• The KIPS Transactions:PartB
• /
• v.17B no.3
• /
• pp.227-232
• /
• 2010

This paper proposes the real time lip reading method in the embedded environment. The embedded environment has the limited sources to use compared to existing PC environment, so it is hard to drive the lip reading system with existing PC environment in the embedded environment in real time. To solve the problem, this paper suggests detection methods of lip region, feature extraction of lips, and awareness methods of phonetic words suitable to the embedded environment. First, it detects the face region by using face color information to find out the accurate lip region and then detects the exact lip region by finding the position of both eyes from the detected face region and using the geometric relations. To detect strong features of lighting variables by the changing surroundings, histogram matching, lip folding, and RASTA filter were applied, and the properties extracted by using the principal component analysis(PCA) were used for recognition. The result of the test has shown the processing speed between 1.15 and 2.35 sec. according to vocalizations in the embedded environment of CPU 806Mhz, RAM 128MB specifications and obtained 77% of recognition as 139 among 180 words were recognized.

• Communications of the Korean Mathematical Society
• /
• v.26 no.3
• /
• pp.499-513
• /
• 2011

By using the Riccati transformation technique, we study the oscillation and asymptotic behavior for the third-order nonlinear delay dynamic equations $(c(t)(p(t)x^{\Delta}(t))^{\Delta})^{\Delta}+q(t)f(x({\tau}(t)))=0$ on a time scale T, where c(t), p(t) and q(t) are real-valued positive rd-continuous functions defined on $\mathbb{T}$. We establish some new sufficient conditions which ensure that every solution oscillates or converges to zero. Our oscillation results are essentially new. Some examples are considered to illustrate the main results.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2000.06a
• /
• pp.1533-1539
• /
• 2000

In this paper, we propose a design method using Taguchi method and a neural network. Using this method, we can design a dual-stage actuator having the required tracking/focusing properties in real time. Also, as an application of this method, a proposed dual-stage pick-up actuator having the required properties was designed. The seek time of this designed actuator is less than 13 msec by a time optimal technique. Simulation results show that this method can potentially be implemented in all the dual-stage actuators.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.5
• /
• pp.980-997
• /
• 2013

Nowadays, wireless communication has a great advantage in technology. We use wireless devices almost in all expected life such as: entertainment, working and recently in the healthcare area, where Wireless Body Area Networks (WBANs) become a hot topic for researchers and system designers. Recent work on WBANs focus on related issues to communication protocol, especially ZigBee network is fine tuned to meet particular requirements in healthcare area. For example, some papers present real-time patient monitoring via ZigBee communication given the short distance between body sensors and remote devices, while the other work solve the limited coverage problem of Zigbee by designing mechanisms to relay Zigbee data to other types of wire or wireless infrastructure. However, very few of them investigate the scenarios of ZigBee coexisting or integrated with other networks. In this paper, we present the real-time data transmission from ZigBee end devices to Wide Area Network (WAN), Worldwide interoperation for microwave access network (WiMAX) and Long Term Evolution network (LTE). We provide in detail the ZigBee gateway components. Our simulation is conducted by OPNET, we visualize many topology network scenarios in ZigBee hybrid system. The results in simulation show that ZigBee end devices can successfully transmit data in real-time to other network end devices.

• Journal of Korean Elementary Science Education
• /
• v.40 no.4
• /
• pp.433-442
• /
• 2021

The purpose of this study is to develop an artificial-intelligence STEAM program for real-time interactive online class for elementary science and to analyze its effect on science academic achievement and creative problem-solving ability. The applied unit was 'Life of plant', a 4th grade science subject with high difficulty in teaching and learning mainly by memorization. The theme of the program is 'Creating a doctor of plant artificial intelligence chatbot'. The results of this study were as follows: The program developed in this study had a positive effect on elementary school students' science academic achievement and creative problem-solving ability. Therefore, the artificial intelligence STEAM program for elementary science interactive online class is effective in improving students' scientific academic achievement and creative problem-solving ability, and further research on artificial intelligence STEAM education theory, method, and practice is required.

• Proceedings of the Korean Institute Of Construction Engineering and Management
• /
• 2007.11a
• /
• pp.823-826
• /
• 2007

In the construction project, the efforts to use IT for efficient management and improvement of productivity is gradually increasing. For instance, the cite management model with 3D CAD and RFID shows one of efforts this model define and systematize a variety of data occurred each work unit(design, material and process management information, etc). However, so far, there has been the problem monitoring the site due to the an inaccurate data and low-practice which people should input in manual. In this paper, we would like to establish the data for real time monitoring system with data inputting automatically from RTPM system and the site, and analyze the relationship between tables consist of similar data through RED Diagram.

• The Bulletin of The Korean Astronomical Society
• /
• v.44 no.1
• /
• pp.61.3-61.3
• /
• 2019

We report the status of KMTNet (Korea Microlensing Telescope Network) microlensing. From KMTNet event-finder, we are annually detecting over 2500 microlensing events. In 2018, we have carried out a real-time alert for only the Northern bulge fields. It was very helpful to select Spitzer targets. Thanks to the real-time alert, KMT-only events for which OGLE and MOA could not detect have been largely increased. The KMTNet event-finder and alert-finder algorithms are being upgraded every year. From these, we found 18 exoplanets and various interesting events, such as an exomoon-candidate, a free-floating candidate, and brown dwarfs, which are very difficult to be detected by other techniques including radial velocity and transit. In 2019, the KMTNet alert will be available in real-time for all bulge fields. As before, we will continue to collaborate with Spitzer team to measure the microlens parallaxes, which are required for estimating physical parameters of the lens. Thus, the KMTNet alert will be helpful to select Spitzer targets again. Also we plan to do follow-up observations for high-magnification events to study the planet multiplicity function. The KMTNet alert will play an important role to do follow-up observations for high-magnification events. Also, we will search for free-floating planets with short timescale (< 3 days) to study the planet frequency in our Galaxy.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.32B no.6
• /
• pp.909-921
• /
• 1995

The objective of this paper is to develop an algorithm for a real-time automatic fingerprint recognition system. The algorithm employs the Fast Fourier Transform (FFT) in determining the directions of ridges in fingerprint images, and utilizes statistical information in recognizing the fingerprints. The information used in fingerprint recognition is based on the dircetions along ridge curves and characteristic points such as core points and delta points. In order to find ridge directions, the algorithm applies the FFT to a small block of the size 8x8 pixels, and decides the directions by interpreting the resulted Fourier spectrum. By using the FFT, the algorithm does not require conventional preprocessing procedures such as smoothing, binarization, thinning, and restorationl. Finally, in matching two fingerprint images, the algorithm searches and compares two kinds of feature blocks, one as the blocks where the dircetions cannot be defined from the Fourier spectrum, and the other as the blocks where the changes of directions become abrupt. The proposed algorithm has been implemented on a SunSparc-2 workstation under the Open Window environment. In the experiment, the proposed algorithm has been applied to a set of fingerprint images obtained by a prism system. The result has shown that while the rate of Type II error - Incorrect recognition of two different fingerprints as the identical fingerprints - is held at 0.0%, the rate of Type I error - Incorrect recognition of two identical fingerprints as the different ones - is 2.2%.

• Journal of Internet of Things and Convergence
• /
• v.10 no.2
• /
• pp.103-108
• /
• 2024

In this paper, a smart elevator system was studied using real-time object detection technology based on YOLO(You only look once)v5. When an external elevator button is pressed, the YOLOv5 model analyzes the camera video to determine whether there are people waiting, and if it determines that there are no people waiting, the button is automatically canceled. The study introduces an effective method of implementing object detection and communication technology through YOLOv5 and MQTT (Message Queuing Telemetry Transport) used in the Internet of Things. And using this, we implemented a smart elevator system that determines in real time whether there are people waiting. The proposed system can play the role of CCTV (closed-circuit television) while reducing unnecessary power consumption. Therefore, the proposed smart elevator system is expected to contribute to safety and security issues.

• IE interfaces
• /
• v.24 no.2
• /
• pp.119-127
• /
• 2011

Most companies have been increasing temporary work projects to maximize the usage of their resources. They also have been developing the effective techniques for analyzing and managing the state of the projects. In order to monitor the state of a project in real-time and predict the project's future state more accurately, this paper suggests the Bayesian Network (BN) as a tool for discovering the causes of project risk and presenting the failure probability of the project. The proposed BN modeling method with consideration of the Earned Value Management (EVM) method shows how to induce the predictive and conditional probability of the risk occurrence in the future. The advantages of the suggested model are (1) that the cause of a project risk can be easily figured out via the BN, (2) that the future value of the project can be sufficiently increased by updating relevant components of the project, and (3) that more credible prediction can be made in the similar and future situation by using the data obtained in current analysis. A numerical example is also given.