Do-Un Jeong

Bio: Do-Un Jeong is an academic researcher from Dongseo University. The author has contributed to research in topics: Wireless sensor network & ECG Measurement. The author has an hindex of 11, co-authored 59 publications receiving 483 citations.

An Efficient Deep Learning Approach to Pneumonia Classification in Healthcare.

Abstract: This study proposes a convolutional neural network model trained from scratch to classify and detect the presence of pneumonia from a collection of chest X-ray image samples. Unlike other methods that rely solely on transfer learning approaches or traditional handcrafted techniques to achieve a remarkable classification performance, we constructed a convolutional neural network model from scratch to extract features from a given chest X-ray image and classify it to determine if a person is infected with pneumonia. This model could help mitigate the reliability and interpretability challenges often faced when dealing with medical imagery. Unlike other deep learning classification tasks with sufficient image repository, it is difficult to obtain a large amount of pneumonia dataset for this classification task; therefore, we deployed several data augmentation algorithms to improve the validation and classification accuracy of the CNN model and achieved remarkable validation accuracy.

Classification of Posture and Movement Using a 3-axis Accelerometer

Abstract: The real-time monitoring about the activity of the human provides useful information about the activity quantity and ability. The present study implemented a small-size and low-power acceleration monitoring system for convenient monitoring of activity volume and recognition of emergent situations such as falling during daily life. For the wireless transmission of acceleration sensor signal, we developed a wireless transmission system based on a sensor network. In addition, we developed a program for storing and monitoring wirelessly transmitted signals on PC in real-time. The performance of the implemented system was evaluated by assessing the output characteristic of the system according to the change of posture, and parameters and a context recognition algorithm were developed in order to monitor activity volume during daily life and to recognize emergent situations such as falling. In particular, recognition error in the sudden change of acceleration was minimized by the application of a falling correction algorithm.

Variable Threshold Method for ECG R-peak Detection

Abstract: In this paper, a wearable belt-type ECG electrode worn around the chest by measuring the real-time ECG is produced in order to minimize the inconvenient in wearing. ECG signal is detected using a potential instrument system. The measured ECG signal is transmits via an ultra low power consumption wireless data communications unit to personal computer using Zigbee-compatible wireless sensor node. ECG signals carry a lot of clinical information for a cardiologist especially the R-peak detection in ECG. R-peak detection generally uses the threshold value which is fixed. There will be errors in peak detection when the baseline changes due to motion artifacts and signal size changes. Preprocessing process which includes differentiation process and Hilbert transform is used as signal preprocessing algorithm. Thereafter, variable threshold method is used to detect the R-peak which is more accurate and efficient than fixed threshold value method. R-peak detection using MIT-BIH databases and Long Term Real-Time ECG is performed in this research in order to evaluate the performance analysis.

Development of a Technique for Cancelling Motion Artifact in Ambulatory ECG Monitoring System

Abstract: ECG is a electrical signal generated by the heart and has a regular rhythm. ECG cycle, however, change depending on the person's activities and heart-related disorders. Therefore, waveform of the ECG signal can be analyzed to assess cardiac abnormalities and lesion of the heart, infer into pathological and biological mechanisms of the heart, and diagnose for various cardiac disorders. ECG enables non-invasive measuring and contains an abundance of health information. That said, this paper discusses a study concerning development of a highly convenient ECG monitoring system. Realization of such monitoring system required development of a portable, miniature, battery-powered, low power consumption, and wireless ECG measuring system featuring belt-type ECG leads worn around the chest. A Zigbee-compatible wireless sensor node was used for wireless transmission of measured ECG data, and a ultra low power consumption wireless data communications units were also developed. And then a monitoring program was coded to enable ECG signal monitoring from a personal computer. Ambulatory ECG measuring is often associated with motion artifact that forms as the subject moves about his or her daily life. Motion artifact's frequency characteristic is that it varies depending on the type of movement. Therefore, an adaptive filter was used to cancel the changing motion artifact and thereby minimize movement-induced motion artifact. Test results confirm that using the ECG monitoring system proposed herein makes it possible to measure ECG signals in non-restrained environments.

Smart chair based on multi heart rate detection system

Abstract: Many modern people wants to live a healthy life. More recently, a lot of interest in the IOT based healthcare solution or smart phone-based, real-time health management solutions by technological development. The health management solution in many cases is provided through the bio-signal measurement and activity level analysis based on the location information. In this study, sitting posture was based on a real-time implementation of the health care system. Implemented system analyzes a person's heart activity through the non-constrained bio-signal measurement. The electrocardiogram measurement is difficult when non-constrained occurs according to the change of the posture that occurs during the life. In this case, the smart chair to complement the ballistocardiogram measurement is additionally possible to utilize the system was implemented.

Preprocessing techniques for context recognition from accelerometer data

Abstract: The ubiquity of communication devices such as smartphones has led to the emergence of context-aware services that are able to respond to specific user activities or contexts. These services allow communication providers to develop new, added-value services for a wide range of applications such as social networking, elderly care and near-emergency early warning systems. At the core of these services is the ability to detect specific physical settings or the context a user is in, using either internal or external sensors. For example, using built-in accelerometers, it is possible to determine whether a user is walking or running at a specific time of day. By correlating this knowledge with GPS data, it is possible to provide specific information services to users with similar daily routines. This article presents a survey of the techniques for extracting this activity information from raw accelerometer data. The techniques that can be implemented in mobile devices range from classical signal processing techniques such as FFT to contemporary string-based methods. We present experimental results to compare and evaluate the accuracy of the various techniques using real data sets collected from daily activities.

Within the lack of chest COVID-19 X-ray dataset: A novel detection model based on GAN and deep transfer learning

Abstract: The coronavirus (COVID-19) pandemic is putting healthcare systems across the world under unprecedented and increasing pressure according to the World Health Organization (WHO). With the advances in computer algorithms and especially Artificial Intelligence, the detection of this type of virus in the early stages will help in fast recovery and help in releasing the pressure off healthcare systems. In this paper, a GAN with deep transfer learning for coronavirus detection in chest X-ray images is presented. The lack of datasets for COVID-19 especially in chest X-rays images is the main motivation of this scientific study. The main idea is to collect all the possible images for COVID-19 that exists until the writing of this research and use the GAN network to generate more images to help in the detection of this virus from the available X-rays images with the highest accuracy possible. The dataset used in this research was collected from different sources and it is available for researchers to download and use it. The number of images in the collected dataset is 307 images for four different types of classes. The classes are the COVID-19, normal, pneumonia bacterial, and pneumonia virus. Three deep transfer models are selected in this research for investigation. The models are the Alexnet, Googlenet, and Restnet18. Those models are selected for investigation through this research as it contains a small number of layers on their architectures, this will result in reducing the complexity, the consumed memory and the execution time for the proposed model. Three case scenarios are tested through the paper, the first scenario includes four classes from the dataset, while the second scenario includes 3 classes and the third scenario includes two classes. All the scenarios include the COVID-19 class as it is the main target of this research to be detected. In the first scenario, the Googlenet is selected to be the main deep transfer model as it achieves 80.6% in testing accuracy. In the second scenario, the Alexnet is selected to be the main deep transfer model as it achieves 85.2% in testing accuracy, while in the third scenario which includes two classes (COVID-19, and normal), Googlenet is selected to be the main deep transfer model as it achieves 100% in testing accuracy and 99.9% in the validation accuracy. All the performance measurement strengthens the obtained results through the research.