AIDS is a serious public health problem. Our projections of the likely incidence of AIDS are of vital importance to the assessment of future healthcare needs. This paper considers an epidemic model of the population dynamics of AIDS, which has been adjusted to take into account the changes in the transmission rate in response to changes in risk behaviors and increased AIDS awareness due to public health policy, AIDS campaigns, and other means of disease prevention. The model, adjusted for reporting delays and for the variable incubation period of the disease, has been applied to AIDS incidence data gathered in Nakhon Pathom, Thailand. Using the least-squares criterion, we solved for the appropriate values of the parameters which gave the best fit of the model to the observation data. The model was found to be capable of generating short-term projections, and offers an explanation for the decline in the number of cases that is evident in more recent data.