Presents author corrections to the paper, “Detection of Resource Overload in Conditions of Project Ambiguity” (Pelikan, M. et al), IEEE Trans. Fuzzy Syst., vol. 25, No. 4, pp. 868–877, Aug 2017, DOI: 10.1109/TFUZZ.2016.2584645.

The planning of project resource allocation is an important part of project management, but it often suffers from uncertainty and ambiguity. Ambiguity conditions can be described and simulated by the theory of fuzzy sets and fuzzy quantities. The fuzzy approach to project planning is usually applied in critical path setting and project duration monitoring. In this article, we show a new application of the fuzzy set theory that involves planning project resource allocation and monitoring resource workloads. We derive the theoretical relations for the membership functions of the corresponding fuzzy quantities and demonstrate their application by taking a simple project as an example. The derived methods were used in planning a real project whose purpose was to analyze the possible resource workload. As a result, it was possible to recognize the serious risk of resource overload, which is not possible with the deterministic approach. They contributed to the success of the project.

An ambiguity problem arises if a distance is measured by observing phase shift of signals when the range of the measured distance is greater than the wavelength of the signals used. This ambiguity generally can be resolved by pumping extra information into the system. A classical estimation problem is the obtained at the expense of reduced autonomy of the estimator due to the demand for external information not inherent to the system. The interval Lambda of the unambiguous estimates can be considerably extended using observations of several different wavelengths lambda /sub i/. This yields Lambda as the least common multiple of all lambda /sub i/. A method of developing optimum estimation rules for this case is introduced. Optimum estimation rules for some typical cases with Gaussian observation errors are also developed.>

The behavior of the sequential probability ratio test (SPRT) can be described using four performance measures, i.e., the probabilities of both types of error\alpha_{0}, \alpha_{1}, and the average test lengths (or sample sizes)E_{0}, E_{1}for the given decision problem. Whereas Bayes optimality of the SPRT is well-known from the work of Wald and Wolfowitz, there is no method to evaluate the performance measures except for Wald's approximations. We present a method to evaluate the performance measures given the thresholds of the SPRT.