Yifan Ma

Yifan Ma

Auto-generated profile, based on publicly available information

Yifan Ma

Shandong University,China

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
2 May 2022
Verified
Conference Paper
Closed access
Pengfei HuPengfei Hu
Pengfei Hu
YMYifan Ma
Yifan Ma
PSPanneer Selvam Santhalingam
Panneer Selvam Santhalingam
PPParth H Pathak
Parth H Pathak
XCXiuzhen Cheng
Xiuzhen Cheng
As acoustic communication systems become more common in homes and offices, eavesdropping brings significant security and privacy risks. Current approaches of acoustic eavesdropping either provide low resolution due to the use of sub-6 GHz frequencies, work only for limited words using classification, or cannot work through-wall due to the use of optical sensors. In this paper, we present MILLIEAR, a mmWave acoustic eavesdropping system that leverages the high-resolution of mmWave FMCW ranging and generative machine learning models to not only extract vibrations but to reconstruct the audio. MILLIEAR combines speaker vibration estimation with conditional generative adversarial networks to eavesdrop with unconstrained vocabulary. We implement and evaluate MIL-LIEAR using off-the-shelf mmWave radar deployed in different scenarios and settings. We find that it can accurately reconstruct the audio even at different distances, angles and through the wall with different insulator materials. Our subjective and objective evaluations show that the reconstructed audio has a strong similarity with the original audio.

10 December 2018 in Measurement Science and Technology
Verified
Journal Article
Closed access
YMYifan Ma
Yifan Ma
QJQi Jiang
Qi Jiang
Automatic reading of pointer meters is of great significance to meter verification and industrial inspection robots. Many automatic reading algorithms of pointer meters based on machine vision have been proposed. However, the pointer shadow problem has not been effectively solved, which hinders the automatic reading of inspection robots in complex lighting environments. Also, pointer line recognition is easily influenced by the images around the pointer. With the aim of addressing these problems, this paper proposes a robust and high-precision pointer meter automatic reading algorithm. In meter center recognition using a round-degree method, this paper uses the eight chain code shape to represent the pixel image shape to prevent abnormal calculation of the round-degree. A novel binarization threshold determination method based on the symmetry degree is proposed to segment the pointer region, which effectively solves the pointer shadow problem. In addition, for pointer recognition, this paper proposes an improved random sample consensus (RANSAC) algorithm to overcome background image interference. The experimental results prove that the algorithm effectively removes pointer shadows and that the reading precision is high.