基于多分主干外部注意力网络的水声信号识别

水声信号识别近年来备受关注,由于海洋信道具有时变空变性、信号传播的衰落特性和水下目标声源具有复杂多变性,水声信号识别任务面临巨大挑战.传统的水声信号识别方法难以充分获取目标的表征信息且不具备良好的抗噪声能力,识别效果有待提升.针对上述问题,本文提出一种基于多分支外部注意力网络(multi-branch external attention network,MEANet)的水声信号识别方法,可以在复杂海洋环境下充分获取水声信号的特征并进行识别.MEANet由多分支主干网络,通道、空间注意力模块和外部注意力模块组成.首先,输入数据通过多个并行的主干网络分支,提取水声信号不同层级的特征信息;其次,辅以通道、空间注意力模块对水声信号的通道和空间维度分别进行加权,调节不同通道和空间位置对特征表示的重要性;最后,整合外部注意力模块,以外部记忆单元和附加计算来引导网络的特征提取和预测,从而显著提高模型的识别率和鲁棒性.实验结果表明,本文提出的MEANet在ShipsEar数据集上的水声信号识别率达到98.84%,显著优于其他对比算法,证实了其有效性.

Universal Index Formula of Parameterized Combination Operator for Eco-environmental Quality Evaluation

[Objective] The aim was to evaluate the regional eco-environmental quality by using the universal index formula of parameterization combination operator based normalized index values.[Method] Through setting reference values and normalized transformation formulae for typical ecological environmental indexes appropriately,the difference among the standard normalized values would become very small after normalized transformation,and the ecological environmental indices expressed by normalized values can be equivalent to normalized indices.Under certain optimization conditions,shuffled frog leaping based on immune evolutionary particle swarm optimization algorithm was applied to optimize the parameters in parameterization combination operator formula,and the universal index formula suited to eco-environmental quality assessment was established finally.[Result] The universal index formula of parameterization combination operator,appropriate for any m(1≤m≤23) ecological environmental indices,was used to assess the eco-environmental quality of towns surrounding Headland Reservoir,and the results were in full accordance with those of unascertained measure method,that is,the eco-environmental quality of five towns around Headland Reservoir was the fourth grade.[Conclusion]The universal index formula of parameterization combination operator,suited to eco-environmental quality evaluation,is simple and intuitive in form,easy in computation and universal in application.

美罗培南联用丙戊酸钠致癫痫的病案分析

目的:让临床医师、药师进一步认识药物间的相互作用,了解其发生机制及处理方法,提高临床诊疗水平。方法:通过分析临床药师参与继发癫痫合并肺部感染患者,经美罗培南和丙戊酸钠(VPA)联合治疗后出现癫痫大发作,进行用药分析排查。结果:美罗培南能使VPA在体内的血药浓度显著降低,诱发癫痫发作。结论:在临床治疗中,应避免两药联用,若确需联用,应监测VPA血药浓度,以便及时调整剂量。