Yaju Liu

Yaju Liu


Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 January 2025 in Atmosphere
Verified
Journal Article
Open access
PDF file
CYCui Yuan
Cui Yuan
YLYaju Liu
Yaju Liu
Jingzhao LuJingzhao Lu
Jingzhao Lu
CGChengyi Guo
Chengyi Guo
TQTingting Quan
Tingting Quan
Wei SuWei Su
Wei Su
Urbanization has greatly altered Earth’s surface form, and land use changes can lead to significant changes in carbon emissions. However, how these changes affect ecosystems remains unclear. Therefore, this study calculated the carbon absorption and emissions in 31 Chinese provinces using high-resolution (300 m) land use data. Subsequently, a carbon flow model was used to evaluate the carbon transfer that occurred from the changes in land use in every province between 2000 and 2020. The standard deviation ellipse analytic techniques were also employed to research the spatiotemporal evolution features of carbon flow in various economic zones. Furthermore, the flux and utility analysis approaches in ecological network analysis were used to quantitatively examine the interaction relationship between two carbon metabolism land uses. The results revealed that the continuous expansion of China’s construction land has reduced the area of agricultural land, resulting in industrial land (53.14%) and urban land (39.38%) being the main contributors to the total carbon emissions. Among them, the five eastern provinces of Hebei, Jiangsu, Zhejiang, Shandong, and Guangdong had carbon emissions of more than 100 million tons. From 2000 to 2020, the center of gravity of the carbon flow in construction land had shifted significantly from Henan Province to Gansu Province. The ecological relationship of exploitation and control dominated the two land use types. It is mostly found in Xinjiang, Qinghai, Gansu, Inner Mongolia, and Ningxia provinces. The findings could provide relevant policy implications for the Chinese government to mitigate carbon metabolism on land.

20 February 2024 in Intelligent Decision Technologies
Verified
Journal Article
Closed access
PDF file
YWYachao Wang
Yachao Wang
YLYaju Liu
Yaju Liu
DWDongxuan Wang
Dongxuan Wang
YLYaju Liu
Yaju Liu
As deep learning continues to advance, object detection technology holds potential and promising prospects in the recognition of cylindrical objects’ quantity, such as in industries like timber processing, construction, and pipeline engineering. The traditional manual counting methods have lower efficiency, a higher error rate, and demand a greater amount of manpower. The introduction of object detection technology can effectively address these issues, enhance work efficiency, and reduce labor costs. Therefore, this research paper introduces a novel variant of the YOLOv5s algorithm, called YOLOv5-COC, specifically designed to tackle the task of counting cylindrical objects. This paper makes the following significant contributions: Firstly, introducing the utilization of data augmentation techniques to augment the dataset, thereby enhancing the generalization ability of the model. Secondly, the K-means+⁣+ algorithm is employed as an alternative to the conventional K-means algorithm in order to enhance the initialization of anchor boxes. Thirdly, introduce distinct methodologies, including the incorporation of a coordinated attention mechanism, the amalgamation of the Bidirectional Feature Pyramid Network (BiFPN), and the substitution of the loss function, in order to further refine the model and enhance its recognition precision. Finally, employ ablation experiments to assess the optimization outcomes of the aforementioned methodologies. The experimental results reveal that the YOLOv5-COC model proposed in this study attains an mAP of 98.7%, operates at a frame rate of 60 FPS, attains a Precision of 98.3%, and boasts a Recall of 99.1%. The mAP@0.5:0.95 stands at 72.4%. In comparison to the original YOLOv5s model, the mAP value exhibits an improvement of 1.3%, the FPS experiences a remarkable surge of 27.7%, detection accuracy elevates by 1%, the recall rate advances by 1%, and the mAP@0.5:0.95 escalates by 3.5%. In summary, the YOLOv5-COC model demonstrates a sufficiently high level of accuracy in object detection tasks, mitigating instances of both false negatives and false positives. It efficiently accomplishes the task of object detection.