• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.377-379
• /
• 2023

Concept drift detection on data stream is the major issue to maintain the performance of the machine learning model. Since the online stream is to be a function of time, the classical statistic methods are hard to apply. In particular case of seasonal time series, a novel window strategy with Fourier analysis however, gives a chance to adapt the classical methods on the series. We explore the KS-test for an adaptation of the periodic time series and show that this strategy handles a complicate time series as an ordinary tabular dataset. We verify that the detection with the strategy takes the second place in time delay and shows the best performance in false alarm rate and detection accuracy comparing to that of arbitrary window sizes.

• Bulletin of the Korean Chemical Society
• /
• v.33 no.10
• /
• pp.3298-3302
• /
• 2012

Although offline enrichment of phosphorylated peptides is widely used, enrichment for phosphopeptides using $TiO_2$ is often performed manually, which is labor-intensive and can lead to irreproducible results. To address the problems associated with offline enrichment and to improve the effectiveness of phosphopeptide detection, we developed an automated online enrichment system for phosphopeptide analysis. A standard protein mixture comprising BSA, fetuin, crystalline, ${\alpha}$-casein and ${\beta}$-casein, and ovalbumin was assessed using our new system. Our multidimensional system has four main parts: a sample pump, a 20-mm $TiO_2$-based column, a weak anion-exchange, and a strong cation-exchange (2:1 WAX:SCX) separation column with LC/MS. Phosphorylated peptides were successfully detected using the $TiO_2$-based online system with little interference from nonphosphorylated peptides. Our results confirmed that our online enrichment system is a simple and efficient method for detecting phosphorylated peptides.

• Journal of Korea Game Society
• /
• v.15 no.1
• /
• pp.35-44
• /
• 2015

The purpose of this study is to analyze user-generated rules in online games and to define the way of players' identities are developed. This study focuses on the online game League of Legends, which originated from use map system. Based on rule theory, this study analyzes the characteristics of user-generated rules. As the result, this study proves that the main rule of online game is not the rules made by developers, but the emergent rules made by players. Through rule-detection and rule-selection process, user-generated rules change the game system. Therefore, the result of this study expects to show meaningful roles of players in game system.

• Industrial Engineering and Management Systems
• /
• v.1 no.1
• /
• pp.64-72
• /
• 2002

In the field of plant maintenance, data that are gathered by sensors on multiple machines are handled and analyzed. Online or pseudo online data handling is required on such fields. When the data occurrence speed exceeds the data handling speed, multiple data should be handled at a time (batch data handling or pseudo online data handling). If l amount of data are received at one time following N amount of data, how to estimate the new parameters effectively is a great concern. A new simplified calculation method, which calculates the N data's weights, is introduced. Numerical examples show that this new method has a fairly god estimation accuracy and the calculation time is less than 1/10 compared with the case when the whole data are re-calculated. Even under the restriction calculation ability in the apparatus is limited, this proposed method makes the failure detection of equipments possible in early stages with a few new coming data. This method would be applicable in many data handling fields.

• Information Systems Review
• /
• v.12 no.2
• /
• pp.89-104
• /
• 2010

Recently, ubiquitous sensor network (USN) has been applied to many areas including environment monitoring. A few studies applied the USN to disaster prevention and emergency management, in particular, aiming to conserve cultural heritage. USN is an useful technology to do online real-time monitoring for the purpose of early detection of the fire which is a critical cause of damage and destruction of cultural heritages. It is necessary to online monitor the cultural heritages that human has a difficulty to access or their external appearance and beauty are important, by using the USN. However, there exists false warning from USN-based monitoring systems without human intervention. In this paper, we presented an alternative to resolve the problem by applying ontology. Our intelligent fire early detection systems for conserving cultural heritages are based on ontology and inference rules, and tested under laboratory environments.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.17 no.3
• /
• pp.121-129
• /
• 2024

The rapid advancement of digital technology and the COVID-19 pandemic have significantly accelerated the growth of online commerce, highlighting the need for support mechanisms that enable small business owners to effectively respond to these market changes. In response, this paper presents a foundational technology leveraging the Online to Offline (O2O) strategy to automatically capture products displayed on retail shelves and utilize these images to create virtual stores. The essence of this research lies in precisely identifying and recognizing the location and names of displayed products, for which a single-class-targeted, lightweight model based on YOLOv8, named ESD-YOLOv8, is proposed. The detected products are identified by their names through feature-point-based technology, equipped with the capability to swiftly update the system by simply adding photos of new products. Through experiments, product name recognition demonstrated an accuracy of 74.0%, and position detection achieved a performance with an F2-Score of 92.8% using only 0.3M parameters. These results confirm that the proposed method possesses high performance and optimized efficiency.

• Journal of Korea Game Society
• /
• v.16 no.2
• /
• pp.51-60
• /
• 2016

The incidents of massive personal information being leaked are occurring continuously over recent years. Personal information leaked outside is used for an illegal use of other's name and account theft. Especially it is happening on online games whose virtual goods, online game money and game items can be exchanged with real cash. When we research the real identity theft cases that happened in an online game, we can see that they happen massively in a short time. In this study, we define the characteristics of the mass attacks of the automated identity theft cases that occur in online games. Also we suggest a system to detect and prevent identity theft attacks in real time.

• The Journal of Society for e-Business Studies
• /
• v.16 no.3
• /
• pp.249-261
• /
• 2011

The rapid growth of e-business market makes new online companies to start and existing offline companies to join in this area. As the number of players of this market grows rapidly, the competition among them is very intense. Many companies invest huge resources to online marketing including search advertisement, email advertisement and banner advertisement. Because these traditional online marketing activities mainly focus on how to invite visitors to their web sites, ROI of these marketing activities are getting lower. Many companies are looking for a new marketing method to escape this situation. In this paper, we propose ROMS (Realtime Online Marketing System) which supports tools to improve conversion ratio of e-commerce sites, ROMS gathers behavioral data of visitors and analyzes it in realtime. ROMS supports live chats, visitor profiling, context analysis, event detection, and live marketing. With ROMS, personalized offers based on visitors' realtime context can be made for each visitor.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.37 no.2
• /
• pp.106-114
• /
• 2017

This paper presents an automated subsurface micro void detection technique based on pulsed infrared thermography for inspecting epoxy molding compounds (EMC) used in electronic device packaging. Subsurface micro voids are first detected and visualized by extracting a lock-in amplitude image from raw thermal images. Binary imaging follows to achieve better visualization of subsurface micro voids. A median filter is then applied for removing sparse noise components. The performance of the proposed technique is tested using 36 EMC samples, which have subsurface (below $150{\mu}m{\sim}300{\mu}m$ from the inspection surface) micro voids ($150{\mu}m{\sim}300{\mu}m$ in diameter). The experimental results show that the subsurface micro voids can be successfully detected without causing any damage to the EMC samples, making it suitable for automated online inspection.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.12
• /
• pp.5905-5926
• /
• 2017

Sentiments can profoundly affect individual behavior as well as decision-making. Confronted with the ever-increasing amount of review information available online, it is desirable to provide an effective sentiment model to both detect and organize the available information to improve understanding, and to present the information in a more constructive way for consumers. This study developed a unified phrase-based topic and sentiment detection model, combined with a tracking model using incremental hierarchical dirichlet allocation (PTSM_IHDP). This model was proposed to discover the evolutionary trend of topic-based sentiments from online reviews. PTSM_IHDP model firstly assumed that each review document has been composed by a series of independent phrases, which can be represented as both topic information and sentiment information. PTSM_IHDP model secondly depended on an improved time-dependency non-parametric Bayesian model, integrating incremental hierarchical dirichlet allocation, to estimate the optimal number of topics by incrementally building an up-to-date model. To evaluate the effectiveness of our model, we tested our model on a collected dataset, and compared the result with the predictions of traditional models. The results demonstrate the effectiveness and advantages of our model compared to several state-of-the-art methods.