• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.5
• /
• pp.193-204
• /
• 2019

The explosion of data due to the improvement of sensor technology and computing performance has become the basis for analyzing the situation in the industrial fields, and various attempts to detect events based on such data are increasing recently. In particular, sound signals collected from sensors are used as important information to classify events in various application fields as an advantage of efficiently collecting field information at a relatively low cost. However, the performance of sound-event classification in the field cannot be guaranteed if noise can not be removed. That is, in order to implement a system that can be practically applied, robust performance should be guaranteed even in various noise conditions. In this study, we propose a system that can classify the sound event after generating the enhanced sound signal based on the deep learning algorithm. Especially, to remove noise from the sound signal itself, the enhanced sound data against the noise is generated using SEGAN applied to the GAN with a VAE technique. Then, an end-to-end based sound-event classification system is designed to classify the sound events using the enhanced sound signal as input data of CNN structure without a data conversion process. The performance of the proposed method was verified experimentally using sound data obtained from the industrial field, and the f1 score of 99.29% (railway industry) and 97.80% (livestock industry) was confirmed.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.5
• /
• pp.2313-2318
• /
• 2012

With the widely applications of tactical radio networks, end-to-end secure speech communication in the heterogeneous network has become a very significant security issue. High-grade end-to-end speech security can be achieved using encryption algorithms at user ends. However, the use of encryption techniques results in a problem that encrypted speech data cannot be directly transmitted over heterogeneous tactical networks. That is, the decryption and re-encryption process must be fulfilled at the gateway between two different networks. In this paper, in order to solve this problem and to achieve optimal end-to-end speech security for heterogeneous tactical environments, we propose a novel mechanism for end-to-end secure speech transmission over ultra high frequency (UHF) and public switched telephone network (PSTN) and evaluate against the performance of conventional mechanism. Our proposed mechanism has advantages of no decryption and re-encryption at the gateway, no processing delay at the gateway, and good inter-operability over UHF and PSTN.

• Journal of Communications and Networks
• /
• v.4 no.2
• /
• pp.108-117
• /
• 2002

TCP, which was developed on the basis of wired links, supposes that packet losses are caused by network congestion. In a wireless network, however, packet losses due to data corruption occur frequently. Since TCP does not distinguish loss types, it applies its congestion control mechanism to non-congestion losses as well as congestion losses. As a result, the throughput of TCP is degraded. To solve this problem of TCP over wireless links, previous researches, such as split-connection and end-to-end schemes, tried to distinguish the loss types and applied the congestion control to only congestion losses; yet they do nothing for non-congestion losses. We propose a novel transport protocol for wireless networks. The protocol called VS-TCP (Variable Segment size Transmission Control Protocol) has a reaction mechanism for a non-congestion loss. VS-TCP varies a segment size according to a non-congestion loss rate, and therefore enhances the performance. If packet losses due to data corruption occur frequently, VS-TCP decreases a segment size in order to reduce both the retransmission overhead and packet corruption probability. If packets are rarely lost, it increases the size so as to lower the header overhead. Via simulations, we compared VS-TCP and other schemes. Our results show that the segment-size variation mechanism of VS-TCP achieves a substantial performance enhancement.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.24 no.4
• /
• pp.625-634
• /
• 2014

Tactical networks is being operated in configuration that consisting of a variety of characteristics communication equipments and heterogeneous networks. In this configurations, end-to-end communication can be achieved using interworking gateway for converting the data format of the network and using encryption algorithm of the networks. The use of mechanism results in a problem that secure data cannot be transferred directly, reprocessing and processing delay of communication in heterogeneous tactical networks. That is, for encoding and decoding of data, the decryption of encrypted data and re-encryption processing must be required at the gateway between different networks. In this paper proposes to mechanism for end-to-end secure communication in heterogeneous tactical networks. Using the proposed method, end-to-end secure communication between heterogeneous tactical networks(PSTN-UHF networks) which removes the necessity of a gateway for converting data into data formats suitable for network to remove a transmission delay factor and enable real-time voice and data communication and achieve end-to-end security for heterogeneous tactical networks. we propose a novel mechanism for end-to-end secure communication over PSTN and UHF networks and evaluate against the performance of conventional mechanism. Our proposal is confirmed removal of security vulnerabilities, end-to-end secure communication in heterogeneous tactical networks.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.40 no.12
• /
• pp.125-135
• /
• 2003

In this paper, we developmed and implemented router and bandwidth broker that provides end-to-end QoS in differentiated service IP networks. Our design goal is to provide end-to-end premium service using the EF PHB. The bandwidth broker and router were implemented in the FreeBSD 4.6 platform. For the DiffServ router, we implemented QoS daemon, rollback managment routine, monitoring, and COPS-PR client. Also, Ive implemented bandwith broker which has SLS and resource management function, and signaling protocols for interfacing intra-and inter-domain. On the testbed, we have validated and evaluated the performance of the implemented DiffServ router and bandwidth broker using the inter-domain signaling protocol client in MS Windows platform. The test results show that the end-to-end QoS can be guaranteed for the inter-domain diffServ by the implemented system.

• Proceedings of the KIEE Conference
• /
• 2003.11c
• /
• pp.894-897
• /
• 2003

Recently, the rapid growth of mobile radio system has led to an increasing demand of low-cost high performance communication IC's. In this paper, we have designed RF front end for wireless LAN receiver employ zero-IF architecture. A low-noise amplifier (LNA) and double-balanced mixer is included in a front end. The zero-IF architecture is easy to integrate and good for low power consumption, so that is coincided to requirement of wireless LAN. But the zero-IF architecture has a serious problem of large offset. Image-reject mixer is a good structure to solve offset problem. Using offset compensation circuit is good structure, too. The front end is implemented in 0.25 ${\mu}m$ CMOS technology. The front end has a noise figure of 5.6 dB, a power consumption of 16 mW and total gain of 22 dB.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.9 no.6
• /
• pp.689-694
• /
• 2014

DDoS attacks on MANET makes disable any node which support network function, cause critical results as a stopping of entire network service or separation to some parts. Packet aggregation, which gather some pieces of short length into a certain length of data, improves transmission performances on MANETs. In this paper, some effects on transmission performance of packet aggregation transmission be caused by DDoS Attacks are measured and analyzed in point of end-to-end level. MANET simulator, based on NS-2, is used for measurement end-to-end performances. MOS, connection rate, delay and packet loss rate is used as performance parameters. VoIP traffic is used for object service measurement. Finally, it is suggested that number of packet aggregation is more then 4 for keeping the transmission quality over MANETs under DDoS attacks.

• Membrane Journal
• /
• v.13 no.4
• /
• pp.283-290
• /
• 2003

To improve membrane performance, the dead-end and Cross-flow ultrafiltration with or without ultrasound irradiation onto the membrane module were carried out using a BSA protein solution. Intermittent or continuous irradiation of ultrasound effectively suppressed the formation of fouling on membrane or removed the fouling layers from membrane. Effect of ultrasound irradiation on the enhancement of ultrafiltration performance was more increased at the operating conditions which form more membrane fouling (at the operating conditions of higher feed concentration and TMP, and lower flow rate). The permeate flukes were enhanced up to 1.9 times in case of the dead-end ultrafiltration and 1.5 times in case of the cross-flow ultrafiltration by ultrasound irradiation onto the membrane module.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.10B
• /
• pp.1675-1689
• /
• 2000

We present CReMeS a CORBA-compliant design and implementation of a new real-time communication service. It provides for efficient predictable and scalable communication between information producers and consumers. The CReMeS architecture is based on MidART's Real-Time Channel-based Reflective Memory (RT-CRM) abstraction. This architecture supports the separation of QoS specification between producer and consumer of data and employs a user-level scheduling scheme for communicating real-time tasks. These help us achieve end-to-end predictability and allows our service to scale. The CReMeS architecture provides a CORBA interface to applications and demands no changes to the ORB layer and the language mapping layer. Thus it can run on non real-time Off-The-Shelf ORBs enables applications on these ORBs to have scalable and end-to-end predictable asynchronous communication facility. In addition an application designer can select whether to use an out-of-band channel or the ORB GIOP/IIOP for data communication. This permits a trade-off between performance predictability and reliability. Experimental results demonstrate that our architecture can achieve better performance and predictability than a real-time implementation of the CORBA Even Service when the out-of-band channel is employed for data communication it delivers better predictability with comparable performance when the ORB GIOP/IIOP is used.

• Journal of international Conference on Electrical Machines and Systems
• /
• v.1 no.1
• /
• pp.121-127
• /
• 2012

An electric power compensation system for a DC transmission system with an integrated wind turbine generator is proposed. The proposed compensation system consists of a synchronous generator and a duplex reactor. This apparatus is connected to the sending-end circuit of the DC transmission system. A set of steady-state equations of the system is first derived. Then, the effect of the duplex reactor, which can eliminate the sending-end grid current distortion due to commutation of the converter, is explored. The relationships among power at the sending-end circuit are also revealed. It is shown that fluctuations in the sending-end grid power due to changes in wind velocities are compensated with the proposed system. Finally, the effects of the sending-end grid conditions on the steady-state characteristics of the system are studied.