Improved YOLOv7-Based Algorithm for Detecting Foreign Objects on the Roof of a Subway Vehicle.

Subway vehicle roofs must be inspected when entering and exiting the depot to ensure safe subway vehicle operations. This paper presents an improved method for detecting foreign objects on subway vehicle roofs based on the YOLOv7 algorithm. First, we capture images of foreign objects using a line-scan camera at the depot entrance and exit, creating a dataset of foreign roof objects. Subsequently, we address the shortcomings of the YOLOv7 algorithm by introducing the Ghost module, an improved weighted bidirectional feature pyramid network (WBiFPN), and the Wise intersection over union (WIoU) bounding-box regression loss function. These enhancements are incorporated to build the subway vehicle roof foreign object detection model based on the improved YOLOv7, which we refer to as YOLOv7-GBW. The experimental results demonstrate the practicality and usability of the proposed method. The analysis of the experimental results indicates that the YOLOv7-GBW algorithm achieves a detection accuracy of 90.29% at a speed of 54.3 frames per second (fps) with a parameter count of 15.51 million. The improved YOLOv7 model outperforms mainstream detection algorithms in terms of detection accuracy, speed, and parameter count. This finding confirms that the proposed method meets the requirements for detecting foreign objects on subway vehicle roofs.

The interactions of algae-bacteria symbiotic system and its effects on nutrients removal from synthetic wastewater.

The ability of Chlorella vulgaris-Bacillus licheniformis and Microcystis aeruginosa-Bacillus licheniformis consortiums to eliminate total dissolved nitrogen (TDN), total dissolved phosphorus (TDP), and soluble chemical oxygen demand (sCOD) from synthetic wastewater was studied. The highest values of dry cell weight, chlorophyll-a, and chlorophyll metabolism related genes/bacterial rRNA gene copies were obtained in the Chlorella vulgaris-Bacillus licheniformis system at Chlorella vulgaris and Bacillus licheniformis ratio of 1:3. On the 10th day, the Chlorella vulgaris-Bacillus licheniformis system at this ratio removed 86.55%, 80.28% and 88.95% of sCOD, TDP and TDN, respectively. But, the Microcystis aeruginosa-Bacillus licheniformis system at this ratio only removed 65.62%, 70.82%, and 21.56% of sCOD, TDP and TDN, respectively. Chlorella vulgaris and Bacillus licheniformis could coexist as an algae-bacteria consortia and quorum sensing substances (autoinducing peptides and bis (3'-5') diguanylic acid) concentrations were measured. Finally, the interactions and communication patterns between Chlorella vulgaris and Bacillus licheniformis were depicted.