• The Journal of the Korea institute of electronic communication sciences
• /
• v.15 no.3
• /
• pp.465-472
• /
• 2020

Recently, various deep neural networks based methods have been proposed for audio event detection. In this study, we improved the performance of audio event detection by adopting an attention approach to a baseline CRNN. We applied context gating at the input of the baseline CRNN and added an attention layer at the output. We improved the performance of the attention based CRNN by using the audio data of strong labels in frame units as well as the data of weak labels in clip levels. In the audio event detection experiments using the audio data from the Task 4 of the DCASE 2018/2019 Challenge, we could obtain maximally a 66% relative increase in the F-score in the proposed attention based CRNN compared with the baseline CRNN.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.24 no.12B
• /
• pp.2233-2248
• /
• 1999

The TMN that appears to operate the various communication networks generally and efficiently is developed under the different platform environment such as the different hardware and the different operating system. One of the main problems is that all the agents of the TMN system must be duplicated and maintain the software and the data blocks that perform the identical function. Therefore, the standard of the Q3 interface development cannot be defined and the multi-platform cannot be supported in the development of the TMN agent. In order to overcome these problems, the Farming methodology that is based on the Farmer model has been suggested. With the Farming methodology, the software and the data components which are duplicated and stored in each distributed object are saved in the platform independent class repository(PICR) by converting into the format of the independent componentware in the platform, so that the componentwares that are essential for the execution can be loaded and used statically or dynamically from PICR as described in the framework of each distributed object. The distributed TMN agent of the personal communication network is designed and developed by using the Farmer model.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.7 no.3
• /
• pp.532-543
• /
• 2003

In this paper, we proposed structure of a reversible discrete-time cellular neural network (DTCNN) for labeling digital images to protect copylight. First, we present the concept and the structure of reversible DTCNN, which can be used to generate 2D binary pseudo-random images sequences. We presented some, output examples of different kinds of reversible DTCNNs to show their complex behaviors. Then both the original image and the copyright label, which is often another binary image, are used to generate a binary random key image. The key image is then used to scramble the original image. Since the reversibility of a reversible DTCNN, the same reversible DTCNN can recover the copyright label from a labeled image. Due to the high speed of a DTCNN chip, our method can be used to label image sequences, e.g., video sequences, in real time. Computer simulation results are presented.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.4 no.2
• /
• pp.313-322
• /
• 2000

The ATM Forum has been focusing on flow control mechanism for ABR traffic management. The goal of this activity is to efficiently manage the leftover network bandwidth and fairly distribute it among contending ABR VC so that communication links can be optimally utilized. ABR traffic is difficult to predict traffic shape because it has bursts and variable behavior. Also it's sensitive to lose but not to delay. This behavior makes difficult to UPC function in network and cause of congestion in switch, thus performance is degraded. To resolve this problem, various flow control mechanism has been worked in the ATM Forum. Especially, the rate-based flow control mechanism for ABR traffic has been standardized in the ATM Forum, Sept. 1994. Thus, various flow control mechanism has been working which likes EFCI, ER, VS/VD. VS/VD control is superior than existed ER control because it isolate different networks from each other. In this paper, we propose an expanded VS/VD flow control algorithm and compare with existed VS/VD flow control algorithm. Simulation result shows that this algorithm improve a problem in aspect of delay and fairness.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.6 no.2
• /
• pp.371-378
• /
• 2002

In the resent years, the term mobile agent is probably one of the most overused words in many appliable areas of distributed open systems as electronic commerce and electronic data interchange, and it has very different meanings in the area of artificial intelligence, network management, or distributed systems. However, the use of mobile agent adds significant problems, primarily in the area of EC/EDI. Therefore it is very important to control the roaming agents to keep one's privacy or property in distributed open networks. The surge in secure intranets for commercial applications provides a robust, secure environment to which trading partners can increasingly entrust their interactions to some mobile agents. In this paper, we introduce a mechanism to protect mobile agent itself from the malicious server he is visiting and also we introduce a mechanism to protect vital resources of the open systems as internet.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.16 no.5
• /
• pp.38-48
• /
• 2017

Link attributes, such as speed, occupancy, and flow, are essential factors for transportation planning and operation. It is, therefore, one of the most important decision-making problems in intelligent transport system (ITS) to determine the optimal location of a sensor for collecting the information on link attributes. This paper aims to develop a model to determine the optimal location of a sensor to minimize the variability of traffic information on whole networks. To achieve this, a network sensor location model (NSLM) is developed to reflect discrete characteristics of data collection. The variability indices of traffic information are calculated based on the summation of diagonal elements of the variance-covariance matrix. To assess the applicability of the developed model, speed data collected from the dedicated short range communication (DSRC) systems were used in Daegu metropolitan area. The developed model in this study contributes to the enhancement of investment efficiency and the improvement of information accuracy in intelligent transport system (ITS).

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.15 no.5
• /
• pp.85-90
• /
• 2015

Work environments within the firm with a concept of mobile office is growing divided into two sections. It's Wi-Fi FMC(Fixed Mobile Convergence) field Which are implemented in a telephone service available from existing fixed-line service in the center of the smart phones and the EMS(Enterprise Mobility Service) field to make people will be able to handle PC the center of the information system within an enterprise using a smart phone instead of terminal facility connects to a system in the workplace and external. This paper developed FMC controller to allow execution IMS(IP Multi-Media Subsystem) services to complement the issues of the FMC corporation, telephony service associated. The controller includes FMC automatic enrollment services, voice quality enhancement of the mobile phone, anywhere within the firm on his mobile phone calls can provide mobility and is also implemented FMC LCR function that use status information from mobile soft-phone within the IP-PBX.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.13 no.6
• /
• pp.203-210
• /
• 2013

Majority of the wireless ad hoc routing protocols are proposed to find feasible routes without considering the network load, end-to-end link quality and bandwidth requirements of the application. Therefore, protocol may not provide sufficient quality of service (QoS) to a high speed traffic such as multimedia. In this paper, we propose a path-quality and bandwidth-estimation based routing protocol (PBBR) for the high quality multimedia stream that can meet the application's bandwidth requirements and find the best reliable route. The novelty of this protocol is to select a reliable path to respond the application's requirements based on available bandwidth at each intermediate node and end-to-end path loss ratio. Obtained results from the simulation demonstrates that our protocol can achieve sufficient performance in terms of throughput and end-to-end delay.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.13 no.6
• /
• pp.243-248
• /
• 2013

With rapid growth and fast diffusion of smartphone technologies, many users are deeply concerned about the smart applications and many mobile applications converged with various related technologies are rapidly disseminated. Especially, the convergence technologies like mobile apps that can establish the wireless ad hoc network between smartphone and other peripherals and exchange data are appear and progressed continuously. In this paper, we design and implement the smart app using bluetooth based wireless ad hoc sensor network that can connect smartphone with sensors and exchange data for various smart applications. The proposed smart application in this paper collects data obtained from more than 2 multi-sensors in real time and fulfills the decision making function by storing data at the database and analysing it. The smart application designed and implemented in this paper is the healthcare application that can analyze and evaluate the patient's health condition with sensing data from multi-sensors in real time through bluetooth module.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.13 no.6
• /
• pp.229-235
• /
• 2013

This paper proposed the method to reduce and manage the amount of using power by using the Self-Learning of inference engine that evolves through learning increasingly smart ways for each spaces with in the Space-Based Energy Management System (SEMS, Space-based Energy Management System) that is defined as smallest unit space with constant size and similar characteristics by using the collectible Big Data from the various information networks and the informations of various sensors from the existing Energy Management System(EMS), mostly including such as the Energy Management Systems for the Factory (FEMS, Factory Energy Management System), the Energy Management Systems for Buildings (BEMS, Building Energy Management System), and Energy Management Systems for Residential (HEMS, Home Energy Management System), that is monitoring and controlling the power of systems through various sensors and administrators by measuring the temperature and illumination.