• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권6호
• /
• pp.2188-2203
• /
• 2021

With the rapid development of mobile Internet, smart phones have been widely popularized, among which Android platform dominates. Due to it is open source, malware on the Android platform is rampant. In order to improve the efficiency of malware detection, this paper proposes deep learning Android malicious detection system based on behavior features. First of all, the detection system adopts the static analysis method to extract different types of behavior features from Android applications, and extract sensitive behavior features through Term frequency-inverse Document Frequency algorithm for each extracted behavior feature to construct detection features through unified abstract expression. Secondly, Long Short-Term Memory neural network model is established to select and learn from the extracted attributes and the learned attributes are used to detect Android malicious applications, Analysis and further optimization of the application behavior parameters, so as to build a deep learning Android malicious detection method based on feature analysis. We use different types of features to evaluate our method and compare it with various machine learning-based methods. Study shows that it outperforms most existing machine learning based approaches and detects 95.31% of the malware.

• Human Ecology Research
• /
• 제59권4호
• /
• pp.489-500
• /
• 2021

The purpose of this study was to identify the impact of pornography use among adolescents on their subsequent violent sexual behavior, and to ascertain the moderating effect of family support. The study was conducted with a sample of 2,087 Korean middle and high-school students. To analyze the data, a descriptive analysis, a correlation analysis, and a Poisson regression were conducted using SPSS 24.0. A Poisson regression was performed because the dependent variable, violent sexual behavior, was measured by the frequency of occurrence, and most responses were distributed at '0', indicating a non-normal distribution. The results indicated that 8.1% of adolescents admitted to having sexually violent experiences over the past year, with a relatively high rate of sexual harassment. Secondly, 53.3% of adolescents had used pornography over the past couple of years, with the highest percentage of use occurring via the Internet. Finally, pornography use among adolescents had a significant and direct impact on their sexually violent behavior, with family support playing a moderating role. This indicated that, for adolescents with a high level of family support, the impact of pornography usage on sexually violent behavior decreased. Based on these results, we discuss practical and policy interventions to prevent sexually violent behavior by adolescents.

• 서비스연구
• /
• 제8권2호
• /
• pp.77-94
• /
• 2018

인터넷전문은행은 핀테크 산업의 핵심 서비스 분야이다. 2017년 국내에서도 케이뱅크와 카카오뱅크가 영업을 개시하였다. 특히 대학생을 중심으로 한 젊은 층이 초기 단계에서 인터넷전문은행의 목표고객이 될 것으로 예상된다. 인터넷전문은행이 영업을 개시한 이 시점에서 그 이용의 동기요인을 분석하여 이론적 관점은 물론이고 실무적 관점에서 시사점을 이끌어낼 필요가 있다. 따라서 본 연구에서는 대학생을 대상으로 TPB(Theory of Planned Behavior) 모형을 준용하여 인터넷전문은행의 이용의도에 영향을 미치는 요인을 실증분석한다. 분석결과, 사회적 영향과 편리성이 인터넷전문은행의 이용의도에 긍정적 영향을 미치고, 프라이버시와 초기 단계에서 검증되지 않은 전문서비스에 대한 불안과 염려가 부정적 영향을 미치는 것으로 나타났다. 그러나 경제적 혜택은 그 이용의도에 유의적 영향을 미치지 않는 것으로 나타났다. 본 연구에서 왜 편리성과 사회적 영향이 인터넷전문은행의 이용의도에 커다란 영향을 미치는가에 대해 논의하는데 역점을 두었다.

• The Journal of Asian Finance, Economics and Business
• /
• 제7권11호
• /
• pp.789-800
• /
• 2020

This study aims to examine the effect of perceived usefulness (PU), perceived ease of use (PEU), trust (TR), subjective norm (SN), and attitude (AT) on customer's Intention to Adopt Internet Banking (IAIB) at Islamic banks and conventional banks before and during the Covid-19 pandemic in Indonesia. The research model is based on the Theory of Planned Behavior (TPB) and the Technology Acceptance Model (TAM). This study involves 213 respondents for Islamic banks and 410 respondents for conventional banks from 25 provinces in Indonesia. Data was analyzed using partial least square (PLS) regression with the Structural Equation Model (SEM) method. The result of data analysis confirms several hypotheses taken from the literature. The results before the Covid-19 pandemic showed that AT and SN influence IAIB in Islamic banks. Whereas in conventional banks, AT, PU, SN, and TR influence IAIB. While during the Covid-19 pandemic, it shows that the AT, PU, IB, SN, and customer TR influence IAIB in Islamic banks and conventional banks. From the analysis, it was found that the PEU variable did not have a significant effect on the intention of customers of Islamic banks and conventional banks to use Internet banking.

• International Journal of Internet, Broadcasting and Communication
• /
• 제15권4호
• /
• pp.61-73
• /
• 2023

As smartphone use is increasing within the middle-aged population, society should pay closer attention to the mental health problems associated with smartphone addiction. This study examines the possibility that depression, anxiety, and ADHD can be interpreted not only as negative aspects, but also as positive aspects, in an addiction-related individual. We used habitual and addictive smartphone behavior as the dependent variables; anxiety, ADHD, depression, and habitual smartphone use as the independent variables; and self-control as a moderating variable. Depression and ADHD in smartphone users were found to be associated with higher levels of addictive smartphone use. Anxiety was having negative effect on addictive smartphone use. However, habitual smartphone use didn't significantly affect addictive smartphone use. Further analysis indicated that depression, anxiety, and ADHD have mediating effects on habitual smartphone use. This study confirmed that psychological factors in adults, as well as habitual/addictive smartphone use and self-control, significantly influence smartphone overdependence.

• 부모자녀건강학회지
• /
• 제8권2호
• /
• pp.112-122
• /
• 2005

Purpose: This study was done to investigate the relation to perceived maternal child rearing behaviors and the level of internet addiction in the upper year grade students. Method: Data was collected through self-report questionnaires in which perceived maternal child rearing behaviors and internet addiction. This study population was comprised of 668 students who enrolled 4~6 year-grade in Kwangwon-Do. The data collected was analyzed by the SPSS program. Results: The level of internet addiction of subjects was rather low. Of the children, 88.2% reported being average on-line users, 7.3%, heavy on-line users, and 4.5%, internet addicted. Gender, existence of father, mother's attitude when child overuse on-line, average playing time of on-line per day, frequency of on-line visits per week and purpose of on-line use for average on-line users were different from that of heavy on-line users. The level of perceived maternal child rearing behaviors were abbreviate positively correlated to the level of internet addiction in subjects. Conclusion: We suggest these results be used to develop a internet addiction prevention program.

• 경영정보학연구
• /
• 제19권1호
• /
• pp.25-48
• /
• 2017

인터넷 사용자 수가 급증하면서, 인터넷 기반의 애플리케이션 중 가장 많이 사용되는 SNS(Social Network Sites)이나 게임 이용은 성별과 연령대에 크게 좌우되지 않는 대중적인 성격을 띠게 되었다. 인터넷의 폭넓은 보급과 사용은 사회에 도움이 되어온 반면, 이와 함께 과도한 인터넷 사용을 통제하지 못하는 인터넷 중독과 같은 부작용 현상도 나타나고 있어 이에 따른 사회적 비용 또한 우려할 만한 수준이다. 인터넷 중독, SNS 중독 그리고 게임 중독은 중독자 개인들의 일상생활 속에서 매우 큰 위치를 차지하고 부정적인 영향을 주고 있으며, 심각한 사회 문제까지도 야기할 수 있다. 본 연구에서는 중독의 원인을 설명할 수 있는 문제행동이론을 도입하여, 인터넷, SNS 그리고 게임에 대한 접촉이 상대적으로 높은 연령대인 20대 대학생들을 주 대상으로 하여 개인적 특성인 자존감과 인지적 가정환경이 인터넷 중독, SNS 중독 그리고 게임 중독에 미치는 영향을 알아보고자 한다. 또한 인터넷 중독, SNS 중독 그리고 게임 중독 사이의 관계를 규명하고자 한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권8호
• /
• pp.3151-3168
• /
• 2015

Automatic detection of estrus in cows is important in cattle management. This paper proposes a method of estrus detection by automatically checking cattle mounting. We use a side-view video camera and apply computer vision techniques to detect mounting behavior. In particular, we extract motion information to select a potential mount-up and mount-down motion and then verify the true mounting behavior by considering the direction, magnitude, and history of the mount motion. From experimental results using video data obtained from a Korean native cattle farm, we believe that the proposed method based on the abrupt change of a mounting cow's height and motion history information can be utilized for detecting mounting behavior automatically, even in the case of fence occlusion.

• Journal of Information Technology Applications and Management
• /
• 제11권1호
• /
• pp.137-159
• /
• 2004

In the past days, most of studies about website and Online behavior have been mainly focused on the adoption of website and internet shopping or internet shopping mall. But the model of website revisit behavior has not been made and the leading theory of website usage behavior has not been existed. Lately, many researches on commercial website revisiting behavior are emphasizing the role of intention, attitude, satisfaction in online visiting behavior such as Jarvenpaa et al. [1997, 1999, 2000], Wang et al. [2001], Moon & Kim [2001], Heijden[2003], Sultan et al. [2002], Yoon [2000], Shankar et al. [2002a, 2002b], Mcknight et al. [2002], Chen & Dhillon [2003] and so on. The purpose of this paper is two-folds. The one is to find the affecting factors on the website users' revisit behavior in commercial website and the other is to search more influencing ones on the determinant factors, to analyze research model using in LISREL. The EFA and reliability test was executed by for finding the validity and reliability, covariance matrix analysis was executed for the purpose of testing the 13 hypotheses. The major finding of this paper would be summarized as followed : (1) The roles of satisfaction and attitude to the revisit behavior are very important and both variables have determining effects in commercial website revisit behavior. (2) The determining factors in positively affecting website users' satisfaction are attitude, perceived usefulness, design. (3) The determining factors in positively affecting website users' attitude are perceived usefulness, design, perceived ease of use, and negatively affecting factor was perceived risk in website.

• 한국식생활문화학회지
• /
• 제25권2호
• /
• pp.160-169
• /
• 2010

This study was conducted to examine the relationship between dietary habits and time spent watching TV and using internet, in elementary school children. The data were collected by a questionnaire survey of 712 elementary school children, within Gwangju and Jeonnam area. The SPSS 12.0/win program was used to analyze the 523 samples. Amount of TV-watching time was found to be related to the dietary habit score in the subjects. The children who watch TV "less than 1 hour/day" on weekdays had a better dietary habit score than those who watch TV "more than 1 hour" (p<0.0001). The children who watch TV "less than 2 hours/day" on weekends had a better dietary habit than the children who watch TV "more than 2 hours/day" (p<0.0001). The internet usage was also related to the dietary habit score in these children: those who use internet "less than 1 hour/day" on weekdays had a better dietary habit score than the children who use internet "more than 2 hours/day" (p<0.0001). The children who use internet "less than 2 hours/day" on weekends had a better dietary habit score than the children who use internet "more than 2 hours/day" (p<0.0001). These results indicate that the children tend to have a better diet when their TV and internet time is limited and thus healthy dietary behavior is negatively associated with a sedentary pattern of activity in elementary school children.