• 제어로봇시스템학회:학술대회논문집
• /
• 2002.10a
• /
• pp.36.5-36
• /
• 2002

$\textbullet$ Introduction $\textbullet$ Localization technique $\textbullet$ Experiments and evolutions $\textbullet$ Conclusions

• Journal of Computing Science and Engineering
• /
• v.9 no.3
• /
• pp.142-154
• /
• 2015

Fault localization techniques help locate faults in source codes by exploiting collected test information and have shown promising results. To precisely locate faults, the techniques require a large number of test cases that sufficiently exercise the executable statements together with the label information of each test case as a failure or a success. However, during the process of software development, developers may not have high-coverage test cases to effectively locate faults. With the test case generation techniques, a large number of test cases without expected outputs can be automatically generated. Whereas the execution results for generated test cases need to be inspected by developers, which brings much manual effort and potentially hampers fault-localization effectiveness. To address this problem, this paper presents a method to select a few test cases from a number of test cases without expected outputs for result inspection, and in the meantime selected test cases can still support effective fault localization. The experimental results show that our approach can significantly reduce the number of test cases that need to be inspected by developers and the effectiveness of fault localization techniques is close to that of whole test cases.

• Korean Journal of Agricultural Science
• /
• v.50 no.3
• /
• pp.399-406
• /
• 2023

In this study, we propose a ripe tomato bunch localization method based on convolutional neural networks, to be applied in robotic harvesting systems. Tomato images were obtained from a smart greenhouse at the Rural Development Administration (RDA). The sample images for training were extracted based on tomato maturity and resized to 128 × 128 pixels for use in the classification model. The model was constructed based on four-layer convolutional neural networks, and the classes were determined based on stage of maturity, using a Softmax classifier. The localization of the ripe tomato bunch region was indicated on a class activation map. The class activation map could show the approximate location of the tomato bunch but tends to present a local part or a large part of the ripe tomato bunch region, which could lead to poor performance. Therefore, we suggest a recursive method to improve the performance of the model. The classification results indicated that the accuracy, precision, recall, and F1-score were 0.98, 0.87, 0.98, and 0.92, respectively. The localization performance was 0.52, estimated by the Intersection over Union (IoU), and through input recursion, the IoU was improved by 13%. Based on the results, the proposed localization of the ripe tomato bunch area can be incorporated in robotic harvesting systems to establish the optimal harvesting paths.

• Journal of Agricultural Extension & Community Development
• /
• v.2 no.2
• /
• pp.109-116
• /
• 1995

The objectives of this study were to identify the roles of field agricultural extension work and its future development directions in the localization process. Literature reviews and participatory research methods were applied to attain the study objectives. Among the identified developmental roles of the field extension work in the localization process were : (1) to build up the agricultural research capability within the locality ; (2) to intensify the field information technology and ; (3) to strengthen the technology management capability of the extension educators.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.32 no.6
• /
• pp.703-710
• /
• 2012

A structural health monitoring technique for locating impact position in a composite plate is presented in this paper. The method employs a single sensor and spatial focusing properties of time reversal(TR) and inverse filtering(IF). We first examine the spatial focusing efficiency of both approaches at the impact position and its surroundings through impact experiments. The imaging results of impact localization show that the impact location can be accurately estimated in any position of the plate. Compared to existing techniques for locating impact or acoustic emission source, the proposed method has the benefits of using a single sensor and not requiring knowledge of anisotropic material properties and geometry of structures. Furthermore, it does not depend on a particular mode of dispersive Lamb waves that is frequently used in other ultrasonic testing of plate-like structures.

• Journal of Positioning, Navigation, and Timing
• /
• v.9 no.3
• /
• pp.221-227
• /
• 2020

In this paper, the Iterated Consider Extended Kalman Filter (ICEKF) is proposed for bearing-only localization of GNSS interference to improve the estimation performance and filter consistency. The ICEKF is an extended version of Consider KF (CKF) for Iterated EKF (IEKF) to consider an effect of bearing measurement bias error to filter covariance. The ICEKF can mitigate the EKF divergence problem which can occur when linearizing the nonlinear bearing measurement by a large initial state error. Also, it can mitigate filter inconsistency problem of EKF and IEKF which can occur when a weakly observable bearing measurement bias error state is not included in filter state vector. The simulation result shows that the localization error of the ICEKF is smaller than the EKF and IEKF, and the Root Mean Square (RMS) estimation error of ICEKF matches the covariance of filter.

• The Journal of Korea Robotics Society
• /
• v.2 no.1
• /
• pp.40-47
• /
• 2007

Recently, with the development of service robots and with the new concept of ubiquitous world, the position estimation of mobile objects has been raised to an important problem. As pre-liminary research results, some of the localization schemes are introduced, which provide the absolute location of the moving objects subjected to large errors. To implement a precise and convenient localization system, a new absolute position estimation method for a mobile robot in indoor environment is proposed in this paper. Design and implementation of the localization system comes from the usage of active beacon systems (based upon RFID technology). The active beacon system is composed of an RFID receiver and an ultra-sonic transmitter: 1. The RFID receiver gets the synchronization signal from the mobile robot and 2. The ultra-sonic transmitter sends out the traveling signal to be used for measuring the distance. Position of a mobile robot in a three dimensional space can be calculated basically from the distance information from three beacons and the absolute position information of the beacons themselves. Since it is not easy to install the beacons at a specific position precisely, there exists a large localization error and the installation time takes long. To overcome these problems, and provide a precise and convenient localization system, a new auto calibration algorithm is developed in this paper. Also the extended Kalman filter has been adopted for improving the localization accuracy during the mobile robot navigation. The localization accuracy improvement through the proposed auto calibration algorithm and the extended Kalman filter has been demonstrated by the real experiments.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.20 no.4
• /
• pp.536-542
• /
• 2017

In this paper, authors described on localization development's results about an electric igniter in thermal battery with a pyrotechnic heat sources. Especially, the development test and evaluation(DT&E) process and the methods in the developments of the electric igniter which is parts of a domestic thermal battery on K-PSAM was in charge of government and developed for defense of a local areas in Korea. We have proposed a process of design and manufacture on the electric igniter. Finally, we verified a quality and a reliability of the electric igniter from test results by Fisher-Snedecor's law and over 99.5 %(C.L. 95 %) for K-PSAM.

• Journal of Agricultural Extension & Community Development
• /
• v.2 no.2
• /
• pp.129-133
• /
• 1995

• Journal of the Korea Institute of Military Science and Technology
• /
• v.19 no.4
• /
• pp.508-516
• /
• 2016

When GPS signals are not available, a relative localization can be alternatively used to represent the topological relationship between mobile nodes. A relative location map of a network can be constructed by using the distance information between all the pairs of nodes in the network. If a network is large, a number of small local maps are individually constructed and are merged to obtain the whole map. However, this approach may result in a high computation and communication overhead. In this paper, we propose a reference-node selection scheme for relative localization map construction, which chooses a subset of nodes as a reference node that is supposed to construct local maps. The scheme is a greedy algorithm that iteratively chooses nodes with high degree as a reference node until the chosen local maps are successfully merged with a sufficient number of common nodes between nearby local maps. The simulation results indicate that the proposed scheme achieves higher localization accuracy with a reduced computational overhead.