• Journal of the Korean Association of Geographic Information Studies
• /
• v.21 no.4
• /
• pp.64-80
• /
• 2018

In Korea, citizens can only know general information about crime. Thus it is difficult to know how much they are exposed to crime. If the police can predict the crime risky area, it will be possible to cope with the crime efficiently even though insufficient police and enforcement resources. However, there is no prediction system in Korea and the related researches are very much poor. From these backgrounds, the final goal of this study is to develop an automated crime prediction system. However, for the first step, we build a big data set which consists of local real crime information and urban physical or non-physical data. Then, we developed a crime prediction model through machine learning method. Finally, we assumed several possible scenarios and calculated the probability of crime and visualized the results in a map so as to increase the people's understanding. Among the factors affecting the crime occurrence revealed in previous and case studies, data was processed in the form of a big data for machine learning: real crime information, weather information (temperature, rainfall, wind speed, humidity, sunshine, insolation, snowfall, cloud cover) and local information (average building coverage, average floor area ratio, average building height, number of buildings, average appraised land value, average area of residential building, average number of ground floor). Among the supervised machine learning algorithms, the decision tree model, the random forest model, and the SVM model, which are known to be powerful and accurate in various fields were utilized to construct crime prevention model. As a result, decision tree model with the lowest RMSE was selected as an optimal prediction model. Based on this model, several scenarios were set for theft and violence cases which are the most frequent in the case city J, and the probability of crime was estimated by $250{\times}250m$ grid. As a result, we could find that the high crime risky area is occurring in three patterns in case city J. The probability of crime was divided into three classes and visualized in map by $250{\times}250m$ grid. Finally, we could develop a crime prediction model using machine learning algorithm and visualized the crime risky areas in a map which can recalculate the model and visualize the result simultaneously as time and urban conditions change.

• Journal of the Korean Academy of Child and Adolescent Psychiatry
• /
• v.8 no.1
• /
• pp.57-69
• /
• 1997

Objective：At the present time in Korea, for a considerable proportion of children and adolescent, delinquent behavior and violence has become as a way of life in their lives and a major social problem issue as well. The contributing factors to this problem were assumed to be the negative interaction between family environment and character of adolescent. The purpose of this study is to search the relationship between these constructs and juvenile delinquency. Method：Data were collected through questionnaire survey over a period of 2 months. Subjects served for this study consisted of 1,863 adolescents including 657 delinquent adolescents and 1,206 student adolescents in Korea, sampled from Korean student population and delinquent adolescent population confined in juvenile corrective institutions, using proportional stratified random sampling method. Their age ranged between 12 and 18 years. Data were analysed by IBM PC using SAS program. Statistical methods employed were Chi-square and principal component analysis. Results：The results of this study were as follows：Inconsistency by parental child rearing patterns tended to affect delinquent behavior among delinquent adolescents. On the other hand, adolescent students were consistently reared by their parent with democratic, flexible, trusting their children and reward-oriented attitudes. In comparison of both parents in the degree of influence on their children, it was revealed that paternal child rearing pattern was more influential on their children’s behaviors than maternal’s. The psychological instability of family, disharmonious parent-child relationships tended to be contributing to delinquent behavior among delinquent adolescents. Especially, It was an interesting finding that student’s mother is the higher employed than delinquent’s mother. However working mother was more prevalent in the student’ adolescents than in student adolescents in previous studies. The delinquent adolescents have more depressive trend, more complaints of psychosomatic symptoms, the higher degree of need frustration, the more maladaptive and antisocial personality pattern than student adolescents. Conclusion：Recently, many studies on association between family factor, character of adolescent and juvenile delinquent behavior have produced relatively consistent results. This study showed that family environment and character trait of adolescent also were linked with delinquent behavior such as smoking, drinking, runaway and physical assaults etc. The results of this survey may provide impetus for future speculation and study of correlation or reciprocal interaction between family factor, character trait of adolescent and delinquent behavior during adolescence and beyond.

• The Journal of Korean Society for School & Community Health Education
• /
• v.5
• /
• pp.107-122
• /
• 2004

To correctly plant the value of sex to the juvenile, we cannot overemphasize the importance of the sexual education in schools. Therefore, the study for teachers' consciousness and view of sex is also necessary, because they are subjects of education and role-models of sex of their students. Especially, if teachers are over fifty in age, it is more important, because it is obvious, as they are in positions of managers and directors of education, that their view of sexual value and consciousness are influencing the aim of education and the course of education. Hereby this study was conducted to check their sexual consciousness, attitude, and condition and to prepare for the basic data needed for the development of a sexual education program suitable to them. The methods of the survey of this study are applied by modifying or supplementing those of precedented studies. They are used after analyzing reliance of items according to Cronbach's $\alpha$ figure calculating law, and modifying or supplementing items lower in reliance. The questionnaire survey was conducted among 1,000 randomly selected from teachers working in middle and high schools in Korea from June 14th in 2004 to June 30th. The survey analyzed 632 questionnaires suitable to it. The outcomes of the survey of this study are like the following: First, the objects of the survey consist of 64.6% men and 35.4% women. Among them, 41.1% are under fifty and the rest are over fifty. As for the periods of marriage, 15.5% are unmarried, 16.3% are under ten years, 18.0% are between ten and twenty, and 50.2% are over twenty. Second, with reagard to sex, 25.6% admit the necessity of a heterosexual friend. 32.0% say that they are conservative to sex. 54.1% are taught sexual education. 67.1% attribute sexual education to nursing teachers. Third, among those who answer that they enoughly know the concept of sex, seenig by age, 25.0% are under fifty and 58.1% are over fifty. Seening by the periods of marriage, 9.2% are unmarried, 28.2% are under ten, 49.1% are between ten and twenty, and 59.0% are over twenty. Among those who answer that they enoughly know the concepts of sexual harassment and sexual violence, seenig by age, in the turns by above-mentioned order, each 47.7% and 76.3%. Seening by the periods of marriage, each 9.2%, 28.2%, 49.1%, and 59.0%. Fourth, among those who answer that "teachers also need sexual education and sexual counsel," by age, each92.7% and 91.4%. By the periods of marriage, each 89.8%, 95.2%, 89.4%, and 92.4%. As a matter of course, we can infer the necessity of the sexual education and sexual counsel for teachers. Fifth, among those who answer that they are satisfied with their sexuality, by age, each 41.1% and 61.3%. By the period of marriage, each 4.1%, 63.1%, 64.1%, and 61.5%. As for the sexual desire like spiritual intercourse, physical intercourse containing sexuality, by age, each 71.9% and 93.5%. By the periods of marriage, each 54.0%, 81.5%, 90.3%, and 93.0%. The survey shows that those over fifty and having long marriage are feeling the stronger desire towards sexuality. Through the outcomes of this survey, a few suggestions are possible: First, it is necessary to check of the teachers' view of sexual value and to study deep about the sexual tendency of them in twenties, thirties, and forties. It is to make them teach their students on the firm basis, and also to develop suitable sexual education and counsel program.

• Korean Journal of Social Welfare Studies
• /
• v.48 no.3
• /
• pp.171-208
• /
• 2017

The purpose of this study is to classify the underlying and parsimonious types of child maltreatment and examine whether the effects of risk factors on child maltreatment recurrence differ by type of maltreatment. We utilized the multiyear national administrative data from the National Child Maltreatment Information System collected by Child Protection Agency in Korea. Of 26,921 child maltreatment victims reported and substantiated on or after January 1, 2012, 1,447 children who had recurrence of child maltreatment until December 31, 2015 were selected as maltreatment recurrence group and 4,580 children who had not experienced maltreatment since first substantiation were assigned as maltreatment non-recurrence group. Latent class analysis(LCA) and latent transition analysis(LTA) were used to group children with similar maltreatment subtypes into discrete classes of child maltreatment recurrence. Logistic regression is employed to examine the association between the child maltreatment predominant types and risk factors for recurrence. Results of LCA and LTA showed four latent classes representing predominant type of child maltreatment: 'physical abuse predominant type', 'emotional abuse predominant type', 'sexual abuse predominant type', and 'neglect type'. Significant differences in the effect of risk factors among latent classes were found in child's age and gender, perpetrator's gender, family poverty, biological parent as the perpetrator, domestic violence toward partner, perpetrator's alcoholic problem, insufficient parenting skills, and out-of-home care service, Based on these findings, results suggested how the typology can be used to guide decision about who to target in prevention and intervention programs, and which features of risk factors to target. Practice and policy implications as well as further research tasks were discussed in the lights of searching for useful and important strategies to prevent recurrence of child maltreatment.