ABSTRACT
This paper presents the design and implementation of a low-noise amplifier (LNA) for millimeter-wave (mm-Wave) 5G wireless applications. The LNA was based on a common-emitter configuration with cascode amplifier topology using an IHP's 0.13 µm Silicon Germanium (SiGe) heterojunction bipolar transistor (HBT) whose f_T/f_MAX/gate-delay is 360/450 GHz/2.0 ps, utilizing transmission lines for simultaneous noise and input matching. A noise figure of 3.02-3.4 dB was obtained for the entire wide bandwidth from 20 to 44 GHz. The designed LNA exhibited a gain (S_21) greater than 20 dB across the 20-44 GHz frequency range and dissipated 9.6 mW power from a 1.2 V supply. The input reflection coefficient (S_11) and output reflection coefficient (S_22) were below -10 dB, and reverse isolation (S_12) was below -55 dB for the 20-44 GHz frequency band. The input 1 dB (P1dB) compression point of -18 dBm at 34.5 GHz was obtained. The proposed LNA occupies only a 0.715 mm2 area, with input and output RF (Radio Frequency) bond pads. To the authors' knowledge, this work evidences the lowest noise figure, lowest power consumption with reasonable highest gain, and highest bandwidth attained so far at this frequency band in any silicon-based technology.
ABSTRACT
The world is significantly affected by infectious coronavirus disease (covid-19). Timely prognosis and treatment are important to control the spread of this infection. Unreliable screening systems and limited number of clinical facilities are the major hurdles in controlling the spread of covid-19. Nowadays, many automated detection systems based on deep learning techniques using computed tomography (CT) images have been proposed to detect covid-19. However, these systems have the following drawbacks: (i) limited data problem poses a major hindrance to train the deep neural network model to provide accurate diagnosis, (ii) random choice of hyperparameters of Convolutional Neural Network (CNN) significantly affects the classification performance, since the hyperparameters have to be application dependent and, (iii) the generalization ability using CNN classification is usually not validated. To address the aforementioned issues, we propose two models: (i) based on a transfer learning approach, and (ii) using novel strategy to optimize the CNN hyperparameters using Whale optimization-based BAT algorithm + AdaBoost classifier built using dynamic ensemble selection techniques. According to our second method depending on the characteristics of test sample, the classifier is chosen, thereby reducing the risk of overfitting and simultaneously produced promising results. Our proposed methodologies are developed using 746 CT images. Our method obtained a sensitivity, specificity, accuracy, F-1 score, and precision of 0.98, 0.97, 0.98, 0.98, and 0.98, respectively with five-fold cross-validation strategy. Our developed prototype is ready to be tested with huge chest CT images database before its real-world application.
