3D human pose estimation is a difficult task, due to challenges such as occluded body parts and ambiguous poses. Graph convolutional networks encode the structural information of the human skeleton in the form of an adjacency matrix, which is beneficial for better pose prediction. We propose one such graph convolutional network named PoseGraphNet for 3D human pose regression from 2D poses. Our network uses an adaptive adjacency matrix and kernels specific to neighbor groups. We evaluate our model on the Human3.6M dataset which is a standard dataset for 3D pose estimation. Our model's performance is close to the state-of-the-art, but with much fewer parameters. The model learns interesting adjacency relations between joints that have no physical connections, but are behaviorally similar.

随着物联网设备越来越多地集成到重要网络，对安全互联网（IoT）设备的需求正在增长。许多系统依靠这些设备保持可用并提供可靠的服务。拒绝对物联网设备的服务攻击是一个真正的威胁，因为这些低功率设备非常容易受到拒绝服务攻击。启用机器学习的网络入侵检测系统可以有效地识别新威胁，但是它们需要大量数据才能正常工作。有许多网络流量数据集，但很少有人关注物联网网络流量。在物联网网络数据集中，缺乏coap拒绝服务数据。我们提出了一个涵盖此差距的新型数据集。我们通过从真正的COAP拒绝服务攻击中收集网络流量来开发新数据集，并在多个不同的机器学习分类器上比较数据。我们证明数据集对许多分类器有效。