Ablation study visualization results. by Xiaozhou Feng (2918222)

“…Compared to the original YOLOv8 model, the improved algorithm shows increases of 2.2% in precision, 0.6% in recall, and 2.0% in mAP@0.5, with a detection speed improvement of 65.48 FPS. …”

Experimental parameter configuration. by Xiaozhou Feng (2918222)

“…Compared to the original YOLOv8 model, the improved algorithm shows increases of 2.2% in precision, 0.6% in recall, and 2.0% in mAP@0.5, with a detection speed improvement of 65.48 FPS. …”

FLMP-YOLOv8 identification results. by Xiaozhou Feng (2918222)

“…Compared to the original YOLOv8 model, the improved algorithm shows increases of 2.2% in precision, 0.6% in recall, and 2.0% in mAP@0.5, with a detection speed improvement of 65.48 FPS. …”

C2f structure. by Xiaozhou Feng (2918222)

“…Compared to the original YOLOv8 model, the improved algorithm shows increases of 2.2% in precision, 0.6% in recall, and 2.0% in mAP@0.5, with a detection speed improvement of 65.48 FPS. …”

Experimental environment configuration. by Xiaozhou Feng (2918222)

“…Compared to the original YOLOv8 model, the improved algorithm shows increases of 2.2% in precision, 0.6% in recall, and 2.0% in mAP@0.5, with a detection speed improvement of 65.48 FPS. …”

Ablation experiment results table. by Xiaozhou Feng (2918222)

“…Compared to the original YOLOv8 model, the improved algorithm shows increases of 2.2% in precision, 0.6% in recall, and 2.0% in mAP@0.5, with a detection speed improvement of 65.48 FPS. …”

YOLOv8 identification results. by Xiaozhou Feng (2918222)

“…Compared to the original YOLOv8 model, the improved algorithm shows increases of 2.2% in precision, 0.6% in recall, and 2.0% in mAP@0.5, with a detection speed improvement of 65.48 FPS. …”

LSKA module structure diagram. by Xiaozhou Feng (2918222)

“…Compared to the original YOLOv8 model, the improved algorithm shows increases of 2.2% in precision, 0.6% in recall, and 2.0% in mAP@0.5, with a detection speed improvement of 65.48 FPS. …”

Comparison of mAP curves in ablation experiments. by Xiaozhou Feng (2918222)

“…Compared to the original YOLOv8 model, the improved algorithm shows increases of 2.2% in precision, 0.6% in recall, and 2.0% in mAP@0.5, with a detection speed improvement of 65.48 FPS. …”

FarsterBlock structure. by Xiaozhou Feng (2918222)

“…Compared to the original YOLOv8 model, the improved algorithm shows increases of 2.2% in precision, 0.6% in recall, and 2.0% in mAP@0.5, with a detection speed improvement of 65.48 FPS. …”

Sample augmentation and annotation illustration. by Xiaozhou Feng (2918222)

“…Compared to the original YOLOv8 model, the improved algorithm shows increases of 2.2% in precision, 0.6% in recall, and 2.0% in mAP@0.5, with a detection speed improvement of 65.48 FPS. …”

YOLOv8 model architecture diagram. by Xiaozhou Feng (2918222)

“…Compared to the original YOLOv8 model, the improved algorithm shows increases of 2.2% in precision, 0.6% in recall, and 2.0% in mAP@0.5, with a detection speed improvement of 65.48 FPS. …”

FLMP-YOLOv8 architecture diagram. by Xiaozhou Feng (2918222)

“…Compared to the original YOLOv8 model, the improved algorithm shows increases of 2.2% in precision, 0.6% in recall, and 2.0% in mAP@0.5, with a detection speed improvement of 65.48 FPS. …”

Uniform Manifold Approximation and Projection (UMAP)-based sorting enhances detection of low-firing rate neurons and boosts mutual information. by Daniel Suárez-Barrera (22676654)

Description of data sources. by Gowtham A. Rao (8261928)

“…<div><p>Objective</p><p>This paper introduces a novel framework for evaluating phenotype algorithms (PAs) using the open-source tool, Cohort Diagnostics.…”

Comparison of Uniform Manifold Approximation and Projection (UMAP)-based and feature-based spike sorting on synthetic data. by Daniel Suárez-Barrera (22676654)

Data and codes for the paper "Machine-Learning-Enabled Spatial Pattern Mining: Evaluating the Impact of Imperfect Inputs". by Zhili Li (18836803)

High-Throughput Mass Spectral Library Searching of Small Molecules in R with NIST MSPepSearch by Andrey Samokhin (20282728)

“…Despite the availability of numerous library search algorithms, those developed by NIST and implemented in MS Search remain predominant, partly because commercial databases (e.g., NIST, Wiley) are distributed in proprietary formats inaccessible to custom code. …”

SpeLL: An Agent for Natural Language-Driven Intelligent Spectral Modeling by Jiashun Fu (20888176)

“…The core strength of SpeLL lies in its dual RAG pathways. The Code RAG provides specialized code knowledge for spectral data analysis, enabling the LLM to generate robust and domain-specific analytical scripts that address the implementation and optimization of algorithms. …”

Various metrics of the training model. by Lai Yingdong (22403854)

“…The proposed YOLOv8 model achieved a mean Average Precision (mAP@50) of 0.953, mAP@50–95 of 0.678, precision of 0.91, and recall of 0.88. …”