Vol. 46, No. 7,
Jul. 2019
Digital Library
V-gram: Malware Detection Using Opcode Basic Blocks and Deep Learning
Seongmin Jeong, Hyeonseok Kim, Youngjae Kim, Myungkeun Yoon
http://doi.org/10.5626/JOK.2019.46.7.599
With the rapid increase in number of malwares, automatic detection based on machine learning becomes more important. Since the opcode sequence extracted from a malicious executable file is useful feature for malware detection, it is widely used as input data for machine learning through byte-based n-gram processing techniques. This study proposed a V-gram, a new data preprocessing technique for deep learning, which improves existing n-gram methods in terms of processing speed and storage space. V-gram can prevent unnecessary generation of meaningless input data from opcode sequences. It was verified that the V-gram is superior to the conventional n-gram method in terms of processing speed, storage space, and detection accuracy, through experiments conducted by collecting more than 64,000 normal and malicious code files.
Expansion of Real-time Locomotion Controller using an Inverted-Pendulum-based Abstract Model
http://doi.org/10.5626/JOK.2019.46.7.606
A hybrid method that integrates both motion capture based method and physics-based method allows natural walking motion. The hybrid method has the advantage of generating diverse walking motions from limited data. However, limited by recorded data, one of the disadvantage associated with hybrid method is that, only the walking style similar to capture motion could be performed. This disadvantage prevents the character from following a specific user-specified path. In a bid to overcome this problem we propose a method that generates a new walking motion by modifying the recorded data. In the learning step, some variables related to a walking style is obtained by analyzing the captured walking and running data. In the synthesis step, we generated a new walking style such as sidesteps or backward walks by modifying those variables. The proposed algorithm can generate a specific path-following motion which cannot be generated using existing approaches.
I/O Completion Technique of Virtualized System Considering CPU Usage with High-Performance Storage Devices
Hyeji Lee, Taehyung Lee, Minho Lee, Yongju Song, Young Ik Eom
http://doi.org/10.5626/JOK.2019.46.7.612
Recently, the advent of high-performance storage devices such as Samsung Z-SSD and Intel Optane SSD has shifted the I/O systems’ performance overhead from the storage devices to the software I/O layer. To optimize the I/O performance of high-performance storage devices, the hypervisor and operating system have focused on the effectiveness of polling technique, which is one of the I/O completion techniques applied in virtualized systems, and new techniques such as hybrid and adaptive polling are being adopted. This paper reveals the problem of the existing adaptive polling techniques provided by QEMU-KVM hypervisor and proposes a new I/O completion technique, which saves on CPU usage while fully utilizing high-performance storage devices. Our evaluation indicates that the proposed technique reduces CPU usage by up to 39.7% while delaying I/O latency to less than 5.3% only, in comparison to conventional systems.
Analysis of Initial Response Status in Online Information Provider Systems
http://doi.org/10.5626/JOK.2019.46.7.620
Online information provider system (OIPS) can contribute to the fast dissemination of information and build new public opinions. However, the increase in OIPS leads to side effects such as fake news, crucial invasion of privacy, online bullying etc. To promote positive functions and prevent side effects, an automated system for analyzing the initial status of information is necessitated. In this paper, for the first time in literature, we provide four criteria for automated analysis and suggest a new model for analysis. After the design of the online information analysis concept, we crawl real data from an OIPS and successfully conducted the initial status analysis.
The analysis of Loan status and Comparison of Default Prediction Performances based on Personal Credit Information Sample Database
http://doi.org/10.5626/JOK.2019.46.7.627
In this paper, we analyze the status of loans and defaults and present statistical data according to the borrower"s gender, age, month, etc. by using the personal credit information sample database offered as a trial service from Korea Credit Information Services. In addition, since domestic and foreign banks are paying attention to minimize the loss caused by default of the borrower, we used the personal credit information sample database to create a predicting model of borrower default and evaluated the model performance. To predict the default for a certain month, the borrower"s demographic information and loan information for the previous six months were processed to generate characteristic data, and a default prediction model was created using Recurrent Neural Network and machine learning algorithm. Based on the performance of each model, Recurrent Neural Network was showed as the model to demonstrate the best performance with Recall of 0.96 and AUC of 0.85 for the default borrower.
Korean Dependency Parser using Higher-order features and Stack-Pointer Networks
http://doi.org/10.5626/JOK.2019.46.7.636
Syntactic parsing is carried out to analyze a syntactic structure and resolve syntactic ambiguities in an input sentence. In general, the Korean language has relatively free word order and frequent omission of nouns such as subjects or objects. Therefore, dependency parsers are known to be suitable for parsing the Korean language. A stack-pointer network is a combination of a pointer network and internal stacks. The network reads and encodes a whole input sentence, and builds a dependency tree top-down in a depth-first fashion. In this paper, we employed a stack-pointer network for parsing the Korean language and utilized higher-order information to benefit from all the previously derived subtree structures. Experimental results revealed that the dependency parser with a sibling node as higher-order features led to Unlabeled Attachment Score(UAS) of 92.63% accuracy.
Metadata Extraction based on Deep Learning from Academic Paper in PDF
Seon-Wu Kim, Seon-Yeong Ji, Hee-Seok Jeong, Hwa-Mook Yoon, Sung-Pil Choi
http://doi.org/10.5626/JOK.2019.46.7.644
Recently, with a rapid increase in the number of academic documents, there has arisen a need for an academic database service to obtain information about the latest research trends. Although automated metadata extraction service for academic database construction has been studied, most of the academic texts are composed of PDF, which makes it difficult to automatically extract information. In this paper, we propose an automatic metadata extraction method for PDF documents. First, after transforming the PDF into XML format, the coordinates, size, width, and text feature in the XML markup token are extracted and constructed as a vector form. Extracted feature information is analyzed using Bidirectional GRU-CRF, which is an deep learning model specialized for sequence labeling, and finally, metadata are extracted. In this study, 10 kinds of journals among various domestic journals were selected and a training set for metadata extraction was constructed and experimented using the proposed methodology. As a result of extraction experiment on 9 kinds of metadata, 88.27% accuracy and 84.39% F1 performance was obtained.
The Effect of Expressions of Self-consciousness in Social Robots during Social Attraction
http://doi.org/10.5626/JOK.2019.46.7.653
The research on social robots is gradually expanding with the inclusion of studies on interaction with humans with emphasis on behavior, facial expressions, nonverbal cues, and emotional expressions. In this study, we investigated the effect of expression of self-consciousness in social robots at the time of social attraction through a survey experiment. In particular, we measured the changes in the social attraction score depending on the public and private self-consciousness expressions and the appearance of the robot, especially when the robot was placed in the uncanny valley. The results showed that the expressions of self-consciousness increased the attractiveness of social robots, but we found mixed effects on message types and the appearance of the robots. This study suggests a new and efficient way to enhance the perceived attractiveness of robots. Also, the results are hypothesized to have practical implications for designing the interface and interaction of social robots and in building a positive social relationship with humans.
An Optimization Method for Perceived Quality of Services in Service-oriented V2X Software Environments
HyeongCheol Moon, KyeongDeok Baek, In-Young Ko
http://doi.org/10.5626/JOK.2019.46.7.664
Recent advancements in computing technologies have led to researches on large-scale Cyber Physical System (CPS) applications such as Vehicle-to-Everything (V2X) applications. Numerous researchers have attempted to apply service computing technologies to V2X environments to make them more flexible and reliable. In a service-oriented V2X environment, users receive services through the Internet of Things (IoT) devices. Most of the existing V2X environments estimate or evaluate service quality from the network point of view. Apparently, the users" perceived Quality of Service (QoS), which is affected by various factors in V2X environments, especially by the users’ mobility, cannot be guaranteed. In the present work, we investigate the mobility-related factors that affect the users’ perceived QoS with an aim to optimize the users’ perceived QoS in V2X environments and propose an algorithm that considers the effectiveness of delivering service effects and the overhead of service handover among different IoT devices. We conducted a series of experiments, and it was observed that our QoS optimization approach outperforms the existing methods that consider only the quality factors in the network"s perspective.
3D Object-grabbing Hand Tracking based on Depth Reconstruction and Prior Knowledge of Grasp
Woojin Cho, Gabyong Park, Woontack Woo
http://doi.org/10.5626/JOK.2019.46.7.673
We propose a real-time 3D object-grabbing hand tracking system based on the prior knowledge of grasping an object. The problem of tracking a hand interacting with an object is more difficult compared to the issue of an isolated hand since it requires consideration of occlusion by an object. Most of the previous studies resort to the insufficient data which lacks the data of occluded hand and the information that the presence of an object may rather be a constraint on the pose of the hand. In the present work, we focused on the sequence of a hand grabbing an object by utilizing prior knowledge about grasp situation. Consequently, an excluded depth data of the hand occluded by the object was reconstructed with proper depth data and a reinitialization process was conducted based on the plausible grasp pose of the human. The effectiveness of the proposed process was verified based on model-based tracker with particle swarm optimization. Quantitative and qualitative experiments demonstrate that the proposed processes can effectively improve the performance of model-based tracker for the object-grabbing hand.
A Script Generation Method for Microservice Deployment in a Container Orchestration Environment
Daeho Kim, Donggyu Yun, Joonseok Park, Keunhyuk Yeom
http://doi.org/10.5626/JOK.2019.46.7.682
Container orchestration technology has been used to develop applications such as microservices and support distribution and management of container environments. Orchestration technology is appropriate for the resilient management of large-scale microservice applications because it enables the automated creation and distribution management of hundreds of containers in batches. However, when the existing monolithic application is converted into a container based on a microservice unit, the components necessary for distribution and management are manually mapped and defined. In this paper, we propose a method to automatically generate a template script to distribute and manage microservices in a container orchestration environment based on UML design data of existing monolithic application. In addition, in the case study, a template script was generated using the method described in Kubernetes, a container orchestration environment. The microservice was distributed and managed by executing the script.
English-to-Korean Machine Translation using Image Information
Jangseong Bae, Hyunsun Hwang, Changki Lee
http://doi.org/10.5626/JOK.2019.46.7.690
Machine translation automatically converts a text in one language into another language. Conventional machine translations use only texts for translation which is a disadvantage in that various information related to input text cannot be utilized. In recent years, multimodal machine translation models have emerged that use images related to input text as additional inputs, unlike conventional machine translations which use only textual data. In this paper, image information was added at decoding time of machine translation according to recent research trends and used for English-to-Korean automated translation. In addition, we propose a model with a decoding gate to adjust the textual and image information at the decoding time. Our experimental results show that the proposed method resulted in better performance than the non-gated model.
Index-based Searching for Isomorphic Subgraphs in Hypergraph Databases
Dae Geun Ha, Tae Wook Ha, Jung Hyuk Seo, Myoung Ho Kim
http://doi.org/10.5626/JOK.2019.46.7.697
A graph data type can represent relationships of objects in the real world and can be used for analyzing given relationships. A hypergraph is a generalized version of a normal graph where a hyperedge represents a relationship between more than or equal to two objects. In this paper, we propose a method that searches isomorphic subgraphs in a data hypergraph to a given query hypergraph. In order to reduce high computational costs of subgraph isomorphism search, previous studies have explored candidates that might be possible answers for each query node and return isomorphic subgraphs that consist of a combination of candidates. In this research, to enhance search performance, we have decomposed a query hypergraph into several subgraphs and discovered the candidates for each subgraph with the proposed structural index, and the proposed search algorithm checks subgraph isomorphism. With real-world datasets, experimental results demonstrate that the search response time of the proposed method is at least 10 times faster than the existing methods.
Semantic Web-based Gateway System for Providing Autonomous Context-Aware Service in IoT Environment
http://doi.org/10.5626/JOK.2019.46.7.706
With the rapid growth of the IoT (Internet of Things) market, seamless connection between independently developed platforms has become an important issue. In addition, research is underway on auto-configuration to minimize human interference while configuring devices for users to utilize IoT applications. However, to realize fully autonomous systems, the machine should be able to perform autonomous interaction between devices by recognizing the context as well as autoconfiguration. In this paper, we propose a semantic Web-based gateway system for providing autonomous context-aware service in IoT environment. The proposed system autonomously performs inter-device interaction by recognizing the state of the device and user-defined rules. Through the real-world implementation, we verify the feasibility of the proposed system.
Deep Reinforcement Learning based Multipath Packet Scheduling
Minwoo Joo, Wonwoo Jang, Wonjun Lee
http://doi.org/10.5626/JOK.2019.46.7.714
Packet scheduling in multipath environments deals with the determination of the manner of distribution of data traffic over multiple network paths and is considered as one of the significant factors affecting the multipath transport performance. However, existing algorithms for packet scheduling rely on particular metrics, which leads to limited performance under dynamic network conditions. In this paper, we propose a deep reinforcement learning (DRL) based packet scheduler with an ability to adapt to dynamic network changes. We have designed a DRL model to automatically capture and discover the network states and effects from the scheduling decisions. The proposed packet scheduler is implemented based on a multipath extension of the Quick UDP Internet Connections (QUIC) network stack and evaluated through network emulation to verify the potential of autonomous networking.
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