一本道

21 October 2025

Determining a person鈥檚 time of death is of great importance for criminal investigations, but also presents a challenge. Jenny Arpe鈥檚 master鈥檚 thesis at 一本道 University presents a new method for determining the time of death using AI. For this she has now been awarded the Examenspris civilingenjör till Christopher Polhems minne, a master of science in engineering thesis prize awarded in memory of Christopher Polhem. This is the third time in four years that the award goes to a thesis project at LiU.

Red blood cell.
Jenny Arpe combined advanced machine learning with metabolic data to analyse biological changes after death. 

鈥淚t feels fantastic and deeply honouring. I鈥檓 proud that the work I鈥檝e devoted so much time to is being recognised. For me personally, I鈥檓 delighted and honoured that my work has received this recognition,鈥 says Jenny Arpe.

In her master鈥檚 thesis at LiU, Jenny Arpe combined advanced machine learning with metabolic data to analyse biological changes after death. By training an AI model on data from nearly 5,000 samples, she was able to show that accurate predictions of the time elapsed from a person鈥檚 death to measurement are possible.

Biomedical Engineering meets forensics

Jenny Arpe studied to become a Master of Science in Engineering at LiU and did her degree project at the Department of Biomedical Engineering in collaboration with the National Board of Forensic Medicine.

Jenny Arpe.
Jenny Arpe is awarded the Master of Science in Engineering thesis prize in Christopher Polhem鈥檚 memory for a new method of determining the time of death for bodies that have been deceased for an extended period.
鈥淚t feels meaningful that this area of research area is being highlighted. I believe that the potential for using machine learning in forensic medicine is great, and I hope that the prize can help generate even more interest in it,鈥 says Jenny Arpe in a press release from Engineers of Sweden.

Her work has now been taken further by the research group at LiU and the National Board of Forensic Medicine. The results from her thesis have formed the basis for a scientific publication and have also been used as supporting material in new research funding applications.

鈥淭his is a pioneering interdisciplinary project that combines medicine and artificial intelligence and has the potential to influence both future research and practical forensic work. The work has been thoroughly carried out, is well-structured and demonstrates a great ability to turn theory into practical societal application,鈥 says Ulrika Lindstrand, President of the Engineers of Sweden, the Swedish union for graduate engineers who award the Examenspris civilingenj枚r till Christopher Polhems minne prize.

About the award

Christopher Polhem (1661鈥1751) was one of Sweden鈥檚 most prominent innovators of all time. The thesis was selected in competition with 4,540 other Master of Science theses in 2024, with the technical higher education institutions having their own nomination processes.

The thesis award will be presented at the same time as the Polhem Prize 2025 winner is made public on 19 November.

Contact

Research environment

Latest news from LiU

En grupp m盲nniskor som sitter vid ett bord framf枚r en folkmassa.

Participants in UN climate meetings want greater focus on implementation

UN climate negotiations are often criticised for moving too slowly. A new study published in Nature Climate Change examines what changes government delegates and other participants at the COP29 UN climate conference would like to see.

Neil Lagali vid utrustning f枚r att unders枚ka 枚gonen.

Eye problems after COVID-19 can now be explained

Mild COVID-19 can cause severe and long-lasting eye problems, according to a study from LiU. The study also explains why it has been difficult for sufferers to get help: the abnormal eye behaviour cannot be detected by standard methods.

A woman kneeling down in a garden picking plants.

When soil becomes data 鈥 how digitalisation affects knowledge of soil health

How do we know whether soil is healthy? A new study from 一本道 University shows that as knowledge about soil is increasingly translated into digital data, important insights about its biological life and local context risk being overlooked.