Vol. 47, No. 2,
Feb. 2020
Digital Library
Host-Level I/O Scheduler for Achieving Performance Isolation with Open-Channel SSDs
Sooyun Lee, Kyuhwa Han, Dongkun Shin
http://doi.org/10.5626/JOK.2020.47.2.119
As Solid State Drives (SSDs) provide higher I/O performance and lower energy consumption compared to Hard Disk Drives (HDDs), SSDs are currently widening its adoption in areas such as datacenters and cloud computing where multiple users share resources. Based on this trend, there is currently greater research effort being made on ensuring Quality of Service (QoS) in environments where resources are shared. The previously proposed Workload-Aware Budget Compensation (WA-BC) scheduler aims to ensure QoS among multiple Virtual Machines (VMs) sharing an NVMe SSD. However, the WA-BC scheduler has a weakness in that it misuses multi-stream SSDs for identifying workload characteristics. In this paper, we propose a new host-level I/O scheduler, which complements this vulnerability of the WA-BC scheduler. It aims to eliminate performance interference between different users that share an Open-Channel SSD. The proposed scheduler identifies workload characteristics without having to allocate separate SSD streams by observing the sequentiality of I/O requests. Although the proposed scheduler exists within the host, it can reflect the status of device internals by exploiting the characteristics of Open-Channel SSDs. We show that by identifying those that attribute more to garbage collection, a source of I/O interference within SSDs, using workload characteristics and penalizing such users helps to achieve performance isolation amongst different users sharing storage resources.
Distributed Storage System for Reducing Write Amplification on Non-Volatile Memory
http://doi.org/10.5626/JOK.2020.47.2.129
Recently, research on non-volatile memory, such as 3DXpoint, in distributed storage systems has received considerable interest from both academia and industry. However, in order to utilize these state-of-the-art non-volatile memory devices effectively in distributed storage systems, there is a need for improvements in traditional architectures of HDD/SSD-based storage systems. This is because current distributed storage system structures use a dedicated space for journaling to make up for slow storage performance. Also, considering the performance characteristics of non-volatile memory, which are similar to that of DRAM, current distributed storage system structures are not only inefficient in terms of overall performance but also cause write amplification. In this paper, we propose an architecture that mitigates the effects of write amplification in non-volatile memory-based distributed storage systems. To evaluate the proposed architecture and scheme, we have conducted diverse experiments in a CEPH storage system environment. Through these experiments, we have confirmed that the DAXNJ structure proposed in this paper decreases write amplification by 61% during 1M object write operations and increases the overall system performance by 15%.
Automatic Convolution Neural Network Model Compression Framework for Resource-Constrained Embedded Systems
Jonghun Jeong, Dasom Lee, Hyeonseok Jung, Hoeseok Yang
http://doi.org/10.5626/JOK.2020.47.2.136
Recently, attempts have been made to directly execute various convolutional neural network applications in resource-constrained embedded systems such as IoT. However, since embedded systems have limited computational capability and memory, the size of the neural network model that can be executed is restricted and may not satisfy real-time constraints. Therefore, in this paper, we propose a framework that automatically compresses a given neural network model to satisfy memory and execution time requirements and automatically generates code that can be executed on the target embedded system. Using the proposed framework, we demonstrate that the given neural network models can be automatically optimized for two STM32 Nucleo series boards with different HW specifications for various execution time and memory requirements.
Comparison of Context-Sensitive Spelling Error Correction using Embedding Techniques
Jung-Hun Lee, Minho Kim, Hyuk-Chul Kwon
http://doi.org/10.5626/JOK.2020.47.2.147
This paper focuses on the use of embedding techniques to solve problems in context-sensitive spelling correction and compare the performance of each technique. A vector of words obtained through embedding learning is used to correct the distance between the correction target word and the surrounding context word. In this paper, we tried to improve the correction performance by reflecting the processing of words not included in the learning corpus and surrounding contextual information of the correction words. The embedding techniques used for proofing were divided into word-based embeddings and embeddings that reflected contextual information. This paper performed correction experiments using the embedding techniques, focusing on the above two improvement goals, and obtained reliable correction performance.
Single Sentence Summarization with an Event Word Attention Mechanism
Ian Jung, Su Jeong Choi, Seyoung Park
http://doi.org/10.5626/JOK.2020.47.2.155
The purpose of summarization is to generate short text that preserves important information in the source sentences. There are two approaches for the summarization task. One is an extractive approach and other is an abstractive approach. The extractive approach is to determine if words in a source sentence are retained or not. The abstractive approach generates the summary of a given source sentence using the neural network such as the sequence-to-sequence model and the pointer-generator. However, these approaches present a problem because such approaches omit important information such as event words. This paper proposes an event word attention mechanism for sentence summarization. Event words serve as the key meaning of a given source sentence, since they express what occurs in the source sentence. The event word attention weights are calculated by event information of each words in the source sentence and then it combines global attention mechanism. For evaluation, we used the English and Korean dataset. Experimental results show that, the model of adopting event attention outperforms the existing models.
Language Style Transfer Based on Surface-Level Neutralization
Wooyong Choi, Yunseok Noh, Seyoung Park
http://doi.org/10.5626/JOK.2020.47.2.162
Two main concerns of language style transfer such as sentiment transfer are neutralization of a stylized sentence and re-stylization of the neutralized sentence with a target style. Generally, neutralization is accomplished by learning a neutralized latent space by adversarial learning. However, this neutralization method suffers from the difficulty of maintaining the original content after style transfer. In this paper, we propose a two-step language style transfer method comprised of a surface-level neutralization that removes style words and a target-style word prediction for the removed words. For this, a self-attentive style classifier and style-specific word predictors are used for the surface neutralization and style word generation, respectively. To evaluate the proposed method, several experiments of language style transfer were conducted with Yelp and Amazon review datasets and Caption dataset. As a result, the proposed method shows superior performance over baseline methods on various evaluation metrics including automatic and human evaluations.
End-to-end Bone Tumor Segmentation and Classification from X-ray Images by Using Multi-level Seg-Unet Model
Nhu-Tai Do, Sung-Taek Jung, Hyung-Jeong Yang, Soo-Hyung Kim
http://doi.org/10.5626/JOK.2020.47.2.170
Knee bone tumor detection plays an essential role in assisting the clinical diagnosis process. To the best of our knowledge, there is no method to integrate end-to-end segmentation and classification for this problem. In this paper, we propose a multi-task deep learning architecture for classification and segmentation of the tumor regions in the knee bone. Also, we introduce multi-level distance masks from the distance transform of tumor region, and these multi-level distance masks have a role as a guided filter in enabling the network to capture semantic data around tumor regions. Besides, the architecture has a regularizing effect on the learning process between segmentation and classification. Our model was evaluated on the Chonnam National University Hospital dataset and achieved good performance compared to other methods.
A Product Review Summarization Considering Additional Information
Jaeyeun Yoon, Ig-hoon Lee, Sang-goo Lee
http://doi.org/10.5626/JOK.2020.47.2.180
Automatic document summarization is a task that generates the document in a suitable form from an existing document for a certain user or occasion. As use of the Internet increases, the various data including texts are exploding and the value of document summarization technology is growing. While the latest deep learning-based models show reliable performance in document summarization, the problem is that performance depends on the quantity and quality of the training data. For example, it is difficult to generate reliable summarization with existing models from the product review text of online shopping malls because of typing errors and grammatically wrong sentences. Online malls and portal web services are struggling to solve this problem. Thus, to generate an appropriate document summary in poor condition relative to quality and quantity of the product review learning data, this study proposes a model that generates product review summaries with additional information. We found through experiments that this model showed improved performances in terms of relevance and readability than the existing model for product review summaries.
Variational Recurrent Neural Networks with Relational Memory Core Architectures
Geon-Hyeong Kim, Seokin Seo, Shinhyung Kim, Kee-Eung Kim
http://doi.org/10.5626/JOK.2020.47.2.189
Recurrent neural networks are designed to model sequential data and learn generative models for sequential data. Therefore, VRNNs (variational recurrent neural networks), which incorporate the elements of VAE (variational autoencoder) into RNN (recurrent neural network), represent complex data distribution. Meanwhile, the relationship between inputs in each sequence has been attributed to RMC (relational memory core), which introduces self-attention-based memory architecture into RNN memory cell. In this paper, we propose a VRMC (variational relation memory core) model to introduce a relational memory core architecture into VRNN. Further, by investigating the music data generated, we showed that VRMC was better than in previous studies and more effective for modeling sequential data.
A Visual Analytics Technique for Analyzing the Cause and Influence of Traffic Congestion
Mingyu Pi, Hanbyul Yeon, Hyesook Son, Yun Jang
http://doi.org/10.5626/JOK.2020.47.2.195
In this paper, we present a technique to analyze the causes of traffic congestion based on the traffic flow theory. We extracted vehicle flows from the traffic data, such as GPS trajectory and Vehicle Detector data. Also, vehicle flow changes were identified by utilizing the entropy from the information theory. Then, we extracted cumulative vehicle count curves (N-curve) that can quantify the vehicle flows in the congestion area. According to the traffic flow theory, unique N-curve patterns can be observed depending on the congestion type. We build a convolution neural network classifier that can classify N-curve into four different congestion patterns. Analyzing the cause and influence of congestion is difficult and requires considerable experience and knowledge. Apparently, we present a visual analytics system that can efficiently perform a series of processes to analyze the cause and influence of traffic congestion. Through case studies, we have evaluated our system that can analyze the cause of traffic congestion.
Latent Representation Learning for Autoencoder-based Top-K Recommender System
Dongmin Park, Junhyeok Kang, Jae-Gil Lee
http://doi.org/10.5626/JOK.2020.47.2.207
As the number of products on the Internet is growing exponentially, it becomes more difficult for customers to choose the product they want. Many researchers have been actively making efforts to develop appropriate recommender systems that satisfy the potential demand of the customer and increase the profit of the seller. Recently, collaborative filtering methods based on an autoencoder have shown high performance. However, little attention has been paid for improving the recommendation performance by changing the distribution of latent representation. In this paper, we propose the Dense Latent Representation learning method (DenseLR) which is combined with the autoencoder-based collaborative filtering method to further improve product recommendation performance. The key idea of the DenseLR is to tighten collaborative filtering effects on the latent space by effectively densifying the latent representations of user (or item) rating vectors. In performance comparison experiments on three real-world datasets, DenseLR showed the highest recommendation performance for all datasets. Furthermore, DenseLR can be flexibly combined with a wide range of autoencoder-based CF models, and we empirically validated the improvement of the f1@k score ranging from 4.6% to 23.7%.
Dynamic Link Key Generation Algorithm for Hardware Oracle Problem in I2C Protocol
Sangrok Lee, Jiwoo Park, Sooyong Park
http://doi.org/10.5626/JOK.2020.47.2.216
Blockchain is a system in which once the data is recorded on the ledger, it is impossible to modify and delete the data. If external data is falsified and recorded in the blockchain, the reliability of the blockchain gets destroyed. Consequently, data integrity must be guaranteed before the data is recorded in the blockchain. However, while attempting to record data from sensors in blockchain, the security mechanism of the I2C protocol, which is a method of communication between the chips inside the device does not exist. Generally, the encryption key is used to avoid hacking; however, the key can be captured and Rekeying overhead can occur. In this paper, a dynamic link-key algorithm is presented for efficient updating of key suitable for the I2C protocol. Based on one of the recent studies on dynamic key generation algorithm based on message sequence, the characteristics of the I2C protocol were reflected, and the limited resources of the sensor were overcome by minimal computation by ensuring the randomness of keys generated through statistical tests.
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