• Journal of Sensor Science and Technology
• /
• v.22 no.1
• /
• pp.18-27
• /
• 2013

Real-time monitoring is one of the prime necessities in a weapon flight test that is required for the efficient and timely collection of large amounts of high-rate sampled data acquired by an event-trigger. The wireless sensor network is a good candidate to resolve this requirement, especially considering the inhospitable environment of a weapon flight test. In this paper, we propose a priority based multi-channel MAC protocol with CSMA/CA over a single radio for a real-time monitoring of a weapon flight test. Multi-channel transmissions of nodes can improve the network performance in wireless sensor networks. Our proposed MAC protocol has two operation modes: Normal mode and Priority Mode. In the normal mode, the node exploits the normal CSMA/CA mechanism. In the priority mode, the node has one of three grades - Class A, B, and C. The node uses a different CSMA/CA mechanism according to its grade that is determined by a signal level. High grade nodes can exploit more channels and lower backoff exponents than low ones, which allow high grade nodes to obtain more transmission opportunities. In addition, it can guarantee successful transmission of important data generated by high grade nodes. Simulation results show that the proposed MAC exhibits excellent performance in an event-triggered real-time application.

• Journal of Biomedical Engineering Research
• /
• v.43 no.6
• /
• pp.441-447
• /
• 2022

In this paper, we propose a pill identification model using engraved text feature and image feature such as shape and color, and compare it with an identification model that does not use engraved text feature to verify the possibility of improving identification performance by improving recognition rate of the engraved text. The data consisted of 100 classes and used 10 images per class. The engraved text feature was acquired through Keras OCR based on deep learning and 1D CNN, and the image feature was acquired through 2D CNN. According to the identification results, the accuracy of the text recognition model was 90%. The accuracy of the comparative model and the proposed model was 91.9% and 97.6%. The accuracy, precision, recall, and F1-score of the proposed model were better than those of the comparative model in terms of statistical significance. As a result, we confirmed that the expansion of the range of feature improved the performance of the identification model.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.32 no.2
• /
• pp.201-211
• /
• 2022

According to the recent change in the cybersecurity paradigm, research on anomaly detection methods using machine learning and deep learning techniques, which are AI implementation technologies, is increasing. In this study, a comparative study on data preprocessing techniques that can improve the anomaly detection performance of a GRU (Gated Recurrent Unit) neural network-based intrusion detection model using NGIDS-DS (Next Generation IDS Dataset), an open dataset, was conducted. In addition, in order to solve the class imbalance problem according to the ratio of normal data and attack data, the detection performance according to the oversampling ratio was compared and analyzed using the oversampling technique applied with DCGAN (Deep Convolutional Generative Adversarial Networks). As a result of the experiment, the method preprocessed using the Doc2Vec algorithm for system call feature and process execution path feature showed good performance, and in the case of oversampling performance, when DCGAN was used, improved detection performance was shown.

• Journal of Navigation and Port Research
• /
• v.33 no.5
• /
• pp.339-344
• /
• 2009

This paper aims at identifying the effectiveness of the maintenance of container cranes in two typical container terminals in Pusan Port based on the empirical data For this the key performance indicator (KPI) was introduced with some information on world class standard level. Then, an empirical analysis was conducted with respect to the interaction of equipment maintenance KPI such as MMBF, PM, EM, and Breakdown ratio.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.7
• /
• pp.2304-2320
• /
• 2021

Intelligently detecting anomalies in health sensor data streams (e.g., Electrocardiogram, ECG) can improve the development of E-health industry. The physiological signals of patients are collected through sensors. Timely diagnosis and treatment save medical resources, promote physical health, and reduce complications. However, it is difficult to automatically classify the ECG data, as the features of ECGs are difficult to extract. And the volume of labeled ECG data is limited, which affects the classification performance. In this paper, we propose a Generative Adversarial Network (GAN)-based deep learning framework (called CAB) for heart arrhythmia classification. CAB focuses on improving the detection accuracy based on a small number of labeled samples. It is trained based on the class-imbalance ECG data. Augmenting ECG data by a GAN model eliminates the impact of data scarcity. After data augmentation, CAB classifies the ECG data by using a Bidirectional Long Short Term Memory Recurrent Neural Network (Bi-LSTM). Experiment results show a better performance of CAB compared with state-of-the-art methods. The overall classification accuracy of CAB is 99.71%. The F1-scores of classifying Normal beats (N), Supraventricular ectopic beats (S), Ventricular ectopic beats (V), Fusion beats (F) and Unclassifiable beats (Q) heartbeats are 99.86%, 97.66%, 99.05%, 98.57% and 99.88%, respectively. Unclassifiable beats (Q) heartbeats are 99.86%, 97.66%, 99.05%, 98.57% and 99.88%, respectively.

• Structural Monitoring and Maintenance
• /
• v.10 no.1
• /
• pp.87-105
• /
• 2023

Seismic regulations have been updated from time to time to accommodate an increase in seismic hazards. Comparison of seismic fragility of the existing bridges in Indonesia from different historical periods since the era before 1990 will be the basis for seismic assessment of the bridge stock in Indonesia, most of which are located in earthquake-prone areas, especially those built many years ago with outdated regulations. In this study, seismic fragility curves were developed using incremental non-linear time history analysis and more holistically according to the actual strength of concrete and steel material in Indonesia to determine the uncertainty factor of structural capacity, βc. From the research that has been carried out, based on the current seismic load in SNI 2833:2016/Seismic Map 2017 (7% probability of exceedance in 75 years), the performance level of the bridge in the era before SNI 2833:2016 was Operational-Life Safety whereas the performance level of the bridge designed with SNI 2833:2016 was Elastic - Operational. The potential for more severe damage occurs in greater earthquake intensity. Collapse condition occurs at As = F_PGA x PGA value of bridge Era I = 0.93 g; Era II = 1.03 g; Era III = 1.22 g; Era IV = 1.54 g. Furthermore, the fragility analysis was also developed with geometric variations in the same bridge class to see the effect of these variations on the fragility, which is the basis for making bridge risk maps in Indonesia.

• Journal of Engineering Education Research
• /
• v.18 no.4
• /
• pp.57-65
• /
• 2015

The purpose of this study is to analyze the performance of ABEEK accredited engineering program in D University. Based on engineering students' perceptions, this study explores how well the students are aware of the accredited engineering program, what change has been made to the courses, to what extent they have been participating in class and interacting with teachers and other students, to what extent they have been actively participating in extra-curricular activities, and to what extent they have achieved program outcomes. The survey was conducted in Fall 2014. The results are as follows: First, the students are well aware of the accredited engineering program; however, they are rarely aware of program outcomes. Second, the students were more satisfied with the major and design courses compared to the MSC and general education courses. Third, the students were more actively participated in the major and design courses compared to the MSC and general education courses. Fourth, the students were passively engaged in extra-curricular activities. Finally, the program outcomes related to soft skills showed low-achievement.

• Journal of the Korea Computer Industry Society
• /
• v.2 no.12
• /
• pp.1505-1516
• /
• 2001

The goal of Medical multimedia server is to develop computer hardware and software which would enable electronic access, storage, transmission, and display of patient data and images. Since the current network only provides so called "best-effort" services, it is impossible to satisfy QoS guarantee that is required for real time application services for emergency room, operating room etc. Accordingly, world-wide research is being made for a variety of services to provide QoS. he goal of DiffServ is to offer scalable differentiated service in Internet which are made possible by traffic classification and conditioning only performed at an edge(or a boundary) node. In case DiffServ was deployed in the Medical multimedia network, it is difficult to estimate how the QoS mechanism would affect totally the network performance. Therefore, we need to verify by simulation the design of algorithm which provide a variety of differentiated services. In QoS for Medical multimedia network, a simulator is designed and implemented using OPNET to investigate the performance of DiffServ QoS support mechanism. The developed DiffServ simulator may generate packets according to random, and bursty traffic models in order to incorporate diverse traffic conditions in the Medical multimedia network environment. Based on our simulation results, we confirmed that service differentiation is possible by using the EF(Expedited Forwarding) class in DiffServ networks.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.17 no.1
• /
• pp.1-7
• /
• 2018

We aimed to develop a high quality 3.5 ton class swing reducer by studying the efficiency improvement of the reducer through the optimum design and performance evaluation of the assembled, high efficiency, lightweight 3.5 ton swing reducer. Based on the optimal design of the worm and worm wheel, the optimal manufacturing method of the worm wheel, the optimized casing design, and the optimum design of the output pinion, Respectively. Therefore, in this paper, to improve the efficiency of the worm gear reducer system, we will develop the manufacturing technology and verify the mass production by combining the manufacturing process design, processing and assembling technology according to the optimization design. We have conducted research to realize mass production by product verification such as product efficiency, reliability and durability according to optimal design of worm gear reducer.

• Culinary science and hospitality research
• /
• v.5 no.2
• /
• pp.447-467
• /
• 1999

Most published work on product quality focuses on manufactured goods. The subject of service quality has received less attention. This distinction is important because some of the quality-improving strategies avaliable to manufacturers may be inappropriate for service firms. Services are performances, not objects. They are often produced in the presence of the customer, as in the cause of hotel restaurant services, quality occurs during service delivery, usually in an interaction between the customer and contact personnel of service firm. for this reason, service quality is highly dependent on the performance of employees, an organizational resource that cannot be controlled to the degree that components of tangible goods can be engineered. The study has begun as a basic study for customer satisfaction-oriented management in understanding the service quality of food & beverage products and through a systematic analysis of it. The major purpose of the study was to examine the relationship of the customer satisfaction and service quality in consideration of reliability, empathy, responsiveness, tangibility and assurance. An empirical research was conducted based on the previous theoretical studies. 286 customer at first class hotels in Seoul were selected as samples of this study. The time period of research was from February through March 1999, and answers were processed by SAS to yield frequency analysis, multivariate statistical analysis and regression analysis. The finding of the statistical treatment are frequencies, factor analysis, multiple regression analysis, path analysis. SERVQUAL method was used the service quality evaluation methods. After factor analysis, it was resulted to 3 factors. those were factor 1(assurance.empathy.responsiveness), factor 2(reliability), factor 3(tangibility). The findings of the statistical treatment are as follows. First, the attribute measurement of performance service quality was affected by customer satisfaction. Second, the attribute measurement of performance service qualify was affected by repurchase intention. Third, The attribute measurement of performance customer satisfaction was affected by repurchase intention. The result of study model was followed, service quality was affected repurchase intention than customer satisfaction. indirected effect through, service duality and customer satisfaction was affected repurchase intention.