سعیده علی اکبری

The main purpose of machine learning is a complex process that is carried out by determining the model and training it using a large volume of data. In the past, the main focus in this field was more on improving the structures of models and algorithms, but recently more emphasis has been placed on the quality and quantity of data. This article aims to provide an overview of the problems in data collection and offer a solution for them.

In this study, the challenges faced by researchers in collecting data and evaluating supervised machine-learning models were examined through a review method. Documentation from PubMed, Scopus, Science Direct databases, and Google Scholar search engine from 2001 to 2023 was retrieved. After screening, a total of 17 full articles were reviewed and included in the study.

The findings indicate that researchers in supervised machine learning studies face four challenges in data collection, which are: insufficient number of samples, unrepresentative training data, poor data quality, and irrelevant features, and in model evaluation, they face four challenges: overfitting, lack of generalizability, lack of sufficient data for validation, and mismatched data.

Increasing the sample size, utilizing a random selection algorithm, data cleansing, using the correct statistical test, feature selection, feature extraction, using a simpler model, the K-fold technique, and data processing are among the factors that contribute to achieving a model with better performance.

The present study seeks to investigate the relationship between the values of the parents and the values of the children. System values as the most basic components of culture in every society is usuallyreproducedthrough a gradual influence of personality, Institutions and social structures And the psychological and social contexts in the light of the prevailing discourse of society keep on surviving. Changes in values, caused changes in the behavior of society. The theoretical framework of this research is based on the ideas of Robert Merton ,The convergence-based mechanical view, divergence-based discourse, Martin Inglhart, Yan Robertson, Mannheim. The research was conducted through questionnaire among 400 families with to a random sampling living in Tehran.aged 30-15 years old, for a cluster of five district: North, South, East, West and center of Tehran aredistributed.TheCronbach''''s alpha test showed that the main indicators of the validity of this study is relatively high. The statistical techniques used are frequency distribution table, central statistics and dispersion, factor analysis, correlation between variables. Findings show that there is a meaningful relationship between the values of parents and children and is the most convergent between the social values of parents and the social values of parents.

In the recent decades the Monte Carlo simulation in the field of radiation therapy has been used a lot. In this study photon contamination of Lead free and flexible internal shield was investigated in the electron field.
Subjects and To evaluate photon contaminationthat caused by this new material in the electron field by Mont Carlo study. Varian 2100 C/D was validated within measurement and then by given energy spectrum shield thickness and photon contamination were obtained and compared to those of lead.
The results show that this material required 1.2 times thickness of those leadfor providing protection. In addition, it causes photon contamination approximately equal those of lead for energy 6 and 9 MeV.
It can be concluded that thickness of specific combination (70% W, 18.61% Ni, 11/39% c) which has equal transmission same as lead caused photon contamination equal those of Lead that it can be acceptable under clinical condition.