Quantifying Uncertainty with Probabilistic Machine Learning Modeling in Wireless Sensing

被引:1
|
作者
Kachroo, Amit [1 ]
Chinnapalli, Sai Prashanth [1 ]
机构
[1] Amazon Lab126, Sunnyvale, CA 94089 USA
关键词
probabilistic modeling; Bayesian networks; wireless sensing; WiFi; uncertainty quantification; machine learning;
D O I
10.1109/CCNC51644.2023.10059612
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
The application of machine learning (ML) techniques in wireless communication domain has seen a tremendous growth over the years especially in the wireless sensing domain. However, the questions surrounding the ML model's inference reliability, and uncertainty associated with its predictions are never answered or communicated properly. This itself raises a lot of questions on the transparency of these ML systems. Developing ML systems with probabilistic modeling can solve this problem easily, where one can quantify uncertainty whether it is arising from the data (irreducible error or aleotoric uncertainty) or from the model itself (reducible or epistemic uncertainty). This paper describes the idea behind these types of uncertainty quantification in detail and uses a real example of WiFi channel state information (CSI) based sensing for motion/no-motion cases to demonstrate the uncertainty modeling. This work will serve as a template to model uncertainty in predictions not only for WiFi sensing but for most wireless sensing applications ranging from WiFi to millimeter wave radar based sensing that utilizes AI/ML models.
引用
收藏
页数:2
相关论文
共 50 条
  • [31] Quantifying uncertainty in chemical systems modeling
    Reagan, MT
    Najm, HN
    Pébay, PP
    Knio, OM
    Ghanem, RG
    INTERNATIONAL JOURNAL OF CHEMICAL KINETICS, 2005, 37 (06) : 368 - 382
  • [32] Quantifying Uncertainty in Food Security Modeling
    Shoaib, Syed Abu
    Khan, Mohammad Zaved Kaiser
    Sultana, Nahid
    Mahmood, Taufique H.
    AGRICULTURE-BASEL, 2021, 11 (01): : 1 - 16
  • [33] Quantifying and explaining machine learning uncertainty in predictive process monitoring: an operations research perspective
    Mehdiyev, Nijat
    Majlatow, Maxim
    Fettke, Peter
    ANNALS OF OPERATIONS RESEARCH, 2024,
  • [34] LUNA: Quantifying and Leveraging Uncertainty in Android Malware Analysis through Bayesian Machine Learning
    Backes, Michael
    Nauman, Mohammad
    2017 IEEE EUROPEAN SYMPOSIUM ON SECURITY AND PRIVACY (EUROS&P), 2017, : 204 - 217
  • [35] Probabilistic Fuzzy Logic Modeling: Quantifying Uncertainty of Mineral Prospectivity Models Using Monte Carlo Simulations
    Lisitsin, Vladimir A.
    Porwal, Alok
    McCuaig, T. Campbell
    MATHEMATICAL GEOSCIENCES, 2014, 46 (06) : 747 - 769
  • [36] Application of Probabilistic Modeling and Machine Learning to the Diagnosis of FTTH GPON Networks
    Gosselin, Stephane
    Courant, Jean-Luc
    Tembo, Serge Romaric
    Vaton, Sandrine
    2017 INTERNATIONAL CONFERENCE ON OPTICAL NETWORK DESIGN AND MODELING (ONDM), 2017,
  • [37] Probabilistic Fuzzy Logic Modeling: Quantifying Uncertainty of Mineral Prospectivity Models Using Monte Carlo Simulations
    Vladimir A. Lisitsin
    Alok Porwal
    T. Campbell McCuaig
    Mathematical Geosciences, 2014, 46 : 747 - 769
  • [38] Three-Dimensional Probabilistic Hydrofacies Modeling Using Machine Learning
    Kawo, Nafyad Serre
    Korus, Jesse
    Kishawi, Yaser
    Haacker, Erin Marie King
    Mittelstet, Aaron R.
    WATER RESOURCES RESEARCH, 2024, 60 (07)
  • [39] Probabilistic Modeling and Machine Learning for Preventative Maintenance Prediction in Semiconductor Manufacturing
    Wright, Tori
    Tse, Brian
    Nsiye, Emmanuel
    Azinord, Timothy
    Medina, David
    Mondesire, Sean
    2024 35TH ANNUAL SEMI ADVANCED SEMICONDUCTOR MANUFACTURING CONFERENCE, ASMC, 2024,
  • [40] Probabilistic Regularized Extreme Learning Machine for Robust Modeling of Noise Data
    Lu, XinJiang
    Ming, Li
    Liu, WenBo
    Li, Han-Xiong
    IEEE TRANSACTIONS ON CYBERNETICS, 2018, 48 (08) : 2368 - 2377