Li-WiGR: Легковесная система распознавания жестов на основе Wi-Fi с группированием поднесущих CSI

?

Li-WiGR: Легковесная система распознавания жестов на основе Wi-Fi с группированием поднесущих CSI

Информационные процессы. 2026. Т. 26. № 2. С. 429–445.

Modern Wi-Fi-based gesture recognition systems that use a single receiver require many computations. The paper proposes Li-WiGR, a system that employs subcarrier grouping and a specialized preprocessing to reduce computational complexity. Experiments on the Widar3 dataset show that in the single-receiver scenario Li-WiGR achieves in-domain and cross-domain classification accuracy of 98.33% and 95.24%, respectively, with a computational complexity of 2.26 million multiply--accumulate operations, which is about 500 times lower than that of the WiZeCSi approach that is close in accuracy. These results demonstrate the potential of the proposed system for deployment on resource-constrained devices.

Language: Russian

Text on another site

WiZeCSi: Towards Wi-Fi-based Single-Link Zero-Effort Cross-Domain Gesture Recognition

Dai T., Khorov E., IEEE Access 2026 Vol. 14

Currently, much effort is devoted to improving the accuracy of Wi-Fi sensing. Despite the typically high density of modern Wi-Fi deployments, in many scenarios, the number of access points under control is limited, which does not allow the simultaneous usage of multiple Wi-Fi links for sensing. To address this issue, the paper proposes a Wi-Fi-based Single-link Zero-effort ...

Added: April 29, 2026

An Overview of Kinect Based Gesture Recognition Methods

Alexeev A., Tsoy T., Martinez-Garcia E. et al., , in: Proceedings Of The 2024 International Conference On Artificial Life And Robotics February 22 To 25, 2024 J:Com Horutohall, Oita, Japan. 29Th Arob International Meeting Series.: ALife Robotics Corporation Ltd., 2024. P. 295–299.

Visual sensors play an important role in a broad variety of robotic systems applications. Even though Kinect technology appeared over 10 years ago, Kinect sensors are still actively employed by researchers around the world. This paper presents an overview of Kinect and Kinect 2 sensors’ applications in a human gesture based control. We analyzed existing research papers to ...

Added: February 19, 2025

Low complexity template-based watermarking with neural networks and various embedding templates

Dzhanashia K., Evsyutin O., Computers and Electrical Engineering 2022 Vol. 102 Article 108194

The popularity of watermarking was amplified due to the emergence of new immersive applications that connect the digital and physical worlds such as reading with a smartphone a watermark located in a physical object that leads to an online, dynamic source. Such applications require new watermarking schemes which must be robust enough to withstand significant ...

Added: June 23, 2022

Continuous Gesture Recognition from sEMG Sensor Data with Recurrent Neural Networks and Adversarial Domain Adaptation

Shpilman A., Sosin I., Kudenko D., , in: 2018 15th International Conference on Control, Automation, Robotics and Vision (ICARCV).: IEEE, 2018. P. 1436–1441.

Movement control of artificial limbs has made big advances in recent years. New sensor and control technology enhanced the functionality and usefulness of artificial limbs to the point that complex movements, such as grasping, can be performed to a limited extent. To date, the most successful results were achieved by applying recurrent neural networks (RNNs), ...

Added: January 18, 2019