Enhanced deep learning based channel estimation for indoor VLC systems

Salama, Wessam M.; Aly, Moustafa H.; Amer, Eman S.

doi:10.1007/s11082-022-03904-4

Cited by 7 publications

(4 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The DNN achieves better results than KF at different constellation values. At BER = 10 −3 , there is an improvement for DNN over KF by ~ 1.2 dB (~ 13%) in 16, 32, 64 and 128. Table 1 shows the comparison of the enhancement of the optimized DNN in the present work, with both NN model in Salama et al (2022) and the KF in Shawky et al (2018).…”

Section: Resultsmentioning

confidence: 99%

“…Both CP and IFFT are used to obtain non-negative symbols and to avoid ISI, Fig. 2 (Salama et al 2022). The imaginary odd input data is used to produce odd and real output, This is used for clipping to remove the negative part of signal, that does not change its amplitude.…”

Section: Aco-ofdmmentioning

confidence: 99%

“…In a previous work Salama et al (2022), performed a comparison between two modulation techniques; ACO-OFDM and DCO-OFDM, by using three different estimators LS, MMSE and KF. We used the DNN model to enhance the deep learning.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Deep learning based channel estimation optimization in VLC systems

2022

Self Cite

View full text Add to dashboard Cite

This paper aims to improve the channel estimation (CE) in the indoor visible light communication system. The proposal of this paper deals with a system that depends on a comparison between Deep Neural Network (DNN), Yolo v3, and Kalman filter (KF) algorithm, for two optical modulation techniques; asymmetrically clipped optical-orthogonal frequency-division multiplexing (ACO-OFDM) and direct current optical-orthogonal frequency division multiplexing (DCO-OFDM). The CE can be evaluated by the error rates in the received bits, where increased error means a performance decrease of the system and vice versa. Receiving less errors at the receiver indicates improved CE and system performance. Hence, the main aim of our work is to decrease the error rate by using different estimators. Furthermore, we apply automatic hyper-parameter approach and Bayesian optimization, to Yolo v3 model to improve the system performance and reduce the positioning error. The metric parameter of bit error rate (BER) aims to determine the improvement ratio in different systems. The model in this paper is based on training with OFDM samples of signal with labels which are received and are corresponding to the signals of OFDM. At a BER = 10−3 with DCO-OFDM, the DNN outperforms KF with 1.7 dB (8.09%) at the bit energy per noise $$(E_{b} {/}N_{o} )$$ ( E b / N o ) axis. Also, for ACO-OFDM at BER = 10−3, the DNN achieves better results than KF by about 1.9 dB (11.8%) at the $$(E_{b} {/}N_{o} ){ }$$ ( E b / N o ) axis. For different values of M in QAM, the DNN outperforms KF for ACO-OFDM by average improvement of ~ 1.2 dB (~ 13%).

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Aco-ofdmmentioning

confidence: 99%

See 1 more Smart Citation

Deep learning based channel estimation optimization in VLC systems

2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…As applied in Salama et al (2022) the channel is modeled as an auto-regressive (AR) process in the model of space state. The AR models and past values take the current values effects.…”

Section: Kalman Algorithmmentioning

confidence: 99%

Deep learning/Kalman filter-based underwater localization in VLC systems

Salama

Aly

Amer³

2023

Opt Quant Electron

Self Cite

View full text Add to dashboard Cite

There is a huge importance for the localization system in underwater visible light communication (VLC) systems as in petroleum, military and diving fields. To enhance the localization system, we use the Kalman filter (KF) algorithm with average received signal strength (RSS) method to obtain the nearest estimated positions. In this paper, two channel modeling weighted double Gamma functions (WDGF) are applied and a combination exponential arbitrary power function (CEAPF) for enhancing localization in VLC underwater systems. Using the proposed KF enhances the localization by ~ 60% as compared to the than average RSS technique for WDGF channel modeling and ~ 78% for the CEAPF channel modeling. Based on the estimate of received signal strength (RSS) by deep learning models (DLMs), underwater localization utilizing VLC is introduced. Our proposed framework is categorized into two phases. First, data collection is collected based on MATLAB software. Second, the training and testing of DLMs, SSD, RetinaNet, ResNet50V2 and InceptionResNetV2 techniques are applied. The channel gains are the DLMs’ input data set, while the DLMs’ output is the RSS intensity technique coordinates for each detector. The DLMs are then developed and trained using Python software. The ResNet50V2 based on average RSS technique hybrid with KF in CEAPF channel model achieves 99.98% accuracy, 99.97% area under the curve, 98.99% precision, 98.88% F1-score, 0.101 RMSE and 0.32 s testing time.

show abstract

Optimized deep learning/kalman filter-based underwater localization in VLC systems

2023

View full text Add to dashboard Cite

Several applications depend on the localization technique in underwater visible light communication (UVLC) systems, as military, petroleum, and diving fields. Recent research aims to develop the localization system by different methods to obtain the optimum position of the receiver. In this paper, we use Kalman Filter (KF) algorithm with average Received Signal Strength (RSS) technique using optimization. Optimized Deep Learning Models (DLMs) are utilized to improve the system performance, including such as ResNet50V2, InceptionResNetV2, SSD, and RetinaNet. Two channel modeling Weighted Double Gamma Function (WDGF) with a Combination Exponential Arbitrary Power Function (CEAPF) are used for sea water to enhance the UVLC localization system. The obtained results show that using CEAPF channel modeling with ResNetV2 strategy achieves the best accuracy of the localization for different methods. Also, the ResNetV2 outperforms other strategies for using RSS average technique. The RSS with KF and DLM achieves a higher accuracy with ResNetV2 than InceptionResNetV2, RetinaNet and SSD. Using WDGF achieves accuracy less than that in CEAPF where for using KF with average RSS method. Applying the RSS with KF with CEAPF channel modeling improves the performance than using WDGF. We use an automatic hyper-parameter (HP) approach to the Bayesian optimization models ResNet50V2, InceptionResNetV2, SSD, and RetinaNet. The ResNet50V2 based on average RSS technique hybrid with KF in CEAPF channel model achieves 99.99% accuracy, 99.99% area under the curve (AUC), 99.98% precision, 99.89% F1-score, 0.099 RMSE and 0.43 s testing time.

show abstract

Enhanced deep learning based channel estimation for indoor VLC systems

Cited by 7 publications

References 16 publications

Deep learning based channel estimation optimization in VLC systems

Deep learning based channel estimation optimization in VLC systems

Deep learning/Kalman filter-based underwater localization in VLC systems

Optimized deep learning/kalman filter-based underwater localization in VLC systems

Contact Info

Product

Resources

About