• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.1-25
• /
• 2020

In this paper, we suggest an application system architecture which provides accurate, fast and efficient automatic gasometer reading function. The system captures gasometer image using mobile device camera, transmits the image to a cloud server on top of private LTE network, and analyzes the image to extract character information of device ID and gas usage amount by selective optical character recognition based on deep learning technology. In general, there are many types of character in an image and optical character recognition technology extracts all character information in an image. But some applications need to ignore non-of-interest types of character and only have to focus on some specific types of characters. For an example of the application, automatic gasometer reading system only need to extract device ID and gas usage amount character information from gasometer images to send bill to users. Non-of-interest character strings, such as device type, manufacturer, manufacturing date, specification and etc., are not valuable information to the application. Thus, the application have to analyze point of interest region and specific types of characters to extract valuable information only. We adopted CNN (Convolutional Neural Network) based object detection and CRNN (Convolutional Recurrent Neural Network) technology for selective optical character recognition which only analyze point of interest region for selective character information extraction. We build up 3 neural networks for the application system. The first is a convolutional neural network which detects point of interest region of gas usage amount and device ID information character strings, the second is another convolutional neural network which transforms spatial information of point of interest region to spatial sequential feature vectors, and the third is bi-directional long short term memory network which converts spatial sequential information to character strings using time-series analysis mapping from feature vectors to character strings. In this research, point of interest character strings are device ID and gas usage amount. Device ID consists of 12 arabic character strings and gas usage amount consists of 4 ~ 5 arabic character strings. All system components are implemented in Amazon Web Service Cloud with Intel Zeon E5-2686 v4 CPU and NVidia TESLA V100 GPU. The system architecture adopts master-lave processing structure for efficient and fast parallel processing coping with about 700,000 requests per day. Mobile device captures gasometer image and transmits to master process in AWS cloud. Master process runs on Intel Zeon CPU and pushes reading request from mobile device to an input queue with FIFO (First In First Out) structure. Slave process consists of 3 types of deep neural networks which conduct character recognition process and runs on NVidia GPU module. Slave process is always polling the input queue to get recognition request. If there are some requests from master process in the input queue, slave process converts the image in the input queue to device ID character string, gas usage amount character string and position information of the strings, returns the information to output queue, and switch to idle mode to poll the input queue. Master process gets final information form the output queue and delivers the information to the mobile device. We used total 27,120 gasometer images for training, validation and testing of 3 types of deep neural network. 22,985 images were used for training and validation, 4,135 images were used for testing. We randomly splitted 22,985 images with 8:2 ratio for training and validation respectively for each training epoch. 4,135 test image were categorized into 5 types (Normal, noise, reflex, scale and slant). Normal data is clean image data, noise means image with noise signal, relfex means image with light reflection in gasometer region, scale means images with small object size due to long-distance capturing and slant means images which is not horizontally flat. Final character string recognition accuracies for device ID and gas usage amount of normal data are 0.960 and 0.864 respectively.

• Journal of KIISE:Computing Practices and Letters
• /
• v.13 no.5
• /
• pp.293-299
• /
• 2007

Intelligent pipeline inspection gauges (PIGs) are inspection vehicles that move along within a (gas or oil) pipeline and acquire signals (also called sensor data) from their surrounding rings of sensors. By analyzing the signals captured in intelligent PIGs, we can detect pipeline defects, such as holes and curvatures and other potential causes of gas explosions. There are two major data access patterns apparent when an analyzer accesses the pipeline signal data. The first is a sequential pattern where an analyst reads the sensor data one time only in a sequential fashion. The second is the repetitive pattern where an analyzer repeatedly reads the signal data within a fixed range; this is the dominant pattern in analyzing the signal data. The existing PIG software reads signal data directly from the server at every user#s request, requiring network transfer and disk access cost. It works well only for the sequential pattern, but not for the more dominant repetitive pattern. This problem becomes very serious in a client/server environment where several analysts analyze the signal data concurrently. To tackle this problem, we devise a fast in-memory cache manager, called T-Cache, by considering pipeline sensor data as multiple time-series data and by efficiently caching the time-series data at T-Cache. To the best of the authors# knowledge, this is the first research on caching pipeline signals on the client-side. We propose a new concept of the signal cache line as a caching unit, which is a set of time-series signal data for a fixed distance. We also provide the various data structures including smart cursors and algorithms used in T-Cache. Experimental results show that T-Cache performs much better for the repetitive pattern in terms of disk I/Os and the elapsed time. Even with the sequential pattern, T-Cache shows almost the same performance as a system that does not use any caching, indicating the caching overhead in T-Cache is negligible.

• The KIPS Transactions:PartC
• /
• v.18C no.5
• /
• pp.343-360
• /
• 2011

The objective of this paper is to analyze and characterize to simulate routing observations on end-to-end routing circuits and a ping experiment of a virtual network after modeling, such as IPv6 migration, an OSPFv3 routing experiment based on an IPv6 environment, and a ping experiment for IPv4/IPv6 dual-stack networks and IPv6 network for OSPFv3 routing using IPv6 planning and operations in an OPNET Modeler. IPv6 deployment based largely on the integrated wired and wireless network was one of the research tasks at hand. The previous studies' researchers recommended that future research work be done on the explicit features of both OSPFv3 and EIGRP protocols in the IPv4/IPv6 environment, and more research should be done to explore how to improve the end-to-end IPv6 performance. Also, most related work was performed with an IPv4 environment but lacked studies related to the OSPFv3 virtual network based on an end-to-end IPv6 environment. Hence, this research continues work in previous studies in analyzing IPv6 migration, an OSPFv3 routing experiment based on IPv6, and a ping experiment for IPv4/IPv6 dual-stack networks and IPv6 network for OSPFv3 routing. In the not too distant future, before enabling the default IPv6, it would help to understand network design and deployment based on an IPv6 environment through IPv6 planning and operations for the end-user perspective such as success or failure of connection on IPv6 migration, exploration of an OSPFv3 routing circuit based on an end-to-end IPv6 environment, and a ping experiment for IPv4/IPv6 dual-stack networks and IPv6 network for OSPFv3 routing. We were able to observe an optimal route for modeling of an end-to-end virtual network through simulation results as well as find what appeared to be a fast ping response time VC server to ensure Internet quality of service better than an HTTP server.

• Journal of Broadcast Engineering
• /
• v.16 no.1
• /
• pp.23-32
• /
• 2011

Design and Implementation of Clipcast Service via Terrestrial DMB This paper outlines the system design and the implementation process of clipcast service that can send clips of video, mp3, text, images, etc. to terrestrial DMB terminals. To provide clipcast service in terrestrial DMB, a separate data channel needs to be allocated and this requires changes in the existing bandwidth allocation. Clipcast contents can be sent after midnight at around 3 to 4 AM, when terrestrial DMB viewship is low. If the video service bit rate is lowered to 352 Kbps and the TPEG service band is fully used, then 320 Kbps bit rate can be allocated to clipcast. To enable clipcast service, the terminals' DMB program must be executed, and this can be done through SMS and EPG. Clipcast service applies MOT protocol to transmit multimedia objects, and transmits twice in carousel format for stable transmission of files. Therefore, 72Mbyte data can be transmitted in one hour, which corresponds to about 20 minutes of full motion video service at 500Kbps data rate. When running the clip transmitted through terrestrial DMB data channel, information regarding the length of each clip is received through communication with the CMS(Content Management Server), then error-free files are displayed. The clips can be provided to the users as preview contents of the complete VOD contents. In order to use the complete content, the user needs to access the URL allocated for that specific content and download the content by completing a billing process. This paper suggests the design and implementation of terrestrial DMB system to provide clipcast service, which enables file download services as provided in MediaFLO, DVB-H, and the other mobile broadcasting systems. Unlike the other mobile broadcasting systems, the proposed system applies more reliable SMS method to activate the DMB terminals for highly stable clipcast service. This allows hybrid, i.e, both SMS and EPG activations of terminals for clipcast services.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.9
• /
• pp.595-602
• /
• 2013

WiFi fingerprinting is well known as an effective localization technique used for indoor environments. However, this technique requires a large amount of pre-built fingerprint maps over the entire space. Moreover, due to environmental changes, these maps have to be newly built or updated periodically by experts. As a way to avoid this problem, crowd-sourced fingerprint mapping attracts many interests from researchers. This approach supports many volunteer users to share their WiFi fingerprints collected at a specific environment. Therefore, crowd-sourced fingerprinting can automatically update fingerprint maps up-to-date. In most previous systems, however, individual users were asked to enter their positions manually to build their local fingerprint maps. Moreover, the systems do not have any principled mechanism to keep fingerprint maps clean by detecting and filtering out erroneous fingerprints collected from multiple users. In this paper, we present the design of a crowd-sourced fingerprint mapping and localization(CMAL) system. The proposed system can not only automatically build and/or update WiFi fingerprint maps from fingerprint collections provided by multiple smartphone users, but also simultaneously track their positions using the up-to-date maps. The CMAL system consists of multiple clients to work on individual smartphones to collect fingerprints and a central server to maintain a database of fingerprint maps. Each client contains a particle filter-based WiFi SLAM engine, tracking the smartphone user's position and building each local fingerprint map. The server of our system adopts a Gaussian interpolation-based error filtering algorithm to maintain the integrity of fingerprint maps. Through various experiments, we show the high performance of our system.

• Journal of KIISE:Computer Systems and Theory
• /
• v.33 no.9
• /
• pp.574-584
• /
• 2006

Recently, ISO/IEC 23000 (also known as 'MPEG-A') has proposed a new file format called 'MAF(Multimedia Application File Format)[1]' which provides a capability of integrating/storing the widely-used compression standards for audio and video and the metadata in MPEG-7 form into a single file format. However, it is still very hard to verify the usefulness of MPEG-A in the real applications because there is still no real system that fully implements this standard. In this thesis, a design and implementation of a multimedia retrieval system based on MPEG-A standard on PC and mobile device is presented. Furthermore, an extension of MPEG-A for describing the metadata for video is also proposed. It is selected and defined as a subset of MPEG-7 MDS[4] and TV-anytime[5] for video that is useful and manageable in the mobile environments. In order to design the multimedia retrieval system based on MPEG-A, we define the system requirements in terms of portability, extensibility, compatibility, adaptability, efficiency. Based on these requirements, we design the system which composed of 3 layers: Application Layer, Middleware Layer, Platform Layer. The proposed system consists of two sub-parts, client-part and server-part. The client-part consists of MAF authoring tool, MAP player tool and MAF searching tool which allow users to create, play and search the MAF files, respectively. The server-part is composed of modules to store and manage the MAF files and metadata extracted from MAF files. We show the usefulness of the proposed system by implementing the client system both on MS-Windows platform on desk-top computer and WIPI platform on mobile phone, and validate whether it to satisfy all the system requirements. The proposed system can be used to verify the specification in the MPEG-A, and to proves the usefulness of MPEG-A in the real application.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.2
• /
• pp.81-90
• /
• 2013

During the past decade, many changes and attempts have been tried and are continued developing new technologies in the computing area. The brick wall in computing area, especially power wall, changes computing paradigm from computing hardwares including processor and system architecture to programming environment and application usage. The high performance computing (HPC) area, especially, has been experienced catastrophic changes, and it is now considered as a key to the national competitiveness. In the late 2000's, many leading countries rushed to develop Exascale supercomputing systems, and as a results tens of PetaFLOPS system are prevalent now. In Korea, ICT is well developed and Korea is considered as a one of leading countries in the world, but not for supercomputing area. In this paper, we describe architecture design of MAHA supercomputing system which is aimed to develop 300 TeraFLOPS system for bio-informatics applications like human genome analysis and protein-protein docking. MAHA supercomputing system is consists of four major parts - computing hardware, file system, system software and bio-applications. MAHA supercomputing system is designed to utilize heterogeneous computing accelerators (co-processors like GPGPUs and MICs) to get more performance/$, performance/area, and performance/power. To provide high speed data movement and large capacity, MAHA file system is designed to have asymmetric cluster architecture, and consists of metadata server, data server, and client file system on top of SSD and MAID storage servers. MAHA system softwares are designed to provide user-friendliness and easy-to-use based on integrated system management component - like Bio Workflow management, Integrated Cluster management and Heterogeneous Resource management. MAHA supercomputing system was first installed in Dec., 2011. The theoretical performance of MAHA system was 50 TeraFLOPS and measured performance of 30.3 TeraFLOPS with 32 computing nodes. MAHA system will be upgraded to have 100 TeraFLOPS performance at Jan., 2013.

• Journal of Intelligence and Information Systems
• /
• v.20 no.2
• /
• pp.163-178
• /
• 2014

Following research proposes "Virtualization of Smart Cards (ViSCa)" which is a security system that aims to provide a multi-device platform for the deployment of services that require a strong security protocol, both for the access & authentication and execution of its applications and focuses on analyzing Virtualization of Smart Cards (ViSCa) platform-based mobile payment service by comparing with other similar cases. At the present day, the appearance of new ICT, the diffusion of new user devices (such as smartphones, tablet PC, and so on) and the growth of internet penetration rate are creating many world-shaking services yet in the most of these applications' private information has to be shared, which means that security breaches and illegal access to that information are real threats that have to be solved. Also mobile payment service is, one of the innovative services, has same issues which are real threats for users because mobile payment service sometimes requires user identification, an authentication procedure and confidential data sharing. Thus, an extra layer of security is needed in their communication and execution protocols. The Virtualization of Smart Cards (ViSCa), concept is a holistic approach and centralized management for a security system that pursues to provide a ubiquitous multi-device platform for the arrangement of mobile payment services that demand a powerful security protocol, both for the access & authentication and execution of its applications. In this sense, Virtualization of Smart Cards (ViSCa) offers full interoperability and full access from any user device without any loss of security. The concept prevents possible attacks by third parties, guaranteeing the confidentiality of personal data, bank accounts or private financial information. The Virtualization of Smart Cards (ViSCa) concept is split in two different phases: the execution of the user authentication protocol on the user device and the cloud architecture that executes the secure application. Thus, the secure service access is guaranteed at anytime, anywhere and through any device supporting previously required security mechanisms. The security level is improved by using virtualization technology in the cloud. This virtualization technology is used terminal virtualization to virtualize smart card hardware and thrive to manage virtualized smart cards as a whole, through mobile cloud technology in Virtualization of Smart Cards (ViSCa) platform-based mobile payment service. This entire process is referred to as Smart Card as a Service (SCaaS). Virtualization of Smart Cards (ViSCa) platform-based mobile payment service virtualizes smart card, which is used as payment mean, and loads it in to the mobile cloud. Authentication takes place through application and helps log on to mobile cloud and chooses one of virtualized smart card as a payment method. To decide the scope of the research, which is comparing Virtualization of Smart Cards (ViSCa) platform-based mobile payment service with other similar cases, we categorized the prior researches' mobile payment service groups into distinct feature and service type. Both groups store credit card's data in the mobile device and settle the payment process at the offline market. By the location where the electronic financial transaction information (data) is stored, the groups can be categorized into two main service types. First is "App Method" which loads the data in the server connected to the application. Second "Mobile Card Method" stores its data in the Integrated Circuit (IC) chip, which holds financial transaction data, which is inbuilt in the mobile device secure element (SE). Through prior researches on accept factors of mobile payment service and its market environment, we came up with six key factors of comparative analysis which are economic, generality, security, convenience(ease of use), applicability and efficiency. Within the chosen group, we compared and analyzed the selected cases and Virtualization of Smart Cards (ViSCa) platform-based mobile payment service.

• Journal of Broadcast Engineering
• /
• v.10 no.1 s.26
• /
• pp.43-56
• /
• 2005

In the existing broadcasting environment, it is not easy to serve the bi-directional service between a broadcasting server and a TV audience. In the uni-directional broadcasting environments, almost TV programs are scheduled depending on the viewers' popular watching time, and the advertisement contents in these TV programs are mainly arranged by the popularity and the ages of the audience. The audiences make an effort to sort and select their favorite programs. However, the advertisement programs which support the TV program the audience want are not served to the appropriate audiences efficiently. This randomly provided advertisement contents can occur to the audiences' indifference and avoidance. In this paper, we propose the target advertisement service for the appropriate distribution of the advertisement contents. The proposed target advertisement service estimates the audience's profile without any issuing the private information and provides the target-advertised contents by using his/her estimated profile. For the experimental results, we used the real audiences' TV usage history such as the ages, fonder and time of the programs from AC Neilson Korea. And we show the accuracy of the proposed target advertisement service algorithm. NDS (Normalized Distance Sum) and the Vector correlation method, and implementation of our target advertisement service system.

• Journal of KIISE:Information Networking
• /
• v.29 no.3
• /
• pp.286-298
• /
• 2002

The Remote Procedure Call(RPC) has been traditionally used for Inter Process Communication(IPC) among precesses in distributed computing environment. As distributed applications have been complicated more and more, the Mobile Agent paradigm for IPC is emerged. Because there are some paradigms for IPC, researches to evaluate and compare the performance of each paradigm are issued recently. But the performance models used in the previous research did not reflect real distributed computing environment correctly, because they did not consider the evacuation elements for providing security services. Since real distributed environment is open, it is very vulnerable to a variety of attacks. In order to execute applications securely in distributed computing environment, security services which protect applications and information against the attacks must be considered. In this paper, we evaluate and compare the performance of the Remote Procedure Call with that of the Mobile Agent in IPC paradigms. We examine security services to execute applications securely, and propose new performance models considering those services. We design performance models, which describe information retrieval system through N database services, using Petri Net. We compare the performance of two paradigms by assigning numerical values to parameters and measuring the execution time of two paradigms. In this paper, the comparison of two performance models with security services for secure communication shows the results that the execution time of the Remote Procedure Call performance model is sharply increased because of many communications with the high cryptography mechanism between hosts, and that the execution time of the Mobile Agent model is gradually increased because the Mobile Agent paradigm can reduce the quantity of the communications between hosts.