• Journal of Internet Computing and Services
• /
• v.22 no.2
• /
• pp.77-87
• /
• 2021

With the development of the Internet and personal computers, various and complex attacks begin to emerge. As the attacks become more complex, signature-based detection become difficult. It leads to the research on behavior-based log anomaly detection. Recent work utilizes deep learning to learn the order and it shows good performance. Despite its good performance, it does not provide any explanation for prediction. The lack of explanation can occur difficulty of finding contamination of data or the vulnerability of the model itself. As a result, the users lose their reliability of the model. To address this problem, this work proposes an explainable log anomaly detection system. In this study, log parsing is the first to proceed. Afterward, sequential rules are extracted by Bayesian posterior probability. As a result, the "If condition then results, post-probability" type rule set is extracted. If the sample is matched to the ruleset, it is normal, otherwise, it is an anomaly. We utilize HDFS datasets for the experiment, resulting in F1score 92.7% in test dataset.

• Journal of Intelligence and Information Systems
• /
• v.29 no.2
• /
• pp.35-56
• /
• 2023

With the development of information and communication technology, numerous reviews are continuously posted on websites, which causes information overload problems. Therefore, users face difficulty in exploring reviews for their decision-making. To solve such a problem, many studies on review helpfulness prediction have been actively conducted to provide users with helpful and reliable reviews. Existing studies predict review helpfulness mainly based on the features included in the review. However, such studies disable providing the reason why predicted reviews are helpful. Therefore, this study aims to propose a methodology for applying eXplainable Artificial Intelligence (XAI) techniques in review helpfulness prediction to address such a limitation. This study uses restaurant reviews collected from Yelp.com to compare the prediction performance of six models widely used in previous studies. Next, we propose an explainable review helpfulness prediction model by applying the XAI technique to the model with the best prediction performance. Therefore, the methodology proposed in this study can recommend helpful reviews in the user's purchasing decision-making process and provide the interpretation of why such predicted reviews are helpful.

• Journal of Magnetics
• /
• v.11 no.1
• /
• pp.12-15
• /
• 2006

Magnetic and electronic properties of reduced rutile titanium dioxide $(TiO_{2-\delta})$ thin films doped by Mn have been investigated. The present sol-gel-grown semiconducting $TiO_{2-\delta}:Mn$ films exhibit a ferromagnetic behavior at room temperature for a limited range of Mn content. The Mn-doped films have p-type electrical conductivity with the carrier concentration near $10^{19}\;cm^{-3}$. The observed room-temperature ferromagnetism is believed to be intrinsic but not related to free carriers such as holes. Oxygen vacancies are likely to contribute to the room-temperature ferromagnetism-trapped carriers in oxygen vacancies can mediate a ferromagnetic coupling between neighboring $Mn^{+3}$ ions. The energy band-gap change due to the Mn doping measured by spectroscopic ellipsometry exhibits a red-shift compared to that of the undoped sample at low Mn content. It is explainable in terms of strong spin-exchange interactions between Mn ion and the carrier.

• Journal of Korean Academy of Nursing
• /
• v.35 no.2
• /
• pp.336-343
• /
• 2005

Purpose: The purpose of this study was to investigate the effects of dependency and abuse on depression according to gender in widowed elderly. Method: A convenient sample consisted of 246 widowed elderly who were more than 65 years old in four cities. Data was collected using a structured questionnaire from August to September, 2002. A dependency Scale developed by Ahn (1999) was used to measure the level of dependency. Emotional abuse and physical abuse were measured by 10 items for emotional abuse and 7 items for physical abuse selected out of the Conditions Scale of Elder Abuse. The level of depression was measured by the Geriatric Depression Scale (GDS). The SPSS WIN 11.0 version program was used for data analysis. Result: In male widowed elderly, dependency affected depression indirectly through emotional abuse. While in female widowed elderly, dependency affected depression directly and affected emotional abuse indirectly. Conclusion: The study showed that dependency was the most explainable variable on depression in widowed female elderly. Therefore, it dependency should be assessed first in nursing intervention to relieve depression of widowed elderly.

• Economic and Environmental Geology
• /
• v.33 no.6
• /
• pp.537-545
• /
• 2000

Shipborne gravity data are analyzed to investigate crustal structure under Dok Island and its surrounding seamounts located in border of Ulleung Basin and Oki Bank in the East Sea. Relatively low free-air gravity anomaly compared with the volume of seamounts may be explainable by isostatic compensation. From 1 st to 3rd Dokdo Seamounts, the decrease of free-air and Bouguer gravity anomalies implies the different degree of isostatic compensation, crustal thickness or/and density contrast. 3-D gravity modelling shows that seamounts have the mirror roots for regional Airy isostatic compensation, and from Ulleung Basin to Oki Bank, Moho discontinuity deepens and the density of crust is decreases. The results infer that study area is transitional zone from thin oceanic to thick continental crust. The depth of Moho discontinuity is about 15∼16 km, which may be interpreted as an uplifting of Mantle to shallow depth comparing with other borders of the Ulleung Basin.

• Ocean Science Journal
• /
• v.43 no.2
• /
• pp.67-79
• /
• 2008

We investigated the relationship between mesoscale spatial distribution of environmental parameters (temperature, salinity, and sigma-t), chlorophyll-a concentration and mesozooplankton in the Yellow Sea during May 1996, 1997, and 1998, with special reference to Yellow Sea Bottom Cold Water (YSBCW). Adult calanoid copepods, Calanus sinicus, Paracalanus parvus s.l., Acartia omorii, and Centropages abdominalis were isolated by BVSTEP analysis based on the consistent explainable percentage (-32.3%) of the total mesozooplankton distributional pattern. The copepods, which accounted for 60 to 87% of the total abundances, occupied 73-78% of the copepod community. The YSBCW consistently remained in the northern part of the study area and influenced the spatial distribution of the calanoid copepods during the study periods. Abundances of C. sinicus and P. parvus s.l., which were high outside the YSBCW, were positively correlated with the whole water average temperature (p<0.01). In contrast, the abundances of C. abdominalis and A. omorii, which were relatively high in the YSBCW, were associated with the integrated chl-a concentration based on factor analysis. These results indicate that the YSBCW influenced the mesoscale spatial heterogeneity of average temperature and integrated chl-a concentration through the water column. This consequently affected the spatial distribution pattern of the dominant copepods in association with their respective preferences for environmental and biological parameters in the Yellow Sea during spring.

• Journal of the Korean Society of Costume
• /
• v.51 no.1
• /
• pp.87-96
• /
• 2001

This study, dealing with obese bodily figures from the viewpoint of garment shape, was conducted with obese male children of late school ages(nine to eleven years old) to provide data for making ready-made clothing for obese children by directly measuring and analysing the bodily figure of the upper body of them. The results of the study are summarized as follows. 1. According to the basic statistics, for most of obese children the values of the measuring items by ages appeared to be large, and the results of comparison with the National Anthropometric Survey of Korea made in 1997 showed that the values were more large than those of standard physical conditions. 2. It was shown that in the correlation between items the upper breast circumference had a high correlation with all items, and the weight did with the following items such as circumference, height, width and thickness. 3. The results of the principal component analysis showed that six main components hand an explainable power of more than 75.60% for all materials. The first factor was thickness and obesity of the upper body, the second one the height, the third one the length of front and rear sides, the fourth one the width of neck, the fifth one the length of shoulder, and the sixth one the breast width and the wrist circumference.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.17 no.1
• /
• pp.11-18
• /
• 1993

The purposes of this study were to identify the most explainable socioeconomic variables influencing clothing selection criteria, and to explore the difference in the clothing seletion criteria among the groups with status inconsistencies. A questionnaire was developed to collect data for clothing selection criteria, and socioeconomic status. Socioeconomic status was measured by education and occupation of husband and wife, and family income. Status inconsistency was defined by the inconsistencies among education, income and occupation. Data were obtained from 369 housewives living in Seoul area. The results of this study were as follows: 1) The education of housewives was the most important variable influencing clothing selection criteria. 2) When the subjects were divided into three groups according to their status inconsistency group, there were partially significant differneces among groups in clothing selection criteria. The "overprivileged" status group attached more importance to the fashionability and psychological dependence than the other status group. The "underprivileged" status group attached more importance to the practicality and ecnomy than the other status group. And when the subject were divided into three groups according to their social mobility, there were sgnificant differences among groups in clothing selection criteria.

• 전기의세계
• /
• v.26 no.2
• /
• pp.89-94
• /
• 1977

In order to investigate the properties of radiation resistance together with dielectric, and mechanical relaxation behaviors of polyvinylcholoride exposed to several different doses under the .gamma.-ray of Co$^{60}$ source, several observations were carried out on the exposed specimens propared by mixing dibutyl-tin-dilaulate and dibutyl-tin-dimaleate as stabilizer with or without adding dioctyl-phthalate as plasticizer. Conclusions obtained from the study are as follows: The origin of the absorption band at 1,540-1,640$cm^{-1}$ / on I.R. spectrum seems to be RCOO- ion originated from ionization of the stabilizer, and this peak can be useful as a measure of radiation resistance on polyvinylchloride. Addition of increasing plasticizer to polyvinylchloride exhibits increasing radiation resistance and the reason for this result may be attributed to aromatic resonance absorption of radiation energy by diotylphthalate. On dose dependent dielectric characteristics, nonplastized specimen shows a peak at about 10 Mrad and that this peak disappears on the plastification of specimens. Those phenomena may be explainable in considering the statistical distribution of scissored chain molecular segments as well as the plastification process of plasticizer to polyvinylchloride chain molecules.

• Korean Journal of Human Ecology
• /
• v.1 no.1
• /
• pp.85-95
• /
• 1992

The purpose of this research was to find out the most explainable variables influencing fashion leadership. This research was carried out by both the theoretical and empirical study. For the theoretical study, the research of fashion leadership was based on the fashion opinion leadership and innovativeness. The study included the analysis of variables influencing fashion leadership, such as clothing importance, clothing conformity, clothing anticonformity, perceived risk of clothing, use of fashion information source and demographic variables. For the empirical study, fashion leadership was measured by fashion opinion leadership and innovativeness. The variables influencing on the fashion leadership were measured by self-image, social participation, clothing behaviors(clothing importance, normative conformity, identificational conformity, clothing anticonformity, clothing independance), demographic variables(major fields of students, year of education, family income). Data were obtained from 335 female college and university students in Chung-Buk area by self-administered questionaire. The data collected through the questionaire were analyzed by the stastical thechique-stepwise regression. The results of the study were as follow: 44.6 percent of the total variance of fashion leadership was explained by the five variables: Clothing importance, use of marketer-dominated fashion information source, identificational conformity, traditional-modern self image and clothing anticonformity. Family income and the major fields of students are significantly related to the fashion leadership.