General Chemically Intuitive Atom- and Bond-Level DFT Descriptors for Machine Learning Approaches to Reaction Condition Prediction by Miguel Nouman (21557202)

“…We show that by combining structural and general DFT descriptors, models with up to 71% fewer trainable parameter than their purely structural counterparts can provide comparable or superior weighted precision, top-1 and top-3 accuracies. Moreover, we report improvements of up to 5, 10, and 11% in weighted precision, top-1 accuracy and <i>F</i>₁ score, respectively, for neural networks trained on hybrid representations which combine general DFT and structural descriptors, when compared to structural models with equivalent architectures and input sizes. …”

General Chemically Intuitive Atom- and Bond-Level DFT Descriptors for Machine Learning Approaches to Reaction Condition Prediction by Miguel Nouman (21557202)

“…We show that by combining structural and general DFT descriptors, models with up to 71% fewer trainable parameter than their purely structural counterparts can provide comparable or superior weighted precision, top-1 and top-3 accuracies. Moreover, we report improvements of up to 5, 10, and 11% in weighted precision, top-1 accuracy and <i>F</i>₁ score, respectively, for neural networks trained on hybrid representations which combine general DFT and structural descriptors, when compared to structural models with equivalent architectures and input sizes. …”

Example of dataset labeling. by Jinxue Sui (19748080)

“…Compared with YOLOv5, it improves 4%, 1.9%, 1.7% and 3%, respectively, which fully proves the advanced and practical nature of the proposed algorithm.…”

Self-built datasets. by Jinxue Sui (19748080)

“…Compared with YOLOv5, it improves 4%, 1.9%, 1.7% and 3%, respectively, which fully proves the advanced and practical nature of the proposed algorithm.…”

CSPBottleneck with 2 conversions (C2f) module. by Jinxue Sui (19748080)

“…Compared with YOLOv5, it improves 4%, 1.9%, 1.7% and 3%, respectively, which fully proves the advanced and practical nature of the proposed algorithm.…”

YOLOv8 network structure. by Jinxue Sui (19748080)

“…Compared with YOLOv5, it improves 4%, 1.9%, 1.7% and 3%, respectively, which fully proves the advanced and practical nature of the proposed algorithm.…”

Decoupling head structure. by Jinxue Sui (19748080)

“…Compared with YOLOv5, it improves 4%, 1.9%, 1.7% and 3%, respectively, which fully proves the advanced and practical nature of the proposed algorithm.…”

RE-YOLO network structure. by Jinxue Sui (19748080)

“…Compared with YOLOv5, it improves 4%, 1.9%, 1.7% and 3%, respectively, which fully proves the advanced and practical nature of the proposed algorithm.…”

EMA module structure. by Jinxue Sui (19748080)

“…Compared with YOLOv5, it improves 4%, 1.9%, 1.7% and 3%, respectively, which fully proves the advanced and practical nature of the proposed algorithm.…”

EMA_C2f network structure. by Jinxue Sui (19748080)

“…Compared with YOLOv5, it improves 4%, 1.9%, 1.7% and 3%, respectively, which fully proves the advanced and practical nature of the proposed algorithm.…”

Detailed structure of RFAConv. by Jinxue Sui (19748080)

“…Compared with YOLOv5, it improves 4%, 1.9%, 1.7% and 3%, respectively, which fully proves the advanced and practical nature of the proposed algorithm.…”

Table 2_SRC is a potential target of Arctigenin in treating triple-negative breast cancer: based on machine learning algorithms, molecular modeling and in Vitro test.xlsx by Yuezhou Huang (9998177)

“…Western blotting indicated that AG significantly reduced the levels of Bcl-2, caspase-3, and caspase-9, as well as decreased SRC, p-PI3K-p85, p-AKT1, p-MEK1/2, and p-ERK1/2 expression in TNBC cells in a concentration dependent manner.…”

Table 3_SRC is a potential target of Arctigenin in treating triple-negative breast cancer: based on machine learning algorithms, molecular modeling and in Vitro test.docx by Yuezhou Huang (9998177)

“…Western blotting indicated that AG significantly reduced the levels of Bcl-2, caspase-3, and caspase-9, as well as decreased SRC, p-PI3K-p85, p-AKT1, p-MEK1/2, and p-ERK1/2 expression in TNBC cells in a concentration dependent manner.…”

Prediction of Activity and Selectivity Profiles of Sigma Receptor Ligands Using Machine Learning Approaches by Lisa Lombardo (7301969)

Subjects: “…distinct physiological functions…”

Data Sheet 1_A three-classification model for identifying migraine with right-to-left shunt using lateralization of functional connectivity and brain network topology: a resting-st... by Weifang Nie (20173242)

Load frequency control performance enhancement of an electric vehicle integrated time-delay multi-microgrid system by Bhuvnesh Khokhar (19665602)

“…A cyclical parthenogenesis algorithm-optimized 2DOF-FOPID controller is implemented to obtain dynamic responses of the M<i>μ</i>G system. …”

Data Sheet 1_Accurate informatic modeling of tooth enamel pellicle interactions by training substitution matrices with Mat4Pep.doc by Jeremy Horst Keeper (20458274)

Experiment 4: Accuracy of modularity-based consensus clustering methods on ring-of-cliques networks of varying sizes. by Yasamin Tabatabaee (18095491)

Supplemental files to the study "Limitations of Current Machine-Learning Models in Predicting Enzymatic Functions for Uncharacterized Proteins" by Valerie de Crecy-Lagard (12823436)

“…An open question is the ability of machine-learning approaches to predict enzymatic functions unseen in the training sets. Using a set of <i>E. coli</i> unknowns, we evaluated the current state-of-the-art machine-learning approaches and found that these methods currently lack the ability to integrate scientific reasoning into their prediction algorithms. …”

Experiment 4: Evaluating CPM-based clustering methods on ring-of-cliques networks. by Yasamin Tabatabaee (18095491)