Genetically Designed Models for Accurate Imputation of Missing Traffic Counts
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.
Bibliographic record
Abstract
Highway agencies traditionally have used simple methods to estimate missing values in their data sets since traffic data programs were established in the 1930s. A literature review shows that current practices for imputing traffic data are varied and intuitive. No research has been conducted to assess imputation accuracy. Typical traditional imputation methods used by highway agencies were identified in a study and used to estimate missing hourly volumes for sample traffic counts from Alberta, Canada, to examine their accuracy. It was found that such models usually resulted in large imputation errors. For example, for imputing missing data of a traffic count located on a commuter site, the 95th percentile errors for the traditional methods are usually between 10% and 20%. Advanced models based on genetic algorithms, a time-delay neural network, and locally weighted regression developed in the study show higher accuracy than traditional imputation models. Most of the 95th percentile errors for genetically designed neural network models tested on the same count are below 6%. For genetically designed regression models, the 95th percentile errors are less than 2%. Study results based on the sample traffic counts from different trip pattern groups and functional classes show that underlying traffic patterns have some influence on imputation accuracy. However, genetically designed regression models still can limit the 95th percentile errors to less than 5% in most cases. It is believed that such accurate imputations should be able to supply satisfactory data for decision making at both planning and operation levels.
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 imitationNot 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.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it