• Title/Summary/Keyword: validation.

Search Result 8,166, Processing Time 0.04 seconds

Design of weighted federated learning framework based on local model validation

  • Kim, Jung-Jun;Kang, Jeon Seong;Chung, Hyun-Joon;Park, Byung-Hoon
    • Journal of the Korea Society of Computer and Information
    • /
    • v.27 no.11
    • /
    • pp.13-18
    • /
    • 2022
  • In this paper, we proposed VW-FedAVG(Validation based Weighted FedAVG) which updates the global model by weighting according to performance verification from the models of each device participating in the training. The first method is designed to validate each local client model through validation dataset before updating the global model with a server side validation structure. The second is a client-side validation structure, which is designed in such a way that the validation data set is evenly distributed to each client and the global model is after validation. MNIST, CIFAR-10 is used, and the IID, Non-IID distribution for image classification obtained higher accuracy than previous studies.

The Proposed Validation Guidelines and Their Application for Performance Verification of UV-VIS Spectrophotometer (UV-VIS 분광기기의 성능검증을 위한 밸리데이션 가이드라인의 제정 및 응용)

  • Jin, Jing-Yu;Kang, Young-Koo;Lee, Won-Jae
    • YAKHAK HOEJI
    • /
    • v.50 no.3
    • /
    • pp.154-159
    • /
    • 2006
  • For the increasing demand for the validation of analytical results, one of the important concerns of the analyst is to be assured that the instrumentation is working to qualified conditions. In this study, we have investigated and compared several validation guidelines of the performance verification of UV-VIS spectrophotometer used in pharmacopoeias of major countries and UV-VIS instrument analytical companies, and we proposed the practically useful validation guidelines of UV-VIS spectrophotometer. Based on our proposed validation guidelines of UV-VIS spectrophotometer, several UV-VIS spectrophotometers used in drug manufacturing laboratories were validated for their performances.

CROSS- VALIDATION OF LANDSLIDE SUSCEPTIBILITY MAPPING IN KOREA

  • LEE SARO
    • Proceedings of the KSRS Conference
    • /
    • 2004.10a
    • /
    • pp.291-293
    • /
    • 2004
  • The aim of this study was to cross-validate a spatial probabilistic model of landslide likelihood ratios at Boun, Janghung and Yongin, in Korea, using a Geographic Information System (GIS). Landslide locations within the study areas were identified by interpreting aerial photographs, satellite images and field surveys. Maps of the topography, soil type, forest cover, lineaments and land cover were constructed from the spatial data sets. The 14 factors that influence landslide occurrence were extracted from the database and the likelihood ratio of each factor was computed. 'Landslide susceptibility maps were drawn for these three areas using likelihood ratios derived not only from the data for that area but also using the likelihood ratios calculated from each of the other two areas (nine maps in all) as a cross-check of the validity of the method For validation and cross-validation, the results of the analyses were compared, in each study area, with actual landslide locations. The validation and cross-validation of the results showed satisfactory agreement between the susceptibility map and the existing landslide locations.

  • PDF

Introduction to the Validation Module Design for CMDPS Baseline Products

  • Kim, Shin-Young;Chung, Chu-Yong;Ou, Mi-Lim
    • Proceedings of the KSRS Conference
    • /
    • 2007.10a
    • /
    • pp.146-148
    • /
    • 2007
  • CMDPS (COMS Meteorological Data Processing System) is the operational meteorological products extraction system for data observed from COMS (Communication, Ocean and Meteorological Satellite) meteorological imager. CMDPS baseline products consist of 16 parameters including cloud information, water vapor products, surface information, environmental products and atmospheric motion vector. Additionally, CMDPS includes the function of calibration monitoring, and validation mechanism of the baseline products. The main objective of CMDPS validation module development is near-real time monitoring for the accuracy and reliability of the whole CMDPS products. Also, its long time validation statistics are used for upgrade of CMDPS such as algorithm parameter tuning and retrieval algorithm modification. This paper introduces the preliminary design on CMDPS validation module.

  • PDF

Fire design of concrete encased columns: Validation of an advanced calculation model

  • Zaharia, R.;Dubina, D.
    • Steel and Composite Structures
    • /
    • v.17 no.6
    • /
    • pp.835-850
    • /
    • 2014
  • The fire resistance of composite steel and concrete structures may be determined by using the simplified methods provided in EN 1994-1-2. For the particular situations not covered by the standard, an advanced calculation model might be applied, using special purpose programs for the analysis of structures in fire. The validation of these programs has always been an important issue for software developers, but also for designers and authorities. Clause 4.4.4 from EN 1994-1-2 refers to the validation of the advanced calculation models and states that these models must be validated through relevant test results. The paper presents the calculation of fire resistance of the composite columns in a high-rise building built in Romania, and focusses on the validation of the calculation model (computer program SAFIR), for this particular case. This validation, asked by the Romanian authorities, considers the available experimental results of a fire test, performed on a similar composite steel-concrete column.

Validation Measures of Bicluster Solutions

  • Lee, Young-Rok;Lee, Jeong-Hwa;Jun, Chi-Hyuck
    • Industrial Engineering and Management Systems
    • /
    • v.8 no.2
    • /
    • pp.101-108
    • /
    • 2009
  • Biclustering is a method to extract subsets of objects and features from a dataset which are characterized in some way. In contrast to traditional clustering algorithms which group objects similar in a whole feature set, biclustering methods find groups of objects which have similar values or patterns in some features. Both in clustering and biclustering, validating how much the result is informative or reliable is a very important task. Whereas validation methods of cluster solutions have been studied actively, there are only few measures to validate bicluster solutions. Furthermore, the existing validation methods of bicluster solutions have some critical problems to be used in general cases. In this paper, we review several well-known validation measures for cluster and bicluster solutions and discuss their limitations. Then, we propose several improved validation indices as modified versions of existing ones.

Validation of UNIST Monte Carlo code MCS for criticality safety calculations with burnup credit through MOX criticality benchmark problems

  • Ta, Duy Long;Hong, Ser Gi;Lee, Deokjung
    • Nuclear Engineering and Technology
    • /
    • v.53 no.1
    • /
    • pp.19-29
    • /
    • 2021
  • This paper presents the validation of the MCS code for critical safety analysis with burnup credit for the spent fuel casks. The validation process in this work considers five critical benchmark problem sets, which consist of total 80 critical experiments having MOX fuels from the International Criticality Safety Benchmark Evaluation Project (ICSBEP). The similarity analysis with the use of sensitivity and uncertainty tool TSUNAMI in SCALE was used to determine the applicable benchmark experiments corresponding to each spent fuel cask model and then the Upper Safety Limits (USLs) except for the isotopic validation were evaluated following the guidance from NUREG/CR-6698. The validation process in this work was also performed with the MCNP6 for comparison with the results using MCS calculations. The results of this work showed the consistence between MCS and MCNP6 for the MOX fueled criticality benchmarks, thus proving the reliability of the MCS calculations.

The Differences of Self-Validation, Regulatory Focus and Information Distortion Between Happiness and Sadness (행복감정과 슬픔감정 간의 자기타당화와 규제초점 및 정보왜곡의 차이)

  • Choi, Nak-Hwan;Chen, Fei;Kim, Min-Ji
    • Science of Emotion and Sensibility
    • /
    • v.20 no.3
    • /
    • pp.71-88
    • /
    • 2017
  • This paper compared self-validation and regulatory focus between consumers who felt happy vs. sad prior to decision and explored the effects of self-validation on regulatory focus and information distortion. The results of empirical analysis are as follows. First, consumers who felt happy beforehand revealed larger self-validation and stronger promotion focus than those who felt sad in advance. Second, compared to sadness, just-felt happiness was found to have partially positive impact on promotion focus by means of self-validation and exercise entirely positive impact on information distortion through mediation of self-validation. This study has made theoretic contributions by identifying the differences in the extent of self-validation and promotion focus between happiness and sadness as ambient emotion felt prior to the impending decision making as well as by investigating the effects of self-validation upon information distortion.

Design of an Algorithm for the Validation of SCL in Digital Substations

  • Jang, B.T.;Alidu, A.;Kim, N.D.
    • KEPCO Journal on Electric Power and Energy
    • /
    • v.3 no.2
    • /
    • pp.89-97
    • /
    • 2017
  • The substation is a critical node in the power network where power is transformed in the power generation, transmission and distribution system. The IEC 61850 is a global standard which proposes efficient substation automation by defining interoperable communication and data modelling techniques. In order to achieve this level of interoperability and automation, the IEC 61850 (Part 6) defines System Configuration description Language (SCL). The SCL is an XML based file format for defining the abstract model of primary and secondary substation equipment, communications systems and also the relationship between them. It enables the interoperable exchange of data during substation engineering by standardizing the description of applications at different stages of the engineering process. To achieve the seamless interoperability, multi-vendor devices are required to adhere completely to the IEC 61850. This paper proposes an efficient algorithm required for verifying the interoperability of multi-vendor devices by checking the adherence of the SCL file to specifications of the standard. Our proposed SCL validation algorithm consists of schema validation and other functionalities including information model validation using UML data model, the Vendor Defined Extension model validation, the User Defined Rule validation and the IED Engineering Table (IET) consistency validation. It also integrates the standard UCAIUG (Utility Communication Architecture International Users Group) Procedure validation for quality assurance testing. Our proposed algorithm is not only flexible and efficient in terms of ensuring interoperable functionality of tested devices, it is also convenient for use by system integrators and test engineers.

Application of Time-series Cross Validation in Hyperparameter Tuning of a Predictive Model for 2,3-BDO Distillation Process (시계열 교차검증을 적용한 2,3-BDO 분리공정 온도예측 모델의 초매개변수 최적화)

  • An, Nahyeon;Choi, Yeongryeol;Cho, Hyungtae;Kim, Junghwan
    • Korean Chemical Engineering Research
    • /
    • v.59 no.4
    • /
    • pp.532-541
    • /
    • 2021
  • Recently, research on the application of artificial intelligence in the chemical process has been increasing rapidly. However, overfitting is a significant problem that prevents the model from being generalized well to predict unseen data on test data, as well as observed training data. Cross validation is one of the ways to solve the overfitting problem. In this study, the time-series cross validation method was applied to optimize the number of batch and epoch in the hyperparameters of the prediction model for the 2,3-BDO distillation process, and it compared with K-fold cross validation generally used. As a result, the RMSE of the model with time-series cross validation was lower by 9.06%, and the MAPE was higher by 0.61% than the model with K-fold cross validation. Also, the calculation time was 198.29 sec less than the K-fold cross validation method.