Over the past decade, the Internet of Thing (IoT) devices have been deployed in wide-scale several applications to collect vast amount of data from different locations in a time-series manner. However, collected data may be missing or damaged due to several issues such as unreliable communications, faulty sensors and synchronization problem that decrees application accuracy. Therefore, a several imputation-based machine learning approaches have been suggested to handle this problem in IoT application. In this study, a new approach is proposed called impute missing data (IMD) based on multi-Spike Neural Network learning method called IMD-SNN, to increase the reliability of missing value imputation in IoT. The method consists of three phases: Inserting missing data, to evaluate the missing values based on the cumulative distribution function (CDF), the multi SNN phase to estimate missing data according to the timestamp and a performance evaluation phase to evaluate an imputation accuracy via made a comparison with two models: imputation based KNN (I-KNN) and Imputation based (I-MLP) model based on resource usage and imputation accuracy assessment metrics. The implementation results have been shown that IMD-SNN utilizes less energy usage in comparison with (I-MLP) model and I-KNN model and gives highest imputation accuracy in contrast with (I-MLP) model and I-KNN model. Also, the IMD-SNN model utilizes less memory usage and needs execution time less than I-MLP model.

Multiple Input and Multiple Output (MIMO) is a promising technology to enable spatial multiplexing and improve throughput in wireless communication networks. To obtain the full benefits of MIMO systems, the Channel State Information (CSI) should be acquired correctly at the transmitter side for optimal beamforming design. The analytical centre-cutting plane method (ACCPM) has shown to be an appealing way to obtain the CSI at the transmitter side. This paper adopts ACCPM to learn down-link CSI in both single-user and multi-user scenarios. In particular, during the learning phase, it uses the null space beamforming vector of the estimated CSI to reduce the power usage, which approaches zero when the learned CSI approaches the optimal solution. Simulation results show our proposed method converges and outperforms previous studies. The effectiveness of the proposed method was corroborated by applying it to the scattering channel and winner II channel models.

Distance measuring equipment (DME), which gauges the distance between an aircraft and a ground station, is an essential navigational tool in aviation. However, because of instrument constraints, multipath interference, and ambient conditions, DME measurements are frequently noisy and prone to errors. This study introduces a framework that integrates machine learning (ML), sensor fusion, neural networks (NNs), and real-time processing with the aim at enhancing the accuracy and reliability of distance estimation, with particular emphasis on regression models. To boost robustness, the suggested system uses sensor fusion to combine DME data with inputs from additional sensors, such as GPS and Inertial Navigation Systems (INS). The intricate correlations between sensor inputs and actual distance are modelled by NNs because of their ability to produce precise predictions even in the presence of noise and they provide a very accurate distance calculation with minimal latency. ML based regression models further improve system reliability by detecting and correcting anomalies in the sensor data. When tested in MATLAB and compared with standalone DME measurements, the proposed system shows higher accuracy of distance estimation. In addition, the real-time sensor fusion ensures precise and timely outputs for essential aviation applications. Using this method not only improves the DME system, but also provides a scalable and flexible solution for different navigation and positioning systems in dynamic scenarios. The system is measured based on significant metrics including mean squared error (MSE), peak signal-to-noise ratio (PSNR) and signal-to-noise ratio (SNR).