Textile ID from Datamars can be an AI-based technology to unlock the entire potential of radio frequency identification (RFID) systems. RFID can be used to recognize, trace, and track textiles across their life time cycle, providing advantages of industrial laundries and their customers, and for rental linen companies, hospitals, assisted living facilities, hotels, restaurants, along with other companies making use of their own laundry.
Technological challenges prevent making probably the most out of RFID systems. The constraint of stray reads-false positive tags detected accidentally by the reader-and difficulties in correctly assigning readings to moving items are two limitations.
The usage of machine learning algorithms ensure probably the most accurate identification up to now, paving the real method for a fresh generation of reading system. This guarantees precision in automated systems: avoiding stray reads; identifying moving textiles without interrupting the workflow; and assigning tags to physical items correctly, in bulk even.
The aim of a RFID system would be to identify and track textiles along their life cycle, enabling precise and automated inventory loss and management reduction, the generation of transparent data and accurate invoicing, higher labor efficiency and increased profitability because of the optimization of textile cycles, and lower charges for the replacement of lost textiles. The bigger the RFID system accuracy is, the more these benefits are achieved fully.
But it’s not easy. The cross and delight of UHF (ultra-high frequency) RFID technology is its capability to read tags without type of sight and from the long distance. This permits the technology to learn a large number of textiles in bulk in a couple of seconds, but risks the accidental read of unwanted tags in the encompassing area, when items are moving especially. This lowers the accuracy of the RFID data collection.
As yet, this challenge has mainly been addressed by containing and limiting the reading area whenever you can with mechanical shielding structures or by manually setting thresholds on reader parameters. The flexibleness is limited by this process of the RFID system and slows operations.
So how exactly does machine learning connect with RFID?
Datamars has applied machine learning ways to the RFID technology. Machine learning is really a branch of artificial intelligence that delivers systems the capability to learn and improve automatically through experience and without having to be explicitly programmed. It examines the provided “training” datasets to get common patterns and create a model to create decisions.
Using machine learning algorithms and a developed neural network specifically, the machine exploits the given information extracted from the info of all RFID tag readings to classify each tag. In this way, of attempting to avoid stray reads instead, the operational system can recognize and discard them. Furthermore, “good” tags are correctly associated to the correct item/textile, if they’re in bulk and in motion even. training the neural network with huge amounts of data
By, the operational system will not require mechanisms, such as thresholds, to be set or with extensive and complex fine-tuning procedures manually. The greater the quantity of data, the better quality and precise the neural network may become, adapting to multiple environments easily, use cases, and laundry evolutions. This permits a lesser hardware investment and, since everything happens because of software algorithms, the reading system’s accuracy shall improve as time passes with a software update and without coping with hardware changes.
“Once more, Datamars is pushing the boundaries of RFID technology to generate probably the most advanced textile identification solutions for the laundry sector,” said Riccardo Mazzolini, General Manager, Datamars Textile ID. “Because of our pioneering usage of artificial intelligence in laundry applications, we have been offering probably the most performing UHF RFID reading systems of the market-more precise, flexible and adaptable-to deliver better user experiences to your customers measurably.”