paper-with-me

Papers

Improved User Identification through Calibrated Monte-Carlo Dropout

2024-09-29 · Knowledge-Based Systems 2024 9 · Rouhollah Ahmadian, Mehdi Ghatee, Johan Wahlström

This paper presents an enhanced approach to user identification using smartphone and wearable sensor data. Our methodology involves segmenting input data and independently analyzing subsequences with CNNs. During testing, we apply calibrated Monte-Carlo Dropout to measure prediction uncertainty. By leveraging the weights obtained from uncertainty quantification, we integrate the results through weighted averaging, thereby improving overall identification accuracy. The main motivation behind this paper is the need to calibrate the CNN for improved weighted averaging. It has been observed that incorrect predictions often receive high confidence, while correct predictions are assigned lower confidence. To tackle this issue, we have implemented the Ensemble of Near Isotonic Regression (ENIR) as an advanced calibration technique. This ensures that certainty scores more accurately reflect the true likelihood of correctness. Furthermore, our experiment shows that calibrating CNN reduces the need for Monte Carlo samples in uncertainty quantification, thereby reducing computational costs. Our thorough evaluation and comparison of different calibration methods have shown improved accuracy in user identification across multiple datasets. Our results showed notable performance improvements when compared to the latest models available. In particular, our approach achieved better results than DB2 by 1.12% and HAR by 0.3% in accuracy.

📄 PDF Abstract BibTeX

Code (1)

Ruhallah93/User-Identification-by-Calibration

Tasks

Classifier calibrationUncertainty QuantificationUser Identification

Methods 이 논문이 사용한 방법론

Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

Uncertainty Quantification to Enhance Probabilistic Fusion Based User Identification Using Smartphones

2024-07-15 · journal 2024 7 · Rouhollah Ahmadian, Mehdi Ghatee, Johan Wahlström, Hadi Zare

User identification through smartphones and wearable sensors holds promise but faces challenges from variability in user activities and sampling windows. This paper presents a method that takes into account uncertainties…

Uncertainty QuantificationUser Identification

Robust Minimum Distance Inference in Structural Models

2023-10-09 · Joan Alegre, Juan Carlos Escanciano

This paper proposes minimum distance inference for a structural parameter of interest, which is robust to the lack of identification of other structural nuisance parameters. Some choices of the weighting matrix lead to a…

Explain then Rank: Scale Calibration of Neural Rankers Using Natural Language Explanations from LLMs

2024-02-19 · Puxuan Yu, Daniel Cohen, Hemank Lamba, Joel Tetreault 외

In search settings, calibrating the scores during the ranking process to quantities such as click-through rates or relevance levels enhances a system's usefulness and trustworthiness for downstream users. While previous …

Document RankingLearning-To-Rank

Laplacian Autoencoders for Learning Stochastic Representations

2022-06-30 · Marco Miani, Frederik Warburg, Pablo Moreno-Muñoz, Nicke Skafte Detlefsen 외

Established methods for unsupervised representation learning such as variational autoencoders produce none or poorly calibrated uncertainty estimates making it difficult to evaluate if learned representations are stable …

Bayesian InferenceOut-of-Distribution DetectionRepresentation Learning

SphUnc: Hyperspherical Uncertainty Decomposition and Causal Identification via Information Geometry

2026-03-01 · Rong Fu, Chunlei Meng, Jinshuo Liu, Dianyu Zhao 외 arxiv

Reliable decision-making in complex multi-agent systems requires calibrated predictions and interpretable uncertainty. We introduce SphUnc, a unified framework combining hyperspherical representation learning with struct…

Representation Learning