发表机构
College of Computer and Data Science, Fuzhou University; Engineering Research Center of Big Data Intelligence, Ministry of Education; Fujian Key Laboratory of Network Computing and Intelligent Information Processing, Fuzhou University; Department of Computer Science, Aalborg University; Space Information Research Institute, Hangzhou Dianzi University; College of Computer Science and Technology, Zhejiang University; State Key Laboratory of Blockchain and Data Security, Zhejiang University; School of Computer Science and Engineering, The University of New South Wales; CSIRO’s Data61（福州大学计算机与数据科学学院; 教育部大数据智能工程研究中心; 福州大学福建省网络计算与智能信息处理重点实验室; 奥尔堡大学计算机科学系; 杭州电子科技大学空间信息研究院; 浙江大学计算机科学与技术学院; 浙江大学区块链与数据安全国家重点实验室; 新南威尔士大学计算机科学与工程学院; 联邦科学与工业研究组织数据61）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对物联网中相关时间序列数据缺失值插补问题，提出AdaCTSi方法，结合一次性时间卷积网络与相关技术提取解耦特征，经实验验证该方法能有效降低MAE，且单个模型支持自适应推理，可部署在商用设备上。
AI 中文摘要
物联网（IoT）应用程序生成大量相关时间序列（CTS）数据，这些数据通常包含缺失值，需要进行插补。现有方法强调准确性，但往往缺乏对不断变化的物联网环境的适应性：它们容易受到传感器故障的影响，无法仅对不完整的传感器进行选择性插补，并且使用不适应资源可用性的静态架构。为了解决这些限制，我们提出了AdaCTSi，一种用于变化环境的自适应CTS插补器。AdaCTSi将一次性时间卷积网络与学习到的时间传感器索引表相结合，以提取复杂的时空特征并将其解耦为传感器级嵌入，从而适应不同的传感器子集。稀疏空间注意力有效地提取动态空间相关性，而相关加权传感器选择则选择信息丰富的传感器以提供足够的空间上下文。在涵盖交通、空气质量和轨迹数据的12种基线方法、3种适应性场景和5个基准数据集上进行的实验表明，相对于每个数据集上最强的基线，AdaCTSi平均将平均绝对误差（MAE）降低了33.1%。单个训练模型支持传感器子集和资源自适应推理，其适度的内存占用使得能够部署在包括微控制器（MCU）在内的商用计算设备上。
英文摘要
Internet of Things (IoT) applications generate vast amounts of Correlated Time Series (CTS) data that often contain missing values and require imputation. Existing methods emphasize accuracy but often lack adaptability to changing IoT environments: they are vulnerable to sensor failures, cannot selectively impute only incomplete sensors, and use static architectures that do not adapt to resource availability. To address these limitations, we propose AdaCTSi, an adaptive CTS imputer for changing environments. AdaCTSi combines a One-shot Temporal Convolutional Network with a Learned Time-Sensor Index Table to extract and decouple complex spatio-temporal features into sensor-wise embeddings, enabling adaptation to varying sensor subsets. Sparse Spatial Attention efficiently extracts dynamic spatial correlations, while Correlation-Weighted Sensor Selection selects informative sensors to provide sufficient spatial context. Experiments with twelve baseline methods, three adaptability scenarios, and five benchmark datasets covering traffic, air quality, and trajectory data show that AdaCTSi reduces MAE by an average of 33.1% relative to the strongest baseline on each dataset. A single trained model supports sensor-subset and resource-adaptive inference, and its modest memory footprint enables deployment on commodity computing devices, including MCUs.
Comments15 pages, 9 figures. Accepted for publication in IEEE Transactions on Knowledge and Data Engineering (IEEE TKDE)
