| 本文已被：浏览 887次 下载 1141次 |
码上扫一扫！ |
|
|
| 时序数据域自适应的时空卷积与对抗互学习 |
|
孙杰1,2,3, 李贳宸2, 陈仲珊3, 王小正1, 郑豪1, 陈长伟1, 常合友1
|
|
1.南京晓庄学院 信息工程学院, 江苏 南京 211171;2.南京邮电大学 计算机学院, 江苏 南京 210023;3.南京特殊教育师范学院 数学与信息科学学院, 江苏 南京 210038
|
|
| 摘要: |
| 在时序数据分析领域, 跨域数据分布的偏移显著削弱了模型的泛化性能. 为此, 开发一种称为TPN的端到端时序数据域自适应框架. 该框架融合了时序模式激活模块(TPAM)与Transformer编码器. TPAM通过双层时空卷积操作捕捉序列特征的空间及时间依赖性, 结合Sigmoid和tanh激活函数对提取的特征进行非线性融合, 再经由线性投影恢复至原通道尺寸, 以此强化模型的时序特征提取能力. TPN还引入了增强对抗范式(EAP), 通过域分类损失和操作顺序预测损失, 增强生成器与判别器的协同对抗, 有效缩减源域与目标域间的数据分布差距, 提升模型的域适应性. 在Opportunity、WISDM及HHAR这3大公开人体活动识别数据集上的实证结果显示, TPN在准确率和F1值方面较现有方法最高提升了6%, 且参数量和运行时间较少. 深入的消融与可视化实验进一步验证了TPAM和EAP的有效性, 表明TPN在特征抽取与域对齐上具有良好表现. |
| 关键词: 时序数据域自适应 时序模式激活模块 增强对抗范式 |
| DOI：10.13328/j.cnki.jos.007430 |
| 分类号:TP18 |
| 基金项目:国家自然科学基金 (62177028); 江苏省教育科学“十四五”重点课题 (B-b/2024/01/145); 江苏省高等教育学会重点课题 (2024CXJG029); 江苏省高等学校自然科学研究面上项目 (22KJD520005) |
|
| Temporal-spatial Convolution and Adversarial Mutual Learning for Time Series Domain Adaptation |
|
SUN Jie1,2,3, LI Shi-Chen2, CHEN Zhong-Shan3, WANG Xiao-Zheng1, ZHENG Hao1, CHEN Chang-Wei1, CHANG He-You1
|
|
1.School of Information Engineering, Nanjing Xiaozhuang University, Nanjing 211171, China;2.School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing 210023, China;3.School of Mathematics and Information Science, Nanjing Normal University of Special Education, Nanjing 210038, China
|
| Abstract: |
| In the field of time series data analysis, cross-domain data distribution shifts significantly weaken model generalization performance. To address this, an end-to-end time series domain adaptation framework, called TPN, is developed. This framework creatively integrates a temporal pattern activation module (TPAM) with a Transformer encoder. TPAM captures spatial and temporal dependencies of sequence features through dual-layer spatio-temporal convolution operations, combines Sigmoid and Tanh activation functions for the non-linear fusion of extracted features, and restores the original channel dimensions via linear projection, thus enhancing the model’s ability to extract temporal features. TPN also introduces an enhanced adversarial paradigm (EAP), which strengthens generator-discriminator-based collaborative adversarial learning through domain classification loss and operation order prediction loss. This effectively reduces data distribution discrepancies between source and target domains, improving the model’s domain adaptability. Empirical results on three public human activity recognition datasets (Opportunity, WISDM, and HHAR) demonstrate that TPN improves accuracy and F1 by up to 6% compared to existing methods, with fewer parameters and shorter runtime. In-depth ablation and visualization experiments further validate the effectiveness of TPAM and EAP, showing TPN’s strong performance in feature extraction and domain alignment. |
| Key words: time series domain adaptation temporal pattern activation module (TPAM) enhanced adversarial paradigm (EAP) |
