• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.3
• /
• pp.279-286
• /
• 2015

The rapid increase of the current marine accidents is mainly due to the human execution errors. In an effort to address this, various kinds of researches such as construction of the digital vessels and vessel information monitoring systems have been conducted. But for safe navigation of vessels, it lack on systems study which can efficiently store, utilize and manage the mass data accepted by the vessel. In this paper, we propose a VWS(Virtual World System) that is based on the architecture of intelligent systems RVC(Reactive Layer-Virtual World-Considerative Layer) model of intelligent autonomous navigation system. VWS is responsible to store all the necessary information for safe navigation of the vessel and the information services to the sub-system of intelligent autonomous navigation system. VWS uses topology database to express the specific problem area, and utilizes a scheduling to reflect the characteristics of the real-time processing environment. Also, Virtual World defines API for the system to reflect the characteristics of the distributed processing environment. As a case study, the VWS is applied to a intelligent ship autonomous navigation system, and simulation is done to prove the effectiveness of the proposed system.

• Journal of Broadcast Engineering
• /
• v.25 no.4
• /
• pp.545-559
• /
• 2020

In this paper, we propose a content creation framework that enables users without programming experience to easily create interactive media content that responds to user gestures. In the proposed framework, users define the gestures they use and the media effects that respond to them by numbers, and link them in a text-based configuration file. In the proposed framework, the interactive media content that responds to the user's gesture is linked with the dynamic projection mapping module to track the user's location and project the media effects onto the user. To reduce the processing speed and memory burden of the gesture recognition, the user's movement is expressed as a gray scale motion history image. We designed a convolutional neural network model for gesture recognition using motion history images as input data. The number of network layers and hyperparameters of the convolutional neural network model were determined through experiments that recognize five gestures, and applied to the proposed framework. In the gesture recognition experiment, we obtained a recognition accuracy of 97.96% and a processing speed of 12.04 FPS. In the experiment connected with the three media effects, we confirmed that the intended media effect was appropriately displayed in real-time according to the user's gesture.

• Journal of the Institute of Convergence Signal Processing
• /
• v.3 no.1
• /
• pp.8-14
• /
• 2002

In this paper, we realized a real-time text-independent speaker recognition system using gaussian mixture model, and applied frame level likelihood normalization method which shows its effects in verification system. The system has three parts as front-end, training, recognition. In front-end part, cepstral mean normalization and silence removal method were applied to consider speaker's speaking variations. In training, gaussian mixture model was used for speaker's acoustic feature modeling, and maximum likelihood estimation was used for GMM parameter optimization. In recognition, likelihood score was calculated with speaker models and test data at frame level. As test sentences, we used text-independent sentences. ETRI 445 and KLE 452 database were used for training and test, and cepstrum coefficient and regressive coefficient were used as feature parameters. The experiment results show that the frame-level likelihood method's recognition result is higher than conventional method's, independently the number of registered speakers.

• Journal of the Institute of Convergence Signal Processing
• /
• v.20 no.3
• /
• pp.151-158
• /
• 2019

Patients with disabilities from various reasons such as disasters, injuries or chronic illness or elderly with limited body motion range due to aging are recommended to participate in rehabilitation programs at hospitals. But typically, it's not as simple for them to commute without help as they have limited access outside of the home. Also, regarding the perspectives of hospitals, having to maintain the workforce and have them take care of the rehabilitation sessions leads them to more expenses in cost aspects. For those reasons, in this paper, a home-based remote rehabilitation system using motion recognition is developed without needing help from others. This system can be executed by a personal computer and a stereo camera at home, the real-time user motion status is monitored using motion recognition feature. The system tracks the joint range of motion(Joint ROM) of particular body parts of users to check the body function improvement. For demonstration, total of 4 subjects with various ages and health conditions participated in this project. Their motion data were collected during all 3 exercise sessions, and each session was repeated 9 times per person and was compared in the results.

• Journal of the Institute of Convergence Signal Processing
• /
• v.12 no.2
• /
• pp.96-101
• /
• 2011

In recent days, the demand for the remote ECG monitoring system has been increasing and the automation of the monitoring system is becoming quite of a concern. Automatic detection of the abnormal ECG beats must be a necessity for the successful commercialization of these real time remote ECG monitoring system. From these viewpoints, in this paper, we proposed an automatic detection algorithm for the abnormal ECG beats using QRS width and RR interval patterns. In the previous research, many efforts have been done to classify the ECG beats into detailed categories. But, these approaches have disadvantages such that they produce lots of misclassification errors and variabilities in the classification performance. Also, they require large amount of training data for the accurate classification and heavy computation during the classification process. But, we think that the detection of abnormality from the ECG beats is more important that the detailed classification for the automatic ECG monitoring system. In this paper, we tried to detect the VEB which is most frequently occurring among the abnormal ECG beats and we could achieve satisfactory detection performance when applied the proposed algorithm to the MIT/BIH database.

• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.10
• /
• pp.473-478
• /
• 2017

Drones require altitude holding in order to achieve flight objectives. The altitude holding of the drone is to repeat the operation of raising or lowering the drone according to the altitude information being measured in real-time. When the drones are maintained altitude, the drone's altitude will continue to change due to external factors such as imbalance in thrust due to difference in motor speed or wind. Therefore, in order to maintain the altitude of drone, we have to exactly measure the continuously changing altitude of the drone. Generally, the acceleration sensor is used for measuring the height of the drones. In this method, there is a problem that the measured value due to the integration error accumulates, and the drone's vibration is recognized by the altitude change. To solve the difficulty of the altitude measurement, commercial drones and existing studies are used for altitude measurement together with acceleration sensors by adding other sensors. However, most of the additional sensors have a limitation on the measurement distance and when the sensors are used together, the calculation processing of the sensor values increases and the altitude measurement speed is delayed. Therefore, it is necessary to accurately measure the altitude of the drone without considering additional sensors or devices. In this paper, we propose a measurement algorithm that improves general altitude measurement method using acceleration sensor and show that accuracy of altitude holding and altitude measurement is improved as a result of applying this algorithm.

• Smart Media Journal
• /
• v.11 no.3
• /
• pp.39-53
• /
• 2022

Cloud of Things (CoT) can provide IoT applications with unlimited storage functions and processing power supported by cloud services. However, in a centralized cloud of things, it can create a single point of failure that can lead to bottleneck problems, outages of the CoT network. In this paper, to solve the problem of centralized cloud of things and interoperate between different service domains, we propose an IoT service interoperability system using distributed fog computing and blockchain technology. Distributed fog is used to provide real-time data processing and services in fog systems located at a geographically close distance to IoT devices, and to enable service interoperability between each fog using smart contracts and distributed ledgers of the blockchain. The proposed system provides services within a region close to the distributed fog entrusted with the service from the cloud, and it is possible to access the services of other fogs without going through the cloud even between fogs. In addition, by sharing a service right token issuance information between the cloud and fog nodes using a blockchain network, the integrity of the token can be guaranteed and reliable service interoperability between fog nodes can be performed.

• Information Systems Review
• /
• v.15 no.2
• /
• pp.1-19
• /
• 2013

Smart working sparked by iPhone3 opens a revolution in smart ways of working at any time, regardless of location and environment. Also, It provide real-time information processing and analysis, rapid decision-making and the productivity of businesses, including through the timely response and the opportunity to increase the efficiency. As a result, every company are developing mobile information systems. But company data is accessed from the outside, it has problems to solve like security, hacking and information leakage. Also, Mobile devices such as smart phones belonging to the privately-owned asset can't be always controlled to archive company security policy. In the meantime, public smart phones owned by company was always applied security policy. But it can't not apply to privately-owned smart phones. Thus, this paper is focused to archive company security policy, but also enable the individual's free to use of smart phones when we use mobile information systems. So, when we use smart phone as individual purpose, the normal operation of all smart phone functions. But, when we use smart phone as company purpose like mobile information systems, the smart phone functions are blocked like screen capture, Wi-Fi, camera to protect company data. In this study, we suggest the design and implementation of real time control and management of mobile device using MDM(Mobile Device Management) solution. As a result, we can archive company security policy and individual using of smart phone and it is the optimal solution in the BYOD(Bring Your Own Device) era.

• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.9
• /
• pp.351-360
• /
• 2018

The LWR (Locally Weighted Regression) model, which is traditionally a lazy learning model, is designed to obtain the solution of the prediction according to the input variable, the query point, and it is a kind of the regression equation in the short interval obtained as a result of the learning that gives a higher weight value closer to the query point. We study on an incremental ensemble learning approach for LWR, a form of lazy learning and memory-based learning. The proposed incremental ensemble learning method of LWR is to sequentially generate and integrate LWR models over time using a genetic algorithm to obtain a solution of a specific query point. The weaknesses of existing LWR models are that multiple LWR models can be generated based on the indicator function and data sample selection, and the quality of the predictions can also vary depending on this model. However, no research has been conducted to solve the problem of selection or combination of multiple LWR models. In this study, after generating the initial LWR model according to the indicator function and the sample data set, we iterate evolution learning process to obtain the proper indicator function and assess the LWR models applied to the other sample data sets to overcome the data set bias. We adopt Eager learning method to generate and store LWR model gradually when data is generated for all sections. In order to obtain a prediction solution at a specific point in time, an LWR model is generated based on newly generated data within a predetermined interval and then combined with existing LWR models in a section using a genetic algorithm. The proposed method shows better results than the method of selecting multiple LWR models using the simple average method. The results of this study are compared with the predicted results using multiple regression analysis by applying the real data such as the amount of traffic per hour in a specific area and hourly sales of a resting place of the highway, etc.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.48 no.4
• /
• pp.9-20
• /
• 2011

Future warfare paradigm is changing to network-centric warfare and effects-based operations. In order to find first and strike the enemy in the battlefield, friendly unit requires real-time target acquisition, intelligence collection, accurate situation assessment, and timely decision. The rapid development in advanced sensor technology and wireless networks requires a significant change in operational concepts of the battlefield surveillance. In particular, the introduction of a battlefield surveillance sensor network system is a big challenge to the ground forces which have lack of automated information collection assets. Therefore this paper proposes an ontology-based context-aware framework for the battlefield surveillance sensor network system which is needed for early finding the enemy and visualizing the battlefield in the ground force operations. Compared with the performance of existing systems, the one of the proposed framework has shown highly positive results by applying the context systems evaluation method. The framework has also proven to be satisfactory by the structured evaluation method using device collaboration. Since the proposed ontology-based context-aware framework has a lot of advantages in terms of scalability and reusability, the ground force's reconnaissance and surveillance system can be widely applied to expand in the future. And, ontology-based model has some weak points such as ontology data size, processing time, and limitation of network bandwidth. However, these problems can be resolved by customizing properly to fit the mission and characteristics of the unit. Moreover, development of the next-generation communication infrastructure can expedite the intelligent surveillance and reconnaissance service and may be expected to contribute greatly to expanding the information capacity.