AOW-YOLO: Experimental Hardware and Software Configuration for Smoking Detection

AOW-YOLO is a novel model achieving a roughly 31.6% faster inference speed than YOLO11n for detecting smoking behavior on construction sites. The dataset, shared by Ruishi Liang on figshare in May 2026, contains the experimental hardware and software configuration details for this model. It is a small 5.5 KB file in XLS format.

Use Cases

• Benchmarking lightweight detection models based on the reported mAP50 and mAP50:95 metrics
• Replicating the AOW-YOLO model's performance based on the described hardware and software setup
• Analyzing the impact of the novel AOWIoU loss function on model training for small object detection
• Investigating the efficiency of the Spatial Grouped-Pointwise (SGP) convolution module for feature integration

Strengths

• Model performance metrics (mAP50, mAP50:95) and a 31.6% speed improvement over YOLO11n are explicitly reported
• Dataset is openly licensed under CC-BY-4.0, facilitating reuse and sharing
• The description provides a detailed technical explanation of the novel AOWIoU loss and SGP convolution module

Limitations

• Row count is unknown, which may limit suitability assessment
• Column-level documentation is absent; field semantics must be inferred after download
• The 5.5 KB size suggests the dataset contains configuration details, not the primary training or evaluation data

Provenance

Source

Ruishi Liang

Collection Method

Likely contains experimental configuration parameters for the AOW-YOLO model.

Time Range

null

Freshness

Last updated 2026-05-06 17:45:41; freshness should be verified

Geography

null