Annals of Applied Sport Science

Background. Simultaneous tiredness of two or more muscles around a joint can be defined as coordinated fatigue (co-fatigue) and might occur between agonist and antagonist muscles, and vary according to the level of sporting activity levels or gender.
Objectives. The aim of this study was to determine the levels of coordinated fatigue in agonist and antagonist muscles during squat-press exercise.
Methods. Twenty athletes and twenty sedentary subjects participated in the study. Surface electromyography signals of the rectus femoris, vastus lateralis obliquus, biceps femoris and semitendinosus muscles were recorded at the squat press position for 15 seconds during isometric contraction. Measurements were repeated five times and a 2-minute rest period was allowed between repetitions. After erroneous EMG elimination, movement artefacts were removed by using a 20 Hz high-pass Butterworth filter. Then, as a well-recognized fatigue index, the median frequency (MF) of each filtered middle part of the EMG signal (5 to 10 s. of contraction) was calculated, given that it is known that the MF decreases during isometric contractions. Finally, each MF-based co-fatigue index was calculated by dividing the mean RF and VLO median frequencies by the mean ST and BF median frequencies. The cumulative co-fatigue values of “male vs. female” and “sedentary vs. athlete” comparisons were performed by using a two-sided Student t-test with a Bonferroni correction.
Results. There was a statistically significant (Bonferroni corrected p-value < 0.05) difference between the mean female (1.57 ∓ 0.53) and the mean male (1.23 ∓ 0.17) co-fatigue values, while there was no statistically significant difference between the mean co-fatigue values of sedentary (1.51 ∓ 0.52) and athlete (1.29 ∓ 0.27) subjects.
Conclusion. The offered co-fatigue indices might be useful for other sports, physiotherapy and related areas if sufficient scientific proof is accumulated.

Background. Combining a One-Class Support Vector Machine (OCSVM) with a Convolutional Neural Network (CNN) is presented as a novel technique for detecting fraud in Enterprise Resource Planning (ERP) systems.
Objectives. The objective of this research is to develop a technique for detecting fraud in Enterprise Resource Planning (ERP) systems by combining a One-Class Support Vector Machine (OCSVM) with a Convolutional Neural Network (CNN), suitable for the Spor Istanbul ERP system.
Methods. This study examines the ERP system utilized by Spor Istanbul, the largest sports enterprise in Turkey, as a case study. The study utilizes a custom database of web-based program files to create a dataset of benign and malicious JavaScript applications. Firstly, the text and control flow graph of the program is analyzed. Secondly, the OCSVM method is applied as an outlier detection technique, and CNN is used as a classifier.
Results. The experimental results indicate that the proposed OCSVM-CNN approach achieves higher accuracy (96.78%) in detecting malicious scripts compared to using only CNN (94.8%).
Conclusion. The research contributes to the development of multi-layered ERP software architecture with AI decision support, improving fraud detection in ERP systems.

Background. The study involves determining individuals' intrinsic leisure motivations and experience preferences for recreation when using various recreational areas such as family life centers.
Objectives. The study analyzes intrinsic leisure motivation and preference for recreation experience in individuals attending family life centers.
Methods. The study was conducted with 240 participants participating in recreational activities in Family Life Centers in Ankara. Data were collected by face-to-face survey method. In addition to the demographic data form, "Intrinsic Leisure Motivation Scale" and "Recreation Experience Preference Scale" were collected. As a result of the analysis, parametric tests were applied since it was determined that the data showed normal distribution. Descriptive statistics, independent samples t-test, one-way variance analysis ANOVA, and Tukey test were used to determine the relationships between groups.
Results. The findings indicate that the participants' intrinsic leisure motivation and recreation experience preference scores are similarly high. There are statistically significant differences between the participants' gender, age, education level, daily leisure duration, and efficient use of leisure and measurement tools.
Conclusion. It is suggested that various variables of the participants participating in recreational activities in family centers differentiate their intrinsic leisure motivation and recreational experience preferences, so it is recommended that programs that will make their motivation and preference factors sustainable should be continued in the centers.