To compare the pattern of brain waves in video game addicts and normal individuals, a case–control study was carried out on both. Thirty participants were recruited from 14 to 20 years old males from two gaming centers. Twenty healthy participants were gathered from different schools in Tehran using the available sampling method. The QEEG data collection was performed in three states: closed-eye and open-eye states, and during a working memory task. As expected, the power ratios did not show a significant difference between the two groups. Regarding our interest in the complexity of signals, we used the Higuchi algorithm as the feature extractor to provide the input materials for the multilayer perceptron classifier. The results showed that the model had at least a 95% precision rate in classifying the addicts and healthy controls in all three types of tasks. Moreover, significant differences in the Higuchi Fractal Dimension of a few EEG channels have been observed. This study confirms the importance of brain wave complexity in QEEG data analysis and assesses the correlation between EEG-complexity and gaming disorder. Moreover, feature extraction by Higuchi algorithm can render support vector machine classification of the brain waves of addicts and healthy controls more accurate.

为了比较电子游戏成瘾者和正常人的脑电波模式，对两者进行了病例对照研究。从两个游戏中心招募了 30 名 14 至 20 岁的男性参与者。使用现有的抽样方法从德黑兰的不同学校收集了 20 名健康参与者。QEEG 数据收集在三种状态下进行：闭眼和睁眼状态，以及在工作记忆任务期间。正如预期的那样，两组之间的功率比没有显示出显着差异。考虑到我们对信号复杂性的兴趣，我们使用 Higuchi 算法作为特征提取器，为多层感知器分类器提供输入材料。结果表明，该模型在所有三类任务中对成瘾者和健康对照者进行分类的准确率至少为 95%。此外，已经观察到一些 EEG 通道的 Higuchi 分形维数存在显着差异。本研究证实了脑电波复杂性在 QEEG 数据分析中的重要性，并评估了 EEG 复杂性与游戏障碍之间的相关性。此外，Higuchi算法的特征提取可以使支持向量机对吸毒者和健康控制者脑电波的分类更加准确。