• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.34 no.2
• /
• pp.281-288
• /
• 2024

The sixth generation(6G) wireless communication technology is advancing toward ultra-high speed, ultra-high bandwidth, and hyper-connectivity. With the development of communication technologies, the formation of a hyper-connected society is rapidly accelerating, expanding from the IoT(Internet of Things) to the IoE(Internet of Everything). However, at the same time, security threats targeting IoT devices have become widespread, and there are concerns about security incidents such as unauthorized access and information leakage. As a result, the need for security-enhancing solutions is increasing. In this paper, we implement an autoencoder-based anomaly detection model utilizing real-time collected network traffics in respond to IoT security threats. Considering the difficulty of capturing IoT device traffic data for each attack in real IoT environments, we use an unsupervised learning-based autoencoder and implement 6 different autoencoder models based on the use of noise in the training data and the dimensions of the latent space. By comparing the model performance through experiments, we provide a performance evaluation of the anomaly detection model for detecting abnormal network traffic.

• International Journal of Computer Science & Network Security
• /
• v.24 no.5
• /
• pp.111-118
• /
• 2024

In general network-based intrusion detection system is designed to detect malicious behavior directed at a network or its resources. The key goal of this paper is to look at network data and identify whether it is normal traffic data or anomaly traffic data specifically for accounting information systems. In today's world, there are a variety of principles for detecting various forms of network-based intrusion. In this paper, we are using supervised machine learning techniques. Classification models are used to train and validate data. Using these algorithms we are training the system using a training dataset then we use this trained system to detect intrusion from the testing dataset. In our proposed method, we will detect whether the network data is normal or an anomaly. Using this method we can avoid unauthorized activity on the network and systems under that network. The Decision Tree and K-Nearest Neighbor are applied to the proposed model to classify abnormal to normal behaviors of network traffic data. In addition to that, Logistic Regression Classifier and Support Vector Classification algorithms are used in our model to support proposed concepts. Furthermore, a feature selection method is used to collect valuable information from the dataset to enhance the efficiency of the proposed approach. Random Forest machine learning algorithm is used, which assists the system to identify crucial aspects and focus on them rather than all the features them. The experimental findings revealed that the suggested method for network intrusion detection has a neglected false alarm rate, with the accuracy of the result expected to be between 95% and 100%. As a result of the high precision rate, this concept can be used to detect network data intrusion and prevent vulnerabilities on the network.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.4
• /
• pp.771-782
• /
• 2021

Regular or irregular situations such as traffic accidents, damage to road facilities, maintenance or repair work, and vehicle breakdowns occur frequently on highways. It is required to provide traffic services to drivers by promptly recognizing these regular or irregular situations, various techniques have been developed for rapidly collecting data and detecting abnormal traffic conditions to solve the problem. We propose a method that can be used for verification and demonstration of unexpected situation algorithms by establishing a system and developing algorithms for detecting unexpected situations on highways. For the detection of emergencies on expressways, a system was established by defining the expressway contingency and algorithm development, and a test bed was operated to suggest a method that can be used for verification and demonstration of contingency algorithms. In this study, a system was established by defining the unexpected situation and developing an algorithm to detect the unexpected situation on the highway, and a method that can be used verifying and demonstrating unexpected situations. It is expected to secure golden time for the injured by reducing the effectiveness of secondary accidents. Also predictable accidents can be reduced in case of unexpected situations and the detection time of unpredictable accidents.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.14 no.2
• /
• pp.130-135
• /
• 2014

For the past three decades, ship-to-ship collision accidents have steadily increased on the coast of South Korea by about 20% annually. Marine accidents have become more likely and more devastating in areas with increasing marine traffic and rising numbers of high-speed ships. Over 30% of the marine accidents in South Korea are concentrated in spring, since Korea's coast is often covered in dense fog at this time of the year. Fog is generated when a large temperature range exists within a day, and this daily temperature range has increased due to abnormal weather conditions. This research proposed a system for transmitting a navigator's intention utilizing electronic methods. A navigator's intention was expressed on the electronic navigation chart for easier understanding of the surrounding situation, and the effectiveness of the system was verified through practical tests.

• Transactions of the KSME C: Technology and Education
• /
• v.3 no.2
• /
• pp.125-130
• /
• 2015

Using flexible multibody system dynamic method, the rigid-flexible coupling multibody dynamic analysis model of the drum brake system was developed, and the kinematic and dynamic simulation of the system was processed as its object of study. Simulations show that the friction will increase with the dynamic friction coefficient, but high dynamic friction coefficient will cause the abnormal vibration and worsen the stability of the brake system, even the stability of the whole automobile. The modeling of flexible multi-body can effectively analyze and solve complex three-dimensional dynamic subjects of brake system and evaluate brake capability. Further research and study on this basis will result in a convenient and effective solution that can be much helpful to study, design and development of the brake system.

• Journal of Chest Surgery
• /
• v.21 no.3
• /
• pp.547-552
• /
• 1988

Rupture of the main bronchus followed by blunt chest trauma is comparatively very rare. Early recognition of bronchial rupture and emergency thoracostomy and management is essential for reducing of morbidity and mortality and late complications. This case was 11 years old female who was a primary school student. The patient was sustained a crushing injury to her right hemithorax by traffic accident and had been taken emergency closed thoracostomy at her second intercostal space, midclavicular line at emergency room. In the course of the next 2 hours, the girl`s condition remained critical with tension pneumothorax and abnormal arterial blood gas analysis. Induction of anesthesia started 3 hours after the accident. During the general anesthesia, cardiac arrest was occurred and cardiac resuscitation was performed. Right upper lobectomy and end-to-end anastomosis of ruptured right main bronchus was performed. Postoperative course was satisfactory.

• Convergence Security Journal
• /
• v.14 no.2
• /
• pp.65-72
• /
• 2014

This paper proposes multi-filtering method on the double firewall to prevent DDoS attack. In the first firewall, R-PA filtering algorithm and rigid hop counter filtering method are applied by analyzing packet paths. In the second firewall, packets are examined to be distinguished abnormal from normal packets. Security policy system monitors each user sessions and if the traffic is over the threshold value, the system blocks that session for an assigned time.

• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.207-208
• /
• 2006

Intrusion detection technology is highlighted in order to establish a safe information-oriented environment. Intrusion detection system can be categorized into anomaly detection and misuse detection according to intrusion detection pattern. In this paper, we propose an architecture to make up for the defect of conventional anomaly intrusion detection. This architecture reduces additional resource consumption and cost by placing the agent in the strategic location in Internet.

• Journal of Pharmacopuncture
• /
• v.22 no.3
• /
• pp.171-175
• /
• 2019

Objectives: TA is a polyherbal extract comprising seven herbs, typically used for the pharmacopuncture treatment of patients with traffic accident- related injuries and musculoskeletal diseases. This animal study was conducted to evaluate the safety of the TA extract, using a single-dose toxicity test. Methods: The dose range and sampling time were first established. Six- week-old Sprague-Dawley rats were administered 1.0 mL of TA or normal saline (control), intramuscularly, for the single-dose toxicity test. The general condition, mortality, and histology of all rats were observed for 2 weeks. Results: No abnormal symptoms or deaths were observed in any group. The body weights of the rats in the TA and control groups were similar. No significant differences in histopathology were observed between the groups. Conclusion : Our study indicates that 1.0 mL of TA extract may be safely administered for pharmacopuncture for treatment of patients in traditional medicine clinics.

• KNOM Review
• /
• v.15 no.1
• /
• pp.31-39
• /
• 2012

오늘날 네트워크 환경은 다양한 응용의 등장으로 트래픽이 복잡 다양해지고 있다. 이러한 상황 속에서 정확한 네트워크의 상태 파악을 위한 트래픽의 응용 별 분류에 대한 중요성은 더욱더 증가하고 있다. 최근 트래픽 플로우의 통계 정보를 이용한 트래픽의 응용 별 분류 방법론에 대한 연구가 활발히 진행되고 있다. 하지만 대부분의 연구들은 TCP 세션의 이상 동작에 대한 고려가 없어 분류결과의 오분류 및 미분류가 발생할 수 있다. 따라서 본 논문에서는 TCP 세션의 이상동작의 문제점을 지적하고 이를 개선하는 방법론을 제안한다. 제안된 방법론을 통계적 응용 트래픽 분류방법에 적용함으로써 그 타당성을 증명한다.