Ning Yang

In this article, we proposed a novel fault-tolerant control scheme for quadrotor unmanned aerial vehicles (UAVs) based on spiking neural networks (SNNs), which leverages the inherent features of neural network computing to significantly enhance the reliability and robustness of UAV flight control. Traditional control methods are known to be inadequate in dealing with complex and real-time sensor data, which results in poor performance and reduced robustness in fault-tolerant control. In contrast, the temporal processing, parallelism, and nonlinear capacity of SNNs enable the fault-tolerant control scheme to process vast amounts of sensory data with the ability to accurately identify and respond to faults. Furthermore, SNNs can learn and adjust to new environments and fault conditions, providing effective and adaptive flight control. The proposed SNN-based fault-tolerant control scheme demonstrates significant improvements in control accuracy and robustness compared with conventional methods, indicating its potential applicability and suitability for a range of UAV flight control scenarios.

In the actual knowledge extraction system, different applications have different entity classes and relationship schema, so the generalization and migration ability of knowledge extraction are very important. By training a knowledge extraction model in the source domain and applying the model to an arbitrary target domain directly, open domain knowledge extraction technology becomes crucial to mitigate the generalization and migration ability issues. Traditional knowledge extraction models cannot be directly transferred to new domains and also cannot extract undefined relation types. In order to deal with the above issues, in this paper, we proposed an end-to-end Chinese open-domain knowledge extraction model, TPORE (Extract Open-domain Relations through Token Pair linking), which combined BERT with a handshaking tagging scheme. TPORE can alleviate the nested entities and nested relations issues. Additionally, a new loss function that conducts a pairwise comparison of target category score and non-target category score to automatically balance the weight was adopted, and the experiment results indicate that the loss function can bring speed and performance improvements. The extensive experiments demonstrate that the proposed method can significantly surpass strong baselines. Specifically, our approach can achieve new state-of-the-art Chinese open Relation Extraction (ORE) benchmarks (COER and SAOKE). In the COER dataset, F1 increased from 66.36% to 79.63%, and in the SpanSAOKE dataset, F1 increased from 46.0% to 54.91%. In the medical domain, our method can obtain close performance compared with the SOTA method in the CMeIE and CMeEE datasets.

Parkinson’s disease (PD) is a nervous disorder that can cause motor impairment. PD severity assessment based on a series of motor movements illustrated in Unified Parkinson’s Disease Rating Scale (UPDRS) is an important part of clinical PD diagnosis. However, the current quantifying method heavily relies on human observation, which is time-consuming and subjective. Therefore, automatic severity estimation stemming from machine learning methods is receiving an increasing amount of research attention. However, these advances are still limited by data availability and interpretability. In this paper, we release a large PD motor dataset of over 300 real PD patients collected under doctors’ instructions and propose a pipeline to automatically quantify the motor severity of PD in finger tapping and postural stability. These two selected movements are representative of local and global motor control, exhibiting great clinical importance. The pipeline contains three-stage: pose estimation, domain knowledge extraction, and classification stage. The pose estimation uses deep-learning-based methods to extract 21 and 17 key points for finger tapping and postural stability respectively. The domain knowledge extraction stage extracts several explicit features pre-defined by experienced neuro-physicians. Finally, a classifier is trained to infer PD severity under MDS-UPDRS. To combine deep-learning-based features from pose estimation and domain features from the expert, the pipeline achieves a better trade-off between the model efficiency and clinical interpretability. Experiments show that our method achieves a micro average f1-score of 88%, 84%, and 84%, respectively on left finger tapping, right finger tapping, and postural stability, outperforming previous methods by a large margin. In addition, involving expert knowledge in the feature extraction stage greatly improves our model’s interpretability, which is essential in automatic PD detection.

Tilted fiber Bragg grating (TFBG) sensors are widely used in biochemical and electrochemical sensing due to their high sensitivity to refractive index (RI) of the surrounding medium. Ability of TFBGs to measure small RI change is currently limited due to the discrete spectral characteristics of TFBG cladding modes. Here we propose a novel method to measure both small and large RI changes with high accuracy and sensitivity by measuring the derivative of the intensity of the entire cladding mode envelope. The peak of the derivative curve provides a continuous and linear response to the RI change, which overcomes the problem of “cut-off mode hopping” that, until now, has limited the resolution of RI measurement using TFBGs. Experimental results demonstrate that, for small RI change (less than 0.002 RIU), the cladding envelope derivative method improves the interrogation sensitivity from tens of nm/RIU (using cut-off mode) to hundreds of nm/RIU (this method) together with a linear response (better than 98%),Moreover, such method provides the ability of temperature crosstalk calibration, offering a powerful new tool for biochemical detection.