• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.5 no.3
• /
• pp.158-163
• /
• 2012

This paper proposes an FHIDS(Fuzzy logic based Hybrid Intrusion Detection System) design that detects anomaly and misuse attacks by using a Naive Bayesian algorithm, Data Mining, and Fuzzy Logic. The NB-AAD(Naive Bayesian based Anomaly Attack Detection) technique using a Naive Bayesian algorithm within the FHIDS detects anomaly attacks. The DM-MAD(Data Mining based Misuse Attack Detection) technique using Data Mining within it analyzes the correlation rules among packets and detects new attacks or transformed attacks by generating the new rule-based patterns or by extracting the transformed rule-based patterns. The FLD(Fuzzy Logic based Decision) technique within it judges the attacks by using the result of the NB-AAD and DM-MAD. Therefore, the FHIDS is the hybrid attack detection system that improves a transformed attack detection ratio, and reduces False Positive ratio by making it possible to detect anomaly and misuse attacks.

• Journal of Nutrition and Health
• /
• v.35 no.4
• /
• pp.489-497
• /
• 2002

This study was conducted to determine if Mehrabian's eating-related characteristics questionnaire could be effectively applied in predicting obesity and eating disorders among Korean college students by examining the correlations between eating-related characteristics and anthropometry, nutrient intakes, psychological aspects of depression, and personality dimensions. The data were collected from 151 female students in classes of nutrition or psychology in Kyungnam University. Measurements of height, weight and triceps skinfold thickness (TSf) were made by well-trained interviewers, and BMI was calculated. Daily nutrient intakes were obtained from the self-reported three-day dietary records for the kinds and the amounts of foods consumed by the student subjects. The students were also asked to complete three questionnaires : Mehrabian's eating-related characteristics questionnaire, Eysenck Personality Questionnaire, and the Berk Depression Inventory. The results of the study were as follows : 1) Reliability of factored homogeneous item dimensions (FHIDS) of the translated version of the eating-related characteristics questionnaire showed a similar profile compared with the original. Moreover, the loading values of Cronbach-$\alpha$ for some FHIDs, which were excluded in order to constitute primary-level factors (for example, 'predisposition to obesity' etc) with a high reliability, were much lower than Mehrabian's. Therefore the eating-related characteristics questionnaire could be effectively used for Korean students for predicting predisposition to obesity and eating disorders. 2) With regard to the relationship between anthropometric indices and eating-related characteristics, BMI measurements showed a high and a positive correlation with 'predisposition to obesity' and 'uncontrollable urges to eat', and a negative correlation with a 'predisposition to anorexia'. The heavier body weight and the more fat mass that the subjects had, the higher the probability that the subjects were overeating. 3) The intakes of some minerals (Fe, K, Na) and Vitamin C showed significantly negative correlations with a 'predisposition to obesity' and a 'predisposition to anorexia'. But the intakes of vitamin B$_2$, niacin, and retinol were positively correlated with'uncontrollable urges to eat'. 4) Among personality dimensions, neuroticism had a positive correlation with a 'predisposition to obesity', 'uncontrollable urges to eat', and 'predisposition to anorexia'. 5) Neuroticism was negatively correlated with intakes of calories, carbohydrates, K, Fe, Vitamin C, etc. On the contrary, all personality dimensions were positively correlated with intakes of retinol. In conclusion, the translated version of Mehrabian's eating-related characteristics questionnaire appears to be effective for nutritional or psychological assessments of any predisposition to eating disorders among Korean college students.