• The Transactions of the Korea Information Processing Society
• /
• v.3 no.1
• /
• pp.200-210
• /
• 1996

Re-engineering has the potential to improve software productivity and quality y across the entire life cycle. It involves improving the software maintenance process and improving existing systems by applying new technologies and tools to software maintenance. Re-engineering can help us understanding existing systems and discover software components(e.g., design structure, data structure that are common across systems. These common components then can be reused in the development (or redevelopment )of systems, thereby significantly shortening the time and lessening the risk of developing systems. The Object-Oriented paradigm has been known to improve software maintainability. There still exist many problems in recognizing object, attributes and operations that are conceptually integrated and constructing of object class. In this paper, we propose a method that defines a fundamental theories of re-engineering and a concept recognition for object- oriented paradigm. We also describe the re-engineering tool that translates the existing procedure-oriented program into object-oriented system. This tool has a strength to solve the conceptual integrity problem in object-oriented recognition.

• The KIPS Transactions:PartD
• /
• v.9D no.2
• /
• pp.227-234
• /
• 2002

When processing a query in a conventional database systems, a set of facts or tuples are usually returned as an answer. This also applies to object -oriented database where a set of objects is returned. Deductive database systems, however, provide the opportunity to obtain the answer of a query as a set of formulas, thereby reduce the costs to process the query, and represent its "intensional answers" in a more compact way independently of the database state. In this paper, by introducing rules info the object-oriented database systems and integrating the intensional query processing of deductive database systems into talc object-oriented database systems, we make it possible not only to answer incomplete queries which are not able to be answered in conventional object-oriented database systems, but also to express the answer-set abstractly as the names of classes, which provides us better understanding of the answer.

• Journal of Broadcast Engineering
• /
• v.28 no.3
• /
• pp.329-332
• /
• 2023

3D Object Detection using deep neural network has been developed a lot for obstacle detection in autonomous vehicles because it can recognize not only the class of target object but also the distance from the object. But in the case of 3D Object Detection models, the detection performance for distant objects is lower than that for nearby objects, which is a critical issue for autonomous vehicles. In this paper, we introduce a technique that increases the performance of 3D object detection models, particularly in recognizing distant objects, by generating virtual 3D vehicle data and adding it to the dataset used for model training. We used a spherical point tracing method that leverages the characteristics of 3D LiDAR sensor data to create virtual vehicles that closely resemble real ones, and we demonstrated the validity of the virtual data by using it to improve recognition performance for objects at all distances in model training.

• 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.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_4
• /
• pp.1925-1934
• /
• 2022

Monitoring nuclear activity for inaccessible areas using remote sensing technology is essential for nuclear non-proliferation. In recent years, deep learning has been actively used to detect nuclear-activity-related small objects. However, high-resolution satellite imagery containing small objects can result in class imbalance. As a result, there is a performance degradation problem in detecting small objects. Therefore, this study aims to improve detection accuracy by analyzing the effect of the ratio of small objects related to nuclear activity in the input data for the performance of the deep learning model. To this end, six case datasets with different ratios of small object pixels were generated and a U-Net model was trained for each case. Following that, each trained model was evaluated quantitatively and qualitatively using a test dataset containing various types of small object classes. The results of this study confirm that when the ratio of object pixels in the input image is adjusted, small objects related to nuclear activity can be detected efficiently. This study suggests that the performance of deep learning can be improved by adjusting the object pixel ratio of input data in the training dataset.

• Journal of the Korean housing association
• /
• v.26 no.4
• /
• pp.83-94
• /
• 2015

Ernst May and the New Frankfurt Initiative are well known for the urban planning and the Housings in Frankfurt a. M. Their works tend to be underestimated because of some factors such as modest attitude toward modernism design vocabulary, short period that their programs lasts, and modification/recession of project in actual construction. So, This study aims to build up the relations related to Housing, such as situation of post World War I in German Society and Frankfurt, May's cognition on the working class, and realization of rationalization as a major tools of the modernity. Ernst May considered the working class with bipolar standpoint. Ernst May and His team considered working class and those families not only as object of relief but also as potential 'modern citizens' to be disciplined; he sympathize poor conditions of working class while discriminating them by their labor charge. Acceptance of Socially Disadvantaged group in construction were also proceeded in means of recession of cost. Even Ernst May and his team did not achieved the goals that they thought they could, their Siedlung and house designs articulated the sense of modernity, which presented in rationalization with highly practical manner. Those are realized in 3 directions; respectful considerations for existing traditional factors, application of extendable logics of physical/social hygiene, and reflection of issues with standardization and mass production.

• Journal of The Korean Association of Information Education
• /
• v.16 no.4
• /
• pp.451-462
• /
• 2012

In this study, our primary areas of mathematical shapes as a way to solve the problem of sixth grade math and geometry around the area in addition to the real world, the virtual objects to explore on their own learning, heuristic principles and learning concepts are developed. To this end, second-class sixth grade in Seoul class M is selected and the area of Augmented Reality class shapes students' academic achievement sure to affect how much agreed. experimental study was developed and then applied to the actual class content across pre and post implementation evaluation, and subsequent academic achievement levels were compared and analyzed. As a result, learners in the experimental group and control group than the class of interested students and class satisfaction, a statistically higher achievement. Learning on augmented reality, which shapes have the gumption to participate in classes, and concepts related to shape the formation and indicates that academic achievement is related.

• Journal of architectural history
• /
• v.16 no.1
• /
• pp.49-68
• /
• 2007

The purpose of this study is analysis of traditional noble houses style of Ha-Dong area in Kyeong-Nam. The sequence of this study is at first finding the list of survey object, and investigating of those houses, after than drawing the site and floor plan, and lately analysis the characters of inner and outer space of them. It required six months. The results of analysis of them are as follows. 1. The noble traditional houses in Ha-Dong are found eight samples which are not noticed in academic society. 2. The constructions of noble housing in late Period of Cho-sun Dynasty are divided in three parts as a general role. Its grade is similar in Ha-Dong. The number of traditional noble house of (old) volunteer class is two cases. The (new) rich-farmer class is four cases. And there are two cases of (long) authority class. 3. The type of site plan is based on Korean south area style which is the style of departed rectangular type. But outdoor spaces are divided in several space by many fence than other area. It is the special item of construction. 4. The special character of indoor space is the use of 'Gong-ru'. It is called similar space used in top of main entrance building of large building. But it is located in various space in Ha-dong. It is included in any space of Sarang-Che, An-Che, Are-Che. The traditional noble houses of Ha-Dong area have special spacial characters. For long time there space was developed based on local identity. And its characters was divided various classes. Thus Ha-Dong area is definite place of useful identified traditional culture.

• 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.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.24 no.66
• /
• pp.1-10
• /
• 2001

Simulation-Based Expert System(SIMBES) is a very effective tool to solve complex antral hard problems. The SIMBES model includes a simulator, a feature extractor, a machine learning system, a performance evaluator, and a Knowledge-Based Expert System(KBES). Since SIMBES depends on Problem domains, a schedule-based material requirements planning problem, which is NP-hard, was selected to exemplify the SIMBES model. To implement the SIMBES application in Smalltalk paradigm, a system class hierarchy was constructed. The hierarchy consists of five large classes such as Job Generator, Job Scheduler, Job Evaluator, Inference Engine, and Executive System. Several classes inside these classes were identified. Additionally, instance protocols about all classes have been described in terms of messages and pseudo methods. These protocols can be implemented easily by any other object-oriented languages. Furthermore, these results may be used as a skeletal system to develop a new SIMBES efficiently, especially when the application is related to other scheduling problems.