• Journal of the Korea Society of Computer and Information
• /
• v.18 no.3
• /
• pp.35-45
• /
• 2013

MANET has a weak point because it allows access from not only legal nodes but also illegal nodes. Most of the MANET researches had been focused on attack on routing path or packet forwarding. Nevertheless, there are insuffcient studies on a comprehensive approach to detect various attacks on malicious nodes at packet forwarding processes. In this paper, we propose a technique, named DTecBC (detection technique of malicious node behaviors based on collaboration), which can handle more effciently various types of malicious node attacks on MANET environment. The DTecBC is designed to detect malicious nodes by communication between neighboring nodes, and manage malicious nodes using a maintain table. OPNET tool was used to compare with Watchdog, CONFIDANT, SRRPPnT for verifying effectiveness of our approach. As a result, DTecBC detects various behaviors of malicious nodes more effectively than other techniques.

• The KIPS Transactions:PartC
• /
• v.19C no.2
• /
• pp.83-90
• /
• 2012

MANET(Mobile Ad-Hoc Network) has a weakness from a security aspect because it operates where no wired network is built, which causes the exposed media, dynamic topology, and the lack of both central monitoring and management. It is especially difficult to detect and mitigate a malicious node because there is not a mediator which controls the network. This kind of malicious node is closely connected to the routing in the field of study of Ad-Hoc security. Accordingly this paper proposes the method on how to enhance the security for the safe and effective routing by detecting the malicious node. We propose MBC(Identification technition of Malicious Behavior node based on Collaboration in MANET) that can effectively cope with malicious behavior though double detecting the node executing the malicious behavior by the collaboration between individual node and the neighbor, and also managing the individual nodes in accordance with the trust level obtained. The simulation test results show that MBC can find the malicious nodes more accurately and promptly that leads to the more effectively secure routing than the existing method.

• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.1
• /
• pp.19-24
• /
• 2018

This paper presents an IoT platform of common interfaces that are flexible IoT applications and Connect the smart devices. The IoT platform includes automatic collaboration discovery the smart Device. It is different things case with connection each device through IoT Platforms are each device and application service. Due to these heterogeneities, it is quite advantages to develop applications working with derived IoT services. This circumstance needs the generic interface and results in a range of IoT architectures by not only the environments settings and discovery resource but also varied uniqe to implementation services working with IoT applications. Therefore, this suggestion of solve the problems and make it possible independent platforms always alive to connection with each devices based on the generic interface. The generic interface is heterogeneity-driven solve the problems and effectively contributions a platform that could be operated in diverse IoT Platforms.

• Journal of Intelligence and Information Systems
• /
• v.13 no.2
• /
• pp.69-80
• /
• 2007

The preferences of customers change over time. However, existing collaborative filtering (CF) systems are static, since they only incorporate information regarding whether a customer buys a product during a certain period and do not make use of the purchase sequences of customers. Therefore, the quality of the recommendations of the typical CF could be improved through the use of information on such sequences. In this study, we propose a new methodology for enhancing the quality of CF recommendation that uses customer purchase sequences. The proposed methodology is applied to a large department store in Korea and compared to existing CF techniques. Various experiments using real-world data demonstrate that the proposed methodology provides higher quality recommendations than do typical CF techniques with better performance.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.5
• /
• pp.663-668
• /
• 2022

As the number of people who experience sleep disorders is increasily growing, users' desire to improve their sleep quality has also increased. Acoordingly, the 'Sleeptech' market is showing a steady growth. This study designs and proposes a system after consideration of existing related research that can help modern people overcome sleep disorders, which is based on the necessity for customized sleep hygien service. This system analyzes user's sleep data collected through smartphone built-in sensors to calculate sleep patterns, provides customized sleep hygiene-based solutions to users through collaborative filtering, and provides an environment suitable for sleep through the automatic control of IoT devices. This method of using sleep data is expected to contribute to the improvement of the quality of life of modern people suffering from sleep disorders, which results from expansion to Sleeptech market as well as improvement of users' sleep habits.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.1
• /
• pp.11-19
• /
• 2024

Multi-agent systems can be utilized in various real-world cooperative environments such as battlefield engagements and unmanned transport vehicles. In the context of battlefield engagements, where dense reward design faces challenges due to limited domain knowledge, it is crucial to consider situations that are learned through explicit sparse rewards. This paper explores the collaborative potential among allied agents in a battlefield scenario. Utilizing the Multi-Robot Warehouse Environment(RWARE) as a sparse reward environment, we define analogous problems and establish evaluation criteria. Constructing a learning environment with the QMIX algorithm from the reinforcement learning library Ray RLlib, we enhance the Agent Network of QMIX and integrate Random Network Distillation(RND). This enables the extraction of patterns and temporal features from partial observations of agents, confirming the potential for improving the acquisition of sparse reward experiences through intrinsic rewards.

• Journal of vocational education research
• /
• v.37 no.3
• /
• pp.65-83
• /
• 2018

In this study, we want to analyze the aspect that required in the classroom for the operation of NCS-based curriculum, the interest of specialized subject teachers on implementable teaching and learning methods. As a result, the overall interest in teaching-learning method of specialized subject teachers was similar to that of non-user patterns among four types of interest patterns. In other words, specialized subject teachers want to know more about teaching-learning method for applying NCS-based curriculum, but we are only aware of the general facts at present, and it seems that there is low interest in actual operation. In addition, there was no statistically significant difference in the degree of interest in the teaching-learning method according to general variables(gender, related training experience, career, and curriculum group) of the specialized subject teachers. The specialized subject teachers are not well aware of the influence of the teaching-learning method according to the introduction of NCS-based curriculum, and to that end, there was little interest in collaboration with colleagues.

• Trans-
• /
• v.13
• /
• pp.35-58
• /
• 2022

This study predicts the paradigm shift that the development of artificial intelligence technology will bring to the production of music content, and suggests that works created through collaboration between artificial intelligence and humans can have artistic value as finished products. Anyone can easily produce music content using artificial intelligence composition programs, and it has become an opportunity to inspire artists with various attempts and creative ideas. Although artificial intelligence technology provides convenience in human life and benefits a lot in the efficient aspect of work, it is difficult to escape the perception of data-based pattern music in the art field so far. Pattern music with many quantitative elements is not recognized as a complete creation due to the absence of abstract symbolism or meaning pursued by art. However, it predicts that if qualitative elements such as emotions and creativity are given to artificial intelligence music through human collaboration, it can be recognized as a complete work of art. The development of artificial intelligence technology increases access to culture and art from the public, and it can be expected that anyone can enjoy it as well as aesthetic experiences. In addition, various contents can be produced by improving individual digital literacy, and it is an opportunity to share and communicate with others. As such, artificial intelligence technology serves as a medium connecting the public with culture and art, and is narrowing the gap between humans and technology through art activities. Along with this cultural phenomenon, we predict the possibility of research on the production of artificial intelligence music contents with artistic value and the development of various convergence and complex art contents using artificial intelligence technology in the future.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.25 no.2
• /
• pp.59-71
• /
• 2022

This study considered regional differences in the university-industry collaboration of Korean universities and performed cluster analysis to identify the spatial range with high university-industry collaboration connectivity. By university establishment type, it was found that the university-industry collaboration capacity of the major national university was superior overall, especially in the technology transfer & commercialization sector and the infrastructure sector, compared to private universities and general national universities. The spatial pattern of university-industry collaboration capacity showed relatively clear differences by city and province. In terms of university-industry collaboration capacity by sector, it was confirmed that the regional gap was not large in the talent training sector and the infrastructure sector, but the regional gap was relatively large in the technology transfer & commercialization sector and the start-up sector. As a result of the cluster analysis to identify a spatial range with high connectivity in terms of similarity and spatial proximity of university-industry collaboration patterns, it is divided into 15 clusters. It is found that most of major national universities are included in one of 15 clusters where all sectors of university-industry collaboration are strong. Therefore, as a policy measure to achieve regional innovative growth through enhancing the effectiveness of university-industry collaboration, we propose the establishment of a hub & spoke network-type collaboration system in which a major national university acts as a hub and nearby local universities play a spoke role.

• The Journal of Society for e-Business Studies
• /
• v.22 no.3
• /
• pp.75-85
• /
• 2017

Personalization recommendations have already proven in many areas of the e-commerce industry. For personalization recommendations, additional work such as reclassifying items is generally necessary, which requires personal information. In this study, we propose a recommendation technique that neither exploit personal information nor reclassify items. We focus on music recommendation and performed experiments with actual music listening data. Experimental analysis shows that the proposed method may result in meaningful recommendations albeit it exploits less amount of data. We analyze the appropriate number of items and present future considerations for contextual recommendation.