• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.30B no.6
• /
• pp.67-75
• /
• 1993

ECG pattern was classified using a back-propagation neural network. An improved feature extractor of ECG is proposed for better classification capability. It is consisted of preprocessing ECG signal by an FIR filter faster than conventional one by a factor of 5. QRS complex recognition by moving-window integration, and peak extraction by quadratic approximation. Since the FIR filter had a periodic frequency spectrum, only one-fifth of usual processing time was required. Also, segmentation of ECG signal followed by quadratic approximation of each segment enabled accurate detection of both P and T waves. When improtant features were extracted and fed into back-propagation neural network for pattern classification, the required number of nodes in hidden and input layers was reduced compared to using raw data as an input, also reducing the necessary time for study. Accurate pattern classification was possible by an appropriate feature selection.

• Journal of Information Processing Systems
• /
• v.16 no.4
• /
• pp.820-831
• /
• 2020

Extractive document summarization aims to select a few sentences while preserving its main information on a given document, but the current extractive methods do not consider the sentence-information repeat problem especially for news document summarization. In view of the importance and redundancy of news text information, in this paper, we propose a neural extractive summarization approach with joint sentence semantic clipping and selection, which can effectively solve the problem of news text summary sentence repetition. Specifically, a hierarchical selective encoding network is constructed for both sentence-level and document-level document representations, and data containing important information is extracted on news text; a sentence extractor strategy is then adopted for joint scoring and redundant information clipping. This way, our model strikes a balance between important information extraction and redundant information filtering. Experimental results on both CNN/Daily Mail dataset and Court Public Opinion News dataset we built are presented to show the effectiveness of our proposed approach in terms of ROUGE metrics, especially for redundant information filtering.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.11
• /
• pp.3493-3506
• /
• 2022

In the field of scene segmentation, the precise segmentation of object boundaries in sports movement scene images is a great challenge. The geometric information and spatial information of the image are very important, but in many models, they are usually easy to be lost, which has a big influence on the performance of the model. To alleviate this problem, a parallel dense dilated convolution merging Network (termed PDDCM-Net) was proposed. The proposed PDDCMNet consists of a feature extractor, parallel dilated convolutions, and dense dilated convolutions merged with different dilation rates. We utilize different combinations of dilated convolutions that expand the receptive field of the model with fewer parameters than other advanced methods. Importantly, PDDCM-Net fuses both low-level and high-level information, in effect alleviating the problem of accurately segmenting the edge of the object and positioning the object position accurately. Experimental results validate that the proposed PDDCM-Net achieves a great improvement compared to several representative models on the COCO-Stuff data set.

• The Bulletin of The Korean Astronomical Society
• /
• v.42 no.2
• /
• pp.70.2-70.2
• /
• 2017

Transit event of exoplanet is a good example of observational studies with youth, because the event is geometrically simple and its analysis is essential to astronomical observation. Therefore, we developed the package of data reduction and aperture photometry in Python for educational purpose. In 27 July, we observed the transit event of TrES-3b with the students of "NYSC Space Science Club" program, and presented the Python package, PyPhotW for data reduction and aperture photometry. PyPhotW consists of simple functions for youth to understand the processes easier. Nonetheless, the photometric results of PyPhotW show a good agreement with those of Source Extractor, ${\Delta}m{\sim}-0.01{\pm}0.03$ and $-0.04{\pm}0.08$ for TrES-3b and TrES-5b time-series observations in 27 - 28 July.

• The Journal of Korea Robotics Society
• /
• v.12 no.4
• /
• pp.385-394
• /
• 2017

Side scanning sonar (SSS) provides valuable information for robot navigation. However using the side scanning sonar images in the navigation was not fully studied. In this paper, we use range data, and side scanning sonar images from UnderWater Simulator (UWSim) and propose measurement models in a feature based simultaneous localization and mapping (SLAM) framework. The range data is obtained by echosounder and sidescanning sonar images from side scan sonar module for UWSim. For the feature, we used the A-KAZE feature for the SSS image matching and adjusting the relative robot pose by SSS bundle adjustment (BA) with Ceres solver. We use BA for the loop closure constraint of pose-graph SLAM. We used the Incremental Smoothing and Mapping (iSAM) to optimize the graph. The optimized trajectory was compared against the dead reckoning (DR).

• Journal of Internet Computing and Services
• /
• v.5 no.6
• /
• pp.1-10
• /
• 2004

A web robot is a software that has abilities of tracking and collecting web documents on the Internet(l), The performance scalability of recent web robots reached the limit CIS the number of web documents on the internet has increased sharply as the rapid growth of the Internet continues, Accordingly, it is strongly demanded to study on the performance scalability in searching and collecting documents on the web. 'Design of web robot based on Multi-Agent to speed up documents collection ' rather than 'Sequentially executing Web Robot based on the existing Fork-Join method' and the results of analysis on its performance scalability is presented in the thesis, For collection speedup, a Multi-Agent based web robot performs the independent process for inactive URL ('Dead-links' URL), which is caused by overloaded web documents, temporary network or web-server disturbance, after dividing them into each agent. The agents consist of four component; Loader, Extractor, Active URL Scanner and inactive URL Scanner. The thesis models a Multi-Agent based web robot based on 'Amdahl's Law' to speed up documents collection, introduces a numerical formula for collection speedup, and verifies its performance improvement by comparing data from the formula with data from experiments based on the formula. Moreover, 'Dynamic URL Partition algorithm' is introduced and realized to minimize the workload of the web server by maximizing a interval of the web server which can be a collection target.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.19 no.2
• /
• pp.73-81
• /
• 2024

Recently, mobile manipulators have been utilized in agriculture industry for weed removal and harvest automation. This paper proposes a domain adaptive fruit detection method for harvest automation, by utilizing OWL-ViT model which is an open-vocabulary object detection model. The vision-language model can detect objects based on text prompt, and therefore, it can be extended to detect objects of undefined categories. In the development of deep learning models for real-world problems, constructing a large-scale labeled dataset is a time-consuming task and heavily relies on human effort. To reduce the labor-intensive workload, we utilized a large-scale public dataset as a source domain data and employed a domain adaptation method. Adversarial learning was conducted between a domain discriminator and feature extractor to reduce the gap between the distribution of feature vectors from the source domain and our target domain data. We collected a target domain dataset in a real-like environment and conducted experiments to demonstrate the effectiveness of the proposed method. In experiments, the domain adaptation method improved the AP50 metric from 38.88% to 78.59% for detecting objects within the range of 2m, and we achieved 81.7% of manipulation success rate.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.6
• /
• pp.1516-1529
• /
• 2023

In this paper, a motor gearbox fault-detection system based on a hierarchical flow-based model is proposed. The proposed system is used for the anomaly detection of a motion sound-based actuator module. The proposed flow-based model, which is a generative model, learns by directly modeling a data distribution function. As the objective function is the maximum likelihood value of the input data, the training is stable and simple to use for anomaly detection. The operation sound of a car's side-view mirror motor is converted into a Mel-spectrogram image, consisting of a folding signal and an unfolding signal, and used as training data in this experiment. The proposed system is composed of an encoder and a decoder. The data extracted from the layer of the pretrained feature extractor are used as the decoder input data in the encoder. This information is used in the decoder by performing an interlayer cross-scale convolution operation. The experimental results indicate that the context information of various dimensions extracted from the interlayer hierarchical data improves the defect detection accuracy. This paper is notable because it uses acoustic data and a normalizing flow model to detect outliers based on the features of experimental data.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.10
• /
• pp.5062-5079
• /
• 2017

Malicious insider threats have increased recently, and methods of the threats are diversifying every day. These insider threats are becoming a significant problem in corporations and governments today. From a technology standpoint, detecting potential insider threats is difficult in early stage because it is unpredictable. In order to prevent insider threats in early stage, it is necessary to collect all of insiders' data which flow in network systems, and then analyze whether the data are potential threat or not. However, analyzing all of data makes us spend too much time and cost. In addition, we need a large repository in order to collect and manage these data. To resolve this problem, we develop an indicator-based behavior ontology (IB2O) that allows us to understand and interpret insiders' data packets, and then to detect potential threats in early stage in network systems including social networks and company networks. To show feasibility of the behavior ontology, we developed a prototype platform called Insider Threat Detecting Extractor (ITDE) for detecting potential insider threats in early stage based on the behavior ontology. Finally, we showed how the behavior ontology would help detect potential inside threats in network system. We expect that the behavior ontology will be able to contribute to detecting malicious insider threats in early stage.

• Journal of KIISE:Software and Applications
• /
• v.31 no.3
• /
• pp.361-368
• /
• 2004

The purpose of this study is to propose a new on-line nonlinear PCA(OL-NPCA) method for a nonlinear feature extraction from the incremental data. Kernel PCA(KPCA) is widely used for nonlinear feature extraction, however, it has been pointed out that KPCA has the following problems. First, applying KPCA to N patterns requires storing and finding the eigenvectors of a N${\times}$N kernel matrix, which is infeasible for a large number of data N. Second problem is that in order to update the eigenvectors with an another data, the whole eigenspace should be recomputed. OL-NPCA overcomes these problems by incremental eigenspace update method with a feature mapping function. According to the experimental results, which comes from applying OL-NPCA to a toy and a large data problem, OL-NPCA shows following advantages. First, OL-NPCA is more efficient in memory requirement than KPCA. Second advantage is that OL-NPCA is comparable in performance to KPCA. Furthermore, performance of OL-NPCA can be easily improved by re-learning the data.