• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.11 no.6
• /
• pp.645-650
• /
• 2018

Software stability is the possibility of operating without any malfunction in the operating environment over time. In a finite failure NHPP for software failure analysis, the failure occurrence rate may be constant, monotonically increasing, or monotonically decreasing. In this study, based on the NHPP model and based on the software failure time data, we compared and analyzed the attributes of the software development cost model using the exponential distribution Rayleigh distribution and inverse exponential distribution considering the shape parameter of the Weibull distribution as the life distribution. The results of this study show that the Rayleigh model is the fastest release time and has the economic cost compared to the inverse-exponential model and the Goel-Okumoto model. Using the results of this study, it can be expected that software developers and operators will be able to predict the optimal release time and economic development cost.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.10a
• /
• pp.221-223
• /
• 2016

Currently in the automobile market, models with many convenient functions combined with IT have been released. This change has a strength that there could be many convenient and useful functions related to driving while flaws of vehicles caused by malfunctions of these electronic equipments could trigger serious incidents. Among them, the sudden unintended acceleration considered as the most serious is a serious flaw that could threaten driver's life. However, the causes for sudden acceleration incidents have not been clearly investigated with no coping measures. As manufacturers shift the responsibility to drivers' carelessness, drivers' burden is continuously increasing. Thus, this paper designed the system to cope with sudden acceleration incidents by changing conditions of controlling parts like accelerator and brake, and internal image of the driver's seat into data through the integrated module.

• Journal of Digital Convergence
• /
• v.17 no.9
• /
• pp.147-152
• /
• 2019

Infrastructure is rapidly growing as Internet business grows with the latest IT technologies such as IoT, BigData, and AI. However, in most companies, a limited number of people need to manage a lot of hardware and software. Therefore, Polestar Enterprise Management System(PEMS) is applied to monitor the system operation status, IT service and key KPI monitoring. Real-time monitor screening prevents system malfunctions and quick response. With PEMS, you can see configuration information related to IT hardware and software at a glance, and monitor performance throughout the entire end-to-end period to see when problems occur in real time.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.213-215
• /
• 2021

With the development of IoT technology, various technologies such as artificial intelligence and automation are being grafted into industrial sites, and accordingly, the importance of data processing is increasing. In particular, a system based on a digital image may cause a malfunction due to noise in the image due to a sensor defect or a communication environment problem. Therefore, research on image processing has been continued as a pre-processing process, and an effective noise reduction technique is required depending on the type of noise and the characteristics of the image. In this paper, we propose a modified spatial weight filter to protect edge components in the impulse noise reduction process. The proposed algorithm divides the filtering mask into four regions and calculates the standard deviation of each region. The final output was filtered by applying a spatial weight to the region with the lowest standard deviation value. Simulation was conducted to evaluate the performance of the proposed algorithm, and it showed superior impulse noise reduction performance compared to the existing method.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.1
• /
• pp.163-169
• /
• 2020

Recently, research on automation and unmanned operation of machines in the industrial field has been conducted with the advent of AI, Big data, and the IoT, which are the core technologies of the Fourth Industrial Revolution. The machines for these automation processes are controlled based on the data collected from the sensors attached to them, and further, the processes are managed. Conventionally, the abnormalities of sensors are periodically checked and managed. However, due to various environmental factors and situations in the industrial field, there are cases where the inspection due to the failure is not missed or failures are not detected to prevent damage due to sensor failure. In addition, even if a failure occurs, it is not immediately detected, which worsens the process loss. Therefore, in order to prevent damage caused by such a sudden sensor failure, it is necessary to identify the failure of the sensor in an embedded system in real-time and to diagnose the failure and determine the type for a quick response. In this paper, a deep neural network-based fault diagnosis system is designed and implemented using Raspberry Pi to classify typical sensor fault types such as erratic fault, hard-over fault, spike fault, and stuck fault. In order to diagnose sensor failure, the network is constructed using Google's proposed Inverted residual block structure of MobilieNetV2. The proposed scheme reduces memory usage and improves the performance of the conventional CNN technique to classify sensor faults.

• Journal of the Institute of Convergence Signal Processing
• /
• v.12 no.2
• /
• pp.133-138
• /
• 2011

In IP-based wireless sensor networks (WSNs), it might be necessary to distribute application updates to the sensor nodes in order to fix bugs or add new functionality. However, physical access to nodes is in many cases extremely limited following deployment. Therefore, network reprogramming protocols have recently emerged as a way to distribute application updates without requiring physical access to sensor nodes. In order to solve the network reprogramming problem over the air interface, this thesis presents a new scheme for new update code propagation using fragmentation scheme and network coding. The proposed code propagation method roughly shows reduced performance improvement in terms of the number of data exchange compared with the previously proposed pipelining scheme. Further, It is shows enhanced reliability for update code propagation and reduced overhead in terms of the number of data exchange. As a result, we can efficiently perform the software update from the viewpoint of speed, energy, and network congestion when the proposed code propagation system is applied. In addition, the proposed system solves overhearing problems of network coding such as the loss of original messages and decoding error using the predefined message. Therefore, our system allows a software update system to exchange reliable data in wireless sensor networks.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.31 no.6
• /
• pp.1215-1225
• /
• 2021

Although Artificial Intelligence (AI) techniques have shown impressive performance in various fields, they are vulnerable to adversarial examples which induce misclassification by adding human-imperceptible perturbations to the input. Previous studies to defend the adversarial examples can be classified into three categories: (1) model retraining methods; (2) input transformation methods; and (3) adversarial examples detection methods. However, even though the defense methods against adversarial examples have constantly been proposed, there is no research to classify the type of adversarial attack. In this paper, we proposed an adversarial attack family classification method based on dimensionality reduction and clustering. Specifically, after extracting adversarial perturbation from adversarial example, we performed Linear Discriminant Analysis (LDA) to reduce the dimensionality of adversarial perturbation and performed K-means algorithm to classify the type of adversarial attack family. From the experimental results using MNIST dataset and CIFAR-10 dataset, we show that the proposed method can efficiently classify five tyeps of adversarial attack(FGSM, BIM, PGD, DeepFool, C&W). We also show that the proposed method provides good classification performance even in a situation where the legitimate input to the adversarial example is unknown.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.5
• /
• pp.555-564
• /
• 2016

This paper proposes a time slot allocation scheme for military patrol environments. This proposal comes from analysis of traffic properties in a military patrol environment. In the near future, robots are expected to explore enemy grounds and measure threat, taking the place of human patrol. In order to control such robots, control messages must be extremely accurate. One mistake from the control center could cause a tragedy. Thus, high reliability must be guaranteed. Another goal is to maintain a continual flow of multimedia data sent from patrol robots. That is, QoS (Quality of Service) must be guaranteed. In order to transmit data while fulfilling both attributes, the per-path based centralized TDMA slot allocation scheme is recommended. The control center allocates slots to robots allowing synchronization among robots. Slot allocation collisions can also be avoided. The proposed scheme was verified through the ns-3 simulator. The scheme showed a higher packet delivery ratio than the algorithm in comparison. It also performed with shorter delay time in the downlink traffic transmission scenario than the algorithm in comparison.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.2
• /
• pp.174-179
• /
• 2015

Failure Mode and Effects Analysis (FMEA) has been used by Dynamic Positioning (DP) system for risk and reliability analysis. However, there are limitations associated with its implementation in offshore project. 1) since the failure data measured from the SCADA system is missing or unreliable, assessments of Severity, Occurrence, Detection are based on expert's knowledge; 2) it is not easy for experts to precisely evaluate the three risk factors. The risk factors are often expressed in a linguistic way. 3) the relative importance among three risk factors are rarely even considered. To solve these problems and improve the effectiveness of the traditional FMEA, we suggest a Fuzzy-FMEA method for risk and failure mode analysis in Dynamic Positioning System of offshore. The information gathered from DP FMEA report and DP FMEA Proving Trials is expressed using fuzzy linguistic terms. The proposed method is applied to an offshore Dynamic Positioning system, and the results are compared with traditional FMEA.

• Composites Research
• /
• v.33 no.6
• /
• pp.365-370
• /
• 2020

The icing formation at aircraft occur problems such as increasing weight of the body, fuel efficiency reduction, drag reduction, the error of sensor, and etc. The viscosity of polyurethane (PU) topcoat was measured at 60℃ in real time to set the pre-curing time. SiO2 nanoparticles were dispersed in ethanol using ultra-sonication method. The SiO2/ethanol solution was sprayed on PU topcoat that was not cured fully with different pre-curing conditions. Surface roughness of SiO2/PU nanocomposites were measured using surface roughness tester and the surface roughness data was visualized using 3D mapping. The adhesion property between SiO2 and PU topcoat was evaluated using adhesion pull-off test. The static contact angle was measured using distilled water to evaluate the hydrophobicity. Finally, the pre-curing time of PU topcoat was optimized to exhibit the hydrophobicity of SiO2/PU topcoat.