Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

The architecture of the proposed DTLME model for feature engineering.

More »

Fig 1 Expand

Fig 2.

Generic VGG16 model.

More »

Fig 2 Expand

Fig 3.

Pre-trained VGG16 model used for transfer learning.

More »

Fig 3 Expand

Fig 4.

Multimodal embedding for feature learning.

(a) User feature learning; (b) Item feature learning.

More »

Fig 4 Expand

Fig 5.

Sparse rating matrix for item pi for user ui.

More »

Fig 5 Expand

Fig 6.

User-item affinity matrix.

More »

Fig 6 Expand

Fig 7.

User profile, similarity calculation and top-n recommendation.

More »

Fig 7 Expand

Table 1.

Training and testing set for Brazilian E-Commerce dataset.

More »

Table 1 Expand

Table 2.

Training and testing set for E-Commerce product images dataset.

More »

Table 2 Expand

Fig 8.

Accuracy measures for VGG-16 model.

More »

Fig 8 Expand

Fig 9.

Loss for VGG-16 model.

More »

Fig 9 Expand

Fig 10.

The average rating for products in BE-dataset.

More »

Fig 10 Expand

Fig 11.

MAE for BE-dataset @100 epochs.

More »

Fig 11 Expand

Fig 12.

MAE for BE-dataset @20 epochs.

More »

Fig 12 Expand

Fig 13.

Precision, recall and F-1 measures for DTLME model.

More »

Fig 13 Expand

Table 3.

Performance comparison of proposed model with baseline recommendation techniques.

More »

Table 3 Expand

Fig 14.

Comparative analysis of DTLME model with CSSVD, BPR and TF baseline RSs.

More »

Fig 14 Expand

Table 4.

Comparison of the proposed model with baseline algorithms for RMSE on the basis of SR.

More »

Table 4 Expand

Table 5.

Performance comparison for item cold-start problem on BE-dataset.

More »

Table 5 Expand

Table 6.

Performance comparison for user cold-start problem on BE-dataset.

More »

Table 6 Expand