• Korean Journal of Logic
• /
• v.12 no.2
• /
• pp.89-114
• /
• 2009

We have many causal beliefs, and they play an important role in our decision making. Unlike evidential decision theory, causal decision theory claims that an account of rational choice must use causal beliefs to identify the considerations that make a choice rational. I claim that evidential decision theory is refuted by the original Newcomb's problem but not by the medical Newcomb problem. The latter is taken to be the best example to point out the weakness of evidential decision theory. However, by the explicit statement about causal relations, I argue that the medical Newcomb problem loses its strength in refuting evidential decision theory. With this argument, this paper clarifies the difference between evidential decision theory and causal decision theory.

• Proceedings of the KIEE Conference
• /
• 1995.11a
• /
• pp.192-194
• /
• 1995

An improved filter for tracking a maneuvering target is presented. The proposed filter consists of two kalman filters based on different dynamic models and double decision logic. The use of double decision logic for the maneuver onset and ending detection leads to reduction in estimation error. This decision rule is based on evidence theory, Dempster-Shafer theory, which is extended in order to be applicable in the tracking problem. Simulation results show that the proposed filter performs better than IMM at a lower computational load.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.2 no.2
• /
• pp.34-41
• /
• 1992

A robust and reliable learning and reasoning mechanism is addressed based upon fuzzy set theory and fuzzy associative memories. The mechanism stores a priori an initial knowledge base via approximate learning and utilizes this information for decision-making systems via fuzzy inferencing. We called this fuzzy computer architecture a 'fuzzy hypercube' processing all the rules in one clock period in parallel. Fuzzy hypercubes can be applied to control of a class of complex and highly nonlinear systems which suffer from vagueness uncertainty. Moreover, evidential aspects of a fuzzy hypercube are treated to assess the degree of certainty or reliability together with parameter sensitivity.

• Journal of Preventive Medicine and Public Health
• /
• v.49 no.2
• /
• pp.80-96
• /
• 2016

Recently, a series of lawsuits were filed in Korea claiming tort liability against tobacco companies. The Supreme Court has already issued decisions in some cases, while others are still pending. The primary issue in these cases is whether the epidemiological evidence submitted by the plaintiffs clearly proves the causal relationship between smoking and disease as required by civil law. Proving causation is difficult in tobacco lawsuits because factors other than smoking are involved in the development of a disease, and also because of the lapse of time between smoking and the manifestation of the disease. The Supreme Court (Supreme Court Decision, 2011Da22092, April 10, 2014) has imposed some limitations on using epidemiological evidence to prove causation in tobacco lawsuits filed by smokers and their family members, but these limitations should be reconsidered. First, the Court stated that a disease can be categorized as specific or non-specific, and for each disease type, causation can be proven by different types of evidence. However, the concept of specific diseases is not compatible with multifactor theory, which is generally accepted in the field of public health. Second, when the epidemiological association between the disease and the risk factor is proven to be significant, imposing additional burdens of proof on the plaintiff may considerably limit the plaintiff's right to recovery, but the Court required the plaintiffs to provide additional information such as health condition and lifestyle. Third, the Supreme Court is not giving greater weight to the evidential value of epidemiological study results because the Court focuses on the fact that these studies were group-level, not individual-level. However, group-level studies could still offer valuable information about individual members of the group, e.g., probability of causation.