Visible Light Communication (VLC) is increasingly seen as a promising solution for indoor ranging systems. This study investigates user range estimation from a light source in a single-input single-output (SISO) system, considering input-signal-dependent shot noise (ISDSN). We apply extended Kalman filter (EKF), maximum likelihood (ML), and nonlinear least square (NLS) estimator techniques for range estimation and derive the Bayesian Cramér–Rao lower bound (BCRLB) to assess system performance. Monte Carlo simulations confirm that the proposed estimators align well with theoretical expectations. The results indicate that estimation error rises with higher ISDSN levels for all techniques and the BCRLB, with the EKF showing superior accuracy in range estimation compared to ML and NLS.

In visible light communications (VLC), signal-dependent shot noise (SDSN) significantly impacts the accuracy of channel estimation. This work introduces a simple yet novel machine learning-based estimator to overcome this challenge. A mathematical framework for the proposed estimator is developed, enabling the computation of its mean square error (MSE). Results show that, in the presence of SDSN, the proposed estimator outperforms the traditional least squares estimator (LS). In the ideal scenario without SDSN, the proposed algorithm remains slightly more efficient and accurate.

The rapid advancement of sequencing technologies has led to the generation of complex multi-omics data, which are often high-dimensional, noisy, and imbalanced, posing significant challenges for traditional machine learning methods. The novelty of this work resides in the architecture-level integration of autoencoders with Generative Adversarial Network (GAN) and Conditional Tabular Generative Adversarial Network (CTGAN) models, where the autoencoder is employed for latent feature extraction and noise reduction, while GAN-based models are used for realistic sample generation and class imbalance mitigation in multi-omics cancer datasets. This study proposes a novel framework that combines an autoencoder for dimensionality reduction and a CTGAN for generating synthetic samples to balance underrepresented classes. The process starts with selecting the most discriminative features, then extracting latent representations for each omic type, merging them, and generating new minority samples. Finally, all samples are used to train a neural network to predict specific cancer outcomes, defined here as clinically relevant biomarkers or patient characteristics. In this work, the considered outcome in the bladder cancer is Tumor Mutational Burden (TMB), while the breast cancer outcome is menopausal status, a key factor in treatment planning. Experimental results show that the proposed model achieves high precision, with an average precision of 0.9929 for TMB prediction in bladder cancer and 0.9748 for menopausal status in breast cancer, and reaches perfect precision (1.000) for the positive class in both cases. In addition, the proposed AE–CTGAN framework consistently outperformed an autoencoder combined with a standard GAN across all evaluation metrics, achieving average accuracies of 0.9929 and 0.9748, recall values of 0.9846 and 0.9777, and F1-scores of 0.9922 for bladder and breast cancer datasets, respectively. A comparative fidelity analysis in the latent space further demonstrated the superiority of CTGAN, reducing the average Euclidean distance between real and synthetic samples by approximately 72% for bladder cancer and by up to 84% for breast cancer compared to a standard GAN. These findings confirm that CTGAN generates high-fidelity synthetic samples that preserve the structural characteristics of real multi-omics data, leading to more reliable class balancing and improved predictive performance. Overall, the proposed framework provides an effective and robust solution for handling class imbalance in multi-omics cancer data and enhances the accuracy of clinically relevant outcome prediction.

The application of Deep learning (DL) in wireless communications has achieved remarkable success. However, there are still marked challenges impeding its use in the physical layer, largely due to the random nature of the wireless channel. This work investigates an end-to-end transceiver based on an unsupervised auto-encoder. We aim to detect a wireless signal suffering from transceiver hardware impairments as it passes through the fading channel. Furthermore, we examine the ability of this receiver to detect signals corrupted with non-Gaussian noise. We use meta and joint learning techniques to train the auto-encoder transceiver with random unknown channels and HWIs to simulate real channel conditions. We compare the results with maximum likelihood detection (MLD) in terms of bit error rate (BER). Our results demonstrate that using meta-learning to train the auto-encoder enhances system performance by reducing the BER of the received signal.