Fangming Hu

Learn More
It is difficult to extract signals under Low Signal Noise Ratio in biomedical signal processing. The elimination of movement artifact is really a bottleneck. A new solution for the movement artifact in pulse signal is proposed in this paper. According to pulse signal features, the signal is decomposed by using wavelet transform firstly. Then empirical mode(More)
Wireless Body Area Network (WBAN) applications have grown immensely in the past few years. However, security and privacy of the user are two major obstacles in their development. The complex and very sensitive nature of the body-mounted sensors means the traditional network layer security arrangements are not sufficient to employ their full potential, and(More)
Sleep posture detection is very important in assisted living, healthcare, etc. With the rapid development of photoelectric technology, the cost of depth sensing equipment is decreasing; therefore, the depth images can be obtained in more ways. Then, SIFT features which represent the visual features of shapes are acquired from the images, feature will be(More)
As an important biological signal, electrocardiogram (ECG) signals provide a valuable basis for the clinical diagnosis and treatment of several diseases. However, its reference significance is based on the effective acquisition and correct recognition of ECG signals. In fact, this mV-level weak signal can be easily affected by various interferences caused(More)
  • 1