• Information Systems Review
• /
• v.21 no.3
• /
• pp.1-26
• /
• 2019

Now we are facing with a possibility of having crimes, which have been only possible offline, in cyber spaces as well.Especially, a recent growth in the use of SNS, promoted by popularization of smart phones, also has led an abrupt increase in cyber crime. It would be important to have a understanding of cyber crime and its characteristics by type as well as factors associated with each type of cyber crime in order to devise appropriate preventive measures against cyber crime. However, most of the previous studies on cyber crimesolely made through literature review or indirect approaches. Therefore, this study has been designed to conduct the interview with actual suspects(criminals) of cyber crime to address factors of cyber crime and to devise specific preventive measures and countermeasures against cyber crime. Especially, among various types of cyber crime, this study aims at addressing the 'trades' and 'financial transaction' of crimes committed using the information and communication network and the 'cyber libel/insult'of crimes committed using unlicensed contents, which have been soared recently and become significant issues. The findings of this study could be beneficial for the society since it has managed to conduct the interview and reveal relationships among major factors of cyber crime. The findings of this study could be used for devising and developing proper preventive and countermeasures against cyber crime, in turn reducing and preventing its damage.

• Annals of Occupational and Environmental Medicine
• /
• v.35
• /
• pp.50.1-50.11
• /
• 2023

Background: The rise in telecommuting or non-face-to-face work owing to the coronavirus disease 2019 pandemic has fueled conversations regarding the "right to disconnect." Although evidence suggests that receiving work-related communications through telecommunication devices outside of work hours may lead to various symptoms and illnesses, limited research has been undertaken on these symptoms. This study therefore aims to investigate the correlation between receiving work communications through telecommunication devices after work hours and the occurrence of work-related headaches and eyestrain in full-time, non-shift white-collar workers. Methods: This study used data from the 6th Korean Working Conditions Survey. The frequency of using telecommunication devices for work purposes outside of working hours was divided into five categories: "Every day," "Several times a week," "Several times a month," "Rarely," and "Never." Work-related headaches and eyestrain were categorized based on a "yes" or "no" response to the survey questions. Descriptive statistics, χ² tests, and multiple logistic regression analyses were performed using SPSS 27.0. Results: After adjusting for sex, age, income level, education, occupation, workplace size, work hours, and sleep disorders, the odds ratio (OR) of work-related headaches and eyestrain based on frequency of telecommunication device usage were as follows: "rarely" (OR: 1.292; 95% confidence interval [CI]: 1.111-1.503), "several times a month" (OR: 1.551; 95% CI: 1.249-1.926), "several times a week" (OR: 1.474; 95% CI: 1.217-1.784), and "every day" (OR: 1.548; 95% CI: 1.321-1.813). Conclusions: Employees who use telecommunication devices for work after regular hours are more susceptible to experiencing work-related headaches and eyestrain compared to those who do not. However, there is a dearth of research examining the physical and mental health impacts of using telecommunication devices for after-hours work. Furthermore, the existing preventative measures in Korea are insufficient. Consequently, it is imperative to develop effective measures and conduct additional research to address this issue.

• Journal of IKEEE
• /
• v.28 no.2
• /
• pp.150-157
• /
• 2024

In this paper, we propose a novel algorithm for predicting the number of apples on an apple tree using a deep learning-based object detection model and a polynomial regression model. Measuring the number of apples on an apple tree can be used to predict apple yield and to assess losses for determining agricultural disaster insurance payouts. To measure apple fruit load, we photographed the front and back sides of apple trees. We manually labeled the apples in the captured images to construct a dataset, which was then used to train a one-stage object detection CNN model. However, when apples on an apple tree are obscured by leaves, branches, or other parts of the tree, they may not be captured in images. Consequently, it becomes difficult for image recognition-based deep learning models to detect or infer the presence of these apples. To address this issue, we propose a two-stage inference process. In the first stage, we utilize an image-based deep learning model to count the number of apples in photos taken from both sides of the apple tree. In the second stage, we conduct a polynomial regression analysis, using the total apple count from the deep learning model as the independent variable, and the actual number of apples manually counted during an on-site visit to the orchard as the dependent variable. The performance evaluation of the two-stage inference system proposed in this paper showed an average accuracy of 90.98% in counting the number of apples on each apple tree. Therefore, the proposed method can significantly reduce the time and cost associated with manually counting apples. Furthermore, this approach has the potential to be widely adopted as a new foundational technology for fruit load estimation in related fields using deep learning.

• Journal of Intelligence and Information Systems
• /
• v.24 no.4
• /
• pp.219-240
• /
• 2018

Sentiment analysis, which is one of the text mining techniques, is a method for extracting subjective content embedded in text documents. Recently, the sentiment analysis methods have been widely used in many fields. As good examples, data-driven surveys are based on analyzing the subjectivity of text data posted by users and market researches are conducted by analyzing users' review posts to quantify users' reputation on a target product. The basic method of sentiment analysis is to use sentiment dictionary (or lexicon), a list of sentiment vocabularies with positive, neutral, or negative semantics. In general, the meaning of many sentiment words is likely to be different across domains. For example, a sentiment word, 'sad' indicates negative meaning in many fields but a movie. In order to perform accurate sentiment analysis, we need to build the sentiment dictionary for a given domain. However, such a method of building the sentiment lexicon is time-consuming and various sentiment vocabularies are not included without the use of general-purpose sentiment lexicon. In order to address this problem, several studies have been carried out to construct the sentiment lexicon suitable for a specific domain based on 'OPEN HANGUL' and 'SentiWordNet', which are general-purpose sentiment lexicons. However, OPEN HANGUL is no longer being serviced and SentiWordNet does not work well because of language difference in the process of converting Korean word into English word. There are restrictions on the use of such general-purpose sentiment lexicons as seed data for building the sentiment lexicon for a specific domain. In this article, we construct 'KNU Korean Sentiment Lexicon (KNU-KSL)', a new general-purpose Korean sentiment dictionary that is more advanced than existing general-purpose lexicons. The proposed dictionary, which is a list of domain-independent sentiment words such as 'thank you', 'worthy', and 'impressed', is built to quickly construct the sentiment dictionary for a target domain. Especially, it constructs sentiment vocabularies by analyzing the glosses contained in Standard Korean Language Dictionary (SKLD) by the following procedures: First, we propose a sentiment classification model based on Bidirectional Long Short-Term Memory (Bi-LSTM). Second, the proposed deep learning model automatically classifies each of glosses to either positive or negative meaning. Third, positive words and phrases are extracted from the glosses classified as positive meaning, while negative words and phrases are extracted from the glosses classified as negative meaning. Our experimental results show that the average accuracy of the proposed sentiment classification model is up to 89.45%. In addition, the sentiment dictionary is more extended using various external sources including SentiWordNet, SenticNet, Emotional Verbs, and Sentiment Lexicon 0603. Furthermore, we add sentiment information about frequently used coined words and emoticons that are used mainly on the Web. The KNU-KSL contains a total of 14,843 sentiment vocabularies, each of which is one of 1-grams, 2-grams, phrases, and sentence patterns. Unlike existing sentiment dictionaries, it is composed of words that are not affected by particular domains. The recent trend on sentiment analysis is to use deep learning technique without sentiment dictionaries. The importance of developing sentiment dictionaries is declined gradually. However, one of recent studies shows that the words in the sentiment dictionary can be used as features of deep learning models, resulting in the sentiment analysis performed with higher accuracy (Teng, Z., 2016). This result indicates that the sentiment dictionary is used not only for sentiment analysis but also as features of deep learning models for improving accuracy. The proposed dictionary can be used as a basic data for constructing the sentiment lexicon of a particular domain and as features of deep learning models. It is also useful to automatically and quickly build large training sets for deep learning models.

• Journal of Intelligence and Information Systems
• /
• v.23 no.2
• /
• pp.39-70
• /
• 2017

Data-drive analytics techniques have been recently applied to public surveys. Instead of simply gathering survey results or expert opinions to research the preference for a recently launched product, enterprises need a way to collect and analyze various types of online data and then accurately figure out customer preferences. In the main concept of existing data-based survey methods, the sentiment lexicon for a particular domain is first constructed by domain experts who usually judge the positive, neutral, or negative meanings of the frequently used words from the collected text documents. In order to research the preference for a particular product, the existing approach collects (1) review posts, which are related to the product, from several product review web sites; (2) extracts sentences (or phrases) in the collection after the pre-processing step such as stemming and removal of stop words is performed; (3) classifies the polarity (either positive or negative sense) of each sentence (or phrase) based on the sentiment lexicon; and (4) estimates the positive and negative ratios of the product by dividing the total numbers of the positive and negative sentences (or phrases) by the total number of the sentences (or phrases) in the collection. Furthermore, the existing approach automatically finds important sentences (or phrases) including the positive and negative meaning to/against the product. As a motivated example, given a product like Sonata made by Hyundai Motors, customers often want to see the summary note including what positive points are in the 'car design' aspect as well as what negative points are in thesame aspect. They also want to gain more useful information regarding other aspects such as 'car quality', 'car performance', and 'car service.' Such an information will enable customers to make good choice when they attempt to purchase brand-new vehicles. In addition, automobile makers will be able to figure out the preference and positive/negative points for new models on market. In the near future, the weak points of the models will be improved by the sentiment analysis. For this, the existing approach computes the sentiment score of each sentence (or phrase) and then selects top-k sentences (or phrases) with the highest positive and negative scores. However, the existing approach has several shortcomings and is limited to apply to real applications. The main disadvantages of the existing approach is as follows: (1) The main aspects (e.g., car design, quality, performance, and service) to a product (e.g., Hyundai Sonata) are not considered. Through the sentiment analysis without considering aspects, as a result, the summary note including the positive and negative ratios of the product and top-k sentences (or phrases) with the highest sentiment scores in the entire corpus is just reported to customers and car makers. This approach is not enough and main aspects of the target product need to be considered in the sentiment analysis. (2) In general, since the same word has different meanings across different domains, the sentiment lexicon which is proper to each domain needs to be constructed. The efficient way to construct the sentiment lexicon per domain is required because the sentiment lexicon construction is labor intensive and time consuming. To address the above problems, in this article, we propose a novel product reputation mining algorithm that (1) extracts topics hidden in review documents written by customers; (2) mines main aspects based on the extracted topics; (3) measures the positive and negative ratios of the product using the aspects; and (4) presents the digest in which a few important sentences with the positive and negative meanings are listed in each aspect. Unlike the existing approach, using hidden topics makes experts construct the sentimental lexicon easily and quickly. Furthermore, reinforcing topic semantics, we can improve the accuracy of the product reputation mining algorithms more largely than that of the existing approach. In the experiments, we collected large review documents to the domestic vehicles such as K5, SM5, and Avante; measured the positive and negative ratios of the three cars; showed top-k positive and negative summaries per aspect; and conducted statistical analysis. Our experimental results clearly show the effectiveness of the proposed method, compared with the existing method.

• Journal of Internet Computing and Services
• /
• v.5 no.5
• /
• pp.1-15
• /
• 2004

In this paper, we explain the design and implementation of GWB(Gene WorkBench), which is a web-based, integrated system for efficiently managing and analyzing genomic sequences, Most existing software systems handling genomic sequences rarely provide both managing facilities and analyzing facilities. The analysis programs also tend to be unit programs that include just single or some part of the required functions. Moreover, these programs are widely distributed over Internet and require different execution environments. As lots of manual and conversion works are required for using these programs together, many life science researchers suffer great inconveniences. in order to overcome the problems of existing systems and provide a more convenient one for helping genomic researches in effective ways, this paper integrates both managing facilities and analyzing facilities into a single system called GWB. Most important issues regarding the design of GWB are how to integrate many different analysis programs into a single software system, and how to provide data or databases of different formats required to run these programs. In order to address these issues, GWB integrates different analysis programs byusing common input/output interfaces called wrappers, suggests a common format of genomic sequence data, organizes local databases consisting of a relational database and an indexed sequential file, and provides facilities for converting data among several well-known different formats and exporting local databases into XML files.

• Journal of Internet Computing and Services
• /
• v.16 no.2
• /
• pp.57-66
• /
• 2015

Considerable research efforts are being directed towards analyzing unstructured data such as text files and log files using commercial and noncommercial analytical tools. In particular, researchers are trying to extract meaningful knowledge through text mining in not only business but also many other areas such as politics, economics, and cultural studies. For instance, several studies have examined national pending issues by analyzing large volumes of text on various social issues. However, it is difficult to provide successful information services that can identify R&D documents on specific national pending issues. While users may specify certain keywords relating to national pending issues, they usually fail to retrieve appropriate R&D information primarily due to discrepancies between these terms and the corresponding terms actually used in the R&D documents. Thus, we need an intermediate logic to overcome these discrepancies, also to identify and package appropriate R&D information on specific national pending issues. To address this requirement, three methodologies are proposed in this study-a hybrid methodology for extracting and integrating keywords pertaining to national pending issues, a methodology for packaging R&D information that corresponds to national pending issues, and a methodology for constructing an associative issue network based on relevant R&D information. Data analysis techniques such as text mining, social network analysis, and association rules mining are utilized for establishing these methodologies. As the experiment result, the keyword enhancement rate by the proposed integration methodology reveals to be about 42.8%. For the second objective, three key analyses were conducted and a number of association rules between national pending issue keywords and R&D keywords were derived. The experiment regarding to the third objective, which is issue clustering based on R&D keywords is still in progress and expected to give tangible results in the future.

• Journal of the Korean Society of Food Science and Nutrition
• /
• v.42 no.5
• /
• pp.818-827
• /
• 2013

The purpose of this study was to identify food consumption patterns of the elderly and factors affecting them to improve their dietary health. Data from 1,172 elderly subjects (over 65 years old) from the fifth Korea National Health and Nutrition Examination Survey (KNHANES V-1) were used in our analysis. Validity and reliability analyses of food consumption frequency allowed the identification of seven factors: fruits, foods for Korean style meal, instant foods, alcohols, carbohydrate-rich snacks, vegetables, and legumes/mixed grains. Food consumption patterns were classified into four groups (according to the food consumption frequency) using cluster analysis. Cluster 4 showed a significantly higher food consumption frequency and Cluster 3 had a relatively high overall food consumption frequency but lower alcohol consumption frequency compared to the other clusters. Cluster 2 was characterized by a generally low food consumption frequency but a significantly higher alcohol consumption frequency. Cluster 1 showed a generally low food consumption frequency; however, the consumption frequency of legumes/mixed grains was higher than Cluster 2. Further analysis showed that the food consumption patterns of the elderly were affected by variables such as gender, age, town, economic status, education level, family type, and frequency of eating out. We conclude that a proper nutritional education program should be conducted to address specific dietary problems for each elderly segment.

• Journal of Climate Change Research
• /
• v.3 no.1
• /
• pp.71-88
• /
• 2012

The global warming is probably the most significant issue of concern all over the world and according to the report published by the Intergovernmental Panel on Climate Change (IPCC), the average temperature and extent of global warming around the globe have been on the rise and so have the uncertainty for the future. Such effects of global warming have adverse effects on basic foundation of the mankind in numerous ways and water resource is no exception. The researches on water resources assessment for climate change are significant enough to be used as the preliminary data for researches in other fields. In this research, a total of 124 peer-reviewed publications and 57 reports on the subject of research on climate change related to water resources, that has been carried out so far in Korea has been reviewed. The research on climate change in Korea (inclusive of the peer-reviewed articles and reports) has mainly focused on the future projection and assessment. In the fields of hydrometeorology tendency and projection, the analysis has been carried out with focus on surface water, flood, etc. for hydrological variables and precipitation, temperature, etc. for meteorological variables. This can be attributed to the large, seasonal deviation in the amount of rainfall and the difficulty of water resources management, which is why, the analysis and research have been carried out with focus on those variables such as precipitation, temperature, surface water, flood, etc. which are directly related to water resources. The future projection of water resources in Korea may differ from region to region; however, variables such as precipitation, temperature, surface water, etc. have shown a tendency for increase; especially, it has been shown that whereas the number of casualties due to flood or drought decreases, property damage has been shown to increase. Despite the fact that the intensity of rainfall, temperature, and discharge amount are anticipated to rise, appropriate measures to address such vulnerabilities in water resources or management of drainage area of future water resources have not been implemented as yet. Moreover, it has been found that the research results on climate change that have been carried out by different bodies in Korea diverge significantly, which goes to show that many inherent uncertainties exist in the various stage of researches. Regarding the strategy in response to climate change, the voluntary response by an individual or a corporate entity has been found to be inadequate owing to the low level of awareness by the citizens and the weak social infrastructure for responding to climate change. Further, legal or systematic measures such as the governmental campaign on the awareness of climate change or the policy to offer incentives for voluntary reduction of greenhouse gas emissions have been found to be insufficient. Lastly, there has been no case of any research whatsoever on the anticipated effects on the economy brought about by climate change, however, there are a few cases of on-going researches. In order to establish the strategy to prepare for and respond to the anticipated lack of water resources resulting from climate change, there is no doubt that a standardized analysis on the effects on the economy should be carried out first and foremost.

• Asia Marketing Journal
• /
• v.13 no.3
• /
• pp.25-53
• /
• 2011

This study probes the effect of loyalty program on the customer retention based on the real transaction data(n=2,892) acquired from education service industry. We try to figure out the outcomes of reward program through more than 1 year-long data gathered and analyzed according to quasi-experimental design(i.e., before and after design). We adopt this kinds of research scheme in regard that previous studies measured the effect of loyalty program by dividing the customers into two group(i.e., members vs. non-members) after the firms or stores had started the program. We believe that it might not avoid the self-selection bias. The research questions of this study could be explained such as: First, most research said that the loyalty programs could increase the customer loyalty and contribute to the sustainable growth of company. But there are little confirmation that this promotional tool could be justified in terms of financial perspective. Thus, we are interested in both the retention rate and financial outcomes caused by the introduction of loyalty programs. Second, reward programs target mainly current customer. Especially CRM(customer relationship management) said that it is more profitable for company to build positive relationship with current customer instead of pursuing new customer. And it claims that reward program is excellent means to achieve this goal. For this purpose, we check in this study whether there is a interaction effect between loyalty program and customer type in retaining customer. Third, it is said that dis-satisfied customers are more likely to leave the company than satisfied customers. While, Bolton, Kannan and Bramlett(2000) claimed that reward program could contribute to minimize the effect of negative service by building emotional link with customer, it is not empirically confirmed. This point of view explained that the loyalty programs might work as exit barrier to current customer. Thus, this study tries to identify whether there is a interaction effect between loyalty program and service experience in keeping customer. To achieve this purpose, this study adopt both Kaplan-Meier survival analysis and Cox proportional hazard model. The research outcomes show that the average retention period is 179 days before introducing loyalty program but it is increased to 227 days after reward is given to the customers. Since this difference is statistically significant, it could be said that H1 is supported. In addition, the contribution margin coming from increased transaction period is bigger than the cost for administering loyalty programs. To address other research questions, we probe the interaction effect between loyalty program and other factors(i.e., customer type and service experience) affecting it. The analysis of Cox proportional hazard model said that the current customer is more likely to engage in building relationship with company compared to new customer. In addition, retention rate of satisfied customer is significantly increased in relation to dis-satisfied customer. Interestingly, the transaction period of dis-satisfied customer is notably increased after introducing loyalty programs. Thus, it could be said that H2, H3, and H4 are also supported. In summary, we found that the loyalty programs have values as a promotional tool in forming positive relationship with customer and building exit barrier.