Vol. 47, No. 3, Mar. 2020
Digital Library


Emotion Recognition based on Multivariate Multiscale Fuzzy Entropy Analysis of EEG Recordings

Dae-Young Lee, Young-Seok Choi

http://doi.org/10.5626/JOK.2020.47.3.227

An Electroencephalogram (EEG) signal is an immediate and continuous signal that records brain activity, and it is mainly used for emotional analysis since it can directly reflect the changes of human emotional states. Among the methods of analyzing the EEG signals, entropy analysis is one of the measures for quantifying the complexity of time series. This quantitative analysis of complexity is promising for investigating non-stationary and nonlinear physiological signals. In this paper, we propose a multivariate multiscale fuzzy entropy (MMFE) analysis method that quantifies the complexity of multivariate time series over various time scales to analyze emotional states using EEG signals recorded from multiple electrodes as input. A public database, DEAP, is used as input data in this analysis, and the results show the possibility that emotional states can be distinguished through the binary classification of high/low arousal and high/low valence.

Space Efficient Top-k Query Encoding Based on Data Distribution

Wooyoung Park, Srinivasa Rao Satti

http://doi.org/10.5626/JOK.2020.47.3.235

We consider an encoding that supports a range top-k query on a two-dimensional array without accessing the original array. We propose a more space-efficient encoding method for top-k query with better average-case query time. Our experiments also show that our encoding is more space-efficient than the earlier ones. Also, based on the learning-based data structure, we propose the use of the learning-based data structure on succinct data structures.

Development of Big Data Platform Operation and Management System Considering HPC Environments

Jae-Hyuck Kwak, Jieun Choi, Eunkyu Byun, Sangwan Kim

http://doi.org/10.5626/JOK.2020.47.3.240

Software technologies in traditional computational science and big data fields have evolved into different forms, but the growth of big data technology and recent advances in artificial intelligence technology have broken down boundaries between the two fields and have lead to generalized, high-performance computing environments. However, as these two areas of software stack were built and developed independently, it is not easy to integrate and operate them seamlessly in high-performance computing environment. In this paper, we developed a big data platform operation and management system considering high-performance computing environment. The system is an extension of Ambari, an open-source Hadoop platform operations management system that also provides installation management for Lustre, configuration of the Hadoop-on-Lustre execution environment, YARN job monitoring with user-defined and dynamic monitoring metrics as well as a web-based interface for high-performance computing resource monitoring.

The Probabilistic Process Algebra to Predict System Behaviors of IoT Systems

Junsup Song, Moonkun Lee

http://doi.org/10.5626/JOK.2020.47.3.247

It is necessary to model the predictability of IoT systems under uncertainty. Probabilistic process algebra can model the predictability of the IoT systems behaviors based on the probability concept, in order to handle the uncertainty. For example, there are a few process algebras with probability property, such as PAROMA, PACSR, etc. However, these algebras are limited to analyzing IoT systems because they are based on simple discrete or exponential models. In order to overcome the existing limitations, this paper presents new process algebra, namely, dTP-Calculus. It enables application of four probabilistic models to smart IoT systems under complex uncertainty. In order to demonstrate the feasibility of the approach, a tool suite, called SAVE, for modeling the IoT system with dTP-Calculus has been developed.

Development of an Information Extraction System Using the Dependency Analysis

Hyeyoung Kim, Hangyeol Sun, Youngwook Kim

http://doi.org/10.5626/JOK.2020.47.3.266

In this paper, we propose an information extraction system that can automatically extract user intended key syntax, by analyzing the dependency parse of a sentence. Previous Open Information Extraction studies extract two related arguments based on a verb to structuralize information, from massive data in unsupervised methods. However, users may be unable to extract key syntax accordingly, from a sentence without a verb or a sentence with various arguments. To solve this problem, this system first splits a sentence into an appropriate length to enhance the accuracy of analysis and incorporates dependency relations between words using a dependency parser. Then, we defined four extraction rules from the most basic sentence structures and built a system to extract meaningful chunking from predefined rules. Consequently, with a rule-based approach, users can freely add or modify extraction rules and derive key syntax from any type of a document. We experimented with Wikipedia data and the system achieved 33% more accuracy than DepOE, another OIE system that applies a dependency parser. As a result of the experiment, the system we propose enables easy analyses of written text and will be useful in analyzing various texts in the future.

A New Light-Weight and Efficient Convolutional Neural Network Using Fast Discrete Cosine Transform

Joonhyun Jeong, Sung-Ho Bae

http://doi.org/10.5626/JOK.2020.47.3.276

Recently proposed light-weight neural networks maintain high accuracy in some degree with a small amount of weight parameters and low computation cost. Nevertheless, existing convolutional neural networks commonly have a lot of weight parameters from the Pointwise Convolution (1x1 convolution), which also induces a high computational cost. In this paper, we propose a new Pointwise Convolution operation with one dimensional Fast Discrete Cosine Transform (FDCT), resulting in dramatically reducing the number of learnable weight parameters and speeding up the process of computation. We propose light-weight convolutional neural networks in two specific aspects: 1) Application of DCT on the block structure and 2) Application of DCT on the hierarchy level in the CNN models. Experimental results show that our proposed method achieved the similar classification accuracy compared to the MobileNet v1 model, reducing 79.1% of the number of learnable weight parameters and 48.3% of the number of FLOPs while achieving 0.8% increase in top-1 accuracy.

GS-RANSAC : An Error Filtering Algorithm for Homography Estimation based on Geometric Similarities of Feature Points

Kiheun Song, Myung-Duk Hong, Geun-Sik Jo

http://doi.org/10.5626/JOK.2020.47.3.283

Augmented Reality (AR) is intended to generate information by displaying augmented objects on real-world objects. AR is essentially used to calculate the coordinates of augmented objects, for which a homography estimation method involving two images is generally used. In homography estimation, the RANSAC (Random Sample Consensus) algorithm is used to select the four most appropriate pairs of feature points extracted from the two images. However, conventional RANSAC algorithms cannot guarantee the geometric similarity of the inter-image locations of the feature points selected randomly. In order to resolve this conundrum, we propose an algorithm to evaluate the geometric similarity of inter-image locations of feature points. The proposed algorithm draws tetragons of feature points on each image. Then the algorithm determines if the tetragons are similar in the order of vertices and the range of internal angles. The experimental results show that the proposed algorithm decreases the failure rate by 8.55% and displays the augmented objects more accurately compared with conventional RANSAC. We improved the accuracy of augmented object coordinates in AR using our proposed algorithm.

A Deep Learning LSTM Framework for Urban Traffic Flow and Fine Dust Prediction

Hongsuk Yi, Khac-Hoai Nam Bui, Choong-Nyoung Seon

http://doi.org/10.5626/JOK.2020.47.3.292

Accurate and timely forecasting is an essential step for the successful deployment of smart cities. With the rapid growth of traffic data collected daily, recent studies have focused on deep learning based on long-term short term memory (LSTM) for short-term traffic prediction, especially in urban areas. However, the short-term (five minutes) LSTM model is limited in the real-time nonlinear traffic flow prediction. Moreover, the fine dust prediction based on traffic data is also an emerging issue in this research area. Thus, this paper designs the multiple traffic data-based multi-input/output LSTM framework for supporting medium and long-term prediction. Additionally, a convolutional LSTM (ConvLSTM) model is developed for predicting fine dust flow based on traffic data. Regarding the experiment, we analyzed data from the Vehicle Detection System (VDS) located on major roads in Daejeon City for the evaluation. The experiment indicates promising results for the proposed approach.

Analysis of the Semantic Answer Types to Understand the Limitations of MRQA Models

Doyeon Lim, Haritz Puerto San Roman, Sung-Hyon Myaeng

http://doi.org/10.5626/JOK.2020.47.3.298

Recently, the performance of Machine Reading Question Answering (MRQA) models has surpassed humans on datasets such as SQuAD. For further advances in MRQA techniques, new datasets are being introduced. However, they are rarely based on a deep understanding of the QA capabilities of the existing models tested on the previous datasets. In this study, we analyze the SQuAD dataset quantitatively and qualitatively to demonstrate how the MRQA models answer the questions. It turns out that the current MRQA models rely heavily on the use of wh-words and Lexical Answer Types (LAT) in the questions instead of using the meanings of the entire questions and the evidence documents. Based on this analysis, we present the directions for new datasets so that they can facilitate the advancement of current QA techniques centered around the MRQA models.

An Autonomous IoT Programming Paradigm Supporting Neuromorphic Models and Machine Learning Models

Sanglok Yoo, Keonmyung Lee, Youngsun Yun, Jiman Hong

http://doi.org/10.5626/JOK.2020.47.3.310

The demands and expectations of the IoT (Internet of Things) application services are increasing with the development of sensor technology and high-speed communication infrastructures. Even with many sensors operating and networked, transmission of all the sensor data to the server for processing is inefficient in terms of communication bandwidth and storage space. Meanwhile, with the recent development of artificial intelligence technology, the demand for intelligent processing of the IoT is increasing. This paper proposes a programming paradigm that can apply neuromorphic model-based models and machine learning models relative to IoT clients, and a programming paradigm that applies machine learning models and knowledge processing models relative to IoT servers. The proposed programming paradigm is expected to be valuable for the intelligent IoT as well as for autonomous IoT environments in that various AI modules can be applied relative to IoT clients and server programs.

A Recommendation Scheme for an Optimal Pre-processing Permutation Towards High-Quality Big Data Analytics

Seounghyun Kim, Young-Kyoon Suh, Byungchul Tak

http://doi.org/10.5626/JOK.2020.47.3.319

Today, due to the explosive increase in data, intelligent service research through big data analysis has been actively conducted in various domains. Pre-processing of training data is essential to big data analytics via data mining or machine learning. Although incomplete and inadequate pre-processing for a given dataset can result in unreliable analysis, it is challenging for users to choose the optimal set and sequence of pre-processing functions that leads to the best results. To address this problem, we have designed and implemented a pre-processing evaluation platform that can analyze the performance of a various permutation of pre-processing functions for a given user dataset and then recommend the best permutation. Evaluation results using the real-world dataset demonstrates that the recommended pre-processing permutation yields the best performance in terms of accuracy when compared to the worst pre-processing permutation. By applying the method proposed in this paper, users can choose the best preprocessing permutation, thus being expected to obtain high-quality big data analysis results.

Outdoor Swarm Flight System Based on the RTK-GPS

SungTae Moon, DoYoon Kim, DonGoo Lee

http://doi.org/10.5626/JOK.2020.47.3.328

The increasing interest in drones has generated new application systems in the various areas. Especially, the drone-show performance applying the swarm flight system impressed many people globally at the Pyeongchang Winter Olympics. However, this technology is Intel technology, not domestic proprietary technology. Thus, the KARI (Korean Aerospace Research Institute) has developed the swarm flight system based on the RTK-GPS and verified the system by showing the 100 drone-show at the independence movement day. In this paper, the propose a robust swarm flight system which can switch the mode according to the RTK-GPS condition. The efficient precise position estimation, communication system, and how to develop the scenario are explained.

Study and Application of RSSI-based Wi-Fi Channel Detection Using CNN and Frequency Band Characteristics

Junhyun Park, Hyungho Byun, Chong-Kwon Kim

http://doi.org/10.5626/JOK.2020.47.3.335

For mobile devices, Wi-Fi channel scanning is essential to initiating an internet connection, which enables access to a variety of services, and maintaining a stable link quality by periodic monitoring. However, inefficient Wi-Fi operation, where all channels are scanned regardless of whether or not an access point (AP) exists, wastes resources and leads to performance degradation. In this paper, we present a fast and accurate Wi-Fi channel detection method that learns the dynamic frequency band characteristics of signal strengths collected via a low power antenna using a convolution neural network (CNN). Experiments were conducted to demonstrate the channel detection accuracy for different AP combination scenarios. Furthermore, we analyzed the expected performance gain if the suggested method were to assist the scanning operation of the legacy Wi-Fi.


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