Vol. 47, No. 9,
Sep. 2020
Digital Library
Superpixel-Based HDR Image Region of Interest Extraction Method
Simon Suh, Seung-Ryeol Ohk, Young-Jin Kim
http://doi.org/10.5626/JOK.2020.47.9.793
Because of the difference in the number of bits per channel between high dynamic range (HDR) and low dynamic range (LDR) images, a tone mapping process is required to represent an HDR image on an LDR display. In this case, by using the difference between the image ROI and the non-ROI, the efficiency of the tone-mapping may be increased. The itti model is a representative method of extracting a region of interest by focusing colors, shapes, and movements of an image. Unlike the itti model, this paper extracts the region of interest using superpixels based on the characteristics of the object. The k-means clustering is performed using the features of the superpixel-based image regions of interest as a seed point, and finally the object-oriented region of interest is extracted from the HDR image. In the proposed technique, the precision and NSS are 10.7% and 28.14% lower than those from the itti model on average, but the recall, SIM, and CC increased by 44.44%, 19.53%, and 7.43%, respectively.
Efficient Test Method for Embedded Software Using Next Software Framework Test Service
Dongeon Lee, Hyunggon Song, Junghun Jin, Kyutae Cho
http://doi.org/10.5626/JOK.2020.47.9.804
In recent years, it has become difficult to maintain the software quality and reliability of embedded software as its size and complexity have increased significantly unlike in the past. To improve such software quality and reliability, the most important factor is efficient testing of the software. Because of the nature of embedded software, it is difficult to apply existing test automation tools mainly used for Windows or Linux in general-purpose systems because of the high coupling with hardware and various platforms. In general, when developing software and hardware together, the number of hardware that can be operated is also minimal compared to the number of software developers. In this paper, we propose a method for the efficient testing of embedded software using NSFW(Next Software Framework) test service. Additionally, this paper suggests a method to test concurrency errors more efficiently.
Location Information Sharing Objects (LISO): Context-aware Intelligence Service Using Social Media Data Based on User Interest
http://doi.org/10.5626/JOK.2020.47.9.814
By analyzing social media (SNS) data with learning algorithms that can be obtained from social networks, it is possible to extract the information of personal or social concerns. The learning algorithms have a problem, however, in that the higher accuracy from analysis requires larger volumes of information but thus increases the analysis duration. To resolve this issue effectively, we propose a system, termed Location Information Sharing Objects (LISO). The LISO has two types of objects. The LISO learns from big data by classifying the role of the objects for analyzing social concerns based on their type. The fixed-position objects manage collecting and analyzing a wide range of location-specific social media data for obtaining social concerns. The mobile objects manage analyzing the information regarding frequently varying situations as well as users’ personal concerns. This role-sharing method for analyzing big social media data based on the type of the objects in the LISO can distribute the load of analyzing.
Variability-Considered Hazards Analysis Technique in Collaboration Environments of Multiple Cyber-Physical Systems
http://doi.org/10.5626/JOK.2020.47.9.820
When multiple cyber-physics systems collaboratively work together to achieve a common mission, unexpected and diverse situations can arise. These variable situations in their functioning are not caused by defects or failures of system elements, but by environmental factors in the context of collaboration. With the recent publication of the SOTIF standard, new safety criteria have been proposed that consider these environmental and variable factors. This paper proposes a hazard analysis technique that considers the variability by extending the existing safety analysis techniques of the software systems. The proposed technique will provide safety for functional behaviors in multi-CPS collaboration.
Breast Cancer Subtype Classification Using Multi-omics Data Integration Based on Neural Network
Joungmin Choi, Jiyoung Lee, Jieun Kim, Jihyun Kim, Heejoon Chae
http://doi.org/10.5626/JOK.2020.47.9.835
Breast cancer is one of the highly heterogeneous diseases comprising multiple biological factors, causing multiple subtypes. Early diagnosis and accurate subtype prediction of breast cancer play a critical role in the prognosis of cancer and are crucial to providing appropriate treatment for each patient with different subtypes. To identify significant patterns from enormous volumes of genetic and epigenetic data, machine learning-based methods have been adopted to the breast cancer subtype classification. Recently, multi-omics data integration has attracted much attention as a promising approach in recognizing complex molecular mechanisms and providing a comprehensive view of patients. However, because of the characteristics of high dimensionality, multi-omics based approaches are limited in prediction accuracy. In this paper, we propose a neural network-based breast cancer subtype classification model using multi-omics data integration. The gene expression, DNA methylation, and miRNA omics dataset were integrated after preprocessing and the classification model was trained based on the neural network using the dataset. Our performance evaluation results showed that the proposed model outperforms all other methods, providing the highest classification accuracy of 90.45%. We expect this model to be useful in predicting the subtypes of breast cancer and improving patients’ prognosis.
CNN-based Reduced Complexity Decision Confidence Estimation for Imbalanced Web Application Attack Detection
Seungyoung Park, Hansung Kim, Taejoon Jung
http://doi.org/10.5626/JOK.2020.47.9.842
As web application attacks have been rapidly increasing and their types have been diversified, there are limitations on detecting them with the existing schemes. To resolve this problem, the detection techniques using machine learning such as the convolutional neural network (CNN) have been proposed. However, the confidence on the decision error sample in these techniques has been unreliable. To estimate more reliable decision confidence, the Monte-Carlo batch normalization (MCBN) technique combined with the CNN has been proposed. In particular, the CNN performs multiple decisions on a given evaluation sample using multiple mini-batches containing it. Then, its decision confidence estimate is obtained by averaging the multiple decision results. However, it requires too large of a computational load. The reason is that each mini-batch comprises randomly selected (M-1) training samples and only one evaluation sample, when the mini-batch size is M. In this paper, we propose a reduced complexity decision confidence estimation scheme for imbalanced web application attack detection. Specifically, the proposed scheme reduces the computational load by up to M times compared to the MCBN scheme. Also, at the estimation process, the ratio of normal and attack samples in the mini-batch should be maintained the same as that of the training process. To achieve this, we found which class size was small by performing a temporal decision on the evaluation samples. Then, the small class was over-sampled using the training samples to maintain the ratio. Our experimental results showed that the performance improved, and the reliability estimation performance was not significantly degraded compared to the MCBN scheme.
Open Domain Question Answering using Knowledge Graph
http://doi.org/10.5626/JOK.2020.47.9.853
In this paper, we propose a novel knowledge graph inference model called KGNet for answering the open domain complex questions. This model addresses the problem of knowledge base incompleteness. In this model, two different types of knowledge resources, knowledge base and corpus, are integrated into a single knowledge graph. Moreover, to derive answers to complex multi-hop questions effectively, this model adopts a new knowledge embedding and reasoning module based on Graph Neural Network (GNN). We demonstrate the effectiveness and performance of the proposed model through various experiments over two large question answering benchmark datasets, WebQuestionsSP and MetaQA.
Improving Mutation-Based Fault Localization for Better Locating Omission Faults Using Coverage Change Information
http://doi.org/10.5626/JOK.2020.47.9.863
Although omission faults are bugs commonly found in real-world programs, existing mutation-based fault localization techniques show low accuracy at locating omission faults because useful mutants are not likely generated at locations where necessary statements are missed. This paper introduces two new techniques, MUSEUM+ and Metallaxis+, an extension of two mutationbased fault localization techniques, MUSEUM and Metallaxis, by adding elements that link the change of coverage information and the change of test results. The proposed MBFL techniques additionally utilize coverage change information to consider the characteristics of omission faults. The experiment with the 16 JFreeChart faults in Defects4J, including 10 omission faults and 6 non-omission faults demonstrate that the presented techniques, MUSEUM+ and Metallaxis+, show improved faults localization accuracy.
Korean Text Summarization using MASS with Relative Position Representation
Youngjun Jung, Hyunsun Hwang, Changki Lee
http://doi.org/10.5626/JOK.2020.47.9.873
In the language generation task, deep learning-based models that generate natural languages using a Sequence-to-Sequence model are actively being studied. In the field of text summarization, wherein the method of extracting only the core sentences from the text is used, an abstract summarization study is underway. Recently, a transfer learning method of fine-tuning using pre-training model based on large amount of monolingual data such as BERT and MASS has been mainly studied in the field of natural language processing. In this paper, after pre-training for the Korean language generation using MASS, it was applied to the summarization of the Korean text. As a result of the experiment, the Korean text summarization model using MASS was higher performance than the existing models. Additionally, the performance of the text summarization model was improved by applying the relative position representation method to MASS.
An Efficient and Differentially Private K-Means Clustering Algorithm Using the Voronoi Diagram
http://doi.org/10.5626/JOK.2020.47.9.879
Studies have been recently conducted on preventing the leakage of personal information from the analysis results of data. Among them, differential privacy is a widely studied standard since it guarantees rigorous and provable privacy preservation. In this paper, we propose an algorithm based on the Voronoi diagram to publish the results of the K-means clustering for 2D data while guaranteeing the differential privacy. Existing algorithms have a disadvantage in that it is difficult to select the number of samples for the data since the running time and the accuracy of the clustering results may change according to the number of samples. The proposed algorithm, however, could quickly provide an accurate clustering result without requiring such a parameter. We also demonstrate the performance of the proposed algorithm through experiments using real-life data.
Realtime Video Streaming System over Narrowband Networks
Hyunmin Noh, Seunghwan Lee, Jeung Won Choi, Donghyun Kim, Kyungwoo Kim, Yunsoo Ko, Sangheon Shin, Hyungjun Kim, Hwangjun Song
http://doi.org/10.5626/JOK.2020.47.9.885
In this paper, we propose a real-time video streaming system over narrow networks that provides high-quality video services. The suggested system uses the raptor code, a forward error correction code, to support the reliable and stable data transmission in the narrowband networks. Also, the proposed system adaptively controls the raptor parameters (source symbol size, the number of source symbols, and code rate) according to the narrow network condition and the remaining buffer status. The proposed system is fully implemented on android devices and examined by using a real-time video transmission. Experimental results showed that the proposed system provides high-quality streaming services over the narrowband networks.
Search
Journal of KIISE
- ISSN : 2383-630X(Print)
- ISSN : 2383-6296(Electronic)
- KCI Accredited Journal
Editorial Office
- Tel. +82-2-588-9240
- Fax. +82-2-521-1352
- E-mail. chwoo@kiise.or.kr