• Korean Journal of Radiology
• /
• v.23 no.10
• /
• pp.949-958
• /
• 2022

Objective: To investigate the feasibility of using a deep learning-based analysis of auscultation data to predict significant stenosis of arteriovenous fistulas (AVF) in patients undergoing hemodialysis requiring percutaneous transluminal angioplasty (PTA). Materials and Methods: Forty patients (24 male and 16 female; median age, 62.5 years) with dysfunctional native AVF were prospectively recruited. Digital sounds from the AVF shunt were recorded using a wireless electronic stethoscope before (pre-PTA) and after PTA (post-PTA), and the audio files were subsequently converted to mel spectrograms, which were used to construct various deep convolutional neural network (DCNN) models (DenseNet201, EfficientNetB5, and ResNet50). The performance of these models for diagnosing ≥ 50% AVF stenosis was assessed and compared. The ground truth for the presence of ≥ 50% AVF stenosis was obtained using digital subtraction angiography. Gradient-weighted class activation mapping (Grad-CAM) was used to produce visual explanations for DCNN model decisions. Results: Eighty audio files were obtained from the 40 recruited patients and pooled for the study. Mel spectrograms of "pre-PTA" shunt sounds showed patterns corresponding to abnormal high-pitched bruits with systolic accentuation observed in patients with stenotic AVF. The ResNet50 and EfficientNetB5 models yielded an area under the receiver operating characteristic curve of 0.99 and 0.98, respectively, at optimized epochs for predicting ≥ 50% AVF stenosis. However, Grad-CAM heatmaps revealed that only ResNet50 highlighted areas relevant to AVF stenosis in the mel spectrogram. Conclusion: Mel spectrogram-based DCNN models, particularly ResNet50, successfully predicted the presence of significant AVF stenosis requiring PTA in this feasibility study and may potentially be used in AVF surveillance.

• Management & Information Systems Review
• /
• v.36 no.4
• /
• pp.33-51
• /
• 2017

With the advent of 'The Forth Industrial Revolution' and the growing demand for quality of life due to economic growth, needs for the quality of medical services are increasing. Artificial intelligence has been introduced in the medical field, but it is rarely used in chronic skin diseases that directly affect the quality of life. Also, atopic dermatitis, a representative disease among chronic skin diseases, has a disadvantage in that it is difficult to make an objective diagnosis of the severity of lesions. The aim of this study is to establish an intelligent severity recognition model of atopic dermatitis for improving the quality of patient's life. For this, the following steps were performed. First, image data of patients with atopic dermatitis were collected from the Catholic University of Korea Seoul Saint Mary's Hospital. Refinement and labeling were performed on the collected image data to obtain training and verification data that suitable for the objective intelligent atopic dermatitis severity recognition model. Second, learning and verification of various CNN algorithms are performed to select an image recognition algorithm that suitable for the objective intelligent atopic dermatitis severity recognition model. Experimental results showed that 'ResNet V1 101' and 'ResNet V2 50' were measured the highest performance with Erythema and Excoriation over 90% accuracy, and 'VGG-NET' was measured 89% accuracy lower than the two lesions due to lack of training data. The proposed methodology demonstrates that the image recognition algorithm has high performance not only in the field of object recognition but also in the medical field requiring expert knowledge. In addition, this study is expected to be highly applicable in the field of atopic dermatitis due to it uses image data of actual atopic dermatitis patients.

• International Journal of Internet, Broadcasting and Communication
• /
• v.12 no.4
• /
• pp.83-92
• /
• 2020

A recent study to determine the fall is focused on analyzing fall motions using a recurrent neural network (RNN), and uses a deep learning approach to get good results for detecting human poses in 2D from a mono color image. In this paper, we investigated the improved detection method to estimate the position of the head and shoulder key points and the acceleration of position change using the skeletal key points information extracted using PoseNet from the image obtained from the 2D RGB low-cost camera, and to increase the accuracy of the fall judgment. In particular, we propose a fall detection method based on the characteristics of post-fall posture in the fall motion analysis method and on the velocity of human body skeleton key points change as well as the ratio change of body bounding box's width and height. The public data set was used to extract human skeletal features and to train deep learning, GRU, and as a result of an experiment to find a feature extraction method that can achieve high classification accuracy, the proposed method showed a 99.8% success rate in detecting falls more effectively than the conventional primitive skeletal data use method.

• International Commerce and Information Review
• /
• v.11 no.4
• /
• pp.229-259
• /
• 2009

Financial service in economy is same with neural net or vein net of human body. Moreover, every economic entity which has experienced global financial crisis in 2008 is realizing more importance and power of financial service, and is recognizing financial service as a part of new engine of growth for economic development. As global linkages relating financial service in the industry are deepened, we can expect that the economic interests between countries are more conflicted. Because financial service is regarded as critical factors in order to ensure future competitive advantage, more active change of financial service paradigm in Korea is required. The purpose of this paper is to analyze the paradigm of financial service in global business aspect, to prepare the global governance strategies about financial service, and to bring up some ideas for Korea's economic development after global financial crisis by intensifying the competitiveness of financial services. It is suggested that Korea should prepare the "Master Law for Financial Service" (provisional name) in advance as governance strategy for financial service. And not only establishing the financial risks prevention system and consumer's protection agency, but financial competitiveness strengthening actions will have to be included in governance strategy of financial service in Korea.

• International Journal of Precision Engineering and Manufacturing
• /
• v.4 no.1
• /
• pp.56-62
• /
• 2003

The objective of this study is to adjust the roll gap for the dimension accuracy of bar in hot bar rolling process considering roll wear. In this study hot bar rolling processes for round and oval passes have been investigated. In order to predict the roll wear, the wear model is reformulated as an incremental form and then wear depth of roll is calculated at each deformation step on contact area using the results of finite element analysis, such as relative sliding velocity and normal pressure at contact area. Archard's wear model was applied to predict the roll wear. To know the effects of thermal softening of DCI (Ductile Cast Iron) roll material according to operating conditions, high temperature micro hardness test is executed and a new wear model has been proposed by considering the thermal softening of DCI roll expressed in terms of the main tempering curve. The new technique developed in this study for adjusting roll gap can give more systematically and economically feasible means to improve the dimension accuracy of bar with full usefulness and generality.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.12
• /
• pp.11-19
• /
• 2014

In this paper, we design an intelligent agent system with the data mining module and information fusion module as the core components of the system and investigate the possibility for the medical expert system. In the data mining module, fuzzy neural network, OFUN-NET analyzes multi-view data and produces fuzzy cluster knowledge base. In the information fusion module and application module, they serve the diagnosis result with possibility degree and useful information for diagnosis, such as uncertainty decision status or detection of asymmetry. We also present the experiment results on the BI-RADS-based feature data set selected form DDSM benchmark database. They show higher classification accuracy than conventional methods and the feasibility of the system as a computer aided diagnosis system.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.3
• /
• pp.1104-1120
• /
• 2020

The chest X-rays are a common way to diagnose lung cancer or pneumonia. In particular, the finding of a lung nodule is the most important problem in the early detection of lung cancer. Recently, a lot of automatic diagnosis algorithms have been studied to find the lung nodules missed by doctors. The algorithms are typically based on segmentation network like U-Net. However, the occurrence of false positives that similar to lung nodules present outside the lungs can severely degrade performance. In this study, we propose a multi-task learning method that simultaneously learns the lung region and nodule-labeled data based on the prior knowledge that lung nodules exist only in the lung. The proposed method significantly reduces false positives outside the lung and improves the recognition rate of lung nodules to 83.8 F1 score compared to 66.6 F1 score of single task learning with U-net model. The experimental results on the JSRT public dataset demonstrate the effectiveness of the proposed method compared with other baseline methods.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 1996.06c
• /
• pp.773-779
• /
• 1996

Dried oak mushroom have complex and various visual features. Grading and sorting of dried oak mushrooms has been done by the human expert. Though actions involved in human grading looked simple, a decision making underneath the simple action comes from the result of the complex neural processing of the visual image. Through processing details involved in human visual recognition has not been fully investigated yet, it might say human can recognize objects via one of three ways such as extracting specific features or just image itself without extracting those features or in a combined manner. In most cases, extracting some special quantitative features from the camera image requires complex algorithms and processing of the gray level image requires the heavy computing load. This fact can be worse especially in dealing with nonuniform, irregular and fuzzy shaped agricultural products, resulting in poor performance because of the sensitiveness to the crisp criteria or specific ules set up by algorithms. Also restriction of the real time processing often forces to use binary segmentation but in that case some important information of the object can be lost. In this paper, the neuro net based real time recognition algorithm was proposed without extracting any visual feature but using only the directly captured raw gray images. Specially formated adaptable size of grids was proposed for the network input. The compensation of illumination was also done to accomodate the variable lighting environment. The proposed grading scheme showed very successful results.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.10a
• /
• pp.201-202
• /
• 2018

In this paper, a dog breed image provided by Dataset of existing ImageNet and Oxford-IIIT Pet Image is combined with a dog breed image obtained through data mining on Internet and a random-label is added. this paper introduces to recognize 122 classes of dog breeds and 1 class that is not dog breeds. The recognition rate of dog breeds using both conventional DB and collection DB was improved 1.5% over Top-1 compared to recognition rate of dog breeds using only existing DB. The image recognition rate about non-dog image, was 93% recognition rate in case of 10000 random DBs.

• Journal of Information Processing Systems
• /
• v.17 no.4
• /
• pp.787-800
• /
• 2021

Three-dimensional (3D) object classification tasks using point clouds are widely used in 3D modeling, face recognition, and robotic missions. However, processing raw point clouds directly is problematic for a traditional convolutional network due to the irregular data format of point clouds. This paper proposes a pointwise convolution neural network (CNN) structure that can process point cloud data directly without preprocessing. First, a 2D convolutional layer is introduced to percept coordinate information of each point. Then, multiple 2D convolutional layers and a global max pooling layer are applied to extract global features. Finally, based on the extracted features, fully connected layers predict the class labels of objects. We evaluated the proposed pointwise CNN structure on the ModelNet10 dataset. The proposed structure obtained higher accuracy compared to the existing methods. Experiments using the ModelNet10 dataset also prove that the difference in the point number of point clouds does not significantly influence on the proposed pointwise CNN structure.