• The KIPS Transactions:PartB
• /
• v.13B no.4 s.107
• /
• pp.429-438
• /
• 2006

Neural Networks(NNs) are applied for solving a wide variety of nonlinear problems in several areas, such as image processing, pattern recognition etc. Although NN can be simulated by using software, many potential NN applications required real-time processing. Thus they need to be implemented as hardware. The hardware implementation of multi-layer perceptrons(MLPs) in several kind of NNs usually uses a fixed-point arithmetic due to a simple logic operation and a shorter processing time compared to the floating-point arithmetic. However, the fixed-point arithmetic-based MLP has a drawback which is not able to apply the MLP software that use floating-point arithmetic. We propose a design method for MLPs which has the floating-point arithmetic-based fully-pipelining architecture. It has a processing speed that is proportional to the number of the hidden nodes. The number of input and output nodes of MLPs are generally constrained by given problems, but the number of hidden nodes can be optimized by user experiences. Thus our design method is using optimized number of hidden nodes in order to improve the processing speed, especially in field of a repeated processing such as image processing, pattern recognition, etc.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.4B
• /
• pp.360-367
• /
• 2009

In this paper, we propose a design methodology of IEEE 802.11n MAC which aims to achieve the higher throughput of more than 100Mbps in downlink as measured at the MAC-SAP and present the implementation results of MAC using the proposed design methodology. With our proposed methodology, different from the conventional design flow which has the separate codes for the protocol validation, for the network simulation, and for the system implementation, the unified code can be used for the network simulation and the implementation of software and hardware. Our MAC architecture is partitioned into two parts, Upper-layer MAC and Lower-layer MAC, in order to achieve the high efficiency for the new features of IEEE 802.11n standard. They are implemented in software and hardware respectively. The implemented MAC is tested on ARM based FPGA board.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.13 no.6
• /
• pp.1183-1190
• /
• 2018

The environmental regulations are being strengthened all over the world, and the introduction of electric vehicles are actively being considered to cope with them effectively. It is essential to establish a charging infrastructure, which is an essential element of electric vehicle distribution. In this paper, power line communication technology essential for smart charging infrastructure is studied. A control board capable of achieving a physical layer speed of 10Mbps and a TCP/IP layer of 4.5Mbps, which conforms to the ISO/IEC 15118 international standard, and a control board mounted on the board and compliant with international standards. We have developed a software solution to perform functions for linking. In addition, in order to be applied to the combo-type DC fast charger, the hardware was designed to meet the industrial environment standard and the V2G communication module was developed by integrating it with the software solution.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.10
• /
• pp.1279-1286
• /
• 2021

The electrocardiogram (ECG) signal is a good indicator for early diagnosis of heart abnormalities. The ECG signal has a different reference normal signal for each person. And it requires lots of data to diagnosis. In this paper, we propose an adaptive OpenCL-based FPGA-GPU hybrid-layer platform to efficiently accelerate ECG signal diagnosis. As a result of diagnosing 19870 number of ECG signals of MIT-BIH arrhythmia database on the platform, the FPGA accelerator takes 1.15s, that the execution time was reduced by 89.94% and the power consumption was reduced by 84.0% compared to the software execution. The GPU accelerator takes 1.87s, that the execution time was reduced by 83.56% and the power consumption was reduced by 62.3% compared to the software execution. Although the proposed FPGA-GPU hybrid platform has a slower diagnostic speed than the FPGA accelerator, it can operate a flexible algorithm according to the situation by using the GPU.

• Nuclear Engineering and Technology
• /
• v.55 no.4
• /
• pp.1218-1224
• /
• 2023

We investigated the radiation shielding competence for TeO₂-V₂O₅-MoO₃ glasses. The Phy-X software was used to report the radiation shielding parameters for the present glasses. With an increase in TeO₂ and MoO₃ content, the samples' linear attenuation coefficient improves. However, at low energies, this change is more apparent. At low energy, the present samples have an effective atomic number (Z_eff) that is relatively high (in order of 16.17-24.48 at 0.347 MeV). In addition, the findings demonstrated that the density of the samples is a very critical factor in determining the half value layer (HVL). The minimal HVL for each sample can be found at 0.347 MeV and corresponds to 1.776, 1.519, 1.391, 1.210 and 1.167 cm for Te1 to Te5 respectively. However, the highest HVL of these glasses is recorded at 1.33 MeV, which corresponds to 3.773, 3.365, 3.218, 2.925 and 2.908 cm respectively. The tenth value layer results indicate that the thickness of the specimens needs to be increased in order to shield the photons that have a greater energy. Also, the TVL results demonstrated that the sample with the greatest TeO₂ and MoO₃ concentration has a higher capacity to attenuate photons.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.23 no.1
• /
• pp.1-9
• /
• 1986

This is the third part of the four-part paper describing the development of a packet-switched computer communication network named the KORNET. In this paper we describe the design and implementation of the X.25 protocol connecting packet mode data terminal equipments(PDTE's) with data circuit terminating equipments(DCE's). In the KORNET, the X.25 protocol has been implemented on the line processing module-A(LPMA) of the network node processor(NNP). In the implementation of X.25, we have divided the software module according to the service function, and have determined the the rules that interact between the modules. Each layer protocol has been developed using the technique of the finite state machine. Before the actual coding of softwares, we hafve used formal software development tools based on the specification and description language (SDL) and program design languate (PDL) recommended by the CCITT. In addition, for the efficient operation of the X.25 protocol system we have analyzed the system performance and the service scheduling method of each module. The results will also be given.

• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.4
• /
• pp.203-210
• /
• 2017

In this paper, we propose an effective neural network model for image caption generation and model transfer. This model is a kind of multi-modal recurrent neural network models. It consists of five distinct layers: a convolution neural network layer for extracting visual information from images, an embedding layer for converting each word into a low dimensional feature, a recurrent neural network layer for learning caption sentence structure, and a multi-modal layer for combining visual and language information. In this model, the recurrent neural network layer is constructed by LSTM units, which are well known to be effective for learning and transferring sequence patterns. Moreover, this model has a unique structure in which the output of the convolution neural network layer is linked not only to the input of the initial state of the recurrent neural network layer but also to the input of the multimodal layer, in order to make use of visual information extracted from the image at each recurrent step for generating the corresponding textual caption. Through various comparative experiments using open data sets such as Flickr8k, Flickr30k, and MSCOCO, we demonstrated the proposed multimodal recurrent neural network model has high performance in terms of caption accuracy and model transfer effect.

• Steel and Composite Structures
• /
• v.47 no.1
• /
• pp.91-102
• /
• 2023

To study the evaluation standard and control limit of mortar filling layer void length, in this paper, the train sub-model was developed by MATLAB and the track-bridge sub-model considering the mortar filling layer void was established by ANSYS. The two sub-models were assembled into a train-track-bridge coupling dynamic model through the wheel-rail contact relationship, and the validity was corroborated by the coupling dynamic model with the literature model. Considering the randomness of fastening stiffness, mortar elastic modulus, length of mortar filling layer void, and pier settlement, the test points were designed by the Box-Behnken method based on Design-Expert software. The coupled dynamic model was calculated, and the support vector regression (SVR) nonlinear mapping model of the wheel-rail system was established. The learning, prediction, and verification were carried out. Finally, the reliable probability of the amplification coefficient distribution of the response index of the train and structure in different ranges was obtained based on the SVR nonlinear mapping model and Latin hypercube sampling method. The limit of the length of the mortar filling layer void was, thus, obtained. The results show that the SVR nonlinear mapping model developed in this paper has a high fitting accuracy of 0.993, and the computational efficiency is significantly improved by 99.86%. It can be used to calculate the dynamic response of the wheel-rail system. The length of the mortar filling layer void significantly affects the wheel-rail vertical force, wheel weight load reduction ratio, rail vertical displacement, and track plate vertical displacement. The dynamic response of the track structure has a more significant effect on the limit value of the length of the mortar filling layer void than the dynamic response of the vehicle, and the rail vertical displacement is the most obvious. At 250 km/h - 350 km/h train running speed, the limit values of grade I, II, and III of the lengths of the mortar filling layer void are 3.932 m, 4.337 m, and 4.766 m, respectively. The results can provide some reference for the long-term service performance reliability of the ballastless track-bridge system of HRS.

• Journal of Digital Contents Society
• /
• v.19 no.6
• /
• pp.1185-1195
• /
• 2018

Industrial Control System (ICS) is a system that carry out monitoring and controls of industrial control process and is applied in infrastructure such as water, power, and gas. Recently, cyber attacks such as Brutal Kangaroo, Emotional Simian, and Stuxnet 3.0 have been continuously increasing in ICS, and these security risks cause damage of human life and massive financial losses. Attacks on the control layer among the attack methods for ICS can malfunction devices of the field device layer by manipulating control commands. Therefore, in this paper, we propose a mechanism that apply the SDN between the control layer and the field device layer in the industrial control system and to determine whether the control command is legitimate or not and we show simulation results on a simply composed control system.

• Journal of KIISE:Software and Applications
• /
• v.30 no.5_6
• /
• pp.540-549
• /
• 2003

In collaborative recommendation two models are generally used: the user model and the article model. A user model learns correlation between users preferences and recommends an article based on other users preferences for the article. Similarly, an article model learns correlation between preferences for articles and recommends an article based on the target user's preference for other articles. In this paper, we investigates various combination methods of the user model and the article model for better recommendation performance. They include simple sequential and parallel methods, perceptron, multi-layer perceptron, fuzzy rules, and BKS. We adopt the multi-layer perceptron for training each of the user and article models. The multi-layer perceptron has several advantages over other methods such as the nearest neighbor method and the association rule method. It can learn weights between correlated items and it can handle easily both of symbolic and numeric data. The combined models outperform any of the basic models and our experiments show that the multi-layer perceptron is the most efficient combination method among them.