Cover Image

The Driver-Blindness Phenomenon: Why Deep Sequence Models Default to Autocorrelation in Blood Glucose Forecasting

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Shakeri, Heman
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

From Prediction to Practice: A Task-Aware Evaluation Framework for Blood Glucose Forecasting
by: Namazi, Alireza, et al.
Published: (2026)

The Metaphysics We Train: A Heideggerian Reading of Machine Learning
by: Shakeri, Heman
Published: (2025)

Why the Counterintuitive Phenomenon of Likelihood Rarely Appears in Tabular Anomaly Detection with Deep Generative Models?
by: Kim, Donghwan, et al.
Published: (2026)

Autocorrelation Reintroduces Spectral Bias in KANs for Time Series Forecasting
by: Zeng, Chen, et al.
Published: (2026)

AttenGluco: Multimodal Transformer-Based Blood Glucose Forecasting on AI-READI Dataset
by: Farahmand, Ebrahim, et al.
Published: (2025)

Glycemic-Aware and Architecture-Agnostic Training Framework for Blood Glucose Forecasting in Type 1 Diabetes
by: Khamesian, Saman, et al.
Published: (2025)

LMS-AutoTSF: Learnable Multi-Scale Decomposition and Integrated Autocorrelation for Time Series Forecasting
by: Delibasoglu, Ibrahim, et al.
Published: (2024)

Mitigating Exposure Bias in Risk-Aware Time Series Forecasting with Soft Tokens
by: Namazi, Alireza, et al.
Published: (2025)

Flexible Blood Glucose Control: Offline Reinforcement Learning from Human Feedback
by: Emerson, Harry, et al.
Published: (2025)

Lightweight Sequential Transformers for Blood Glucose Level Prediction in Type-1 Diabetes
by: Barbato, Mirko Paolo, et al.
Published: (2025)

Blood Glucose Control Via Pre-trained Counterfactual Invertible Neural Networks
by: Jiang, Jingchi, et al.
Published: (2024)

An Interpretable Approach to Load Profile Forecasting in Power Grids using Galerkin-Approximated Koopman Pseudospectra
by: Tavasoli, Ali, et al.
Published: (2023)

Online Meal Detection Based on CGM Data Dynamics
by: Tavasoli, Ali, et al.
Published: (2025)

PhysioSeq2Seq: A Hybrid Physiological Digital Twin and Sequence-to-Sequence LSTM for Long-Horizon Glucose Forecasting in Type 1 Diabetes
by: Tran, Phat, et al.
Published: (2026)

Privacy Preserved Blood Glucose Level Cross-Prediction: An Asynchronous Decentralized Federated Learning Approach
by: Piao, Chengzhe, et al.
Published: (2024)

Evaluating the Sensitivity of BiLSTM Forecasting Models to Sequence Length and Input Noise
by: Albelali, Salma, et al.
Published: (2025)

A Multitask VAE for Time Series Preprocessing and Prediction of Blood Glucose Level
by: AbuSaleh, Ali, et al.
Published: (2024)

Grokking Explained: A Statistical Phenomenon
by: Carvalho, Breno W., et al.
Published: (2025)

GARNN: An Interpretable Graph Attentive Recurrent Neural Network for Predicting Blood Glucose Levels via Multivariate Time Series
by: Piao, Chengzhe, et al.
Published: (2024)

MC-GTA: Metric-Constrained Model-Based Clustering using Goodness-of-fit Tests with Autocorrelations
by: Wang, Zhangyu, et al.
Published: (2024)

Enhancing Solar Driver Forecasting with Multivariate Transformers
by: Sanchez-Hurtado, Sergio, et al.
Published: (2024)

Why Do Transformers Fail to Forecast Time Series In-Context?
by: Zhou, Yufa, et al.
Published: (2025)

Towards Faster Training of Diffusion Models: An Inspiration of A Consistency Phenomenon
by: Xu, Tianshuo, et al.
Published: (2024)

GSA-Forecaster: Forecasting Graph-Based Time-Dependent Data with Graph Sequence Attention
by: Li, Yang, et al.
Published: (2021)

A Multi-scenario Attention-based Generative Model for Personalized Blood Pressure Time Series Forecasting
by: Wan, Cheng, et al.
Published: (2024)

Data Complexity-aware Deep Model Performance Forecasting
by: Chen, Yen-Chia, et al.
Published: (2026)

Baguan-TS: A Sequence-Native In-Context Learning Model for Time Series Forecasting with Covariates
by: Yang, Linxiao, et al.
Published: (2026)

Long Input Sequence Network for Long Time Series Forecasting
by: Ma, Chao, et al.
Published: (2024)

Deep Kernel Learning for Stratifying Glaucoma Trajectories
by: Rushing, Bruce, et al.
Published: (2026)

On Identifying Why and When Foundation Models Perform Well on Time-Series Forecasting Using Automated Explanations and Rating
by: Widener, Michael, et al.
Published: (2025)

Optimal Kernel Tuning Parameter Prediction using Deep Sequence Models
by: Mahmood, Khawir, et al.
Published: (2024)

The Stationarity Bias: Stratified Stress-Testing for Time-Series Imputation in Regulated Dynamical Systems
by: Fathkouhi, Amirreza Dolatpour, et al.
Published: (2026)

Default Machine Learning Hyperparameters Do Not Provide Informative Initialization for Bayesian Optimization
by: Prieto, Nicolás Villagrán, et al.
Published: (2026)

Knowledge-enhanced Transformer for Multivariate Long Sequence Time-series Forecasting
by: Kakde, Shubham Tanaji, et al.
Published: (2024)

Detecting the Future: All-at-Once Event Sequence Forecasting with Horizon Matching
by: Karpukhin, Ivan, et al.
Published: (2024)

Crime Forecasting: A Spatio-temporal Analysis with Deep Learning Models
by: Mao, Li, et al.
Published: (2025)

ARIES: Relation Assessment and Model Recommendation for Deep Time Series Forecasting
by: Wang, Fei, et al.
Published: (2025)

Heterogeneous Graph Pre-training Based Model for Secure and Efficient Prediction of Default Risk Propagation among Bond Issuers
by: Li, Xurui, et al.
Published: (2025)

The Over-Certainty Phenomenon in Modern Test-Time Adaptation Algorithms
by: Amin, Fin, et al.
Published: (2024)

Beyond the Hype: Comparing Lightweight and Deep Learning Models for Air Quality Forecasting
by: Gondal, Moazzam Umer, et al.
Published: (2025)