• Journal of Internet Computing and Services
• /
• v.11 no.1
• /
• pp.117-128
• /
• 2010

There are many researches related to a simulated shooting training system for replacing the real military and police shooting training. In this paper, we propose the point of impact from a simulated shooting target based on image processing instead of using a sensor based approach. The point of impact is extracted by analyzing the image extracted from the camera on the muzzle of a gun. The final shooting result is calculated by mapping the target and the coordinates of the point of impact. The recognition system is divided into recognizing the projection zone, extracting the point of impact on the projection zone, and calculating the shooting result from the point of impact. We find the vertices of the projection zone after converting the captured image to the binary image and extract the point of impact in it. We present the extracting process step by step and provide experiments to validate the results. The experiments show that exact vertices of the projection area and the point of impact are found and a conversion result for the final result is shown on the interface.

• Journal of IKEEE
• /
• v.23 no.3
• /
• pp.947-953
• /
• 2019

The purpose of this paper is to explore an ASIC design for estimating sizes and concentrations of airborne micro-particles by the means of integrating, amplifying and digitizing electric charge signals generated by photo-sensors as it receives scattered photons by the presence of micro-particles, consisting of a pre-amplifier that detects and amplifies voltage or current signal from photo-sensor that generates charges (hole-electron pairs) when exposed to visible rays, infrared rays, ultraviolet rays, etc. according to the intensity of rays; a shaper for shaping the amplified signal to a semi-gaussian waveform; two discriminators and binary counters for outputting digital signals by comparing the magnitude of the shaped signal with an arbitrary reference voltages. The ASIC with the proposed architecture and functional blocks in this study was designed with a 0.18um standard CMOS technology from Global Foundries and the operation and performances of the ASIC has been verified by the silicons fabricated by using the process.

• Journal of Sensor Science and Technology
• /
• v.31 no.6
• /
• pp.433-440
• /
• 2022

Recently, owing to global warming, average summer temperatures are increasing and the number of hot days is increasing is increasing, which leads to an increase in heat stroke. In particular, outdoor workers directly exposed to the heat are at higher risk of heat stroke; therefore, preventing heat-related illnesses and managing safety have become important. Although various wearable devices have been developed to prevent heat stroke for outdoor workers, applying various sensors to the safety helmets that workers must wear is an excellent alternative. In this study, we developed a smart helmet that measures various vital signs of the wearer such as body temperature, heart rate, and sweat rate; external environmental signals such as temperature and humidity; and movement signals of the wearer such as roll and pitch angles. The smart helmet can acquire the various data by connecting with a smartphone application. Environmental data can check the status of heat wave advisory, and the individual vital signs can monitor the health of workers. In addition, we developed an algorithm that classifies the risk of heat-related illness as normal and abnormal by inputting a set of vital signs of the wearer using a support vector machine technique, which is a machine learning technique that allows for rapid binary classification with high reliability. Furthermore, the classified results suggest that the safety manager can supervise the prevention of heat stroke by receiving feedback from the control system.

• Journal of the Society of Disaster Information
• /
• v.18 no.3
• /
• pp.433-443
• /
• 2022

Purpose: In this paper, we propose a study of deep learning algorithms that estimate and predict sarcopenia by exploiting the high penetration rate of smart devices. Method: To utilize deep learning techniques, experimental data were collected by using the inertial sensor embedded in the smart device. We implemented a smart device application for data collection. The data are collected by labeling normal and abnormal gait and five states of running, falling and squat posture. Result: The accuracy was analyzed by comparative analysis of LSTM, CNN, and RNN models, and binary classification accuracy of 99.87% and multiple classification accuracy of 92.30% were obtained using the CNN-LSTM fusion algorithm. Conclusion: A study was conducted using a smart sensoring device, focusing on the fact that gait abnormalities occur for people with sarcopenia. It is expected that this study can contribute to strengthening the safety issues caused by sarcopenia.

• Convergence Security Journal
• /
• v.22 no.1
• /
• pp.29-38
• /
• 2022

The importance of prevention of epidemics is increasing due to the serious spread of infectious diseases. For prevention of epidemics, we need to focus on the non-contact industry. Therefore, in this paper, a face recognition door lock that controls access through non-contact is designed and developed. First very simple features are combined to find objects and face recognition is performed using Haar-based cascade algorithm. Then the texture of the image is binarized to find features using LBPH. An non-contact door lock system which composed of Raspberry PI 3B+ board, an ultrasonic sensor, a camera module, a motor, etc. are suggested. To verify actual performance and ascertain the impact of light sources, various experiment were conducted. As experimental results, the maximum value of the recognition rate was about 85.7%.

• Korean Journal of Clinical Laboratory Science
• /
• v.44 no.2
• /
• pp.52-58
• /
• 2012

Patients with obstructive sleep apnea (OSA) often have more aggravated symptoms in the supine position. We tried to investigate the clinical characteristics and the predictive factors for positional OSA. Polysomnographic data were reviewed for OSA patients (apnea hypopnea index, $AHI{\geq}5$) from April, 2008 to April, 2011 at the Asan Medical Center. Clinical data, comorbid medical condition data and questionnaires (SF-36, MFI-20, ESS, BDI, STAI) were assessed. All patients were classified into two groups: positional patients (PP) group and non-positional patients (NPP) group. PP was defined as a patient who had the AHI in the supine position was at least twice as high as that in the lateral position. The body position of patients was confirmed by sleep position sensor and video monitor. All patients had at least 30 minutes of positional and 30 minutes of non-positional sleep. We compared clinical, medical, polysomnographic data, and questionnaire results between two (PP and NPP) groups and investigated predictive factors for the PP group using binary logistic regression analysis. In total, 371 patients were investigated. 265 (71.4%) was categorized as PP group and 106 (28.5%) as NPP group. The mean age ($mean{\pm}SD$) was higher in the PP group ($52.4{\pm}9.8$) than in the NPP group ($49.5{\pm}11.9$) (p<0.05). Comparison of sleep parameters between the PP and the NPP group showed that the PP group had significantly lower BMI (PP: $26.1{\pm}3.2kg/m^2$; NPP: $27.8{\pm}4.3kg/m^2$, p<0.001), neck circumference (PP: $39.7{\pm}2.8cm$; NPP: $41.5{\pm}3.7cm$, p<0.001) and hypertension rate (PP: n=89/265 (33.5%); NPP: n=48/106 (45.2%), p=0.0240). In the PP group, the percentage of deep sleep (PP: $8.7{\pm}8.1%$; NPP: $5.6{\pm}7.0%$, P=0.001) and rapid eye movement (REM) (PP: $17.5{\pm}6.1%$; NPP: $14.0{\pm}6.9%$, p<0.001) were significantly higher whereas the percentage of light sleep (stage N1) was significantly lower than the NPP group (PP: $30.4{\pm}12.3$; NPP: $44.5{\pm}20.8%$, p<0.001). During the sleep, the AHI in the supine position (PP: $48.6{\pm}19.5$; NPP: $60.5{\pm}22.6$, p<0.001) and in the non-supine position (PP: $9.4{\pm}8.9$; NPP: $48.4{\pm}24.8$, p=<0.001) were significantly lower and the minimal arterial oxygen saturation in non-REM sleep was significantly higher in the PP group (PP: $80.3{\pm}7.6$; NPP: $75.1{\pm}9.9$, p=<0.001). There were no significant differences in all questionnaires including quality of life. The results of the binary logistic regression analysis showed that age, the amount of REM sleep(%) and AHI were significant predictive factors for positional OSA. The significant predictive factors for positional OSA were older age, higher percentage of REM and lower AHI. The questionnaire results were not significantly different between the two groups.

• Journal of Korea Spatial Information System Society
• /
• v.11 no.1
• /
• pp.127-136
• /
• 2009

This paper proposes an on-line mining algorithm of moving trajectory patterns in RFID data streams considering changing characteristics over time and constraints of single-pass data scan. Since RFID, sensor, and mobile network technology have been rapidly developed, many researchers have been recently focused on the study of real-time data gathering from real-world and mining the useful patterns from them. Previous researches for sequential patterns or moving trajectory patterns based on stream data have an extremely time-consum ing problem because of multi-pass database scan and tree traversal, and they also did not consider the time-changing characteristics of stream data. The proposed method preserves the sequential strength of 2-lengths frequent patterns in binary relationship table using the time-evolving graph to exactly reflect changes of RFID data stream from time to time. In addition, in order to solve the problem of the repetitive data scans, the proposed algorithm infers candidate k-lengths moving trajectory patterns beforehand at a time point t, and then extracts the patterns after screening the candidate patterns by only one-pass at a time point t+1. Through the experiment, the proposed method shows the superior performance in respect of time and space complexity than the Apriori-like method according as the reduction ratio of candidate sets is about 7 percent.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.17 no.1
• /
• pp.21-32
• /
• 2007

Vuillaume-Okeya presented unsigned receding methods for protecting modular exponentiations against side channel attacks, which are suitable for tamper-resistant implementations of RSA or DSA which does not benefit from cheap inversions. The proposed method was using a signed representation with digits set ${1,2,{\cdots},2^{\omega}-1}$, where 0 is absent. This receding method was designed to be computed only from the right-to-left, i.e., it is necessary to finish the receding and to store the receded string before starting the left-to-right evaluation stage. This paper describes new receding methods for producing SPA-resistant unsigned representations which are scanned from left to right contrary to the previous ones. Our contributions are as follows; (1) SPA-resistant unsigned left-to-right receding with general width-${\omega}$, (2) special case when ${\omega}=1$, i.e., unsigned binary representation using the digit set {1,2}, (3) SPA-resistant unsigned left-to-right Comb receding, (4) extension to unsigned radix-${\gamma}$ left-to-right receding secure against SPA. Hence, these left-to-right methods are suitable for implementing on memory limited devices such as smartcards and sensor nodes

• Journal of Intelligence and Information Systems
• /
• v.18 no.1
• /
• pp.125-141
• /
• 2012

These days, the malicious attacks and hacks on the networked systems are dramatically increasing, and the patterns of them are changing rapidly. Consequently, it becomes more important to appropriately handle these malicious attacks and hacks, and there exist sufficient interests and demand in effective network security systems just like intrusion detection systems. Intrusion detection systems are the network security systems for detecting, identifying and responding to unauthorized or abnormal activities appropriately. Conventional intrusion detection systems have generally been designed using the experts' implicit knowledge on the network intrusions or the hackers' abnormal behaviors. However, they cannot handle new or unknown patterns of the network attacks, although they perform very well under the normal situation. As a result, recent studies on intrusion detection systems use artificial intelligence techniques, which can proactively respond to the unknown threats. For a long time, researchers have adopted and tested various kinds of artificial intelligence techniques such as artificial neural networks, decision trees, and support vector machines to detect intrusions on the network. However, most of them have just applied these techniques singularly, even though combining the techniques may lead to better detection. With this reason, we propose a new integrated model for intrusion detection. Our model is designed to combine prediction results of four different binary classification models-logistic regression (LOGIT), decision trees (DT), artificial neural networks (ANN), and support vector machines (SVM), which may be complementary to each other. As a tool for finding optimal combining weights, genetic algorithms (GA) are used. Our proposed model is designed to be built in two steps. At the first step, the optimal integration model whose prediction error (i.e. erroneous classification rate) is the least is generated. After that, in the second step, it explores the optimal classification threshold for determining intrusions, which minimizes the total misclassification cost. To calculate the total misclassification cost of intrusion detection system, we need to understand its asymmetric error cost scheme. Generally, there are two common forms of errors in intrusion detection. The first error type is the False-Positive Error (FPE). In the case of FPE, the wrong judgment on it may result in the unnecessary fixation. The second error type is the False-Negative Error (FNE) that mainly misjudges the malware of the program as normal. Compared to FPE, FNE is more fatal. Thus, total misclassification cost is more affected by FNE rather than FPE. To validate the practical applicability of our model, we applied it to the real-world dataset for network intrusion detection. The experimental dataset was collected from the IDS sensor of an official institution in Korea from January to June 2010. We collected 15,000 log data in total, and selected 10,000 samples from them by using random sampling method. Also, we compared the results from our model with the results from single techniques to confirm the superiority of the proposed model. LOGIT and DT was experimented using PASW Statistics v18.0, and ANN was experimented using Neuroshell R4.0. For SVM, LIBSVM v2.90-a freeware for training SVM classifier-was used. Empirical results showed that our proposed model based on GA outperformed all the other comparative models in detecting network intrusions from the accuracy perspective. They also showed that the proposed model outperformed all the other comparative models in the total misclassification cost perspective. Consequently, it is expected that our study may contribute to build cost-effective intelligent intrusion detection systems.