• Journal of Information Processing Systems
• /
• 제13권5호
• /
• pp.1052-1070
• /
• 2017

For the autoencoder (AE) implemented as a construction component, this paper uses the method of greedy layer-by-layer pre-training without supervision to construct the stacked autoencoder (SAE) to extract the abstract features of the original input data, which is regarded as the input of the logistic regression (LR) model, after which the click-through rate (CTR) of the user to the advertisement under the contextual environment can be obtained. These experiments show that, compared with the usual logistic regression model and support vector regression model used in the field of predicting the advertising CTR in the industry, the SAE-LR model has a relatively large promotion in the AUC value. Based on the improvement of accuracy of advertising CTR prediction, the enterprises can accurately understand and have cognition for the needs of their customers, which promotes the multi-path development with high efficiency and low cost under the condition of internet finance.

• 한국운동역학회지
• /
• 제33권3호
• /
• pp.94-100
• /
• 2023

Objective: Few studies have investigated alterations of ground reaction force (GRF) in individuals with chronic ankle instability (CAI) compared with lateral ankle sprain (LAS) copers and healthy controls during walking. This study aimed to investigate differences in GRF variables among the CAI, LAS coper, and control groups. Method: Eighteen individuals with CAI, 18 LAS copers, and 18 healthy controls were recruited for this study. All participants walked on 8-m walkway with a force plate three times. GRF data during stance phase were extracted and analyzed. The analysis of variance and ensemble curve analysis were used for statistical analyses of discrete points and time-series data respectively. Results: The CAI group showed a greater loading rate (LR) and a shorter time to impact peak force than the other groups, as well as decreased vGRF from 56% to 65% in the stance phase than the control group. No significant differences were noted in the other variables. Conclusion: Based on these findings, individuals with CAI should enhance their ability to create propulsion during the push-off phase and spend more time absorbing GRF to decrease the LR, which is considered one of risk factors for overuse injury and ankle osteoarthritis.

• 디지털콘텐츠학회 논문지
• /
• 제1권1호
• /
• pp.1-11
• /
• 2000

최근 인터넷상에서는 원격교육이나 온라인 교육에서 다양한 교육용 디지털 컨텐츠가 제공되고 있다. 특히 에듀테인먼트분야가 활성화되면서 흥미위주의 교육 컨텐츠가 많이 개발되고 있다. 하지만 컨텐츠가 적정기간($1{\sim}2$년) 동안 학습자가 흥미를 잃지 않고 스스로 학습하도록 유도하는가 라는 질적인 면에서 고려해 볼 때 부족한 면이 많다. 그러므로 학습자로부터 자발적이면서 적극적인 학습을 촉진시키기 위해서 학습자의 학습동기를 강화시키는 시스템이 필요하다. 본 논문은 후견인과 학습자가 제시한 목표의 성취도에 따라 보상을 제공하는 학습보상시스템 (LRS)을 설계 및 구현한다. LRS는 기존의 에듀테인먼트 컨텐츠를 활용하여 동시에 흥미와 보상을 함께 제공함으로써 교육효과증진을 목적으로 한다.