Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; 22 of the 22 references it cites were found in a registry or an index; none of the 27 sources its claims cite is checked for support yet.

Probabilistic Intentionality Prediction for Target Selection Based on Partial Cursor Tracks

Ahmad, Bashar I., Langdon, Patrick M., Bunch, Pete, Godsill, Simon J. · 2014 · Lecture Notes in Computer Science

Overview

CoChat Summary

TL;DR

The paper introduces probabilistic intentionality prediction algorithms that infer the intended target from partial cursor tracks, including nearest neighbour, bearing angle, mean reverting diffusion, composite, and weighted bearing with distance models, with optional linear Kalman filter smoothing. Across two point-click datasets, MRD and LKF-smoothed predictors gave the highest correct-prediction rates, with over 60% accuracy for the able-bodied user and notable gains for the motor-impaired user after smoothing.

Key findings

  • The MRD-based predictor outperformed the other methods: able-bodied raw MRD 61.8% and LKF-MRD 62.1%; motor-impaired raw MRD 18.6% and LKF-MRD 44.1%.
  • LKF smoothing markedly improved motor-impaired performance: NN 15.3% to 38.4%, BA 4.3% to 28.3%, MRD 18.6% to 44.1%, WBD 16.4% to 38.8%, and COM 14.8% to 39.7%; for the able-bodied user the LKF impact was marginal, e.g. MRD 61.8% to 62.1%.
  • The paper reports that WBD and COM brought notable benefits compared with conventional NN and BA, and that with the adopted prediction algorithms the system can correctly anticipate the target with over 60% accuracy, potentially reducing pointing time by 60% for able-bodied users.
  • The paper states that 20% of the cursor track can suffice to make a correct prediction on the intended target.

Methods

  • Design: a probabilistic MAP framework for predicting the intended target from partial cursor tracks, with algorithms NN, BA, MRD, COM, and WBD, plus LKF-based smoothing of perturbed cursor trajectories.
  • Data: two point-click datasets, one from an able-bodied user and one from a severely motor-impaired user with notable tremor, using ISO 9241-like selection tasks with multiple distractors on screen.
  • Analysis: performance was measured as the percentage of time the predictor made a correct decision from a partial cursor track; design parameters were obtained from Monte Carlo simulations, selecting parameters that yielded the highest percentage of correct predictions.

Limitations

  • The paper states that BA performs poorly when more than one target is present in the cursor direction of travel, especially when the cursor is far from the target cluster; BA angle can also become arbitrarily large near the target, leading to small likelihood probabilities and incorrect predictions.
  • The paper states that regression-based approaches are ineffective for motor-impaired users because their cursor tracks are highly nonlinear and perturbed, and that inverse-optimal-control prediction has high computational cost, requires substantial parameter training, and imposes stringent trajectory constraints.
  • Evident from the text: the evaluation uses only two participants (one able-bodied, one severely motor impaired), so generalizability is limited; design parameters were selected via Monte Carlo simulations to maximize correct predictions, which may overfit to the tested datasets.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.1007/978-3-319-07446-7_42

Cites

22 of 22 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Verification

Claims the paper makes

0 Valid · 2 Not valid · 16 Not checked · 21 Own results and interpretations

10 more claims

Create a free account to see all 39 claims and every source verdict.

See all claims — free account
  • The quote only partly states this claim. 1
  • It may state two separate claims as one. 13
  • Probably not a substantial claim. 12

Create a free account to see these claims.

Citations

Cites

Show all 21 references

Cited by

See all 8

Metadata

Authors
Ahmad, B. I., Langdon, P. M., Bunch, P., & Godsill, S. J.
Affiliations
University of Cambridge (GB)
Venue
Lecture Notes in Computer Science
Published
2014
Pages
427-438
ISSN
  • 0302-9743 (ISSN-L)
  • 1611-3349
OpenAlex
W2436819
Cited by
8
References
21
Citations by year
2025: 1 · 2023: 1 · 2021: 1 · 2020: 1 · 2018: 1 · 2016: 1 · 2015: 2
FWCI
0.77
Type
conference paper
Language
en
Open access
closed
Licence
www.springer.com/tdm (tdm)
Locations
  • Lecture notes in computer science (publishedVersion)
  • Cambridge University Engineering Department Publications Database (submittedVersion)
Funders
Engineering and Physical Sciences Research Council (EP/K020153/1)
Topics
  • Physical Sciences › Computer Science › Human-Computer Interaction › Gaze Tracking and Assistive Technology
  • Physical Sciences › Computer Science › Human-Computer Interaction › Interactive and Immersive Displays
  • Life Sciences › Neuroscience › Cognitive Neuroscience › Motor Control and Adaptation
Keywords
target selection, pointing task, probabilistic forecasting, pointing accuracy, human-computer interaction

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

A language model drew the claims from the paper on 2026-09-30, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).

A second model labelled each claim on 2026-09-30 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Probabilistic Intentionality Prediction for Target Selection Based on Partial Cursor Tracks. https://app.cochat.ai/papers/10.1007/978-3-319-07446-7_42
The paper
Ahmad, B. I., Langdon, P. M., Bunch, P., & Godsill, S. J. (2014). Probabilistic Intentionality Prediction for Target Selection Based on Partial Cursor Tracks. Lecture Notes in Computer Science. https://doi.org/10.1007/978-3-319-07446-7_42

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.