• Nuclear Engineering and Technology
• /
• v.54 no.10
• /
• pp.3620-3630
• /
• 2022

The diagnosis of abnormalities in a nuclear power plant is essential to maintain power plant safety. When an abnormal event occurs, the operator diagnoses the event and selects the appropriate abnormal operating procedures and sub-procedures to implement the necessary measures. To support this, abnormality diagnosis systems using data-driven methods such as artificial neural networks and convolutional neural networks have been developed. However, data-driven models cannot always guarantee an accurate diagnosis because they cannot simulate all possible abnormal events. Therefore, abnormality diagnosis systems should be able to detect their own potential misdiagnosis. This paper proposes a rulebased diagnostic validation algorithm using a previously developed two-stage diagnosis model in abnormal situations. We analyzed the diagnostic results of the sub-procedure stage when the first diagnostic results were inaccurate and derived a rule to filter the inconsistent sub-procedure diagnostic results, which may be inaccurate diagnoses. In a case study, two abnormality diagnosis models were built using gated recurrent units and long short-term memory cells, and consistency checks on the diagnostic results from both models were performed to detect any inconsistencies. Based on this, a re-diagnosis was performed to select the label of the second-best value in the first diagnosis, after which the diagnosis accuracy increased. That is, the model proposed in this study made it possible to detect diagnostic failures by the developed consistency check of the sub-procedure diagnostic results. The consistency check process has the advantage that the operator can review the results and increase the diagnosis success rate by performing additional re-diagnoses. The developed model is expected to have increased applicability as an operator support system in terms of selecting the appropriate AOPs and sub-procedures with re-diagnosis, thereby further increasing abnormal event diagnostic accuracy.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.12
• /
• pp.3904-3922
• /
• 2022

As a research hotspot, pedestrian detection has a wide range of applications in the field of computer vision in recent years. However, current pedestrian detection methods have problems such as insufficient detection accuracy and large models that are not suitable for large-scale deployment. In view of these problems mentioned above, a lightweight pedestrian detection and early warning method using a new model called you only look once (Yolov5) is proposed in this paper, which utilizing advantages of Yolov5s model to achieve accurate and fast pedestrian recognition. In addition, this paper also optimizes the loss function of the batch normalization (BN) layer. After sparsification, pruning and fine-tuning, got a lot of optimization, the size of the model on the edge of the computing power is lower equipment can be deployed. Finally, from the experimental data presented in this paper, under the training of the road pedestrian dataset that we collected and processed independently, the Yolov5s model has certain advantages in terms of precision and other indicators compared with traditional single shot multiBox detector (SSD) model and fast region-convolutional neural network (Fast R-CNN) model. After pruning and lightweight, the size of training model is greatly reduced without a significant reduction in accuracy, and the final precision reaches 87%, while the model size is reduced to 7,723 KB.

• Journal of the Korea Society for Simulation
• /
• v.19 no.4
• /
• pp.51-58
• /
• 2010

SIP is a flexible and extensible call setup protocol that may be combined with other protocols used in the Internet to make various services like voice communication. Voice communication can be classified into normal calls used for communication between common users and emergency calls for 112, 119 and other services through public safety networks. It is required to research to process effectively these normal calls and emergency calls through public networks such as the Internet. In this paper, we propose a bypass scheme for emergency calls by giving priority to INVITE messages for them and processing them with priority in the SIP proxy queue. We perform simulation studies using the network simulator ns-2 for the performance evaluation. Simulation results show that the proposed scheme processes emergency calls faster than normal calls and thus it is expected to make a special purpose network like the national disaster network efficiently by using the existing Internet.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.667-669
• /
• 2021

Recently, RFID/USN technology has been applied in various fields such as logistics, environment, education, home network, disaster prevention, military, and medical care, but despite the remarkable development of RFID/USN technology, it is difficult to apply it to marine industry due to the characteristics of poor marine environment. Therefore, satellites are mainly used in the marine sector, and existing communication networks are used in the coast, so measures for forming a shelf-only short-range network in the ocean are being considered. In this paper, we consider the use of drones as mobile base stations of USN as a base station role using USN in existing PS-LTE and LTE networks.Since autonomous navigation vessels are aiming for the intelligent system, the number of crew and labor force should be reduced and the function of autonomous network formation in the form of more stable and intelligent ICT convergence technology should be strengthened.

• The Journal of Korean Institute of Next Generation Computing
• /
• v.13 no.5
• /
• pp.51-70
• /
• 2017

The reliability of broadcasting over vehicular ad hoc networks (VANETs) is one of the most critical factors for driving safety applications. There exists limitations to improve the reliability of broadcast transmissions in saturated VANETs where previous proposals in literature tackle the problem by heuristically adapting the size of the contention window (CW). This paper considers improving the reliability by proposing a new probability model based on the counting methods of permutations and combinations, which counts all the possible cases of broadcast failures in a single-hop broadcast transmission for a given CW. From the model, we calculate the best CW size given the number of contention nodes, which significantly improves the reliability and satisfying the timely dissemination of emergency broadcasting messages. Through extensive VANET simulations with varying densities, we show that our model maintains near 100 percent success rate for single-hop broadcast as well as multi-hop broadcast (e.g. 40 hops) and achieves minimal broadcast delay.

• International conference on construction engineering and project management
• /
• 2020.12a
• /
• pp.455-462
• /
• 2020

Noise which is unwanted sound is a serious pollutant that can affect human health, as well as the working and living environment if exposed to humans. However, current noise management on the construction project is generally conducted after the noise exceeds the regulation standard, which increases the conflicts with inhabitants near the construction site and threats to the safety and productivity of construction workers. To overcome the limitations of the current noise management methods, the activities of construction equipment which is the main source of construction noise need to be managed throughout the construction period in real-time. Therefore, this paper proposed a framework for automatically detecting noise sources in construction sites in real-time based on convolutional neural networks (CNNs) according to the following four steps: (i) Step 1: Definition of the noise sources; (ii) Step 2: Data preparation; (iii) Step 3: Noise source classification using the audio CNN; and (iv) Step 4: Noise source detection using the visual CNN. The short-time Fourier transform (STFT) and temporal image processing are used to contain temporal features of the audio and visual data. In addition, the AlexNet and You Only Look Once v3 (YOLOv3) algorithms have been adopted to classify and detect the noise sources in real-time. As a result, the proposed framework is expected to immediately find construction activities as current noise sources on the video of the construction site. The proposed framework could be helpful for environmental construction managers to efficiently identify and control the noise by automatically detecting the noise sources among many activities carried out by various types of construction equipment. Thereby, not only conflicts between inhabitants and construction companies caused by construction noise can be prevented, but also the noise-related health risks and productivity degradation for construction workers and inhabitants near the construction site can be minimized.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.11 no.5
• /
• pp.15-26
• /
• 2012

Government agencies including the national police agency have executed diverse efforts including continuous improvements of traffic facilities and operation methods, education, enforcements in order to improve traffic operation systems; nevertheless there have been continuous criticisms on irrationality in traffic signal and road facility operation. One of the reasons may be the lack of systematic preliminary evaluations on various alternatives. However, there was no appropriate tool to evaluate the mobility and safety of thus alternatives in a systematic way. Therefore, this study proposes the systematic use of microscopic traffic simulation models as a comprehensive evaluation tool. In addition, this study verified the potential of using a microscopic traffic simulation model using the case of operating an overlap phase on a shared-left-turn lane through a systematic way where the evaluation was conducted through data collection, building networks, calibrating microscopic simulation models, producing performance measures, evaluating mobility and safety, and so on. As a result, the operation of overlap phase on a shared-left-turn lane showed no big difference from other operation scenarios such as leading left-turn on exclusive left turn lane in terms of mobility. However the operation of overlap phase on a shared-left-turn lane decreased safety by increasing potential conflicts.

• Journal of the Korea Society for Simulation
• /
• v.24 no.4
• /
• pp.1-9
• /
• 2015

As the use of software is more wider in the safety-critical nuclear fields, so study to improve safety and quality of the software has been actively carried out for more than the past decade. In the nuclear power plant, nuclear man-machine interface systems (MMIS) performs the function of the brain and neural networks of human and consists of fully digitalized equipments. Therefore, errors in the software for nuclear MMIS may occur an abnormal operation of nuclear power plant, can result in economic loss due to the consequential trip of the nuclear power plant. Verification and validation (V&V) is a software-engineering discipline that helps to build quality into software, and the nuclear industry has been defined by laws and regulations to implement and adhere to a through verification and validation activities along the software lifecycle. V&V is a collection of analysis and testing activities across the full lifecycle and complements the efforts of other quality-engineering functions. This study propose a methodology based on V&V activities and related tool-chain to improve quality for software in the nuclear power plant. The optimized methodology consists of a document evaluation, requirement traceability, source code review, and software testing. The proposed methodology has been applied and approved to the real MMIS project for Shin-Hanul units 1&2.

• The KIPS Transactions:PartC
• /
• v.14C no.6
• /
• pp.537-544
• /
• 2007

A home network is a residential local area network in which digital home appliances are connected with each other. Applying the mobile agent technology to the home network is expected to provide a new computing model. In particular, mobility and asynchronous ability of mobile agent can be used to reduce network traffic generated for managing home appliances. However, in order to apply the mobile agent concept to the home network, access control for mobile agents is necessary. In the existing home network system, there is one special server, sometimes called home server This server generally has mapping tables to be updated periodically, which describes access control lists between users' authorities and corresponding devices. In this paper, we propose a role-based access control framework with mobile agents in home networks. This framework, called Secure KAgent framework, is designed and implemented based on KAgent system. It has two main characteristics: to control access permissions based on Role-Based Access Control(RBAC) scheme and to safety assign roles to mobile agents by role tickets.

• The KIPS Transactions:PartC
• /
• v.16C no.2
• /
• pp.165-182
• /
• 2009

Mobile IPv6 spends considerable bandwidth considering that its signal volume is proportional to the mobile and also it should be strengthened to support the binding signal volume, the traffic, and effective mobility. So, the study in NEMO(Network Mobility), an extended version of Mobile IPv6, has been conducted. NEMO provides its mobility by putting several mobiles and more than one portable router into one unit called as mobile network. Because nodes access Internet via the portable router at this time, it receives transparency without any additional work and that much reduces binding signal while solving binding storm. By supporting mobility, NEMO is able to have various mobile structures which realize several networks hierarchically and it is necessary to improve its safety and security by authenticating among the upper networks or the lower ones while moving. Also, it is extremely required to begin a study in the device to improve efficiency accompanied with mobility, which is executed by the fast hand-off as well as the safe authentication. For those reasons, this paper not only classifies various NEMO mobile scenarios into 7 ways, but also provides AAA authentication of each scenario, the authentication through the safety authentication and fast handoff authentication using F+HMIPv6 and the way to reduce both signaling volume and packet delays efficiently during the handoff.