• Communications for Statistical Applications and Methods
• /
• v.30 no.2
• /
• pp.119-133
• /
• 2023

With the rapid growth of the economy and fossil fuel consumption, the concentration of air pollutants has increased significantly and the air pollution problem is no longer limited to small areas. We conduct statistical analysis with the actual data related to air quality that covers the entire of South Korea using R and Python. Some factors such as SO₂, CO, O₃, NO₂, PM₁₀, precipitation, wind speed, wind direction, vapor pressure, local pressure, sea level pressure, temperature, humidity, and others are used as covariates. The main goal of this paper is to predict air quality index (AQI) spatio-temporal data. The observations of spatio-temporal big datasets like AQI data are correlated both spatially and temporally, and computation of the prediction or forecasting with dependence structure is often infeasible. As such, the likelihood function based on the spatio-temporal model may be complicated and some special modelings are useful for statistically reliable predictions. In this paper, we propose several methods for this big spatio-temporal AQI data. First, random effects with spatio-temporal basis functions model, a classical statistical analysis, is proposed. Next, neural networks model, a deep learning method based on artificial neural networks, is applied. Finally, random forest model, a machine learning method that is closer to computational science, will be introduced. Then we compare the forecasting performance of each other in terms of predictive diagnostics. As a result of the analysis, all three methods predicted the normal level of PM_2.5 well, but the performance seems to be poor at the extreme value.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.12 no.1
• /
• pp.71-81
• /
• 1987

To fuly utilize the availability of the ISDN, it is very important to develop the ISDN user terminals which can provide various user services. In this paper, the basic concept of the ISDN user terminal is briefly studied and, based on this study, a stimulus type digital telephone which can be connected directly to the ISDN is designed. This digital telephone can provide the basic voice service and has general functions such as voice encoding / decoding(PCM is used), user-network signalling, digital tone supply, channel selection, key pad and atatus display. Echo cancellation method is adopted for the digital subscirber loop transmission and user-network signalling is implemented according to the LAPD(Link Access Procedure on D-channel) protocol recommended by the CCITT's recommendations I.440-I.441. The validity of designed S/W and H/W functions are verified by testing them with ISDN circuit switching emulator described in the first part of this paper.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.36 no.2B
• /
• pp.131-140
• /
• 2011

As the number of Internet users and applications is increasing, the importance of application traffic classification is growing more and more for efficient network management. While a number of methods for traffic classification have been introduced, such as signature-based and machine learning-based methods, Skype application, which uses encrypted communication on its own P2P network, is known as one of the most difficult traffic to identify. In this paper we propose a novel method to identify Skype application traffic on the fly. The main idea is to setup a list of Skype host information {IP, port} by examining the packets generated in the Skype login process and utilizes the list to identify other Skype traffic. By implementing the identification system and deploying it on our campus network, we proved the performance and feasibility of the proposed method.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.7
• /
• pp.816-822
• /
• 2016

Content-Based image retrieval is a method to search by image features such as local color, texture, and other image content information, which is different from conventional tag or labeled text-based searching. In real life data, the number of images having tags or labels is relatively small, so it is hard to search the relevant images with text-based approach. Existing image search method only based on image feature similarity has limited performance and does not ensure that the results are what the user expected. In this study, we propose and validate a machine learning based approach to improve the performance of the image search engine. We note that when users search relevant images with a query image, they would expect the retrieved images belong to the same category as that of the query. Image classification method is combined with the traditional image feature similarity method. The proposed method is extensively validated on a public PASCAL VOC dataset consisting of 11,530 images from 20 categories.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.38A no.6
• /
• pp.486-491
• /
• 2013

This paper proposes a fast and efficient Haar-like feature selection algorithm for training classifier used in object detection. Many features selected by Haar-like feature selection algorithm and existing AdaBoost algorithm are either similar in shape or overlapping due to considering only feature's error rate. The proposed algorithm calculates similarity of features by their shape and distance between features. Fast and efficient feature selection is made possible by removing selected features and features with high similarity from feature set. FERET face database is used to compare performance of classifiers trained by previous algorithm and proposed algorithm. Experimental results show improved performance comparing classifier trained by proposed method to classifier trained by previous method. When classifier is trained to show same performance, proposed method shows 20% reduction of features used in classification.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.36C no.12
• /
• pp.36-46
• /
• 1999

As the requirements of embedded systems increase, the design complexity of the system becomes higher. The formal design methodology is required which supports well-balanced specification for control and dataflow to design a complex system. In this paper, control modules and function modules are separately described with FSMs and dataflow graphs respectively, and integrated into a system specification via inter-model communications. In previous approaches, the system could not be verified until control modules and dataflow modules are combined at the final design stage. However our approach enables us to design each part as the proper model of computation at early stage, and to verify the compositions and to co-synthesize the system effectively in the same framework. Especially this paper focuses on the communication protocols between control and dataflow models. Preliminary experiments show practicality of the proposed technique.

• Journal of the Economic Geographical Society of Korea
• /
• v.12 no.3
• /
• pp.277-290
• /
• 2009

This paper aims to draw essential facts of network city, to analyze the urban corridor in South-East region, Korea, as a network city. Firstly, the characteristics of the network city is examined theoretically. The global economy is developing an innovative class of network cities. A network cities evolve when two or more previously independent cities, potentially complementary in function, strive to cooperate and achieve significant scope economies aided by-fast and reliable transport and communications infrastructure. Network Cities place a higher priority on knowledge-based activities like research, education and the creative arts. Each constituting city stands to benefit from the synergies of interactive growth via reciprocity, knowledge exchange and unexpected creativity. Secondly, we discussed the network structure of cities in South-East region, Korea itself intensively. We survey the network location and outline of the urban corridor in South-East region, spatial specialization and interaction between the constituting cities. We also discussed the problems of the network cities in South-East region, Korea and introduced the desirable policies and alternatives. We can ascertain from the case study of cities in South-East region that the cities in South-East region corresponds the network city model fairly.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.42 no.5
• /
• pp.1110-1116
• /
• 2017

Depending on the operating characteristics, track circuit is installed for the purpose of direct or indirect control of the signal device, point switch machine and other security device. These are mainly used for train detection, transmission of information, broken rail detection and transmission of return current. Especially, the return current is related to signal system, power system and catenary line, and track circuit systems. It is one of the most important component shall be dealt for the safety of track side staff and for the protection of railway-related electrical system according to electrification. Therefore, an accurate analysis of the return current is needed to prevent the return current unbalance and the system induced disorder and failure due to an over current condition. Also, if the malfunction occurred by the return current harmonics, it can cause problems including train operation interruption. In this paper, we presented measurement and analysis method at return current and it's harmonics by high speed train operation on the honam high speed line.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.33 no.6B
• /
• pp.456-468
• /
• 2008

In this paper, we design Input/Output modules as a preference work for implementation of hybrid two stage AWG based WDM-PON and verify operations of each function modules through the logic simulation. This WDM-PON system provides service to 128 ONUs through 32 wavelength and one wavelength is shared for upstream transmission with four ONU while each wavelength is allocated to each ONU for downstream transmission. The designed WDM-PON MAC chip is based on sub-MAC which consists of one control unit and reception unit and four transmission unit. To design the reception and transmission unit of sub-MAC, we define the functions of the sub-MAC, pins of the modules, control signal and timing of each signal. We intend to design MAC chip with 1Gbps transmission rate. Thus the designed MAC chip is worked on 125MHz clock rate. We define FSM and design Input/Output modules with VHDL. The logic simulation of the modules is executed by the ModelSIM simulator.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39C no.9
• /
• pp.811-819
• /
• 2014

Activity recognition is a key component in identifying the context of a user for providing services based on the application such as medical, entertainment and tactical scenarios. Instead of applying numerous sensor devices, as observed in many previous investigations, we are proposing the use of smartphone with its built-in multimodal sensors as an unobtrusive sensor device for recognition of six physical daily activities. As an improvement to previous works, accelerometer, gyroscope and magnetometer data are fused to recognize activities more reliably. The evaluation indicates that the IBK classifier using window size of 2s with 50% overlapping yields the highest accuracy (i.e., up to 99.33%). To achieve this peak accuracy, simple time-domain and frequency-domain features were extracted from raw sensor data of the smartphone.