• 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 Digital Contents Society
• /
• v.19 no.5
• /
• pp.963-969
• /
• 2018

Wi-Fi and Bluetooth technologies are perhaps the most prominent examples of wireless communication technologies used in the Internet of Things (IoT) environment. Compared to widely used Wi-Fi, Bluetooth technology has some flaws including 1:1 connection (one-way) between Master and Slave, slow transmission, and limited connection range; Bluetooth is mainly used for connecting audio devices. Since the release of Bluetooth Low Energy (BLE), some of the flaws of Bluetooth technology have been improved but it still failed to become a competitive alternative of Wi-Fi. This paper presents a method of data transmission through broadcasting in BLE and demonstrates its performance, one-to-many data transfer result. The Connection-Free Data Transmission proposed in this paper will hopefully be utilized in special circumstances requiring 1:N data transmission or disaster security network.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.11
• /
• pp.5110-5116
• /
• 2011

In this paper, multiplexing automation system will be proposed for the automobile electromotive mirror using CAN(Controller Area Network) protocol which has been known that it has a high reliability on the signal in the various network protocols. To do this, a master controller and two (input/output) slave controllers (H/W) are being made and application layer (S/W) is being programmed for effective going and communicating between subsystems. The possibility of the effectiveness of application and control ability will be shown when the system has minimum electrical lines by testing the experimental systems which was made up of the automobile electromotive mirror.

• Journal of KIISE:Information Networking
• /
• v.32 no.6
• /
• pp.668-675
• /
• 2005

With the proliferation of wireless network and the advances of the embedded systems, the traditional distributed systems begin to include the wireless embedded systems. Clock synchronization in the distributed systems is one of the major issues that should be considered for diverse Purposes including synchronization, ordering, and consistency. Many clock synchronization algorithms have been proposed over the years. Since clock synchronization in wireless embedded systems should consider the low bandwidth of a network and the poor resources of a system, most traditional algorithms cannot be applied directly. We propose a clock synchronization algorithm in wireless embedded systems, extending IEEE 802.11 standard. The proposed algorithm can not only achieve high precision by loosening constraints and utilizing the characteristics of wireless broadcast but also provide continuous time synchronization by tolerating the message losses. In master/slave structure the master broadcasts the time information and the stave computes the clock skew and the drift to estimate the synchronized time of the master. The experiment results show that the achieved standard deviation by the Proposed scheme is within the bound of about 200 microseconds.

• ETRI Journal
• /
• v.32 no.5
• /
• pp.713-721
• /
• 2010

E-textile technology has earned a great deal of interest in many fields; however, existing wearable network protocols are not optimized for use with conductive yarn. In this paper, some of the basic properties of conductive textiles and requirements on wearable personal area networks (PANs) are reviewed. Then, we present a wearable personal network (WPN), which is a four-layered wearable PAN using bus topology. We have designed the WPN to be a lightweight protocol to work with a variety of microcontrollers. The profile layer is provided to make the application development process easy. The data link layer exchanges frames in a master-slave manner in either the reliable or best-effort mode. The lower part of the data link layer and the physical layer of WPN are made of a fabric serial-bus interface which is capable of measuring bus signal properties and adapting to medium variation. After a formal verification of operation and performances of WPN, we implemented WPN communication modules (WCMs) on small flexible printed circuit boards. In order to demonstrate the behavior of our WPN on a textile, we designed a WPN tutorial shirt prototype using implemented WCMs and conductive yarn.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.922-925
• /
• 2004

Bluetooth technology is essentially a method for wireless connection of a diverse set of devices ranging from PDAs, mobile phone, notebook computers, to another equipments. The bluetooth system supports both point-to-point connection and point-to-multipoint connections. In point-to-multipoint connection, the channel is shared among several bluetooth devices. Two or more devices sharing the same channel form a piconet. There is one master device and up to seven active slave devices in a piconet. The radio operates in the unlicensed 2.45GHz ISM band. This allows users who travel world-wide to use bluetooth equipments anywhere. Since the link is based on frequency-hop spread spectrum, multiple channels can exist at the same time. The Bluetooth standard has been suggested that Bluetooth equipments can be used in the short-range, maximum 100 meters . It has been defined that the time takes to setup and establish a bluetooth connection among devices is 10 seconds. It is a long time and may be a cause to lose a chance of finding other non-fixed devices. We propose a routing protocols for scatternets which can be used to control a mobile units(MUs) in this network. The proposed routing protocol is composed of two kinds of bluetooth information, access point(AP) and MU.

• Journal of Institute of Control, Robotics and Systems
• /
• v.10 no.12
• /
• pp.1233-1240
• /
• 2004

Recently the need for cooperative control among robots is increasing in a variety of industrial robot applications. Such a control framework enhances the efficiency of the real robotic assembly environment along with extending the robot application. In this paper, an ethernet-based cooperative control framework was proposed. The cooperative control of robots can multiply the handling capacity of robot system, and make it possible to implement jigless cooperation, due to realization of trajectory-synchronized movement between a master robot and slave robots. Coordinate transformation was used to relate among robots in a common coordinate. An optimized ethernet protocol of HiNet was developed to maximize the speed of communication and to minimize the error of synchronous movement. The proposed algorithm and optimization of network protocol was tested in several class of robots.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2004.04a
• /
• pp.54-57
• /
• 2004

블루투스는 작은 크기와 저렴한 가격, 표준화된 프로토콜, 저전력 소모 등의 잇점으로 인해 로봇에 응용하기 적합한 무선 기술로 주목받고 있다. 그러나 단일 통신망을 구성하기 위해서는 1：7의 Master/slave 구조와 무선 통신거리 등의 제약사항이 있다. 블루투스를 로봇 시스템에 적용하기 위해서는 주위 환경에 따른 자기 조직화를 통해서 이러한 단점을 보완하고 주위 환경의 변화에 적절하게 대응을 할 수 있도록 하는 네트워크 구성 시스템이 필요하다. 자기 조직화를 하기 위해서는 Discovery, Organization, Maintenance, Reorganization의 크게 4단계의 과정을 거친다. 본 논문에서는 분산 로봇 시스템을 위해 트리구조를 이용한 자기 조직화 가능한 블루투스 네트워크를 구현하고 그 성능을 평가한다.

• Proceedings of the IEEK Conference
• /
• 1999.11a
• /
• pp.412-415
• /
• 1999

In this paper, we describe an implementation of the B-Link bus interface logic for a directory controller and a remote access cash controller in the SCI-based CC-NUMA multimedia server developed by ETRI . The CC-NUMA multimedia server is composed of a number of Pentium III SHV nodes and a SCI interconnection network. To communicate with remote nodes, each node has a CC-Agent which consists of a processor bus interface(PIF). a directory controller(DC), a remote access cash controller(RC), and two SCI 1ink controllers(LCs). The B-Link bus interface logic is developed for a directory controller and a remote access cash controller in order to communicate with a SCI link controller on a B-Link bus. It consists of a sending master controller a receiving slave controller, and asynchronous data buffers. And It performs a self-arbitration, a data packet transmission, a queue allocation, an early terminal ion. and a cut-through data path.

• Proceedings of the KIEE Conference
• /
• 2000.07d
• /
• pp.2542-2544
• /
• 2000

In this paper, CAN(Controller Area Network)is used to solve the wire harness problem in the outside mirror of automobile which has a lot of functions in narrow space. If the number of wires is reduced, it has benefits of lower product cost and maintenance. CAN was originally developed by the German company Robert Bosch for use in the car industry to provide a cost-effective communications bus for in car electronics and as alternative to expensive and cumbersome wiring looms. CAN controller is a serial communication protocol which efficiently supports distributed real-time control with a very high level of security. The communication between master CAN controller and slave CAN controller is realized and controller's performance is tested by experiment.