• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.6
• /
• pp.2282-2303
• /
• 2021

To solve the problems of heavy computing load and system transmission pressure in energy internet (EI), we establish a three-tier cloud-edge integrated EI network based on a cloud-edge collaborative computing to achieve the tradeoff between energy consumption and the system delay. A joint optimization problem for resource allocation and task offloading in the threetier cloud-edge integrated EI network is formulated to minimize the total system cost under the constraints of the task scheduling binary variables of each sensor node, the maximum uplink transmit power of each sensor node, the limited computation capability of the sensor node and the maximum computation resource of each edge server, which is a Mixed Integer Non-linear Programming (MINLP) problem. To solve the problem, we propose a joint task offloading and resource allocation algorithm (JTOARA), which is decomposed into three subproblems including the uplink transmission power allocation sub-problem, the computation resource allocation sub-problem, and the offloading scheme selection subproblem. Then, the power allocation of each sensor node is achieved by bisection search algorithm, which has a fast convergence. While the computation resource allocation is derived by line optimization method and convex optimization theory. Finally, to achieve the optimal task offloading, we propose a cloud-edge collaborative computation offloading schemes based on game theory and prove the existence of Nash Equilibrium. The simulation results demonstrate that our proposed algorithm can improve output performance as comparing with the conventional algorithms, and its performance is close to the that of the enumerative algorithm.

• International journal of advanced smart convergence
• /
• v.12 no.2
• /
• pp.56-66
• /
• 2023

The goal of deep learning is to extract complex features from multidimensional data use the features to create models that connect input and output. Deep learning is a process of learning nonlinear features and functions from complex data, and the user data that is employed to train deep learning models has become the focus of privacy concerns. Companies that collect user's sensitive personal information, such as users' images and voices, own this data for indefinite period of times. Users cannot delete their personal information, and they cannot limit the purposes for which the data is used. The study has designed a deep learning method that employs privacy protection technology that uses distributed collaborative learning so that multiple participants can use neural network models collaboratively without sharing the input datasets. To prevent direct leaks of personal information, participants are not shown the training datasets during the model training process, unlike traditional deep learning so that the personal information in the data can be protected. The study used a method that can selectively share subsets via an optimization algorithm that is based on modified distributed stochastic gradient descent, and the result showed that it was possible to learn with improved learning accuracy while protecting personal information.

• Journal of the Korean Society of Industry Convergence
• /
• v.26 no.1
• /
• pp.211-215
• /
• 2023

In this paper, the stability and effectiveness of the force control with a 6-axis compliance device are verified by performing comparative experiments with a commercial F/T sensor. The position/force control algorithm based on the Cartesian stiffness of a compliance device is briefly introduced and the design result of a 6-axis compliance device with F/T sensing is presented. The comparative experiments show that the force control using a compliance device is much more stable than that with rigid F/T sensor due to the enough compliance of a compliance device larger than robot positional resolution.

• Architectural research
• /
• v.7 no.2
• /
• pp.23-33
• /
• 2005

The use of computers in architectural professions has grown with the power of easy data management, increased sophistication of standalone applications, inexpensive hardware, improved speed of processing, use of standard library and tools for communication and collaboration. Recently, there has been a growing interest in distributed CAAD (Computer-Aided Architectural Design) integration due to the needs of direct collaboration among project participants in different locations, and Internet is becoming the optimal tool for collaboration among participants in architectural design and construction projects. The aim of this research is to provide a new paradigm for a CAAD system by combining research on integrated CAAD applications with recent collaboration technologies. To accomplish this research objective, interactive three-dimensional (3D) design tools and applications running on the Web have been developed for an Internet-based distributed CAAD application system, specifically designed to meet the requirements of the architectural design process. To this end, two different scopes of implementation are evaluated: first, global architecture and the functionality of a distributed CAAD system; and, second, the association of an architectural application to the system.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.264-267
• /
• 2022

Recently, federated learning (FL) has increased prominence as a viable approach for enhancing user privacy and data security by allowing collaborative multi-party model learning without exchanging sensitive data. Despite this, most present FL systems still depend on a centralized aggregator to generate a global model by gathering all submitted models from users, which could expose user privacy and the risk of various threats from malicious users. To solve these issues, we suggested a safe FL framework that employs differential privacy to counter membership inference attacks during the collaborative FL model training process and empowers blockchain to replace the centralized aggregator server.

• The Journal of the Korea Contents Association
• /
• v.15 no.2
• /
• pp.529-541
• /
• 2015

Collaborative learning of collective intelligence-based model is also ideal in higher education did not yet consensus still in the theoretical level. To become collective intelligence-based collaborative learning is to mobilize the competence of the various members should be promoted as much as possible with their own services designed to actively participate in and contribute to the goals of the joint. Is still based collaborative learning model of collective intelligence, which does the actual model is not developed in education is a key program in creative fusion judge called talent. The evolution of the main features of the house just in shaping the content of a modern lecture geureohagi need to check from time to time to see and pay attention. As part of this study, attempts were associated with the tvN planning and attention to trying connector Executive Lecture show "Creative Club 199" content. Well oriented intention to converge the needs of the times, but it is even more compelling naeeotda implement the collective intelligence based on 'how' the reality is that together with the participants.

• Journal of Digital Convergence
• /
• v.15 no.2
• /
• pp.115-120
• /
• 2017

Online reputation systems for social network services(SNS) aggregate users' feedback and estimate the reputation of contents or providers. The aim of this research is to enhance credibility of the online reputation system on the SNS based e-Commerce(we called it as social commerce). SNS users usually refer to evaluations from other users who bought the products before. Most social commerce sites provide reputation system to help their customer make a decision, but sometimes we can't believe the reputation because the reputation is too subjective and the seller can deceive the customer for sales promotion. Threrefore, we usually use just the average value to show the general customer's evaluation result. We applied collaborative filtering method to give more weighting to the users who have evaluated correctly in the past. As a result, we could get more accurate evaluation results by considering each customers' credibility value that was computed by collaborative filtering.

• Journal of Digital Convergence
• /
• v.16 no.7
• /
• pp.243-248
• /
• 2018

The most important factor for collaborative learning to be effective is the selection of tools that constitute groups. Grouping is to facilitate collaborative learning, learners form groups based on various characteristics. If a group of students fails to form properly due to the selection of the wrong tools, problems can arise where complaints from students can lead to lectures and the effects of learning. In this paper, we have implemented a group of configuration tools that considered improving learning effects and diagnosing bulling tendency. We have proposed a group composition tool that can take into consideration the learning effect and also diagnose the tendency of the bullring by constructing the group according to the teacher's preference by inputting the class preference and the student's grade through the sociometry survey. We expect that the teacher will be able to grasp the students' friendship in advance and cope with the bulling that can happen in the class, as well as the cooperative learning that can lead the class to improve the learning effect.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.6
• /
• pp.173-178
• /
• 2022

Recently, a recommendation system using deep learning in social network services has been actively studied. However, in the case of a recommendation system using deep learning, the cold start problem and the increased learning time due to the complex computation exist as the disadvantage. In this paper, the user-tailored exercise routine recommendation algorithm is proposed using the user's metadata. Metadata (the user's height, weight, sex, etc.) set as the input of the model is applied to the designed model in the proposed algorithms. The exercise recommendation system model proposed in this paper is designed based on the neural collaborative filtering (NCF) algorithm using multi-layer perceptron and matrix factorization algorithm. The learning proceeds with proposed model by receiving user metadata and exercise information. The model where learning is completed provides recommendation score to the user when a specific exercise is set as the input of the model. As a result of the experiment, the proposed exercise recommendation system model showed 10% improvement in recommended performance and 50% reduction in learning time compared to the existing NCF model.

• Journal of Korea Game Society
• /
• v.21 no.2
• /
• pp.139-150
• /
• 2021

This study analyzed the effectiveness by developing an online program to enhance collaborative problem-solving capabilities for college freshmen using gamification. According to the research results, the operational model of the online program for enhancing collaborative problem-solving capabilities using gamification was presented in five stages: 1 preparation, 2 team building, 3 assessment, 4 feedback, and 5 achievement sharing. The results of the "pre-test" and post T-test of creative problem-solving capabilities, the variables related to creative problem-solving skills, academic challenge, creative thinking ability, and convergence value creation have been significantly improved. What should be discussed in the future is the need to experience collaborative problem solving process online, and to develop game design and platform that can discuss and communicate.