• Journal of Korea Multimedia Society
• /
• v.25 no.8
• /
• pp.1049-1058
• /
• 2022

HAR(Human Action Recognition) such as anomaly and object detection has become a trend in research field(s) that focus on utilizing Artificial Intelligence (AI) methods to analyze patterns of human action in crime-ridden area(s), media services, and industrial facilities. Especially, in real-time system(s) using video streaming data, HAR has become a more important AI-based research field in application development and many different research fields using HAR have currently been developed and improved. In this paper, we propose and analyze a deep-learning-based HAR that provides more efficient scheme(s) using an intelligent AI models, such system can be applied to media services using RGB video streaming data usage without feature extraction pre-processing. For the method, we adopt Slowfast based on the Deep Neural Network(DNN) model under an open dataset(HMDB-51 or UCF101) for improvement in prediction accuracy.

• The Journal of the Korea Contents Association
• /
• v.12 no.7
• /
• pp.176-182
• /
• 2012

Voice Phishing finds out personal information illegally using electrification and it is confidence game that withdraw deposit on the basis of this. It appeared by new social problem as damage instances increase rapidly. Target of the damage is invading indiscriminately to good civilian and is crime that commit by foreigners such as a most Chinese, Formosan. Voice Phishing can be crime type of new form in terms of criminal practice is achieved in the foreign countries. Therefore, this study wishes to analyze present occurrence actual conditions and example, and search effective confrontation plan regarding Voice Phishing. Voice Phishing criminal offense is growing as crime is not eradicated in spite of continuous public relations and control, and technique is diversified and specializes preferably. Hereafter, confrontation plan about problem may have to be readied in banking communication investigation to eradicate Voice Phishing. Also, polices control activity may have to be reinforce through quick investigation's practice and development of investigation technique, and relevant government ministry and international mutual assistance cooperation such as the Interpol should be reinforced because is shown international crime personality.

• Convergence Security Journal
• /
• v.23 no.5
• /
• pp.117-123
• /
• 2023

Recently, as the demand for Generative Artificial Intelligence (AI) and artificial intelligence has increased, the seriousness of misuse and abuse has emerged. However, intelligent CCTV, which maximizes detection of abnormal behavior, is of great help to prevent crime in the military and police. AI performs learning as taught by humans and then proceeds with self-learning. Since AI makes judgments according to the learned results, it is necessary to clearly understand the characteristics of learning. However, it is often difficult to visually judge strange and abnormal behaviors that are ambiguous even for humans to judge. It is very difficult to learn this with the eyes of artificial intelligence, and the result of learning is very many False Positive, False Negative, and True Negative. In response, this paper presented standards and methods for clarifying the learning of AI's strange and abnormal behaviors, and presented learning measures to maximize the judgment ability of intelligent CCTV's False Positive, False Negative, and True Negative. Through this paper, it is expected that the artificial intelligence engine performance of intelligent CCTV currently in use can be maximized, and the ratio of False Positive and False Negative can be minimized..

• Journal of Digital Convergence
• /
• v.18 no.8
• /
• pp.85-95
• /
• 2020

It is a newly defined concept of digital sex crimes as the sex crime pattern in Korea is integrated with digital technology. After examining the current status and response of digital sex crimes in Korea, legal and institutional gaps are identified.It is also aimed at drawing up appropriate responses to domestic situations compared to cases in major foreign countries. This study adopted the mode of literature research.It used related data from government agencies, various statistics and survey data, seminar data organized by the National Assembly office, women's organizations, and research reports. The ultimate goal is to derive the problem situation by analyzing the current system.The results of this study are to discuss digital sex crimes that are being expanded and reproduced by the development of digital media. It also points out that the legal vacuum caused by the law's failure to keep up with the law needs to be continued.Our conclusion is that we should actively accept best practices from abroad. In addition, it is necessary to create a community value in which all members of society become "monitors" in the recognition that they may be perpetrators or victims.

• Korean Journal of Cognitive Science
• /
• v.32 no.4
• /
• pp.169-191
• /
• 2021

With the development of artificial intelligence(AI), the jobs of many human experts are threatened, and this also applies to the legal profession. This study attempted to investigate whether AI can actually replace humans in the legal profession, especially the role of judges making final judgments. For this purpose, from the perspective of uniqueness neglect, this study was conducted to confirm the effect of involvement and the severity on acceptance of the judgment made by the AI judge (Experiment 1) and the AI jury (Experiment 2). The involvement was manipulated as if the subject who was sentenced for committing a crime was his or her family (mother, father) or stranger, and the severity was manipulated by the extent of the damage, the perception of the crime, and the number of applied crimes. In Experiment 1, the interactive effect of involvement and severity was found. Specifically, when the involvement was low, the acceptance of AI judges was higher in high severity (vs. low severity). Conversely, when the involvement was high, the acceptance of AI judges was higher in low severity (vs. high severity). The same interactions as in Experiment 1 occurred in Experiment 2. Specifically, when the involvement was low, a larger number of AI jury members were allocated in high severity (vs. low severity). On the other hand, when the involvement was high, the number of AI juries increased in low severity (vs. high severity). This study has implications in that it is the first experimental study in Korea on artificial intelligence legal judgment and that it presents the prospects for the jobs of legal experts.

• Journal of English Language & Literature
• /
• v.56 no.5
• /
• pp.931-946
• /
• 2010

This paper examines the role of gender ideology in early British and American detective fiction focusing on the female detectives. Since a detective's attributes honor and idealize such traditionally masculine qualities as independence, intelligence, heroism, and bravery, the woman detective fiction has potentiality to operate against the established gender norms. The narratives about women in pursuit of justice and order through their criminal investigation can allow women to possess the masculine rationality and power. The subversive possibility inherent in the woman detective fiction is, however, contained by the representation of the female detectives and the negotiation through narratives. A female detective is represented either as unfeminine and thus unattractive and unlikeable or as desperate for survival. Her threatening potentiality is easily dismissed as that of an inadequate woman or a desperate one. The compromise in narratives is effected by the following three ways: first, a female detective is assigned to investigate crimes as an assistant to the male detectives; second, staying within the domestic sphere, she solves crimes by using her expert knowledge of the domestic service; and third, her detective narrative ends with the conventional marriage plot. Confining the female detectives within the conventional feminine roles and domains, the woman detective fiction supports and reestablishes the dominant gender ideology.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.14 no.2
• /
• pp.149-160
• /
• 2021

In this study, artificial intelligence-based algorithms were proposed, which included a fuzzy search for matching suspects between current and historical crimes in order to obtain related cases in criminal history, as well as conditional generative adversarial networks for crime prediction system (CPS) using Timor-Leste as a case study. By comparing the data from the criminal records, the built algorithms transform witness descriptions in the form of sketches into realistic face images. The proposed algorithms and CPS's findings confirmed that they are useful for rapidly reducing both the time and successful duties of police officers in dealing with crimes. Since it is difficult to maintain social safety nets with inadequate human resources and budgets, the proposed implemented system would significantly assist in improving the criminal investigation process in Timor-Leste.

• Journal of Arbitration Studies
• /
• v.19 no.3
• /
• pp.93-119
• /
• 2009

Nowadays the number of crimes is increasing rapidly and society is getting more and more dangerous. Recently the criminal aspect of our society, the intelligence, diversity, localized area, as well as for the crime victims also difficult to predict the damage recovery is not easy to change their level of pain and are also serious. This phenomenon is increasingly expected to intensify, the proper response is a factory. The more so if the victim of murder. The criminal mediation working on the operational adjustments Borrower payment, Construction charges, investments and financial transactions due to interpersonal conflicts that occurred as a fraud, embezzlement, breach of trust property crimes such accused, individuals between the defamatory, offensive, encroachment, violating intellectual property rights and private Disputes about the complaint case and other criminal disputes submitted to mediation to resolve it deems relevant to the case who are accused. But the core of a detective control adjustment, adjust the members' representative to the region, including front-line player or a lawyer appointed by the attorney general at this time by becoming parties to this negative view may be ahead. Some scholars are criticizing the current criminal justice system for the absence of proper care for the criminal victims, as an alternative to the traditional criminal justice system. The introduction of the summary trial and related legal cases, the command structure, compensation system, crime victims' structural system can be seen as more classify, crime subject to victim's complaint, By case with a criminal misdemeanor in addition to disagree not punish criminal, minor offense destination, traffic offenders, regular property crime, credit card theft, intellectual property rights violators can be seen due to more categories can try. They sued in law enforcement, Prosecution case has been received and if any one party to the criminal detective Arbitration request arbitration by the parties can agree to immediately contact must be referred to arbitration within 15 days of when the arbitration case will be dismissed. These kinds of early results of the case related to, lawyers are involved directly in the arbitration shall be excluded. Arbitration system is the introduction of criminal justice agencies working to help resolve conflicts caused by adjustment problems will be able to. This article does not argue that we should stick to the traditional justice system as a whole. Instead it argues that the restrictive role of the traditional justice is to be preserved.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.22 no.4
• /
• pp.328-334
• /
• 2016

The everyday life of police officers requires them to face a number of criminal acts and enter compromising crime scenes. In this case, officers may be compelled to make a personal expression of negative emotions. Negative emotions of members confidence for effective job processing and contributions duties and achievement of the job within the marine police force. Therefore, to control the emotive dissonance of organization members is a great help to the development of the organization. This study focuses on emotional dissonance among marine police officers to verify the impact of this dissonance on job burnout and consider the mediating effect of emotional intelligence. Research results are as follows: First, the relationship between emotional dissonance sub-factors and job burnout among marine police officers was studied. It was found that marine police did not feel emotionally jarred because they consciously tried to abstain from emotional engagement, but this was found to reduce emotional intelligence as related to desired emotions as well. Second, Emotional intelligence of the Marine Police was found on a significant impact on job burnout. Third, the impact of emotions in relation to emotional dissonance that job burnout of marine police intelligence officials confirmed that there is a statistically significant mediating effect. Finally, in a comparison of direct effects versus mediated effects, marine police were seen to be prone to emotional dissonance and experienced job burnout as a direct result of applying greater emotional intelligence.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.191-193
• /
• 2022

The advent of the 4th Industrial Revolution due to the trigger of digital technologies such as artificial intelligence and big data has caused many changes in society, culture, and industry. However, traditional markets in each region are not responding quickly to new distribution environments and consumer changes. In particular, in the case of traditional markets in Jeju, regional characteristics such as marketing strategies for tourists visiting Jeju have not been utilized. Therefore, this study proposes the establishment of a smart traditional market based on big data and artificial intelligence that utilizes the regional characteristics of Jeju. The research contents include customer profiling through visitor big data analysis, providing tourist movement results through traffic analysis, providing real-time popular product charts, and developing video-based fire and crime prevention functions.