AD or Non-AD: A Deep Learning Approach to Detect Advertisements from Magazines

Massive open online courses (MOOCs), which have been deemed a revolutionary teaching mode, are increasingly being used in higher education. However, there remain deficiencies in understanding the relationship between online behavior of students and their performance, and in verifying how well a student comprehends learning material. Therefore, we propose a method for predicting student performance and mastery of knowledge points in MOOCs based on assignment-related online behavior; this allows for those providing academic support to intervene and improve learning outcomes of students facing difficulties. The proposed method was developed while using data from 1528 participants in a C Programming course, from which we extracted assignment-related features. We first applied a multi-task multi-layer long short-term memory-based student performance predicting method with cross-entropy as the loss function to predict students’ overall performance and mastery of each knowledge point. Our method incorporates the attention mechanism, which might better reflect students’ learning behavior and performance. Our method achieves an accuracy of 92.52% for predicting students’ performance and a recall rate of 94.68%. Students’ actions, such as submission times and plagiarism, were related to their performance in the MOOC, and the results demonstrate that our method predicts the overall performance and knowledge points that students cannot master well.

Section: Loss Functionmentioning

confidence: 99%

Predicting Student Performance and Deficiency in Mastering Knowledge Points in MOOCs Using Multi-Task Learning

Xu-ri

et al. 2019

“…In recent years, deep learning has shown great improvement in pattern recognition and other application fields [ 27 , 28 , 29 , 30 ]. In this section, we introduce the related techniques on the application of deep learning in the field of RS.…”

Section: Related Workmentioning

confidence: 99%

Joint Deep Model with Multi-Level Attention and Hybrid-Prediction for Recommendation

Lin

Tang

Zhang

2019

The Recommender System (RS) has obtained a pivotal role in e-commerce. To improve the performance of RS, review text information has been extensively utilized. However, it is still a challenge for RS to extract the most informative feature from a tremendous amount of reviews. Another significant issue is the modeling of user–item interaction, which is rarely considered to capture high- and low-order interactions simultaneously. In this paper, we design a multi-level attention mechanism to learn the usefulness of reviews and the significance of words by Deep Neural Networks (DNN). In addition, we develop a hybrid prediction structure that integrates Factorization Machine (FM) and DNN to model low-order user–item interactions as in FM and capture the high-order interactions as in DNN. Based on these two designs, we build a Multi-level Attentional and Hybrid-prediction-based Recommender (MAHR) model for recommendation. Extensive experiments on Amazon and Yelp datasets showed that our approach provides more accurate recommendations than the state-of-the-art recommendation approaches. Furthermore, the verification experiments and explainability study, including the visualization of attention modules and the review-usefulness prediction test, also validated the reasonability of our multi-level attention mechanism and hybrid prediction.

“…Previously a machine learning technique was proposed using a random forest (RF) classifier based on hand-crafted features [ 34 ]. Alternatively, deep neural networks (DNN) have shown superior performance in classification problems with large datasets in many fields [ 35 , 36 , 37 , 38 ]. DNN solutions have no need of feature engineering as the signals are directly fed to the network which does the exploratory data analysis.…”

Section: Introductionmentioning

confidence: 99%

Deep Neural Networks for ECG-Based Pulse Detection during Out-of-Hospital Cardiac Arrest

Elola

Aramendi

Irusta

et al. 2019

The automatic detection of pulse during out-of-hospital cardiac arrest (OHCA) is necessary for the early recognition of the arrest and the detection of return of spontaneous circulation (end of the arrest). The only signal available in every single defibrillator and valid for the detection of pulse is the electrocardiogram (ECG). In this study we propose two deep neural network (DNN) architectures to detect pulse using short ECG segments (5 s), i.e., to classify the rhythm into pulseless electrical activity (PEA) or pulse-generating rhythm (PR). A total of 3914 5-s ECG segments, 2372 PR and 1542 PEA, were extracted from 279 OHCA episodes. Data were partitioned patient-wise into training (80%) and test (20%) sets. The first DNN architecture was a fully convolutional neural network, and the second architecture added a recurrent layer to learn temporal dependencies. Both DNN architectures were tuned using Bayesian optimization, and the results for the test set were compared to state-of-the art PR/PEA discrimination algorithms based on machine learning and hand crafted features. The PR/PEA classifiers were evaluated in terms of sensitivity (Se) for PR, specificity (Sp) for PEA, and the balanced accuracy (BAC), the average of Se and Sp. The Se/Sp/BAC of the DNN architectures were 94.1%/92.9%/93.5% for the first one, and 95.5%/91.6%/93.5% for the second one. Both architectures improved the performance of state of the art methods by more than 1.5 points in BAC.