Human-centered systems of systems such as social networks, Internet of Things, or healthcare systems are growingly becoming major facets of modern life. Realistic models of human behavior in such systems play a significant role in their accurate modeling and prediction. Yet, human behavior under uncertainty often violates the predictions by the conventional probabilistic models. Recently, quantum-like decision theories have shown a considerable potential to explain the contradictions in human behavior by applying quantum probability. But providing a quantum-like decision theory that could predict, rather than describe the current, state of human behavior is still one of the unsolved challenges. The main novelty of our approach is introducing an entangled Bayesian network inspired by the entanglement concept in quantum information theory, in which each human is a part of the entire society. Accordingly, society's effect on the dynamic evolution of the decision-making process, which is less often considered in decision theories, is modeled by the entanglement measures. The proposed predictive entangled quantum-like Bayesian network (PEQBN) is evaluated on 22 experimental tasks. Results confirm that PEQBN provides more realistic predictions of human decisions under uncertainty, when compared with classical Bayesian networks and three recent quantum-like approaches.
翻译:以人类为中心的系统体系体系,如社交网络、物联网或医疗体系,正日益成为现代生活的主要方面。这些体系中真实的人类行为模式在精确的建模和预测中起着重要作用。然而,不确定性中的人类行为往往违反传统概率模型的预测。最近,量子类决策理论显示出相当的潜力,通过应用量子概率来解释人类行为中的矛盾。但提供量子类决定理论,可以预测而不是描述当前人类行为状况,这仍然是尚未解决的挑战之一。我们的方法的主要新颖之处是引入一个由量子信息理论的纠缠概念所启发的缠绕的贝叶西亚网络,其中每个人都是整个社会的一部分。因此,社会对决策过程动态演变的影响,在决策理论中不太经常考虑,是以纠缠措施为模型的模型。在22项实验任务中评估了拟议的预测性缠绕的量子类巴耶西亚网络(PEQQBNBN),对22项实验性任务进行了评估。结果证实,在比较最近的一种基质网络时,PEQBN提供了更现实性的方法。