Detection of malignant skin lesions is important for early and accurate diagnosis of skin cancer. In this work, a hybrid method for malignant lesion detection from dermoscopy images is proposed. The method combines the feature extraction process of convolutional neural networks (CNN) with an ensemble learner called stacked cross-validation (CV). The features extracted by three different CNN architectures, namely, ResNet50, Xception, and VGG16 are used for training of four different baseline classifiers, which are support vector machines, k-nearest neighbors, artificial neural networks, and random forests. The stacked outputs of these classifiers are used to train a logistic regression model as a meta-classifier. The performance of the proposed method is compared with the baseline classifiers trained individually as well as AdaBoost classifier, another ensemble learner. Feature extraction with Xception architecture, outperforms all other benchmark models by achieving scores of 0.909, 0.896, 0.886, and 0.917 for accuracy, F1-score, sensitivity, and AUC, respectively.
22 March 2023 in Multimedia Tools and Applications
Fifth-generation (5G) networks are facing critical security challenges in device authentication for massive Internet of Things deployments while preserving privacy. Traditional federated learning approaches depend on the computationally expensive homomorphic encryption to protect model gradients, resulting in substantial latency and communication overhead, leading to impractical energy consumption for resource-constrained 5G devices. This paper proposes Zero-Knowledge Federated Learning (ZK-FL), eliminating homomorphic encryption by enabling devices to prove model correctness without revealing gradients. Our approach integrates zero-knowledge proofs with FL updates, where each device generates a proof , demonstrating computational integrity. The experimental results from 10,000 authentication attempts demonstrate ZK-FL achieves 78.4 ms average authentication latency versus 342.5 ms for homomorphic encryption-based FL (77% reduction), proof sizes of 0.128 kB versus 512 kB (99.97% reduction), and energy consumption of 284.5 mJ versus 6525 mJ (95% reduction), while maintaining 99.3% authentication success rate with formal privacy guarantees. These results demonstrate ZK-FL enables practical privacy-preserving authentication for massive-scale 5G deployment.
25 December 2024 in Edelweiss Applied Science and Technology
This study investigates the influence of various environmental factors, particularly temperature, relative humidity, smoke, and dust particles, on the optical output power (P) of a 650 nm semiconductor laser. The effects of environmental factors on beam transmission are experimentally investigated with embedded messages and without. The experiments are conducted with a laser under different environmental factors to simulate typical operating conditions for optical devices. The results show that the transmitted signal with the message gradually decreases in P from 317.5 µW to 255.2 µW with increasing temperature from 28 °C to 55 °C. When the relative humidity increases from 10% to 80%, the P decreases from 245.3 µW to 67.5 µW similar to the case of the temperature effect. However, with the massage scenario humidity less affected the laser signal. Furthermore, when measuring the P at a smoke concentration of 182 ppm to 268 ppm, its value decreases from 305.4 µW to 54.4 µW, which shows less effect than temperature and humidity. The dust density used in the channel is 8.57 mg/m³ to 208.44 mg/m³ to simulate different amounts of airborne particles found in various environments to study their effect on the signal. The power signal has decreased dramatically as the dust concentration increases, with and without massage. As observed from the results, smoke concentration has a minimal impact compared to other factors, temperature fluctuations, humidity, and dust density. These results give useful information for applications that used transmitting data under similar environmental conditions, making this work suitable for providing insights into different atmospheric conditions.
The proliferation of Unmanned Aerial Vehicles (UAVs) in various applications has created a pressing need for robust and efficient communication systems. Fifth-generation (5G) networks can support UAV connectivity through high bandwidth and low-latency communication; however, rapid three-dimensional UAV mobility creates handover-management challenges that can increase signalling overhead, service interruption, and Quality of Service (QoS) degradation. This paper presents an integrated framework that combines LSTM-based multi-UAV trajectory prediction with proactive handover optimization using an Advantage Actor–Critic (A2C) Deep Reinforcement Learning (DRL) agent. The LSTM predictor is evaluated on a real-world UAV trajectory dataset and reports a root mean square error (RMSE) of 4.37 m over a 5 s prediction horizon after conversion to a local East–North–Up coordinate frame. A lightweight simulation-level coordination mechanism is included to reduce simultaneous target-cell contention among multiple UAVs; it is not claimed as a new standardized 3GPP signalling procedure. Handover performance is evaluated by replaying 180 held-out flight trajectories in a controlled 5G simulation across ten independent random seeds. Under these stated assumptions, the proposed framework achieves a handover success rate of %, an average SINR of dB, a handover delay of ms, and a handover frequency of HOs/min, outperforming the tuned 3GPP A3, reactive SINR, and CASH baselines in the reported simulation results (Wilcoxon signed-rank test, , Bonferroni-corrected). The experimental setup is described in detail to support methodological transparency and facilitate future replication, but the handover results should be interpreted as simulation-based evidence rather than live-network validation.
Digital financial inclusion (DFI) has become a central topic in financial inclusion research because digital payments, mobile money, internet banking, and platform-based finance can reduce access barriers and expand formal financial participation. Prior studies have documented the development relevance of financial inclusion and have constructed multidimensional financial inclusion and DFI indices, often using PCA and related composite-indicator methods. A remaining measurement gap concerns the equal observability of different digital-finance architectures within a common cross-country indicator set. This study addresses that gap by analyzing an existing PCA-based DFI score for 40 Organisation of Islamic Cooperation (OIC) countries over 2015–2024 through a channel-observability framework. The objective is to examine whether the observed DFI ranking is captured more directly through mobile-money indicators than through the available infrastructure-based representation of bank-led digital finance. The analysis decomposes the six available indicators into a bank-led visibility proxy, based on internet penetration and ATM density, and a mobile-money visibility proxy, based on mobile agents, mobile accounts, mobile transaction volume, and transaction value relative to GDP. The OIC-wide mean DFI score increased from 11.31 in 2015 to 31.24 in 2024, while dispersion widened and the 2015 and 2024 top-ten country groups had zero overlap. The channel diagnostics show that the highest observed DFI scores are concentrated among countries whose digital-finance activity is directly recorded through mobile-money indicators, whereas several financially advanced economies are visible mainly through the bank-led infrastructure proxy. Zero-coded mobile-money observations are interpreted as indicator-visibility signals for the standalone mobile-money channel and considered separately from broader digital-finance activity. The Random Forest analysis functions as a bounded internal sensitivity audit of the existing six-indicator score and shows that mobile-money transaction variables carry the largest within-score explanatory weight. The theoretical contribution is to frame DFI measurement as an architecture-dependent observability problem rather than only as a weighting problem. The practical implication is that cross-country DFI rankings should be interpreted together with channel diagnostics, especially when bank-led digital services such as mobile banking, card payments, POS transactions, QR payments, and instant-payment systems are outside the balanced indicator set.