This thesis develops a more realistic and applicable new set covering model that is adjusted and supplied by the existing set covering models, and induces an algorithm for solving the new set covering model, and applies the new model and the algorithm to an actual set covering problems. The new set covering model introduces a probabilistic covering aistance ($0{\eqslantless}p{\eqslantless}1$)or time($0{\eqslantless}p{\eqslantless}1$) instead of a deterministic covering distance(0 or 1) or time (0 or 1) of the existing set covering model. The existing set covering model has not considered the merit of the overcover of customers. But this new set covering model leads a concept of this overcover to a concept of the parallel system reliability. The algorithm has been programmed on the UNIVAC 9030 for solving large-scale covering problems. An application of the new set covering model is presented in order to determine the locations of the air surveillance radars as a set covering problem for a case-study.

A procedure is established for combining a regression model and a time series model to fit to a set of autocorrelated data. This procedure is based on an iterative method to compute regression parameter estimates and time series parameter estimates simultaneously. The time series model which is discussed is basically AR(p) model, since MA(q) model or ARMA(p,q) model can be inverted to AR({$\infty$) model which can be approximated by AR(p) model. The procedure discussed in this articled is applied in general to any combination of regression model and time series model.

Experiments have been performed for estimating the individual muscle capabilities of the biceps brachii and the quadriceps femoris muscle. The surface EMG has been recorded on the bellies of the biceps brachii and the quadriceps femoris muscle during isometric contractions at $50\%,\;75\%,\;and\;100\%$ MVC. The rectified EMG amplitudes of the maximum voluntary contraction (MVC) were in the range of $2.8\~3.0\;mV\;and\;6.9\~7.2\;mV$ the biceps brachii and the quadriceps femoris, respectively. In the biceps brachii, Type S motor units were recruited in the range of $41\~49\%$ MVC; and Type F motor units were recruited in the range of $51\~59\%$ MVC, In the quadriceps femoris, Type S, Type SF, and Type F motor units were recruited in the ranges of $31\~38\%,\;33\~48\%$, and $21\~29\%$ MVC respectively.

This paper is concerned with the optimality of exponential smoothing applied to the general IMA process with different moving average and differencing orders. Numerical experiments were performed for IMA(m,n) process with various combinations of m and n, and the corresponding forecast errors were compared. Results show that the higher differencing order is more critical to the optimality of exponential smoothing, i.e., the IMA process with the higher moving average order, forecasted by exponential smoothing, has comparatively smaller forecast error. If the difference between the differencing order and the moving average order becomes larger, the accuracy of forecast by exponential smoothing declines gradually.