• 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 KIISE
• /
• v.44 no.4
• /
• pp.417-422
• /
• 2017

Anomaly detection is the identification of data that do not conform to a normal pattern or behavior model in a dataset. It can be utilized for detecting errors among data generated by devices or user behavior change in a social network data set. In this study, we proposed a new approach using rank correlation coefficient to efficiently detect abnormal data in devices of a building. With the increased push for energy conservation, many energy efficiency solutions have been proposed over the years. HVAC (Heating, Ventilating and Air Conditioning) system monitors and manages thousands of sensors such as thermostats, air conditioners, and lighting in large buildings. Currently, operators use the building's HVAC system for controlling efficient energy consumption. By using the proposed approach, it is possible to observe changes of ranking relationship between the devices in HVAC system and identify abnormal behavior in social network.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.11
• /
• pp.795-800
• /
• 2013

Early detection of oestrus in Korean cows is one of the important issues in maximizing the economic benefit. Although various methods have been proposed, we still need to improve the performance of the oestrus detection system. In this paper, we propose a video surveillance system which can detect unusual behavior of multiple cows including the mounting activity. The unusual behavior detection is to detect the dangerous or abnormal situations of cows in video coming in real time from a surveillance camera promptly and correctly. The prototype system for unusual behavior detection gets an input video from a fixed location camera, and uses the motion vector to represent the motion information of cows in video, and finally selects a SVDD (one of the most well-known types of one-class SVM) as a detector by reinterpreting the unusual behavior into an one class decision problem from the practical points of view. The experimental results with the videos obtained from a farm located in Jinju illustrate the efficiency of the proposed method.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.01a
• /
• pp.137-140
• /
• 2019

본 논문에서는 자동 제어 시스템의 이상행위를 분석하기 위하여 MODBUS 프로토콜 기반의 제어 명령을 수집 분류하여 등록된 화이트리스트 기반으로 이를 탐지하는 시스템을 구현하였다. 구현 시스템은 자동 제어 시스템 기반으로 다양한 생산설비를 동작시키는 스마트팩토리 시스템을 비롯하여 국가기간 산업에 활용 가능하며, 생산설비의 이상 작동을 확인하기 위하여 생산설비의 동작 신호를 주기적으로 수집 분석하여 정상적인 작업형태에서 벗어나는 이상 작업을 판단할 수 있도록 구성하였다. 또한, 소형화된 공장 자동화 설비를 구성하여 실제 스마트팩토리 환경에서 제어명령을 수집하고, 수집된 신호로부터 이상 작동을 검출하는 제안 시스템의 구현 결과를 설명한다.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.21 no.6
• /
• pp.183-190
• /
• 2011

In this paper, we propose a prototype system for abnormal sound detection and identification which detects and recognizes the abnormal situations by means of analyzing audio information coming in real time from CCTV cameras under surveillance environment. The proposed system is composed of two layers: The first layer is an one-class support vector machine, i.e., support vector data description (SVDD) that performs rapid detection of abnormal situations and alerts to the manager. The second layer classifies the detected abnormal sound into predefined class such as 'gun', 'scream', 'siren', 'crash', 'bomb' via a sparse representation classifier (SRC) to cope with emergency situations. The proposed system is designed in a hierarchical manner via a mixture of SVDD and SRC, which has desired characteristics as follows: 1) By fast detecting abnormal sound using SVDD trained with only normal sound, it does not perform the unnecessary classification for normal sound. 2) It ensures a reliable system performance via a SRC that has been successfully applied in the field of face recognition. 3) With the intrinsic incremental learning capability of SRC, it can actively adapt itself to the change of a sound database. The experimental results with the qualitative analysis illustrate the efficiency of the proposed method.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.26 no.6
• /
• pp.390-396
• /
• 2021

Lithium-ion batteries have been designed and used as battery packs with series and parallel combinations that are suitable for use. However, due to its internal electrochemical properties, producing the battery's condition at the same value is impossible for individual cells. In addition, the management of characteristic deviations between individual cells is essential for the safe and efficient use of batteries as aging progresses with the use of batteries. In this work, we propose a method to manage deviation properties and detect abnormal behavior in the configuration of a combined battery pack of these multiple battery cells. The proposed method can separate and detect probabilistic low-frequency information according to statistical information based on Z-score. The verification of the proposed algorithm was validated using experimental results from 10S3P battery packs, and the implemented algorithm based on Z-score was validated as a way to effectively manage multiple individual cell information.

• Journal of Korea Multimedia Society
• /
• v.9 no.8
• /
• pp.1030-1036
• /
• 2006

The rapid proliferation of wireless networks and mobile computing applications has changed the landscape of network security. Anomaly detection is a pattern recognition task whose goal is to report the occurrence of abnormal or unknown behavior in a given system being monitored. This paper presents an efficient rough set based anomaly detection method that can effectively identify a group of especially harmful internal masqueraders in cellular mobile networks. Our scheme uses the trace data of wireless application layer by a user as feature value. Based on the feature values, the use pattern of a mobile's user can be captured by rough sets, and the abnormal behavior of the mobile can be also detected effectively by applying a roughness membership function considering weighted feature values. The performance of our scheme is evaluated by a simulation. Simulation results demonstrate that the anomalies are well detected by the method that assigns different weighted values to feature attributes depending on importance.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.8 no.2
• /
• pp.41-47
• /
• 2012

MANET has vulnerable structure on security owing to structural characteristics as follows. MANET consisted of moving nodes is that every nodes have to perform function of router. Every node has to provide reliable routing service in cooperation each other. These properties are caused by expose to various attacks. But, it is difficult that position of environment intrusion detection system is established, information is collected, and particularly attack is detected because of moving of nodes in MANET environment. It is not easy that important profile is constructed also. In this paper, conformal predictor - support vector machine(CP-SVM) based intrusion detection technique was proposed in order to do more accurate and efficient intrusion detection. In this study, IDS-agents calculate p value from collected packet and transmit to cluster head, and then other all cluster head have same value and detect abnormal behavior using the value. Cluster form of hierarchical structure was used to reduce consumption of nodes also. Effectiveness of proposed method was confirmed through experiment.

• Proceedings of the Korean Information Science Society Conference
• /
• 2011.06d
• /
• pp.115-117
• /
• 2011

Intrusion detection systems (IDS) are supposed to be an efficient safety measure against inside attacks. In purely distributed IDS approach, IDS agent is installed in every node. It checks abnormal behavior of neighboring nodes locally. It collects the data that it receives from nodes in its radio range. Sensor nodes audit that data and generate alerts for abnormal activity. Here, there are two ways of taking decision. First, it can take decision individually and second, it can communicate with its neighbor to find the status of the claimed compromised nodes. In this paper, we propose a collaborative decision making scheme for purely distributed detection system. The proposed scheme is light weight compared to consensus based validation methodology. It provides a better scheme to find intrusions by interacting with other nodes.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.29 no.2
• /
• pp.321-330
• /
• 2019

Prevention of corporate confidentiality leakage by insiders in enterprises is an essential task for the survival of enterprises. In order to prevent information leakage by insiders, companies have adopted security solutions, but there is a limit to effectively detect abnormal behavior of insiders with access privileges. In this study, we use the Unsupervised Learning algorithm of the machine learning technique to effectively and efficiently cluster the normal and abnormal access logs of the worker's work screen in the manufacturing information system, which includes the company's product manufacturing history and quality information. We propose an optimal feature selection model for anomaly detection by studying clustering methods.