Millimeter waves are complicated to model using conventional empirical methods since they are susceptible to complex environmental influences caused by various landscapes and building structures. We present a novel convolutional neural network (CNN)-based path loss modelling method based on a set of 28 GHz mmWave field measurements in suburban scenarios. The Enhanced Local Area Multi-Scanning algorithm (E-LAMS) that provides a CNN with path loss environmental information is proposed. A new CNN structure with four subnetworks and feature-sharing layers added between convolutional layers is also proposed. The proposed methods demonstrate their superior performance over empirical models and deterministic models in terms of accuracy and complexity. The root mean square error of 8.59 dB has been achieved in path loss prediction in the test scenarios.

This paper presents a location-based interactive model of Internet of Things (IoT) and cloud integration (IoT-cloud) for mobile cloud computing applications, in comparison with the periodic sensing model. In the latter, sensing collections are performed without awareness of sensing demands. Sensors are required to report their sensing data periodically regardless of whether or not there are demands for their sensing services. This leads to unnecessary energy loss due to redundant transmission. In the proposed model, IoT-cloud provides sensing services on demand based on interest and location of mobile users. By taking advantages of the cloud as a coordinator, sensing scheduling of sensors is controlled by the cloud, which knows when and where mobile users request for sensing services. Therefore, when there is no demand, sensors are put into an inactive mode to save energy. Through extensive analysis and experimental results, we show that the location-based model achieves a significant improvement in terms of network lifetime compared to the periodic model.

An accurate and efficient path loss modeling method for millimeter wave communications plays a significant role in the large-scale deployment of a fifth-generation (5G) mobile communication system. Conventional path loss modeling methods such as deterministic methods, empirical methods, and machine learning-based methods, in practice, cannot achieve the desired level of performance in terms of accuracy. This paper proposes a novel path loss model for 5G communications in suburban scenarios using deep learning with dilated convolution and attention. Dilated convolution is used to alleviate the locality of feature extraction and capture the global information on input images. Attention rendered by global context blocks helps the attention-enhanced convolutional neural network (AE-CNN) model utilize the global information on inputs to extract essential features of propagation environments. A distance-embedded local area multi-scanning algorithm which generates input images that can improve learning the latent features with dependency on distance is proposed. The experimental results indicate that the AE-CNN model can outperform state-of-the-art deterministic and empirical methods in terms of root mean square error in test scenarios.

Lee JE, et al. J Korean Med Sci. 2016 Jun;31(6):859-865. http://dx.doi.org/10.3346/jkms.2016.31.6.859

Kong SH, et al. J Gastric Cancer. 2019 Jan;19:e2. https://doi.org/10.5230/jgc.2019.19.e2

Accurate and efficient path loss prediction in mmWave communication plays an important role in large-scale deployment of the mmWave-based 5G mobile communication systems. Existing methods often present limitations in accuracy and efficiency and fail to fulfill the requirements of cell planning, especially in dense urban environments. In this paper, we propose a novel training method called multi-way local attentive learning, which allows for learning from multiple perspectives on the same set of training samples with local attention paid to each subset of the entire dataset. The sample data set can be partitioned in various ways with respect to different attributes, such that a larger amount of knowledge can be extracted from the same data set. The proposed scheme outperforms the existing schemes in terms of prediction accuracy at the average RMSE of 6.01 dBm.