• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.4
• /
• pp.671-678
• /
• 2022

Approximate computing is an computational technique that is acceptable degree of inaccurate results of accurate results. Approximate multiplication is one of the approximate computing methods for high-performance and low-power computing. In this paper, we propose a high-density, low-power, and high-speed approximate multiplier using approximate 4-2 compressor and improved full adder. The approximate multiplier with approximate 4-2 compressor consists of three regions of the exact, approximate and constant correction regions, and we compared them by adjusting the size of region by applying an efficient partial product reduction. The proposed approximate multiplier was designed with Verilog HDL and was analyzed for area, power and delay time using Synopsys Design Compiler (DC) on a 25nm CMOS process. As a result of the experiment, the proposed multiplier reduced area by 10.47%, power by 26.11%, and delay time by 13% compared to the conventional approximate multiplier.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.8
• /
• pp.985-992
• /
• 2020

Edge computing is a technology that can prepare for a new era of cloud computing. Edge computing is not a remote data center where data is processed and computed, but low-latency/high-speed computing is realized by adding computing power and data processing power to the edge side close to an access point such as a terminal device or a gateway. It is possible. The types of edge computing include mobile edge computing, fog computing, and cloudlet computing. In this article, we describes existing open source platforms for implementing edge computing nodes. By presenting and comparing the structure, features of open source edge platforms, it is possible to acquire knowledge required to select the best edge platform for industrial engineers who want to build an edge node using an actual open source edge computing platform.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.9
• /
• pp.1538-1544
• /
• 2006

This paper proposes a non-systolic parallel $AB^2+C$ Computing unit based on irreducible AOP order m of $GF(2^m)$. Proposed circuit have only AND gates and EX-OR gates, composes of cyclic shift operation, multiplication operation power operation power-sum operation and addition operation using a merry irreducible AOP. Suggested operating a method have an advantage high speed data processing, low power and integration because of only needs AND gates and EX-OR gates. $AB^2+C$ computing unit has delay-time of $T_A+(1+[log^m_2])T_X$.

• Journal of Computing Science and Engineering
• /
• v.6 no.3
• /
• pp.227-242
• /
• 2012

Vehicular Ad Hoc Networks (VANETs) are highly dynamic and unstable due to the heterogeneous nature of the communications, intermittent links, high mobility and constant changes in network topology. Currently, some of the most important challenges of VANETs are the scalability problem, congestion, unnecessary duplication of data, low delivery rate, communication delay and temporary fragmentation. Many recent studies have focused on a hybrid mechanism to disseminate information implementing the store and forward technique in sparse vehicular networks, as well as clustering techniques to avoid the scalability problem in dense vehicular networks. However, the selection of intermediate nodes in the store and forward technique, the stability of the clusters and the unnecessary duplication of data remain as central challenges. Therefore, we propose an adaptable destination-based dissemination algorithm (DBDA) using the publish/subscribe model. DBDA considers the destination of the vehicles as an important parameter to form the clusters and select the intermediate nodes, contrary to other proposed solutions. Additionally, DBDA implements a publish/subscribe model. This model provides a context-aware service to select the intermediate nodes according to the importance of the message, destination, current location and speed of the vehicles; as a result, it avoids delay, congestion, unnecessary duplications and low delivery rate.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.11
• /
• pp.4065-4083
• /
• 2021

Super-resolution can improve the clarity of low-resolution (LR) images, which can increase the accuracy of high-level compute vision tasks. Portable devices have low computing power and storage performance. Large-scale neural network super-resolution methods are not suitable for portable devices. In order to save the computational cost and the number of parameters, Lightweight image processing method can improve the processing speed of portable devices. Therefore, we propose the Enhanced Information Multiple Distillation Network (EIMDN) to adapt lower delay and cost. The EIMDN takes feedback mechanism as the framework and obtains low level features through high level features. Further, we replace the feature extraction convolution operation in Information Multiple Distillation Block (IMDB), with Ghost module, and propose the Enhanced Information Multiple Distillation Block (EIMDB) to reduce the amount of calculation and the number of parameters. Finally, coordinate attention (CA) is used at the end of IMDB and EIMDB to enhance the important information extraction from Spaces and channels. Experimental results show that our proposed can achieve convergence faster with fewer parameters and computation, compared with other lightweight super-resolution methods. Under the condition of higher peak signal-to-noise ratio (PSNR) and higher structural similarity (SSIM), the performance of network reconstruction image texture and target contour is significantly improved.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.3
• /
• pp.351-355
• /
• 2010

The service which is required wide bandwidth is growing in these days, so building up High Speed communication system is being required. The Task Force team of IEEE 802.3ah set the EPON as a standard; next generation subscriber access network. For offering a high quality service, 10G EPON that is changed from 1Gbps uplink downlink bandwidth to 10Gbps is come up. Although Kramer had studied 10G EPON there was a QoS limitation, when load is low, End-to-End maximum delay is increased. This paper is suggesting time synch ronization method, resource reservation method, band width allocation method. We confirmed that 10EPON was able to offer quality service by the result of the OPNET.