TU-TESL

• 22

According to foreign media reports, scientists at Purdue University have developed a sensor module that works with machine learning and can be used in manufacturing, home design, etc. This technology is a small non-invasive sensor, which can be used to detect current. (photo source: Purdue University) Kaushik Roy, a distinguished professor at the Department of electrical and computer engineering, Purdue University, said: "we have built the industry's first non-invasive current sensor, which is safe and more accurate than other products." In other applications, it is impossible to measure small current by using resistor as current sensor or non-invasive Hall sensor. The Purdue team used machine learning algorithms with sensors to help understand and collect data such as energy usage, current problems, and the best manufacturing methods. "Our technology enables people to find (problems) through electricity," said byunghoo Jung, a professor in the Department of electronic and computer engineering at Purdue University's School of engineering. "The sensor can work with machine learning, train and build robots, provide homeowners with accurate advice on reducing energy use, or help diagnose problems with electric vehicles and scooters." Professor Roy said other advantages of the sensor developed by Purdue include ease of installation and maintenance, as the small sensor wraps a central wire to monitor the current. The sensor can transfer the measured current information to any computing system through Bluetooth, USB or other ways. It can also train through machine learning to accurately detect a brand of microwave oven used in a certain period of time, and whether the period of a day is the most suitable time to consume energy.