A Deep-Learning Classification Framework for Reducing Communication Errors in Dynamic Hand Signaling for Crane Operation
Bibliographic record
Abstract
Crane operators and signalmen play an integral role in the safe and efficient operation of cranes on a construction site. Operating a crane is a complex and demanding task that requires careful coordination between operator and signalmen in order to avoid errors that could have dire consequences, including serious injury or loss of life. Therefore, special considerations should be taken to mitigate communication errors that could occur between the two parties. Technology can play an important role in enhancing communication, and, with recent advancements in technology, human–computer interaction has emerged as an active area of research within the field of computer vision. This paper presents a framework that integrates the YOLOv4 model (for object detection) and the long short-term memory (LSTM) model (a recurrent neural network) for dynamic hand signal classification in real time. The first step is the creation of a crane signalman dynamic hand signal data set with 18 classes. The YOLOv4 model is then customized for this application by modifying the activation function. Three modified YOLOv4 models are then integrated with the LSTM model. The modified YOLOv4 integrated with LSTM is found to achieve a maximum overall accuracy of 94.8% with an inference time of 55.1 frames per second. The model is further validated with real-time dynamic hand signal classification, achieving an accuracy of 93.5% and an inference time of 44 frames per second. The proposed models show improved quality in classification accuracy as well as in processing speed in comparison to some of the most widely used models currently in use. The proposed novel framework can be used as another layer of communication to supplement current practice and reduce communication errors between crane signalmen and crane operators.
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 | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| 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 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".