Auto-Tagging for Massive Online Selection Tests: Machine Learning to the Rescue

Krithivasan, Saraswathi; Gupta, Shelly; Shandilya, S.; Arya, Kavi; Lala, K.

doi:10.1109/t4e.2016.050

Cited by 3 publications

(1 citation statement)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Artificial Intelligence (AI) enables computers to mimic the problem-solving process of human brain, freeing humans from the heavy calculation burden in science and engineering. Currently, the AI is being applied in various scenarios, including smart home appliances, virtual reality retailing, smart transport, smart medical service, and smart logistics [8][9][10][11][12]. Klette and Blikstad-Balas [13] pointed out that, compared with other intelligent products and services, intelligent robots like the Pepper humanoid robot and the Xiaomi floor mopping robot have a broad development prospect.…”

Section: Introductionmentioning

confidence: 99%

Analysis on Class Participation Based on Artificial Intelligence

Liu¹

2020

RIA

View full text Add to dashboard Cite

Artificial Intelligence (AI) frees humans from the heavy calculation burden in science and engineering. The AI can analyze the mass data on classroom behavior and the backend data of intelligent teaching platforms, and extract the useful features of student behaviors in class. Based on feature fusion, this paper develops a novel method to analyze class participation, which correlates class participation with classroom behaviors. Firstly, the basic data for the class participation analysis were processed, including the participation records of online classroom teaching and the data of classroom video, and the relevant calculation formulas were constructed. After that, the features of classroom behaviors were processed, and a training network for classroom behaviors was created. Next, the correlations between classroom behaviors and class participation were analyzed, and the similarity of facial features were evaluated, followed by the fusion of classroom behavior features. Experimental results show that our method can effectively and accurately evaluate class participation.

show abstract