Sperm detection performance is particularly critical for sperm motility tracking. However, there are a large number of non-sperm objects, sperm occlusion and poorly detailed texture features in semen images, which directly affect the accuracy of sperm detection. To solve the problem of false detection and missed detection in sperm detection, a multi-sperm target detection model, Yolov5s-SA, with an SA attention mechanism is proposed based on the YOLOv5s algorithm. Firstly, a depthwise, separable convolution structure is used to replace the partial convolution of the backbone network, which can ensure stable precision and reduce the number of model parameters. Secondly, a new multi-scale feature fusion module is designed to enhance the perception of feature information to supplement the positional information and high-resolution of the deep feature map. Finally, the SA attention mechanism is integrated into the neck network before the output of the feature map to enhance the correlation between the feature map channels and improve the fine-grained feature fusion ability of YOLOv5s. Experimental results show that compared with various YOLO algorithms, the proposed algorithm improves the detection accuracy and speed to a certain extent. Compared with the YOLOv3, YOLOv3-spp, YOLOv5s and YOLOv5m models, the average accuracy increases by 18.1%, 15.2%, 6.9% and 1.9%, respectively. It can effectively reduce the missed detection of occluded sperm and achieve lightweight and efficient multi-sperm target detection.

This paper proposes a low-sidelobe wideband design methodology for leaky-wave antennas based on an Improved Discrete Mutation Particle Swarm Optimization (IMDPSO) algorithm. The approach addresses critical limitations in electromagnetic simulation co-design, including computational inefficiency, insufficient optimization accuracy, and challenges in balancing multi-objective optimization, thereby achieving co-optimization of low sidelobe levels and wideband characteristics. By introducing a non-inertial weight function, an asymmetric learning factor function, and a Gaussian-disturbance particle mutation function, an enhanced discrete particle swarm optimization algorithm is developed. This improved algorithm demonstrates superior global search capability, local optimum escape efficiency, and convergence speed compared to conventional discrete particle swarm optimization methods. Furthermore, a multi-objective IMDPSO framework is established by constructing a bandwidth optimization fitness function based on S11 curve data and a sidelobe-level optimization fitness function derived from gain curve analysis. To validate the methodology, an 11 GHz vehicular millimeter-wave antenna is optimized and experimentally verified. Results indicate significant improvements: the proposed method enhances convergence speed while expanding the relative bandwidth from 4.0% to 8.5% and reducing the maximum sidelobe level from 14.4 dB to 19.6 dB, confirming its feasibility.

A dual-branched Convolutional Neural Network integrated with hybrid training criteria is proposed for real-time multi-beam synthesis in planar uniform antenna arrays. For higher speed in dataset generation, pattern superposition method is introduced in this article, which significantly improves data generation speed (~0.7ms per each). With a new hybrid training strategy integrating both “Data-Driven Approximation” and “Physics-Informed Approximation” criteria, flexible training while maintaining model synthesis efficiency is achieved simultaneously. Based on approaches mentioned above, the proposed dual-branched convolutional neural network enables dynamic multi-objective balance between its two branch outputs, accomplishing amplitude-phase synthesis for antenna array design. In the numerical simulation, consistent sidelobe suppression (20~40dB) is demonstrated for dual-beam steering across 10°~20° off-axis angles, with high synthesis speeds (~0.05s per each) on suitable computing platforms. In comparison experiments, the proposed method outperforms typical population-based stochastic optimization algorithms and Deep Neuron Network structure in both synthesis efficiency and pattern regularity. The model's real-time capability is verified for beam reconfiguration scenarios requiring sub-second responses, suggesting a new pathway for physics-embedded deep learning in antenna array synthesis.

This letter proposed the Cryptogenic particle swarm optimization (CPSO) and a novel design methodology for multi-sense antennas. The TM10 mode with varying phase delays of the proposed antenna is implemented by incorporating two coupled lines, and the phase diversity of the TM10 modes enables the antenna to achieve orthogonal circular polarization across a few adjacent frequency bands. CPSO integrates the cryptogenic mechanism within particle swarm optimization (PSO) to direct the design of multi-sense antennas. When the antenna design process reaches local optimality, CPSO can offer a means to transition to a more optimal solution. The proposed antenna attains the impedance bandwidths of 128MHz (2.326GHz ∼2.454GHz) and 23MHz(2.541GHz∼2.564GHz), with the circular polarization operating bands of 2.354GHz∼2.369GHz (Left-handed circular polarization), 2.432GHz∼2.448GHz (Right-handed circular polarization), and 2.549GHz∼2.56GHz (Left-handed circular polarization), respectively. The frequency ratio between the highest and lowest operating bands is 1.08. This represents the inaugural implementation of multi-sense antennas.

A deep-learning-based antenna array synthesis method for varied aperture lengths is proposed in this article. Inspired by Natural Language Processing (NLP), a tri-branched Recurrent Neural Network (RNN) based on Long Short Term Memory (LSTM) layers and “encoder-decoder” structure is designed as the backbone architecture of the proposed model. To further enhance deep models' comprehension of physical scenarios, this article also proposes an improved word embedding method that allows continuous real-valued parameters to be mapped into high-dimensional vectors in a manner similar to individual vocabulary terms, while preserving their original “semantic” relationships. Based the approaches mentioned above, the proposed model is built and operates through an interactive way, similar to a chatbot. Once receiving main lobe direction and array element positions as inputs, it automatically generates amplitude-phase synthesis results that meet specified requirements while ensuring sidelobe levels are minimized to the greatest extent possible. In the numerical experiments, it shows that this method can generate patterns whose main lobe covers the range from 45° to 135° on non-uniform linear arrays with 15-30 isotropic elements, while controlling the side lobe level below 15 dB, effectively improving the directivity of the antenna array. Compared to genetic algorithms, particle swarm optimization and DNN, this method demonstrates significant advantages in both synthesis performance and computational efficiency, significantly reducing the training time while achieving better radiation pattern characteristics.