Vol. 46, No. 9,
Sep. 2019
Digital Library
Developing Room Management Cloud Service for Small Hotels based on Micro-Service Architecture
http://doi.org/10.5626/JOK.2019.46.9.869
Recently, O2O service, OTA(Online Travel Agency)service in Korea and abroad has changed the business environment and it is demanding quick response ability in hospitality business. In this situation, companies offering small-scale accommodation are required to build a light and efficient system with services comparable to large hotels. We propose a method to provide cloud - based service using micro - service architecture(MSA). It is a suitable implementation method for rapid business environment change by enabling continuous improvement without affecting the whole service. Integration of the external reservation systems with room sales management into a single service has resolved the challenges associated with overbooking and limited room inventory problem. As a result, the accuracy of reservation has been improved along with efficiency in inventory management.
PARPA: A Parallel Framework Simultaneously Using Heterogeneous Architecture for High Performance Computing
Hyojae Cho, Taehyun Han, Hyeonmyeong Lee, Heeseung Jo
http://doi.org/10.5626/JOK.2019.46.9.876
With the substantial performance improvements achieved in GPU, they have come to be commonly used not only in computer graphics but also in high performance computing. Simply using a CPU and a GPU concurrently is not difficult. However, distributing works and adjusting the computing ratio among these heterogeneous processors are challenging issues. We propose a novel framework in this paper, named PARPA, which automatically distributes and processes tasks to a CPU and a GPU. PARPA can maximize computation performance by using a CPU and a GPU simultaneously. The load balancing between them can be performed dynamically based on their usage and features. The evaluation results indicate that PARPA shows 3.48 times better performance.
A Compression-based Data Consistency Mechanism for File Systems
Dong Hyun Kang, Sang-Won Lee, Young Ik Eom
http://doi.org/10.5626/JOK.2019.46.9.885
Data consistency mechanism is a crucial component in any file system; the mechanism prevents the corruption of data from system crashes or power failures. For the sake of performance, the default journal mode of the Ext4 file system guarantees only the consistency of metadata while compromising with the consistency of normal data. Specially, it does not guarantee full consistency of the whole data of the file system. In this paper, we propose a new crash consistency scheme which guarantees strong data consistency of the data journal mode by still providing higher or comparable performance to the weak default journal mode of the Ext4 file system. By leveraging a compression mechanism, the proposed scheme can halve the amount of write operations as well as the number of fsync() system calls. For evaluation of the performance, we modified the codes related to the jbd2 and compared the proposed scheme with two journaling modes in Ext4 on SSD and HDD. The results clearly confirm that the proposed scheme outperforms the default journal mode by 8.3x times.
Extraction of Cognitive Psychological Features of Mobile Gamers and Improvement of Purchases Prediction Performance
Jihoon Jeon, Seongil Yang, KyungJoong Kim
http://doi.org/10.5626/JOK.2019.46.9.892
In-game purchases are one of the important factors that directly affect a company"s revenue. In total, 95% of gamers do not pay for in-game purchases, meaning that a small number of gamers are responsible for most of the revenue of the company behind their games. For this reason, game companies must maintain and augment these few purchasing gamers. In this paper, we extracted seven cognitive psychological features (competitive, challenge, loyal, social, activity, efficient, and sincerity) that can be used to estimate the cognitive psychology of a gamer by using log data of a mobile RPG game. We analyzed the gamers, classified by payment amount, based on seven cognitive psychological features. As a result, the cognitive psychological features and payment amount of the gamers could be correlated. In addition, using seven cognitive psychological features, we predicted the purchasing behavior of gamers with high accuracy. This implies that gamers can be analyzed based on their cognitive psychology and the gamer"s purchases can be predicted with comparatively high performance.
Korean Movie Review Sentiment Analysis using Self-Attention and Contextualized Embedding
Cheoneum Park, Dongheon Lee, Kihoon Kim, Changki Lee, Hyunki Kim
http://doi.org/10.5626/JOK.2019.46.9.901
Sentiment analysis is the processing task that involves collecting and classifying opinions about a specific object. However, it is difficult to grasp the subjectivity of a person using natural language, so the existing sentimental word dictionaries or probabilistic models cannot solve such a task, but the development of deep learning made it possible to solve the task. Self-attention is a method of modeling a given input sequence by calculating the attention weight of the input sequence itself and constructing a context vector with a weighted sum. In the context, a high weight is calculated between words with similar meanings. In this paper, we propose a method using a modeling network with self-attention and pre-trained contextualized embedding to solve the sentiment analysis task. The experimental result shows an accuracy of 89.82%.
Automatic Extraction of Sentence Embedding Features for Question Similarity Analysis in Dialogues
Kyo-Joong Oh, Dongkun Lee, Chae-Gyun Lim, Ho-Jin Choi
http://doi.org/10.5626/JOK.2019.46.9.909
This paper describes a method for the automatic extraction of feature vectors that can be used to analyze the similarity among natural language sentences. Similarity analysis among sentences is a necessary aspect of measuring semantic or structural similarity in natural language understanding. The analysis results can be used to find answers in Question and Answer (Q&A) systems and dialogue systems. The similarity analysis uses sentence vectors extracted by two deep learning models: the Recurrent Neural Network (RNN) to reflect sequential information of expressions such as syllables and semantic morphemes, and the Convolutional Neural Network (CNN) for characterizing the appearance patterns of similar expressions such as words or phrases. In this paper, we examine the accuracy and quality of the method using sentence vectors that are automatically extracted by the models from dialogues related to banking service. This method can find more similar questions and answers in FAQs than existing methods. The automatic feature extraction method can be used to analyze the similarity of Korean sentences across various application domains and systems.
Design of Video Advertisement Analysis via Analysis of Internet Term Sensitivity
Sejin Kim, Jieun Kim, Wonyoung Seong, Yoonhee Kim
http://doi.org/10.5626/JOK.2019.46.9.919
Analysis of the increasing influence of video advertisements via Social Networking Service (SNS) is important in identifying their effects. However, the traditional methods of survey-based analysis are not suitable for measurement of the effectiveness of SNS advertisements that are distributed rapidly via smartphone use and the current system does not consider the sensitivity of users expressed in various forms, such as slang, and emoticons. This study proposes an automated system for the analysis of the effects of video ads via video comments, reflecting the characteristics of short Korean sentences.
This system uses machine learning for the interpretation of Internet terms and compilation of a sentiment dictionary specializing in SNS short sentences. Emoticon, which is used to emphasize the sensitivity of users in comments, is used for sentiment analysis when applied to Korean syntax rules, and the system is designed and implemented for more sophisticated emotional analysis by calculating the emotional values of nouns that are subject to sentiment.
Automatic Test Case Generation through Concolic Testing to Improve SW Quality of Defense Weapon System
Kunwoo Park, Joohyun Lee, Hyunggon Song, Kyu Tae Cho, Yunho Kim, Moonzoo Kim
http://doi.org/10.5626/JOK.2019.46.9.926
To improve SW quality of defense weapon system, automatic and systematic generation of test cases is necessary; however, that is not the case in the traditional practice of labor-intensive and manual SW testing. The paper applies concolic testing to the defense weapon system SW, effectively generates test cases that achieve high coverage, and discovers defects which contributes to the improvement in SW quality. Also, two methods are proposed using 4 search strategies in concolic testing and using LIA logic, to increase the efficiency of concolic testing for a program with high complexity. In addition, a symbolic modeling method is proposed as an example to extend concolic testing for practitioners.
Sentence Generation from Knowledge Base Triples Using Attention Mechanism Encoder-decoder
http://doi.org/10.5626/JOK.2019.46.9.934
In this paper, we have investigated the generation of natural language sentences by using Knowledge Base Triples data with a structured structure. In order to generate a sentence that expresses the triple, a LSTM (Long Short-term Memory Network) encoder-decoder structure is used along with an Attention Mechanism. The BLEU score and ROUGE score for the test data were 42.264 (BLEU-1), 32.441 (BLEU-2), 26.820 (BLEU-3), 24.446 (BLEU-4), and 47.341 and 0.8% (based on BLEU-1) for the data comparison model. In addition, the average of the top 10 test data BLEU scores was recorded as 99.393 (BLEU-1).
Deep Ensemble Network with Explicit Complementary Model for Accuracy-balanced Classification
http://doi.org/10.5626/JOK.2019.46.9.941
One of the major evaluation metrics for classification systems is average accuracy, while accuracy deviation is another important performance metric used to evaluate various deep neural networks. In this paper, we present a new ensemble-like fast deep neural network, Harmony, that can reduce the accuracy deviation among categories without degrading the overall average accuracy. Harmony consists of three sub-models: the Target model, Complementary model, and Conductor model. In Harmony, an object is classified by using either the Target model or the Complementary model. The Target model is a conventional classification network for general categories, while the Complementary model is a classification network specifically for weak categories that are inaccurately classified by the Target model. The Conductor model is used to select one of the two models. The experimental results indicate that Harmony accurately classifies categories and also, reduces the accuracy deviation among the categories.
Recursive Compaction Method of LSM-tree based Key-value Store
Jongbin Kim, Seohui Son, Hyunsoo Cho, Hyungsoo Jung
http://doi.org/10.5626/JOK.2019.46.9.946
LSM-tree-based key-value stores exhibit an optimized structure for data writing operations and typically maintain the form of LSM tree by executing a compaction operation. The compaction operation which reads data from the storage device into memory for sorting it and writes back the result data in to the storage device several times causes some problems. In this paper, we analyzed the performance degradation and the write amplification caused by the compaction, and proposed a new compaction method known as recursive compaction. Recursive compaction alleviates the problems involving the compaction operation by utilizing multiple threads to perform multiple compactions at a time, handling read operation and garbage collection properly. We implemented this technique for Google LevelDB and analyzed the results.
An Approach to Detect Macros via Self-similarity of Mobile Input
http://doi.org/10.5626/JOK.2019.46.9.951
Macros that repeats specified in-game actions without the need for human interaction are a major cause of unfairness in computer gaming. For the success of a game service, the organizational use of macros which destroys the game’s economy and can deteriorate a user’s game motivation should be prohibited. It is particularly easy for macros to be generated and used in mobile games, because a mobile game’s design and playing sequence are likely to be relatively simple compared to those of PC games because of the limited hardware resources and, inefficient input methods of mobile devices compared to PCs. At the same time, the current macro detection methods used in mobile games can consume substantial amounts of resources. Thus, macro detection is still a challenge in mobile game services. In this paper, we propose a method to detect macros via self-similarity based on the mobile input. Our proposed method sets the unit for effectively obtaining self-similarity with fewer resources. We applied the proposed method to two mobile games and showed that macro and human activities can be distinguished with high accuracy.
Radio Resource Allocation in 5G New Radio: A Neural Networks Approach
Madyan Alsenwi, Kitae Kim, Choong Seon Hong
http://doi.org/10.5626/JOK.2019.46.9.961
The minimum frequency-time unit that can be allocated to User Equipments (UEs) in the fifth generation (5G) cellular networks is a Resource Block (RB). A RB is a channel composed of a set of OFDM subcarriers for a given time slot duration. 5G New Radio (NR) allows for a large number of block shapes ranging from 15 kHz to 480 kHz. In this paper, we address the problem of RBs allocation to UEs. The RBs are allocated at the beginning of each time slot based on the channel state of each UE. The problem is formulated based on the Generalized Proportional Fair (GPF) scheduling. Then, we model the problem as a 2-Dimension Hopfield Neural Networks (2D-HNN). Finally, in an attempt to solve the problem, the energy function of 2D-HNN is investigated. Simulation results show the efficiency of the proposed approach.
Style Transfer Deep Learning Framework for Nighttime Robust Vehicle Detection in On-Road Mobile Platforms
http://doi.org/10.5626/JOK.2019.46.9.968
Car recognition has become an important part of self-driving car technologies. In autonomous driving, vehicle detection techniques are important to prevent vehicle-to-vehicle accidents. Traditional image processing methods for vehicle detection perform car detection via deep learning. Studies indicate that although these methods are effective in more than fifty percent of cases in daytime detection, their performance is insufficient for nighttime recognition. Vehicle detection is one of the tasks involved in minimizing the loss of human lives. Further, the nighttime scenario is more common, and therefore, in this paper, we propose an improved and robust method for detection of the car via filter-based image style transfer. The results of the proposed method were obtained using real-world data and experiments, and indicate the superiority of our method compared with other methods in terms of accuracy of ideal segmentation.
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