• KIISE Transactions on Computing Practices
• /
• v.21 no.6
• /
• pp.412-417
• /
• 2015

Context-sensitive spelling errors (CSSE) are hard to correct, since they are perfect words when analyzed alone. Determined only by considering the semantic and syntactic relations of their context, CSSEs affect largely the performance of spelling and grammar checkers. The existing Korean Spelling and Grammar Checker (KSGC 4.5) adopts a rule-based method, which uses hand-made correction rules for CSSEs. Using rule-based method, the KSGC 4.5 is designed to obtain the very high precision, which results in the extremely low recall. In this paper, we integrate our previous works that control the CSSE correction rules, in order to improve the recall without sacrificing the precision. In addition to the integration, facultative insertion of adverbs and conjugation suffix of predicates are also considered, as for constraint-loosening linguistic features.

• Journal of KIISE
• /
• v.42 no.5
• /
• pp.629-636
• /
• 2015

The types of errors corrected by a Korean spelling and grammar checker can be classified into isolated-term spelling errors and context-sensitive spelling errors (CSSE). CSSEs are difficult to detect and to correct, since they are correct words when examined alone. Thus, they can be corrected only by considering the semantic and syntactic relations to their context. CSSEs, which are frequently made even by expert wiriters, significantly affect the reliability of spelling and grammar checkers. An existing Korean spelling and grammar checker developed by P University (KSGC 4.5) adopts hand-made correction rules for correcting CSSEs. The KSGC 4.5 is designed to obtain very high precision, which results in an extremely low recall. Our overall goal of previous works was to improve the recall without considerably lowering the precision, by generalizing CSSE correction rules that mainly depend on linguistic knowledge. A variety of rule-based methods has been proposed in previous works, and the best performance showed 95.19% of average precision and 37.56% of recall. This study thus proposes a statistics based method using a conditional probability model with dynamic window sizes. in order to further improve the recall. The proposed method obtained 97.23% of average precision and 50.50% of recall.

• The Korean Journal of Rehabilitation Nursing
• /
• v.10 no.2
• /
• pp.134-140
• /
• 2007

Purpose: The purpose of this study was to find out relation of general characteristics and memory performance of old adults. Method: The subjects consisted of 160 old adults over the age 60 who living in Seoul. Data were collected by the interview method, using a structured questionnaire and the testing method on the memory performance. Data were analyzed by SPSS PC. Result: The level of memory performance is 63.0 points in the 84 point scale, immediate recall is 7.8 points in the 12 point scale, delayed recall is 7.6 points in the 12 point scale, word recognition is 16 points in the 24 point scale, & face recognition is 16 points in the 24 point scale, & face recognition is 26.8 points in the 40 point scale. Analysis of memory performance according to general characteristics showed that there were statistically differences for age, sex, religion and alcohol. Memory performance showed a significantly negative correlation with age and alcohol, but positive correlation with sex. The significant variables to predict old adults'memory performance are age and alcohol. Conclusion: The findings of this study give useful information for constructing an memory performance improving program based on general characteristics in old adults.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.2
• /
• pp.494-510
• /
• 2024

Internet users are exposed to sophisticated cyberattacks that intrusion detection systems have difficulty detecting. Therefore, research is increasing on intrusion detection methods that use artificial intelligence technology for detecting novel cyberattacks. Unsupervised learning-based methods are being researched that learn only from normal data and detect abnormal behaviors by finding patterns. This study developed an anomaly-detection method based on unsupervised machines and deep learning for a network intrusion detection system (NIDS). We present a hybrid anomaly detection approach based on unsupervised learning techniques using the autoencoder (AE), Isolation Forest (IF), and Local Outlier Factor (LOF) algorithms. An oversampling approach that increased the detection rate was also examined. A hybrid approach that combined deep learning algorithms and traditional machine learning algorithms was highly effective in setting the thresholds for anomalies without subjective human judgment. It achieved precision and recall rates respectively of 88.2% and 92.8% when combining two AEs, IF, and LOF while using an oversampling approach to learn more unknown normal data improved the detection accuracy. This approach achieved precision and recall rates respectively of 88.2% and 94.6%, further improving the detection accuracy compared with the hybrid method. Therefore, in NIDS the proposed approach provides high reliability for detecting cyberattacks.

• Journal of KIISE:Computing Practices and Letters
• /
• v.15 no.3
• /
• pp.221-225
• /
• 2009

Constructing an ontology using a mass corpus begins with an automatic semantic relation extraction. A general method regards words appearing between terms as patterns which are used to extract semantic relations. However, previous approaches consider only one sentence to extract a pattern, so they cannot extract semantic relations for terms in different sentences. This paper proposes a semantic relation extraction method using pairs of patterns sharing a term, where each pattern is extracted using one of the seed term pair satisfying the target relation. In our experiments, we achieved the accuracy 83.75% improving previous methods by 7.5% in is-${\alpha}$ relation and the accuracy 83.75% improved by 5% in part-of relation. We also present a possibility of improving the recall by the relative recall.

• Journal of Korean Academy of Nursing
• /
• v.35 no.6
• /
• pp.1014-1024
• /
• 2005

Purpose: This study was to exam me the effects of auricular acupuncture on insomnia in Korean elderly. Method: The study design was a triangulation study. Subjects were 40 elderly who were 65 years and over in Seoul, and 10 subjects for a qualitive study who were saturated with interviews and observation. The first auricular acupuncture was applied for three days, and this was applied to subjects on a 5 times series. The quantative data was analyzed by SPSS PC+ and the qualitive data was analyzed by driving of core meaning and abstract concepts using a semi-structural interview and observation. Result: I. The experimental group had higher significant sleep scores than that of the control group (t=32.739, p=.001). 2. The experimental group had higher significant self- satisfaction scores on sleep than that of the control group (t=30.049, p=.001). 3. In the qualitive study, insomnia characteristics before application of auricular acupressure therapy were confirmed by physical dysfunction, recall of past, and psychological dysfunction. Insomnia characteristics after application of auricular acupressure therapy were confirmed by recovery of physical dysfunction, improving recall of past, and recovery of psychological dysfunction. Conclusion: Auricular acupuncture was effective on insomnia in Korean elderly.

• The Korean Journal of Rehabilitation Nursing
• /
• v.13 no.2
• /
• pp.161-170
• /
• 2010

Purpose: This study was to confirm the influence of memory intensive training program on the elderly people's cognitive function, memory performance, and self-esteem. Method: Using a quasi-experimental or experimental design, 60 elderly aged over 60 years randomly assigned the experimental and control groups completed pretest-post evaluation. The experimental group participated in the memory intensive training program was offered to the participants in the experimental group for three weeks (2times/week). The t-test and $X^2$-test using SAS program. Results: 1) The cognitive function was significantly higher in the experimental group compared to that in the control group (t=3.26, p=.002). 2) The memory performance that included immediate word recall tasks, word recognition tasks and delayed word recall tasks was significantly higher in the experimental group than in the control group (t=5.30, p<.001). The experimental group showed significantly higher scores for memory performance than the control group (t=5.30, p<.001). 3) The self-esteem was higher in the experimental group than in the control group, but there was no significant difference between the two groups (t=1.94, p=.058). Conclusion: The Memory Intensive Training Program could be an effective intervention for improving cognitive function, and memory performance of the elderly people.

• Journal of the Semiconductor & Display Technology
• /
• v.7 no.4
• /
• pp.57-62
• /
• 2008

Image retrieval is one of the most exciting and rapidly growing research issues in the field of multimedia technology. This paper proposes a new method that performs search the relevant images by using query-by-example. The proposed method for search and retrieval of images utilizes the location information where the image had been taken. The system associates the photo images with their corresponding GPS coordinates that are used as metadata for searching. Experimental results show that the proposed method demonstrates better performance improving up to 59% of average recall and 49% of average precision. Moreover, we learned from the experimental results geo-location information embedded within the image header is more effective and positive on the search and storage.

• Journal of Information Processing Systems
• /
• v.17 no.2
• /
• pp.426-439
• /
• 2021

To alleviate the cold-start problem and data sparsity in web service recommendation and meet the personalized needs of users, this paper proposes a personalized web service recommendation method based on a hybrid social network and multi-objective immune optimization. The network adds the element of the service provider, which can provide more real information and help alleviate the cold-start problem. Then, according to the proposed service recommendation framework, multi-objective immune optimization is used to fuse multiple attributes and provide personalized web services for users without adjusting any weight coefficients. Experiments were conducted on real data sets, and the results show that the proposed method has high accuracy and a low recall rate, which is helpful to improving personalized recommendation.

• Korean Journal of Community Nutrition
• /
• v.19 no.3
• /
• pp.231-240
• /
• 2014

Objectives: This study was intended to examine the seasonal differences in outdoor activity times and dietary vitamin D intakes, and explicates their relative impact on improving serum 25-(OH) vitamin D status among Korean young women. Methods: A cross-sectional study was conducted with 135 free-living women aged 19-39 years in Daegu-Kyungbook, Korea. We compared the results from 52 women for the summer and 83 women for the winter. Dietary intake of vitamin D was assessed by 24 hour recall method for non-consecutive three days as well as by food frequency method. Daily outdoor activity times were derived from 24 hour physical activity diary. Results: The average dietary intake of vitamin D of the participants by 24 hour recall method was 3.1 ${\mu}g$ during the summer, 3.3 ${\mu}g$ during the winter, showing no significant difference between the two seasons. Times spent on outdoor activities (p < 0.01) in the summer (= $23.8{\pm}23.6$ min) were much longer than that in the winter (= $10.8{\pm}13.4$ min). The serum 25-(OH) vitamin D levels of participants were $17.5{\pm}7.5$ ng/mL in the summer and $13.4{\pm}4.3$ ng/mL in the winter, showing that the latter was significantly lower than that of the former (p<0.001). The serum 25-(OH) vitamin D levels of subjects were positively related to outdoor activities (r=0.315, p<0.05) during the summer, while related to dietary intake (r=0.252, p<0.05) during the winter. Conclusions: In order to improve the current vitamin D status of Korean young women, nutrition education programs should focus on increasing more dietary intake especially during the winter, and performing more outdoor activities in other seasons.