Home
Resource
Memoryprints: identifying individuals based on memory recall
PDF
PDF format is widely accepted and good for printing.
Plug-in required
Access to this PDF has been restricted at the author's request. It will be publicly available after May 31, 2025.
Citation & Export
View Usage Statistics
Staff View

Citation & Export
Hide

Simple citation

Kochrekar, Siddhant Mohan. Memoryprints: identifying individuals based on memory recall. Retrieved from https://doi.org/doi:10.7282/t3-3mnn-b215

Export

Click here for information about Citation Management Tools at Rutgers.

Statistics
Hide

Description

TitleMemoryprints: identifying individuals based on memory recall
NameKochrekar, Siddhant Mohan (author); Zhang, Qiong (chair); Torres, Elizabeth B (member); Marian, Amélie (member); Rutgers University; School of Graduate Studies
Date Created2023
Other Date2023-05 (degree)
SubjectComputer science, Cognitive psychology, Classification, Delayed free recall, Memory recall, Similarity learning, User authentication, User identification
Extent40 pages : illustrations
DescriptionThis research explores the feasibility of using human memory recall as a form of user identification. Traditional authentication methods such as passwords and biometrics have well-known limitations, including susceptibility to theft or duplication. In contrast, human memory is highly individualized and difficult to imitate. To evaluate this hypothesis, a user study was carried out, which included 87 participants. These individuals were instructed to recall a particular group of words in a delayed free recall (DFR) setup. We qualitatively and quantitatively analyzed the patterns and characteristics of their memory recall using machine learning algorithms in Classification and Similarity settings. Our results show that memory recall can be a reliable and effective means of user identification, with an accuracy rate of 78%. Overall, this research demonstrates the promise of using human memory recall for user identification, highlighting its potential as a valuable addition to the authentication landscape.
NoteM.S.
NoteIncludes bibliographical references
Genretheses
Persistent URLhttps://doi.org/doi:10.7282/t3-3mnn-b215
LanguageEnglish
CollectionSchool of Graduate Studies Electronic Theses and Dissertations
Organization NameRutgers, The State University of New Jersey
RightsThe author owns the copyright to this work.
Version 8.5.5
Rutgers University Libraries - Copyright ©2024