Yoonseon Song

Realization of an e-Health System to Perceive Emergency Situations

Emergency situations can occur anywhere and anytime in daily life. In the paper, we present an e-health system to perceive emergency situations of a patient. Using a wearable shirt (BioShirt) and a personal monitoring system (PBM), we obtain the body signals of a user. The monitoring system collects and transmits the vital signs to a personal digital assistant (PDA) via a BlueTooth communication module. To detect emergency from the received data, a simple detection algorithm is performed in the PDA. And the PDA forwards the data to an e-health central monitoring room (ECMR), if necessary. In the ECMR, several operators supervise the registered users based on incoming body signals from each user™s device. If an automatic decision-making algorithm generates an emergency alarm, the operators try to contact the corresponding patient and recognize his status. Ultimately if they decide that the patient is an urgent situation, they give phone calls and messages to the emergency center and the patient™s medical attendant immediately.

Comparison of conductive fabric sensor and Ag-AgCl sensor under motion artifacts

A wearable electrocardiogram(ECG) device using conductive fabric sensor was compared with traditional Ag-AgCl electrode ECG device. The ECG signals were measured under existence of motion artifacts on variable running speed using treadmill to verify that wearable device can substitute traditional ECG device. A signal to noise ratio (SNR) and RR interval were compared between the two devices. The SNR of wearable device was similar or higher than that of clinical device and difference of RR interval was 2ms. The results show that the wearable ECG device using conductive fabric sensor can make similar performance with ECG device using Ag-AgCl electrode even under motion artifacts.

EEG-based discrimination between Yes and No

For a brain-computer interface, the authors discriminate between Yes and No, which are the most elementary expressions in communication between human beings. For this purpose, they perform a time-frequency analysis of the EEG for visual and auditory stimuli and for Yes/No question. They also train an artificial neural network.

Sequential algorithm for the detection of the shockable rhythms in electrocardiogram

We suggest a sequential algorithm for the detection of the ventricular fibrillation (VF) and ventricular tachycardia (VT) of a rate above 180 bpm, so called shockable rhythms. The built-in algorithm for ECG analysis embedded in the portable bio-signal sensing module is aimed to discriminate between shockable and non-shockable rhythms and its accuracy is analyzed. An algorithm for VF/VT detection is proposed to analyze every 1 s ECG episode using the past 8 s episodes. The method is tested with 844,587 ECG episodes from the widely accepted databases. A sensitivity of 86.8 % and a specificity of 99.4 % were obtained and compared with the previous results.

Development of a patch type embedded cardiac function monitoring system using dual microprocessor for arrhythmia detection in heart disease patient

A patch type embedded cardiac function monitoring system was developed to detect arrhythmias such as PVC (Premature Ventricular Contraction), pause, ventricular fibrillation, and tachy/bradycardia. The overall system is composed of a main module including a dual processor and a Bluetooth telecommunication module. The dual microprocessor strategy minimizes power consumption and size, and guarantees the resources of embedded software programs. The developed software was verified with standard DB, and showed good performance.

A basic study for patch type ambulatory 3-electrode ECG monitoring system for the analysis of acceleration signal and the limb leads and augmented unipolar limb leads signal

A compact and portable device was designed for preliminary study of patch type ambulatory 3-electrode ECG monitoring system for limb leads and augmented unipolar limb leads signal analysis. The developed system also can measure and send the acceleration signals wirelessly during daily life to analyze the users information. The 3-electrode system is feasible to provide the information of limb leads and augmented unipolar limb leads for further arrhythmia analysis and simultaneously shows lots of issues to be more broadly applicable and more powerful device.

Random Search Based on Genetic Operators

This paper presents a new way of optimization based on genetic operators. It has been known that the canonical genetic algorithm (CGA) does not guarantee convergence to the global optimum and also has the problem of premature saturation (or convergence). In this sense, this paper suggests a new way of searching based on genetic operators in which convergence to the global optimum is guaranteed and efficiency in searching is considered. The basic scheme of the suggested approach is to apply the genetic operators in the case of searching for solutions and the random perturbation in the case of premature saturation. To show the effectiveness of our approach, simulation for vector quantization has been performed.

A basic study of activity type detection and energy expenditure estimation for children and youth in daily life using 3-axis accelerometer and 3-stage cascaded artificial neural network.

It is important to prevent obesity in childhood given that many obese adults have been obese since childhood. An activity monitor could provide an effective aid in preventing obesity if it records not only the calorie assessment but also activity detection to check how active a child is in daily life. The current study is for activity monitoring algorithm and we designed 3-stage cascaded artificial neural network. To develop the algorithm, we recruited 76 participants, made 3-axis accelerometer for them, and acquired activity data and calorie consumption data through them. Finally, we designed 3-stage cascaded network to classify the activities and to assess energy consumption. The 3-stage network classifies 4 activities of walking, running, stairs moving, and jumping rope with overall accuracy of 94.70%, and predicts calorie consumption with average accuracy of 81.91%, which is better than the results of the 2-stage network. Future work would include the enhancement of the network performance.

A preliminary study of the effect of electrode placement in order to define a suitable location for two electrodes and obtain sufficiently reliable ECG signals when monitoring with wireless system

Most countries face high and increasing rates of cardiovascular disease. Each year, heart disease kills more Americans than cancer. Therefore, there has been a promising market for portable ECG equipment and it is increasing. To use portable ECG measuring devices, it is essential to define a suitable location for the measuring as we need to reduced electrode size and distance. This research proposes to study how the inter-electrode distance affects the signal and how the electrode pair should be placed on the chest in order to obtain a sufficiently reliable ECG signal to detect heart arrhythmias in any environment, such as home or work. Therefore, we developed a compact, portable patch type ambulatory ECG monitoring system, Heart Tracker, using a microprocessor for preliminary study of signal analysis. To optimize the electrode arrangement in wireless environment, we compared HT and standard 12 lead with changing electrode position.

A wavefront array processing architecture for real-time simulation of large scale neural networks

Describes a scalable parallel architecture for real-time, large scale neural network simulations. Currently the SIMD architecture is largely adopted for implementing digital neurocomputers. However, it is not efficient for simulating large scale neural networks in real-time because of its limited scalability and flexibility. The authors investigate, as a solution, a wavefront array processing (WAP) architecture based on asynchronous communications. The authors compare both architectures in scalability, performance, and flexibility for simulating multi-layer perceptrons. The authors also briefly discuss implementing a high performance digital neurocomputer based on the WAP.