• Asia pacific journal of information systems
• /
• v.31 no.4
• /
• pp.491-526
• /
• 2021

Airlines can employ a variety of quality monitoring procedures. In this study, we employ a content analysis of 8 years of online reviews for Korean airlines in contrast to other international airlines. Online airline reviews are infrequent, relative to the total number of passengers - the number of reviews is multiple orders of magnitude lower than passenger volumes - and online airline reviews are, therefore, not representative of passenger attitudes overall. Nevertheless, online reviews may be indicative of specific service issues, and draw attention to aspects that require further study by airline operators. Furthermore, significant words and phrases used in these airline reviews may help airline operators to rapidly automate filtering, partitioning, and analysis of incoming passenger comments via other channels, including email, social media posts, and call center transcripts. The current study provides insights into the contents of online reviews of Korean vs Other-International airlines, and opportunities for service enhancement. Further, we provide a set of marker words and phrases that may be helpful for management dashboards that require automated partitioning of passenger comments.

• Korean Journal of Remote Sensing
• /
• v.38 no.5_3
• /
• pp.925-938
• /
• 2022

Agricultural reservoirs are an important water resource nationwide and vulnerable to abnormal climate effects such as drought caused by climate change. Therefore, it is required enhanced management for appropriate operation. Although water-level tracking is necessary through continuous monitoring, it is challenging to measure and observe on-site due to practical problems. This study presents an objective comparison between multiple AI models for water-body extraction using radar images that have the advantages of wide coverage, and frequent revisit time. The proposed methods in this study used Sentinel-1 Synthetic Aperture Radar (SAR) images, and unlike common methods of water extraction based on optical images, they are suitable for long-term monitoring because they are less affected by the weather conditions. We built four AI models such as Support Vector Machine (SVM), Random Forest (RF), Artificial Neural Network (ANN), and Automated Machine Learning (AutoML) using drone images, sentinel-1 SAR and DSM data. There are total of 22 reservoirs of less than 1 million tons for the study, including small and medium-sized reservoirs with an effective storage capacity of less than 300,000 tons. 45 images from 22 reservoirs were used for model training and verification, and the results show that the AutoML model was 0.01 to 0.03 better in the water Intersection over Union (IoU) than the other three models, with Accuracy=0.92 and mIoU=0.81 in a test. As the result, AutoML performed as well as the classical machine learning methods and it is expected that the applicability of the water-body extraction technique by AutoML to monitor reservoirs automatically.

• Korean Journal of Remote Sensing
• /
• v.32 no.2
• /
• pp.119-131
• /
• 2016

Descriptions are provided of the automated aerosol-type classification and mass concentration calculation algorithm for real-time data processing and aerosol products in Korea Aerosol Lidar Observation Network (KALION, http://www.kalion.kr). The KALION algorithm provides aerosol-cloud classification and three aerosol types (clean continental, dust, and polluted continental/urban pollution aerosols). It also generates vertically resolved distributions of aerosol extinction coefficient and mass concentration. An extinction-to-backscatter ratio (lidar ratio) of 63.31 sr and aerosol mass extinction efficiency of $3.36m^2g^{-1}$ ($1.39m^2g^{-1}$ for dust), determined from co-located sky radiometer and $PM_{10}$ mass concentration measurements in Seoul from June 2006 to December 2015, are deployed in the algorithm. To assess the robustness of the algorithm, we investigate the pollution and dust events in Seoul on 28-30 March, 2015. The aerosol-type identification, especially for dust particles, is agreed with the official Asian dust report by Korean Meteorological Administration. The lidar-derived mass concentrations also well match with $PM_{10}$ mass concentrations. Mean bias difference between $PM_{10}$ and lidar-derived mass concentrations estimated from June 2006 to December 2015 in Seoul is about $3{\mu}g\;m^{-3}$. Lidar ratio and aerosol mass extinction efficiency for each aerosol types will be developed and implemented into the KALION algorithm. More products, such as ice and water-droplet cloud discrimination, cloud base height, and boundary layer height will be produced by the KALION algorithm.

• Geophysics and Geophysical Exploration
• /
• v.16 no.3
• /
• pp.171-179
• /
• 2013

An automated ultrasonic velocity measurement system adopting pulse-echo-overlap (PEO) method has been constructed, which is known to be a precise and versatile method. It has been applied to velocity measurements for 5 kinds of engineering plastic cores and compared to first arrival picking (FAP) method. Because it needs multiple reflected waves and waves travel at least 4 times longer than FAP, PEO has basic restriction on sample length measurable. Velocities measured by PEO showed slightly lower than that by FAP, which comes from damping and diffusive characteristics of the samples as the wave travels longer distance in PEO. PEO, however, can measure velocities automatically by cross-correlating the first echo to the second or third echo, so that it can exclude the operator-oriented errors. Once measurable, PEO shows essentially higher repeatability and reproducibility than FAP. PEO system can diminish random noises by stacking multiple measurements. If it changes the experimental conditions such as temperature, saturation and so forth, the automated PEO system in this study can be applied to monitoring the velocity changes with respect to the parameter changes.

• Journal of Veterinary Clinics
• /
• v.32 no.5
• /
• pp.399-403
• /
• 2015

Peritoneal dialysis (PD) is a treatment for renal failure and acute poisoning, and uses the patient's peritoneum in the abdomen as a membrane across which fluids and dissolved substances are exchanged from the blood. In this study, we evaluated the therapeutic efficacy and complications of automated peritoneal dialyzer (APD) in dogs with renal failure. PD was performed in 10 dogs using a swan neck catheter (Neonatal, Coviden) and automatic APD. The efficacy for each dog was assessed by calculating urea reduction ratio (URR) and creatinine reduction ratio (CRR). Mean concentrations of pre-dialysis creatinine and blood urea (BUN) were $7.09{\pm}3.84$ and $145.8{\pm}48.5$, respectively. The mean number of peritoneal dialysis cycles applied was $6{\pm}1$ cycles. Peritoneal dialysis resulted in a significant decrease in BUN concentration in 7/10 dogs, while a significant decrease in creatinine concentration in 9/10 dogs. The mean of URR was higher than that of CRR ($0.39{\pm}0.16$ vs $0.38{\pm}0.13$). The mean CRR and URR per dialysis cycles were $0.064{\pm}0.023$ and $0.065{\pm}0.023$, respectively. Complications found in this study were catheter occlusion, subcutaneous dialysate leakage, septic peritonitis, hypoalbuminemia and overhydration. This study found PD using a swan neck catheter and APD machine showed acceptable efficacy for successful peritoneal dialysis in dogs. However, close monitoring is required to minimize the risk of complication.

• Analytical Science and Technology
• /
• v.14 no.5
• /
• pp.432-441
• /
• 2001

An automated on-line portable preconcentration-short column gas chromatograph was developed, which used preconcentrator using adsorption tube with Tenax-GR and Curie-point heating. The developed system operated with 3 steps of processing, preconcentration, thermal desorption, and analysis and cleaning, and could continued operating within 1~2 min cycle. The recoveries of preconcentrator for toluene was ranged between $94.7{\pm}6.6%$ and $103.8{\pm}3.1%$ with less than 7% of RSD. For benzene, toluene and xylene(BTX) standard gas test, IDL was 41, 49, $472ng/m^3$ benzene, toluene and o-xylene, respectively. The BTX mixture was analyzed within 30 sec with baseline separation by the system equipped with 4 m long capillary column. The deficiency of separation power caused by short column was solved by the control of sample injection volume and inlet/outlet pressure ratio. The automated portable preconcentration-short column gas chromatograph system was found to be useful for the continuous air monitoring of BTX at ppb levels in ambient air.

• Journal of KIISE:Software and Applications
• /
• v.34 no.9
• /
• pp.817-827
• /
• 2007

In the age of ubiquitous environment, huge number of devices and computing services are provided to users. Personalized service, which is modeled according to the character of each and every individual is of particular need. In order to provide various dynamic services according to user's movement, service unit and operating mode should be able to operate automatically with minimum user intervention. In this paper, we discuss the steps of offering approximate service based on user's request in ubiquitous environment. First, we present our simulator designed for modeling the physical resource and computing object in smart space - the infrastructure in ubiquitous. Second, intelligent agents, which we developed based on a FIPA specification compliant multi-agent framework will be discussed. These intelligent agents are developed for achieving the service goal through cooperation between distributed agents. Third, we propose an automated service discovery and composition method in heterogeneous environment using semantic message communication between agents, according to the movement by the user interacting with the service available in the smart space. Fourth, we provide personalized service through agent monitoring anytime, anywhere from user's profile information stored on handhold device. Therefore, our research provides high quality service more than general automated service operation.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.22 no.3
• /
• pp.107-116
• /
• 2020

In this data paper, we share the dataset obtained during 2019 from the test-bed to develop soil moisture estimation technology for upland fields, which was built in Seosan and Taean, South Korea on May 3. T his dataset includes various eco-hydro-meteorological variables such as soil moisture, evapotranspiration, precipitation, radiation, temperature, humidity, and vegetation indices from the test-bed nearby the Automated Agricultural Observing System (AAOS) in Seosan operated by the Korea Meteorological Administration. T here are three remarkable points of the dataset: (1) It can be utilized to develop and evaluate spatial scaling technology of soil moisture because the areal measurement with wide spatial representativeness using a COSMIC-ray neutron sensor as well as the point measurement using frequency/time domain reflectometry (FDR/TDR) sensors were conducted simultaneously, (2) it can be used to enhance understanding of how soil moisture and crop growth interact with each other because crop growth was also monitored using the Smart Surface Sensing System (4S), and (3) it is possible to evaluate the surface water balance by measuring evapotranspiration using an eddy covariance system.

• The KIPS Transactions:PartD
• /
• v.15D no.2
• /
• pp.271-284
• /
• 2008

Self-healing is an approach to evaluating constraints defined in target system and to applying an appropriate strategy when violating he constrains. Today, the computing environment is very complex, so researches that endow a system with the self-healing's ability that recognizes problem arising in a target system are being an important issues. However, most of the existing researches are that self-healing developers need much effort and time to analyze and model constraints. Thus, this paper proposes an automated approach to determine problem arising in external and internal system environment. The approach proposes: 1) Specifying the target system through the models created in design phase of target system. 2) Automatically creating constraints for external and internal system environment, by using the specified contents. 3) Deriving a dependency model of a component based on the created internal state rule. 4) Translating the constraints and dependency model into code evaluating behaviors of the target system, and determinating problem level. 5) Monitoring an internal and external status of system based on the level of problem determination, and applying self-healing strategy when detecting abnormal state caused in the target system. Through these, we can reduce the efforts of self-healing developers to analyze target system, and heal rapidly not only abnormal behavior of target system regarding external and internal problem, but also failure such as system break down into normal state. To evaluate the proposed approach, through video conference system, we verify an effectiveness of our approach by comparing proposed approach's self-healing activities with those of the existing approach.

• KNOM Review
• /
• v.23 no.2
• /
• pp.29-41
• /
• 2020

Networks are growing faster than ever before causing a multi-domain complexity. The diversity, variety and dynamic nature of network traffic and services require enhanced orchestration and management approaches. While many standard orchestrators and network operators are resulting in an increase of complexity for handling E2E slice orchestration. Besides, there are multiple domains involved in E2E slice orchestration including access, edge, transport and core network each having their specific challenges. Hence, handling of multi-domain, multi-platform and multi-operator based networking environments manually requires specified experts and using this approach it is impossible to handle the dynamic changes in the network at runtime. Also, the manual approaches towards handling such complexity is always error-prone and tedious. Hence, this work proposes an automated and abstracted solution for handling E2E slice orchestration using an intent-based approach. It abstracts the domains from the operators and enable them to provide their orchestration intention in the form of high-level intents. Besides, it actively monitors the orchestrated resources and based on current monitoring stats using the machine learning it predicts future utilization of resources for updating the system states. Resulting in a closed-loop automated E2E network orchestration and management system.