Search Results (3)

This paper introduces a database-based design methodology aimed at optimizing a 26 GHz MIMO antenna system through machine learning (ML) techniques. The procedure is divided into two primary phases. Initially, a rectangular microstrip patch antenna is designed and enhanced using analytical models alongside ML algorithms that are trained on a detailed dataset of geometric parameters. This yields effective impedance matching (S11 < −45 dB) and a high gain (~6.64 dBi), which serve as the foundation for the MIMO structure. In the second phase, split ring resonator (SRR) configurations are integrated between the antenna elements to reduce mutual coupling. A specialized dataset, featuring varied dimensions of SRR, quantities of unit cells, and spatial placements, is utilized to train Random Forest models that forecast arrangements achieving optimal isolation (S21 < −40 dB) while maintaining low reflection losses. Additionally, a secondary dataset is constructed to investigate the best strategies for SRR placement, ensuring an optimal balance between isolation and return loss. The ultimate MIMO design is validated via comprehensive full-wave electromagnetic simulations and experimental measurements. The proposed system exhibits noteworthy performance enhancements, including an envelope correlation coefficient (ECC) < 0.005, diversity gain (DG) ≈ 9.99 dB, channel capacity loss (CCL) < 0.3 bits/s/Hz, total active reflection coefficient (TARC) < −30 dB, radiation efficiency exceeding 80%, and a maximum gain increase up to 10.22 dB. The close correlation between predicted and measured outcomes validates the effectiveness of the ML-driven approach in expediting antenna optimization for 5G and future applications. Full article

The proliferation of classification-capable artificial intelligence (AI) across a wide range of domains (e.g., agriculture, construction, etc.) has been allowed to optimize and complement several tasks, typically operationalized by humans. The computational training that allows providing such support is frequently hindered by various challenges related to datasets, including the scarcity of examples and imbalanced class distributions, which have detrimental effects on the production of accurate models. For a proper approach to these challenges, strategies smarter than the traditional brute force-based K-fold cross-validation or the naivety of hold-out are required, with the following main goals in mind: (1) carrying out one-shot, close-to-optimal data arrangements, accelerating conventional training optimization; and (2) aiming at maximizing the capacity of inference models to its fullest extent while relieving computational burden. To that end, in this paper, two image-based feature-aware dataset splitting approaches are proposed, hypothesizing a contribution towards attaining classification models that are closer to their full inference potential. Both rely on strategic image harvesting: while one of them hinges on weighted random selection out of a feature-based clusters set, the other involves a balanced picking process from a sorted list that stores data features’ distances to the centroid of a whole feature space. Comparative tests on datasets related to grapevine leaves phenotyping and bridge defects showcase promising results, highlighting a viable alternative to K-fold cross-validation and hold-out methods. Full article

With great significance in military and civilian applications, the topic of detecting small and densely arranged objects in wide-scale remote sensing imagery is still challenging nowadays. To solve this problem, we propose a novel effectively optimized one-stage network (NEOON). As a fully convolutional network, NEOON consists of four parts: Feature extraction, feature fusion, feature enhancement, and multi-scale detection. To extract effective features, the first part has implemented bottom-up and top-down coherent processing by taking successive down-sampling and up-sampling operations in conjunction with residual modules. The second part consolidates high-level and low-level features by adopting concatenation operations with subsequent convolutional operations to explicitly yield strong feature representation and semantic information. The third part is implemented by constructing a receptive field enhancement (RFE) module and incorporating it into the fore part of the network where the information of small objects exists. The final part is achieved by four detectors with different sensitivities accessing the fused features, all four parallel, to enable the network to make full use of information of objects in different scales. Besides, the Focal Loss is set to enable the cross entropy for classification to solve the tough problem of class imbalance in one-stage methods. In addition, we introduce the Soft-NMS to preserve accurate bounding boxes in the post-processing stage especially for densely arranged objects. Note that the split and merge strategy and multi-scale training strategy are employed in training. Thorough experiments are performed on ACS datasets constructed by us and NWPU VHR-10 datasets to evaluate the performance of NEOON. Specifically, 4.77% and 5.50% improvements in mAP and recall, respectively, on the ACS dataset as compared to YOLOv3 powerfully prove that NEOON can effectually improve the detection accuracy of small objects in remote sensing imagery. In addition, extensive experiments and comprehensive evaluations on the NWPU VHR-10 dataset with 10 classes have illustrated the superiority of NEOON in the extraction of spatial information of high-resolution remote sensing images. Full article