In post-disaster environments, telecommunication infrastructure is often disrupted due to damage in power and communication lines, resulting in reduced wireless connectivity. This study investigates an External Rescue Publisher (ERP) system to mitigate communication disconnectivity in a simulated post-earthquake indoor environment. A ray-tracing-based simulation using a computer-aided design model was conducted in a typical office setting comprising 30 room scenarios (15 corner, 15 non-corner) across three Philippine Institute of Volcanology and Seismology (PHIVOLCS) Earthquake Intensity Levels (6, 7, and 8) and three subscriber-to-publisher cardinalities (1:1, 1:3, 1:5), yielding 90 simulation runs. Under the baseline in-room ceiling publisher, evaluated across 150 unique subscriber positions at 1:5 cardinality, only 114 nodes (76.0%) satisfied the −91 dBm receiver sensitivity threshold. In contrast, 36 nodes (24.0%) fell below it, with failed nodes exhibiting a median received power of −100.6 dBm against an all-node mean of −80.8 dBm. Failure rates increased with debris severity, from 18% at Intensity Level 6 to 34% at Level 8, and were marginally higher in corner rooms (25%) than in non-corner rooms (23%). Repositioning the ERP outside the room restored connectivity in 57% of affected rooms at nominal transmit power alone, with the remainder requiring incremental power increases of 10–30 dBm. Overall, ERP intervention restored all 36 previously disconnected nodes to at least −91 dBm, a 100% recovery rate, with a median power gain of 21.4 dBm. Power Delay Profile and Power Angular Profile analysis further showed that below-threshold subscribers consistently exhibited smaller delay and angular spreads, indicating fewer resolvable multipath components.
The rapid deployment of 5G mobile communications has drastically increased the energy consumption of radio access networks, and Base Stations (BSs) account for 60%–80% of network energy consumption. This work presents a low-complexity predictive base station sleep mode framework based on Long Short-Term Memory (LSTM) traffic forecasting and a threshold-based control loop. It is based on proactive forecasting that is able to automatically transition BSs to sleep mode during low-demand state transitions in the predicted low-demand periods of the network, thereby minimizing frequent state-switching overhead and extending low-power intervals. Based on the real-world Telecom Italia Mobile Big Data Challenge data set (Milan and Trentino), our framework realized energy savings of up to 45.8% over the always-on baseline and 32.0% over the reactive baseline. Most importantly, our system does not breach Quality of Experience (QoE) service at the optimal 100 Mbps speed, and it requires much less computational effort than state-of-the-art reinforcement learning structures. A multi-objective sensitivity analysis presents the Pareto front to capture energy efficiency and service reliability. These results indicate that the lightweight predictive engineering frameworks can be a very practical and scalable way to manage the green 5G networks.
This paper presents a fully learned neural network surrogate of the Advanced Encryption Standard (AES) encryption algorithm under any oracle-provided key. Each round is split into three learned modules—ShiftRows-SubBytes, MixColumns, and AddRoundKey—with the round key given as input so one model handles arbitrary keys. Trained on fewer than 50,000 samples, the surrogate empirically attains perfect bit accuracy with zero observed errors over millions of unseen evaluations, without overfitting. Inspecting the models reveals behaviour atypical of deep learning: accuracy drops with depth, hinges on a sharp hidden-dimension threshold, and rests on near-binary sparse weights that collapse under pruning. As an exact, differentiable model of AES, the surrogate provides an empirical baseline for gradient-based and surrogate-assisted analysis of cryptographic primitives.
Accurate and early prediction of Cardiovascular Disease (CVD) plays an important role in improving patient survival and enabling timely preventive or therapeutic interventions. In this study, we propose an enhanced Crow Search Algorithm (eCSA) that integrates feature selection and hyperparameter optimization into a unified framework to improve the performance of a Bidirectional Long Short-Term Memory (Bi-LSTM) based heart disease prediction network. By employing a hybrid binary-continuous search strategy, the proposed eCSA jointly identifies discriminative features and optimizes Bi-LSTM hyperparameters, resulting in improved predictive performance and enhanced feature-level interpretability. Experimental evaluations were conducted on two benchmark datasets, namely the Cleveland Heart Disease dataset and the Framingham Heart Study dataset, under multiple train-test split conditions (80:20 and 70:30). Comparative analysis against state-of-the-art approaches, including Stochastic Configuration Network–Deep Bidirectional Long Short-Term Memory (SCN-Deep Bi-LSTM), Fitness-based Horse Optimization–Bidirectional Long Short-Term Memory (FHO-Bi-LSTM), Quantum Hybrid Deep Network (QHDN), and Convolutional Transformer Network (CTN-Trans), demonstrated that the proposed eCSA-BiLSTM model consistently outperformed competing methods across multiple evaluation metrics. Performance was assessed using accuracy, macro-averaged F1-Score (Macro-F1), precision, recall, Matthews Correlation Coefficient (MCC), and Area Under the Receiver Operating Characteristic Curve (AUC-ROC). The proposed model achieved an accuracy of up to 0.95 on the Cleveland dataset and 0.91 on the Framingham dataset, while maintaining stable and consistent performance across stratified 5-fold cross-validation and repeated train–test split experiments.
In this paper, we present a comprehensive approach for depth map completion using a variable pipeline model. The pipeline is designed to be flexible, and its structure is dynamically determined during the training phase by minimizing a fitness function. To achieve this objective, we used the Particle Swarm Optimization (PSO) technique, which efficiently ex-plores the solution space to optimize key parameters. The pipeline itself consists of three main stages: a convolutional stage (Lab Convolution), an Interpolation Model (IM), and a post-Convolutional Stage (SC2). During training, our model automatically adjusts several aspects, including the selection of filter parameters, interpolator settings, and the number of filters used at each stage. Moreover, the pipeline is capable of interchanging the execution order between the stages, either processing in the sequence of Lab Convolution-IM-SC2 or SC2-IM-Lab Convolution. This flexible structure allows for the discovery of better configurations that significantly im-prove the performance of depth map completion tasks. Our approach demonstrates superior results by adapting to the specific characteristics of the input data.
