1710 papers
This paper presents the design, machine learning-assisted optimization, and experimental validation of a 2.6 GHz single-element switched-beam antenna that utilizes a Random Forest algorithm to accurately predict beam direction and reflection coefficient, enabling reliable eight-direction beam switching for 5G sub-6 GHz applications.
This study integrates petrographic characterization, triaxial mechanical testing, and genetic algorithm optimization to quantify the anisotropic strain energy evolution and failure patterns of gneiss rock in the Chamoli region, demonstrating the method's effectiveness in predicting nonlinear strength and shear parameters for improved rock mass stability assessment.
This paper proposes an energy-aware framework for FPGA-based Wireless Sensor Networks that leverages Dynamic Partial Reconfiguration to dynamically adapt node assignments and maintain both security requirements and coverage sustainability, achieving up to 80% improvement in service duration without compromising cryptographic strength.
This paper utilizes a probabilistic framework and a database of 75 designs to demonstrate that vendor-announced timelines for Small Modular Reactor (SMR) First-of-a-Kind deployment are systematically overambitious, projecting a median of only 13 designs operational by 2035 and 24 to 48 by 2050, with near-term growth concentrated in China and Russia before shifting to OECD markets.
This study demonstrates that a machine learning framework using foot-mounted inertial sensors can accurately estimate continuous foot clearance trajectories across varying walking speeds, with performance influenced by walking speed, temporal representation, and sensor feature selection.
This paper presents the design and simulation of a high-capacity RoFSO system utilizing WDM-MUX, polarization methods, and optical amplifiers to achieve 10–20 Gbps data transmission over 50 km for 6G applications, demonstrating robust performance metrics like high Q-factors and low BER under clear weather conditions while highlighting performance degradation in adverse weather.
This paper presents a trim-constrained aero-propulsive framework for integrating twelve distributed electric ducted fans on a fixed-wing UAV, revealing that while the configuration significantly augments lift, it incurs substantial drag penalties and reduces elevator authority, ultimately identifying an aft-center-of-gravity position as the optimal compromise for vehicle feasibility.
This paper proposes a permutation-equivariant Transformer Deep Equilibrium Network (DERDEQN) that achieves O(1) parameter scaling and real-time inference for dispatching thousands of heterogeneous distributed energy resources by learning competitive equilibria and clearing prices through an unsupervised, label-free training process based on market-clearing and KKT conditions.
This paper presents an integrated IoT-based predictive maintenance framework that combines high-resolution electrical sensing, multivariate feature engineering, and a hybrid Prophet-LSTM deep learning model to effectively detect incipient faults and quantify energy inefficiencies in industrial electrical assets.
This paper proposes a Proximal Policy Optimization (PPO)-based control framework for load frequency management in renewable-integrated power systems that outperforms traditional and other deep reinforcement learning controllers by achieving significantly lower error rates and superior stability across diverse multi-scenario disturbances without requiring heuristic tuning.