AC-LayeringNetV2 architecture module. by Wenhao Ren (2561731)

“…Additionally, the model achieves a 6.55% reduction in size and a 0.03% decrease in computational complexity. These results highlight the practical applicability and efficiency of the proposed approach for automatic crack detection in building structures, emphasizing the novel integration of feature fusion and attention mechanisms to address challenges in real-time and high-accuracy detection of micro-cracks in complex environments.…”

Cracks included in the dataset. by Wenhao Ren (2561731)

“…Additionally, the model achieves a 6.55% reduction in size and a 0.03% decrease in computational complexity. These results highlight the practical applicability and efficiency of the proposed approach for automatic crack detection in building structures, emphasizing the novel integration of feature fusion and attention mechanisms to address challenges in real-time and high-accuracy detection of micro-cracks in complex environments.…”

Loss function comparison plot. by Wenhao Ren (2561731)

“…Additionally, the model achieves a 6.55% reduction in size and a 0.03% decrease in computational complexity. These results highlight the practical applicability and efficiency of the proposed approach for automatic crack detection in building structures, emphasizing the novel integration of feature fusion and attention mechanisms to address challenges in real-time and high-accuracy detection of micro-cracks in complex environments.…”

Edge device performance benchmarking. by Wenhao Ren (2561731)

“…Additionally, the model achieves a 6.55% reduction in size and a 0.03% decrease in computational complexity. These results highlight the practical applicability and efficiency of the proposed approach for automatic crack detection in building structures, emphasizing the novel integration of feature fusion and attention mechanisms to address challenges in real-time and high-accuracy detection of micro-cracks in complex environments.…”

Typical error cases. by Wenhao Ren (2561731)

“…Additionally, the model achieves a 6.55% reduction in size and a 0.03% decrease in computational complexity. These results highlight the practical applicability and efficiency of the proposed approach for automatic crack detection in building structures, emphasizing the novel integration of feature fusion and attention mechanisms to address challenges in real-time and high-accuracy detection of micro-cracks in complex environments.…”

Computational efficiency comparison. by Wenhao Ren (2561731)

“…Additionally, the model achieves a 6.55% reduction in size and a 0.03% decrease in computational complexity. These results highlight the practical applicability and efficiency of the proposed approach for automatic crack detection in building structures, emphasizing the novel integration of feature fusion and attention mechanisms to address challenges in real-time and high-accuracy detection of micro-cracks in complex environments.…”

Backbone comparison in crack detection. by Wenhao Ren (2561731)

“…Additionally, the model achieves a 6.55% reduction in size and a 0.03% decrease in computational complexity. These results highlight the practical applicability and efficiency of the proposed approach for automatic crack detection in building structures, emphasizing the novel integration of feature fusion and attention mechanisms to address challenges in real-time and high-accuracy detection of micro-cracks in complex environments.…”

Statistical analysis table for ablation tests. by Wenhao Ren (2561731)

“…Additionally, the model achieves a 6.55% reduction in size and a 0.03% decrease in computational complexity. These results highlight the practical applicability and efficiency of the proposed approach for automatic crack detection in building structures, emphasizing the novel integration of feature fusion and attention mechanisms to address challenges in real-time and high-accuracy detection of micro-cracks in complex environments.…”

Summary of false positives and false negatives. by Wenhao Ren (2561731)

“…Additionally, the model achieves a 6.55% reduction in size and a 0.03% decrease in computational complexity. These results highlight the practical applicability and efficiency of the proposed approach for automatic crack detection in building structures, emphasizing the novel integration of feature fusion and attention mechanisms to address challenges in real-time and high-accuracy detection of micro-cracks in complex environments.…”

PR parameter comparison chart. by Wenhao Ren (2561731)

“…Additionally, the model achieves a 6.55% reduction in size and a 0.03% decrease in computational complexity. These results highlight the practical applicability and efficiency of the proposed approach for automatic crack detection in building structures, emphasizing the novel integration of feature fusion and attention mechanisms to address challenges in real-time and high-accuracy detection of micro-cracks in complex environments.…”

RAK-Conv. by Wenhao Ren (2561731)

“…Additionally, the model achieves a 6.55% reduction in size and a 0.03% decrease in computational complexity. These results highlight the practical applicability and efficiency of the proposed approach for automatic crack detection in building structures, emphasizing the novel integration of feature fusion and attention mechanisms to address challenges in real-time and high-accuracy detection of micro-cracks in complex environments.…”

Structure of YOLOv8n. by Wenhao Ren (2561731)

“…Additionally, the model achieves a 6.55% reduction in size and a 0.03% decrease in computational complexity. These results highlight the practical applicability and efficiency of the proposed approach for automatic crack detection in building structures, emphasizing the novel integration of feature fusion and attention mechanisms to address challenges in real-time and high-accuracy detection of micro-cracks in complex environments.…”

Underlying data for the main figures. by Tamjid A. Chowdhury (14149846)

“…Loss of RBM-26 function causes a dramatic overexpression of <i>mals-1</i> mRNA and MALS-1 protein. …”

Underlying data for the supplemental figures. by Tamjid A. Chowdhury (14149846)

“…Loss of RBM-26 function causes a dramatic overexpression of <i>mals-1</i> mRNA and MALS-1 protein. …”

Determination of Light and Condensate Oil Categories in a Complex Petroleum System by Fluorescence Parameters: A Case Study on the Northern Tazhong Uplift, Tarim Basin, China by Peng Cheng (153428)

“…For the TZ-I, TZ-II, and TZ-III oils, τ_oil progressively increases, and the fluorescence spectra gradually shift blue with decreases in Q_510/430, Q_650/500, and λ_max, which results from the successive decreases in gas invasion extent for the three types of Tazhong oils. …”

Room-Temperature Self-Healable Glassy Semicrystalline Polymers via Ionic Aggregations by Pengxiang Si (5676260)

“…Semicrystalline polymers constitute the largest fraction of industrial and engineering plastics but are difficult to automatically self-heal in their glassy state due to the frozen molecular chains. …”

Room-Temperature Self-Healable Glassy Semicrystalline Polymers via Ionic Aggregations by Pengxiang Si (5676260)

“…Semicrystalline polymers constitute the largest fraction of industrial and engineering plastics but are difficult to automatically self-heal in their glassy state due to the frozen molecular chains. …”

Room-Temperature Self-Healable Glassy Semicrystalline Polymers via Ionic Aggregations by Pengxiang Si (5676260)

“…Semicrystalline polymers constitute the largest fraction of industrial and engineering plastics but are difficult to automatically self-heal in their glassy state due to the frozen molecular chains. …”

Room-Temperature Self-Healable Glassy Semicrystalline Polymers via Ionic Aggregations by Pengxiang Si (5676260)

“…Semicrystalline polymers constitute the largest fraction of industrial and engineering plastics but are difficult to automatically self-heal in their glassy state due to the frozen molecular chains. …”

R project including metadata update. by Frederik Stein (22146203)

“…Without such amendments, the accumulation of contradictory species assignments within BINs will continue to rise and the reliability of specimen identification by BOLD will decrease.</p></div>…”