Melanoma is the most aggressive form of skin cancer, and its early and accurate diagnosis is crucial for patient treatment. Gene expression profiling has become a powerful tool to capture the molecular portraits of tumors, but it suffers from the difficulties of small sample size and high dimensionality. In this study, we propose a lightweight one-dimensional convolutional neural network (1D-CNN) for melanoma sample classification from mRNA expression data. The proposed framework involves mutual information for feature selection to reduce dimensionality, supported by preprocessing steps such as log transformation, low-variance gene removal, and filtering of weakly expressed genes to improve data quality before modeling. The proposed CNN is benchmarked against classical machine learning (ML) methods- K-nearest neighbors (KNN), Random Forest (RF), and AdaBoost-across multiple gene subsets (150, 300, and 450). Experimental results indicate that when 300 genes are selected, the proposed CNN demonstrates a consistent improvement with an F 1 -score of 97% and a peak accuracy of 96%, while providing robustness across different feature sizes. Compared with classical models, the proposed CNN delivers a more stable trade-off between precision and recall. The results show that streamlined deep learning (DL) models enable accurate and efficient melanoma subtype classification, which highlights potential for clinical application.

Relying on ground-based infrastructure for model training in Low Earth Orbit (LEO) constellations introduces significant challenges, including intermittent and costly spaceground communication. To address these challenges, this paper proposes a decentralized learning framework that enables model training directly within satellite constellations, utilizing intra-and inter-plane inter-satellite links (ISLs) for information exchange. The paper develops a geo-spatial filtering mechanism that selects the most relevant satellites to form a smaller, more efficient constellation. It then introduces a novel Adaptive Halving-Doubling (AHD) algorithm that enables collective communication within the emerging partial ring topology. Experimental results validate the framework's effectiveness, efficiency, and scalability. Notably, the transmission energy was observed to constitute less than 10% of traditional full constellation (FC) setups, even with increasing model sizes. Moreover, communication overhead relative to FC setups decreased with increasing constellation size, highlighting the operational efficiency of the framework.

To keep up with the continuously growing coverage demands and attain true global coverage, the deployment of multi-layered low Earth orbit satellite constellations is necessary. Next-generation mega satellite constellations are expected to rely on inter-satellite links to relay information, which will enable fast and reliable communications between the different satellite nodes in free-space and facilitate the utilization of coverage diversity modes that can further enhance the quality-of-service provided in the network. However, materializing these high performing systems is challenging due to the complexity of the network architecture which may require long and complex simulation processes during design. In this article, we develop theoretical modeling for the probability of coverage for various diversity modes in mega satellite constellations by leveraging tools from stochastic geometry. We first develop analytical models for conventional single-shell networks and then extend these models to incorporate multi-shell networks. The analysis is validated using Monte-Carlo simulations which show a close fit to the analytical models derived. Moreover, the analytical models provide a performance baseline that is comparable to practical networks that rely on regular network architectures such as SpaceX’s Starlink. This allows network operators to devise expansion strategies to cater for expanding demands and gain insights into the performance of the network as more shells are introduced into the network.

Mega satellite networks recently emerged to com-plement the current terrestrial infrastructure to attain global coverage and faster communication links. However, with in-creased congestion in the radio spectrum, migrating satellite communication to high frequencies can provide higher data rates. Nevertheless, signal fading due to weather conditions and atmospheric losses becomes significant at such high frequencies. In this paper, we leverage tools from stochastic geometry to provide an analytical framework that captures the effect of high frequency fading for satellite constellations in the downlink. The analytical framework presented exploits the spatial diversity provided by the satellite network and examines the performance of the dominant satellite (satellite providing the best quality of service). Results show a close fit to the performance of practical networks and can thus provide network designers with an analytical benchmark to assist with network tuning.

With the exponential growth of the Internet of Things (IoT) landscape and the resulting spectrum congestion, innovative techniques for spectrum monitoring are crucial. This paper presents an approach to spectrum monitoring harnessing the power of spiking neural networks (SNNs) with a focus on image segmentation using the UNet architecture. Traditional methods, including energy detection, have been widely used but are not without challenges, especially in environments with varying signal-to-noise ratios. In contrast, the presented SNN approach in this paper demonstrates through simulations performance metrics that significantly surpass energy detection methods and closely align with conventional convolutional neural network techniques while also exhibiting favorable energy efficiency. Future explorations will delve into enhancing the framework using machine learning techniques for advanced feature extraction and multiclass segmentation.

Cell-free (CF) massive multiple-input multiple-output (MIMO), as a promising network architecture for beyond the fifth generation (5G), has a great potential to support grant-free (GF) transmission for machine-type communication (MTC). To shed light on this subject, this work aims to model and evaluate the performance of GF transmission in CF massive MIMO under a realistic network deployment scenario, where the spatial locations of both access points (APs) and devices are assumed to be random in nature. In particular, by capitalizing on the distinctive CF network architecture and features, we design a new two-disk based geometric model for GF transmission, which facilitates analysis and understanding in CF massive MIMO. Based on the proposed two-disk model, we derive an approximated closed-form expression for the access success probability by leveraging on techniques from stochastic geometry, and investigate the impact of different key system parameters on the network performance, which have not been presented previously. To highlight the performance superiority of CF massive MIMO, we further provide a comparative analysis by using an analogous single-disk model in an equivalent co-located massive MIMO network. Simulation results verify our analysis and demonstrate that CF massive MIMO is able to significantly outperform its co-located counterpart in terms of access success probability and provide robust performance against increased access density, which well suits to crowd scenarios.

Utilizing Low Earth Orbit (LEO) satellite networks equipped with Inter-Satellite Links (ISL) is envisioned to provide lower delay compared to traditional optical networks. However, LEO satellites have constrained energy resources as they rely on solar energy in their operations. Thus requiring special consideration when designing network topologies that do not only have low-delay link paths but also low-power consumption. In this paper, we study different satellite constellation types and network typologies and propose a novel power-efficient topology. As such, we compare three common satellite architectures, namely; (i) the theoretical random constellation, the widely deployed (ii) Walker-Delta, and (iii) Walker-Star constellations. The comparison is performed based on both the power efficiency and end - to-end delay. The results show that the proposed algorithm outperforms long-haul ISL paths in terms of energy efficiency with only a slight hit to delay performance relative to the conventional ISL topology.

Recent satellite constellations are being deployed to serve massive numbers of wireless devices, especially targeting those located in rural and offshore settings. Accordingly, business models relying on data reported via wireless Internet-of-Things (IoT) networks can now easily utilize satellite constellations to expand their offerings. In this paper, we present an analytic framework for modeling the uplink performance of massive IoT-over-Satellite networks. The framework utilizes tools from stochastic geometry to model the satellites and the users as two random point processes enabling the development of a tractable analytic model for the uplink outage probability. Furthermore, the paper derives the expected normalized throughput and compares the results to Monte-Carlo simulations for intractable constellations such as the Walker models adopted by current satellite deployments. Comparisons show that random constellations provide a tractable lower bound to the performance and average throughput compared to Walker constellations. The analytic model can provide the fast estimation of the uplink performance aiding in designing the IoT-over-Satellite system.

The LoRa modulation scheme is becoming one of the most adopted Internet of Things wireless physical layer due to its ability to transmit data over long distances with low power requirements. Typical demodulation techniques for LoRa utilize variants of non-coherent Frequency Shift Keying demodulation. This paper aims to capitalize on the robustness of deep learning techniques, specifically by using convolutional neural networks to demodulate LoRa symbols. We achieve this by building a dataset consisting of emulated time-domain LoRa symbols across a range of channel impairments; namely, we examine additive white Gaussian noise together with carrier frequency offset and time offset. The presented results show an improvement when utilizing deep learning over typical non-coherent detection while performing very close to the optimal matched filter.

Spectrum scarcity has surfaced as a prominent concern in wireless radio communications with the emergence of new technologies over the past few years. As a result, there is a growing need for better understanding of the spectrum occupancy with newly emerging access technologies supporting the Internet of Things. In this article, we present a framework to capture and model the traffic behavior of short-time spectrum occupancy for Internet-of-Things (IoT) applications in the shared bands to determine the existing interference. The proposed capturing method utilizes a software-defined radio to monitor the short bursts of IoT transmissions by capturing the time-series data which is converted to power spectral density to extract the observed occupancy. Furthermore, we propose the use of an unsupervised machine learning technique to enhance conventionally implemented energy detection methods. Our experimental results show that the temporal and frequency behavior of the spectrum can be well captured using the combination of two models, namely, semi-Markov chains and a Poisson-distribution arrival rate. We conduct an extensive measurement campaign in different urban environments and incorporate the spatial effect on the IoT shared spectrum.