Anna A. Trofimova

Anna A. Trofimova

Auto-generated profile, based on publicly available information

Anna A. Trofimova

School of Computer Science, University of Auckland, Auckland, New Zealand

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 January 2017 in Technology and Disability
Verified
Journal Article
Closed access
PDF file
FVFabio Veronese
Fabio Veronese
AMAndrea Masciadri
Andrea Masciadri
ATAnna A. Trofimova
Anna A. Trofimova
MMMatteo Matteucci
Matteo Matteucci
FSFabio Salice
Fabio Salice
Smart Homes technologies development is oriented toward intelligent services for the dweller. Designing the Artificial Intelligence which plays behind the scenes in a Smart Home requires large datasets for several reasons: training machine learning a

1 January 2017
Verified
Book Chapter
Closed access
PDF file
AMAndrea Masciadri
Andrea Masciadri
TATrofimova Anna A.
Trofimova Anna A.
MMMatteucci Matteo
Matteucci Matteo
SFSalice Fabio
Salice Fabio
The proposed system aims at elderly people independent living by providing an early indicator of habits changes which might be relevant for a diagnosis of diseases. It relies on Hidden Markov Model to describe the behavior observing sensors data, while Likelihood Ratio Test gives the variation within different time periods.

9 February 2026
Verified
Conference Paper
Open access
LNLogan James Nilson
Logan James Nilson
ASAsma Shakil
Asma Shakil
SSShyamli Sindhwani
Shyamli Sindhwani
ATAnna Trofimova
Anna Trofimova
In group software projects, individual contributions often vary significantly, but detecting imbalances is time-consuming and complex. This research project examines how Large Language Models (LLMs) can aid in validating student contributions by analysing self-reports and Git histories. We developed a prototype tool that automatically extracts coding-related claims, locates corresponding commits, and verifies supporting evidence. Evaluation across two course cohorts shows the tool achieves high claim validation precision (0.94); however, it is stricter than human reviewers in its requirement for explicit evidence.