Generalized q-rung orthopair fuzzy interactive Hamacher power average and Heronian means for MADM

Li, Jinjun; Chen, Minghao; Pei, Shibing

doi:10.1007/s10462-022-10376-1

Cited by 10 publications

(2 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The 914 dimensional node feature vector is encoded to a 16 dimensional one by a embedding layer

θ_{italicemb}

, and then it is updated four times to take into account the features of distant atoms. The model is not exactly deep by today's standards, but it was found to be almost optimal, as in previous study 20 . This model has about 25,000 (25 k) learnable parameters (Table 2).…”

Section: Methodssupporting

confidence: 56%

Learning organo‐transition metal catalyzed reactions by graph neural networks

Sakai,

Kaneshige,

Yasuda

2023

J Comput Chem

View full text Add to dashboard Cite

Chemical reaction outcome prediction presents a fundamental challenge in synthetic chemistry. Most existing machine learning (ML) approaches focus on chemical reactions of typical elements. We developed a simple ML model focused on organo‐transition metal‐catalyzed reactions (OMCRs). Instead of overall reactions observed in experiments, we let the ML model learn the sequence of simplified elementary reactions. This drastically reduced the complexity of the model and helped it find common patterns from distinct reactions. We let a graph neural network learn the reactivity index of a pair of atoms. The model was able to learn a wide variety of OMCRs, and the accuracy of reaction prediction reached 97%, even though the model has extremely fewer learnable parameters than other standards. The learned reactivity indices of bonds nicely summarize the knowledge of reactions in the dataset.

show abstract

“…The 914 dimensional node feature vector is encoded to a 16 dimensional one by a embedding layer

θ_{italicemb}

Section: Methodssupporting

confidence: 56%

Learning organo‐transition metal catalyzed reactions by graph neural networks

Sakai,

Kaneshige,

Yasuda

2023

J Comput Chem

View full text Add to dashboard Cite

show abstract

“…The multiple attribute decision-making (MADM) method has found extensive applications in various domains, including production and daily life [15,42,43]. However, different fuzzy sets are employed in different environments.…”

Section: Introductionmentioning

confidence: 99%

A Warning Feedback Model Based on Online Learning Engagement Evaluation Under Interval-valued q-rung Orthopair Fuzzy

Wan,

Xie,

Pierre

2023

Preprint

View full text Add to dashboard Cite

When real-time detection indicates a low level of student engagement in online classrooms, selecting an appropriate time for feedback can enhance learner engagement. To address this issue, this study proposes an Interval-valued q-rung orthopair fuzzy warning feedback model based on the evaluation of online learning engagement. The designed warning feedback model utilizes a sliding window to capture the linguistic evaluation results of facial expressions, eye gaze, and limb states of online learners. By employing the developed IVq-ROFWDBM operator, as well as feature weight derivation and sample point weight derivation methods, the fuzzy comprehensive evaluation of sample points within the sliding window is conducted. When the evaluation result indicates low engagement, timely feedback is provided to the learners. The implementation of case studies demonstrates that the proposed warning feedback model can provide timely and effective feedback, avoiding the contradiction between excessive and untimely feedback. Comparative analysis results indicate that the proposed operator can obtain more accurate feedback outcomes.

show abstract