• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권2호
• /
• pp.327-347
• /
• 2024

Edge computing is frequently employed in the Internet of Vehicles, although the computation and communication capabilities of roadside units with edge servers are limited. As a result, to perform distributed machine learning on resource-limited MEC systems, resources have to be allocated sensibly. This paper presents an Improved MADDPG algorithm to overcome the current IoV concerns of high delay and limited offloading utility. Firstly, we employ the MADDPG algorithm for task offloading. Secondly, the edge server aggregates the updated model and modifies the aggregation model parameters to achieve optimal policy learning. Finally, the new approach is contrasted with current reinforcement learning techniques. The simulation results show that compared with MADDPG and MAA2C algorithms, our algorithm improves offloading utility by 2% and 9%, and reduces delay by 29.6%.

• 대한기계학회논문집A
• /
• 제22권1호
• /
• pp.1-15
• /
• 1998

In this paper, thermo-viscoplastic finite element analysis of the effect of tool edge radius on cutting process are performed. The thermo-viscoplastic cutting model is capable of dealing with free chip geometry and chip-tool contact length. The coupling with thermal effects is also considered. Orthogonal cutting experiments are performed for 0.2% carbon steel with tools having 3 different edge radii and the tool forces are measured. The experimental results are discussed in comparison with the results of the FEM analysis. From the study, we confirm that this cutting model can well be applied to the cutting process considered the tool edge radius and that a major causes of the "size effect" is the tool edge radius. With numerical analysis, the effects of the tool edge radius on the stress distributions in workpiece, the temperature distributions in workpiece and tool, and the chip shape are investigated.estigated.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.273-273
• /
• 2000

We present a new scheme to increase the performance of edge-preserving image smoothing from the parameter tuning of a Markov random field (MRF) function. The method is based on automatic control of the image smoothing-strength in MRF model ing in which an introduced parameter function is based on control of enforcing power of a discontinuity-adaptive Markov function and edge magnitude resulted from discontinuities of image intensity. Without any binary decision for the edge magnitude, adaptive control of the enforcing power with the full edge magnitude could improve the performance of discontinuity-preserving image smoothing.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권11호
• /
• pp.2903-2923
• /
• 2023

Knowledge recommendation is a type of recommendation system that recommends knowledge content to users in order to satisfy their needs. Although using graph neural networks to extract data features is an effective method for solving the recommendation problem, there is information loss when modeling real-world problems because an edge in a graph structure can only be associated with two nodes. Because one super-edge in the hypergraph structure can be connected with several nodes and the effectiveness of knowledge graph for knowledge expression, a dual-channel hypergraph convolutional neural network model (DCHC) based on hypergraph structure and knowledge graph is proposed. The model divides user data and knowledge data into user subhypergraph and knowledge subhypergraph, respectively, and extracts user data features by dual-channel hypergraph convolution and knowledge data features by combining with knowledge graph technology, and finally generates recommendation results based on the obtained user embedding and knowledge embedding. The performance of DCHC model is higher than the comparative model under AUC and F1 evaluation indicators, comparative experiments with the baseline also demonstrate the validity of DCHC model.

• 전자통신동향분석
• /
• 제37권5호
• /
• pp.44-53
• /
• 2022

The Internet of Things (IoT) is growing exponentially, with the number of IoT devices multiplying annually. Accordingly, the paradigm is changing from cloud computing to edge computing and even tiny edge computing because of the low latency and cost reduction. Machine learning is also shifting its role from the cloud to edge or tiny edge according to the paradigm shift. However, the fragmented and resource-constrained features of IoT devices have limited the development of artificial intelligence applications. Edge MLaaS (Machine Learning as-a-Service) has been studied to easily and quickly adopt machine learning to products and overcome the device limitations. This paper briefly summarizes what Edge MLaaS is and what element of research it requires.

• Ocean Systems Engineering
• /
• 제6권3호
• /
• pp.217-231
• /
• 2016

This paper presents a new approach for underwater image analysis using the bi-dimensional empirical mode decomposition (BEMD) technique and the phase congruency information. The BEMD algorithm, fully unsupervised, it is mainly applied to texture extraction and image filtering, which are widely recognized as a difficult and challenging machine vision problem. The phase information is the very stability feature of image. Recent developments in analysis methods on the phase congruency information have received large attention by the image researchers. In this paper, the proposed method is called the EP model that inherits the advantages of the first two algorithms, so this model is suitable for processing underwater image. Moreover, the receiver operating characteristic (ROC) curve is presented in this paper to solve the problem that the threshold is greatly affected by personal experience when underwater image edge detection is performed using the EP model. The EP images are computed using combinations of the Canny detector parameters, and the binaryzation image results are generated accordingly. The ideal EP edge feature extractive maps are estimated using correspondence threshold which is optimized by ROC analysis. The experimental results show that the proposed algorithm is able to avoid the operation error caused by manual setting of the detection threshold, and to adaptively set the image feature detection threshold. The proposed method has been proved to be accuracy and effectiveness by the underwater image processing examples.

• 한국기계가공학회지
• /
• 제19권8호
• /
• pp.35-42
• /
• 2020

In discharge machining, material is removed by electrical discharge between the electrode and the workpiece. An important consideration in EDM is that the wear of the electrodes decreases the final precision of the workpiece. The edge wear of the electrodes proceeds very quickly because sparks occur more frequently at the edges with high local electrical strength. In this study, mold steel was discharged with a wedge-shaped graphite electrode to measure the edge wear of the electrode according to the depth. The electrode edge wear increased with depth during EDM and a wear model was developed. The model predicted that the edge wear can be reduced by approximately 70% using two electrodes instead of a single electrode. The model was supported by the experimental comparison of the dual electrode method and the single electrode method.

• Journal of Platform Technology
• /
• 제11권3호
• /
• pp.3-11
• /
• 2023

실시간 관제 시스템은 IoT, 이동통신과 같은 기반 기술의 발달과 공장관리, 차량 운행 체크 등 실시간성이 중요시되는 서비스가 증가함에 따라 급격히 성장하고 있다. 이 시스템의 시간적 민감성을 높이기 위해 다양한 솔루션이 제시되어 왔으나, 현재 대부분의 실시간 관제 시스템은 관제소 등에 위치한 로컬 서버와 다수의 클라이언트로 구성되어 있고, 이들은 다양한 단계를 거쳐 관제 시스템이 위치한 로컬 서버로 전송되고, 그 대응 역시 동일한 단계를 거쳐 진행되는 등 기존 네트워크 및 시스템의 구조적 한계가 있다. 본 논문에서는 실시간 관제 시스템 중 하나인 버스 정보 시스템이 정보를 수집한 시점에서 사용자에게 해당 정보를 제공하기까지 소모되는 시간을 줄일 수 있는 엣지 컴퓨팅 기반 실시간 관제 모델을 제안하였다. 기존 모델과 엣지 컴퓨팅 모델을 시뮬레이션 한 결과, 엣지 컴퓨팅 모델은 사용자에게 데이터를 전송하기 위한 코스트가 기존 모델에 비해 최소 10% 에서 최대 80%까지 감소함을 확인하였다.

• Journal of the Optical Society of Korea
• /
• 제20권3호
• /
• pp.381-388
• /
• 2016

The performance of a staring infrared imaging system can be characterized based on estimating the modulation transfer function (MTF). The slant edge method is a widely used MTF estimation method, which can effectively solve the aliasing problem caused by the discrete undersampling of the infrared focal plane array. However, the traditional slant edge method has some limitations such as the low precision of the edge angle extraction and using the approximate function to fit the edge spread function (ESF), which affects the accuracy of the MTF estimation. In this paper, we propose a modified slant edge method, including an edge angle extraction method that can improve the precision of the edge angle extraction and an ESF fitting algorithm which is based on the transfer function model of the imaging system, to enhance the accuracy of the MTF estimation. This modified slant edge method presents higher estimation accuracy and better immunity to noise and edge angle than other traditional methods, which is demonstrated by the simulation and application experiments operated in our study.

• 정보저장시스템학회논문집
• /
• 제2권3호
• /
• pp.184-188
• /
• 2006

In recent years the flying height of the head/slider has been decreasing in order to increase the recording density of hard disk drive (HDD). Accordingly, it was predicted that direct contact between slider and disk surface (slider slap) can cause defects on the disk such as scratch and particle generation. In this work, we theoretically demonstrate the effect of rounded-edge slider using Hertzian contact theory. Depth and width of scratch were predicted by plowing model. Furthermore, as we fabricated rounded-edge slider, rounded-edge slider was tested and compared with sharp-edge slider. The experimental results show rounded-edge was effective for reducing scratch depth.