• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.2138-2142
• /
• 2005

A wearable sensor system is proposed as a man-machine interface to control a device for walking assistance. The sensor system is composed of small sensors to detect the information about the user's body motion such as the activity level of skeletal muscles and the acceleration of each body parts. Each sensor includes a microcomputer and all the sensors are connected into a network by using the serial communication function of the microcomputer. The whole network is integrated into a belt made of soft fabric, thus, users can put on/off very easily. The sensor system is very reliable because of its decentralized network configuration. The body information obtained from the sensor system is used for controlling the assisting device to achieve a comfortable and an effective walking training.

• Journal of information and communication convergence engineering
• /
• v.7 no.4
• /
• pp.475-479
• /
• 2009

In ad hoc network, the scarce energy management of the mobile devices has become a critical issue in order to extend the network lifetime. Current research activity for the Minimum Energy Multicast (MEM) problem has been focused on devising efficient centralized greedy algorithms for static ad hoc networks. In this paper, we consider mobile ad hoc networks(MANETs) that could provide the reliable monitoring and control of a variety of environments for remote place. Mobility of MANET would require the topology change frequently compared with a static network. To improve the routing protocol in MANET, energy efficient routing protocol would be required as well as considering the mobility would be needed. In this paper, we propose a new method, the CACH(Context-aware Clustering Hierarchy) algorithm, a hybrid and clustering-based protocol that could analyze the link cost from a source node to a destination node. The proposed analysis could help in defining the optimum depth of hierarchy architecture CACH utilize. The proposed CACH could use localized condition to enable adaptation and robustness for dynamic network topology protocol and this provide that our hierarchy to be resilient. As a result, our simulation results would show that CACH could find energy efficient depth of hierarchy of a cluster.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.1
• /
• pp.454-475
• /
• 2018

This paper presents a novel Android malware classification model planned to classify and categorize Android malicious code at Drebin dataset. The amount of malicious mobile application targeting Android based smartphones has increased rapidly. In this paper, Restricted Boltzmann Machine and Deep Belief Network are used to classify malware into families of Android application. A texture-fingerprint based approach is proposed to extract or detect the feature of malware content. A malware has a unique "image texture" in feature spatial relations. The method uses information on texture image extracted from malicious or benign code, which are mapped to uncompressed gray-scale according to the texture image-based approach. By studying and extracting the implicit features of the API call from a large number of training samples, we get the original dynamic activity features sets. In order to improve the accuracy of classification algorithm on the features selection, on the basis of which, it combines the implicit features of the texture image and API call in malicious code, to train Restricted Boltzmann Machine and Back Propagation. In an evaluation with different malware and benign samples, the experimental results suggest that the usability of this method---using Deep Belief Network to classify Android malware by their texture images and API calls, it detects more than 94% of the malware with few false alarms. Which is higher than shallow machine learning algorithm clearly.

• Journal of Communications and Networks
• /
• v.17 no.4
• /
• pp.406-418
• /
• 2015

Cognitive radio networks (CRNs) have emerged as a promising solution to the problem of spectrum under utilization and artificial radio spectrum scarcity. The paradigm of dynamic spectrum access allows a secondary network comprising of secondary users (SUs) to coexist with a primary network comprising of licensed primary users (PUs) subject to the condition that SUs do not cause any interference to the primary network. Since it is necessary for SUs to avoid any interference to the primary network, PU activity precludes attempts of SUs to access the licensed spectrum and forces frequent channel switching for SUs. This dynamic nature of CRNs, coupled with the possibility that an SU may not share a common channel with all its neighbors, makes the task of multicast routing especially challenging. In this work, we have proposed a novel multipath on-demand multicast routing protocol for CRNs. The approach of multipath routing, although commonly used in unicast routing, has not been explored for multicasting earlier. Motivated by the fact that CRNs have highly dynamic conditions, whose parameters are often unknown, the multicast routing problem is modeled in the reinforcement learning based framework of learning automata. Simulation results demonstrate that the approach of multipath multicasting is feasible, with our proposed protocol showing a superior performance to a baseline state-of-the-art CRN multicasting protocol.

• Asia pacific journal of information systems
• /
• v.13 no.1
• /
• pp.103-118
• /
• 2003

Software project planning is usually represented by a project activity network that is composed of stages of tasks to be done and precedence restrictions among them. The project network is very complex and its construction requires a vast amount of field knowledge and experience. So this study proposes a case-based reasoning approach that can generate the project network automatically based on the past cases and modification knowledge. For the case indexing, we have adopted 17 factors, each with a few alternative values. A special structure of this problem is that the modification effort can be identified by each factor independently. Thus it is manageable to identify 85 primitive modification actions(add and delete activities) and estimate its modification efforts in advance. A specific case requires a combination of primitive modifications. Based on the modification effort knowledge, we have adopted the Least Modification approach as a metric of similarity between a new project and past cases. Using the Least Modification approach and modification knowledge base, we can automatically generate the project network. To validate the performance of Least Modification approach, we have compared its performance with an ordinary minimal distance approach for 21 test cases. The experiment showed that the Least Modification approach could reduce the modification effort significantly.

• Journal of Electrical Engineering and Technology
• /
• v.9 no.3
• /
• pp.1060-1071
• /
• 2014

Signals of the Electroencephalogram (EEG) can reflect the electrical background activity of the brain generated by the cerebral cortex nerve cells. This has been the mostly utilized signal, which helps in effective analysis of brain functions by supervised learning methods. In this paper, an approach for improving the accuracy of EEG signal classification is presented to detect epileptic seizures. Moreover, Independent Component Analysis (ICA) is incorporated as a preprocessing step and Short Time Fourier Transform (STFT) is used for denoising the signal adequately. Feature extraction of EEG signals is accomplished on the basis of three parameters namely, Standard Deviation, Correlation Dimension and Lyapunov Exponents. The Artificial Neural Network (ANN) is trained by incorporating Levenberg-Marquardt(LM) training algorithm into the backpropagation algorithm that results in high classification accuracy. Experimental results reveal that the methodology will improve the clinical service of the EEG recording and also provide better decision making in epileptic seizure detection than the existing techniques. The proposed EEG signal classification using feed forward Backpropagation Neural Network performs better than to the EEG signal classification using Adaptive Neuro Fuzzy Inference System (ANFIS) classifier in terms of accuracy, sensitivity, and specificity.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.2
• /
• pp.385-390
• /
• 2008

The Study of environment monitoring through huge network of wireless sensor node is worked with activity. The sensor nodes must be very small, light and low cost. The localization which may determine where a given node is physically located in a network is one of the quite important problems for wireless sensor network. But simple localization method is required as excluding the usage of GPS(Global Positioning System) by the limit condition such as the node size, costs, and so on. In this paper, very simple method using connectivity for the outdoor RF communication environment is proposed. The proposed method is demonstrated through simulation.

• The Journal of the Korea Contents Association
• /
• v.14 no.9
• /
• pp.567-581
• /
• 2014

Recently, with the introduction of social network services, studies that try to make use of them for the various purposes have been actively developed. In order to proceed with the research that takes advantage of social network services, it is necessary to review the relevant literature and to identify trends in researches. However, the researches of social network service since 2007 are massive amount, so to review the huge amount of relevant research literature is a very difficult task. Therefore, in this study, we analyze systematically the tendency of research related to social network service focusing on Twitter. Especially, we use the SLR(Systematic Literature Review) technique for systematic literature survey and analysis. For the literature survey, we select five well-known literature resource sites and 128 studies of literature that are surveyed. In order to identify various research trends, we conduct the survey with two research groups: researches since 2007 and researches since 2011. As a result of the investigation, since 2007, the researches associated with "Application", "User Activity" and "User Content Analysis" main study topics have been mostly carried out. In addition to the result, the trend of secondary study topics in a main study topic, trends in research based on the number of citations and the scale of the experimental data and characteristics of the author are analyzed from a variety of perspectives.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2012.05a
• /
• pp.819-822
• /
• 2012

This study is about social network services for tourism. In detail, the relationship among relation oriented activities, relation value, commitment and loyalty is analyzed in this paper.

• Journal of Korea Multimedia Society
• /
• v.23 no.8
• /
• pp.986-1005
• /
• 2020

In this paper, we propose AnoVid, an automated video annotation tool based on deep neural networks, that automatically generates various meta data for each scene or shot in a long drama video containing rich elements. To this end, a novel meta data schema for drama video is designed. Based on this schema, the AnoVid video annotation tool has a total of six deep neural network models for object detection, place recognition, time zone recognition, person recognition, activity detection, and description generation. Using these models, the AnoVid can generate rich video annotation data. In addition, AnoVid provides not only the ability to automatically generate a JSON-type video annotation data file, but also provides various visualization facilities to check the video content analysis results. Through experiments using a real drama video, "Misaeing", we show the practical effectiveness and performance of the proposed video annotation tool, AnoVid.