Reconfigurable Intelligent Surfaces (RISs) provide a promising avenue for enhancing performance and implementation efficiency in multiuser wireless communication systems by enabling the manipulation of radio wave prop...
详细信息
Reconfigurable Intelligent Surfaces (RISs) provide a promising avenue for enhancing performance and implementation efficiency in multiuser wireless communication systems by enabling the manipulation of radio wave propagation. In this paper, an Augmented jellyfish search optimization algorithm (AJFSOA) is specifically designed to optimize the achievable rate in RIS-equipped systems. AJFSOA distinguishes itself from previous approaches through the integration of a novel quasi-reflection operator, which aids in escaping local optima, and an adaptive neighborhood search mechanism that improves the algorithm's exploitation capabilities. These enhancements enable AJFSOA to efficiently refine promising solutions near the current best solution. Unlike prior research, our work explores two objective models: maximizing the average achievable rate for all users to ensure balanced system performance and maximizing the minimum achievable rate for individual users to improve worst-case scenarios. The comprehensive analysis demonstrates that AJFSOA effectively increases system capacity and supports a larger number of users simultaneously. An extensive testing is performed on communication systems with twenty and fifty users, comparing AJFSOA's performance against existing algorithms, including the standard JFSOA, Particle Swarm optimization (PSO), Ant Colony optimization (ACO), Genetic algorithm (GA) and Differential Evolution (DE). Results show that AJFSOA outperforms the other algorithms significantly, with improvements of 26.59%, 9.75%, 14.71%, 0.29% and 13.52% over JFSOA, PSO, ACO, GA and DE, respectively, for the first objective model, and 21.66%, 10.6%, .17.44%, 2.71% and 22.36% for the second model. These findings highlight the distinct advantages and superior performance of the presented AJFSOA in efficient optimizing multiuser wireless networks.
In this research, Attention Induced Multi-head Convolutional Neural Network Organization using MobileNetv1 Transfer Learning and COVID-19 Diagnosis using jellyfishsearchoptimization Process on Chest X-ray Images (C1...
详细信息
In this research, Attention Induced Multi-head Convolutional Neural Network Organization using MobileNetv1 Transfer Learning and COVID-19 Diagnosis using jellyfishsearchoptimization Process on Chest X-ray Images (C19D-AIMCNN-MNet-JSOA) is proposed. Initially, the input images are taken from chest X-ray dataset. Fairnessaware Collaborative Filtering (FCF) is utilized for eliminating the noise and also improves the X-ray image quality. Next, these pre-processed images are given to Adaptive and Concise Empirical Wavelet Transform (ACEWT) for extracting Grayscale statistic and Haralick Texture features. The extracted features are given into the Attention Induced Multi-head Convolutional Neural Network with MobileNetv1 (AIMCNN-MNet) which classifies the COVID-19, like Normal, COVID-19, SARS, Pneumocystis. In general, AIMCNN-MNet does not show any optimization adaption techniques to determine the ideal parameter to provide precise COVID-19 categorization. The proposed C19D-AIMCNN-MNet-JSOA model experimentally authenticated utilizing chest X-ray dataset in MATLAB and performance metrics including sensitivity, precision, F-Score, specificity, accuracy, Kappa, computation time, error rate used to examine the efficiency of proposed method. The performance of the C19D-AIMCNN-MNet-JSOA approach attains 25.99%, 20.34%, 30%, 19% and 20.35% high Precision, 25.43%, 29.53%, 22%, 28% and 25.31% lower computation Time and 15.249%, 25.491%, 10%, 31% and 13.98% higher RoC comparing with existing methods like novel hand-crafted fusion model founded on deep learning features COVID-19 diagnosis and organization using X-ray pictures of the chest (C19D-CNN-MLP), Multi-modal fusion of deep transfer learning founded COVID-19 diagnosis and organization utilizing chest x-ray images (C19D-MMFDTL), Recognition and organization of lung diseases for pneumonia and Covid-19 utilizing machine along deep learning methods (C19D-RNN-LSTM).
Incomplete closure around the spinal cord is the underlying cause of spina bifida, a birth condition. Multiple methods exist for identifying the presence of spina bifida. Ultrasound can be used to look for spinal axis...
详细信息
暂无评论