Scientific integrity: analysis of Misconduct in images of scientific papers

• Grant number: 18/15864-4
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: November 01, 2018
• End date: October 31, 2019
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computer Systems
• Principal Investigator: Anderson de Rezende Rocha
• Grantee: João Phillipe Cardenuto
• Host Institution: Instituto de Computação (IC). Universidade Estadual de Campinas (UNICAMP). Campinas , SP, Brazil
• Associated research grant: 17/12646-3 - Déjà vu: feature-space-time coherence from heterogeneous data for media integrity analytics and interpretation of events, AP.TEM

Abstract

Recently, due to the rising number of scientific papers being published, the number of cases of misconduct in the scientific community is increasing, generating financial investments and professional disappointments by irreproducible research. This project aims to assist the scientific community, verifying the integrity of papers, by automating forensic processes in their images, through artificial intelligence and computer vision methods. In its pipeline, we propose a process that begins with a raw digital paper in PDF format (standard in the literature), followed by the identification and segmentation of images likely to be fraudulent and, finally, the identification of possible frauds in those images. With the help of partner institutions - Defense Advanced Research Projects Agency (DARPA) and University of Notre Dame- , initial studies in biomedical papers point relevant results in the detection of fraud, which indicate the potential for this project. Finally, it is important mention that the proposed work is integrated into the DéjáVu research project, whose objective, among others, is focused on information integrity.