Search

Finding a feasible, collision-free path in line with social activities is an important and challenging task for robots working in dense crowds. In recent years, many studies have used deep reinforcement learning techniques to solve this problem. In particular, it is necessary to find an efficient path in a short time which often requires predicting the interaction with neighboring agents. However, as the crowd grows and the scene becomes more and more complex, researchers usually simplify the problem to a one-way human-robot interaction problem. But, in fact, we have to consider not only the interaction between humans and robots but also the influence of human-human interactions on the movement trajectory of the robot. Therefore, this article proposes a method based on deep reinforcement learning to enable the robot to avoid obstacles in the crowd and navigate smoothly from the starting point to the target point. We use a dual social attention mechanism to jointly model human-robot and human-human interaction. All sorts of experiments demonstrate that our model can make robots navigate in dense crowds more efficiently compared with other algorithms.

When communicating in aeronautical wireless channels, the difficulty of radio modulation recognition increases due to the loss of information caused by noise; particularly in circumstances with low signal-to-noise ratios (SNRs), it is difficult to achieve recognition rates exceeding 90.0%. To improve the radio modulation recognition performances of networks at low SNRs in complex electromagnetic environments, a modulation recognition method based on multidimensional feature analysis is proposed in this paper. It is realized through a cascaded structure including a Deep Cross Network (DCN) and an improved Visual Geometry Group Network 16 (VGG16). Our network framework is divided into two modules. In the one-dimensional data analysis module, we take the high-order cumulant of a transmitted signal as the one-dimensional feature input of the DCN. In the two-dimensional data analysis module, the color constellation density of the signal is extracted as the feature map input of the improved VGG16. Finally, we build a cascaded neural network with hybrid feature inputs for modulation recognition. Experimental results show that the recognition rate of our method is higher than 90.0% at an SNR of −4 dB. Compared with other methods, the proposed method has better recognition performance at low SNRs in aeronautical wireless channels.

With the continuous development of deep learning, more and more huge deep learning models are developed by researchers, which leads to an exponential increase of the parameters of models. Therein, the convolutional recurrent network as a type of widely used deep learning method is often employed to handle spatiotemporal data, e.g., traffic data. However, because of the large number of parameters in the model, the convolutional recurrent network needs to consume a lot of computing resources and time in the training process. To reduce the consumption of resources, we propose a sparse convolutional recurrent network with a sparse gating mechanism that is able to reduce the complexity of the network by an improved gate unit while keeping the performance of the model. We evaluate the performance of our proposed network on traffic flow datasets, and the experimental results show that the parameters of the model are significantly reduced under the condition of similar prediction accuracy compared with the traditional convolutional recurrent network.

GWAS, or Genome-wide association study, is a statistical analysis method to reveal specific genetic variations, usually single nucleotide polymorphisms, with particular phenotypes or diseases. The power to scan whole genomes from large scale samples made the method an efficient tool for information discovery. In the last decades, the application of GWAS has flourished, which benefited our understanding related to diseases, breeding and many other topics. In this review, we overviewed the history of GWAS, as well as different approaches to perform the analysis under different circumstances during different stages. Meanwhile, we also showed how different GWAS approaches benefited diverse research and application fields, and the potential limitations of the method.

Target tracking system has strong-nonlinearity with non-Gaussian noise, thus making traditional Cubature Kalman Filter have low tracking accuracy due to sensitivity to non-Gaussian noise. Considering that the High-degree CKF and Maximum Correntropy Kalman Filter can conquer the nonlinearity of system and non-Gaussianity of measurement noise and system noise respectively, the measurement update process of HCKF is transformed to statistical linear regression equation based on the combination of Maximum Correntropy Criterion and HCKF, and adjust the kernel width adaptively, which solves the nonlinearity and non-Gaussianity problem. Simulation proves that the proposed robust generalized high-degree cubature filter is better than traditional CKF and simple MCKF both in tracing accuracy.

Based on the detection criterion of traditional single threshold residual information, in order to get likelihood probability, this paper makes residual information fuzzy which is in the range of the upper and lower bounds (UBL for short) of sensor residual information effectiveness that is under incomplete measurement respectively set by steady-state error covariance under incomplete measurement and posterior Cramer-Rao bound (CRB). It advances the detection criteria on the basis of UBL of residual under incomplete measurement on the premise of residual information confidence at the moment according to Bayes formula and accomplishes the simulation.

To explore the mechanism of acute ischemia-reperfusion injury (IRI) to renal-transplantA total of 12 Chinese Sichuan White Pigs (SWPs) (2-3 months old, 17.5 +/- 4.6 kg, with clear family background) were used. 3 pairs of them with better tissue typing were subjected to renal allotransplantation. The other SWPs were allocated to renal autotransplantation. We assessed the SWPs' kidney function, serum superoxide dismutase (SOD) and malonaldehyde (MDA) after transplantation so as to shed light on the possible mechanism of IRI and to find out good detecting methods which could monitor IRI.Serum creatinine and urea increased in 2 days of postoperation and then returned to normal in both groups except the pigs that suffered from acute tubular necrosis or acute rejection. The concentrations of serum MDA and SOD began to increase 2 days after operation (P0.05). More increase of serum MDA and less increase of SOD were detected in renal allotransplant groups than in renal autotransplant groups (P0.05). The concentration of serum SOD and MDA were correlated (r = 0.961).IRI could initiate lipid peroxidation. IRI could be a single factor or be synergistic with immunologic factors to injure the transplanted organs.

To inquire into the mechanism of the protective efficacy of Yisheng injection against ischemia/reperfusion injury(IRI) in pig renal-transplant model.A total of 24 Chinese Sichuan White Pigs (SWPs) (2-3 months old, 17.5 +/- 4.6 kg, with clear family background) were used. 6 pairs of SWPs with better results of tissue typing were allocated to the group of renal allotransplantation. The other SWPs were subjected to renal autotransplantation. Yisheng injection was added into the preservative fluid and injected intravenously after transplantation in the test groups against IRI. We detected the SWPs' liver and kidney functions and serum superoxide dismutase(SOD) and malondialdehyde(MDA) concentrations after transplantation.Serum creatinine and urea levels increased in 2 days after operation and then returned to normal in both groups except the pigs suffering from acute tubular necrosis or acute rejection. The concentrations of serum MDA, SOD began to increase 2 days after operation (P0.05). Less increase of serum MDA, less decrease of NO and more increase of SOD in test groups were detected, compared with those in control groups (P0.05).Yisheng injection has protective efficacy against IRI and hence may have an application foreground.

The glutamate dehydrogenase (GDH) (EC 1.4.1.4) productivity of the immobilized Corynebacterium glutamicum T6-13 protoplasts in Ca-alginate gels was investigated. GDH in Corynebacterium glutamicum T6-13 cells is an intracellular enzyme. The cells pretreated with 0.5 U/l −1 penicillin G were used for the preparation of protoplasts. Protoplasts were prepared by treating these cells with lysozyme at 30°C for 14 h in 0.5 m NaCl solution and separating the protoplasts. Protoplasts were directly immobilized in 3% Ca-alginate gels (method I). The immobilized protoplasts could be also prepared by treating the immobilized whole cells with lysozyme (method II); this method was more convenient than method I. The GDH productivity of the immobilized protoplasts amounted to 20% of that of the free cells (intracellular). The immobilized protoplasts could be repeatedly used for at least 6 batches (18 days) and had good storage stability.