Increasing the Robustness of Model Predictions to Missing Sensors in Earth Observation
University of Kaiserslautern-Landau, Kaiserslautern, Germany(凯撒斯劳滕-兰道大学,凯撒斯劳滕,德国);German Research Center for Artificial Intelligence, Kaiserslautern, Germany(德国人工智能研究中心,凯撒斯劳滕,德国)
Francisco Mena, Diego Arenas, Andreas Dengel
备注:
Accepted at the MACLEAN workshop in the ECML/PKDD 2024
发表信息:
Machine Learning and Principles and Practice of Knowledge Discovery in Databases. ECML PKDD 2024
Multi-sensor ML models for EO aim to enhance prediction accuracy by integrating data from various sources. However, the presence of missing data poses a significant challenge, particularly in non-persistent sensors that can be affected by external factors. Existing literature has explored strategies like temporal dropout and sensor-invariant models to address the generalization to missing data issues. Inspired by these works, we study two novel methods tailored for multi-sensor scenarios, namely Input Sensor Dropout (ISensD) and Ensemble Sensor Invariant (ESensI). Through experimentation on three multi-sensor temporal EO datasets, we demonstrate that these methods effectively increase the robustness of model predictions to missing sensors. Particularly, we focus on how the predictive performance of models drops when sensors are missing at different levels. We observe that ensemble multi-sensor models are the most robust to the lack of sensors. In addition, the sensor dropout component in ISensD shows promising robustness results.
Missing Data as Augmentation in the Earth Observation Domain: A Multi-View Learning Approach
Department of Computer Science, University of Kaiserslautern-Landau (RPTU)(卡斯尔拉特-兰道大学计算机科学系);SDS, German Research Center for Artificial Intelligence (DFKI)(德国人工智能研究中心(DFKI))
SERT: A Transfomer Based Model for Spatio-Temporal Sensor Data with Missing Values for Environmental Monitoring
Hamilton Institute(汉密尔顿研究所);Insight Centre for Data Analytics(洞察数据分析中心);Maynooth University(梅努斯大学);University of León(莱昂大学);Dublin City University(都柏林城市大学)
Ensemble Learning for Fusion of Multiview Vision with Occlusion and Missing Information: Framework and Evaluations with Real-World Data and Applications in Driver Hand Activity Recognition
Activity and Subject Detection for UCI HAR Dataset with & without missing Sensor Data
dept. of Electrical Eng. Stony Brook University(电气工程系 斯通布鲁克大学);dept. of Comp. Sci. Stony Brook University(计算机科学系 斯通布鲁克大学);dept. of Comp. Eng. American International University Bangladesh(计算机工程系 美国国际大学(孟加拉国))
本文提出基于 LSTM 的轻量级模型,在 UCI HAR 数据集上同时完成活动与主体识别,并通过 KNN 等插补方法有效处理传感器缺失。
Uncertainty-aware Traffic Prediction under Missing Data
School of Computing and Augmented Intelligence(计算与增强智能学院);Arizona State University(亚利桑那州立大学);Faculty of Electronic and Information Engineering(电子与信息工程学院);Xi’an Jiaotong University(西安交通大学);School of Electronic Information and Electrical Engineering(电子信息与电气工程学院);Shanghai Jiaotong University(上海交通大学)
Multi-modal Co-learning for Earth Observation: Enhancing single-modality models via modality collaboration
Department of Computer Science, University of Kaiserslautern-Landau (RPTU)(科斯拉尔特伦大学计算机科学系);SDS, German Research Center for Artificial Intelligence (DFKI)(德国人工智能研究中心(DFKI));INRAE, UMR TETIS, University of Montpellier(蒙彼利埃大学UMR TETIS);CIRAD, UMR TETIS, University of Montpellier(蒙彼利埃大学UMR TETIS);INRIA, EVERGREEN, University of Montpellier(蒙彼利埃大学)
Deep Multimodal Learning with Missing Modality: A Survey
The Australian National University(澳大利亚国立大学);Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学);Adelaide University(阿德莱德大学);The University of Surrey(萨里大学)
SpectralEarth-FM: Bringing Hyperspectral Imagery into Multimodal Earth Observation Pretraining
Chair of Data Science in Earth Observation(地球观测数据科学主任);Technical University of Munich(慕尼黑技术大学);Remote Sensing Technology Institute(遥感技术研究所);German Aerospace Center (DLR)(德国航空航天中心);Department of Aerospace Engineering(航空航天工程系);University of the Bundeswehr Munich(联邦国防军慕尼黑大学);LEAP;Munich Center for Machine Learning (MCML)(慕尼黑机器学习中心);Univ. Grenoble Alpes(格勒诺布尔阿尔卑斯大学);Inria(法国国家信息与自动化技术研究院);CNRS(法国国家科学研究中心);Grenoble INP(格勒诺布尔INP);LJK
Robust Multimodal Learning Framework For Intake Gesture Detection Using Contactless Radar and Wearable IMU Sensors
e-Media Research Lab(e-Media研究实验室);ESAT-STADIUS Division, KU Leuven(ESAT-STADIUS部门,KU莱顿大学);M-Group, DistriNet, Department of Computer Science, KU Leuven(M组、DistriNet、计算机科学系,KU莱顿大学)
DiffLight: A Partial Rewards Conditioned Diffusion Model for Traffic Signal Control with Missing Data
School of Computer Science and Technology, Beijing Jiaotong University(北京交通大学计算机与信息技术学院);Beijing Key Laboratory of Traffic Data Analysis and Mining(北京市交通数据分析与挖掘重点实验室)
Federated Latent Factor Learning for Recovering Wireless Sensor Networks Signal with Privacy-Preserving
College of Computer and Information Science(计算机与信息科学学院);Southwest University(西南大学);School of Engineering(工程学院);University of Western Australia(西澳大学);College of Food Science(食品科学学院);Chongqing True Flavor Food Co LTD(重庆真味食品有限公司)
Disentangling Imperfect: A Wavelet-Infused Multilevel Heterogeneous Network for Human Activity Recognition in Flawed Wearable Sensor Data
School of Computer Science and Engineering, Tianjin University of Technology(天津理工大学计算机科学与工程学院);Technical University of Denmark(丹麦技术大学);Aalborg University(奥尔堡大学)
TSGuard: A Real-Time Framework for Detecting and Imputing Missing Data in Streaming Time Series
University of Luxembourg(卢森堡大学);Hassiba Benbouali University of Chlef(谢莱夫哈西巴·本布阿里大学);Université Paris Cité(巴黎西岱大学);École Supérieure d’Informatique(高等计算机学院)