Читать книгу Handbook of Intelligent Computing and Optimization for Sustainable Development - Группа авторов - Страница 130

5.3.2.2 Results and Discussion

Оглавление

The training and testing of the models are set up in Keras built on top of TensorFlow using Google Colaboratory. COST 2100 channel model is used to generate the data set. The data set provided by Wen et al. [20] is used for simulation here. The training data consists of 100,000 samples. The validation and test set contain 30,000 and 20,000 samples, respectively. All the test samples are independent of the training and validation samples. The network is trained for 100 epochs with a batch size of 200. The learning rate is set to 0.001. Adam optimizer is used to update the parameters, and the mean squared error (MSE) function is used as the loss function. The NMSE quantitatively provides the difference between the original channel matrix and the recovered channel matrix Hr.

(5.1)

The CSI feedback serves as a beamforming vector. Consider hrn as the reconstructed channel vector of the nth sub-carrier and as the original channel vector of the nth subcarrier. Cosine similarity (ρ), which measures the quality of the beamforming vector can be given as

(5.2)

where Nc is the number of sub-carriers.

Figure 5.8 shows the pseudo gray plots of the channel matrices. The recovered channel images for both CsiNet and InceptNet with CR = 1/4.


Figure 5.8 Pseudo gray plots of (a) original image (b) image recovered by CsiNet for CR= 1/4 (c) image recovered by InceptNet for CR= 1/4.

Table 5.2 shows the comparative analysis between the already existing CsiNet and the proposed InceptNet. For low compression ratio of 1/4, the NMSE for InceptNet is −18.68 dB and for CsiNet −14.43 dB. The InceptNet gives a better recovery of the channel matrix as compared to the CsiNet. Even for a high compression ratio of 1/32, it is observed that NMSE is “−7.987” dB for InceptNet and “−5.32” for CsiNet. It is observed that the InceptNet outperforms the CsiNet in both NMSE and cosine similarity for all compression ratios. The InceptNet achieves better performance by training for only 100 epochs. The parallel inception blocks with different filter sizes help in better extraction of both high level and subtle features. The training time and quantitative results can be further improved by using the recently developed network architectures.

Table 5.2 Performance comparison analysis for 100 epochs between CsiNet and InceptNet.

CR CsiNet InceptNet
NMSE (dB) Cosine Similarity NMSE (dB) Cosine Similarity
1/4 −14.43 0.979 −18.68 0.989
1/8 −11.35 0.963 −13.014 0.973
1/16 −8.08 0.932 −9.357 0.941
1/32 −5.32 0.874 −7.987 0.918
Handbook of Intelligent Computing and Optimization for Sustainable Development

Подняться наверх