With the rapid development of online learning platforms, learners have more access to various kinds of courses. However, they may find it difficult to make choices due to the massive number of courses. The main contribution of our research is the design of a course recommendation framework which extracts multimodal course features based on deep learning models. In this framework, different kinds of information of course, such as course title, and course audio and course comments, are used to make proper recommendation in online learning platforms. Moreover, we utilize both explicit and implicit feedback to infer learner’s preference. Based on real‐world datasets, our empirical results show that the proposed framework performs well in course recommendation, achieving an AUC score of 79.03%. This framework can provide technical support for course video recommendation, thus helping online learning platforms to manage course resources and optimize user learning experience.

Reducing the vibration of marine power machinery can improve warships' capabilities of concealment and reconnaissance. Being one of the most effective means to reduce mechanical vibrations, the active vibration control technology can overcome the poor effect in low frequency of traditional passive vibration isolation. As the vibrations arising from operation of marine power machinery are actually the frequency-varying disturbances, the H 1 control method is adopted to suppress frequency-varying disturbances. The H 1 control method can solve the stability problems caused by the uncertainty of the model and reshape the frequency response function of the closed loop system. Two-input twooutput continuous transfer function models were identified by using the system identification method and are validated in frequency domain of which all values of best fit exceeds 89%. The method of selecting the weighting functions on the mixed sensitivity problem is studied. Besides, the H 1 controller is designed for a multiple input multiple output (MIMO) system to suppress the single-frequency-varying disturbance. The numerical simulation results show that the magnitudes of the error signals are reduced by more than 50%, and the amplitudes of the dominant frequencies are attenuated by more than 10 dB. Finally, the single excitation source dual-channel control experiments are conducted on the floating raft isolation system. The experiment results reveal that the root mean square values of the error signals under control have fallen by more 74% than that without control, and the amplitudes of the error signals in the dominant frequencies are attenuated above 13 dB. The experiment results and the numerical simulation results are basically in line, indicating a good vibration isolation effect.

Objective: This study aims to implement and investigate the application of a special intelligent diagnostic system based on deep learning in the diagnosis of pterygium using anterior segment photographs.Methods: A total of 1,220 anterior segment photographs of normal eyes and pterygium patients were collected for training (using 750 images) and testing (using 470 images) to develop an intelligent pterygium diagnostic model. The images were classified into three categories by the experts and the intelligent pterygium diagnosis system: (i) the normal group, (ii) the observation group of pterygium, and (iii) the operation group of pterygium. The intelligent diagnostic results were compared with those of the expert diagnosis. Indicators including accuracy, sensitivity, specificity, kappa value, the area under the receiver operating characteristic curve (AUC), as well as 95% confidence interval (CI) and F1-score were evaluated.Results: The accuracy rate of the intelligent diagnosis system on the 470 testing photographs was 94.68%; the diagnostic consistency was high; the kappa values of the three groups were all above 85%. Additionally, the AUC values approached 100% in group 1 and 95% in the other two groups. The best results generated from the proposed system for sensitivity, specificity, and F1-scores were 100, 99.64, and 99.74% in group 1; 90.06, 97.32, and 92.49% in group 2; and 92.73, 95.56, and 89.47% in group 3, respectively.Conclusion: The intelligent pterygium diagnosis system based on deep learning can not only judge the presence of pterygium but also classify the severity of pterygium. This study is expected to provide a new screening tool for pterygium and benefit patients from areas lacking medical resources.

No abstract

This study is aimed at developing an intelligent algorithm based on deep learning and discussing its application for the classification and diagnosis of retinal vein occlusions (RVO) using fundus images. A total of 501 fundus images of healthy eyes and patients with RVO were used for model training and testing to investigate an intelligent diagnosis system. The images were first classified into four categories by fundus disease specialists: (i) healthy fundus (group 0), (ii) branch RVO (BRVO) (group 1), (iii) central RVO (CRVO) (group 2), and (iv) macular branch RVO (MBRVO) (group 3), before being diagnosed using the ResNet18 network model. Intelligent diagnoses were compared with clinical diagnoses. The specificity of the intelligent diagnosis system under each attention mechanism was 100% in group 0 and also revealed a high sensitivity of over 95%, F 1 score of over 97%, and an accuracy of over 97% in this group. For the other three groups, the specificities of diagnosis ranged from 0.45 to 0.91 with different attention mechanisms, in which the ResNet18+coordinate attention (CA) model had the highest specificities of 0.91, 0.88, and 0.83 for groups 1, 2, and 3, respectively. It also provided a high accuracy of over 94% with a coordinate attention mechanism in all four groups. The intelligent diagnosis and classifier system developed herein based on deep learning can determine the presence of RVO and classify disease according to the site of occlusion. This proposed system is expected to provide a new tool for RVO diagnosis and screening and will help solve the current challenges due to the shortage of medical resources.