Learning source weights for target-position estimation: comparing fixed weights and an input-dependent rule
- 1Kyushu Institute of Technology
Abstract
Estimating an object's location requires combining uncertain measurements. Weights derived from an earlier calibration may become inappropriate when measurement errors change. We examined whether learning from noisy reference measurements improves position estimates, and whether weights computed from current inputs improve further than one learned set of weights used throughout evaluation. In simulations, we generated noisy position measurements of a target that remained fixed within each trial. Each two-input method combined the current measurement with the mean of three initial measurements. Measurement-accuracy reductions and added measurement offsets applied only after initialization. The estimator received no current or previous true target position. We repeated coordinate calibration, training, validation, and independent evaluation 100 times in each of four error conditions. Recalibration and fixed-weight learning explained most of the improvement over earlier supplied weights under reduced measurement accuracy and temporal correlation. With occasional large measurement errors, input-dependent weighting reduced mean squared error by 4.05% relative to learned fixed weights and assigned lower mean weights to measurements with added offsets. Its additional benefit was below 0.5% under independent errors and reduced current accuracy, while fixed weights had slightly lower mean error under temporal correlation. Methods using longer observation histories performed better in several conditions. Sensitivity analysis showed that shared coordinate bias and correlated reference errors limit conclusions about physical accuracy. The results show benefits and limits of recalibration, input-dependent weighting, and observation history within these measurement models.
Related
- Comparing pest survey methods through detection probability: seasonal and abundance-dependent detection of spotted lanternfly (Lycorma delicatula, Hemiptera: Fulgoridae)
- Comparing the efficacy of LORETA neurofeedback versus cognitive rehabilitation on working memory in children with learning disorders: A double-blind clinical trial.
- Predicting Elephant Crop-Raiding with Machine Learning to Inform Conservation Planning: A Case Study Comparing the Performance and Tradeoffs of GeoAI Algorithms in Northwestern Zimbabwe
- AMADEUS: Annotation-free multi-animal direction estimation using self-supervised learning
- Impaired value estimation over space explains turn-induced freezing of gait in Parkinson's disease: A cortico-basal ganglia-inspired reinforcement learning model
BibTeX
@misc{kobayashi2026learning,
title = {{Learning source weights for target-position estimation: comparing fixed weights and an input-dependent rule}},
author = {J. Kobayashi},
howpublished = {bioRxiv},
year = {2026},
month = jun,
doi = {10.64898/2026.06.08.730995},
url = {https://www.biorxiv.org/content/10.64898/2026.06.08.730995v2},
note = {CC BY},
}
RIS
TY - UNPB
TI - Learning source weights for target-position estimation: comparing fixed weights and an input-dependent rule
AU - J. Kobayashi
PY - 2026
DA - 2026/06/08
PB - bioRxiv
DO - 10.64898/2026.06.08.730995
UR - https://www.biorxiv.org/content/10.64898/2026.06.08.730995v2
AB - Estimating an object's location requires combining uncertain measurements. Weights derived from an earlier calibration may become inappropriate when measurement errors change. We examined whether learning from noisy reference measurements improves position estimates, and whether weights computed from current inputs improve further than one learned set of weights used throughout evaluation. In simulations, we generated noisy position measurements of a target that remained fixed within each trial. Each two-input method combined the current measurement with the mean of three initial measurements. Measurement-accuracy reductions and added measurement offsets applied only after initialization. The estimator received no current or previous true target position. We repeated coordinate calibration, training, validation, and independent evaluation 100 times in each of four error conditions. Recalibration and fixed-weight learning explained most of the improvement over earlier supplied weights under reduced measurement accuracy and temporal correlation. With occasional large measurement errors, input-dependent weighting reduced mean squared error by 4.05% relative to learned fixed weights and assigned lower mean weights to measurements with added offsets. Its additional benefit was below 0.5% under independent errors and reduced current accuracy, while fixed weights had slightly lower mean error under temporal correlation. Methods using longer observation histories performed better in several conditions. Sensitivity analysis showed that shared coordinate bias and correlated reference errors limit conclusions about physical accuracy. The results show benefits and limits of recalibration, input-dependent weighting, and observation history within these measurement models.
ER -