• The Journal of Society for e-Business Studies
• /
• v.23 no.4
• /
• pp.19-39
• /
• 2018

Recently, fake news has attracted worldwide attentions regardless of the fields. The Hyundai Research Institute estimated that the amount of fake news damage reached about 30.9 trillion won per year. The government is making efforts to develop artificial intelligence source technology to detect fake news such as holding "artificial intelligence R&D challenge" competition on the title of "searching for fake news." Fact checking services are also being provided in various private sector fields. Nevertheless, in academic fields, there are also many attempts have been conducted in detecting the fake news. Typically, there are different attempts in detecting fake news such as expert-based, collective intelligence-based, artificial intelligence-based, and semantic-based. However, the more accurate the fake news manipulation is, the more difficult it is to identify the authenticity of the news by analyzing the news itself. Furthermore, the accuracy of most fake news detection models tends to be overestimated. Therefore, in this study, we first propose a method to secure the fairness of false news detection model accuracy. Secondly, we propose a method to identify the authenticity of the news using the social data broadly generated by the reaction to the news as well as the contents of the news.

• Korean Journal of Remote Sensing
• /
• v.35 no.1
• /
• pp.39-55
• /
• 2019

In this study, we have proposed an improved method to detect forest fires by correcting the reflected signals of day images using the middle-wavelength infrared (MWIR) channel. The proposed method is allowed to remove the reflected signals only using the image itself without an existing data source such as a land-cover map or atmospheric data. It includes the processing steps for calculating a solar-reflected signal such as 1) a simple correction model of the atmospheric transmittance for the MWIR channel and 2) calculating the image-based reflectance. We tested the performance of the method using the MODIS product. When compared to the conventional MODIS fire detection algorithm (MOD14 collection 6), the total number of detected fires was improved by approximately 17%. Most of all, the detection of fires improved by approximately 30% in the high reflection areas of the images. Moreover, the false alarm caused by artificial objects was clearly reduced and a confidence level analysis of the undetected fires showed that the proposed method had much better performance. The proposed method would be applicable to most satellite sensors with MWIR and thermal infrared channels. Especially for geostationary satellites such as GOES-R, HIMAWARI-8/9 and GeoKompsat-2A, the short acquisition time would greatly improve the performance of the proposed fire detection algorithm because reflected signals in the geostationary satellite images frequently vary according to solar zenith angle.

• Journal of Biomedical Engineering Research
• /
• v.44 no.3
• /
• pp.211-217
• /
• 2023

Recently, many studies have introduced artificial intelligence systems in the surgical process to reduce the incidence and mortality of complications in patients. Bleeding is a major cause of operative mortality and complications. However, there have been few studies conducted on detecting bleeding in surgical videos. To advance the development of deep learning models for detecting intraoperative hemorrhage, three models have been trained and compared; such as, YOLOv5, RetinaNet50, and RetinaNet101. We collected 1,016 bleeding images extracted from five surgical videos. The ground truths were labeled based on agreement from two specialists. To train and evaluate models, we divided the datasets into training data, validation data, and test data. For training, 812 images (80%) were selected from the dataset. Another 102 images (10%) were used for evaluation and the remaining 102 images (10%) were used as the evaluation data. The three main metrics used to evaluate performance are precision, recall, and false positive per image (FPPI). Based on the evaluation metrics, RetinaNet101 achieved the best detection results out of the three models (Precision rate of 0.99±0.01, Recall rate of 0.93±0.02, and FPPI of 0.01±0.01). The information on the bleeding detected in surgical videos can be quickly transmitted to the operating room, improving patient outcomes.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.449-451
• /
• 2021

Cyber-attacks targeting endpoints have developed sophisticatedly into targeted and intelligent attacks, Advanced Persistent Threat (APT) targeting the Industrial Internet of Things (IIoT) has increased accordingly. Machine learning-based Endpoint Detection and Response (EDR) solutions combine and complement rule-based conventional security tools to effectively defend against APT attacks are gaining attention. However, universal EDR solutions have a high false positive rate, and needs high-level analysts to monitor and analyze a tremendous amount of alerts. Therefore, the process of optimizing machine learning-based EDR solutions that consider the characteristics and vulnerabilities of IIoT environment is essential. In this study, we analyze the flow and impact of IIoT targeted APT cases and compare the method of machine learning-based APT detection EDR solutions.

• Convergence Security Journal
• /
• v.23 no.2
• /
• pp.85-94
• /
• 2023

In the face of the serious security situation with the increasing threat from North Korea, Korean Army is pursuing a reduction in troops through the performance improvement project of the GOP science-based border security system, which utilizes advanced technology. In order for the GOP science-based border security system to be an effective alternative to the decrease in military resources due to the population decline, it must guarantee a high detection and identification rate and minimize troop intervention by dramatically improving the false detection rate. Recently introduced in Korean Army, the GOP science-based border security system is known to ensure a relatively high detection and identification rate in good weather conditions, but its performance in harsh weather conditions such as rain and fog is somewhat lacking. As an alternative to overcoming this, a radar-based border security system that can detect objects even in bad weather has been proposed. This paper proves the effectiveness of the AI-based scientific border security system based on radar that is being currently tested at the 00th Division through the 2021 Rapid Acquisition Program, and suggests the direction of development for the GOP scientific border security system.

• Journal of Biomedical Engineering Research
• /
• v.44 no.6
• /
• pp.384-391
• /
• 2023

Among the elderly, fatal injuries and deaths are significantly attributed to falls. Therefore, a pre-impact fall detection system is necessary for injury prevention. In this study, a robust threshold-based algorithm was proposed for pre-impact fall detection, reducing false positives in highly dynamic daily-living movements. The algorithm was validated using public datasets (KFall and FARSEEING) that include the real-world elderly fall. A 6-axis IMU sensor (Movella Dot, Movella, Netherlands) was attached to S2 of 20 healthy adults (aged 22.0±1.9years, height 164.9±5.9cm, weight 61.4±17.1kg) to measure 14 activities of daily living and 11 fall movements at a sampling frequency of 60Hz. A 5Hz low-pass filter was applied to the IMU data to remove high-frequency noise. Sum vector magnitude of acceleration and angular velocity, roll, pitch, and vertical velocity were extracted as feature vector. The proposed algorithm showed an accuracy 98.3%, a sensitivity 100%, a specificity 97.0%, and an average lead-time 311±99ms with our experimental data. When evaluated using the KFall public dataset, an accuracy in adult data improved to 99.5% compared to recent studies, and for the elderly data, a specificity of 100% was achieved. When evaluated using FARSEEING real-world elderly fall data without separate segmentation, it showed a sensitivity of 71.4% (5/7).

• 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.

• Journal of the Korea Society of Computer and Information
• /
• v.18 no.6
• /
• pp.21-28
• /
• 2013

This paper proposes an effective fire detection approach that includes the following multiple heterogeneous algorithms: moving region detection using grey level histograms, color segmentation using fuzzy c-means clustering (FCM), feature extraction using a grey level co-occurrence matrix (GLCM), and fire classification using support vector machine (SVM). The proposed approach determines the optimal threshold values based on grey level histograms in order to detect moving regions, and then performs color segmentation in the CIE LAB color space by applying the FCM. These steps help to specify candidate regions of fire. We then extract features of fire using the GLCM and these features are used as inputs of SVM to classify fire or non-fire. We evaluate the proposed approach by comparing it with two state-of-the-art fire detection algorithms in terms of the fire detection rate (or percentages of true positive, PTP) and the false fire detection rate (or percentages of true negative, PTN). Experimental results indicated that the proposed approach outperformed conventional fire detection algorithms by yielding 97.94% for PTP and 4.63% for PTN, respectively.

• Journal of Advanced Navigation Technology
• /
• v.27 no.2
• /
• pp.190-196
• /
• 2023

Recently, following the development of LIDAR technology which can detect distance from the object, the interest for LIDAR based 3D object detection network is getting higher. Previous networks generate inaccurate localization results due to spatial information loss during voxelization and downsampling. In this study, we propose an attention-based convergence method and a camera-LIDAR convergence system to acquire high-level features and high positional accuracy. First, by introducing the attention method into the Voxel-RCNN structure, which is a grid-based 3D object detection network, the multi-scale sparse 3D convolution feature is effectively fused to improve the performance of 3D object detection. Additionally, we propose the late-fusion mechanism for fusing outcomes in 3D object detection network and 2D object detection network to delete false positive. Comparative experiments with existing algorithms are performed using the KITTI data set, which is widely used in the field of autonomous driving. The proposed method showed performance improvement in both 2D object detection on BEV and 3D object detection. In particular, the precision was improved by about 0.54% for the car moderate class compared to Voxel-RCNN.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.10 no.9
• /
• pp.979-986
• /
• 2015

Security solutions using fiber-optic cable have not yet secured a solid technical stability, through which the Acoustic detection security system also did not have a complete defense techniques such as false alarm and detecting fail due to a number of variables. In this paper, we investigate 4 characteristics for the channel of underwater acoustic communication. We also construct detection system as a construction method for security system using optical cable through the analysis of acoustic signal in underwater. We perform analysis of signal characteristics and noise of underwater optical cable, and then we confirms the possibility of real application.