用同一模型同时识别心跳身份和动作，准确率超99%。
DT4ECG: A Dual-Task Learning Framework for ECG-Based Human Identity Recognition and Human Activity Detection
- 双任务学习框架，用1D-CNN加残差块提取心电特征。
- 在真实数据上实现99.12%身份识别与90.11%动作分类准确率。
- 适合智能健康设备、可穿戴系统等场景使用。
本文提出DT4ECG，一种基于心电图（ECG）的人体身份识别与活动检测双任务学习框架。该框架采用带残差块的一维卷积神经网络（1D-CNN）作为主干网络，提取具有区分性的心电特征。为增强特征表达，提出一种新型序列通道注意力（SCA）机制，融合通道与时间序列上下文注意力，有效突出时空维度上的关键特征。针对多任务学习中的梯度不平衡问题，引入GradNorm方法，根据梯度幅值动态调整损失权重，保障各任务训练均衡。实验结果表明，模型在身份分类任务上达到99.12%准确率，在活动分类任务上达90.11%准确率。这些成果展示了该框架在健身监测、个性化医疗等场景中提升安全性和用户体验的潜力，为心电生物识别技术融入日常智能设备提供了新路径。
原文摘要 · Abstract (English)
This article introduces DT4ECG, an innovative dual-task learning framework for Electrocardiogram (ECG)-based human identity recognition and activity detection. The framework employs a robust one-dimensional convolutional neural network (1D-CNN) backbone integrated with residual blocks to extract discriminative ECG features. To enhance feature representation, we propose a novel Sequence Channel Attention (SCA) mechanism, which combines channel-wise and sequential context attention to prioritize informative features across both temporal and channel dimensions. Furthermore, to address gradient imbalance in multi-task learning, we integrate GradNorm, a technique that dynamically adjusts loss weights based on gradient magnitudes, ensuring balanced training across tasks. Experimental results demonstrate the superior performance of our model, achieving accuracy rates of 99.12% in ID classification and 90.11% in activity classification. These findings underscore the potential of the DT4ECG framework in enhancing security and user experience across various applications such as fitness monitoring and personalized healthcare, thereby presenting a transformative approach to integrating ECG-based biometrics in everyday technologies.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。