• The Transactions of the Korea Information Processing Society
• /
• v.7 no.9
• /
• pp.3037-3047
• /
• 2000

This paper describes a method of tracking a close leading vehicle by color image processing using the pairs of tail and brake lights. which emit red light and are housed on the rear of the vehicle in stop-and-go traffic condition. In the color image converted as an HSV color model. candidate regions of rear lights are identified using the color features of a pair of lights. Then. the pair of tailor brake lights are detected by means of the geometrical features and location features for the pattern of the tail and brake lights. The location of the leading vehicle can be estimated by the location of the detected lights and the vehicle can be tracked continuously. It is also possible to detect the braking status of the leading vehicle by measuring the change in HSV color components of the pair of lights detected. In the experiment. this method tracked a leading vehicle successfully from urban road images and was more useful at night than in the daylight. The KAV-Ill (Korea Autonomous Vehicle- Ill) equipped with a color vision system implementing this algorithm was able to follow a leading vehicle autonomously at speeds of up to 15km!h on a paved road at night. This method might be useful for developing an LSA (Low Speed Automation) system that can relieve driver's stress in the stop-and-go traffic conditions encountered on urban roads.

• Korean Journal of Remote Sensing
• /
• v.27 no.2
• /
• pp.75-87
• /
• 2011

This paper presents a method for region-based building extraction from high resolution satellite images(HRSI) using integrated information of spectral and color invariant features without user intervention such as selecting training data sets. The purpose of this study is also to evaluate the effectiveness of the proposed method by applying to IKONOS and QuickBird images. Firstly, the image is segmented by the MSRG method. The vegetation and shadow regions are automatically detected and masked to facilitate the building extraction. Secondly, the region merging is performed for the masked image, which the integrated information of the spectral and color invariant features is used. Finally, the building regions are extracted using the shape feature for the merged regions. The boundaries of the extracted buildings are simplified using the generalization techniques to improve the completeness of the building extraction. The experimental results showed more than 80% accuracy for two study areas and the visually satisfactory results obtained. In conclusion, the proposed method has shown great potential for the building extraction from HRSI.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.12
• /
• pp.507-516
• /
• 2019

Costs invested in road maintenance and road development are on the rise. However, due to accidents such as portholes and ground subsidence, the risks to the drivers' safety and the material damage caused by accidents are also increasing. Following this trend, we have developed a system that determines road damage, according to the magnitude of vibration generated without directly intervening the driver when driving. In this paper, we implemented the system using a remote control car (RC car) simulator due to the limitation of the environment in which the actual vehicle is not available in the process of developing the system. In addition, we attached a vibration sensor and GPS sensor to the body of the RC car simulator to measure the vibration value and location information generated by the movement of the vehicle in real-time while driving, and transmitting the corresponding data to the server. In this way, we implemented a system that allows external users to check the damage of roads and the maintenance of the repaired roads based on data more easily than the existing systems. By using this system, we can perform early prediction of road breakage and pattern prediction based on the data. Further, for the RC car simulator, commercialization will be possible by combining it with business in other fields that require flatness.

• Journal of KIISE:Software and Applications
• /
• v.33 no.9
• /
• pp.787-801
• /
• 2006

Ontology merging describes the process of integrating two ontologies into a new ontology. How this is done best is a subject of ongoing research in the Semantic Web, Data Integration, Knowledge Management System, and other ontology-related application systems. Earlier research on ontology merging, however, has studied for developing effective ontology matching approaches but missed analyzing and solving methods of problems of merging two ontologies given correspondences between them. In this paper, we propose a specific ontology merging process and a generic operator, T-MERGE, for integrating two source ontologies into a new ontology. Also, we define a taxonomy of merging conflicts which is derived from differing representations between input ontologies and a method for detecting and resolving them. Our T-MERGE operator encapsulates the process of detection and resolution of conflicts and merging two entities based on given correspondences between them. We define a data structure, MergeLog, for logging the execution of T-MERGE operator. MergeLog is used to inform detailed results of execution of merging to users or recover errors. For our experiments, we used oriental philosophy ontologies, western philosophy ontologies, Yahoo western philosophy dictionary, and Naver philosophy dictionary as input ontologies. Our experiments show that the automatic merging module compared with manual merging by a expert has advantages in terms of time and effort.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.1
• /
• pp.32-40
• /
• 2008

Fuzzy rules are very useful and efficient to describe classification rules especially when the attribute values are continuous and fuzzy in nature. However, it is generally difficult to determine membership functions for generating efficient fuzzy classification rules. In this paper, we propose a method of automatic generation of efficient fuzzy classification rules using evolutionary algorithm. In our method we generate a set of initial membership functions for evolutionary algorithm by supervised clustering the training data set and we evolve the set of initial membership functions in order to generate fuzzy classification rules taking into consideration both classification accuracy and rule comprehensibility. To reduce time to evaluate an individual we also propose an evolutionary algorithm with data partition evaluation in which the training data set is partitioned into a number of subsets and individuals are evaluated using a randomly selected subset of data at a time instead of the whole training data set. We experimented our algorithm with the UCI learning data sets, the experiment results showed that our method was more efficient at average compared with the existing algorithms. For the evolutionary algorithm with data partition evaluation, we experimented with our method over the intrusion detection data of KDD'99 Cup, and confirmed that evaluation time was reduced by about 70%. Compared with the KDD'99 Cup winner, the accuracy was increased by 1.54% while the cost was reduced by 20.8%.

• The KIPS Transactions:PartB
• /
• v.16B no.2
• /
• pp.181-194
• /
• 2009

With the increased interest on the document copyright, many of researches related to the document plagiarism have been done up to now. The plagiarism problem of newspaper articles has attracted much interest because the plagiarism cases of the articles having much commercial values in market are currently happened very often. Many researches related to the document plagiarism have been so hard to be applied to the newspaper articles because they have strong real-time characteristics. So to detect the plagiarism of the articles, many human detectors have to read every single thousands of articles published by hundreds of newspaper companies manually. In this paper, we firstly sorted out the articles with high possibility of being copied by utilizing OpenAPI modules supported by web search companies such as Naver and Daum. Then, we measured the document similarity between selected articles and the original article and made the system decide whether the article was plagiarized or not. In experiment, we used YonHap News articles as the original articles and we also made the system select the suspicious articles from all searched articles by Naver and Daum news search services.

• The KIPS Transactions:PartC
• /
• v.10C no.6
• /
• pp.799-808
• /
• 2003

Existing security solutions such as Firewell and IDS (Intrusion Detection System) have a trouble in getting accurate detection rate about new attack and can not block interior attack. That is, existing securuty solutions have various shortcomings. Shortcomings of these security solutions can be supplemented with mechanism which guarantees an availability of systems. The mechanism which guarantees the survivability of node is various, we approachintrusion telerance using real time response mechanism. The monitoring code monitors related resources of system for survivability of vulnerable systm continuously. When realted resources exceed threshold, monitoring and response code is deployed to run. These mechanism guarantees the availability of system. We propose control mathod about resource monitoring. The monitoring code operates with this method. The response code may be resident in active node for availability or execute a job when a request is occurred. We suggest the node survivability mechanism that integrates the intrusion tolerance mechanism that complements the problems of existing security solutions. The mechanism takes asvantage of the automated service distribution supported by Active Network infrastructure instead of passive solutions. The mechanism takes advantage of the automated service distribution supported by Active Network infrastructure instead of passive system reconfiguration and patch.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.23 no.6
• /
• pp.549-558
• /
• 2021

In order to keep infrastructures such as tunnels and underground facilities safe, cracks of concrete lining in tunnel should be detected by regular inspections. Since regular inspections are accomplished through manual efforts using maintenance lift vehicles, it brings about traffic jam, exposes works to dangerous circumstances, and deteriorates consistency of crack inspection data. This study aims to provide methodology to automatically extract cracks from tunnel concrete lining images generated by the existing tunnel image acquisition system. Specifically, we train a deep learning based semantic segmentation model with open dataset, and evaluate its performance with the dataset from the existing tunnel image acquisition system. In particular, we compare the model performance in case of using all of a public dataset, subset of the public dataset which are related to tunnel surfaces, and the tunnel-related subset with negative examples. As a result, the model trained using the tunnel-related subset with negative examples reached the best performance. In the future, we expect that this research can be used for planning efficient model training strategy for crack detection.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.2
• /
• pp.99-110
• /
• 2023

This study proposed a classification of malicious network traffic using the cyber threat framework(Mitre ATT&CK) and machine learning to solve the real-time traffic detection problems faced by current security monitoring systems. We applied a network traffic dataset called UNSW-NB15 to the Mitre ATT&CK framework to transform the label and generate the final dataset through rare class processing. After learning several boosting-based ensemble models using the generated final dataset, we demonstrated how these ensemble models classify network traffic using various performance metrics. Based on the F-1 score, we showed that XGBoost with no rare class processing is the best in the multi-class traffic environment. We recognized that machine learning ensemble models through Mitre ATT&CK label conversion and oversampling processing have differences over existing studies, but have limitations due to (1) the inability to match perfectly when converting between existing datasets and Mitre ATT&CK labels and (2) the presence of excessive sparse classes. Nevertheless, Catboost with B-SMOTE achieved the classification accuracy of 0.9526, which is expected to be able to automatically detect normal/abnormal network traffic.

• Korean Journal of Remote Sensing
• /
• v.39 no.2
• /
• pp.183-192
• /
• 2023

The remotely sensed data, such as satellite imagery and aerial photos, can be used to extract and detect some objects in the image through image interpretation and processing techniques. Significantly, the possibility for utilizing digital map updating and land monitoring has been increased through automatic object detection since spatial resolution of remotely sensed data has improved and technologies about deep learning have been developed. In this paper, we tried to extract plastic greenhouses into aerial orthophotos by using fully convolutional densely connected convolutional network (FC-DenseNet), one of the representative deep learning models for semantic segmentation. Then, a quantitative analysis of extraction results had performed. Using the farm map of the Ministry of Agriculture, Food and Rural Affairsin Korea, training data was generated by labeling plastic greenhouses into Damyang and Miryang areas. And then, FC-DenseNet was trained through a training dataset. To apply the deep learning model in the remotely sensed imagery, instance norm, which can maintain the spectral characteristics of bands, was used as normalization. In addition, optimal weights for each band were determined by adding attention modules in the deep learning model. In the experiments, it was found that a deep learning model can extract plastic greenhouses. These results can be applied to digital map updating of Farm-map and landcover maps.