No Identification Records
Researchers from the Michigan State University are using GPU-powered artificial intelligence and fingerprints to help keep kids healthy. Many children living in developing countries lack any form of identification, making it hard to know what babies have received which vaccine or booster shot.
“We want to make sure there’s complete coverage, that every child is given the right vaccinations,” research lead Prof. Anil Jain says. “With fingerprint-based health records, we can track this.”
Apart from keeping track of vaccination shots, fingerprint scans can also help authorities identify missing children or resolve cases in which newborns are swapped at birth. However, Jain and his team says it been a challenge to capture a usable fingerprint from the soft, pliant skin of babies, especially when they keep on moving.
“When you put a finger on the sensor and apply the slightest pressure, there’s a lot of distortion in the fingerprint image,” Jain says. The ridges and valleys on the fingerprint are not yet well-defined, so the contrast is poor.
To that end, Jain’s team developed machine-learning algorithms to enhance the quality of fingerprint scans using accelerators to train their deep neural networks. They also worked with fingerprint-scanner maker NEC to create a scanner designed for infants, with more than twice the resolution of a standard scanner.
Researchers fingerprinted more than 300 babies at Saran Ashram Hospital in Agra, India. They were able to identify infants who were first fingerprinted at 6 months or older with nearly 99 percent accuracy, but for babies who are four weeks-old, the accuracy rates fell to 80 percent.
“We’re designing our own fingerprint-matching (software) and training it using GPUs and deep learning,” Jain said.
The technology can be used in hospitals, by healthcare workers who serve several villages, and also in the small, sometimes remote clinics where many children receive health care.