• Communications for Statistical Applications and Methods
• /
• v.27 no.4
• /
• pp.487-500
• /
• 2020

Insurers face increasing demands for cyber liability; entailed in part by a variety of new forms of risk of data breaches. As data breach occurrences develop, our understanding of the volatility in data breach counts has also become important as well as its expected occurrences. Volatility clustering, the tendency of large changes in a random variable to cluster together in time, are frequently observed in many financial asset prices, asset returns, and it is questioned whether the volatility of data breach occurrences are also clustered in time. We now present volatility analysis based on INGARCH models, i.e., integer-valued generalized autoregressive conditional heteroskedasticity time series model for frequency counts due to data breaches. Using the INGARCH(1, 1) model with data breach samples, we show evidence of temporal volatility clustering for data breaches. In addition, we present that the firms' volatilities are correlated between some they belong to and that such a clustering effect remains even after excluding the effect of financial covariates such as the VIX and the stock return of S&P500 that have their own volatility clustering.

• Smart Media Journal
• /
• v.12 no.11
• /
• pp.36-47
• /
• 2023

Industrial Control System(ICS), which controls facilities at major industrial sites, is increasingly connected to other systems through networks. With this integration and the development of intelligent attacks that can lead to a single external intrusion as a whole system paralysis, the risk and impact of security on industrial control systems are increasing. As a result, research on how to protect and detect cyber attacks is actively underway, and deep learning models in the form of unsupervised learning have achieved a lot, and many abnormal detection technologies based on deep learning are being introduced. In this study, we emphasize the application of preprocessing methodologies to enhance the anomaly detection performance of deep learning models on time series data. The results demonstrate the effectiveness of a Wavelet Transform (WT)-based noise reduction methodology as a preprocessing technique for deep learning-based anomaly detection. Particularly, by incorporating sensor characteristics through clustering, the differential application of the Dual-Tree Complex Wavelet Transform proves to be the most effective approach in improving the detection performance of cyber attacks.

• Journal of Families and Better Life
• /
• v.29 no.4
• /
• pp.175-186
• /
• 2011

The purpose of this study was to explore the differences in interactive peer play according to the type of problem behavior. The subjects were 112(67 boys, 45 girls) S-year-old children at 25 daycare centers in Seoul, Gyeonggi, and Gyeongsang areas. Instruments included the Preschool Behavior Questionnaire(PBQ; Behar & Stringfield, 1974) and the Penn Interactive Peer Play Scale(PIPPS) in both the teacher version(Choi & Shin, 2008) and the parent version(Fantuzzo, Mendez, & Tighe, 1998). The data were analyzed with descriptive statistics, cluster analysis, t-test, and one-way ANOVA using the SPSS 18.0 software program. The results showed that the clusters of problem behaviors on the PBQ could be grouped into four categories; 'hostility-aggressiveness', 'hyperactivity- distractibility', 'anxiety-fear', and 'combined'. In addition, group differences among the problem behaviors were significantly found in 'play disruption' and 'play disconnection' but not in 'play interaction' of the PIPPS on teachers' and parents' ratings. Specifically, group differences were not found in the parental reports, while significant group differences were noted in the 'play disconnection on PIPPS component of the teachers' reports.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.33-34
• /
• 2023

성장하는 빅 데이터 시장과 빅 데이터 수의 기하급수적인 증가는 기존 컴퓨팅 환경에서 데이터 처리의 어려움을 야기한다. 특히 이미지 데이터 처리 속도는 데이터양이 많을수록 현저하게 느려진다. 이에 본 논문에서는 Apache Spark와 OpenCV를 활용한 분산 클러스터 컴퓨팅 환경의 대용량 이미지 머신러닝 시스템을 제안한다. 제안하는 시스템은 Apache Spark를 통해 분산 클러스터를 구성하며, OpenCV의 이미지 처리 알고리즘과 Spark MLlib의 머신러닝 알고리즘을 활용하여 작업을 수행한다. 제안하는 시스템을 통해 본 논문은 대용량 이미지 데이터 처리 및 머신러닝 작업 속도 향상 방법을 제시한다.

• 한국노년학
• /
• v.36 no.3
• /
• pp.711-726
• /
• 2016

The purpose of this study was to analyze to 1) the differences according to demographic characteristics 2) select the type-specific communities online channels of the baby boomer customers group, who ever search for restaurant information through on-line for the previous three months. The study was based on a total of 280 samples obtained from on-line networking service users in a metropolitan area from April 15 to 30, 2016. The major findings are as follows. The data were analysed using frequency, factor analysis, cluster analysis and ${\chi}^2test$. According to the results of factor analysis, on-line utilizing attributes were separated into three factors: commitment of useful information, activity of leading on-line, and habit. The based on a factor analysis, cluster analysis was adopted to segment baby boomer customers. The identified four clusters showed in using on-line: type of active utilization, habit, seeking information and passive utilization. The clusters had significant differences in gender and monthly income by demographics. All of four clusters selected blog, face book, twitter in turn through the personal on-line channels. Cluster type of active utilization and habit selected restaurant home pages, restaurant blog, restaurant face book, restaurant twitter in turn through the public on-line channels. Cluster type of seeking information and passively utilization selected restaurant home pages, restaurant blog, restaurant twitter, restaurant face book in turn through the public on-line channels. Implications and future research were also discussed.

• Journal of the Korean Data and Information Science Society
• /
• v.20 no.2
• /
• pp.329-338
• /
• 2009

The importance performance analysis is a simple and condensed analytic method for decision making based on the level of performance or satisfaction. Many researches already have witnessed usefulness of the importance performance analysis, but it also has some drawbacks from the statistical points of view. In this article, some additional techniques dealing the importance performance analysis are introduced and it is shown that these techniques would turn out to be very informative. The importance performance analysis uses the arithmetic average as the main statistic, but by the use of the median, the frequency and the cluster analysis it is shown that the importance performance analysis can be carried out with more crucial information. In addtion to that, it is demonstrated that the combination of the analytic hierarchy process and importance performance analysis could enable more reliable decision making.

• Korean Journal of Social Welfare Studies
• /
• v.49 no.1
• /
• pp.163-190
• /
• 2018

The citizen-initiative has been frequently mentioned in community building project which is being promoted by Seoul City. The citizen-initiative has become an important concept in the direction of community welfare efforts. However, this concept has not been defined clearly in social welfare. In this context, the purpose of this study is to find how the practitioners of the social welfare practice field recognize the concept of citizen-initiative. In this study, concept mapping method was used to generate 59 statements about the citizeninitiative in 10 social workers in Seoul. Multidimensional scaling analysis and hierarchical cluster analysis are used to do mapping and grouping the 59 statements. The results are as follows. A total of 6 categories were derived. The six categories are named "Inducement of Participation", "Practice", "Procedure", "Awareness and Interest extension", "Expression of Opinion", "Attitude and Emotion". "Practice" category was revealed as a core category in the concept of citizen-initiative. This study is meaningful as a first step to discuss "what is the citizen-initiative?" and to make consensus in social welfare academic area and practice field.

• Journal of Korea Multimedia Society
• /
• v.21 no.8
• /
• pp.952-959
• /
• 2018

Clustering is one of the most fundamental algorithms in machine learning. The performance of clustering is affected by the distribution of data, and when there are more data or more dimensions, the performance is degraded. For this reason, we use a stacked auto encoder, one of the deep learning algorithms, to reduce the dimension of data which generate a feature vector that best represents the input data. We use k-means, which is a famous algorithm, as a clustering. Sine the feature vector which reduced dimensions are also multi dimensional, we use the Euclidean distance as well as the cosine similarity to increase the performance which calculating the similarity between the center of the cluster and the data as a vector. A deep clustering networks combining a stacked auto encoder and k-means re-trains the networks when the k-means result changes. When re-training the networks, the loss function of the stacked auto encoder and the loss function of the k-means are combined to improve the performance and the stability of the network. Experiments of benchmark image ad document dataset empirically validated the power of the proposed algorithm.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.37 no.1
• /
• pp.27-38
• /
• 2013

Word-of-mouth (WOM) communication (traditionally important in consumption) is expanding its influence into cyber space and is playing an important role in online shopping. Consumers who use online shopping might not readily make purchasing decisions due to information overload, lack of accurate product recognition, and the distrust of commercial information. Subsequently, people use WOM communication for a mutual interchange with others who share common concerns, interests, and purposes. This study examines the consumer characteristics, perceived risk on online shopping and benefits of online shopping according to WOM behavior that may significantly affect consumer actions. Factor analysis, t-test, one-way ANOVA, cluster analysis, and Chi-square analysis were used for statistical analysis to identify the differences in consumer characteristics. Online WOM behavior consumers purchased more various items than offline WOM behavior consumers; however, the most influential purchasing factor was price regardless of WOM behavior. Offline WOM behavior consumers have shown higher perceived online shopping risks and benefits.

• Journal of Digital Contents Society
• /
• v.16 no.3
• /
• pp.373-379
• /
• 2015

In this paper, we propose an online VQ Codebook generation method for updating an existing VQ Codebook in real-time and adding to an existing cluster with newly created text data which are news paper, web pages, blogs, tweets and IoT data like sensor, machine. Without degrading the performance of the batch VQ Codebook to the existing data, it was able to take advantage of the newly added data by using a triangle inequality which modifying the VQ Codebook progressively show a high degree of accuracy and speed. The result of applying to test data showed that the performance is similar to the batch method.