• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.42 no.6 s.336
• /
• pp.67-74
• /
• 2005

In this paper, high LO-RF isolation W-band MIMIC single-balanced mixer was designed and fabricated using a branch line coupler and a $\lambda$/4 transmission line. The simulation results of the designed 94 GHz balun show return loss of -27.9 dB, coupling of -4.26 dB, and thru of -3.77 dB at 94 GHz, respectively. The isolation and phase difference were 23.5 dB and $180.2^{\circ}$ at 94 GHz. The W-band MIMIC single-balanced mixer was designed using the 0.1 $\mu$m InGaAs/InAlAs/GaAs Metamorphic HEMT diode. The fabricated MHEMT was obtained the cut-off frequency(fT) of 189 GHz and the maximum oscillation frequency(fmax) of 334 GHz. The designed MIMIC single-balanced mixer was fabricated using 0.1 $\mu$m MHEMT MIMIC Process. From the measurement, the conversion loss of the single-balanced mixer was 23.1 dB at an LO power of 10 dBm. Pl dB(1 dB compression point) of input and output were 10 dBm and -13.9 dBm respectively. The LO-RF isolations of single-balanced mixer was obtained 45.5 dB at 94.19 GHz. We obtained in this study a higher LO-RF isolation compared to some other balanced mixers in millimeter-wave frequencies.

• Journal of IKEEE
• /
• v.25 no.3
• /
• pp.493-500
• /
• 2021

In this paper, we propose the development of deep learning structure to improve quality of polygonal containers. The deep learning structure consists of a convolution layer, a bottleneck layer, a fully connect layer, and a softmax layer. The convolution layer is a layer that obtains a feature image by performing a convolution 3x3 operation on the input image or the feature image of the previous layer with several feature filters. The bottleneck layer selects only the optimal features among the features on the feature image extracted through the convolution layer, reduces the channel to a convolution 1x1 ReLU, and performs a convolution 3x3 ReLU. The global average pooling operation performed after going through the bottleneck layer reduces the size of the feature image by selecting only the optimal features among the features of the feature image extracted through the convolution layer. The fully connect layer outputs the output data through 6 fully connect layers. The softmax layer multiplies and multiplies the value between the value of the input layer node and the target node to be calculated, and converts it into a value between 0 and 1 through an activation function. After the learning is completed, the recognition process classifies non-circular glass bottles by performing image acquisition using a camera, measuring position detection, and non-circular glass bottle classification using deep learning as in the learning process. In order to evaluate the performance of the deep learning structure to improve quality of polygonal containers, as a result of an experiment at an authorized testing institute, it was calculated to be at the same level as the world's highest level with 99% good/defective discrimination accuracy. Inspection time averaged 1.7 seconds, which was calculated within the operating time standards of production processes using non-circular machine vision systems. Therefore, the effectiveness of the performance of the deep learning structure to improve quality of polygonal containers proposed in this paper was proven.