• The Journal of the Korea Contents Association
• /
• v.14 no.4
• /
• pp.19-28
• /
• 2014

Recent advancements in the IT industry have made daily life more convenient than ever before. In particular, studies have focused on the position detection of individuals using the GPS in smartphones, and this application has been utilized actively in emergency rescue organizations. However, existing methods send the location information of a user to a predetermined guardian set by the user or to a control center when the user enters into or deviates from a predetermined space. Such spaces are created by an arbitrary radius, thereby making it difficult to set a detailed area by using an existing radius-area creation method in an unstructured space and path with a specific road, such as for trekking, amusement parks, or mountaineering. This study proposes a novel method for setting up an area by connecting multiple radii to improve the existing radius-area creation method in order to easily set a detailed area in smart devices or on the Internet. In addition, an optimization method for resource use is proposed by comparing the operation results in which a user's location is detected by using the proposed location-based area setup method and deviation detection.

• Journal of Astronomy and Space Sciences
• /
• v.25 no.4
• /
• pp.481-490
• /
• 2008

Reaction wheel is one of the actuators for spacecraft attitude control, which generates torque by changing an inertial rotor speed inside of the wheel. In order to generate required torque accurately and estimate an accurate angular momentum, wheel speed should be measured as close to the actual speed as possible. In this study, two conventional speed detection methods for high speed motor with digital tacho pulse (Elapsed-time method and Pulse-count method) and their resolutions are analyzed. For satellite attitude maneuvering and control, reaction wheel shall be operated in bi directional and low speed operation is sometimes needed for emergency case. Thus the bias error at low speed with constant acceleration (or deceleration) is also analysed. As a result, the speed detection error of elapsed-time method is largely influenced upon the high-speed clock frequency at high speed and largely effected on the number of tacho pulses used in elapsed time calculation at low speed, respectively.

• Information Systems Review
• /
• v.12 no.2
• /
• pp.89-104
• /
• 2010

Recently, ubiquitous sensor network (USN) has been applied to many areas including environment monitoring. A few studies applied the USN to disaster prevention and emergency management, in particular, aiming to conserve cultural heritage. USN is an useful technology to do online real-time monitoring for the purpose of early detection of the fire which is a critical cause of damage and destruction of cultural heritages. It is necessary to online monitor the cultural heritages that human has a difficulty to access or their external appearance and beauty are important, by using the USN. However, there exists false warning from USN-based monitoring systems without human intervention. In this paper, we presented an alternative to resolve the problem by applying ontology. Our intelligent fire early detection systems for conserving cultural heritages are based on ontology and inference rules, and tested under laboratory environments.

• Korean Journal of Radiology
• /
• v.21 no.7
• /
• pp.891-899
• /
• 2020

Objective: To assess the diagnostic performance of a deep learning-based algorithm for automated detection of acute and chronic rib fractures on whole-body trauma CT. Materials and Methods: We retrospectively identified all whole-body trauma CT scans referred from the emergency department of our hospital from January to December 2018 (n = 511). Scans were categorized as positive (n = 159) or negative (n = 352) for rib fractures according to the clinically approved written CT reports, which served as the index test. The bone kernel series (1.5-mm slice thickness) served as an input for a detection prototype algorithm trained to detect both acute and chronic rib fractures based on a deep convolutional neural network. It had previously been trained on an independent sample from eight other institutions (n = 11455). Results: All CTs except one were successfully processed (510/511). The algorithm achieved a sensitivity of 87.4% and specificity of 91.5% on a per-examination level [per CT scan: rib fracture(s): yes/no]. There were 0.16 false-positives per examination (= 81/510). On a per-finding level, there were 587 true-positive findings (sensitivity: 65.7%) and 307 false-negatives. Furthermore, 97 true rib fractures were detected that were not mentioned in the written CT reports. A major factor associated with correct detection was displacement. Conclusion: We found good performance of a deep learning-based prototype algorithm detecting rib fractures on trauma CT on a per-examination level at a low rate of false-positives per case. A potential area for clinical application is its use as a screening tool to avoid false-negative radiology reports.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.13 no.2
• /
• pp.138-144
• /
• 2020

Currently, an autonomous vehicle studies are working to develop a four-level autonomous vehicle that can cope with emergencies. In order to flexibly respond to an emergency, the autonomous vehicle must move in a direction to minimize the damage, which must be conducted by judging all the states of the road, such as the surrounding pedestrians, road conditions, and surrounding vehicle conditions. Therefore, in this paper, we suggest a passenger detection and sharing system to detect the passenger situation inside the autonomous vehicle and share it with V2V to the surrounding vehicles to assist in the operation of the autonomous vehicle. Passenger detection and sharing system improve the weighting method that recognizes passengers in the current vehicle to identify the passenger's position accurately inside the vehicle, and shares the passenger's position of each vehicle with other vehicles around it in case of emergency. So, it can help determine the driving of a vehicle. As a result of the experiment, the body pressure sensor applied to the passenger recognition sub-module showed about 8% higher accuracy than the conventional resonant sensor and about 17% higher than the piezoelectric sensor.

• 재활복지
• /
• v.21 no.3
• /
• pp.129-146
• /
• 2017

In an event of an emergency, such as fire in a building, visually impaired and blind people are prone to exposed to a level of danger that is greater than that of normal people, for they cannot be aware of it quickly. Current fire detection methods such as smoke detector is very slow and unreliable because it usually uses chemical sensor based technology to detect fire particles. But by using vision sensor instead, fire can be proven to be detected much faster as we show in our experiments. Previous studies have applied various image processing and machine learning techniques to detect fire, but they usually don't work very well because these techniques require hand-crafted features that do not generalize well to various scenarios. But with the help of recent advancement in the field of deep learning, this research can be conducted to help solve this problem by using deep learning-based object detector that can detect fire using images from security camera. Deep learning based approach can learn features automatically so they can usually generalize well to various scenes. In order to ensure maximum capacity, we applied the latest technologies in the field of computer vision such as YOLO detector in order to solve this task. Considering the trade-off between recall vs. complexity, we introduced two convolutional neural networks with slightly different model's complexity to detect fire at different recall rate. Both models can detect fire at 99% average precision, but one model has 76% recall at 30 FPS while another has 61% recall at 50 FPS. We also compare our model memory consumption with each other and show our models robustness by testing on various real-world scenarios.

• Journal of Biomedical Engineering Research
• /
• v.38 no.6
• /
• pp.330-335
• /
• 2017

Cardiac arrest is owing to the failure of the heart that makes the blood circulation stop. Arrested blood circulation prevents the supply of the oxygen and the glucose and it results the loss of consciousness and, finally, brain death. Many public institution installed the AED for emergency treatment, but, it is not efficient when the patient is alone. In this paper, we made multiplexed wearable device for cardiac arrest detection. With this device, we measure the individual's electrocardiography, heart sound and motion. If the cardiac arrest is detected, the device make a warning horn and transmit the signal for defibrillation. We obtain 98.33% of ECG data, 94.5% of PCG data and 98.38% of IMU data accuracy for each evaluation and 93.33% accuracy for integrated evaluation.

• Journal of Internet Computing and Services
• /
• v.20 no.6
• /
• pp.137-142
• /
• 2019

This paper Various services exist to detect and monitor abnormal event. However, most services focus on fires and gas leaks. so It is impossible to prevent and respond to emergency situations for the elderly and severely disabled people living alone. In this study, AI model is designed and compared to detect abnormal event of heart rate signal which is considered to be the most important among various bio signals. Specifically, electrocardiogram (ECG) data is collected using Physionet's MIT-BIH Arrhythmia Database, an open medical data. The collected data is transformed in different ways. We then compare the trained AI model with the modified and ECG data.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.13 no.4
• /
• pp.215-220
• /
• 2013

Recently, death number of heart attack in the world is increasing rapidly. Therefore, to solve these problem, it is trend that is making mandatory automatic defibrillator AED establishment to airport, school, at home. However, AED use in an emergency or equipment failure caused malfunctions if equipped with AED may even become obsolete. In this paper, in order to improve this problem, AED Simulator using the fuzzy simulation technique in comparison to existing methods Tilt ambient temperature conditions and in consideration of the conditions, self-diagnostics, error detection at the time to determine whether the development of intelligent simulation. Moreover, in this paper, it proved that fuzzy AED Simulation improved fault detection probability results 30% more than conventional method.

• Journal of the Korea Society of Computer and Information
• /
• v.22 no.11
• /
• pp.17-23
• /
• 2017

In this paper, we implemented a respiration measurement system consisting of piezoelectric sensor, respiration signal processing device, and a viewer on a notebook. We tried an experiment for measuring respiration and detecting sleep apnea syndrome when a subject lay on a bed. We applied the respiration measurement algorithm to sensor data obtained from four subjects. In order to get a good graph shape, data manipulation methods such as moving averages and maximum values were applied. The window size for moving average was chosen as N=70, and the threshold value for each subject was customized. In this case, the proposed system showed 96.0% accuracy. When the maximum value among 90 data was applied instead of moving average, our system achieved 95.1% accuracy. In an experiment for detecting sleep apnea syndrome, the system showed that sleep apnea occurred correctly and calculated the average interval of sleep apnea. While infants or the elderly as well as patients with sleep apnea syndrome are lying down on a bed, our results are also expected to be able to cope with some accidental emergency situation by observing their respiration and detecting sleep apnea.