Earticle

본 연구는 데이터 품질관리 평가 모델에 관한 연구이다. 정보통신기술이 고도화되고 저장 및 관리에 대한 중요성 이 증가를 하기 시작하며서 데이터에 대한 괌심이 증가를 하고 있다. 특히 최근에는 4차산업혁명과 인공지능에 대해 관심이 증가를 하고 있다. 4차산업혁몽과 인공지능 시대에 중요한 것이 바로 데이터이다. 21세기는 데이터가 새로운 원유로서의 역할을 수행할 것으로 보인다. 이러한 데이터의 품질에 대한 관리가 매우 중요하다고 할 수 있다. 그러나 실무적인 차원에서의 연구는 진행이 되고 있으나 학문적 차원의 연구는 부족한 실정이다. 이에 본 연구에서는 전문가를 대상으로 데이터 품질관리에 영향을 미치는 요인에 대해 살펴보고 시사점을 제시하였다. 분석결과 데이터 품질관리의 중요도에는 차이가 있는 것으로 나타났다.

This study is about the data quality management evaluation model. As the information and communication technology is advanced and the importance of storage and management begins to increase, the guam feeling for data is increasing. In particular, interest in the fourth industrial revolution and artificial intelligence has been increasing recently. Data is important in the fourth industrial revolution and the era of artificial intelligence. In the 21st century, data will likely play a role as a new crude oil. It can be said that the management of the quality of this data is very important. However, research is being conducted at a practical level, but research at an academic level is insufficient. Therefore, this study examined factors affecting data quality management for experts and suggested implications. As a result of the analysis, there was a difference in the importance of data quality management.

Due to the low efficiency and poor accuracy of current college teaching intelligence evaluation methods, an improved method is proposed. Firstly, an improved apriori (IApriori) algorithm is utilized to filter evaluation indexes and establish a teaching quality evaluation indicator system. Secondly, considering the high complexity and low accuracy of the backpropagation neural network (BPNN), principal component analysis (PCA) is taken to reduce the input data's dimension. An improved sparrow search algorithm (ISSA) is simultaneously utilized to optimize the parameters of BPNN. Finally, a PCA-ISSA-BPNN teaching intelligence evaluation model is constructed. The experiments validated that when the number of transactions was 1,000, the IApriori only took 0.32 seconds to run. While the number of projects was 11, IApriori ran in 15.28 seconds. The evaluation accuracy of the PCA-ISSA-BPNN model reached 99.05%, the F1 value was 96.43%, the recall was 97.26%, and the AUC was 0.981. The above data show that IApriori has a higher efficiency in data mining and can more effectively screen evaluation indicators. This research method can effectively and accurately evaluate teaching quality, and has a positive impact on promoting student development, advancing teaching reform, and improving teaching quality.

Driven by the vague assessment big data, a product service system (PSS) evaluation method is developed based on a hybrid model of multi-weight combination and improved TOPSIS by relative entropy. The index values of PSS alternatives are solved by the integration of the stakeholders' vague assessment comments presented in the form of trapezoidal fuzzy numbers. Multi-weight combination method is proposed for index weight solving of PSS evaluation decision-making. An improved TOPSIS by relative entropy (RE) is presented to overcome the shortcomings of traditional TOPSIS and related modified TOPSIS and then PSS alternatives are evaluated. A PSS evaluation case in a printer company is given to test and verify the proposed model. The RE closeness of seven PSS alternatives are 0.3940, 0.5147, 0.7913, 0.3719, 0.2403, 0.4959, and 0.6332 and the one with the highest RE closeness is selected as the best alternative. The results of comparison examples show that the presented model can compensate for the shortcomings of existing traditional methods.

This study aimed to develop a hybrid stem taper and volume estimation model using multi-platform LiDAR data for Pinus koraiensis (PK) and Larix kaempferi (LK) in a forest located in Gangwon Province, Republic of Korea. The research employed Terrestrial Laser Scanning (TLS) to capture detailed point cloud data of tree stems and Airborne Laser Scanning (ALS) for precise height measurements. By integrating the stem profiles derived from TLS with Kozak’s stem taper model, a hybrid estimation model was constructed to improve the accuracy of calculating individual tree taper curves and stem volumes. The proposed model was tested against traditional volume estimation methods, specifically the Korea Forest Service's standard volume table, to assess its accuracy. The standard volume table method exhibited root mean square error (RMSE) values of 0.12 m³ for PK and 0.13 m³ for LK. In contrast, the hybrid model showed significantly lower RMSE values of 0.07 m³ for PK and 0.05 m³ for LK, representing an accuracy improvement of approximately 42% for PK and 62% for LK. Additionally, the study estimated log production based on individual tree profiles generated from the hybrid model, accounting for factors such as stem length, diameter, and curvature. The increased accuracy of the hybrid model highlights its potential for providing more precise stem volume estimations and improving the reliability of forest inventories. The results suggest that this hybrid approach, leveraging the strengths of both TLS and ALS, offers a more efficient and accurate alternative to traditional volume estimation methods. The precise taper curves and volume estimates derived from this method can significantly contribute to sustainable forest management practices, particularly in assessing timber production and monitoring forest growth. By eliminating the need for destructive sampling, this method provides a non-invasive solution for estimating tree volumes. In conclusion, the multi-platform LiDAR-based hybrid model offers a promising solution for more accurate stem volume estimation, supporting forest inventory development and enhancing decision-making in forest management and timber production.

IT기술이 발전함에 따라, 우리가 접하는 데이터의 양은 기하급수적으로 늘어나고 있다. 이처럼 방대한 데이터들을 분석하고 관리하기 위한 기술로 등장한 것이 빅데이터 분산처리시스템이다. 기존 분산처리시스템에 대한 품질평가는 정형 데이터 중심의 환경을 바탕으로 이루어져 왔다. 그러므로, 이를 비정형 데이터 분석이 핵심인 빅데이터 분산처리시스템에 그대로 적용시킬 경우, 정확한 품질평가가 이루어질 수 없다. 따라서, 빅데이터 분석 환경을 고려한 분산처리시스템의 품질평가모델에 대한 연구가 필요하다. 본 논문에서는 소프트웨어 품질에 관한 국제 표준인 ISO/IEC9126에 근거하여 빅데이터 분산처리 시스템에서 요구되는 품질평가 요소를 도출하고, 이를 측정하기 위한 메트릭을 정의함으로써 새로이 품질평가모델을 제안한다.

According to the evolving of IT technologies, the amount of data we are facing increasing exponentially. Thus, the technique for managing and analyzing these vast data that has emerged is a distributed processing system of big data. A quality evaluation for the existing distributed processing systems has been proceeded by the structured data environment. Thus, if we apply this to the evaluation of distributed processing systems of big data which has to focus on the analysis of the unstructured data, a precise quality assessment cannot be made. Therefore, a study of the quality evaluation model for the distributed processing systems is needed, which considers the environment of the analysis of big data. In this paper, we propose a new quality evaluation model by deriving the quality evaluation elements based on the ISO/IEC9126 which is the international standard on software quality, and defining metrics for validating the elements.

PURPOSES : This study was conducted to develop a traffic accident prediction model using traffic accident data and management and service evaluation data on bus companies in Busan, and to determine the possibility of establishing customized traffic accident prevention measures for each company. METHODS : First, we collected basic data on the characteristics of urban bus traffic accidents and conducted basic statistical analysis. Then, we developed traffic accident prediction models using Poisson regression and negative binomial regression to examine the characteristics of major items of management and service evaluation affecting traffic accidents. RESULTS : The Poisson regression model showed overdispersion; hence, the negative binomial regression model was selected. The results of the traffic accident prediction model developed using negative binomial regression are acceptable at 95% confidence level (a = 0.05). CONCLUSIONS : The traffic accident prediction model indicates that the management of the traffic record system and internal and external management items in service evaluation have a significant effect on the reduction of traffic accidents. In particular, because human factors are the main cause of traffic accidents, bus traffic accidents are expected to greatly decrease if drivers' dangerous driving behaviors are effectively controlled by bus companies.

인간활동으로 인해 서식처의 변화, 서식처의 파편화를 비롯하여 기후변화, 토지이용의 변화 등으로 생태계 생물 다양성은 빠르게 손실되고있는 상황이다. 최근 들어 유역의 건전성을 확보하기 위해 유역관리 차원에서 접근하려는 시도가 시작되었으나 어떠한 수단을 통해 생물다양성과 서식처 관리에 대하여 접근할 수 있는지에 대한 연구는 아직 부족한 실정이다. 본 연구의 목적은 금강유역을 대상으로 Integrated Valuation of Ecosystem Services and Tradeoffs (InVEST) habitat quality model을 이용하여 유역의 서식처 질을 평가하는 것이다. 서식처 평가결과는 생태·자연도 및 수생태 건전성 평가결과와의 비교분석을 통해 검증되었다. 금강유역의 서식처 질은 0.0 ~ 0.86으로 분석되었으며, 유역의 하류보다 상류에서 서식처 질이 더 높은 것으로 나타났다. 생태·자연도 등급별 평균 서식처 질을 비교한 결과 1등급, 2등급, 3등급에서 각각 0.80, 0.76, 0.71이었다. 수생태 건전성 결과와의 상관성 분석결과 R²은 0.58, Pearson 상관계수는 0.76 였다. 본 연구의 결과는 향후 서식처 보호의 강화와 장기적인 생물 다양성 관련 정책의 실행을 지원하는 기초자료로 활용될 수 있다.

Ecosystem biodiversity is rapidly being lost due to changes in habitat, fragmentation of habitat, climate change, and land use changes by human activities. Recently, attempts have been made to approach the watershed management level to secure the health of the watershed, but studies on how to approach biodiversity and habitat management are still in lack. The purpose of this study is to evaluate the habitat quality of Geum river basin using Integrated Valuation of Ecosystem Services and Tradeoffs (InVEST) habitat quality model. The results of habitat quality was verified to eco-natural map and ecological watershed health evaluation results. The habitat quality of watershed was evaluated from 0 to 0.86 and the results showed that habitat quality was higher in upstream than downstream. Compared the habitat quality value in each eco-natural grade, the average habitat quality of 1st, 2nd and 3rd grades were 0.80, 0.76 and 0.71 respectively. The results of the correlation analysis with ecological watershed health data, the coefficient of determination (R²) was 0.58, and the person coefficient was 0.76. The results of this study may be used as foundation data to support habitat protection and implementation of long-term biodiversity-related policies.

미세먼지에 대한 연구는 실시간으로 발전하고 있으며, 예측 모델의 정확도를 향상시키기 위해 다양한 방법이 연구되고 있다. 또한 미세먼지의 정확한 원인과 영향을 파악하기 위해 이러한 다양한 요소들을 고려하는 연구들이 활발히 이루어지고 있다. 본 논문에서는 PM_2.5와 상관성이 있는 데이터를 계절을 기준으로 구분하여 학습하는 예측 모델과 특정 농도를 기준으로 저농도와 고농도를 구분하여 학습하는 모델을 통해 예측 성능의 비교 및 분석을 진행하였다. 기상데이터와 대기오염 물질 데이터를 사용하였으며 PM_2.5와 상관관계를 확인하여 학습 및 평가를 위한 데이터를 구성하였다. 계절별 예측 모델과 농도별 예측 모델은 LSTM으로 설계하였으며, 세부 파라미터는 하이퍼 파라미터 탐색을 통해 적용하였다. 예측 모델의 성능 평가는 정확도, RMSE, MAPE, 저농도와 고농도 구간에서의 정확도 그리고 AQI를 기준으로 4개의 범위에 대한 정확도로 진행하였다. 성능 평가 결과, 농도별 학습을 진행한 예측 모델이 AQI 기준 "나쁨" 구간의 정확도에서 91.02%의 정확도를 보였으며, 계절별 학습을 진행한 예측 모델보다 전반적으로 좋은 성능을 보였다.

Research on particulate matter is advancing in real-time, and various methods are being studied to improve the accuracy of prediction models. Furthermore, studies that take into account various factors to understand the precise causes and impacts of particulate matter are actively being pursued. This paper trains an LSTM model using seasonal data and another LSTM model using concentration-based data. It compares and analyzes the PM_2.5 prediction performance of the two models. To train the model, weather data and air pollutant data were collected. The collected data was then used to confirm the correlation with PM_2.5. Based on the results of the correlation analysis, the data was structured for training and evaluation. The seasonal prediction model and the concentration-specific prediction model were designed using the LSTM algorithm. The performance of the prediction model was evaluated using accuracy, RMSE, and MAPE. As a result of the performance evaluation, the prediction model learned by concentration had an accuracy of 91.02% in the "bad" range of AQI. And overall, it performed better than the prediction model trained by season.

본 연구는 미호천 유역의 월 단위 지하수위 관리 취약 시기 평가와 LSTM을 이용한 미래 지하수위 관리 취약 시기 평가 기법을 제안하였다. 미호천 유역 내의 지하수위 및 강수량 관측소 관측자료를 수집하고, LSTM을 구성한 후 강수량과 지하수위에 대한 2020~2022년 예측 값을 산정하고, 미래 지하수위 관리 취약시기 평가를 수행하였다. 지하수위 관리 취약시기 평가를 위하여 지하수위와 강수량 간의 상관관계를 고려한 가중치와 기후변화로 인한 관측자료의 변동을 고려하기 위한 가중치를 산정한 후, 이를 조합하여 최종 가중치를 산정하였다. 평가 결과 미호천 유역은 2월, 3월, 6월에 지하수위 관리 취약성이 높게 나타났고, 특히 천안수신 관측소 인근은 미래에 지하수위 관리 취약성 지수가 악화 될 것으로 분석되어 추가 관리 방안 도입이 필요할 것으로 나타났다. 본 연구의 결과는 지하수위 관리 취약 시기 평가 및 LSTM을 활용한 미래 예측 기법을 제시함으로써 발생할 수 있는 유역 내 지하수자원 문제에 선제적인 대응방안 도출에 기여할 것으로 기대된다.

This study proposed a evaluation of the monthly vulnerable period for groundwater level management in the Miho stream watershed and a technique for evaluating the vulnerable period for future groundwater level management using LSTM. Observation data from groundwater level and precipitation observation stations in the Miho stream watershed were collected, LSTM was constructed, predicted values for precipitation and groundwater levels from 2020 to 2022 were calculated, and future groundwater management was evaluated when vulnerable. In order to evaluate the vulnerable period of groundwater level management, the correlation between groundwater level and precipitation was considered, and weights were calculated to consider changes caused by climate change. As a result of the evaluation, the Miho stream watershed showed high vulnerability to underground water management in February, March, and June, and especially near the Cheonan Susin observation well, the vulnerability index for groundwater level management is expected to deteriorate in the future. The results of this study are expected to contribute to the evaluation of the vulnerable period of groundwater level management and the derivation of preemptive countermeasures to the problem of groundwater resources in the basin by presenting future prediction techniques using LSTM.

저자명 식별은 학술 정보 시스템의 핵심 과제이나, 영문 중심인 OpenAlex 모델의 국내 학술 생태계 적용성에 대한 검증은 미비하다. 본 연구는 KISTI OCEAN 데이터베이스의 2023~2024년 논문 54,049건을 활용해 OpenAlex 모델의 한국 데이터 적용성을 평가하고, 한국어 특성에 맞춘 7개 특성 최적화를 수행하였다. 단계적 실험 결과, F1 점수는 0.852(v1-1)에서 0.860(v2-2)으로 향상되었으며, 정답셋 보정 후에는 정확도 0.930, F1 점수 0.931을 달성하였다. 또한 ORCID 기반 교차 검증에서 F1 점수 0.892를 기록하여 모델의 신뢰성을 확인하였다. 특히 대규모 데이터의 효율적 관리를 위해 증분적 처리 방식을 도입하고 수작업 검증을 결합한 최적화 공정을 제안하였으며, 최종적으로 국내 저자 183,105명을 109,205개 식별자로 그룹화하는 파이프라인을 구축하여 실무적 타당성을 검증하였다.

Author Name Disambiguation(AND) is a critical task in scholarly information systems; however, the applicability of the English-centric OpenAlex model to the Korean academic ecosystem has yet to be fully validated. This study evaluates OpenAlex's performance using 54,049 papers (2023-2024) from KISTI's OCEAN database and optimizes seven features tailored to Korean linguistic characteristics. Stepwise experiments demonstrate that the F1-score improved from 0.852 (v1-1) to 0.860 (v2-2), ultimately achieving an accuracy of 0.930 and an F1-score of 0.931 after ground-truth refinement. Cross-validation with ORCID yielded an F1-score of 0.892, confirming the model's reliability. Specifically, we propose an optimization process that combines incremental processing with manual verification to manage large-scale data efficiently. Finally, the study validates a pipeline that successfully clusters 183,105 author records into 109,205 unique identifiers, verifying its practical feasibility and scalability for Korean scholarly metadata.

[목적] 본 연구는 2001년부터 2024년까지의 PGA 투어 데이터를 기반으로 선수의 경기 성적(총 타수)을 예측할 수 있 는 인공지능(AI) 회귀 모델을 구축하고, 그 성능을 분석·검증하는 데 목적이 있다. [방법] 선수별 시즌 기록(평균 타 수, 상금, 순위 등)을 활용하여 Random Forest Regressor와 Gradient Boosting Regressor 두 가지 모델을 구현하였다. 학습 데이터는 전체 경기 기록을 기반으로 구성되었으며, 예측 성능 평가는 MAE(평균 절대 오차), RMSE(평균 제곱 근 오차), R²(결정계수) 등의 지표를 중심으로 수행하였다. [결과] 두 모델 모두 안정적인 예측 성능을 보였으며, Gradient Boosting Regressor는 MAE 5.48, RMSE 6.94, R² .836을 기록하여 비교적 우수한 결과를 나타냈다. 이는 기 존 골프 예측 연구의 평균 오차 수준(6~8타)과 비교해 실용 가능성이 높은 수준으로 해석된다. [결론] 본 연구는 오픈 스포츠 데이터를 기반으로 경기력 예측 AI 모델의 실현 가능성을 제시하였으며, 향후 다양한 종목 및 성과 지표에 대한 확장 가능성과 실무 적용 가능성을 확인하였다.

[Purpose] This study aims to develop and evaluate AI-based regression models to predict golf players' performance—specifically total strokes—using PGA Tour data from 2001 to 2024. [Methods] Season-level player statistics, including average score, prize money, and ranking, were used as input variables to build two machine learning models: Random Forest Regressor and Gradient Boosting Regressor. Model performance was evaluated using standard regression metrics such as Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and R-squared (R²). [Results] Both models demonstrated stable prediction performance, with the Gradient Boosting Regressor showing superior results (MAE: 5.48, RMSE: 6.94, R²: 0.836). These outcomes indicate a competitive level of accuracy compared to existing golf prediction studies, which typically report MAE values in the range of 6 to 8 strokes. [Conclusion] The findings suggest that practical performance prediction is feasible using publicly available golf statistics, without the need for advanced shot-tracking data. The study also highlights the potential for future application in other sports domains and performance indicators.

Reliability is very important in wireless network since large number of wireless standards are widely used in our daily life. The network flow ratio and workload will increase significantly as well. It is observed that network manager is not able to ensure the reliability of the network even if the network connection is smooth. This paper proposes a network reliability evaluation model using factorization approach for the small and medium-sized wireless communication network. The factorization approach is a decomposition of an object into a product of other objects or factors, which when multiplied together give the original for example a number a polynomial or a matrix. With the model, the solution algorithms are proposed to work out the corresponding defined objectives. Experiments show that, the proposed model outperforms the ergodic method which uses large number of loops to obtain the network reliability. From the experiment, when Pc = 0.9 and Pm = 0.1 as well as Pc = 0.9 and Pm = 0.01, it could be find that there are six transmission lines which are with the maximum reliability.

With the rapid development of higher education, how to safeguard and promote the quality of degree training has increasingly become the focus of all sectors of society and training units. Strengthening evaluation is an important process to ensure the quality of the degree-granting. To weaken the human factor and reduce the complexity of human intervention in the evaluation process, this paper presents a new degree evaluation model. This model consists of a command management unit, data unit, sampling rules unit, index system unit, evaluation system unit and information feedback unit. In this model, data cleaning and data integration are used to deal with multi-source heterogeneous degree data, and the rule sampling method is applied to achieve the complex and diverse sampling requirements. To prove the scientific and effective nature of this evaluation model, we applied this model to a sampling of master's dissertations from Shanghai in 2014. The result of using this evaluation model on this sampling met the requirement of the Municipal Degree Committee.

In allusion to such problems as the no use of the structural information of the dataset in the traditional clustering effectiveness evaluation function and the excessive noisy point deletion, the research method integrating theoretical analysis and empirical analysis is adopted to establish KPI management index system model for telecommunication enterprises. A new clustering effectiveness evaluation function is proposed in this article. Specifically, PCA (principal component analysis) method in multivariate statistics is applied in the performance evaluation systems of telecommunication enterprises, and meanwhile relevant instances are analyzed and evaluated. Therein, the evaluation index system has the features of simpleness, strong practicability, low operation cost and high accuracy, and the geometric structure features of dataset are added for the performance evaluation of telecommunication enterprises. Additionally, distance critical value L is added in the compact indexes and the constraint condition thereof is also given in order to construct a new clustering effectiveness evaluation index model which can more scientifically and rationally reflect the actual evaluation result.

Multi-tenant data storage model has multiple solutions and comparing the different storage solutions can help users improve their work efficiency. This paper proposes a query performance evaluation method based on the relational algebra. First of all, we introduce three wide table models. Secondly, we unite the format of tenant query SQL statement by analyzing structure of storage model, replace the unified format SQL with the relational algebra and evaluate the I/O cost of SQL query using relational algebra. Finally, through theoretical calculations and experimental simulations, we evaluate the performance of multi-tenant storage model according to query performance. The results show our evaluation method based on relational algebra provides new perspective for the study of performance evaluation in multi-tenant data model.

Data mining is the process of searching the information from a large amount of data. In order to evaluate the stock crash this paper proposes general decrementing service M/G/1 queue system with multiple adaptive vacations to find information related to stock crash in data about Shanghai Composite Index. We use the probability generating function (P.G.F.) of stationary queue length and LST of waiting time, and their stochastic decomposition to calculate Existing money flow. Existing Money flow calculation model is improved based on the stationary queue length and LST of waiting time. We program to achieve the stock of existing money flow algorithm, and get the number of existing money flow. The improved algorithm can early warn the stock market crash. The empirical result shows that: There will be a rise in price before the Stock Market Crash, and the stock of existing money inflow begin to decrease. The stock market crash fell for at least six months. The stock market crash fell by at least fifty-five percent. Most of the stock market crash fell by over seventy-percent. The stock market crash down time is inversely proportional to the magnitude of the decline. If the down time is short, the magnitude of the decline is large. If the down time is long, the magnitude of the decline is small. The stock market crash is great harm to investors.

The vigorous development of various technologies in the cloud computation field promotes the development and progress of cloud services. But with the large accumulation of information data in the cloud services, in order to meet user’s needs of cloud services multi-function, the operation capacity of a single cloud service is not enough. Now, combining two or many cloud services is a hot research problem. The other hot research problem is that the task of data construction is assigned to different cloud service platforms. However, the combination schemes are too much, so how to ensure the optimal scheme is credible? It has become the key to solve the problem. After reading a large number of literatures, the paper proposes the big data reliable combination evaluation method based on the cloud service QoS model. By getting the contribution of each of the services in the combination scheme set, the method chooses the optimal cloud service combination scheme. Then the optimal scheme is evaluated its reliability.

It has been increasingly difficult to predict the amounts of Acer mono sap to be collected due to droughts and cold waves caused by recent climate changes with few studies conducted on the prediction of its collection volume. This study thus set out to propose a Big Data prediction system based on meteorological information for the collection of Acer mono sap. The proposed system would analyze collected data and provide managers with a statistical chart of prediction values regarding climate factors to affect the amounts of Acer mono sap to be collected, thus enabling efficient work. It was designed based on Hadoop for data collection, treatment and analysis. The study also analyzed and proposed an optimal prediction model for climate conditions to influence the volume of Acer mono sap to be collected by applying a multiple regression analysis model based on Hadoop and Mahout.

원자력 시설에서 방사선 방출에 의한 주거 인구에 미치는 영향을 분석평가하는데 부지의 기상 조건을 직접 관련시키는 방법을 고려해 보았다. 이 방법은 정상가동시에 누출되는 방사능과 가상사고시의 누출로 부터 자연환경에 주는 영향을 보다 현실에 맞게 평가하는데 사용될 수 있다. 개개인이 받을 방사선량과 전체인구가 받을 피폭선량을 보다 논리적으로 계산함으로써 설비 설계에 반영하여 누출량과 대기내의 화산을 별도로 분석하여 평가하는 재래식 방법으로 부터 초래되는 필요 이상의 안전설계를 지양할 수 있다.

A model is considered in order to evaluate the potential risk from a nuclear facility directly combining the on-site meteorological data. The model is utilized to evaluate the environmental consequences from the routine releases during normal plant operation as well as following postulated accidental releases. The doses to individual and risks to the population-at-large are also analyzed in conjunction with design of rad-waste management and safety systems. It is observed that the conventional analysis, which is done in two separate unaffiliated phases of releases and atmospheric dispersion tends to result in unnecessary over-design of the systems because of high resultant doses calculated by multiplication of two extreme values.