Bibliographic record
Abstract
Over the past few years, we have been involved in several projects related to vehicular in-cabin sensing.These projects resulted in numerous products that are available today in the automotive market.This talk will describe some of these projects, key lessons learned, and select challenges that remain to be resolved.Specifically, we discuss the architecture of various sensor systems that employ radar chipsets for detecting the presence of passengers, counting the number of occupied seats, differentiating between adults and children, monitoring the driver behavior, monitoring the vital signs of all vehicle occupants, alongside with detecting gestures for infotainment system control.In select applications, we showcase that radar signal processing suffices in achieving satisfactory performance.However, in a number of particular cases, we demonstrate the need for pairing machine learning and artificial intelligence with radar sensing to achieve the desired capabilities.For example, we discuss the performance of a Multiple Input Multiple Output Frequency Modulated Continuous Wave (MIMO FMCW) radar operating at millimeter-wave frequencies when placed by the rear-view mirror of a 7-passenger van.We outline the encountered challenges due to the low angular resolution of the radar, which limited the visual perception of the occupant's location.We then describe how machine learning algorithms, such as Support Vector Machine (SVM), Random Forest (RF), and K-Nearest Neighbors (KNN) enhanced the accuracy of the detection system.The talk will feature multiple video demos covering the aforementioned use-cases.We conclude the talk with a discussion on the co-existence of multiple in-cabin radar sensors, and select approaches to enable seamless operation.
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.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.004 | 0.001 |
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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".