EVALUATION OF ARTIFICIAL NEURAL NETWORKS EFFECTIVENESS FOR UNFOLDING GAMMA-SPECTRUM OF 137CS
نویسندگان
چکیده
Development of machine learning methods for spectrum processing is one the most promising ways gamma- spectrometry automation and accuracy improvement. Effectiveness fully connected convolution neural networks quantitative γ-spectrometry analysis using scintillation detector NaI(Tl) lead shielding presented in article. Semi-synthetic spectrums were used models training; semi-synthetic are channels additions random measured at a short duration. The shows advantages artificial compare to common analytical method unfolding. mean square error activity evaluation 2–4 times lower than if measuring time equal 100 s. In highly standardized conditions measuring, appear with increasing radiation source activity. Validation sources not training has shown can have over standard when γ-radiation relatively high.
منابع مشابه
HYBRID ARTIFICIAL NEURAL NETWORKS BASED ON ACO-RPROP FOR GENERATING MULTIPLE SPECTRUM-COMPATIBLE ARTIFICIAL EARTHQUAKE RECORDS FOR SPECIFIED SITE GEOLOGY
The main objective of this paper is to use ant optimized neural networks to generate artificial earthquake records. In this regard, training accelerograms selected according to the site geology of recorder station and Wavelet Packet Transform (WPT) used to decompose these records. Then Artificial Neural Networks (ANN) optimized with Ant Colony Optimization and resilient Backpropagation algorith...
متن کاملscour modeling piles of kambuzia industrial city bridge using hec-ras and artificial neural network
today, scouring is one of the important topics in the river and coastal engineering so that the most destruction in the bridges is occurred due to this phenomenon. whereas the bridges are assumed as the most important connecting structures in the communications roads in the country and their importance is doubled while floodwater, thus exact design and maintenance thereof is very crucial. f...
Performance evaluation of artificial neural networks in statistical downscaling of monthly precipitation (Case study: Minab watershed)
متن کامل
Application of Artificial Neural Networks for Analysis of Flexible Pavements under Static Loading of Standard Axle
In this study, an artificial neural network was developed in order to analyze flexible pavement structure and determine its critical responses under the influence of standard axle loading. In doing so, more than 10000 four-layered flexible pavement sections composed of asphalt concrete layer, base layer, subbase layer, and subgrade soil were analyzed under the impact of standard axle loading. P...
متن کاملEvaluation of loading efficiency of azelaic acid-chitosan particles using artificial neural networks
Objective(s): Chitosan, a biodegradable and cationic polysaccharide with increasing applications in biomedicine, possesses many advantages including mucoadhesivity, biocompatibility, and low-immunogenicity. The aim of this study, was investigating the influence of pH, ratio of azelaic acid/chitosan and molecular weight of chitosan on loading efficiency of azelaic acid in chitosan particles. Mat...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Žurnal Belorusskogo gosudarstvennogo universiteta
سال: 2021
ISSN: ['2663-7294', '2521-6821']
DOI: https://doi.org/10.46646/2521-683x/2021-2-44-54