This work proposes and describes a deep learning-based approach utilizing recurrent neural networks (RNNs) for beam pattern synthesis considering uniform linear arrays. In this particular case, the deep neural network (DNN) learns from previously optimized radiation patterns as inputs and generates complex excitations as output. Beam patterns are optimized using a genetic algorithm during the training phase in order to reduce sidelobes and achieve high directivity. Idealized and test beam patterns are employed as inputs for the DNN, demonstrating their effectiveness in scenarios with high prediction complexity and closely spaced elements. Additionally, a comparative analysis is conducted among the three DNN architectures. Numerical experiments reveal improvements in performance when using the long short-term memory network (LSTM) compared to fully connected and convolutional neural networks.

In recent years, the recreational and commercial use of flight and driving simulators has become more popular. All these applications require the calculation of orientation in either two or three dimensions. Besides the Euler angles notation, other alternatives to represent rigid body rotations include axis-angle notation, homogeneous transformation matrices, and quaternions. All these methods involve transcendental functions in their calculations, which represents a disadvantage when these algorithms are implemented in hardware. The use of transcendental functions in software-based algorithms may not represent a significant disadvantage, but in hardware-based algorithms, the potential of rational models stands out. Generally, to calculate transcendental functions in hardware, it is necessary to utilize algorithms based on the CORDIC algorithm, which requires a significant amount of hardware resources (parallel) or the design of a more complex control unit (pipelined). This research presents a new procedure for model orientation using rational trigonometry and quaternion notation, avoiding trigonometric functions for calculations. We describe the orientation of a gimbal mechanism presented in many applications, from autonomous vehicles such as cars or drones to industrial manipulators. This research aims to compare the efficiency of a rational implementation to classical modeling using the techniques mentioned above. Furthermore, we simulate the models with software tools and propose a hardware architecture to implement our algorithms.

Real-time biosensing systems can interrogate the association between the analyte and the biorecognition element across time. Typically, the resulting data are preprocessed to offer valuable bioanalytical information obtained at a single optimal point of such a real-time response; for instance, a diagnosis of certain medical conditions can be established depending on a biomarker (analyte) concentration measured at an optimal time, that is, a threshold. Exploiting this conventional approach, we previously developed a nanophotonic immunoassay for bacterial vaginosis diagnosis exhibiting a clinical sensitivity and specificity of ca. 96.29% (n = 162). Herein, we demonstrate that a real-time biosensing platform assisted by artificial intelligence not only obviates biomarker concentration (i.e., a threshold) determination but also increases sensitivity and specificity in the targeted diagnostic, thereby reaching values of up to 100%.

This study presents a deep learning-based framework for beam pattern synthesis in optimized uniform linear antenna arrays, combining Differential Evolution–based pre-optimization with recurrent neural network (RNN) modeling. Radiation patterns are first generated to satisfy sidelobe suppression and directivity constraints and are then used to train recurrent models that learn the mapping between radiation patterns and complex excitation parameters. A formal mathematical formulation of the Simple RNN, Gated Recurrent Unit (GRU), and Long Short-Term Memory (LSTM) architectures is provided, together with a per–time-step computational cost analysis based on dominant matrix–vector multiplications. A comparative evaluation under identical training conditions shows that gated architectures significantly outperform the standard RNN. Although the LSTM achieves the lowest prediction errors, the GRU attains comparable performance with reduced structural complexity. Beam pattern synthesis experiments for unseen steering directions demonstrate accurate reconstruction of main lobe alignment, sidelobe levels (approximately −12 to −13 dB), and directivity values close to 8 dB. The floating-point operations (FLOPs) analysis indicates that the GRU requires fewer dominant operations per time step than the LSTM, potentially reducing computational cost and energy consumption in resource-constrained beamforming applications.