• Journal of the Korea Institute of Information Security & Cryptology
• /
• 제21권6호
• /
• pp.183-190
• /
• 2011

In this paper, we propose a prototype system for abnormal sound detection and identification which detects and recognizes the abnormal situations by means of analyzing audio information coming in real time from CCTV cameras under surveillance environment. The proposed system is composed of two layers: The first layer is an one-class support vector machine, i.e., support vector data description (SVDD) that performs rapid detection of abnormal situations and alerts to the manager. The second layer classifies the detected abnormal sound into predefined class such as 'gun', 'scream', 'siren', 'crash', 'bomb' via a sparse representation classifier (SRC) to cope with emergency situations. The proposed system is designed in a hierarchical manner via a mixture of SVDD and SRC, which has desired characteristics as follows: 1) By fast detecting abnormal sound using SVDD trained with only normal sound, it does not perform the unnecessary classification for normal sound. 2) It ensures a reliable system performance via a SRC that has been successfully applied in the field of face recognition. 3) With the intrinsic incremental learning capability of SRC, it can actively adapt itself to the change of a sound database. The experimental results with the qualitative analysis illustrate the efficiency of the proposed method.

• The Korean Journal of Applied Statistics
• /
• 제34권3호
• /
• pp.309-327
• /
• 2021

Dynamic treatment regimes (DTRs) are decision-making rules designed to provide personalized treatment to individuals in multi-stage randomized trials. Unlike classical methods, in which all individuals are prescribed the same type of treatment, DTRs prescribe patient-tailored treatments which take into account individual characteristics that may change over time. The Q-learning method, one of regression-based algorithms to figure out optimal treatment rules, becomes more popular as it can be easily implemented. However, the performance of the Q-learning algorithm heavily relies on the correct specification of the Q-function for response, especially in observational studies. In this article, we examine a number of double-robust weighted least-squares estimating methods for Q-learning in high-dimensional settings, where treatment models for propensity score and penalization for sparse estimation are also investigated. We further consider flexible ensemble machine learning methods for the treatment model to achieve double-robustness, so that optimal decision rule can be correctly estimated as long as at least one of the outcome model or treatment model is correct. Extensive simulation studies show that the proposed methods work well with practical sample sizes. The practical utility of the proposed methods is proven with real data example.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• 제21권12호
• /
• pp.395-400
• /
• 2020

Pigs have been used widely in biomedical research owing to their physiologic and anatomic similarities to humans. Analysis of the hematologic and biochemical values in pigs is an important basis for biomedical research and veterinary clinical diagnosis, but research on transgenic pigs has been sparse. This study was conducted to obtain basic data on transgenic pigs and to describe and compare the reference values for hematologic and biochemical parameters in human tissue plasminogen activator (htPA) transgenic pigs vs normal pigs. Blood samples were obtained from 7 normal LY (Landrace-Yorkshire crossbred) pigs and 8 transgenic pigs and 16 hematologic and 15 serum biochemical parameters were tested. Among the hematologic parameters tested, significant differences were observed in the red blood cells (RBC), mean red blood cell hemoglobin (MCH), and lymphocytes (LYM), between the non-transgenic and transgenic pigs. Among the biochemical parameters tested, the blood urea nitrogen (BUN), total protein (TP), cholesterol (CHOL), alanine aminotransferase (ALT), creatinine (CREA), gamma glutamyl transpeptidase (GGT), globin (GOB), and amylase (AMYL) showed significant differences between the two groups. Thus, the values determined in this study can be used as basic reference values for transgenic pigs and will contribute to their use in biomedical research.

• Animal Bioscience
• /
• 제35권11호
• /
• pp.1787-1799
• /
• 2022

Objective: Choline deficiency, one main trigger for nonalcoholic fatty liver disease (NAFLD), is closely related to lipid metabolism disorder. Previous study in a choline-deficient model has largely focused on gene expression rather than gene structure, especially sparse are studies regarding to alternative splicing (AS). In modern life science research, primary hepatocytes culture technology facilitates such studies, which can accurately imitate liver activity in vitro and show unique superiority. Whereas limitations to traditional hepatocytes culture technology exist in terms of efficiency and operability. This study pursued an optimization culture method for duck primary hepatocytes to explore AS in choline-deficient model. Methods: We performed an optimization culture method for duck primary hepatocytes with multi-step digestion procedure from Pekin duck embryos. Subsequently a NAFLD model was constructed with choline-free medium. RNA-seq and further analysis by rMATS were performed to identify AS events alterations in choline-deficency duck primary hepatocytes. Results: The results showed E13 (embryonic day 13) to E15 is suitable to obtain hepatocytes, and the viability reached over 95% by trypan blue exclusion assay. Primary hepatocyte retained their biological function as well identified by Periodic Acid-Schiff staining method and Glucose-6-phosphate dehydrogenase activity assay, respectively. Meanwhile, genes of alb and afp and specific protein of albumin were detected to verify cultured hepatocytes. Immunofluorescence was used to evaluate purity of hepatocytes, presenting up to 90%. On this base, choline-deficient model was constructed and displayed significantly increase of intracellular triglyceride and cholesterol as reported previously. Intriguingly, our data suggested that AS events in choline-deficient model were implicated in pivotal biological processes as an aberrant transcriptional regulator, of which 16 genes were involved in lipid metabolism and highly enriched in glycerophospholipid metabolism. Conclusion: An effective and rapid protocol for obtaining duck primary hepatocytes was established, by which our findings manifested choline deficiency could induce the accumulation of lipid and result in aberrant AS events in hepatocytes, providing a novel insight into various AS in the metabolism role of choline.

• KIPS Transactions on Software and Data Engineering
• /
• 제12권2호
• /
• pp.99-110
• /
• 2023

This study proposed a classification of malicious network traffic using the cyber threat framework(Mitre ATT&CK) and machine learning to solve the real-time traffic detection problems faced by current security monitoring systems. We applied a network traffic dataset called UNSW-NB15 to the Mitre ATT&CK framework to transform the label and generate the final dataset through rare class processing. After learning several boosting-based ensemble models using the generated final dataset, we demonstrated how these ensemble models classify network traffic using various performance metrics. Based on the F-1 score, we showed that XGBoost with no rare class processing is the best in the multi-class traffic environment. We recognized that machine learning ensemble models through Mitre ATT&CK label conversion and oversampling processing have differences over existing studies, but have limitations due to (1) the inability to match perfectly when converting between existing datasets and Mitre ATT&CK labels and (2) the presence of excessive sparse classes. Nevertheless, Catboost with B-SMOTE achieved the classification accuracy of 0.9526, which is expected to be able to automatically detect normal/abnormal network traffic.

• Information Systems Review
• /
• 제25권4호
• /
• pp.233-248
• /
• 2023

The increasing integration of intelligent information technologies within organizational systems has amplified the risk to personal information security. This escalation, in turn, has fueled growing apprehension about an organization's capabilities in safeguarding user data. While Internet users adopt a multifaceted approach in assessing a company's information security, existing research on the multiple dimensions of information security is decidedly sparse. Moreover, there is a conspicuous gap in investigations exploring whether users' evaluations of organizational information security differ across industry types. With an aim to bridge these gaps, our study strives to identify which information security attributes users perceive as most critical and to delve deeper into potential variations in these attributes across different industry sectors. To this end, we conducted a structured survey involving 498 users and utilized the analytic hierarchy process (AHP) to determine the relative significance of various information security attributes. Our results indicate that users place the greatest importance on the technological dimension of information security, followed closely by transparency. In the technological arena, banks and domestic portal providers earned high ratings, while for transparency, banks and governmental agencies stood out. Contrarily, social media providers received the lowest evaluations in both domains. By introducing a multidimensional model of information security attributes and highlighting the relative importance of each in the realm of information security research, this study provides a significant theoretical contribution. Moreover, the practical implications are noteworthy: our findings serve as a foundational resource for Internet service companies to discern the security attributes that demand their attention, thereby facilitating an enhancement of their information security measures.

• Journal of Korean Society of Forest Science
• /
• 제111권4호
• /
• pp.461-472
• /
• 2022

Natural and anthropogenic factors cause forest types to continuously change. Since the ratio of forest area by forest type is important information for identifying the characteristics of national forest resources, an accurate understanding of the prospect of forest type change is required. The study aim was to use National Forest Inventory (NFI) time-series data to understand the characteristics of forest type change and to estimate future prospects of nationwide forest type change. We used forest type change information from the fifth and seventh NFI datasets, climate, topography, forest stand, and disturbance variables related to forest type change to analyze trends and characteristics of forest type change. The results showed that the forests in Korea are changing in the direction of decreasing coniferous forests and increasing mixed and broadleaf forests. The forest sites that were changing from coniferous to mixed forests or from mixed to broadleaf forests were mainly located in wet topographic environments and climatic conditions. The forest type changes occurred more frequently in sites with high disturbance potential (high temperature, young or sparse forest stands, and non-forest areas). We used a climate change scenario (RCP 8.5) to establish a forest type change model (SVM) to predict future changes. During the 40-year period from 2015 to 2055, the SVM predicted that coniferous forests will decrease from 38.1% to 28.5%, broadleaf forests will increase from 34.2% to 38.8%, and mixed forests will increase from 27.7% to 32.7%. These results can be used as basic data for establishing future forest management strategies.

• Journal of Intelligence and Information Systems
• /
• 제20권2호
• /
• pp.137-148
• /
• 2014

Recommender system has become one of the most important technologies in e-commerce in these days. The ultimate reason to shop online, for many consumers, is to reduce the efforts for information search and purchase. Recommender system is a key technology to serve these needs. Many of the past studies about recommender systems have been devoted to developing and improving recommendation algorithms and collaborative filtering (CF) is known to be the most successful one. Despite its success, however, CF has several shortcomings such as cold-start, sparsity, gray sheep problems. In order to be able to generate recommendations, ordinary CF algorithms require evaluations or preference information directly from users. For new users who do not have any evaluations or preference information, therefore, CF cannot come up with recommendations (Cold-star problem). As the numbers of products and customers increase, the scale of the data increases exponentially and most of the data cells are empty. This sparse dataset makes computation for recommendation extremely hard (Sparsity problem). Since CF is based on the assumption that there are groups of users sharing common preferences or tastes, CF becomes inaccurate if there are many users with rare and unique tastes (Gray sheep problem). This study proposes a new algorithm that utilizes Social Network Analysis (SNA) techniques to resolve the gray sheep problem. We utilize 'degree centrality' in SNA to identify users with unique preferences (gray sheep). Degree centrality in SNA refers to the number of direct links to and from a node. In a network of users who are connected through common preferences or tastes, those with unique tastes have fewer links to other users (nodes) and they are isolated from other users. Therefore, gray sheep can be identified by calculating degree centrality of each node. We divide the dataset into two, gray sheep and others, based on the degree centrality of the users. Then, different similarity measures and recommendation methods are applied to these two datasets. More detail algorithm is as follows: Step 1: Convert the initial data which is a two-mode network (user to item) into an one-mode network (user to user). Step 2: Calculate degree centrality of each node and separate those nodes having degree centrality values lower than the pre-set threshold. The threshold value is determined by simulations such that the accuracy of CF for the remaining dataset is maximized. Step 3: Ordinary CF algorithm is applied to the remaining dataset. Step 4: Since the separated dataset consist of users with unique tastes, an ordinary CF algorithm cannot generate recommendations for them. A 'popular item' method is used to generate recommendations for these users. The F measures of the two datasets are weighted by the numbers of nodes and summed to be used as the final performance metric. In order to test performance improvement by this new algorithm, an empirical study was conducted using a publically available dataset - the MovieLens data by GroupLens research team. We used 100,000 evaluations by 943 users on 1,682 movies. The proposed algorithm was compared with an ordinary CF algorithm utilizing 'Best-N-neighbors' and 'Cosine' similarity method. The empirical results show that F measure was improved about 11% on average when the proposed algorithm was used