• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.49 no.2
• /
• pp.7-12
• /
• 2012

Recently the medical field to efficiently process the vast amounts of information to decision trees, neural networks, Bayesian Networks, including the application method of various data mining techniques are investigated. In addition, the basic personal information or patient history, family history, in addition to information such as MRI, HRCT images and additional information to collect and leverage in the diagnosis of disease, improved diagnostic accuracy is to promote a common status. But in real world situations that affect the results much because of the variable exists for a particular data mining techniques to obtain information through the enemy can be seen fairly limited. Medical images were taken as well as a minor can not give a positive impact on the diagnosis, but the proportion increased subjective judgments by the automated system is to deal with difficult issues. As a result of a complex reality, the situation is more advantageous to deal with the relative probability of the multivariate model based on Bayesian network, or TAN in the K2 search algorithm improves due to expansion model has been proposed. At this point, depending on the type of search algorithm applied significantly influenced the performance characteristics of the extended Bayesian network, the performance and suitability of each technique for evaluation of the facts is required. In this paper, we extend the Bayesian network for diagnosis of diseases using the same data were carried out, K2, TAN and changes in search algorithms such as classification accuracy was measured. In the 10-fold cross-validation experiment was performed to compare the performance evaluation based on the analysis and the onset of high-risk classification for patients with HRCT images could be possible to identify high-risk data.

• Journal of Broadcast Engineering
• /
• v.26 no.2
• /
• pp.155-166
• /
• 2021

Most object detection algorithms are studied based on RGB images. Because the RGB cameras are capturing images based on light, however, the object detection performance is poor when the light condition is not good, e.g., at night or foggy days. On the other hand, high-quality infrared(IR) images regardless of weather condition and light can be acquired because IR images are captured by an IR sensor that makes images with heat information. In this paper, we performed the object detection algorithm based on the compression ratio in RGB and IR images to show the detection capabilities. We selected RGB and IR images that were taken at night from the Free FLIR Thermal dataset for the ADAS(Advanced Driver Assistance Systems) research. We used the pre-trained object detection network for RGB images and a fine-tuned network that is tuned based on night RGB and IR images. Experimental results show that higher object detection performance can be acquired using IR images than using RGB images in both networks.

• Journal of IKEEE
• /
• v.25 no.2
• /
• pp.273-279
• /
• 2021

In this paper, we propose an algorithm that shortens the learning time by performing individual learning using partitioning the deep learning structure. The proposed algorithm consists of four processes: network classification origin setting process, feature vector extraction process, feature noise removal process, and class classification process. First, in the process of setting the network classification starting point, the division starting point of the network structure for effective feature vector extraction is set. Second, in the feature vector extraction process, feature vectors are extracted without additional learning using the weights previously learned. Third, in the feature noise removal process, the extracted feature vector is received and the output value of each class is learned to remove noise from the data. Fourth, in the class classification process, the noise-removed feature vector is input to the multi-layer perceptron structure, and the result is output and learned. To evaluate the performance of the proposed algorithm, we experimented with the Extended Yale B face database. As a result of the experiment, in the case of the time required for one-time learning, the proposed algorithm reduced 40.7% based on the existing algorithm. In addition, the number of learning up to the target recognition rate was shortened compared with the existing algorithm. Through the experimental results, it was confirmed that the one-time learning time and the total learning time were reduced and improved over the existing algorithm.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.11
• /
• pp.21-31
• /
• 2021

As the COVID-19 pandemic rapidly changes healthcare around the globe, the need for smart healthcare that allows for remote diagnosis is increasing. The current classification of respiratory diseases cost high and requires a face-to-face visit with a skilled medical professional, thus the pandemic significantly hinders monitoring and early diagnosis. Therefore, the ability to accurately classify and diagnose respiratory sound using deep learning-based AI models is essential to modern medicine as a remote alternative to the current stethoscope. In this study, we propose a deep learning-based respiratory sound classification model using data collected from medical experts. The sound data were preprocessed with BandPassFilter, and the relevant respiratory audio features were extracted with Log-Mel Spectrogram and Mel Frequency Cepstral Coefficient (MFCC). Subsequently, a Parallel CNN network model was trained on these two inputs using stacking ensemble techniques combined with various machine learning classifiers to efficiently classify and detect abnormal respiratory sounds with high accuracy. The model proposed in this paper classified abnormal respiratory sounds with an accuracy of 96.9%, which is approximately 6.1% higher than the classification accuracy of baseline model.

• Journal of Korea Water Resources Association
• /
• v.56 no.7
• /
• pp.439-449
• /
• 2023

Recent advancements in data measuring technology have facilitated the installation of various sensors, such as pressure meters and flow meters, to effectively assess the real-time conditions of water distribution systems (WDSs). However, as cities expand extensively, the factors that impact the reliability of measurements have become increasingly diverse. In particular, demand data, one of the most significant hydraulic variable in WDS, is challenging to be measured directly and is prone to missing values, making the development of accurate data generation models more important. Therefore, this paper proposes an adversarially trained autoencoder (ATAE) model based on generative deep learning techniques to accurately estimate demand data in WDSs. The proposed model utilizes two neural networks: a generative network and a discriminative network. The generative network generates demand data using the information provided from the measured pressure data, while the discriminative network evaluates the generated demand outputs and provides feedback to the generator to learn the distinctive features of the data. To validate its performance, the ATAE model is applied to a real distribution system in Austin, Texas, USA. The study analyzes the impact of data uncertainty by calculating the accuracy of ATAE's prediction results for varying levels of uncertainty in the demand and the pressure time series data. Additionally, the model's performance is evaluated by comparing the results for different data collection periods (low, average, and high demand hours) to assess its ability to generate demand data based on water consumption levels.

• Journal of Internet Computing and Services
• /
• v.21 no.6
• /
• pp.23-31
• /
• 2020

This study was carried out to generate various images of railroad surfaces with random defects as training data to be better at the detection of defects. Defects on the surface of railroads are caused by various factors such as friction between track binding devices and adjacent tracks and can cause accidents such as broken rails, so railroad maintenance for defects is necessary. Therefore, various researches on defect detection and inspection using image processing or machine learning on railway surface images have been conducted to automate railroad inspection and to reduce railroad maintenance costs. In general, the performance of the image processing analysis method and machine learning technology is affected by the quantity and quality of data. For this reason, some researches require specific devices or vehicles to acquire images of the track surface at regular intervals to obtain a database of various railway surface images. On the contrary, in this study, in order to reduce and improve the operating cost of image acquisition, we constructed the 'Defective Railroad Surface Regeneration Model' by applying the methods presented in the related studies of the Generative Adversarial Network (GAN). Thus, we aimed to detect defects on railroad surface even without a dedicated database. This constructed model is designed to learn to generate the railroad surface combining the different railroad surface textures and the original surface, considering the ground truth of the railroad defects. The generated images of the railroad surface were used as training data in defect detection network, which is based on Fully Convolutional Network (FCN). To validate its performance, we clustered and divided the railroad data into three subsets, one subset as original railroad texture images and the remaining two subsets as another railroad surface texture images. In the first experiment, we used only original texture images for training sets in the defect detection model. And in the second experiment, we trained the generated images that were generated by combining the original images with a few railroad textures of the other images. Each defect detection model was evaluated in terms of 'intersection of union(IoU)' and F1-score measures with ground truths. As a result, the scores increased by about 10~15% when the generated images were used, compared to the case that only the original images were used. This proves that it is possible to detect defects by using the existing data and a few different texture images, even for the railroad surface images in which dedicated training database is not constructed.

• Journal of Ship and Ocean Technology
• /
• v.6 no.4
• /
• pp.1-12
• /
• 2002

A control system for an automated line heating process is developed by use of object-oriented methodology. The main function of the control system is to provide real-time heating information to technicians or automated machines. The information includes heating location, torch speed, heating order, and others. The system development is achieved by following the five steps in the object-oriented procedure. First, requirements are specified and corresponding objects are determined. Then, the analysis, design, and implementation of the proposed system are sequentially carried out. The system consists of six subsystems, or modules. These are (1) the inference module with an artificial neural network algorithm, (2) the analysis module with the Finite Element Method and kinematics analysis, (3) the data access module to store and retrieve the forming information, (4) the communication module, (5) the display module, and (6) the measurement module. The system is useful, irrespective of the heating sources, i.e. flame/gas, laser, or high frequency induction heating. A newly developed automated line heating machine is connected to the proposed system. Experiments and discussions follow.

• 전자공학회논문지 IE
• /
• v.43 no.4
• /
• pp.13-20
• /
• 2006

In the advanced country, It is forecasting farm prices using intelligence style of farming technique. In our country, It is offering basis research to prevent the prices rising and falling, But, It is impossible that no one can predict exactly for farming price. In this paper to improve forecasting farming price using neural network as a preprocessing. Also, we developed a fuzzy algorithm for real time forecasting as a postprocessing about unexpectable conditions. Computer simulation results preyed reducing pricing error which proposed farming price expecting system better than conventional demand forecasting system does not using fuzzy rules.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.57 no.6
• /
• pp.1058-1062
• /
• 2008

In clinical decision support system(CDSS), unlike rule-based expert method, appropriate data-driven machine learning method can easily provide the information of individual feature(clinical test) for disease classification. However, currently developed methods focus on the improvement of the classification accuracy for diagnosis. With the analysis of feature importance in classification, one may infer the novel clinical test sets which highly differentiate the specific diseases or disease states. In this background, we introduce a novel CDSS that integrate a classifier and feature selection module together. Random forest algorithm is applied for the classifier and the feature importance measure. The system selects the significant clinical tests discriminating the diseases by examining the classification error during backward elimination of the features. The superior performance of random forest algorithm in clinical classification was assessed against artificial neural network and decision tree algorithm by using breast cancer, diabetes and heart disease data in UCI Machine Learning Repository. The test with the same data sets shows that the proposed system can successfully select the significant clinical test set for each disease.

• Journal of Environmental Science International
• /
• v.17 no.6
• /
• pp.679-687
• /
• 2008

In this study, we implemented landslide distribution of Jeju Island using ANN and GIS, respectively. To do this, we first get the counter line from 1:2,5000 digital map and use this counter line to make the DEM. for the evaluate the land slide susceptibility. Next, we abstracted slop map and aspect map from the DEM and get the land use map using ISODATA classification method from Landsat 7 images. In the computation processes of landslide analysis, we make the class to the soil map, tree diameter map, Isohyet map, geological map and so on. Finally, we applied the ANN method to the landslide one and calculated its weighted values. GIS results can be calculated by using Acrview program and produced Jeju landslide susceptibility map by usign Weighted Overlay method. Based on our results, we found the relatively weak points of landslide ware concentrated to the top of Halla mountains.