• 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.

• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.57-73
• /
• 2021

Maintenance and prevention of failure through anomaly detection of ICT infrastructure is becoming important. System monitoring data is multidimensional time series data. When we deal with multidimensional time series data, we have difficulty in considering both characteristics of multidimensional data and characteristics of time series data. When dealing with multidimensional data, correlation between variables should be considered. Existing methods such as probability and linear base, distance base, etc. are degraded due to limitations called the curse of dimensions. In addition, time series data is preprocessed by applying sliding window technique and time series decomposition for self-correlation analysis. These techniques are the cause of increasing the dimension of data, so it is necessary to supplement them. The anomaly detection field is an old research field, and statistical methods and regression analysis were used in the early days. Currently, there are active studies to apply machine learning and artificial neural network technology to this field. Statistically based methods are difficult to apply when data is non-homogeneous, and do not detect local outliers well. The regression analysis method compares the predictive value and the actual value after learning the regression formula based on the parametric statistics and it detects abnormality. Anomaly detection using regression analysis has the disadvantage that the performance is lowered when the model is not solid and the noise or outliers of the data are included. There is a restriction that learning data with noise or outliers should be used. The autoencoder using artificial neural networks is learned to output as similar as possible to input data. It has many advantages compared to existing probability and linear model, cluster analysis, and map learning. It can be applied to data that does not satisfy probability distribution or linear assumption. In addition, it is possible to learn non-mapping without label data for teaching. However, there is a limitation of local outlier identification of multidimensional data in anomaly detection, and there is a problem that the dimension of data is greatly increased due to the characteristics of time series data. In this study, we propose a CMAE (Conditional Multimodal Autoencoder) that enhances the performance of anomaly detection by considering local outliers and time series characteristics. First, we applied Multimodal Autoencoder (MAE) to improve the limitations of local outlier identification of multidimensional data. Multimodals are commonly used to learn different types of inputs, such as voice and image. The different modal shares the bottleneck effect of Autoencoder and it learns correlation. In addition, CAE (Conditional Autoencoder) was used to learn the characteristics of time series data effectively without increasing the dimension of data. In general, conditional input mainly uses category variables, but in this study, time was used as a condition to learn periodicity. The CMAE model proposed in this paper was verified by comparing with the Unimodal Autoencoder (UAE) and Multi-modal Autoencoder (MAE). The restoration performance of Autoencoder for 41 variables was confirmed in the proposed model and the comparison model. The restoration performance is different by variables, and the restoration is normally well operated because the loss value is small for Memory, Disk, and Network modals in all three Autoencoder models. The process modal did not show a significant difference in all three models, and the CPU modal showed excellent performance in CMAE. ROC curve was prepared for the evaluation of anomaly detection performance in the proposed model and the comparison model, and AUC, accuracy, precision, recall, and F1-score were compared. In all indicators, the performance was shown in the order of CMAE, MAE, and AE. Especially, the reproduction rate was 0.9828 for CMAE, which can be confirmed to detect almost most of the abnormalities. The accuracy of the model was also improved and 87.12%, and the F1-score was 0.8883, which is considered to be suitable for anomaly detection. In practical aspect, the proposed model has an additional advantage in addition to performance improvement. The use of techniques such as time series decomposition and sliding windows has the disadvantage of managing unnecessary procedures; and their dimensional increase can cause a decrease in the computational speed in inference.The proposed model has characteristics that are easy to apply to practical tasks such as inference speed and model management.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.21 no.3
• /
• pp.175-186
• /
• 2019

Efforts have been made to introduce the climate smart agriculture (CSA) for adaptation to future climate conditions, which would require collection and management of site specific meteorological data. The objectives of this study were to identify requirements for construction of agricultural meteorology information service system (AMISS) using technologies that lead to the fourth industrial revolution, e.g., internet of things (IoT), artificial intelligence, and cloud computing. The IoT sensors that require low cost and low operating current would be useful to organize wireless sensor network (WSN) for collection and analysis of weather measurement data, which would help assessment of productivity for an agricultural ecosystem. It would be recommended to extend the spatial extent of the WSN to a rural community, which would benefit a greater number of farms. It is preferred to create the big data for agricultural meteorology in order to produce and evaluate the site specific data in rural areas. The digital climate map can be improved using artificial intelligence such as deep neural networks. Furthermore, cloud computing and fog computing would help reduce costs and enhance the user experience of the AMISS. In addition, it would be advantageous to combine environmental data and farm management data, e.g., price data for the produce of interest. It would also be needed to develop a mobile application whose user interface could meet the needs of stakeholders. These fourth industrial revolution technologies would facilitate the development of the AMISS and wide application of the CSA.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.11 no.3
• /
• pp.1-15
• /
• 2016

This study has analyzed predication capabilities leveraging multi-variate model, logistic regression model, and artificial neural network model based on financial information of medium-small sized companies list in KOSDAQ. 83 delisted companies from 2009 to 2012 and 83 normal companies, i.e. 166 firms in total were sampled for the analysis. Modelling with training data was mobilized for 100 companies inlcuding 50 delisted ones and 50 normal ones at random out of the 166 companies. The rest of samples, 66 companies, were used to verify accuracies of the models. Each model was designed by carrying out T-test with 79 financial ratios for the last 5 years and identifying 9 significant variables. T-test has shown that financial profitability variables were major variables to predict a financial risk at an early stage, and financial stability variables and financial cashflow variables were identified as additional significant variables at a later stage of insolvency. When predication capabilities of the models were compared, for training data, a logistic regression model exhibited the highest accuracy while for test data, the artificial neural networks model provided the most accurate results. There are differences between the previous researches and this study as follows. Firstly, this study considered a time-series aspect in light of the fact that failure proceeds gradually. Secondly, while previous studies constructed a multivariate discriminant model ignoring normality, this study has reviewed the regularity of the independent variables, and performed comparisons with the other models. Policy implications of this study is that the reliability for the disclosure documents is important because the simptoms of firm's fail woule be shown on financial statements according to this paper. Therefore institutional arragements for restraing moral laxity from accounting firms or its workers should be strengthened.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.3
• /
• pp.101-108
• /
• 2020

Since the performance of deep learning techniques has recently been proven in the field of image processing, there are many attempts to perform classification, analysis, and detection of images using such techniques in various fields. Among them, the expectation of medical image analysis software, which can serve as a medical diagnostic assistant, is increasing. In this study, we are attention to the capsule endoscope image, which has a large data set and takes a long time to judge. The purpose of this paper is to distinguish the gastrointestinal landmarks and to estimate the gastrointestinal transition location that are common to all patients in the judging of capsule endoscopy and take a lot of time. To do this, we designed CNN-based Classifier that can identify gastrointestinal landmarks, and used it to estimate the gastrointestinal transition location by filtering the results. Then, we estimate gastrointestinal transition location about seven of eight patients entered the suspected gastrointestinal transition area. In the case of change from the stomach to the small intestine(pylorus), and change from the small intestine to the large intestine(ileocecal valve), we can check all eight patients were found to be in the suspected gastrointestinal transition area. we can found suspected gastrointestinal transition area in the range of 100 frames, and if the reader plays images at 10 frames per second, the gastrointestinal transition could be found in 10 seconds.

• Journal of IKEEE
• /
• v.22 no.1
• /
• pp.162-167
• /
• 2018

In this paper, we propose a method to classify radar signals according to the jamming technique by applying the machine learning to parameter data extracted from received radar signals. In the present army, the radar signal is classified according to the type of threat based on the library of the radar signal parameters mostly built by the preliminary investigation. However, since radar technology is continuously evolving and diversifying, it can not properly classify signals when applying this method to new threats or threat types that do not exist in existing libraries, thus limiting the choice of appropriate jamming techniques. Therefore, it is necessary to classify the signals so that the optimal jamming technique can be selected using only the parameter data of the radar signal that is different from the method using the existing threat library. In this study, we propose a method based on machine learning to cope with new threat signal form. The method classifies the signal corresponding the new jamming method for the new threat signal by learning the classifier composed of the hidden Markov model and the neural network using the existing library data.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.8
• /
• pp.530-536
• /
• 2020

The use of minutiae by fingerprint readers is robust against presentation attacks, but one weakness is that the mismatch rate is high. Therefore, minutiae tend to be used with skeleton images. There have been many studies on security vulnerabilities in the characteristics of minutiae, but vulnerability studies on the skeleton are weak, so this study attempts to analyze the vulnerability of presentation attacks against the skeleton. To this end, we propose a method based on the skeleton to recover the original fingerprint using a learning algorithm. The proposed method includes a new learning model, Pix2Pix, which adds a latent vector to the existing Pix2Pix model, thereby generating a natural fingerprint. In the experimental results, the original fingerprint is restored using the proposed machine learning, and then, the restored fingerprint is the input for the fingerprint reader in order to achieve a good recognition rate. Thus, this study verifies that fingerprint readers using the skeleton are vulnerable to presentation attacks. The approach presented in this paper is expected to be useful in a variety of applications concerning fingerprint restoration, video security, and biometrics.

• Journal of Internet Computing and Services
• /
• v.19 no.5
• /
• pp.21-31
• /
• 2018

Cyber penetration attacks can not only damage cyber space but can attack entire infrastructure such as electricity, gas, water, and nuclear power, which can cause enormous damage to the lives of the people. Also, cyber space has already been defined as the fifth battlefield, and strategic responses are very important. Most of recent cyber attacks are caused by malicious code, and since the number is more than 1.6 million per day, automated analysis technology to cope with a large amount of malicious code is very important. However, it is difficult to deal with malicious code encryption, obfuscation and packing, and the dynamic analysis technique is not limited to the performance requirements of dynamic analysis but also to the virtual There is a limit in coping with environment avoiding technology. In this paper, we propose a machine learning based malicious code analysis technique which improve the weakness of the detection performance of existing analysis technology while maintaining the light and high-speed analysis performance applicable to commercial endpoints. The results of this study show that 99.13% accuracy, 99.26% precision and 99.09% recall analysis performance of 71,000 normal file and malicious code in commercial environment and analysis time in PC environment can be analyzed more than 5 per second, and it can be operated independently in the endpoint environment and it is considered that it works in complementary form in operation in conjunction with existing antivirus technology and static and dynamic analysis technology. It is also expected to be used as a core element of EDR technology and malware variant analysis.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.18 no.2
• /
• pp.185-195
• /
• 2018

As machines have been automated in the field of industries in recent years, it is a paramount importance to manage and maintain the automation machines. When a fault occurs in sensors attached to the machine, the machine may malfunction and further, a huge damage will be caused in the process line. To prevent the situation, the fault of sensors should be monitored, diagnosed and classified in a proper way. In the paper, we propose a sensor fault detection scheme based on SVM and CNN to detect and classify typical sensor errors such as erratic, drift, hard-over, spike, and stuck faults. Time-domain statistical features are utilized for the learning and testing in the proposed scheme, and the genetic algorithm is utilized to select the subset of optimal features. To classify multiple sensor faults, a multi-layer SVM is utilized, and ensemble technique is used for CNN. As a result, the SVM that utilizes a subset of features selected by the genetic algorithm provides better performance than the SVM that utilizes all the features. However, the performance of CNN is superior to that of the SVM.

• Journal of the Institute of Convergence Signal Processing
• /
• v.4 no.1
• /
• pp.15-26
• /
• 2003

Ultrasonic inspection methods are widely used for detecting flaws in materials. The signal analysis step plays a crucial part in the data interpretation process. A number of signal processing methods have been proposed to classify ultrasonic flaw signals. One of the more popular methods involves the extraction of an appropriate set of features followed by the use of a neural network for the classification of the signals in the feature space. This paper describes an alternative approach which uses the least mean square (LMS) method and expectation maximization (EM) algorithm with the model based deconvolution which is employed for classifying nondestructive evaluation (NDE) signals from steam generator tubes in a nuclear power plant. The signals due to cracks and deposits are not significantly different. These signals must be discriminated to prevent from happening a huge disaster such as contamination of water or explosion. A model based deconvolution has been described to facilitate comparison of classification results. The method uses the space alternating generalized expectation maximization (SAGE) algorithm In conjunction with the Newton-Raphson method which uses the Hessian parameter resulting in fast convergence to estimate the time of flight and the distance between the tube wall and the ultrasonic sensor Results using these schemes for the classification of ultrasonic signals from cracks and deposits within steam generator tubes are presented and showed a reasonable performances.