MétaCan
Menu
Back to cohort
Record W2133406022 · doi:10.11575/prism/26254

Gait Analysis for Pedestrian Navigation Using MEMS Handheld Devices

2012· dissertation· en· W2133406022 on OpenAlex
Melania Susi

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

fundA Canadian funder is recorded on the work.
no affNo Canadian affiliation: this work is invisible to an affiliation-only frame.
No Canadian affiliation. An affiliation-only frame, the usual design, would never have seen this work. It is one of the works that make the case for inverting the frame.

Bibliographic record

VenuePRISM (University of Calgary) · 2012
Typedissertation
Languageen
FieldEngineering
TopicGait Recognition and Analysis
Canadian institutionsnot available
FundersWestern Economic Diversification CanadaMinistry of Advanced Education, Government of Alberta
KeywordsInertial measurement unitAccelerometerGaitGyroscopeGait analysisInertial navigation systemOrthogonalityComputer scienceEngineeringArtificial intelligenceNoise (video)Inertial frame of referenceMathematicsMedicinePhysical medicine and rehabilitationPhysics

Abstract

fetched live from OpenAlex

Advances in Micro-Electro-Mechanical Systems (MEMS) technology play a central role in the design of new generation of smartphones. Indeed MEMS sensors, such as accelerometers and gyroscopes, are currently embedded in most smart devices in order to augment their capabilities. In the near future, it is expected that these sensors will be further exploited for pedestrian navigation purposes. However, the processing of signals from MEMS sensors cannot provide accurate navigation solutions without external aiding, e.g. from GNSS (Global Navigation Satellite Systems) signals, since their signals deteriorate due to significant errors, principally biases and drift which requires frequent sensor resets. When GNSS is not available and the sensors are mounted on the user’s foot, periodic zero velocity updates can be performed during the identified stance phases of the foot, namely the periods when the foot is flat on the ground. In the case of handheld devices, this approach cannot be adopted, since zero velocity periods are not present. Furthermore, when the sensors are held in a hand, the sensed motion can be decoupled from the global user’s motion rendering the situation much more complex to deal with. For this reason previous studies on pedestrian navigation are mainly focused on the body fixed sensor case. In this thesis, algorithms for characterizing the gait cycle of a pedestrian holding an IMU (Inertial Measurement Unit) in hand are proposed but without constraining the user in its behaviour and thus taking into account several sensor carrying modes. In view of the variety and complexity of human motions, the recognition of the user’s global motion from handheld devices is first thoroughly examined. A classifier able to recognize several different motion modes, including standing, walking, running, climbing and descending the stairs, is designed and implemented. Then an algorithm for evaluating the linear displacement of a pedestrian walking on a flat plane using only a handheld IMU is proposed. The complete algorithm comprises the following three modules: (1) Characterization of the user's activity and recognition of the sensor carrying mode, (2) Step detection and (3) Step length evaluation. The analysis leads to a novel step length model combining the user’s height, the step frequency and a set of three constants. First a universal model is proposed where the three constants have been trained with 12 different test subjects. Then, the same model is used for 10 different subjects to calibrate individually the set of constants. The validity of both universal and calibrated models is assessed in position domain using the above 10 test subjects. The fitted solution achieves an error between 2.5 and 5 % of the travelled distance, which is comparable with the performance of models proposed in the literature for body fixed sensors.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.885
Threshold uncertainty score0.979

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.018
GPT teacher head0.224
Teacher spread0.206 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it