• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.756-760
• /
• 2005

By development of a robot technology, personal robot is being developed very actively. Various infra-technologies are accumulated in hardware and software how by internal a lot of research and development efforts, and it is circumstance that actual commodity is announced. But, personal robot is applied to be acting near human, and takes charge of safety and connected directly a lot of works of home security, gas-leakage, fire-warning facilities, or/and etc. So personal robot must do safe and stable action even if any unexpected accidents are happened, important functions are always operated. In this paper, we are wished to show design structures for supporting fault-tolerant operation from our real-time robot middleware viewpoint. Personal robot, in being developed, was designed by module structure to do to interconnect and to interoperate among each module that is mutually implemented by each research facilities or company. Also, each modules can use appreciate network system that is fit for handling and communicating its data. To guarantee this, we have being developed a real-time network middleware, for especially personal robot. Recent our working is to add and to adjust some functions like connection management, distributed routing mechanism, remote object management, and making platform independent robot application execution environment with self-moving of robot application, for fault-tolerant personal robot.

• The KIPS Transactions:PartA
• /
• v.13A no.4 s.101
• /
• pp.317-322
• /
• 2006

The development of RFID system is increasing rapidly by applying to variety fields recently. Especially, RFID system is used to the focus technology of the supply chain management in distribution field of the supplier. In distribution field, We have to grasp products quickly and correctly, but this has a problem to make an inventory of products in real-time because of products transfer. In this paper, to solve this problems. We grasp the state of inventory in real-time by using EPC-IS network becoming the organizational standard of RFID network. also, We offer an authentation of product service to grasp counterfeits and stolen goods in real-time. Therefore, in this paper, We show to be able to process an authentation of product service and inventory of products in distribution field in real-time.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2003.05b
• /
• pp.90-95
• /
• 2003

For the safety driving of an automobile which is become individual requisites, a new Neural Network algorithm which recognized the load vehicles in real time is proposed. The proposed neural network technique is the real time computation method through the inter-node diffusion. In the network, a node corresponds to a state in the quantized input space. Each node is composed of a processing unit and fixed weights from its neighbor nodes as well as its input terminal. The most reliable algorithm derived for real time recognition of vehicles, is a dynamic programming based algorithm based on sequence matching techniques that would process the data as it arrives and could therefore provide continuously updated neighbor information estimates. Through several simulation experiments, real time reconstruction of the nonlinear image information is processed. 1-D LIPN hardware has been composed and various experiments with static and dynamic signals have been implemented.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.592-597
• /
• 2003

In this paper, some differential geometric conditions for the observer using a recurrent neural network are provided in terms of a stochastic nonlinear system control. In the stochastic nonlinear system, it is necessary to make an additional condition for observation of stochastic nonlinear system, called perfect filtering condition. In addition, we provide a observer using a recurrent neural network for the observation of a stochastic nonlinear system with the proposed observation conditions. Computer simulation shows that the control performance of the stochastic nonlinear system with a observer using a recurrent neural network satisfying the proposed conditions is more efficient than the conventional observer as Kalman filter

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2002.05a
• /
• pp.491-494
• /
• 2002

The real-time industrial network often referred to as fieldbus, is an important element for building automated manufacturing systems. Thus, in order to satisfy the real-time requirements of field devices such as sensors, actuators, and controllers. numerous standard organizations and vendors have developed various fieldbus protocols such as Profibus, WorldFIP and Foundation Fieldbus. However, the application of fieldbus has been limited due to the high cost of hardware and the difficulty in interfacing with multi-vendor products. In order to solve these problems, the computer network technology, especially Ethernet (IEEE 802.3), is being adopted lo the industrial environment. The crucial technical obstacle for Ethernet is that its non-deterministic behavior makes it inadequate for industrial applications where real-time data such as control command and alarm signal hale to be delivered within a certain time limit. Recently, the development of switched Ethernet shows a very promising prospect for industrial application due to the elimination of uncertainties in the network operation resulting in much improved performance. This paper focuses on the application of the switched Ethernet for industrial comm unications.

• Journal of Institute of Control, Robotics and Systems
• /
• v.10 no.8
• /
• pp.718-725
• /
• 2004

The real-time industrial network, often referred to as fieldbus, is an important element for intelligent manufacturing systems. Thus, in order to satisfy the real-time requirements of field devices, numerous fieldbus protocols have been announced. But, the application of fieldbus has been limited due to the high cost of hardware and the difficulty in interfacing with multi-vendor products. Therefore, as an alternative to fieldbus, the computer network technology, especially Ethernet (IEEE 802.3), is being adapted to the industrial environment. However, the crucial technical obstacle for Ethernet is its non-deterministic behavior that makes it inadequate for industrial applications where real-time data have to be delivered within a certain time limit. Recently, the development of switched Ethernet shows a very promising prospect for industrial application due to the elimination of uncertainties in the network operation resulting in much improved performance. This paper focuses on the application of the switched Ethernet with cascade structure for industrial communications. More specifically, this paper presents an analytical performance evaluation of switched Ethernet with cascade structure, and a case study about networked control system.

• Journal of Institute of Control, Robotics and Systems
• /
• v.10 no.2
• /
• pp.197-203
• /
• 2004

A real-time network in a distributed control system plays an important role for the reliable data transmission. Compared to the field-buses used in the past, TCP/IP protocol on the top of Ethered provides a compatibility between applications as well as an economical method to develop softwares. This paper proposes a modified TCP/IP structure for IEEE-1394 network, with which asynchronous and isochronous data transmission is selectively used for the real-time data transmission in a distributed control system. This paper also shows the performance of the proposed protocol by experiments.

• Journal of Computing Science and Engineering
• /
• v.9 no.2
• /
• pp.108-117
• /
• 2015

Interrupt handling is generally separated from process scheduling. This can lead to a scheduling anomaly and priority inversion. The processor can interrupt a higher priority process that is currently executing, in order to handle a network packet reception interruption on behalf of its intended lower priority receiver process. We propose a new network interrupt handling scheme that combines interrupt handling with process scheduling and the priority of the process. The proposed scheme employs techniques to identify the intended receiver process of an incoming packet at an earlier phase. We implement a prototype system of the proposed scheme on Linux 2.6, and our experiment results show that the prototype system supports the predictable real-time behavior of higher priority processes even when excessive traffic is sent to lower priority processes.

• International Journal of Computer Science & Network Security
• /
• v.24 no.4
• /
• pp.1-10
• /
• 2024

In the era of big data, the growth of e-commerce transactions brings forth both opportunities and risks, including the threat of data theft and fraud. To address these challenges, an automated real-time fraud detection system leveraging machine learning was developed. Four algorithms (Decision Tree, Naïve Bayes, XGBoost, and Neural Network) underwent comparison using a dataset from a clothing website that encompassed both legitimate and fraudulent transactions. The dataset exhibited an imbalance, with 9.3% representing fraud and 90.07% legitimate transactions. Performance evaluation metrics, including Recall, Precision, F1 Score, and AUC ROC, were employed to assess the effectiveness of each algorithm. XGBoost emerged as the top-performing model, achieving an impressive accuracy score of 95.85%. The proposed system proves to be a robust defense mechanism against fraudulent activities in e-commerce, thereby enhancing security and instilling trust in online transactions.

• Journal of Information Processing Systems
• /
• v.18 no.3
• /
• pp.428-442
• /
• 2022

A reliable automatic passenger counting (APC) system is a key point in transportation related to the efficient scheduling and management of transport routes. In this study, we introduce a lightweight head detection network using deep learning applicable to an embedded system. Currently, object detection algorithms using deep learning have been found to be successful. However, these algorithms essentially need a graphics processing unit (GPU) to make them performable in real-time. So, we modify a Tiny-YOLOv3 network using certain techniques to speed up the proposed network and to make it more accurate in a non-GPU environment. Finally, we introduce an APC system, which is performable in real-time on embedded systems, using the proposed head detection algorithm. We implement and test the proposed APC system on a Samsung ARTIK 710 board. The experimental results on three public head datasets reflect the detection accuracy and efficiency of the proposed head detection network against Tiny-YOLOv3. Moreover, to test the proposed APC system, we measured the accuracy and recognition speed by repeating 50 instances of entering and 50 instances of exiting. These experimental results showed 99% accuracy and a 0.041-second recognition speed despite the fact that only the CPU was used.