ID 原文 译文
3193 在该模型基础上，提出了一种基于功率分配协作的 SWIPT 中继选择策略。 Based on the model, apower distribution collaboration SWIPT relay selection strategy was proposed to optimize system throughput.
3194 该策略基于通信服务质量与源节点发射功率等约束建立问题模型， Firstly, the problem model was established based on the constraints of communication quality of service and transmission power of source nodes.
3195 通过数学变换将原非线性 0-1 规划问题转换为一对耦合优化问题，基于内部优化问题的最优解解决最优中继选择的外部优化问题， And then, the original nonlinear 0-1 programming problem was converted into a pair of coupling optimiza-tion problem by mathematical transformation, and the optimal relay selection of outer optimization problem was solved based on the optimal solution of the internal optimization problem.
3196 利用最优中继选择算法最大化系统吞吐量。 Finally, an optimal relay selection algorithm was used to maximize system throughput.
3197 仿真结果表明，所提模型和策略在吞吐量增益方面优于传统的最大最小中继选择方案，并且 EAP 的考虑能够显著提高系统中断性能。 Simulation results show that the proposed model and strategy are superior to the tradi-tional maximum-minimum relay selection schemes in terms of throughput gain, and the consideration of EAP can signif-icantly improve the interrupt performance.
3198 针对复杂环境导致目标跟踪性能显著下降的问题，提出基于粒子滤波与度量学习的目标跟踪方法。 Focusing on the issue of the significant degradation of target tracking performance caused by adverse factorsin complex environment, a target tracking method based on particle filtering and metric learning was proposed.
3199 所提方法首先离线训练可高效获取目标特征的卷积神经网络（CNN）； First of all, a convolutional neural network (CNN) was offline-trained via the proposed method to effectively obtain the target characteristics.
3200 其次，基于核回归度量学习（MLKR）方法构建最小化预测误差的距离度量矩阵优化模型，并利用梯度下降法求解所得模型以获得候选目标最优解； After that, the distance measurement matrix optimization model to minimize the prediction error could beconstructed on the basis of the metric learning for kernel regression (MLKR) method, and the resultant model could be handled via using the gradient descent approach to obtain the optimal solution of the candidate target.
3201 再次，基于最优候选预测值计算重构误差以构建目标观测模型； Moreover, based on the predicted value of the optimal candidate target, the reconstruction error was calculated to construct the target observa-tion model.
3202 最后，引入长短时稳定更新策略并基于粒子滤波跟踪框架实现有效跟踪。 Finally, a long-short-term update strategy was introduced to achieve the effective target tracking under theparticle filter tracking framework.