Facial action unit (AU) recognition is a crucial task for facial expressions analysis and has attracted extensive attention in the field of artificial intelligence and computer vision. Existing works have either focused on designing or learning complex regional feature representations, or delved into various types of AU relationship modeling. Albeit with varying degrees of progress, it is still arduous for existing methods to handle complex situations. In this paper, we investigate how to integrate the semantic relationship propagation between AUs in a deep neural network framework to enhance the feature representation of facial regions, and propose an AU semantic relationship embedded representation learning (SRERL) framework. Specifically, by analyzing the symbiosis and mutual exclusion of AUs in various facial expressions, we organize the facial AUs in the form of structured knowledge-graph and integrate a Gated Graph Neural Network (GGNN) in a multi-scale CNN framework to propagate node information through the graph for generating enhanced AU representation. As the learned feature involves both the appearance characteristics and the AU relationship reasoning, the proposed model is more robust and can cope with more challenging cases, e.g., illumination change and partial occlusion. Extensive experiments on the two public benchmarks demonstrate that our method outperforms the previous work and achieves state of the art performance.

A completely non-invasive and unconstrained method is proposed to detect respiration rhythm and pulse rate during sleep. By employing wavelet transformation (WT), waveforms corresponding to the respiration rhythm and pulse rate can be extracted from a pulsatile pressure signal acquired by a pressure sensor under a pillow. The respiration rhythm was obtained by an upward zero-crossing point detection algorithm from the respiration-related waveform reconstructed from the WT 2(6) scale approximation, and the pulse rate was estimated by a peak point detection algorithm from the pulse-related waveform reconstructed from the WT 2(4) and 2(5) scale details. The finger photo-electric plethysmogram (FPP) and nasal thermistor signals were recorded simultaneously as reference signals. The reference pulse rate and respiration rhythm were detected with the peak and upward zero-crossing point detection algorithm. This method was verified using about 24 h of data collected from 13 healthy subjects. The results showed that, compared with the reference data, the average error rates were 3.03% false negative and 1.47% false positive for pulse rate detection in the extracted pulse waveform. Similarly, 4.58% false negative and 3.07% false positive were obtained for respiration rhythm detection in the extracted respiration waveform. This study suggests that the proposed method is suitable, in sleep monitoring, for the diagnosis of sleep apnoea or sudden death syndrome.

No abstract

No abstract

An unconstrained method for the long-term monitoring of heart and breath rates during sleep is proposed. The system includes a sensor unit and a web-based network module. The sensor unit is set beneath a pillow to pick up the pressure variations from the head induced by inhalation/exhalation movements and heart pulsation during sleep. The measured pressure signal was digitized and transferred to a remote database server via the network module. A wavelet-based algorithm was employed to detect the heart and breath rates, as well as body movement, during sleep. The overall system was utilized for a total six-month trial operation delivered to a female subject. The profiles of the heart and breath rates on a beat-by-beat and daily basis were obtained. Movements during sleep were also estimated. The results show that the daily average percentage of undetectable periods (UPs) during 881.6 sleep hours over a 180 day period was 17.2%. A total of 89.2% of sleep hours had a UP of not more than 25%. The profile of the heart rate revealed a periodic property that corresponded to the female monthly menstrual cycle. Our system shows promise as a long-term unconstrained monitor for heart and breath rates, and for other physiological parameters related to the quality of sleep and the regularity of the menstrual cycle.