• Journal of Biomedical Engineering Research
• /
• v.43 no.1
• /
• pp.45-51
• /
• 2022

The purpose of this study is to improve the classification accuracy compared to the existing InceptionV3 model by proposing a new model modified with the fully connected hierarchical structure of InceptionV3, which showed excellent performance in medical image classification. The data used for model training were trained after data augmentation on a total of 1026 chest X-ray images of patients diagnosed with normal heart and Cardiomegaly at Kyungpook National University Hospital. As a result of the experiment, the learning classification accuracy and loss of the InceptionV3 model were 99.57% and 1.42, and the accuracy and loss of the proposed model were 99.81% and 0.92. As a result of the classification performance evaluation for precision, recall, and F1 score of Inception V3, the precision of the normal heart was 78%, the recall rate was 100%, and the F1 score was 88. The classification accuracy for Cardiomegaly was 100%, the recall rate was 78%, and the F1 score was 88. On the other hand, in the case of the proposed model, the accuracy for a normal heart was 100%, the recall rate was 92%, and the F1 score was 96. The classification accuracy for Cardiomegaly was 95%, the recall rate was 100%, and the F1 score was 97. If the chest X-ray image for normal heart and Cardiomegaly can be classified using the model proposed based on the study results, better classification will be possible and the reliability of classification performance will gradually increase.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.28 no.9
• /
• pp.1117-1123
• /
• 2004

The characteristics of soot near the soot inception point for an ethene-air flame was carried out in a WSR (well-stirred reactor). The new sampling tool like the temperature controlled filter system was introduced to minimize the condensation during sampling. The new analysis tools applied include the real time size distribution analysis with the Nano-DMA, particle size by transmission electron microscopy, C/H analysis, g filter analysis, and thermogravimetric analysis using both non-oxidative and oxidative pyrolysis. The WSR can generate young soot particles that can be collected and examined to gain insight into inception. For the current conditions, soot does not form for ${\Phi}$=1.9, inception occurs at or before ${\Phi}$=2.0, and inception combined with soot surface growth and/or coagulation occurs for ${\Phi}$=2.1. The filter samples for ${\Phi}$=1.9 are composed of volatile compounds that evolve at relatively low temperatures when heated in the presence or absence of O$_2$. The samples collected from the WSR at ${\Phi}$=2.0 and ${\Phi}$=2.1 are precursor-like in morphology and size. They have higher C/H ratios and lower organic percentages than precursor particles, but they are clearly not fully carbonized soot. The WSR PAH distribution is similar to that in young soot from inverse flames.

• Proceedings of the KSME Conference
• /
• 2004.04a
• /
• pp.1298-1303
• /
• 2004

The characteristics of soot near the soot inception point for an ethene-air flame was carried out in a WSR (well-stirred reactor). The new sampling tool like the temperature controlled filter system was introduced to minimize the condensation during sampling. The new analysis tools applied include the real time size distribution analysis with the Nano-DMA, particle size by transmission electron microscopy, C/H analysis, g filter analysis, and thermogravimetric analysis using both non-oxidative and oxidative pyrolysis. The WSR can generate young soot particles that can be collected and examined to gain insight into inception. For the current conditions, soot does not form for ${\Phi}=1.9$, inception occurs at or before ${\Phi}=2.0$, and inception combined with soot surface growth and/or coagulation occurs for ${\Phi=2.1}$. The filter samples for ${\Phi}$=1.9 are composed of volatile compounds that evolve at relatively low temperatures when heated in the presence or absence of $O_2$. The samples collected from the WSR at ${\Phi}=2.0$ and ${\Phi}=2.1$ are precursor-like in morphology and size. They have higher C/H ratios and lower organic percentages than precursor particles, but they are clearly not fully carbonized soot. The WSR PAH distribution is similar to that in young soot from inverse flames.

• Proceedings of the Korean Society of Propulsion Engineers Conference
• /
• 2017.05a
• /
• pp.1077-1079
• /
• 2017

The cavitation in the turbopump inducer progresses from the inception to the critical point, and finally develops to a breakdown which sharply declined in head. In this paper, we evaluated characteristics and predicted empirical equations about the cavitation inception of a turbopump inducer. The empirical equation of the cavitation inception for the elliptical plate was relatively well predicted to the turbopump inducer. However, in case of the marine propeller, it showed a big difference due to Reynolds number under the operating point.

• Journal of Korea Multimedia Society
• /
• v.25 no.11
• /
• pp.1653-1671
• /
• 2022

Crop diseases affect crop production, more than 30 billion USD globally. We proposed a classification study of crop species and diseases using deep learning algorithms for corn, cucumber, pepper, and strawberry. Our study has three steps of species classification, disease detection, and disease classification, which is noteworthy for using captured images without additional processes. We designed deep learning approach of deep learning convolutional neural networks based on Mask R-CNN model to classify crop species. Inception and Resnet models were presented for disease detection and classification sequentially. For classification, we trained Mask R-CNN network and achieved loss value of 0.72 for crop species classification and segmentation. For disease detection, InceptionV3 and ResNet101-V2 models were trained for nodes of crop species on 1,500 images of normal and diseased labels, resulting in the accuracies of 0.984, 0.969, 0.956, and 0.962 for corn, cucumber, pepper, and strawberry by InceptionV3 model with higher accuracy and AUC. For disease classification, InceptionV3 and ResNet 101-V2 models were trained for nodes of crop species on 1,500 images of diseased label, resulting in the accuracies of 0.995 and 0.992 for corn and cucumber by ResNet101 with higher accuracy and AUC whereas 0.940 and 0.988 for pepper and strawberry by Inception.

• The KSFM Journal of Fluid Machinery
• /
• v.15 no.1
• /
• pp.52-57
• /
• 2012

Stall inception characteristics are researched to understand stall well. To realize different stall inception patterns, IGV stagger angle was changed. At design IGV stagger angle, spike, which is short length scale, is observed. Decreasing IGV stagger angle, spike changes to mode, which is long length scale, and further decreasing get multi cell. Compressor maps for each IGV stagger are shown to compare different stall inceptions. The characteristics of both spike and mode are confirmed in this experiment. Furthermore, transient from spike to mode is find. multi cell has 4cells and is little bit faster than mode. and multi cell shows 2nd, 3rd characteristics on compressor map.

• Fire Science and Engineering
• /
• v.16 no.4
• /
• pp.59-64
• /
• 2002

Investigation of flow characteristics on pressure loss and cavitations of the butterfly valve has been carried out. The pressure loss coefficient on opening angle of valve has been formulated by applying the Carnot's equations. Cavitations (such as cavitation Inception, super cavitation inception, cavitation damage inception, choking cavitation) have been predicted from the pressure loss coefficient of valve. The prediction of pressure loss and cavitation has been carried out change of the thickness ratio on opening angle of valve. The prediction data is utilize to necessary engineering data to develope of the butterfly valve.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.66 no.12
• /
• pp.1745-1750
• /
• 2017

Starting from the distribution transformer, the insulation oil for the oil immersed power transformer is being used to convert the vegetable oil from the existing mineral oil. Vegetable oil is better in temperature characteristics and insulation performance, is not toxic, and has better biodegradable characteristic than that of mineral oil. In order to investigate the corona inception voltage and dieclectic charateristics of the two insulating oils, three oil immersed transformers using mineral oil and vegetable oil were made and thermal cyclic aged. In this paper, the changes in the corona discharge inception voltage, chemical and electrical properties of the two sampled insulating oils from the transformers had been studied.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.3
• /
• pp.1450-1463
• /
• 2019

The problem towards crowd behavior recognition in a serious clustered scene is extremely challenged on account of variable scales with non-uniformity. This paper aims to propose a crowed behavior classification framework based on a transferring hybrid network blending 3D res-net with inception-v3. First, the 3D res-inception network is presented so as to learn the augmented visual feature of UCF 101. Then the target dataset is applied to fine-tune the network parameters in an attempt to classify the behavior of densely crowded scenes. Finally, a transferred entropy function is used to calculate the probability of multiple labels in accordance with these features. Experimental results show that the proposed method could greatly improve the accuracy of crowd behavior recognition and enhance the accuracy of multiple label classification.

• Journal of Internet Computing and Services
• /
• v.18 no.5
• /
• pp.61-67
• /
• 2017

In this paper we introduce two experimental results from classification of Instagram images and some valuable lessons from them. We have tried some experiments for evaluating the competitive power of Convolutional Neural Network(CNN) in classification of real social network images such as Instagram images. We used AlexNet and ResNet, which showed the most outstanding capabilities in ImageNet Large Scale Visual Recognition Challenge(ILSVRC) 2012 and 2015, respectively. And we used 240 Instagram images and 12 pre-defined categories for classifying social network images. Also, we performed fine-tuning using Inception V3 model, and compared those results. In the results of four cases of AlexNet, ResNet, Inception V3 and fine-tuned Inception V3, the Top-1 error rates were 49.58%, 40.42%, 30.42%, and 5.00%. And the Top-5 error rates were 35.42%, 25.00%, 20.83%, and 0.00% respectively.