• International Journal of Computer Science & Network Security
• /
• v.23 no.10
• /
• pp.199-208
• /
• 2023

The emergence of COVID-19 virus has shaken almost every aspect of human life including but not limited to social, financial, and economic changes. One of the most significant impacts was obviously healthcare. Now though the pandemic has been over, its aftereffects are still there. Among them, a prominent one is people lifestyle. Work from home, enhanced screen time, limited mobility and walking habits, junk food, lack of sleep etc. are several factors that have still been affecting human health. Consequently, diseases like diabetes, high blood pressure, anxiety etc. have been emerging at a speed never witnessed before and it mainly includes the people at young age. The situation demands an early prediction, detection, and warning system to alert the people at risk. AI and Machine learning has been investigated tremendously for solving the problems in almost every aspect of human life, especially healthcare and results are promising. This study focuses on reviewing the machine learning based approaches conducted in detection and prediction of diabetes especially during and post pandemic era. That will help find a research gap and significance of the study especially for the researchers and scholars in the same field.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.17 no.1
• /
• pp.67-75
• /
• 2024

Crosswalks play an important role for the safe movement of pedestrians in a complex urban environment. However, for the visually impaired, crosswalks can be a big risk factor. Although assistive tools such as braille blocks and acoustic traffic lights exist for safe walking, poor management can sometimes act as a hindrance to safety. This paper proposes a method to improve accuracy in a deep learning-based real-time crosswalk detection model that can be used in applications for pedestrian assistance for the disabled at the beginning. The image was binarized by utilizing the characteristic that the white line of the crosswalk image contrasts with the road surface, and through this, the crosswalk could be better recognized and the location of the crosswalk could be more accurately identified by using two models that learned the whole and the middle part of the crosswalk, respectively. In addition, it was intended to increase accuracy by creating a boundary box that recognizes crosswalks in two stages: whole and part. Through this method, additional frames that the detection model did not detect in RGB image learning from the crosswalk image could be detected.

• The Journal of Korea Robotics Society
• /
• v.18 no.4
• /
• pp.496-504
• /
• 2023

This paper recognizes the motion intention of the wearer using a muscle stiffness sensor and proposes a control system for a wearable robot based on this. The proposed system recognizes the onset time of the motion using sensor data, determines the assistance mode, and provides assistive torque to the hip flexion/extension motion of the wearer through the generated reference trajectory according to the determined mode. The onset time of motion was detected using the CUSUM algorithm from the muscle stiffness sensor, and by comparing the detection results of the onset time with the EMG sensor and IMU, it verified its applicability as an input device for recognizing the intention of the wearer before motion. In addition, the stability of the proposed method was confirmed by comparing the results detected according to the walking speed of two subjects (1 male and 1 female). Based on these results, the assistance mode (gait assistance mode and muscle strengthening mode) was determined based on the detection results of onset time, and a reference trajectory was generated through cubic spline interpolation according to the determined assistance mode. And, the practicality of the proposed system was also confirmed by applying it to an actual wearable robot.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.882-885
• /
• 2003

In this paper, we describe a haptic jacket and wheel as a haptic interface to enhance VR game realism. Building upon the VR game system using this devices, our haptic interface technique allows the user to intuitive interact on game contents, and then to sense the game event properties such as walking, attacking, driving and fire in a natural way. In addition, we extended the initial haptic model to support haptic decoration and dynamic interactions due to the added game event in a real time display. An application example presented here is a VR Dino-Attack game. This game supports interactions among dynamic and our intuitive haptic interface. Modeling physic interactions involves precise collision detection, real-time force computation, and high control-loop bandwidth.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.56 no.9
• /
• pp.1688-1693
• /
• 2007

The aim of this paper is to develop and verify the system which can detect heart rate during exercise by using conductive fabric electrode and transportable measurement module. The experiment was performed under 4 conditions(resting, walking, jogging, running) and 18 subjects data are used. By using the ECG measurement system used in cardiac stress testing as reference value in order to verify the accuracy of the developed system, the relative error and correlation coefficient was calculated for each subject at every 3 seconds. The results have shown that the high correlation between the developed system and the reference system for detecting heart rate during exercise. Relative error and correlation coefficient are 2.27% and 0.9877, respectively. 7 subjects data are omitted in these calculations because of severe noises. Therefore, it is expected that this system could be used as a health monitoring system in ubiquitous environment in the future.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2007.04a
• /
• pp.315-319
• /
• 2007

This paper presents a algorithm, what is able to recognize 4 different continuous human motion using a single stationary camera as input. For the first step, we acquire images from a camera. To enhance the image, we perform preprocessing which deals with removing noise using median filter, thresholding. And then morphological operations are performed to remove which small blobs and eliminates small holes. At the forth step, blobs are analysed to extracts for foreground region. Then, motions are predicted from these images by using optical flow technique, and the predicted motion data are refined by comparing our cardboard models so as to judge behavior pattern.

• ETRI Journal
• /
• v.40 no.4
• /
• pp.522-530
• /
• 2018

In this study, we developed a robotic walker that actively controls its speed and direction of movement according to the user's gait intention. Sensor fusion between a low-cost light detection and ranging (LiDAR) sensor and inertia measurement units (IMUs) helps determine the user's gait intention. The LiDAR determines the walking direction by detecting both knees, and the IMUs attached on each foot obtain the angular rate of the gait. The user's gait intention is given as the directional angle and the speed of movement. The two motors in the robotic walker are controlled with these two variables, which represent the user's gait intention. The estimated direction angle is verified by comparison with a Kinect sensor that detects the centroid trajectory of both the user's feet. We validated the robotic walker with an experiment by controlling it using the estimated gait intention.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2009.01a
• /
• pp.185-188
• /
• 2009

단일 카메라 영상으로 입력되는 환경 정보에 대해서 보도에 대한 길의 소실점과 보도 영역에 대한 정보를 획득하는 방법과 보도 영역에 대해 블록 세그멘테이션을 통하여 장애물과 같은 물체 영역을 구분한다. 소실정과 보도 영역을 획득하기 위한 방법으로 에지영상에서 보도의 외곽선 정보를 추출하도록 한다. 이를 위해 체인코드를 이용하여 특정한 방향으로 향하는 직선 성분을 검출하도록 한다 보도 영역 내에 존재하는 물체의 영역을 구분하기 위해서 영역을 특정 크기를 가지는 블록으로 구분하고 각 블록이 가지는 평균 컬러 정보를 이용하여 영역을 세그멘테이션 한다. 세그멘테이션을 통해 얻은 영역을 통해 보도의 영역과 장애물의 영역을 구분하고 각 장애물의 위치를 계산하다. 알고리즘의 평가를 위해 실내의 복도 환경과 단순한 형태를 가지는 실외 환경에서 획득한 영상을 이용하여 실험하였다.

• Journal of information and communication convergence engineering
• /
• v.18 no.2
• /
• pp.132-146
• /
• 2020

Biometric technologies have become widely available in many different fields. However, biometric technologies using existing physical features such as fingerprints, facial features, irises, and veins must consider forgery and alterations targeting them through fraudulent physical characteristics such as fake fingerprints. Thus, a trend toward next-generation biometric technologies using behavioral biometrics of a living person, such as bio-signals and walking characteristics, has emerged. Accordingly, in this study, we developed a bio-signal authentication algorithm using electrocardiogram (ECG) signals, which are the most uniquely identifiable form of bio-signal available. When using ECG signals with our system, the personal identification and authentication accuracy are approximately 90% during a state of rest. When using fingerprints alone, the equal error rate (EER) is 0.243%; however, when fusing the scores of both the ECG signal and fingerprints, the EER decreases to 0.113% on average. In addition, as a function of detecting a presentation attack on a mobile phone, a method for rejecting a transaction when a fake fingerprint is applied was successfully implemented.

• Proceedings of the IEEK Conference
• /
• 1998.06a
• /
• pp.565-568
• /
• 1998

In this paper, we implemented the electornic moving aid system for safe walking of the blind. An obstacle detecting of each sector used ultrasound and a distance measurement used time of flight. The alarm is designed to have a sound and a tactile function that can be selected on an user's convenience. This system can detect and obstacle of upward, forward, downward and optimally warn to the blind with vibration, beep sound by appling warning algorithm on object detection. Experimental testing and performance evaluation have been successfully carried out with a prototype cane, and the experiment shows the capability of the function to detect unknown objects within an assigned distance, under knees, over head height, and crushed puddles.