A novel technique is proposed for joint multi-impairment optical performance monitoring (OPM) with bit-rate and modulation format identification (BR-MFI) in next-generation heterogeneous optic communication networks by convolution neural network (CNN)-based deep multi-task learning (MTL) on asynchronous delay-tap sampling (ADTS) phase portraits. Instead of treating the monitoring and identification tasks as separate problems, a novel MTL technique is used to joint optimization of them utilizing the ability of feature extraction and feature sharing. Compared with principal component analysis (PCA)-based pattern recognition algorithm, CNN-based MTL achieves the better accuracies and has a shorter processing time (~56ms). The combination signals of three modulation formats and two bit rates under various impairments are used in numerical simulation. For OPM, the results show monitoring of optical signal-to-noise ratio (OSNR), chromatic dispersion (CD), and differential group delay (DGD) with root-mean-square (RMS) error of 0.73 dB, 1.34 ps/nm, and 0.47 ps, respectively. Similarly, for BR-MFI, even in the case of limited training data, 100% accuracies can be achieved. Additionally, the effects of training data size, task weights, and model structure on CNN-based MTL performance are comprehensively studied. The proposed technique can intelligently analyze the signals of future heterogeneous optic communication networks, and the analysis results are helpful for better management of optical networks.

In this work, a novel positioning algorithm based on a long short term memory-fully connected network (LSTM-FCN) is proposed to improve the performance of an indoor visible light positioning (VLP) system. Using the proposed LSTM-FCN based positioning algorithm, the VLP system with a single light emitting diode (LED) and multiple photodetectors (PDs) was implemented. On this basis, the positioning performance of the established VLP system using proposed LSTM-FCN, traditional FCN and support vector regression (SVR) based algorithm is investigated and compared. It is demonstrated that the VLP system using the proposed LSTM-FCN based algorithm has better performance than that using other machine learning algorithms. As a result, an average positioning error of 0.92 cm and a maximum positioning error of less than 5 cm can be obtained for the established VLP system.

This paper presents a visible light positioning (VLP) system using a single light emitting diode (LED) and a novel receiver. In the proposed system, the receiver is composed of a horizontal photodetector (PD) and two tilted PDs, and a known calibration point is deployed to improve the accuracy of the positioning. Based upon the multi-PDs' relative positions and the received signal strength (RSS), the location of the receiver can be estimated regardless of the LED's and PDs' characteristics. The influences of tilted PDs on the positioning errors are discussed, i.e. the polar angle - and the difference - between two azimuth angles. The experimental results show that high accuracy can be achieved when α=20° and θ ranges from 30° to 90°. The average and maximum errors are 2.15cm and 4.01cm respectively in the case of α=20° and θ=45°. The proposed system avoids the inter-cell interference (ICI) caused by different transmitters and can be applied in scenarios with limited LEDs.

In this paper, a novel laser spot tracking algorithm that incorporates the Kalman filter with the continuously adaptive Meanshift algorithm (Cam-Kalm) is proposed and employed in an underwater optical wireless communication (UOWC) system. Since the Kalman filter has the advantage of predicting the state information of the target spot based on its spatial motion features, the proposed algorithm can improve the accuracy and stability of the moving laser spot tracking. A 2 m optical wireless communication experimental system with auto-tracking based on a green laser diode (LD) is built to evaluate the tracking performance of different algorithms. Experimental results verify that the proposed algorithm outperforms conventional tracking algorithms in aspects of tracking accuracy, interference resistance, and response time. With the proposed Cam-Kalm algorithm, the experimental system can establish an effective communication link, while the maximum tracking speed is 20 mm/s given the forward-error-correction (FEC) threshold.

In this paper, an integrated visible light communication and positioning (VLCP) code division multiple access (CDMA) system is proposed for recovering original user data and obtaining positioning information simultaneously. A generalized modification method for balanced bipolar code set is presented, which can be applied to VLCP-CDMA system with intensity modulation. Both modified bipolar code sets, zero correlation zone (ZCZ) code set and Walsh code set, are employed and evaluated in VLCP-CDMA systems. When considering synchronous and quasi-synchronous (QS) systems, it is demonstrated that the modified ZCZ code set with ideal zero correlation zone properties performs better communication and positioning performance than the modified Walsh code set by system simulations and experiments. As a result, a bit error rate (BER) of 1.8×10⁻³ and an average positioning error of 1.50 cm are successfully obtained by adopting modified ZCZ code set in a 4-user real-time VLCP-CDMA system. It will offer a promising solution to meet both communication and positioning requirements of future intelligent systems.