• Journal of the Korea Safety Management & Science
• /
• v.23 no.4
• /
• pp.93-104
• /
• 2021

In this paper, we propose a method for diagnosing overload and working load of collaborative robots through performance analysis of machine learning algorithms. To this end, an experiment was conducted to perform pick & place operation while changing the payload weight of a cooperative robot with a payload capacity of 10 kg. In this experiment, motor torque, position, and speed data generated from the robot controller were collected, and as a result of t-test and f-test, different characteristics were found for each weight based on a payload of 10 kg. In addition, to predict overload and working load from the collected data, machine learning algorithms such as Neural Network, Decision Tree, Random Forest, and Gradient Boosting models were used for experiments. As a result of the experiment, the neural network with more than 99.6% of explanatory power showed the best performance in prediction and classification. The practical contribution of the proposed study is that it suggests a method to collect data required for analysis from the robot without attaching additional sensors to the collaborative robot and the usefulness of a machine learning algorithm for diagnosing robot overload and working load.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.41 no.10
• /
• pp.11-16
• /
• 2004

This paper proposes the overload reduction method for the connection information audit processor in ATM switch. Based on this method, we design the simple IPC exchange method and non-stop auditing method for IPC loss. We evaluate the performance about the proposed Audit method. At the result of evaluation, we figure out that the p개posed audit method reduces the load of call control processor because of a fewer IPC and prevent stopping audit function for IPC loss because of requesting the lost connection information again. Therefore, we confirm that the proposed audit method can reestablish a Mismatched connection information with a little load and elevate correctness about audit function.

• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.957-958
• /
• 2006

PC users could experience some inconvenience when they use their PC that was physically connected to network printers shared by other people in the network due to the overload. This paper shows how to resolve this kind of overload problem and established the embedded printer system based on embedded Linux system which performs the printer server in order for any users in the office to do printing work more smoothly via current network. It's own capabilities and functions were verified throughout the various tests in practical environment.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.59 no.3
• /
• pp.506-514
• /
• 2010

Defense systems are needed to prevent catastrophic failures of a power grid due to cascaded events. Cascaded events can be occurred by power flow overload. Especially, it is the most dangerous problem that overload line is outage, because it can make the power system face danger of cascaded. In this paper, vulnerability evaluation for monitoring wide are outage is proposed using by configuration information of transmission systems. This method of vulnerability evaluation is considered direct effect and indirect effect of power flow, especially overload. What is more, it can be used when the configuration of power system changes, as simple fault occurs or maintenance of facility. In the case studies, the estimation and simulation network have been testified and analysed in PSSE and C programming.

• Proceedings of the KIEE Conference
• /
• 2001.11c
• /
• pp.268-271
• /
• 2001

This paper presents observer-based on-line overload monitoring scheme for a PMSM(Permanent Magnet Synchronous Motor) drive system. Proposed scheme is to monitor overload status of motor drive system at remote place. The drive system is previously installed on main system and has no communication function. Proposed scheme consists of intelligent sensing head and monitoring part. Intelligent sensing head acquire motor 3-Phase currents and transmit data to monitoring part over serial communication interface. Monitoring part estimates motor speed using state observer. By comparing estimated speed with reference speed, we can detect motor fault. In this scheme observed information must coded and transmitted over a digital communication channel with finite capacity. We consider communication constraint as time delay and we design discrete-time observer. The proposed scheme is tested on the actual drive system.

• Journal of Veterinary Clinics
• /
• v.34 no.2
• /
• pp.98-102
• /
• 2017

A 7-year-old, intact, female Siberian husky presented with vomiting and diarrhea after a fight with a dog with which it lived. The bitch was diagnosed with pyometra and severe dehydration. The patient received IV fluid therapy for 2 day pre- and post-operatively. Four days post-surgery, the patient had a decreased level of consciousness and suffered a tonic-clonic generalized seizure. On magnetic resonance imaging and histopathological findings, a diagnosis of laminar cortical necrosis caused by fluid overload was made. This case provides important information on the potential for fluid overload in a dehydrated patient giving rise to critical condition and death.

• Journal of Information Technology Applications and Management
• /
• v.28 no.5
• /
• pp.61-70
• /
• 2021

With the proliferation of smartphones and 5G networks, mobile social network service (SNS) has become an indispensable part of people's daily lives. However, with the use of SNS, fatigue and withdrawal behavior gradually emerged. Based on The Transactional Theory of Stress and Coping (TTSC), we explored the mechanism of SNS overload on users' discontinuous intention under the framework of "stressor-strain-outcome". And we also investigated the moderating effects of gender in this process. We hope that through our research, we can help SNS users to reduce unnecessary fatigue, and provide better suggestions for platform designers to adjust product design to improve user experience.

• Proceedings of the Korea Contents Association Conference
• /
• 2006.11a
• /
• pp.503-506
• /
• 2006

The amounts of information and services are rapidly increasing. This causes inefficiency of retrievals of information overload problem. To overcome this kind of problems, This article suggests Odin system, keyword suggestion system based on Thesaurus. Odin system will suggest appropriate search-words and this leads to the user's satisfied result.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2005.11a
• /
• pp.415-424
• /
• 2005

The rapid growth of blog has caused information overload where bloggers in the virtual community space are no longer able to effectively choose the blogs they are exposed to. Recommender systems have been widely advocated as a way of coping with the problem of information overload in e-business environment. Collaborative Filtering (CF) is the most successful recommendation method to date and used in many of the recommender systems. Therefore, we propose a CF-based recommender system for bloggers in the virtual community space. Our proposed methodology consists of three main phases: In the first phase, we apply the "Interest Value" to a recommender system. The Interest Value is a quantity value about user preference in virtual community, and can measure the opinion of users accurately. Next phase, we generate the neighborhood group based on the Interest Value. In the final phase, we use the Community Likeness Score (CLS) to generate the top-n recommendation list. The methodology is explained step by step with an illustrative example and is verified with real data of a blog service provider.

• Journal of Computing Science and Engineering
• /
• v.1 no.1
• /
• pp.31-55
• /
• 2007

Contemporary end-servers and network-routers rely on traffic shaping to deal with server overload and network congestion. Although such traffic shaping provides a means to mitigate the effects of server overload and network congestion, the lack of cooperation between end-servers and network-routers results in waste of network resources. To remedy this problem, we design, implement, and evaluate NetDraino, a novel mechanism that extends the existing queue-management schemes at routers to exploit the link congestion information at downstream end-servers. Specifically, NetDraino distributes the servers' traffic-shaping rules to the congested routers. The routers can then selectively discard those packets-as early as possible-that overloaded downstream servers will eventually drop, thus saving network resources for forwarding in-transit packets destined for non-overloaded servers. The functionality necessary for servers to distribute these filtering rules to routers is implemented within the Linux iptables and iproute2 architectures. Both of our simulation and experimentation results show that NetDraino significantly improves the overall network throughput with minimal overhead.