Threshold Decision Rules Research Articles

Robustness is Not Dimensionality: On the Sensitivity of Component Comparability Coefficients to Sample Size.

Everett (1983) has proposed that, under certain conditions, replicability provides an answer to the question of the number of dimensions to retain in component analysis. But replicability must logically be a function of sample size as well as dimensionality. In the present study, the effects of sample size and sample composition are systematically examined on the replicability of principal components. Using observer ratings of personality from the California Adult Q-Set, comparability coefficients are examined in 192 series of principal components analyses. Results indicate that (a) once one has 20 or more subjects per item, the most comparable solution typically has as many components as items; (b) if these full solutions are ignored, there is still a substantial relationship between prescribed number of components and sample size when one uses either the .90 or .85 threshold decision rules and (c) other criteria for determining the number of components to retain, such as the Minimum Average Partial (MAP) rule, do not show the same relationship with sample size. These results indicate that dimensionality cannot be inferred from component robustness, as these are empirically as well as logically separate matters.

Information Value in Weed Management

Use of the economic threshold to improve the efficiency of preemergent-herbicide treatment decisions is limited by a lack of weed information. An economic model for assessing the expected value of weed information needed to implement a threshold decision rule is developed. Empirical results suggest that early season weed information can have value in cabbage weed management in Massachusetts.

Optimum threshold diversity reception of NCFSK signals in non-gaussian noise

The theory of threshold reception in non-Gaussian noise is applied to synthesise a locally and asymptotically optimum diversity structure for the noncoherent reception of binary frequency-shift keying signals subject to amplitude fluctuations. The optimum threshold decision rule is obtained for arbitrary slow-fading laws on the diversity branches.With reference to Rayleigh distributed amplitude fluctuations, the performance of the proposed reception structure is evaluated for the general case of arbitrary noise distributions on the diversity channels.

Active mate choice at cock-of-the-rock leks: tactics of sampling and comparison

The importance of active mate choice as a component of sexual selection remains controversial, despite recent studies identifying traits that correlate with male mating success. We analyzed the sampling sequences of individual female Guianan cock-of-the-rock, providing quantitative documentation of active female choice in this lekbreeding species. We compared observed sampling patterns with null models of random female movement and of movement weighted by the observed distribution of male success. The courts actually visited by individual females were significantly more clumped and centrally located than predicted by computer simulations of either random or weighted movement. Contrary to simplified hypotheses of female choice, hen cock-of-the-rock were not limited either to sequential comparisons or to threshold decision rules when selecting mates. Instead, they repeatedly sampled a subset of potential mates, using the “pool-comparison” tactic. Within this pool, females preferentially mated with the males ranked highest in terms of total courtship visits received, and rejected low-ranking males. Our results suggest complex interactions between patterns of female sampling and male dispersion in lek mating systems, and also provide insights into the constraints on female sampling in lek species.

The construction of an optimal linear threshold decision rule

The construction of an optimal linear threshold decision rule

Scene matching with invariant moments

The ability to extract invariant features from an image is important in the field of pattern recognition and image processing. An object in the image can then be identified independently of its position, size, and orientation. In this paper, the derivation of moment equations and a method of moment measurement are described. A threshold sequence and decision rules are developed and implemented in the matching of radar to optical images using a hierarchical search technique with the invariant moments as similarity measures. Experimental results of the scene matching are described and discussed.

Decision Hysteresis Reduces Digital Pe

It is shown that the source statistics influence the form of the decision threshold in an optimum receiver. For a first-order Markov source, a simple suboptimum realization is a hysteresis loop. The performance improvement over the single threshold decision rule is modest but in some cases it is possible to cut the P e in half. One case where decision hysteresis performs best is in a modem that uses split phase or data scrambling to ensure that the transmitted signal tends to alternate. As a practical matter, it turns out that hysteresis can do more damage than good if the signal-to-noise ratio is variable.

Decision Functions for Voiced-Unvoiced-Silence Detection

At the June, 1960, Acoustical Society of America meeting, we described a voiced-unvoiced-silence detection procedure. It incorporated two independent threshold decision rules, one operating on the zero moment of the speech spectrum for the spoken-silent choice, the other operating on the first moment for the voiced-unvoiced choice. A generalization of this procedure involves a decision which depends jointly on the two moments. This paper compares the performance of this process with the simpler one. Value functions placing specified weights on the nine possible outcomes of this 3×3 detection situation were defined, and decision rules maximizing the values were computed. Maximum likelihood, maximum likelihood weighted by prior probabilities, and rules tailored to vocoder applications were studied. Probabilities of the six possible confusions and the three correct answers were computed for all rules. Data for the evaluation consisted of twenty 3-sec utterances by two men and two women. Voiced, unvoiced, and silent intervals in these speech samples were established visually from spectrograms. Performance depends, of course, on the value functions, but at most a reduction of 13 in the over-all error rate over the simple rule was achieved.