Visible light communication (VLC) is now used to achieve high data rates. Opticalorthogonal frequency division multiplexing (O-OFDM) is a strong technique for intensity modulation and direct detection (IM-DD). Direct current biased O-OFDM (DCO-OFDM) and asymmetrically clipped O-OFDM are two modern O-OFDM systems that operate with IM-DD constraints (ACO-OFDM). Due to severe out of band interference, the DCO-OFDM and ACO-OFDM systems have a high peak to average power ratio (PAPR) and substantial adjacent channel interference (ACI) (OOB). Furthermore, as compared to bipolar OFDM systems, they obtain a greater chance of bit error. The combination of the STC scheme, symbol extension, and pulse shaping signal is presented in this paper for improving the performance of the O-OFDM system without affecting system throughput. This article also decreases the OOB, PAPR, and bit error rate (BER) of DCO-OFDM and ACO-OFDM systems. Further analytical analyses for the proposed systems, such as OOB, PAPR, and computing complexity, are obtained in this paper. The simulation results verify the analytical study of the proposed methods for OOB reduction and PAPR reduction. As compared to typical O-OFDM systems, the proposed shaped STC-DCO-OFDM scheme and the proposed shaped STC-ACO-OFDM scheme lower the OOB by about 40 dB and the PAPR by about 4 dB at the 10 -3 probability point of the complementary cumulative distribution function (CCDF). The proposed systems outperform existing O-OFDM systems under AWGN for the BPSK modulation scheme in terms of BER, and reduce the computational complexity.

Artificial neural networks have advanced the frontiers of reversible steganography. The core strength of neural networks is the ability to render accurate predictions for a bewildering variety of data. Residual modulation is recognised as the most advanced reversible steganographic algorithm for digital images. The pivot of this algorithm is predictive analytics in which pixel intensities are predicted given some pixel-wise contextual information. This task can be perceived as a low-level vision problem and hence neural networks for addressing a similar class of problems can be deployed. On top of the prior art, this paper investigates predictability of pixel intensities based on supervised and unsupervised learning frameworks. Predictability analysis enables adaptive data embedding, which in turn leads to a better trade-off between capacity and imperceptibility. While conventional methods estimate predictability by the statistics of local image patterns, learning-based frameworks consider further the degree to which correct predictions can be made by a designated predictor. Not only should the image patterns be taken into account but also the predictor in use. Experimental results show that steganographic performance can be significantly improved by incorporating the learning-based predictability analysers into a reversible steganographic system.

It is challenging to place drones in the best possible locations to monitor all sensor targets while keeping the number of drones to a minimum. Strawberry optimization (SBA) has been demonstrated to be more effective and superior to current methods in evaluating engineering functions in various engineering problems. Because the SBA is a new method, it has never been used to solve problems involving optimal drone placement. SBA is preferred for optimizing drone placement in this study due to its promising results for nonlinear, mixed, and multimodal problems. Based on the references listed below, no study has investigated the need to develop a parallelized strategy version. Several studies have been conducted on the use of drones for coverage. However, no optimization algorithms have been evaluated regarding time complexity or execution time. Despite what has been said thus far, no study has looked into the significance of a systematic framework for assessing drone coverage techniques using test suits. An optimized drone placement algorithm based on strawberry optimization is presented in the paper. The strawberry optimization algorithm will solve the drone placement problem through parallelization. In addition, the authors deploy test suits that vary in size from small to large. The dataset consists of four categories with three problems each. Results indicate that strawberry optimizers outperform Genetic algorithms (GA) and particle swarm optimization algorithms (PSO) in the number of drones, convergence, and computation time. Furthermore, the proposed approach achieves the best solution in a finite number of steps. In small-scale problems, the performance of all algorithms is convergent. As the size of the data set increases, the superiority of Strawberry optimization algorithms becomes evident. Overall, Strawberry comes out on top for eleven out of twelve comparisons.