Next-generation communication systems will face new challenges related to efficiently managing the available resources, such as the radio spectrum. DL is one of the optimization approaches to address and solve these challenges. However, there is a gap between research and industry. Most AI models that solve communication problems cannot be implemented in current communication devices due to their high computational capacity requirements. New approaches seek to reduce the size of DL models through quantization techniques, changing the traditional method of operations from a 32 (or 64) floating-point representation to a fixed point (usually small) one. However, there is no analytical method to determine the level of quantification that can be used to obtain the best trade-off between the reduction of computational costs and an acceptable accuracy in a specific problem. In this work, we propose an analysis methodology to determine the degree of quantization in a DNN model to solve the problem of AMR in a radio system. We use the Brevitas framework to build and analyze different quantized variants of the DL architecture VGG10 adapted to the AMR problem. The evaluation of the computational cost is performed with the FINN framework of Xilinx Research Labs to obtain the computational inference cost. The proposed design methodology allows us to obtain the combination of quantization bits per layer that provides an optimal trade-off between the model performance (i.e., accuracy) and the model complexity (i.e., size) according to a set of weights associated with each optimization objective. For example, using the proposed methodology, we found a model architecture that reduced 75.8% of the model size compared to the non-quantized baseline model, with a performance degradation of only 0.06%.

Traffic Classification (TC) systems are designed to identify the applications generating network traffic. Recent advancements in TC leverage Deep Learning (DL) techniques, surpassing traditional methods in complex scenarios, including those with encrypted traffic. Notably, state-of-the-art DL-based TC systems have been developed for wireless networks using Physical Layer (L1) packets. This approach overcomes the common limitation in TC research that assumes traffic flows within a wired network under a single network management domain. Despite their benefits, DL-based TC systems often demand significant computational resources, typically available only in cloud environments. Consequently, deploying models at the edge is often infeasible due to their resource-intensive nature, given their original training and optimization for high-resource environments. The inherent challenge lies in adapting these systems for edge computing scenarios, including deployment at access points. In this paper, we propose a novel methodology that exploits expert knowledge in combination with recent advances in Multi-Task Learning (MTL) and Deep Neural Network (DNN) optimization to allow spectrum-based TC systems to run on constrained devices. This paper propose a well-defined and innovative methodology for resource-efficient, spectrum-based TC to address this issue, combining MTL with DNN optimization techniques. Performance evaluations on an NVIDIA Jetson TX2 demonstrate that our most optimized MTL model, handling four TC tasks, can reduce memory requirements by a factor of 2.65x and improve execution time by 3.6x compared to sequential execution of four Single-Task Learning (STL) models in a server-grade configuration, with minimal accuracy impact (less than a 0.5% drop) and energy efficiency of 0.97 millijoules per sample at inference. Compared to other edge platforms such as the Raspberry Pi model 3B+ (RPI3B+) with a low-power Artificial Intelligence (AI)-accelerator such as the Coral Tensor Processing Unit (TPU), the NVIDIA Jetson achieves a 12-fold improvement in energy efficiency with no impact on accuracy.These are the first available results to provide a benchmark for different performance metrics (memory, computing, energy) over heterogeneous constrained devices for this type of TC system.

The objective of this study, reflected in this document, was to implement a rectenna for 2.45 GHz and 5.38 GHz wireless local area applications. For this purpose, the antenna dimensions were set to 18 mm × 44 mm, which is simulated using the optimization software CST Studio, manufactured on FR4 substrate with a thickness of 1.6 mm, where the conductive material has a thickness of 0.035 mm. Likewise, the rectangular slot technique was used to improve the bandwidth of the antenna; this technique consists of inserting slots in the structure to modify the displacement of the surface current. The above presented a gain of 2.49 dB at the 2.45 GHz frequency and 4.01 dB at the 5.38 GHz frequency. The proposed antenna for RF energy harvesting applications exhibits a dipole type radiation pattern, which enhances the capture of RF energy from various directions. The triple slotted-band rectifier with T-shaped impedance matching network was designed in FR4, using a Schotkky HSMS-286C diode for AC to DC RF control switching. A tp-link TL-WR940N wireless router was used as the RF emitting source at 30 cm separation between it and the proposed rectenna. The DC output of the rectenna is 3 volts with a generated signal power of 20 dBm at 2.4 GHz. The low-cost rectenna can be used for power-charging applications in the Internet of things (IoT) systems.

Flight route planning in civil aviation seeks to minimize the total cost of the operation while maintaining high safety standards. Therefore, the increase in the number of air routes as well as air traffic in commercial aviation poses new challenges for planning optimal routes. This work proposes a method to plan routes using a bio-inspired technique called Particle Swarm Optimization (PSO). Such method aims to obtain the shortest distance between two points, thus reducing NO_X, CO₂ and H₂O emissions. The analysis of fuel consumption and emissions was carried out using a multidisciplinary simulation tool, the Preliminary Multidisciplinary Design Framework (PMDF). The latter was applied to an aircraft with a conventional configuration powered by an innovative turbofan engine. The planner provides a new route with the shortest possible flight distance and, at the same time, considers unexpected obstacles on the route, thus minimizing fuel consumption and possible polluting emissions into the atmosphere. This is one of a series of works that will use the proposed design tool. Different economic and environmental scenarios will be evaluated once such studies are concluded.

In conventional aviation, flight route planning aims to guarantee security and reduce the operating costs of the different types of aircraft that are currently available. This paper presents and analyses the results obtained from planning a flight route in real time for short-range aircraft fitted with geared turbofans with a constant volumecombustor to reduce operating costs by optimizing the route in terms of less distance traveled. In the analysis, an off-line route obtained from a flight profile using the Preliminary Multidisciplinary Design Framework tool is compared with the same route that is run in real time using a route planner optimized with a particle swarm optimization algorithm. The average results indicate that the route proposed by the optimization algorithm reduces direct and indirect operating costs if compared to the alternative route (traditional approach according to flight plan). This is mainly due to the lower fuel consumption and maintenance costs when selecting an optimized route. In cases where direct and alternate routes are completely obstructed, the planner can find an optimized route based on the lower costs. In this way, the pilot and the flight controller on the ground can make the decision whether to risk the aircraft with passengers on a route with adverse weather conditions or to have an optimized and safe one. The use of this type of route optimizer leads to significant benefits with respect to aircraft environmental taxes for emissions and noise, and increases aviation safety. This finding indicates that the route planner is a suitable support option when the course of an aircraft must be changed to follow a different route than the suggested alternative.

Tele-education went from being an option to becoming a necessity given the current public health problems. Due to this, the educational sector has included blended courses as part of its training offer. Mobile Ad Hoc Networks (MANETs) will therefore, become an important resource to work, under this class format, with students outside the classroom, in accordance with the standards recommended inside a university campus. MANETs require certain parameters that ensure the quality of communications and identify the factors that influence Quality of Service (QoS). The purpose of this study is to determine the factors that affect the quality of communications in a tele-education environment. For this purpose, the QoS of a MANET supporting a real-time video streaming is evaluated based on throughput. As a result, the main factors that directly or indirectly affect the operation of the network could be identified, which may help in making decisions regarding aspects such as the number of nodes and the node mobility speed. Moreover, the versatility and scalability of the MANET was proven, as when the number of nodes went from 5 to 10, throughput increased by 14 %. This also occurred with the transmission rate factor when the video was streamed in a channel with a variable bitrate (64–4096 kbps).