With inherent sparse spike-based coding and asynchronous event-driven computation, spiking neural network (SNN) is naturally suitable for processing event stream data of event cameras. In order to improve the feature extraction and classification performance of bio-inspired hierarchical SNNs, in this paper an event camera object recognition system based on biological synaptic plasticity is proposed. In our system input event streams were firstly segmented adaptively using spiking neuron potential to improve computational efficiency of the system. Multi-layer feature learning and classification are implemented by our bio-inspired hierarchical SNN with synaptic plasticity. After Gabor filter-based event-driven convolution layer which extracted primary visual features of event streams, we used a feature learning layer with unsupervised spiking timing dependent plasticity (STDP) rule to help the network extract frequent salient features, and a feature learning layer with reward-modulated STDP rule to help the network learn diagnostic features. The classification accuracies of the network proposed in this paper on the four benchmark event stream datasets were better than the existing bio-inspired hierarchical SNNs. Moreover, our method showed good classification ability for short event stream input data, and was robust to input event stream noise. The results show that our method can improve the feature extraction and classification performance of this kind of SNNs for event camera object recognition.
ObjectiveTo investigate the incidence of nosocomial infection in acute and serious schizophrenic inpatients and its risk factors. MethodsBetween January 1st and December 31st, 2012, we investigated 1 621 schizophrenic patients on the status of nosocomial infections according to the hospital standard of nosocomial infection diagnosis. They were divided into infected group and uninfected group according to the survey results. The risk factors were analyzed by logistic regression method. ResultsTwenty-nine infected patients were found among the 1 621 patients, and the incidence rate was 1.79%. Among the nosocomial infections, the most common one was respiratory infection (79.31%), followed by gastrointestinal infection and urinary infection (6.90%). There were significant differences between the two groups of patients in age, hospital stay, positive and negative syndrome scale (PASS), combined somatopathy, the time of protective constraint, modified electraconvulsive therapy (MECT), using two or more antipsychotics drugs, using antibiotics and side effects of drugs (P<0.05). However, there were no statistical differences in gender, age classes, the course of disease, frequency of hospitalization and seasonal incidence of hospital infection (P>0.05). The results of multivariate analysis showed that hospital stay, positive symptom score, negative symptom score, the time of protective constraint, MECT, using two or more antipsychotics drugs and side effects of drugs were the main risk factors for nosocomial infection of inpatients with psychopathy (P<0.05). ConclusionBased on the different traits and treatments of acute and serious schizophrenia, a screening table of infections should be set. For the high risk group of nosocomial infection, effective measures should be taken to prevent and control the nosocomial infection of patients with schizophrenia.
ObjectiveTo explore the effects of drug management skill training on lightening the family burden of schizophrenic patients in their recovery period. MethodsBetween December 2011 and December 2013, 101 patients with schizophrenia were randomly divided into experimental group (n=56) and control group (n=45). The experimental group was given drug management skill training, while the control group only received routine follow-up. The course of the research was six months. Both groups were assessed by the positive and negative syndrome scale on patients' psychological symptoms, and family burden scale of diseases was used to assess the burden of the family. ResultsCompared with the controls, patients in the experimental group improved more in their positive symptoms (t=2.692, P=0.008), negative symptoms (t=2.729, P=0.008), general psychopathology symptoms (t=3.231, P=0.002) and the whole psychiatric symptoms (t=3.870, P<0.001). Moreover, the degree of patients' symptom improvement was positively correlated with the degree of family burden lightening (r=0.44, P<0.001). ConclusionFor patients with schizophrenia, reasonable drug management skill training can effectively improve patients' medication compliance, promote treatment effect and lighten family burden.
To explore the self-organization robustness of the biological neural network, and thus to provide new ideas and methods for the electromagnetic bionic protection, we studied both the information transmission mechanism of neural network and spike timing-dependent plasticity (STDP) mechanism, and then investigated the relationship between synaptic plastic and adaptive characteristic of biology. Then a feedforward neural network with the Izhikevich model and the STDP mechanism was constructed, and the adaptive robust capacity of the network was analyzed. Simulation results showed that the neural network based on STDP mechanism had good rubustness capacity, and this characteristics is closely related to the STDP mechanisms. Based on this simulation work, the cell circuit with neurons and synaptic circuit which can simulate the information processing mechanisms of biological nervous system will be further built, then the electronic circuits with adaptive robustness will be designed based on the cell circuit.