Scholarlink

<p>Effective decision-making relies on the integration of cognitive intuition, situational awareness, and analytical reasoning. Advancing decision-making proficiency plays a pivotal role in strengthening individuals’ strategic positioning across professional domains. This study investigates the predictive modeling of decision-making performance while evaluating the influence of indoor environmental factors, adopting a quantitative methodology distinct from traditional empirical approaches. Leveraging sensor-based environmental monitoring and cognitive behavioral data from Chinese chess gameplay, we develop SA-LSTM, a hybrid neural architecture that synergizes self-attention (SA) mechanisms with long-short term memory (LSTM) network. The results confirm that the superior predictive capacity of SA-LSTM model for the decision-making performance. Compared with other seven models, SA-LSTM has lower error and better goodness of fit. Specifically, the root mean square error and mean absolute error of our model are reduced by 11% and 14% compared with the second best performing model LSTM. The architecture additionally demonstrates enhanced robustness across diverse metrics. Interpretive analysis reveals the environmental impacts on decision-making performance, with the self-attention mechanism elucidating feature interaction patterns. This not only validates environmental variables as critical predictors but also advances decision-making performance forecasting precision through multidimensional relationship mining.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

SA-LSTM: A Deep Learning Model for the Prediction of Decision-making Performance Based on Chinese Chess

  • 期刊论文

  • 发表日期：

    2026年7月28日

查看全文
  • Erbiao Yuan,
  • Guangfei Yang,
  • Weidong Sun,
  • Yi Sun

摘要

Effective decision-making relies on the integration of cognitive intuition, situational awareness, and analytical reasoning. Advancing decision-making proficiency plays a pivotal role in strengthening individuals’ strategic positioning across professional domains. This study investigates the predictive modeling of decision-making performance while evaluating the influence of indoor environmental factors, adopting a quantitative methodology distinct from traditional empirical approaches. Leveraging sensor-based environmental monitoring and cognitive behavioral data from Chinese chess gameplay, we develop SA-LSTM, a hybrid neural architecture that synergizes self-attention (SA) mechanisms with long-short term memory (LSTM) network. The results confirm that the superior predictive capacity of SA-LSTM model for the decision-making performance. Compared with other seven models, SA-LSTM has lower error and better goodness of fit. Specifically, the root mean square error and mean absolute error of our model are reduced by 11% and 14% compared with the second best performing model LSTM. The architecture additionally demonstrates enhanced robustness across diverse metrics. Interpretive analysis reveals the environmental impacts on decision-making performance, with the self-attention mechanism elucidating feature interaction patterns. This not only validates environmental variables as critical predictors but also advances decision-making performance forecasting precision through multidimensional relationship mining.