How it works: Backscattering enables devices to modulate and reflect incoming wireless signals back to the transmitter, akin to how RFID chips and contactless payment cards operate by harvesting energy from the reader. This facilitates battery-free communication for IoT devices.
Recently, a team of researchers from South Korea’s Pusan National University has pioneered a new method based on the same technology. This new method is about 40 percent more energy-efficient than existing techniques.
Backscattering itself is not a novel concept. However, the innovation lies in the team’s use of AI to enhance the system, making it significantly more efficient for low-power applications like IoT sensors. Their methodology involves employing machine learning to precisely model the optimal “reflection coefficients” that dictate how much of the wireless signal is reflected.
Traditionally, determining these coefficients has depended on simulations that do not perfectly mirror real-world conditions, posing challenges in achieving low bit error rates and high data rates. Nonetheless, the researchers have addressed this by using a technique known as “transfer learning,” in which an AI model is initially trained on one task and then refined using data from the actual target task.
To implement this, they pre-trained an artificial neural network on simulated input voltages to understand the behavior of the modulation circuitry under varying voltage conditions. Subsequently, they further trained that pre-trained model using real experimental data, allowing it to accurately predict the reflection coefficients for their specific hardware.
With these finely-tuned AI models, the team optimized their 4-QAM and 16-QAM modulation schemes for maximum efficiency. QAM stands for Quadrature Amplitude Modulation, a scheme extensively used in Wi-Fi communication systems. Their resulting prototype system consumes less than 0.6 milliwatts during transmission—a fraction of the power needed for conventional wireless radios.
The system also integrates a 2×2 MIMO antenna setup to enhance signal reception. During tests in the 5.7-5.8 GHz range, it achieved a spectral efficiency of 2 bits/second/hertz using 4-QAM modulation.
“The combination of accurate circuit modeling, advanced modulation techniques, and polarization diversity, all tested in over-the-air environments, presents a holistic approach to tackling the challenges in ISC and IoT,” stated Professor Sangkil Kim, who led the study.
According to the Pusan researchers, this groundwork paves the way for reliable, ultra-low-power backscatter systems with potential applications in consumer electronics, healthcare monitoring, smart urban infrastructure, environmental sensing, and radar communication.
Their findings have been published in a paper in the IEEE Internet of Things Journal.
