• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.6
• /
• pp.706-714
• /
• 2012

The Korea Meteorological Administration provided the recent four-years records of weather dataset for our very short-term heavy rainfall prediction. We divided the dataset into three parts: train, validation and test set. Through feature selection, we select only important features among 72 features to avoid significant increase of solution space that arises when growing exponentially with the dimensionality. We used a differential evolution algorithm and two classifiers as the fitness function of evolutionary computation to select more accurate feature subset. One of the classifiers is Support Vector Machine (SVM) that shows high performance, and the other is k-Nearest Neighbor (k-NN) that is fast in general. The test results of SVM were more prominent than those of k-NN in our experiments. Also we processed the weather data using undersampling and normalization techniques. The test results of our differential evolution algorithm performed about five times better than those using all features and about 1.36 times better than those using a genetic algorithm, which is the best known. Running times when using a genetic algorithm were about twenty times longer than those when using a differential evolution algorithm.

• Journal of Korea Water Resources Association
• /
• v.36 no.3 s.134
• /
• pp.495-505
• /
• 2003

Convective weather systems such as organized mesoscale convective systems (Mesoscale Convective Complex, MCC and Convective Cloud Clusters, CCC) and much weaker Disorganized Short-lived Convection (DSC) in the region of India and Nepal were analyzed using the Meteosat-5 IR imagery. The diurnal march and propagation of patterns of convective activity in the Himalayas and Northern Indian subcontinent were examined. Results indicate that infrared satellite images of Northern India and along the southern flank of the Himalayas reveal a strong presence of convective weather systems during the 1999 and 2000 monsoons, especially in the afternoon and during the night. The typical MCCs have life-times of about 11 hours, and areal extent about $300,000km^2$. Although the core of MCC activity remains generally away from the Middle Himalayan range, the occurrence of heavy precipitation events in this region can be directly linked to MCCs that venture into the Lesser Himalayan region and remain within the region bounded by $25^{\circ}-30^{\circ}N$. One principal feature in the spatial organization of convection is the dichotomy between the Tibetan Plateau and the Northern Indian Plains: CCCs and DSCs begin in the Tibetan Plateau in the mid-afternoon into the evening; while they are most active in the mid-night and early morning in the Gangetic Plains and along the southern facing flanks of the Himalayas. Furthermore, these data are consistent with the daily cycle of rainfall documented for a network of 20 hydrometeorological stations in Central Nepal, which show strong nocturnal peaks of intense rainfall consistent with the close presence of Convective Weather Systems (CWSs) in the Gangetic Plains (Barros et al. 2000).

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.12 no.4
• /
• pp.263-269
• /
• 2012

The ability to characterize feature objects from radar readings is often limited by simply looking at their still frame reflectivity, differential reflectivity and differential phase data. In many cases, time-series study of these objects' reflectivity profile is required to properly characterize features objects of interest. This paper introduces a novel technique to automatically track multiple 3D radar structures in C,S-band in real-time using Doppler radar and profile their characteristic reflectivity distribution in time series. The extraction of reflectivity profile from different radar cluster structures is done in three stages: 1. static frame (zone-linkage) clustering, 2. dynamic frame (evolution-linkage) clustering and 3. characterization of clusters through time series profile of reflectivity distribution. The two clustering schemes proposed here are applied on composite multi-layers CAPPI (Constant Altitude Plan Position Indicator) radar data which covers altitude range of 0.25 to 10 km and an area spanning over hundreds of thousands $km^2$. Discrete numerical simulations show the validity of the proposed technique and that fast and accurate profiling of time series reflectivity distribution for deformable 3D radar structures is achievable.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.15 no.3
• /
• pp.129-137
• /
• 2019

Recommendation systems help users by suggesting items such as products, services, and information. However, most research on recommendation systems has not considered people's moods although the appropriate contents recommended to people would be changed by people's moods. In this paper, we propose a situation-based recommendation system which exploits people's mood. The proposed scheme is based on the fact that the mood of a user is changed frequently by the surrounding environments such as time, weather, and anniversaries. The environments are defined as feature identifications, and the rating values on items are stored as feature identifications at a database. Then, people can be recommended diverse items according to their environments. Our proposed scheme has some advantages such as no problem of cold start, low processing overhead, and serendipitous recommendation. The proposed scheme can be also a good option as of assistance to other recommendation systems.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.45 no.4
• /
• pp.127-133
• /
• 2022

Many manufacturers applying third party logistics (3PLs) have some challenges to increase their logistics efficiency. This study introduces an effort to estimate the weight of the delivery trucks provided by 3PL providers, which allows the manufacturer to package and load products in trailers in advance to reduce delivery time. The accuracy of the weigh estimation is more important due to the total weight regulation. This study uses not only the data from the company but also many general prediction variables such as weather, oil prices and population of destinations. In addition, operational statistics variables are developed to indicate the availabilities of the trucks in a specific weight category for each 3PL provider. The prediction model using XGBoost regressor and permutation feature importance method provides highly acceptable performance with MAPE of 2.785% and shows the effectiveness of the developed operational statistics variables.

• Proceedings of the KSRS Conference
• /
• 2005.10a
• /
• pp.169-172
• /
• 2005

Modem SAR interferometry (IFSAR) sensors delivering intensity images and corresponding digital terrain model (DTM) allow for a thorough surface lineament interpretation with the all-weather day-night applicability. In this paper, an automatic linear-feature detection algorithm for high-resolution SAR images acquired in Taiwan is proposed. Methodologies to extract linear features consist of several stages. First, the image denoising techniques are used to remove the speckle noise on the raw image. In this stage, the Lee filter has been chosen because of its superior performance. After denoising, the Coefficient of Variation Detector is performed on the result images for edge enhancements and detection. Dilation and erosion techniques are used to reconnect the fragmented lines. The Hough transform, which is a special case of a more general transform known as Radon transform, is a suitable method for line detection in our analysis. Finally, linear features are extracted from the binary edge image. The last stage contains many substeps such as edge thinning and curve pruning.

• Atmosphere
• /
• v.23 no.1
• /
• pp.33-37
• /
• 2013

In meteorology, exploitation of Kalman filter as a data assimilation system is virtually impossible due to simultaneous requirements of adjoint model and large computer resource. The other substitute of utilizing ensemble Kalman filter is only affordable by compensating an enormous usage of computing resource. Furthermore, the latter employs ensemble integration sets for evolving the background error covariance matrix by compensating the dynamical feature of the temporal evolution of weather conditions. We propose a new implementation method that works without the adjoint model by utilizing the explicit expression of the background error covariance matrix in backward evolution. It will also break a barrier in the evolution of the covariance matrix. The method may be applied with a slight modification to the real time assimilation or the retrospective analysis.

• 제어로봇시스템학회:학술대회논문집
• /
• 1994.10a
• /
• pp.202-206
• /
• 1994

Mathematical model of the pollution rate of substation insulators is constructed, taking the model parameters as wind speed, wind direction, typhoon conditions and rainfall in an hourly basis. The main feature of model construction is to distinguish the effect of each parameter by separately analyzing the positive and negative pollution causing factors. Model parameters for the insulators of Karatsu substation, Saga, Japan were estimated and model validation was done using the actual data, in which the pollution deposits on the insulators were measured using pilot insulator and 'salt meter'. The proposed model of the pollution rate [mg/cm$^{2}$/hr] enables the identification of the effective parameters and prediction of the pollution rate so that it helps for the automatic decision making for insulator cleaning or the model can be used as a tool for the substation engineers to make precautionary measures.

• International Journal of Internet, Broadcasting and Communication
• /
• v.8 no.4
• /
• pp.58-62
• /
• 2016

Shipping related services is attracting attention as a UAV (Unmanned Aerial Vehicle) application with the recent economy has been generally accepted drones. UAV of the existing military-driven logistics delivery, aerial photography, wireless Internet connection, broadcasting, disaster research, digital maps, transportation, advertising, meteorological, border surveillance, agricultural use, such as hobbies range of uses from up military are diverse and growing. The advantage of delivery drones seems to be an important feature of delivery of the goods, including labor-saving, long-distance transportation in cold weather. UAV is demanded by competitive performance development for commercialization. Privacy issues that may arise during the drone operation, ensuring marketability issues, control system, regulations, operational standards and specifications, etc. should be addressed. Development direction of Korea UAV based in current technology, regulation, and growth potential presented by deriving from the idea of 'GIF 2016 Gang-won Hackathon.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.04b
• /
• pp.583-585
• /
• 2001

방대한 양의 격자점 데이터 및 일기도 관련 데이터를 효율적으로 저장 및 검색 하기위해서는 데이터들의 유형을 찾아 서로 유형이 비슷한 데이터를 하나의 클러스터로 연관지어 놓으면 효율적인 저장과 검색을 할 수 있다. 클러스터링에서 데이터들의 어떤 특징 벡터를 추출하는가가 클러스터링의 결과에 가장 중요한 영향을 끼친다. 본 논문에서는 격자점, 기압값 데이터로부터 일기도의 특징을 표현할 수 있는 벡터로 변환 한반도도 중심의 8방향에 대한 고/저기압의 분포와 동아시아 지역을 24영역으로 나누어 각 영역별로 고/저기압의 분포 정보를 특징벡터로 추출하여 클러스터링하였다. 클러스터팅 알고리즘으로는 unsupervised mode인 SOM(Self Organizing Map) 기법을 사용하였다.