جستجوی مقالات مرتبط با کلیدواژه « Artificial Neural Network » در نشریات گروه « تربیت بدنی »

The aim of this research was Investigating and Prioritizing Factors Affecting Cyberloafing Behavior among Youth and Sport Office Employees in Yazd Province using Artificial Neural Network Technique. This study was an applied research in terms of purpose and a descriptive- survey research in terms of method. The statistical population was the employees of youth and sport office in Yazd province. The statistical sample was selected using simple random sampling method. For gathering data about dependent variable, 22-item cyberloafing behavior scale by Stoddart (2016) was used. Reliability of scale was confirmed by Cronbach’s Alfa and validity of the scale was confirmed by content analysis. Data were analyzed using SPSS software version 24. For analysis of data including 23 independent variables and one dependent variable, two types of neural network including MLP and RBF were designed and implemented. Correct percent of cyberloafing prediction in the training, testing and validation data for the MLP neural network was 87.8, 75.0 and 72.7, respectively, and 83.6, 81.8 and 91.7 for the RBF neural network, respectively. The area under the rock for MLP and RBF networks was 0.611 and 0.677 respectively. Comparison of two MLP and RBF neural networks based on rock curve and prediction Correct percent showed that RBF neural network is more effective in forecasting cyberloafing, and the variables Proximity of supervisor, teaching master students, age and locus of control had the greatest impact on cyberloafing.

The purpose of this study was to design a model for prioritizing the factors influencing the acceptance of social responsibility using artificial neural networks. The method of this research is descriptive-survey. The statistical population of the research is all employees of the Department of Sports of Kurdistan Province, which was 240 at the time of the research. The target population is, in the first place, experts in the academic field. In the first phase, four main dimensions of social responsibility were collected by studying literature of authoritative literature (library studies) (Table 1).These factors were at the disposal of the panel of experts, including 11 university professors. The experts verified the content validity of the factors with an average above 79/0. The statistical population in the second section was the staff and managers of the Department of Sports and Youth of Kurdistan province. Based on the Klein index, 100 individuals were selected as the sample. After ensuring the initial validity, the components were based on a Likert scale-based questionnaire. Structural Validity (Confirmatory Factor Analysis) and Reliability (Cronbach's Alpha) were evaluated. Finally, validity (0.79) and structural reliability (0.891) were confirmed. Then, using artificial neural network method, the factors influencing the acceptance of social responsibility among employees were estimated and measured. The results of the research showed that, in the process of accepting social responsibility among employees, the component of ethics of business in the first priority and the component of economic needs were placed in the top priority.

The aim of this research was to optimize of resistance training volume for improvement maximal strength with the help of artificial neural network. For this purpose, 12 different combines of sets and repetitions has considered, then 94 untrained male selected as available sample between all boy students of Hakim Sabzevari University (age: 22±1.2 years, height: 173±7 cm, body mass: 66±10.7 kg) that had registered physical education, and were randomly assigned to 8 training groups (3×3 RM, 3×4 RM, 3×6 RM, 4×4 RM, 4×6 RM, 5×3 RM, 5×5 RM and 5×6 RM), and 4 remained groups (3×5 RM, 4×3 RM, 4×5 RM and 5×4 RM) eliminated from proposed sets and repetitions domain because with the help of artificial neural network can be predicted results of this groups. Subjects in each training groups performed bench press, leg press, rowing and lying leg adduction exercises, 2 days per week, for 8 weeks. Before beginning and after ending of training period, lean body mass, body fat percentage, and 1 repetition maximum (1RM) values for leg press and bench press was measured. In this research artificial neural network model, designed with 2 input variables and one output variable. At the end, the results of experimental and predicted groups, that they have stated in percentage, was compared with each other, and following results gained: the 5×6 RM group achieved greater increase in leg press 1RM and lean body mass and greater decrease in body fat percentage, whereas 4×4 RM group achieved greater increase in bench press 1RM. According to these results, people who are interested to gain greater maximal strength in lower body muscles, lean body mass and decrease in body fat percentage, in above-mentioned of domain of sets and repetitions, high volumes training protocol, is superior to other protocols; whereas increasing of maximal strength in upper body muscles by use of lower volume protocols, will be achieved too.