• Journal of Korean Tunnelling and Underground Space Association
• /
• v.26 no.2
• /
• pp.129-152
• /
• 2024

In the application of deep learning object detection via CCTV in tunnels, a large number of false positive detections occur due to the poor environmental conditions of tunnels, such as low illumination and severe perspective effect. This problem directly impacts the reliability of the tunnel CCTV-based accident detection system reliant on object detection performance. Hence, it is necessary to reduce the number of false positive detections while also enhancing the number of true positive detections. Based on a deep learning object detection model, this paper proposes a false positive data training method that not only reduces false positives but also improves true positive detection performance through retraining of false positive data. This paper's false positive data training method is based on the following steps: initial training of a training dataset - inference of a validation dataset - correction of false positive data and dataset composition - addition to the training dataset and retraining. In this paper, experiments were conducted to verify the performance of this method. First, the optimal hyperparameters of the deep learning object detection model to be applied in this experiment were determined through previous experiments. Then, in this experiment, training image format was determined, and experiments were conducted sequentially to check the long-term performance improvement through retraining of repeated false detection datasets. As a result, in the first experiment, it was found that the inclusion of the background in the inferred image was more advantageous for object detection performance than the removal of the background excluding the object. In the second experiment, it was found that retraining by accumulating false positives from each level of retraining was more advantageous than retraining independently for each level of retraining in terms of continuous improvement of object detection performance. After retraining the false positive data with the method determined in the two experiments, the car object class showed excellent inference performance with an AP value of 0.95 or higher after the first retraining, and by the fifth retraining, the inference performance was improved by about 1.06 times compared to the initial inference. And the person object class continued to improve its inference performance as retraining progressed, and by the 18th retraining, it showed that it could self-improve its inference performance by more than 2.3 times compared to the initial inference.

• Journal of KIISE:Software and Applications
• /
• v.29 no.8
• /
• pp.543-554
• /
• 2002

System developers create a lot of design documents by various case tools. It is necessary to have the tools for facilitating the analysis of the documents. These tools can be used to understand and verify the whole process of a system, by defining relationships among the documents and providing free navigation methods. In this paper, we develop a navigation tool that enables the developers to systematically analyze the system by capturing duplication, instance, and transition relationships between the documents. Different from the navigation facilities of the other UML design tools, this tool makes it possible to navigate design elements in design documents such as sequence diagrams, state diagrams and class diagrams. In other words, it can be used to systematically capture and verify both the static structure and the dynamic behavior of the system by keeping track of such elements. To provide such a facility, 1) we define three relationships: duplication, instance, and transition, 2) assign relation to the related design elements according to the predefined way. and then 3) present a set of functions for navigating related design elements.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.2
• /
• pp.244-251
• /
• 2007

Intention reading technique is essential to provide personalized services toward more convenient and human-friendly services in complex ubiquitous environment such as a smart home. If a system has knowledge about an user's intention of his/her behavioral pattern, the system can provide mote qualified and satisfactory services automatically in advance to the user's explicit command. In this sense, learning capability is considered as a key function for the intention reading technique in view of knowledge discovery. In this paper, ore introduce a personalized media control method for a possible application iii a smart home. Note that data pattern such as human behavior contains lots of inconsistent data due to limitation of feature extraction and insufficiently available features, where separable data groups are intermingled with inseparable data groups. To deal with such a data pattern, we introduce an effective engineering approach with the combination of fuzzy logic and probabilistic reasoning. The proposed learning system, which is based on IFCS (Iterative Fuzzy Clustering with Supervision) algorithm, extract probabilistic fuzzy rules effectively from the given numerical training data pattern. Furthermore, an extended architectural design methodology of the learning system incorporating with the IFCS algorithm are introduced. Finally, experimental results of the media contents recommendation system are given to show the effectiveness of the proposed system.

• Journal of KIISE:Computing Practices and Letters
• /
• v.9 no.2
• /
• pp.133-145
• /
• 2003

Web applications based on J2EE($Java^{TM}$ 2 Platform, Enterprise Edition) were occurred for solution to overcome the limitations in time and space that the former applications had. Recently, lots of solutions using frameworks are being suggested to develope applications more quickly and efficiently. In this paper, we propose the template for several processes and types, which should be taken in presentation layer of web applications. This idea was based on the fact that web applications developers can concentrate on their specific tasks with independent manner in layered architecture. This template is XML-typed document that shows information about presentation layer of Web applications, which the user wants to compose. This template is inputted to the code generator. After then, the code generator generates skeleton code in presentation layer automatically after parsing information of XML documents. It means that we can develope Web applications more efficiently, by constructing skeleton code which inherits from hot spot classes of framework. Using this template and code generator, developer can develop Web applications with little practice and also is easy to cooperate with other developers to develop them just in time with distributing the standard development process.

• The KIPS Transactions:PartC
• /
• v.11C no.4
• /
• pp.509-518
• /
• 2004

Many simulators have been developed and are being used for the complex and various mobile communication service environments. Each of these simulators has its own teletraffic model that consists of traffic source model and network traffic model. In this paper, network traffic model and traffic source model, which are based on the data gathered in real environment, are defined in order to get more accurate simulation results in the mobile communication simulation for the urban region. The network traffic model suggested in this paper reflects the hourly call generation rate and call duration time by analyzing the data collected from actually installed base station by the time and place, and the traffic source model includes the delivery share ratio and average speed information in the region where the base station is installed. This paper defined and designed Mobile Host object that reflects the suggested traffic source model, and Call Generator object that reflects the network traffic model, and other objects support both objects. Using the teletraffic model suggested in the paper, user mobility similar to real service environment and traffic characteristics can be reflected on the simulation, and also more accurate simulation results can be got through that. In addition, by using object-oriented techniques, new service feature or environment can be easily added or changed so that the developed mobile communication simulator can reflect the real service environment all the time.

• Journal of KIISE:Computing Practices and Letters
• /
• v.13 no.7
• /
• pp.442-453
• /
• 2007

A model-based integrated development tool for the development of USN application programs is proposed in this paper. The proposed tool has been implemented as a plug-in for Eclipse platform. The tool consists of Graphical User Interface, Modeler, Configuration Information Generator, Validity Checker, Source Code Generator and Templates Storage. Developers can implement USN applications from models of sensor networks using the tool. The developer can implement USN applications by automatic generation of execution code of each node in the sensor network after he/she designs a model of the sensor network. The configuration information of each node is automatically generated from the validated USN model. Then, the execution code is automatically generated using the configuration information and the predefined templates. Through the tool of this paper, developers can easily implement valid USN applications even if they do not know the details of low-level information. Also, a large number of application programs can be generated at once because application programs are generated from sensor network model instead of models of applications. Accordingly, the development effort of USN applications will be decreased and developers can consistently construct USN applications from USN models using the proposed tool.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.15 no.2
• /
• pp.113-125
• /
• 2012

This research is aimed at evaluating the land surface characterization of KOMPSAT-3A middle infrared (MIR) data. Airborne Hyperspectral Scanner (AHS) data, which has MIR bands with high spatial resolution, were used to assess land surface temperature (LST) retrieval and classification accuracy of MIR bands. Firstly, LST values for daytime and nighttime, which were calculated with AHS thermal infrared (TIR) bands, were compared to digital number of AHS MIR bands. The determination coefficient of AHS band 68 (center wavelength $4.64{\mu}m$) was over 0.74, and was higher than other MIR bands. Secondly, The land cover maps were generated by unsupervised classification methods using the AHS MIR bands. Each class of land cover maps for daytime, such as water, trees, green grass, roads, roofs, was distinguished well. But some classes of land cover maps for nighttime, such as trees versus green grass, roads versus roofs, were not separated. The image classification using the difference images between daytime AHS MIR bands and nighttime AHS MIR bands were conducted to enhance the discrimination ability of land surface for AHS MIR imagery. The classification accuracy of the land cover map for zone 1 and zone 2 was 67.5%, 64.3%, respectively. It was improved by 10% compared to land cover map of daytime AHS MIR bands and night AHS MIR bands. Consequently, new algorithm based on land surface characteristics is required for temperature retrieval of high resolution MIR imagery, and the difference images between daytime and nighttime was considered to enhance the ability of land surface characterization using high resolution MIR data.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.5
• /
• pp.251-260
• /
• 2016

Face recognition is a technology to extract feature from a facial image, learn the features through various algorithms, and recognize a person by comparing the learned data with feature of a new facial image. Especially, in order to improve the rate of face recognition, face recognition requires various processing methods. In the training stage of face recognition, feature should be extracted from a facial image. As for the existing method of extracting facial feature, linear discriminant analysis (LDA) is being mainly used. The LDA method is to express a facial image with dots on the high-dimensional space, and extract facial feature to distinguish a person by analyzing the class information and the distribution of dots. As the position of a dot is determined by pixel values of a facial image on the high-dimensional space, if unnecessary areas or frequently changing areas are included on a facial image, incorrect facial feature could be extracted by LDA. Especially, if a camera image is used for face recognition, the size of a face could vary with the distance between the face and the camera, deteriorating the rate of face recognition. Thus, in order to solve this problem, this paper detected a facial area by using a camera, removed unnecessary areas using the facial feature area calculated via a Gabor filter, and normalized the size of the facial area. Facial feature were extracted through LDA using the normalized facial image and were learned through the artificial neural network for face recognition. As a result, it was possible to improve the rate of face recognition by approx. 13% compared to the existing face recognition method including unnecessary areas.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.5
• /
• pp.3-9
• /
• 2015

The wireless communication system adopts an appropriate retransmission scheme on each system protocol layer to improve reliability of data transmission. In each system protocol layer, the retransmission scheme operates in independently other layers and operates based on the parameters without reference to end-to-end performance of wireless communication system. For this reason, it is difficult to design the optimal system parameters that satisfy the QoS requirements for each service class. Thus, the performance analysis of wireless communication system is needed to design the optimal system parameters according to the end-to-end QoS requirements for each service class. In this paper, we derive the mathematical model to formulate the end-to-end performance of wireless communication system. We also evaluate the performance at the MAC and transport layers in terms of average spectral efficiency and average transmission delay. Based on the results of performance evaluations, we design the optimal system parameters according to the QoS requirements of service classes. From the results, the HARQ combined with AMC is appropriate for the delay-sensitive service and the ARQ combined with AMC is appropriate for a service that is insensitive to transmission delay. Also, the TCP can be applied for the delay-insensitive service only.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.27 no.4
• /
• pp.821-830
• /
• 2017

The internet is an important infra resource that it controls the economy and society of our country. Also, it is providing convenience and efficiency of the everyday life. But, a case of various are occurred through an using vulnerability of an internet infra resource. Recently various attacks of unknown to the user are an increasing trend. Also, currently system of security control is focussing on patterns for detecting attacks. However, internet threats are consistently increasing by intelligent and advanced various attacks. In recent, the darknet is received attention to research for detecting unknown attacks. Since the darknet means a set of unused IP addresses, no real systems connected to the darknet. In this paper, we proposed an algorithm for finding black IPs through collected the darknet traffic based on a statistics data of port information. The proposed method prepared 8,192 darknet space and collected the darknet traffic during 3 months. It collected total 827,254,121 during 3 months of 2016. Applied results of the proposed algorithm, black IPs are June 19, July 21, and August 17. In this paper, results by analysis identify to detect frequency of black IPs and find new black IPs of caused potential cyber threats.