• The Journal of the Convergence on Culture Technology
• /
• v.8 no.6
• /
• pp.861-866
• /
• 2022

Seoul introduced the shared bicycle system, "Seoul Public Bike" in 2015 to help reduce traffic volume and air pollution. Hence, to solve various problems according to the supply and demand of the shared bicycle system, "Seoul Public Bike," several studies are being conducted. Most of the research is a strategic "Bicycle Rearrangement" in regard to the imbalance between supply and demand. Moreover, most of these studies predict demand by grouping features such as weather or season. In previous studies, demand was predicted by time-series-analysis. However, recently, studies that predict demand using deep learning or machine learning are emerging. In this paper, we can show that demand prediction can be made a little better by discovering new features or ordering the importance of various features based on well-known feature-patterns. In this study, by ordering the selection of new features or the importance of the features, a better coefficient of determination can be obtained even if the well-known deep learning or machine learning or time-series-analysis is exploited as it is. Therefore, we could be a better one for demand prediction.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.2
• /
• pp.907-923
• /
• 2020

For the severe haze situation in the Beijing-Tianjin-Hebei region, conventional fine particulate matter (PM2.5) concentration prediction methods based on pollutant data face problems such as incomplete data, which may lead to poor prediction performance. Therefore, this paper proposes a method of predicting the PM2.5 concentration based on image analysis technology that combines image data, which can reflect the original weather conditions, with currently popular machine learning methods. First, based on local parameter estimation, autoregressive (AR) model analysis and local estimation of the increase in image blur, we extract features from the weather images using an approach inspired by free energy and a no-reference robust metric model. Next, we compare the coefficient energy and contrast difference of each pixel in the AR model and then use the percentages to calculate the image sharpness to derive the overall mass fraction. Furthermore, the results are compared. The relationship between residual value and PM2.5 concentration is fitted by generalized Gauss distribution (GGD) model. Finally, nonlinear mapping is performed via the wavelet neural network (WNN) method to obtain the PM2.5 concentration. Experimental results obtained on real data show that the proposed method offers an improved prediction accuracy and lower root mean square error (RMSE).

• Atmosphere
• /
• v.16 no.4
• /
• pp.319-332
• /
• 2006

This study examines the capability of the WRF (Weather Research and Forecasting) model in reproducing heavy rainfall that developed over the Korean peninsula on 26-27 June 2005. The model is configured with a triple nesting with the highest horizontal resolution at a 3-km grid, centered at Yang-dong, Gyeonggi-province, which recorded the rainfall amount of 376 mm. In addition to the control experiment employing realistic orography over Korea, two consequent sensitivity experiments with 1) no orography, and 2) no land over Korea were designed to investigate orographic effects on the development of heavy rainfall. The model was integrated for 48 hr, starting at 1200 UTC 25 June 2005. The overall features of the large-scale patterns including a cyclone associated with the heavy rainfall are reasonably reproduced by the control run. The spatial distribution of the simulated rainfall over Korea agreed fairly well with the observed. The amount of predicted maximum rainfall at the 3-km grid is 377 mm, which located about 50 km southeast from the observed point, Yang-Dong, indicating that the WRF model is capable of predicting heavy rainfall over Korea at the cloud resolving resolutions. Further, it was found that the complex orography over the Korean peninsula plays a role in enhancing the rainfall intensity by about 10%. The land-sea contrast over the peninsula was fund to be responsible for additional 10% increase of rainfall amount.

• Journal of the Korean Society for Marine Environment & Energy
• /
• v.13 no.3
• /
• pp.127-134
• /
• 2010

This study investigated the accuracy of mean sea level pressure(MSLP) predicted by weather models around Korean Peninsula during typhoon Manyi and Usagi period in 2007. The mesoscale regional model, RDAPS, KWRF with 30 and 10 km horizontal resolution and developed high-resolution WRF models with 9 and 3 km horizontal resolutions are used to predict the features of MSLP. The predicted MSLP aspects were verified using observed results from total 35 coastal stations including AWS and ocean buoy. Although 4 models showed the reasonable MLSP results during typhoon periods, the highest resolution, 3km WRF model show the most accurate MSLP results with maximum 69% and 60% improvement with comparisons of RDAPS and KWRF, respectively.

• Journal of the Semiconductor & Display Technology
• /
• v.17 no.2
• /
• pp.76-80
• /
• 2018

In recent years, with the development of automobile technology, smart system technology that assists safe driving has been developed. A camera is installed on the front and rear of the vehicle as well as on the left and right sides to detect and warn of collision risks and hazards. Beyond the technology of simple black-box recording via cameras, we are developing intelligent systems that combine various computer vision technologies. However, most related studies have been developed to optimize performance in laboratory-like environments that do not take environmental factors such as weather into account. In this paper, we propose a method to detect object by restoring visibility in image with degraded image due to weather factors such as fog. First, the image quality degradation such as fog is detected in a single image, and the image quality is improved by restoring using an intermediate value filter. Then, we used an adaptive feature extraction method that removes unnecessary elements such as noise from the improved image and uses it to recognize objects with only the necessary features. In the proposed method, it is shown that more feature points are extracted than the feature points of the region of interest in the improved image.

• Journal of the Korean association of regional geographers
• /
• v.11 no.5
• /
• pp.368-382
• /
• 2005

This paper deals with the village names in Geoje City[Geoje Island], Hundreds of village names in the city are found to be based on some environmental features such as landforms, weather, and soil of the island. A considerable number of village names in the city are derived from the mountainous landforms with steep slopes or from the extremely indented coastlines with many small islands, and some village names are originated from the weather and soil. In this paper, it is realized that the village names often reflect the environments perception of the residents and that they can give some clues to the environment's changes of the places.

• Korean Journal of Remote Sensing
• /
• v.19 no.4
• /
• pp.291-305
• /
• 2003

The cost of deploying Geological and Environmental information gathering systems, especially when such systems obtain remote sensing and photographic data through the use of commercial satellites and aircraft. Besides the high cost equipment required, adverse weather conditions can further restrict a researcher's ability to collect data anywhere and anytime. To mitigate this problem, we have developed a compact, multi-spectral automatic Aerial photographic system. This system's Multi-spectral camera is capable of the visible (RGB) and infrared (NIR) bands (3032*2008 pixel). It consists of a thermal infrared camera and automatic balance control, and can be managed by a palm-top computer. Other features includes a camera gimbal system, GPS receiver, weather sensor among others. We have evaluated the efficiency of this system in several field tests at the following locations: Kyongsang-bukdo beach, Nakdong river (at each site of mulkeum-namji and koryung-gumi), and Kyungahn River. Its tested ability in aerial photography, weather data, as well as GPS data acquisition demonstrates its flexibility as a tool for environmental data monitoring.

• Journal of Korean Society of Archives and Records Management
• /
• v.3 no.2
• /
• pp.143-155
• /
• 2003

As archives, photograph is the evident records of historical facts and experiences. Thus, it is worth preserving. Unlike other documents silver halide photographic films and prints are quite sensitive to environmental factors such as light, temperature and humidity, which demands careful treatment in preservation. This study was carried out to select popular photographic films and papers on the market, to examine their photographic speeds (or sensitivities) and to compare and analyze their preservative features after keeping them some time in a weather-o-meter. Consequently, B/W materials were superior to color ones in preservation. And films were better than papers in the same manner. But we were not able to observe remarkable differences among material's manufacturers.

• International Journal of Computer Science & Network Security
• /
• v.22 no.8
• /
• pp.371-379
• /
• 2022

The environment in Kosovo is a topic of concern for the citizens and the state because of the temperatures that affect the health of the citizens and the climate around the world. Kosovo's climate is related to its geographical position. Stretching in the middle latitude, Kosovo's climate depends on the amount of heat coming from the Sun, the proximity of the Adriatic Sea, the Vardar valley, the openness to the north. In order to better understand the climatic features of Kosovo, one must know the elements of the climate such as: sunshine, temperature, precipitation, atmospheric pressure, winds. The Meteorological Institute of Kosovo is responsible for measuring temperatures in Kosovo since 2014 and until now 12 meteorological stations have been operationalized with automatic measurement and real-time data transfer to the central system for data collection and archiving. The hydrometeorological institute lacks an application for measuring temperatures in all the countries of Kosovo. Software applications are generally built to suit the requirements of different governments and clients in order to enable easier management of the jobs they operate on. One of the forms of application development is the development of mobile applications based on android. The purpose of the work is to create a mobile application based on the Android operating system that aims to display information about the weather, this type of application is necessary and important for users who want to see the temperature in different places in Kosovo, but also the world. This type of application offers many options such as maximum temperature, minimum temperature, humidity, and air pressure. The built application will have real and accurate data; this will be done by comparing the results with other similar applications. Such an application is necessary for everyone, especially for those people whose daily work is dependent on the weather or even for those who decide to spend their vacations, such as summer or winter. In this paper, comparisons are also made within android applications for tablets, televisions and smart watches.

• Journal of the Korean earth science society
• /
• v.44 no.2
• /
• pp.105-118
• /
• 2023

In this study, we predicted the presence of fog with a one-hour delay using the XGBoost DART machine learning algorithm for Andong, which had the highest occurrence of fog among inland stations from 2016 to 2020. We used six datasets: meteorological data, agricultural observation data, additional derived data, and their expanded data. The weather phenomenon numbers obtained through naked-eye observations and the visibility distances measured by visibility meters were classified as fog [1] or no-fog [0]. We set up twelve machine learning modeling experiments and used data from 2021 for model validation. We mainly evaluated model performance using recall and AUC-ROC, considering the harmful effects of fog on society and local communities. The combination of oversampled meteorological data features and the target induced by weather phenomenon numbers showed the best performance. This result highlights the importance of naked-eye observations in predicting fog using machine learning algorithms.