This research investigated the difference in aspects of gaze control between esports experts (Expert) and players with lower skills (Low Skill) while playing the real-time strategy game called ...StarCraft. Three versions of this game at different difficulty levels were made with the StarCraft Editor, and the gaze movements of seven Expert and nine Low Skill players were analyzed while they played the games. The gaze of Expert players covered a significantly larger area in the horizontal direction than the gaze of Low Skill players. Furthermore, the magnitude and number of saccadic eye movements were greater, and saccade velocity was faster in the Expert than in the Low Skill players. In conclusion, StarCraft experts have a specific gaze control ability that enables them to quickly and widely take visual information from all over the monitor. This could be one of the factors enabling StarCraft experts to perform better than players with lower skills when playing games that require task-switching ability.
This study investigated the specific gaze control ability of expert players and low-skill players of League of Legends (LoL). Eleven expert and nine low-skill players were divided according to their ...official ranking. Then, the gaze movement of each participant when performing each task (e.g., easy task and moderate task) while competing against a computer artificial intelligence system was recorded. Experts were found to have a significantly wide horizontal gaze distribution. Additionally, experts had a consistently short gaze fixation duration during the moderate task. These results suggest that a wide horizontal gaze distribution allows experts to obtain information from a wider area. Additionally, the consistently short fixation duration of the experts indicated that they need only a short period to assess information, which is advantageous because large amounts of information need to be processed within a limited time while playing. This specific gaze control ability could be an important factor that contributes to the superior performance of expert LoL players.
•We investigated cortical activity and game performance in first-person shooter (FPS) players in similar to actual gaming environments.•High-skilled FPS players have fast reaction times and high ...accuracy during tasks.•High-skilled FPS players had a lower delta and theta power spectral density in the frontal and temporal areas.•High cortical activity and accuracy during the task were associated.
First-person shooting (FPS) games are among the most famous video games worldwide. However, cortical activities in environments related to real FPS games have not been studied. This study aimed to determine differences in cortical activity between low- and high-skilled FPS game players using 160-channel electroencephalography. Nine high-skilled FPS game players (official ranks: above the top 10%) and eight low-skilled FPS game players (official ranks: lower than the top 20%) were recruited for the experiment. The task was set for five different conditions using the AimLab program, which was used for the FPS game players’ training. Additionally, we recorded the brain activity in the resting condition before and after the task, in which the participants closed their eyes and relaxed. The reaction time and accuracy (the number of hit-and-miss targets) were calculated to evaluate the task performance. The results showed that high-skilled FPS game players have fast reaction times and high accuracy during tasks. High-skilled FPS game players had higher cortical activity in the frontal cortex than low-skilled FPS game players during each task. In low-skilled players, cortical activity level and performance level were associated. These results suggest that high cortical activity levels were critical to achieving high performance in FPS games.
This research investigated the difference in aspects of gaze control between esports experts (Expert) and players with lower skills (Low Skill) while playing the real-time strategy game called ...StarCraft. Three versions of this game at different difficulty levels were made with the StarCraft Editor, and the gaze movements of seven Expert and nine Low Skill players were analyzed while they played the games. The gaze of Expert players covered a significantly larger area in the horizontal direction than the gaze of Low Skill players. Furthermore, the magnitude and number of saccadic eye movements were greater, and saccade velocity was faster in the Expert than in the Low Skill players. In conclusion, StarCraft experts have a specific gaze control ability that enables them to quickly and widely take visual information from all over the monitor. This could be one of the factors enabling StarCraft experts to perform better than players with lower skills when playing games that require task-switching ability.
The term "esports" refers to all sporting competitions played with electronic devices, and highly skilled esports players are known to possess superior physical characteristics. In this study, we ...focused on the activity of the forearm and hand intrinsic muscles during esports as an index that reflects the superior physical characteristics of esports experts. The analysis method of examining the mean power frequency of muscle activity is widely used in the field of sports science as a method of quantitatively evaluating muscle activity. In this study, we aimed to investigate the correlation between the mean power frequency of forearm and hand intrinsic muscles and performance level during esports in order to examine some of the superior physical characteristics of skilled esports players. 10 adult male subjects (age: 24.7 ± 2.7 years, experience: 10.6 ± 7.6 years, mean ± standard deviation) with esports experience were included in the study. Participants performed 5 different tasks created using AimLab. The activity of the radial carpal flexor, extensor carpi radialis, first dorsal interosseous muscle, and short thumb abductor muscles during the tasks was measured by surface electromyography. Correlation analysis showed that the lower the mean power frequency of activity of the extensor carpi radialis muscle, the higher the success rate and the faster the reaction time during the task (p<0.05). These results indicate that forearm extensor muscle activity may contribute to quick and accurate movement control during esports.
The current study investigated the gaze movements of FPS gamers in actual game environments. We developed a low-cost analysis tool using Python to identify gaze movements in real-world gaming ...environments. In Experiment 1, 11 middle-skilled and ten high-skilled FPS gamers performed a task under the experimental condition. Gaze position, reaction time, and accuracy were calculated during the task. Reaction time exhibited a significant positive correlation with task accuracy, suggesting that speed and accuracy were associated with higher game performance. The middle-skilled gamers had a significantly wider horizontal gaze distribution than the high-skilled gamers, and gaze distribution and reaction time showed a negative correlation. These results suggested that high-skilled players utilize peripheral vision during gameplay. In Experiment 2, 15 middle-skilled and 12 high-skilled FPS gamers performed an actual FPS game match. The gaze distribution, kill/death/assist ratio (KDA), and percentage of gaze on game information were calculated. In experiment 2, gaze locations in less important areas were positively correlated with KDA. Thus, performance was determined by the important areas where the gaze was focused rather than by the coordination of gaze position alone. Therefore, a broader range of environments is necessary to comprehend the superior performance of FPS gamers.
Predicting Other's Minds Using Model-based Reinforcement Learning Joo, Haram; Jeong, Inhyeok; Baek, Jong Woo ...
2022 Joint 12th International Conference on Soft Computing and Intelligent Systems and 23rd International Symposium on Advanced Intelligent Systems (SCIS&ISIS),
2022-Nov.-29
Conference Proceeding
Most of the studies on model-based reinforcement learning (RL) have been confined to single agent learning scenarios. This impedes us from fully exploring the nature and potential of model-based RL. ...In this study, we design a simple model-based RL agent capable of performing multi-agent tasks and evaluate the ability of model-based RL using various types of iterative Keynesian beauty contests. We examined its characteristics from various perspectives, including dominance in the competition as a performance measure, evolutionary process as an adaptation measure, the rate of convergence to the Nash equilibrium as a basic measure of effectiveness, and the degree of cooperation as an alternative measure of it. Simulations showed that the model-based RL agent outperforms other types of agents, including rule-based methods and model-free RL, by all measures.
To evaluate a fully deep learning mask region-based convolutional neural network (R-CNN) method for automated tooth segmentation using individual annotation of panoramic radiographs.
In total, 846 ...images with tooth annotations from 30 panoramic radiographs were used for training, and 20 panoramic images as the validation and test sets. An oral radiologist manually performed individual tooth annotation on the panoramic radiographs to generate the ground truth of each tooth structure. We used the augmentation technique to reduce overfitting and obtained 1024 training samples from 846 original data points. A fully deep learning method using the mask R-CNN model was implemented through a fine-tuning process to detect and localize the tooth structures. For performance evaluation, the F1 score, mean intersection over union (IoU), and visual analysis were utilized.
The proposed method produced an F1 score of 0.875 (precision: 0.858, recall: 0.893) and a mean IoU of 0.877. A visual evaluation of the segmentation method showed a close resemblance to the ground truth.
The method achieved high performance for automation of tooth segmentation on dental panoramic images. The proposed method might be applied in the first step of diagnosis automation and in forensic identification, which involves similar segmentation tasks.
Mitochondrial dysfunction is a key element in the progression of Parkinson's disease (PD). The inefficient operation of the electron transport chain (ETC) impairs energy production and enhances the ...generation of oxidative stress contributing to the loss of dopaminergic cells in the brain. ATPase inhibitory factor 1 (IF1) is a regulator of mitochondrial energy metabolism. IF1 binds directly to the F
Fo ATP synthase and prevents ATP wasting during compromised energy metabolism. In this study, we found treatment with IF1 protects mitochondria against PD-like insult in vitro. SH-SY5Y cells treated with IF1 were resistant to loss of ATP and mitochondrial inner membrane potential during challenge with rotenone, an inhibitor of complex I in the ETC. We further demonstrated that treatment with IF1 reversed rotenone-induced superoxide production in mitochondria and peroxide accumulation in whole cells. Ultimately, IF1 decreased protein levels of pro-apoptotic Bax, cleaved caspase-3, and cleaved PARP, rescuing SH-SY5Y cells from rotenone-mediated apoptotic death. Administration of IF1 significantly improved the results of pole and hanging tests performed by PD mice expressing human α-synuclein. This indicates that IF1 mitigates PD-associated motor deficit. Together, these findings suggest that IF1 exhibits a neuroprotective effect preventing mitochondrial dysfunction in PD pathology.