Search

We focus on prediction of channel quality between any two devices using Deep Neural Network (DNN) from information already known to mobile networks. The DNN-based prediction reduces a cost of a common pilot-based channel quality measurement in scenarios with many ad-hoc communicating devices. However, collecting a sufficient number of high-quality and well-distributed training samples in real-world is not feasible. Hence, in this paper, we develop and validate a concept of DNN-based channel quality prediction between any two devices based on a low-complexity and easy-to-create digital twin. The digital twin serves for a generation of a large synthetic training dataset for channel quality prediction. As the low-complexity digital twin cannot capture all real-world aspects of the channels, we enhance the digital twin with real-world measured and artificially augmented inputs via transfer learning. The proposed concept is implemented and validated in software defined mobile network. We demonstrate that the proposed concept predicts the channel quality with a very high accuracy (mean average error of only 0.66 dB) in a real-world complex indoor scenario. Such error is sufficient for practical applications of the developed channel quality prediction concept and the error is few times lower than the error achievable by state-of-the-art solutions.

In 6th generation (6G), a plethora of novel services is unfolding to cater to a myriad of Internet of Things (IoT) devices, surpassing the conventional offerings of mobile phones and internet connectivity. Instances of these services encompass extended reality gadgets, sensors, as well as ground and aerial robots. Nonetheless, the implementation of these sophisticated services presents hurdles for the wireless network, specifically in its capacity to uphold pervasive connections while adhering to varied quality-of-service (QoS) specifications. To sustain capacity growth at an economical cost and low energy consumption while meeting diverse QoS requirements, the advent of innovative technologies is imperative. Recent considerations include millimeter-wave, TeraHertz, and optical frequencies, holographic multiple-input multiple-output (MIMO), ultramassive MIMO, reconfigurable intelligent surfaces (RIS), and ultra-dense networks for various applications. Additionally, the overall system performance is further enhanced through various techniques like beamforming-enabled antennas, cognitive spectrum utilization, and advancements in modulation and coding.

The aim of this report is to evolve the suggestion for determining the limiting value of the qualitative requirements for the flow resistance during high temperatures for reinforced bitumen sheets that are used as the waterproofing of the concrete bridge decks due to EN 14695:2010 and ČSN 736242:2010. Suggested revisions of the standards will lead manufacturers to improve the bitumen sheets which are affecting the processability when using in practice.

This contribution deals with the issue of the weight absorption of bitumen waterproofing sheets. The aim is to determine which parameter the weight absorption depends on, according to the laboratory measurement and the statistical evaluation. This dependence is to be examined based on the results of the weight absorption achieved by the two different testing methodologies [1], [2]. The laboratory measurement was performed on bitumen waterproofing sheets used for waterproofing concrete bridge decks [3].

This paper is based on research dealing with defects that appear on concrete bridge decks with an insulating layer from asphalt strips on the interface between the asphalt strip and its basis. The durability and lifespan of the bearing structure of concrete bridge is determined by insulating layer that constitutes, together with the primary layer and a protective layer, the insulation system of the concrete bridge deck. Paints based on low viscosity epoxy resigns are one of the possibilities of primary layer implementation. These paints may be performed as anchoring-impregnation paints that usually represent single layer paint on the bridge deck surface. Sealing layer is another variant. Sealing layer is a multilayer consisting of anchoring- impregnation paint and sealing paint. The primary layers mainly provide vapour closing of the concrete surface, and partly, through roughening the surface, contribute to adhesion of bitumen (asphalt) insulation (waterproofing) layer. Application of the primary layer has been spreading in the Czech Republic since the 1990s. Now, after approximately 30 years of use defects in these epoxy based sealing layers at the interface between primary layer and waterproofing layer of reinforced bitumen sheets (RBS) are being solved in the Czech Republic. After performance of the first test focusing on breaking-strength, it was found that the strength between the asphalt and the primary belt layer in some types of low-viscosity resin-epoxy decreases and after a certain period of time again increases, depending on the time. Tensile strength test is carried out on a sample of asphalt strip, which is fused onto the substrate with a primer coat. It was therefore proceeded to test the shear adhesion. Testing of the shear adhesion is conducted on the entire concrete deck waterproofing system. It was supposed that the decrease of adhesion at this test become evident in higher extent. Adhesion tests in shear were performed on the primary layer consisting of an anchoring impregnation coating and sealing layer.