Wireless Sensor Networks(WSNs)have emerged as crucial tools for real-time environmental monitoring through distributed sensor nodes(SNs).However,the operational lifespan of WSNs is significantly constrained by the lim...Wireless Sensor Networks(WSNs)have emerged as crucial tools for real-time environmental monitoring through distributed sensor nodes(SNs).However,the operational lifespan of WSNs is significantly constrained by the limited energy resources of SNs.Current energy efficiency strategies,such as clustering,multi-hop routing,and data aggregation,face challenges,including uneven energy depletion,high computational demands,and suboptimal cluster head(CH)selection.To address these limitations,this paper proposes a hybrid methodology that optimizes energy consumption(EC)while maintaining network performance.The proposed approach integrates the Low Energy Adaptive Clustering Hierarchy with Deterministic(LEACH-D)protocol using an Artificial Neural Network(ANN)and Bayesian Regularization Algorithm(BRA).LEACH-D improves upon conventional LEACH by ensuring more uniform energy usage across SNs,mitigating inefficiencies from random CH selection.The ANN further enhances CH selection and routing processes,effectively reducing data transmission overhead and idle listening.Simulation results reveal that the LEACH-D-ANN model significantly reduces EC and extends the network’s lifespan compared to existing protocols.This framework offers a promising solution to the energy efficiency challenges in WSNs,paving the way for more sustainable and reliable network deployments.展开更多
针对当前雷达电子战中装备的小型化和智能化需求,考虑将探测波形隐藏在干扰波形中,提出了基于深度强化学习的干扰探测一体化波形设计。首先,通过伪随机码噪声调频信号和线性调频信号复合调制完成一体化波形建模;其次,构造速度模糊函数...针对当前雷达电子战中装备的小型化和智能化需求,考虑将探测波形隐藏在干扰波形中,提出了基于深度强化学习的干扰探测一体化波形设计。首先,通过伪随机码噪声调频信号和线性调频信号复合调制完成一体化波形建模;其次,构造速度模糊函数、多普勒模糊函数和脉压后的均值标准差之比等目标函数,引入深度Q网络(deep Q learning network,DQN)算法对目标函数求解;最后,针对DQN类算法中存在的过估计问题,提出了双重竞争深度正则化Q学习(double dueling deep Q-learning network based on regularization,D3QN-Reg)算法对一体化波形进行优化,优化后的脉压幅度最高提升13.6%,速度域的第一旁瓣幅度降低19.1%。展开更多
基于事件的社交网(event-based social networks,EBSN)中的个性化推荐服务是一个十分重要且颇具应用价值的问题,现有研究工作主要基于普通图来对EBSN中的关系进行建模,但由于EBSN是一种异构型复杂社交网络,具有多种不同类型实体,因而用...基于事件的社交网(event-based social networks,EBSN)中的个性化推荐服务是一个十分重要且颇具应用价值的问题,现有研究工作主要基于普通图来对EBSN中的关系进行建模,但由于EBSN是一种异构型复杂社交网络,具有多种不同类型实体,因而用普通图建模EBSN会存在高维信息丢失问题,导致推荐质量降低.基于此,首先提出一种基于超图模型的EBSN个性化推荐(hypergraph-based personalized recommendation in EBSN,PRH)算法,其基本思想在于利用超图具有不丢失高维数据信息之特点来更准确地对EBSN中复杂社交关系数据进行高维建模,并利用流形排序正则化计算获取初步推荐结果.其次,又分别从查询向量设置方式改进和对不同类超边施以不同权重等角度,提出了优化的PRH(optimized PRH,oPRH)算法以进一步优化PRH算法所获推荐结果,从而实现精准推荐.扩展实验表明,基于超图的EBSN个性化推荐及其优化算法,推荐结果相比于以前基于普通图的推荐算法具有更高准确性.展开更多
文摘Wireless Sensor Networks(WSNs)have emerged as crucial tools for real-time environmental monitoring through distributed sensor nodes(SNs).However,the operational lifespan of WSNs is significantly constrained by the limited energy resources of SNs.Current energy efficiency strategies,such as clustering,multi-hop routing,and data aggregation,face challenges,including uneven energy depletion,high computational demands,and suboptimal cluster head(CH)selection.To address these limitations,this paper proposes a hybrid methodology that optimizes energy consumption(EC)while maintaining network performance.The proposed approach integrates the Low Energy Adaptive Clustering Hierarchy with Deterministic(LEACH-D)protocol using an Artificial Neural Network(ANN)and Bayesian Regularization Algorithm(BRA).LEACH-D improves upon conventional LEACH by ensuring more uniform energy usage across SNs,mitigating inefficiencies from random CH selection.The ANN further enhances CH selection and routing processes,effectively reducing data transmission overhead and idle listening.Simulation results reveal that the LEACH-D-ANN model significantly reduces EC and extends the network’s lifespan compared to existing protocols.This framework offers a promising solution to the energy efficiency challenges in WSNs,paving the way for more sustainable and reliable network deployments.
文摘针对当前雷达电子战中装备的小型化和智能化需求,考虑将探测波形隐藏在干扰波形中,提出了基于深度强化学习的干扰探测一体化波形设计。首先,通过伪随机码噪声调频信号和线性调频信号复合调制完成一体化波形建模;其次,构造速度模糊函数、多普勒模糊函数和脉压后的均值标准差之比等目标函数,引入深度Q网络(deep Q learning network,DQN)算法对目标函数求解;最后,针对DQN类算法中存在的过估计问题,提出了双重竞争深度正则化Q学习(double dueling deep Q-learning network based on regularization,D3QN-Reg)算法对一体化波形进行优化,优化后的脉压幅度最高提升13.6%,速度域的第一旁瓣幅度降低19.1%。
文摘基于事件的社交网(event-based social networks,EBSN)中的个性化推荐服务是一个十分重要且颇具应用价值的问题,现有研究工作主要基于普通图来对EBSN中的关系进行建模,但由于EBSN是一种异构型复杂社交网络,具有多种不同类型实体,因而用普通图建模EBSN会存在高维信息丢失问题,导致推荐质量降低.基于此,首先提出一种基于超图模型的EBSN个性化推荐(hypergraph-based personalized recommendation in EBSN,PRH)算法,其基本思想在于利用超图具有不丢失高维数据信息之特点来更准确地对EBSN中复杂社交关系数据进行高维建模,并利用流形排序正则化计算获取初步推荐结果.其次,又分别从查询向量设置方式改进和对不同类超边施以不同权重等角度,提出了优化的PRH(optimized PRH,oPRH)算法以进一步优化PRH算法所获推荐结果,从而实现精准推荐.扩展实验表明,基于超图的EBSN个性化推荐及其优化算法,推荐结果相比于以前基于普通图的推荐算法具有更高准确性.
