• Journal of Korea Multimedia Society
• /
• v.24 no.5
• /
• pp.695-700
• /
• 2021

The Faster RCNN-based shellfish recognition algorithm is introduced for shellfish recognition studies that currently do not have any deep learning-based algorithms in a practical setting. The original feature extraction module is replaced by DenseNet, which fuses multi-level feature data and optimises the NMS algorithm, network depth and merging method; overcoming the omission of shellfish overlap, multiple shellfish and insufficient light, effectively solving the problem of low shellfish classification accuracy. In the complexifier test environment, the test accuracy was improved by nearly 4%. Higher testing accuracy was achieved compared to the original testing algorithm. This provides favourable technical support for future applications of the improved Faster RCNN approach to seafood quality classification.

• Nuclear Engineering and Technology
• /
• v.53 no.2
• /
• pp.583-591
• /
• 2021

Various compositions of CeO₂-Ce₃Si₂ (0, 10, 30, 50, and 100 wt%Ce₃Si₂) composites were fabricated using conventional sintering and spark plasma sintering. Lower relative density, enhanced interdiffusion of oxygen and silicon, and silicide agglomerations from the congruent melting of Ce₃Si₂ at 1390 ℃ were only observed from conventionally-sintered pellets. Thermal conductivity of spark plasma sintered CeO₂-Ce₃Si₂ composites was calculated from the measured thermal diffusivity, specific heat, and density, which exhibited dense (>90 %TD) and homogeneous microstructure. The composite with 50 wt%Ce₃Si₂ exhibited 55% higher thermal conductivity than CeO₂ at 500 ℃, and 81% higher at 1000 ℃.

• The Journal of Korea Robotics Society
• /
• v.17 no.2
• /
• pp.133-141
• /
• 2022

This paper introduces model compression algorithms which make a deep neural network smaller and faster for embedded systems. The model compression algorithms can be largely categorized into pruning, quantization and knowledge distillation. In this study, gradual pruning, quantization aware training, and knowledge distillation which learns the activation boundary in the hidden layer of the teacher neural network are integrated. As a large deep neural network is compressed and accelerated by these algorithms, embedded computing boards can run the deep neural network much faster with less memory usage while preserving the reasonable accuracy. To evaluate the performance of the compressed neural networks, we evaluate the size, latency and accuracy of the deep neural network, DenseNet201, for image classification with CIFAR-10 dataset on the NVIDIA Jetson Xavier.

• International Journal of Computer Science & Network Security
• /
• v.22 no.4
• /
• pp.139-146
• /
• 2022

Wireless access technologies are emerging to enable high data rates for mobile users and novel applications that encompass both human and machine-type interactions. An essential approach to meet the rising demands on network capacity and offer high coverage for wireless users on upcoming fifth generation (5G) networks is heterogeneous networks (HetNets), which are generated by combining the installation of macro cells with a large number of densely distributed small cells Deployment in 5G architecture has several issues because to the rising complexity of network topology in 5G HetNets with many distinct base station types. Aside from the numerous benefits that dense small cell deployment delivers, it also introduces key mobility management issues such as frequent handover (HO), failures, delays and pingpong HO. This article investigates 5G HetNet mobility management in terms of radio resource control. This article also discusses the key challenges for 5G mobility management.

• Journal of Information Processing Systems
• /
• v.18 no.4
• /
• pp.480-488
• /
• 2022

Images of tobacco retail licenses have complex unstructured characteristics, which is an urgent technical problem in the robot process automation of tobacco marketing. In this paper, a novel recognition approach using a double attention mechanism is presented to realize the automatic recognition and information extraction from such images. First, we utilized a DenseNet network to extract the license information from the input tobacco retail license data. Second, bi-directional long short-term memory was used for coding and decoding using a continuous decoder integrating dual attention to realize the recognition and information extraction of tobacco retail license images without segmentation. Finally, several performance experiments were conducted using a largescale dataset of tobacco retail licenses. The experimental results show that the proposed approach achieves a correction accuracy of 98.36% on the ZY-LQ dataset, outperforming most existing methods.

• Korean Journal of Plant Tissue Culture
• /
• v.22 no.6
• /
• pp.323-327
• /
• 1995

This experiment was carried out to observe the origin and developmental pattern of somatic embryos of Oenanthe javanica ($B^{L}.$) DC. The experiment included observation of embryogenic cells and their development stages by light microscope, transmission electron microscope and scanning electron microscope. The embryogenic cells, which were smaller than non-embryogenic cells in size with expanded nucleus and dense cytoplasm. When stained with hematoxylin, the embryogenic cells were readily distinguished from the non-embryogenic cells of which cell walls were stained with safranin. It was observed at somatic embryos developed from single cells on the epidermis of developing embryos or in the surface or inside of embryogenic clumps by segmentation pattern. Observation with a transmission electron microscope revealed that the embryogenic cells had dense cytoplasm expanded nucleus, small vacuoles, large amyloplasts containing starch grains, and abundant organelles including lipid bodies. Under a scanning electron microscope, embryogenic callus was shown to consist of very smaller cells than non-embryogenic cells in an orderly arrangement and covered with a net-like structure, while the non-embryogenic callus consisted of large cells, irregular in size and arrangement, and covered with a gelatin-like material.

• Asian-Australasian Journal of Animal Sciences
• /
• v.30 no.10
• /
• pp.1396-1404
• /
• 2017

Objective: This study was determined the influence of virginiamycin supplementation on growth-performance and characteristics of digestion of cattle with decreasing dietary net energy value of the diet for maintenance ($NE_m$) from 2.22 to 2.10 Mcal/kg. Methods: Eighty crossbred beef steers ($298.2{\pm}6.3kg$) were used in a 152-d performance evaluation consisting of a 28-d adaptation period followed by a 124-d growing-finishing period. During the 124-d period steers were fed either a lesser energy dense (LED, $2.10Mcal/kg\;NE_m$) or higher energy dense (HED, $2.22Mcal/kg\;NE_m$) diet. Diets were fed with or without 28 mg/kg (dry matter [DM] basis) virginiamycin in a $2{\times}2$ factorial arrangement. Four Holstein steers ($170.4{\pm}5.6kg$) with cannulas in the rumen (3.8 cm internal diameter) and proximal duodenum were used in $4{\times}4$ Latin square experiment to study treatment effects on characteristics of digestion. Results: Neither diet energy density nor virginiamycin affected average daily gain (p>0.10). As expected, dry matter intake and gain efficiency were greater (p<0.01) for LED- than for HED-fed steers. Virginiamycin did not affect estimated net energy value of the LED diet. Virginiamycin increased estimated NE of the HED diet. During daylight hours when the temperature humidity index averaged $81.3{\pm}2.7$, virginiamycin decreased (p<0.05) ruminal temperature. Virginiamycin did not influence (p>0.10) ruminal or total tract digestion. Ruminal (p = 0.02) and total tract digestion (p<0.01) of organic matter, and digestible energy (p<0.01) were greater for HED vs LED. Ruminal microbial efficiency was lower (p<0.01) for HED vs LED diets. Conclusion: The positive effect of virginiamycin on growth performance of cattle is due to increased efficiency of energy utilization, as effects of virginiamycin on characteristics of digestion were not appreciable. Under conditions of high ambient temperature virginiamycin may reduce body temperature.

• The Journal of the Convergence on Culture Technology
• /
• v.6 no.4
• /
• pp.789-795
• /
• 2020

Many deaths have been reported due to the worldwide pandemic of COVID-19. In order to prevent the further spread of COVID-19, it is necessary to quickly and accurately read images of suspected patients and take appropriate measures. To this end, this paper introduces a deep learning-based COVID-19 chest X-ray reading technique that can assist in image reading by providing medical staff whether a patient is infected. First of all, in order to learn the reading model, a sufficient dataset must be secured, but the currently provided COVID-19 open dataset does not have enough image data to ensure the accuracy of learning. Therefore, we solved the image data number imbalance problem that degrades AI learning performance by using a Stacked Generative Adversarial Network(StackGAN++). Next, the DenseNet-based classification model was trained using the augmented data set to develop the reading model. This classification model is a model for binary classification of normal chest X-ray and COVID-19 chest X-ray, and the performance of the model was evaluated using part of the actual image data as test data. Finally, the reliability of the model was secured by presenting the basis for judging the presence or absence of disease in the input image using Grad-CAM, one of the explainable artificial intelligence called XAI.

• Journal of Korea Multimedia Society
• /
• v.25 no.8
• /
• pp.1224-1232
• /
• 2022

Whole body bone scan is the most frequently performed nuclear medicine imaging to evaluate bone metastasis in cancer patients. We evaluated the performance of a VGG16-based transfer learning classifier for bone scan images in which metastatic bone lesion was present. A total of 1,000 bone scans in 1,000 cancer patients (500 patients with bone metastasis, 500 patients without bone metastasis) were evaluated. Bone scans were labeled with abnormal/normal for bone metastasis using medical reports and image review. Subsequently, gradient-weighted class activation maps (Grad-CAMs) were generated for explainable AI. The proposed model showed AUROC 0.96 and F1-Score 0.90, indicating that it outperforms to VGG16, ResNet50, Xception, DenseNet121 and InceptionV3. Grad-CAM visualized that the proposed model focuses on hot uptakes, which are indicating active bone lesions, for classification of whole body bone scan images with bone metastases.

• ETRI Journal
• /
• v.46 no.2
• /
• pp.290-306
• /
• 2024

To treat the novel COronaVIrus Disease (COVID), comparatively fewer medicines have been approved. Due to the global pandemic status of COVID, several medicines are being developed to treat patients. The modern COVID medicines development process has various challenges, including predicting and detecting hazardous COVID medicine responses. Moreover, correctly predicting harmful COVID medicine reactions is essential for health safety. Significant developments in computational models in medicine development can make it possible to identify adverse COVID medicine reactions. Since the beginning of the COVID pandemic, there has been significant demand for developing COVID medicines. Therefore, this paper presents the transferlearning methodology and a multilabel convolutional neural network for COVID (MLCNN-COV) medicines development model to identify negative responses of COVID medicines. For analysis, a framework is proposed with five multilabel transfer-learning models, namely, MobileNetv2, ResNet50, VGG19, DenseNet201, and Inceptionv3, and an MLCNN-COV model is designed with an image augmentation (IA) technique and validated through experiments on the image of three-dimensional chemical conformer of 17 number of COVID medicines. The RGB color channel is utilized to represent the feature of the image, and image features are extracted by employing the Convolution2D and MaxPooling2D layer. The findings of the current MLCNN-COV are promising, and it can identify individual adverse reactions of medicines, with the accuracy ranging from 88.24% to 100%, which outperformed the transfer-learning model's performance. It shows that three-dimensional conformers adequately identify negative COVID medicine responses.