Optimal Motion Cueing Algorithm Selection and Parameter Tuning for Sickness-Free Robocoaster Ride Simulations

2015 ◽  
pp. 127-135 ◽  
Author(s):  
Duc An Pham ◽  
Sebastian Röttgermann ◽  
Francisco Geu Flores ◽  
Andrés Kecskeméthy
Keyword(s):  
Parameter Tuning ◽  
Optimal Motion ◽  
Algorithm Selection ◽  
Motion Cueing

Applied Motion Cueing Strategies for Three Different Types of Motion Systems

2011 ◽  
Vol 11 (4) ◽  
Author(s):  
Martin Fischer ◽  
Håkan Sehammar ◽  
Göran Palmkvist
Keyword(s):  
Parameter Tuning ◽  
Degree Of Freedom ◽  
Motion Cues ◽  
Motion System ◽  
Motion Cueing ◽  
Different Types ◽  
Frequency Variations ◽  
Filter Frequency ◽  
Cross System

Simulators with motion systems are used to give the driver a motion feedback. The type of the motion system and its related motion envelope is a major factor for the ability to present certain motion cues. This paper describes algorithms for three types of motion systems with the focus on a new algorithm for 8-degree-of-freedom systems. As new features compared to other algorithms for this type of motion system consequent complementary splitting into low-, mid-, and high-frequent signals and cross-system washout compensation are introduced. Parameter tuning effects according to washout and signal splitting filter frequency variations are shown and analyzed.

scholarly journals Towards improving edge quality using combinatorial optimization and a novel skeletonize algorithm

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Marvin Arnold ◽  
Stefanie Speidel ◽  
Georges Hattab
Keyword(s):  
Optimal Parameter ◽  
Parameter Tuning ◽  
Natural Image ◽  
Data Sets ◽  
Post Processing ◽  
Algorithm Selection ◽  
Object Boundary ◽  
Discrete Parameter ◽  
Extensive Evaluation ◽  
Edge Quality

Abstract Background Object detection and image segmentation of regions of interest provide the foundation for numerous pipelines across disciplines. Robust and accurate computer vision methods are needed to properly solve image-based tasks. Multiple algorithms have been developed to solely detect edges in images. Constrained to the problem of creating a thin, one-pixel wide, edge from a predicted object boundary, we require an algorithm that removes pixels while preserving the topology. Thanks to skeletonize algorithms, an object boundary is transformed into an edge; contrasting uncertainty with exact positions. Methods To extract edges from boundaries generated from different algorithms, we present a computational pipeline that relies on: a novel skeletonize algorithm, a non-exhaustive discrete parameter search to find the optimal parameter combination of a specific post-processing pipeline, and an extensive evaluation using three data sets from the medical and natural image domains (kidney boundaries, NYU-Depth V2, BSDS 500). While the skeletonize algorithm was compared to classical topological skeletons, the validity of our post-processing algorithm was evaluated by integrating the original post-processing methods from six different works. Results Using the state of the art metrics, precision and recall based Signed Distance Error (SDE) and the Intersection over Union bounding box (IOU-box), our results indicate that the SDE metric for these edges is improved up to 2.3 times. Conclusions Our work provides guidance for parameter tuning and algorithm selection in the post-processing of predicted object boundaries.

scholarly journals Auto-CaseRec: Automatically Selecting and Optimizing Recommendation-Systems Algorithms

2020 ◽  
Author(s):  
Srijan Gupta ◽  
Joeran Beel
Keyword(s):  
Machine Learning ◽  
Recommender Systems ◽  
Recommender System ◽  
Parameter Tuning ◽  
Machine Learning Algorithms ◽  
Algorithm Selection ◽  
Automated Algorithm ◽  
Recommendation Algorithms ◽  
Automated Machine Learning ◽  
Human Effort

The advances in the field of Automated Machine Learning (AutoML) have greatly reduced human effort in selecting and optimizing machine learning algorithms. These advances, however, have not yet widely made it to Recommender-Systems libraries. We introduce Auto-CaseRec, a Python framework based on the CaseRec recommender-system library. Auto-CaseRec provides automated algorithm selection and parameter tuning for recommendation algorithms. An initial evaluation of Auto-CaseRec against the baselines shows an average 13.88% improvement in RMSE for theMovielens100K dataset and an average 17.95% improvement in RMSE for the Last.fm dataset.

Optimal motion cueing for 5-DOF motion simulations via a 3-DOF motion simulator

2009 ◽  
Vol 17 (1) ◽  
pp. 170-184 ◽  
Author(s):  
Yang-Hung Chang ◽  
Chung-Shu Liao ◽  
Wei-Hua Chieng
Keyword(s):  
Optimal Motion ◽  
Motion Simulator ◽  
Motion Cueing

Optimal Motion-Cueing Algorithm Using Motion System Kinematics

2012 ◽  
Vol 18 (4) ◽  
pp. 363-375 ◽  
Author(s):  
Masoumeh Aminzadeh ◽  
Ali Mahmoodi ◽  
Mehdi Sabzehparvar
Keyword(s):  
Optimal Motion ◽  
Motion System ◽  
Motion Cueing

A novel motion cueing algorithm integrated multi-sensory system–Vestibular and proprioceptive system

2019 ◽  
Vol 234 (2) ◽  
pp. 256-271
Author(s):  
Pham Duc-An ◽  
Nguyen Duc-Toan
Keyword(s):  
Visual Motion ◽  
Driving Simulator ◽  
Sensory System ◽  
Lateral Acceleration ◽  
Optimal Motion ◽  
Tilted Angle ◽  
Motion Cueing ◽  
Simulated Motion ◽  
S Curve ◽  
The Mathematical Model

Motion cueing algorithms are used to produce a motion which feels as realistic as possible while remaining in the limited workspace of driving simulators. Several optimal motion cueing algorithms were developed to improve both the exploitation of the workspace of a driving simulator and the realistic of the simulated motion. In the dynamics model of the optimal motion cueing algorithms, several kinds of motion-sensory systems are integrated to optimize the simulated motion sensation. However, most previous works have just focused on the visual and vestibular system. The mathematical model of the proprioceptive system, that also senses the non-visual motion, has rarely been concerned. In this paper, a novel optimal motion cueing algorithm, which integrates model of the proprioceptive system, is developed to reduce the false cues from muscle spindle of head/neck system sensing lateral tilted angle. The optimal motion cueing algorithm has a significant effect on the pilot's perception when the tilted angle is rather large. An example of the simulation of a roller coaster running along a planar S-curve trajectory with only lateral acceleration is investigated with current motion cueing algorithms and optimal motion cueing algorithm. Several objective criteria were introduced to evaluate the simulated perception of all investigated motion cueing algorithms. The results demonstrate that optimal motion cueing algorithm is better than current motion cueing algorithms in most criteria and also sub-criteria.

scholarly journals Optimal Motion Cueing Algorithm Using the Human Body Model.

2002 ◽  
Vol 45 (2) ◽  
pp. 487-491 ◽  
Author(s):  
Myung-Chul HAN ◽  
Hyung-Sang LEE ◽  
Suk LEE ◽  
Man Hyung LEE
Keyword(s):  
Human Body ◽  
Human Body Model ◽  
Optimal Motion ◽  
Body Model ◽  
Motion Cueing
Sign in / Sign up

Export Citation Format

Share Document