A methodology for enhancing the reliability of expert system applications in probabilistic risk assessment
روشی برای افزایش قابلیت اطمینان برنامه های کاربردی سیستم خبره در ارزیابی ریسک احتمالی-2019
In highly complex industries, capturing and employing expert systems is significantly important to an organizations success considering the advantages of knowledge-based systems. The two most important issues within the expert system applications in risk and reliability analysis are the acquisition of domain experts professional knowledge and the reasoning and representation of the knowledge that might be expressed. The first issue can be correctly handled by employing a heterogeneous group of experts during the expert knowledge acquisition processes. The members of an expert panel regularly represent different experiences and knowledge. Subsequently, this diversity produces various sorts of information which may be known or unknown, accurate or inaccurate, and complete or incomplete based on its cross-functional and multidisciplinary nature. The second issue, as a promising tool for knowledge reasoning, still suffers from lack of deficiencies such as weight and certainty factor, and are insufficient to accurately represent complex rule-based expert systems. The outputs in current expert system applications in probabilistic risk assessment could not accurately represent the increasingly complex knowledge-based systems. The reason is the lack of certainty and self-assurance of experts when they are expressing their opinions. In this paper, a novel methodology is presented based on the concept of Znumbers to overcome this issue. A case study in a high-tech process industry is provided in detail to demonstrate the application and feasibility of the proposed methodology.
Keywords: Confidence level | Z-numbers | Fault tree analysis | Spherical hydrocarbon storage tank
Application of machine learning in safety evaluation of athletes training based on physiological index monitoring
کاربرد یادگیری ماشینی در ارزیابی ایمنی تمرینات ورزشکاران بر اساس نظارت بر شاخص فیزیولوژیکی-2019
In order to realize the monitoring and adaptive evaluation of athletes training safety, the physiological index monitoring and training safety evaluation method of athletes based on machine learning is put forward. Taking the physiological index parameters such as heart rate HR, maximum oxygen uptake VO2max, oxygen pulse O2P, respiratory entropy RQ, maximum ventilation (VEmax) as constraint indexes, the physiological index monitoring big data analysis model of athlete training safety evaluation is constructed. The multivariate index joint analysis modeling method is used to reconstruct the characteristics of athletes physiological index monitoring, the related characteristic quantities of athletes physiological index monitoring data are extracted, the correlation of athletes physiological indexes is analyzed by using association rule reconstruction method, and the adaptive training of athletes physiological index monitoring and safety evaluation is carried out combined with machine learning method. The statistical analysis and optimization control model of athletes training safety evaluation is constructed, and the physiological index monitoring and training safety evaluation of athletes are realized under machine learning. The simulation results show that the confidence level of this method is high and the convergence of the evaluation process is good, so it has a good application value in athletes training and physiological monitoring.
Keywords: Physiological index monitoring | Athletes | Training | Safety assessment | Machine learning
Estimation of missing values in a food property database by matrix completion using PCA-based approaches
برآورد ارزش های گم شده در یک پایگاه داده دارایی مواد غذایی با تکمیل ماتریس با استفاده از رویکردهای مبتنی بر PCA-2017
In this work, five matrix completion algorithms were investigated for the estimation of missing values in a food property database: iterative PCA with (IPCAE) and without (IPCA) early stopping, trimmed scores regression with (TSRE) and without (TSR) early stopping and variational Bayesian PCA (VBPCA). Matrix completion was applied in the context of a food property database (31 properties×663 observations) developed by meta-analysis for new food product development, a novel application of matrix completion. The database contained 68.7% of missing values. VBPCA and TSRE were the most accurate algorithms and explained on average 42% and 40%, respectively, of the variance of the missing values. The incorporation of an early stopping step in the TSR and IPCA algorithms decreased overfitting and improved significantly their accuracy. The accuracy of the missing value estimates varied significantly according to the property, and the coefficient of determination for each property with VBPCA ranged from 0.02 to 0.84. The accuracy of the missing value estimates was higher when the property known for only a few observations were included in the database, indicating that the matrix completion algorithms successfully used the additional information that those properties provided to improve the estimation of the other properties in the database. For 17% of the database, the matrix completion algorithms could identify if the missing value was above or below the average value of the property with a confidence level above 90%, providing additional information for product characterization at no experimental cost.
Keywords: Matrix completion | Principal component analysis (PCA) | Trimmed scores regression (TSR) | Food properties | Database
Gender Violence and Social Networks in Adolescents: The Case of the Province of Malaga
خشونت جنسیتی و شبکه های اجتماعی نوجوانان: مورد استان مالاگا-2017
Gender violence and the violence exerted on social networks are particularly current issues of interest for both the scientific community and the media. When both types of violence are present during adolescence, a more specific area of study arises that is circumscribed to cyberbullying exerted and suffered by adolescents on the Internet. This work is part of a larger project carried out in secondary schools in Spain, with special focus on Andalusia (financed by BBVA, 2014-2016). The case here presented is the one for the province of Malaga. The educational community of Malaga is of a peculiar and heterogeneous nature that combines a large foreign section of the population that was the result of tourism (since the seventies in the past century) with other migratory phenomena that are shared with other regions of Spain. The purpose of the study was to show the prevalence of gender violence among adolescent students in the 15-17-year age bracket from the province of Malaga, and to identify the predictive factors of occasional and frequent violence on social networks. A survey was designed and validated that was applied in electronic format to a random sample of public schools in Malaga (n=282). The sample size allowed us to work with an error of ±0.06 (confidence level of 95%). The results and conclusions identify predictive factors of occasional and frequent violence, and suggest improvements to be made in action guidelines and protocols, as well as in the action to foster awareness among adolescents and the general public in regard to these issues.
Keywords: Student violence | Bullying | Cyberbullying | Adolescents
Development of a machine vision system for determination of mechanical properties of onions
توسعه یک سیستم بینایی ماشین برای تعیین خواص مکانیکی پیاز-2017
In this research, a machine vision system was developed to measure the contact area and dimensions of agricultural samples in mechanical properties testing. Two probes were made of aluminum and round glass panes. The Universal Testing Machine was equipped with these probes. One camera was positioned inside the probe to monitor the contact area between probe and samples. Other camera was located out- side of probe to measure dimension of samples during the test. Onions were selected as study products and those mechanical properties were measured using this machine vision system. Also, to verify the results of this system, the mechanical properties were calculated using conventional methods. The effects of onion cultivars (red and yellow), loading direction (polar and equatorial) and loading speed (15 and 25 mm/min) on the size of contact area, the stress and strain, elasticity modulus and Poisson’s ratio were examined. The results showed that there was no any statistically significant differences between conven- tional method and our presented method at 99% confidence level. Therefore, a machine vision system can be replaced with conventional method. It was possible to assimilate the shape of contact area to a near perfect circle. The effect of loading direction on Poisson’s ratio and the loading speed on stress and elas- ticity modulus were significant. Red onions under polar loading with speed 15 mm/min had maximum Poisson’s ratio, stress and modulus of elasticity. The stress was obtained as 0.281 ± 0.044 MPa. The values of elasticity modulus were obtained as 2.56 ± 1.4 and 2.77 ± 1.8 MPa for yellow and red onions, respec- tively. The Poisson’s ratio along x and y axis were obtained as 0.393 ± 0.05 and 0.375 ± 0.07, respectively. Polar loading samples were easy to deform laterally compared to equatorial loading samples. The contact area, stress and Poisson’s ratio increased with increasing deformation while the modulus of elasticity decreased.© 2017 Elsevier B.V. All rights reserved.
Keywords:Contact area | Image analysis | Machine vision | Modulus of elasticity | Onion | Poisson’s ratio
Analysis of LBLOCA using best estimate plus uncertainties for three-loop nuclear power plant power uprate
تجزیه و تحلیل LBLOCA با استفاده از بهترین تخمین عدم قطعیت پلاس برای uprate نیروگاه برق هسته ای سه حلقه ای-2016
The best estimate (BE) calculation with uncertainty evaluation of large break loss of coolant accident (LBLOCA) has been increasingly applied to the licensing applications of nuclear power plants (NPPs). The KINS-realistic evaluation methodology (KINS-REM) was developed for the independent audit calcu- lation based on the best estimate plus uncertainty (BEPU) method, and the code accuracy and statistical method have been improved. Power uprate has been implemented at a number of NPPs in many coun- tries. It is generally categorized based on the increment of power and the method of increasing power. In this study, assuming the 4.5% stretch power uprate of typical three-loop nuclear power plant and cor- responding design modifications, the LBLOCA was analyzed by applying the KINS-REM. The MARS-KS code was used as a frozen BE code, and 18 uncertainty parameters were considered in the analysis. The nodalization of the three-loop plant was defined by implementing specific separate and integral effect test nodalization scheme, and the thermal–hydraulic behavior in the system during the LBLOCA was analyzed through the basecase calculation. The 95 percentile peak cladding temperature (PCT) with 95% confidence level was determined by 124 calculations based on Wilks’ formula of the non-parametric statistics, and additional biases for emergency core coolant (ECC) bypass and steam binding were added to account for untreatable phenomena and models. It was confirmed that the analysis results of the LBLOCA for the three-loop plant power uprate met the PCT acceptance criteria.© 2015 Elsevier Ltd. All rights reserved.
Keywords: LBLOCA | KINS-REM | Stretched power uprate
رویکرد داده کاوی برای ارزیابی آموزش در آموزش مبتنی بر شبیه سازی
سال انتشار: 2015 - تعداد صفحات فایل pdf انگلیسی: 10 - تعداد صفحات فایل doc فارسی: 27
با تکامل قابل توجه فن آوری کامپیوتر، شبیه سازی به یک ابزار یادگیری تجربی واقعی تر و موثرتر برای کمک به آموزش سازمانی تبدیل شده است. اگر چه آموزش مبتنی بر شبیه سازی می تواند اثربخشی آموزش برای کارکنان شرکت را بهبود بخشد، همچنان چالش های مدیریتی بسیاری وجود دارد که باید برطرف شود. این مقاله یک چارچوب ترکیبی توسعه می دهد که تکنیک های داده کاوی را با آموزش مبتنی بر شبیه سازی ادغام می کند تا اثربخشی ارزیابی آموزش بهبود پیدا کند. مفهوم یادگیری مبتنی بر اعتماد به نفس اعمال می شود تا نتایج آموزش کارآموزان از دو بعد دانش / سطح مهارت و سطح اعتماد به نفس ارزیابی شود. تکنیک های داده کاوی برای تجزیه و تحلیل پروفایل کارآموزان و اطلاعات تولید شده از آموزش مبتنی بر شبیه سازی برای ارزیابی عملکرد کارآموزان و رفتار یادگیری آنها مورد استفاده قرار می گیرد. روش ارائه شده با مثالی از یک مورد واقعی آموزش تیراندازی پیاده نظام مبتنی بر شبیه سازی در تایوان نشان داده شده است. نتایج نشان می دهد که روش پیشنهادی می تواند به دقت عملکرد کارآموزان و رفتارهای یادگیری آنها را ارزیابی کرده و دانش نهفته برای بهبود یادگیری کارآموزان را کشف کند. کلمات کلیدی: ارزیابی آموزش، شبیه سازی، سیستم های چند رسانه ای، داده کاوی
|مقاله ترجمه شده|