,if the participating devices are of different types,each device may never observe the same types of events,which leads to the device heterogeneity problem.In this study,we investigate how data augmentation can be applied to address these challenges and improving detection performance in an anomaly detection task using IoT datasets.Our extensive experimental results with three publicly accessible IoT datasets show the performance improvement of up to 22.9％with the approach of data augmentation,compared to the baseline(without relying on data augmentation).In particular,stratified random sampling and uniform random sampling show the best improvement in detection performance with only a modest increase in computation time,whereas the data augmentation scheme using Generative Adversarial Networks is the most time-consuming with limited performance benefits.

Brett Weinger;Jinoh Kim;Alex Sim;Makiya Nakashima;Nour Moustafa;K.John Wu

Stony Brook University,Stony Brook,NY,USA;Lawrence Berkeley National Laboratory,Berkeley,CA,USA;Texas A&M University,Commerce,TX,USA;University of New South Wales,Canberra,Australia

数字通信与网络（英文）

[1]Brett Weinger;Jinoh Kim;Alex Sim;Makiya Nakashima;Nour Moustafa;K.John Wu-.Enhancing IoT anomaly detection performance for federated learning)[J].数字通信与网络（英文）,2022(03):314-323

Enhancing,IoT,anomaly,detection,performance,federated,learning,Federated,Learning,FL,mobile,computing,Internet,Things,effective,cooperative,approach,However,several,technical,challenges,still,need,addressed,For,instance,dividing,training,process,among,devices,may,impact,Machine,ML,algorithms,often,significantly,degrading,prediction,accuracy,compared,centralized,One,primary,reasons,such,degradation,that,each,only,small,fraction,generates,which,limits,efficacy,local,model,constructed,could,exacerbated,when,participating,produce,different,classes,events,known,balance,problem,Moreover,types,never,observe,same,leads,heterogeneity,this,study,investigate,augmentation,applied,these,improving,task,using,datasets,Our,extensive,experimental,results,three,publicly,accessible,show,improvement,up,baseline,without,relying,particular,stratified,random,sampling,uniform,best,modest,increase,computation,whereas,scheme,Generative,Adversarial,Networks,most,consuming,limited,benefits

0.565624