• Proceedings of the KIEE Conference
• /
• 1993.07a
• /
• pp.211-213
• /
• 1993

In this paper, we proposed a design method of self-learning fuzzy logic controller using fuzzy neural network. The parameters of membership function in premise are modified by descent method and also consequent parameters by learning mechanism of animal conditioning theory. The proposed method is applied to pole balancing system in order to confirm the feasibility.

• Korean Management Science Review
• /
• v.11 no.1
• /
• pp.187-196
• /
• 1994

Time-Space-Time(T-S-T) switching network is modeled as a graceful degrading system. Call blocking probability is defined as a measure of performance. Several performance related measures are suggested under the presence of failure. An optimization model is proposed, which determines optimal values of system parameters of the switching network.

• Journal of Internet Computing and Services
• /
• v.2 no.5
• /
• pp.49-58
• /
• 2001

Mobile positioning measurement is the most important technology for Location Based Services in the cellular networks. Generally, we are expecting to use GPS to guarantee high accuracy of the mobile position, A CDMA network-based technique for the Mobile Station position calculation needs to be implemented in the cdma2000 network whether the handsets have GPS or not, The most reliable methods of the network-based location technologies are based on the estimation of time of signal traveling between MS and B18 in a network whose coordinates are identified, Other signal parameters such as the power of the received signal and the signal arrival direction cannot be used as main data for a location system because adoption of only the signal parameters will not meet the FCC requirements, In practice, the estimates of the time of signal propagation between MS and BTS always have errors resulting from low-resolution power of measurements and multi path signal propagation, This paper describes the combined network-based location technology in the cdma2000 1× necessary to meet US FCC requirements. The issues of a calibration table and statistic processing based on the pilot strength as well as combined network-based location technologies(TOA/ TDOA) will help to achieve higher location accuracy than specified in the US FCC Rule.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.1826-1829
• /
• 2005

Recent advancement in wireless communications and electronics has enabled the development of low power sensor network. Wireless sensor network are often used in remote monitoring control applications, health care, security and environmental monitoring. Wireless sensor networks are an emerging technology consisting of small, low-power, and low-cost devices that integrate limited computation, sensing, and radio communication capabilities. Sensor network platform for health care has been designed, fabricated and tested. This system consists of an embedded micro-controller, Radio Frequency (RF) transceiver, power management, I/O expansion, and serial communication (RS-232). The hardware platform uses Atmel ATmega128L 8-bit ultra low power RISC processor with 128KB flash memory as the program memory and 4KB SRAM as the data memory. The radio transceiver (Chipcon CC1000) operates in the ISM band at 433MHz or 916MHz with a maximum data rate of 76.8kbps. Also, the indoor radio range is approximately 20-30m. When many sensors have to communicate with the controller, standard communication interfaces such as Serial Peripheral Interface (SPI) or Integrated Circuit ($I^{2}C$) allow sharing a single communication bus. With its low power, the smallest and low cost design, the wireless sensor network system and wireless sensing electronics to collect health-related information of human vitality and main physiological parameters (ECG, Temperature, Perspiration, Blood Pressure and some more vitality parameters, etc.)

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.58 no.1
• /
• pp.126-131
• /
• 2009

This study was carried out for the reliability of PD(Partial Discharge) pattern recognition. For the pattern recognition, the database for PD was established by use of self-designed insulation defects which occur and were mostly critical in GIS(Gas Insulated Switchgear). The acquired database was analyzed to distinguish patterns by means of PRPD(Phase Resolved Partial Discharge) method and stored to the form with to unite the average amplitude of PD pulse and the number of PD pulse as the input data of neural network. In order to prove the performance of genetic algorithm combined with neural network, the neural networks with trial-and-error method and the neural network with genetic algorithm were trained by same training data and compared to the results of their pattern recognition rate. As a result, the recognition success rate of defects was 93.2% and the neural network train process by use of trial-and-error method was very time consuming. The recognition success rate of defects, on the other hand, was 100% by applying the genetic algorithm at neural network and it took a relatively short time to find the best solution of parameters for optimization. Especially, it could be possible that the scrupulous parameters were obtained by genetic algorithm.

• Journal of Internet Computing and Services
• /
• v.21 no.5
• /
• pp.21-29
• /
• 2020

Accurate estimation of human pose relies on backbone method in which its role is to extract feature map. Up to dated, the method of backbone feature extraction is conducted by the plain convolutional neural networks named by CNN and the residual neural networks named by Resnet, both of which have various architectures and performances. The CNN family network such as VGG which is well-known as a multiple stacked hidden layers architecture of deep learning methods, is base and simple while Resnet which is a bottleneck layers architecture yields fewer parameters and outperform. They have achieved inspired results as a backbone network in human pose estimation. However, they were used then followed by different pose estimation networks named by pose parsing module. Therefore, in this paper, we present a comparison between the plain CNN family network (VGG) and bottleneck network (Resnet) as a backbone method in the same pose parsing module. We investigate their performances such as number of parameters, loss score, precision and recall. We experiment them in the bottom-up method of human pose estimation system by adapted the pose parsing module of openpose. Our experimental results show that the backbone method using VGG network outperforms the Resent network with fewer parameter, lower loss score and higher accuracy of precision and recall.

• Journal of the Korean Society for Precision Engineering
• /
• v.11 no.4
• /
• pp.138-147
• /
• 1994

Performance management of computer networks is intended to improve a given network performance in order for more efficient information exchange between subsystems of an integrated large-scale system. Improtance of performance management is growing as many function of the large- scale system depend on the quality of communication services provided by the network. The role of performance management is to manipulate the adjustable protocol parameters on line so that the network can adapt itself to a dynamic environment. This can be divided into two subtasks : performance evaluation to find how changes in protocol parameters affect the network performance and decision making to detemine the magnitude and direction of parameter adjustment. This paper is the second part of the two papers focusing on conceptual design, development, and evaluation of performance management for token bus networks. This paper specifically deals with the task of decision making which utilizes the principles of stochastic optimization and learning automata. The developed algorithm can adjuxt four timer settings of a token bus protocol based on the result of performance evaluation. The overall performance management has been evaluated for its efficacy on a network testbed.

• International Journal of Computer Science & Network Security
• /
• v.21 no.9
• /
• pp.203-211
• /
• 2021

Image tampering detection and localization have become an active area of research in the field of digital image forensics in recent times. This is due to the widespread of malicious image tampering. This study presents a new method for image tampering detection and localization that combines the advantages of dilated convolution, residual network, and UNET Architecture. Using the UNET architecture as a backbone, we built the proposed network from two kinds of residual units, one for the encoder path and the other for the decoder path. The residual units help to speed up the training process and facilitate information propagation between the lower layers and the higher layers which are often difficult to train. To capture global image tampering artifacts and reduce the computational burden of the proposed method, we enlarge the receptive field size of the convolutional kernels by adopting dilated convolutions in the residual units used in building the proposed network. In contrast to existing deep learning methods, having a large number of layers, many network parameters, and often difficult to train, the proposed method can achieve excellent performance with a fewer number of parameters and less computational cost. To test the performance of the proposed method, we evaluate its performance in the context of four benchmark image forensics datasets. Experimental results show that the proposed method outperforms existing methods and could be potentially used to enhance image tampering detection and localization.

• Smart Structures and Systems
• /
• v.28 no.6
• /
• pp.799-810
• /
• 2021

When monitoring the structural integrity of a bridge using data collected through accelerometers, identifying the profile of the load exerted on the bridge from the vehicles passing over it becomes a crucial task. In this study, the speed and location of vehicles on the deck of a bridge is reconfigured using real-time video to implicitly associate the load applied to the bridge with the response from the bridge sensors to develop an image-based deep learning network model. Instead of directly measuring the load that a moving vehicle exerts on the bridge, the intention in the proposed method is to replace the correlation between the movement of vehicles from CCTV images and the corresponding response by the bridge with a neural network model. Given the framework of an input-output-based system identification, CCTV images secured from the bridge and the acceleration measurements from a cantilevered beam are combined during the process of training the neural network model. Since in reality, structural damage cannot be induced in a bridge, the focus of the study is on identifying local changes in parameters by adding mass to a cantilevered beam in the laboratory. The study successfully identified the change in the material parameters in the beam by using the deep-learning neural network model. Also, the method correctly predicted the acceleration response of the beam. The proposed approach can be extended to the structural health monitoring of actual bridges, and its sensitivity to damage can also be improved through optimization of the network training.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.44 no.6
• /
• pp.1-10
• /
• 2007

This paper presents a direct nonlinear multivariable self-tuning PID controller using neural network which adapts to the changing parameters of the nonlinear multivariable system with noises and time delays. The nonlinear multivariable system is divided linear part and nonlinear part. The linear controller are used the self-tuning PID controller that can combine the simple structure of a PID controllers with the characteristics of a self-tuning controller, which can adapt to changes in the environment. The linear controller parameters are obtained by the recursive least square. And the nonlinear controller parameters are achieved the through the Back-propagation neural network. In order to demonstrate the effectiveness of the proposed algorithm, the computer simulation results are presented to adapt the nonlinear multivariable system with noises and time delays and with changed system parameter after a constant time. The proposed PID type nonlinear multivariable self-tuning method using neural network is effective compared with the conventional direct multivariable adaptive controller using neural network.