Thickened synovium with a hypoxic oxygenation status as measured with photoacoustic imaging was associated with fewer Doppler US signals and higher disease activity in study participants with rheum... Background Synovial hypoxia is a hallmark of rheumatoid arthritis (RA). Photoacoustic (PA) imaging, based on the use of laser-generated US, can detect the oxygenation status of tissue in individual...

Biomedical named entity recognition (Bio-NER) is an important preliminary step for many biomedical text mining tasks. The current mainstream methods for NER are based on the neural networks to avoid the complex hand-designed features derived from various linguistic analyses. However, the performance of these methods is always limited to exploring dependencies across output label and ignoring some potential word-level and sentence-level semantic information. Therefore, we propose a novel Long Short Term Memory (LSTM) Networks model SC-LSTM-CRF integrating two channels and the sentence-level embeddings for Bio-NER. In our model, two channels word embeddings are introduced as the input to obtain more abundant potential information, and the sentence-level reading control gate (SC) is inserted into the networks to integrate the implicit meaning of an entire sentence. The experimental results conducted on the BioCreative II GM corpus show that our method can achieve an F-score of 89.49%, which outperforms all state-of-the-art systems and is 0.88% higher than the best performing neural networks.

Face gender recognition is a challenging problem in the traditional field of pattern recognition. In this paper, we propose a deep learning model that can learn the joint high-level and low-level features of human face to address this problem. Our deep neural networks apply convolution and subsampling in extracting the local and abstract features of human face, and reconstruct the raw input images to learn global and effective features as supplementary information at the same time. We also add a trainable weight in the networks when combining the two kinds of features to realize the final gender classification. Experiment results show that our method achieves the highest accuracy compared with existing methods, when test on the mixed face dataset. Further, in the generalization test, the average classification rate on 3 public datasets of our method is 5% higher than the joint Local Binary Pattern (LBP) and Support Vector Machine (SVM) method, and is nearly 1% higher than the SVM with face pixels method. This proves our method outperforms the traditional methods in both learning ability and generalization ability.

SPIE Digital Library Proceedings

Time-frequency synchronization is a basic element in some fields such as deep space exploration and satellite navigation. Its accuracy and precision are closely related to the measurement results of these systems. In high signal-to-noise ratio situation, the accuracy of time-frequency synchronization is affected by the Doppler frequency shift. In this study, we propose an interpolation model that can mitigate the impact of the Doppler frequency shift, which is constructed from the prior information of the system and related to phase difference of the pseudo-random code. A coherent heterodyne ranging system is built, which is phase-modulated by pseudo-random binary code. And interpolation model is experimentally verified. The experimental results show that the ranging deviation is not more than 0.55 mm for static target. For the moving target, the ranging deviation does not exceed 0.40 mm, and the deviation of the velocity measurement is within 0.45 mm/s.