Data recovery from flash memory in the mobile device can effectively reduce the loss caused by data corruption.Type recognition of data fragment is an essential prerequisite to the low-level data recovery.Pre-vious works in this field classify data fragment based on its file type.Still,the classification efficiency is low,espe-cially when the data fragment is a part of a composite file.We propose a fine-grained approach to classifying data fragment from the low-level flash memory to improve the classification accuracy and efficiency.The proposed meth-od redefines flash-memory-page data recognition problem based on the encoding format of the data segment,and applies a hybrid machine learning algorithm to detect the data type of the flash page.The hybrid algorithm can sig-nificantly decompose the given data space and reduce the cost of training.The experimental results show that our method achieves better classification accuracy and higher time performance than the existing methods.

ZHANG Li;HAO Shengang;ZHANG Quanxin

Department of Media Engineering,Zhejiang University of Media and Communication,Hangzhou 310018,China;School of Computer Science,Beijing Institute of Technology,Beijing 100081,China

电子学报（英文）

[1]ZHANG Li;HAO Shengang;ZHANG Quanxin-.A Fine-Grained Flash-Memory Fragment Recog-nition Approach for Low-Level Data Recovery)[J].电子学报（英文）,2022(04):732-740

Recog,redefines

Fine,Grained,Flash,Memory,Fragment,Approach,Low,Level,Data,Recovery,recovery,from,flash,memory,mobile,device,effectively,reduce,loss,caused,by,data,corruption,Type,recognition,fragment,essential,prerequisite,low,level,Pre,vious,works,this,field,its,file,type,Still,classification,efficiency,espe,cially,when,part,composite,We,grained,approach,classifying,improve,accuracy,proposed,page,problem,encoding,format,segment,applies,hybrid,machine,learning,algorithm,detect,sig,nificantly,decompose,given,space,cost,training,experimental,results,show,that,our,achieves,better,higher,performance,than,existing,methods

0.562136