Nonmetric Multidimensional Scaling Solutions Research Articles

Wireless Network Indoor Positioning Method Using Nonmetric Multidimensional Scaling and RSSI in the Internet of Things Environment

Aiming at the problem that the indoor target location algorithm based on received signal strength (RSSI) in the IoT environment is susceptible to interference and large fluctuations, an indoor localization algorithm combining RSSI and nonmetric multidimensional scaling (NMDS) is proposed (RSSI- NMDS). First, Gaussian filtering is performed on the received plurality of sets of RSSI signals to eliminate abnormal fluctuations of the RSSI. Then, based on the RSSI data, the dissimilarity matrix is constructed, and the relative coordinates of the nodes in the low-dimensional space are obtained by NMDS solution. Finally, according to the actual coordinates of the reference node, the coordinate transformation is performed by the planar four-parameter model, and the position of the node in the actual coordinate system is obtained. The simulation results show that the proposed method has strong anti-RSSI perturbation and high positioning accuracy.

P-1037 - There is more to depression than factors can get: core symptoms and qualitative facets in the BDI-II item structure

Introduction An adequate assessment of depression has been a concern to many researches over the last half-century. These efforts have brought forth a manifold of depression rating scales, of which one of the most commonly used self-assessment scales is the Beck Depression Inventory (BDI). Since its revision by Beck, Steer, and Brown (1996), the item structure of the BDI-II has been examined in many factor analyses, both, exploratory and confirmatory. Yet, a consensus about the underlying factor structure could not be achieved. Aim/objectives The present study was conducted to reexamine the item structure based on robust Nonmetric Multidimensional Scaling (NMDS). The NMDS solution allows for evaluating the diverging results from the factor analyses conducted so far. Methods The norm sample of the German version of the BDI-II was used (Hautzinger, Keller, & Kuhner, 2006), which consisted of N = 266 patients diagnosed with a major depressive disorder. Results The NMDS solution emphasized a facet oriented structure and revealed the insufficiency of the factor analyses to adequately capture the data. Conclusions Based on the NMDS solution, we propose an item structure consisting of a depressive core syndrome, surrounded by five specific facets (Figure 1). The core syndrome measures the severity of the depression mainly, whereas the five facets pronounce different qualities inherent to depression. Download : Download full-size image [Figure 1]

Individual differences in voice quality perception.

Sixteen listeners (10 expert, 6 naive) judged the dissimilarity of pairs of voices drawn from pathological and normal populations. Separate nonmetric multidimensional scaling solutions were calculated for each listener and voice set. The correlations between individual listeners' dissimilarity ratings were low. However, scaling solutions indicated that each subject judged the voices in a reliable, meaningful way. Listeners differed more from one another in their judgments of the pathological voices (which varied widely on a number of acoustic parameters) than they did for the normal voices (which formed a much more homogeneous set acoustically). The acoustic features listeners used to judge dissimilarity were predictable from the characteristics of the stimulus sets: only parameters that showed substantial variability were perceptually salient across listeners. These results are consistent with prototype models of voice perception. They suggest that traditional means of assessing listener reliability in voice perception tasks may not be appropriate, and highlight the importance of using explicit comparisons between stimuli when studying voice quality perception.

Acquiescence in Components Analysis and Multidimensional Scaling of Self-Rating Items

Earlier work has shown that when multidimensional scaling (MDS) is applied to item intercorrelations, met ric MDS implicitly subtracts the standardized person mean (SPM) from responses. As a result, when a met ric or nonmetric MDS solution is compared to a com ponents solution, the components solution often con tains one component with no counterpart among the scaling dimensions. If self-report items form a bal anced scale and negatively worded items are not re verse scored, the SPM is closely related to several con cepts of acquiescence and disacquiescence. In this paper, MDS and components solutions are compared using two balanced self-report item sets. In the Likert self-report attitude item set, the MDS and components solutions were essentially the same. In a set of affec tive well-being items, the components solution con tained a general component with no counterpart among the scaling dimensions. Scores along the general com ponent were substantially correlated with measures of acquiescence and disacquiescence. Results in the sec ond dataset suggest that when the self-report items are balanced and the negatively worded items have not been reverse scored, MDS and components solutions can differ largely with respect to a component closely associated with certain measures of acquiescence. In dex terms: acquiescence, attitude measurement, factor analysis, multidimensional scaling, personality mea surement, response bias, self-report items.

Data Collection Effects on Nonmetric Multidimensional Scaling Solutions

This study investigates four widely used methods of collecting direct similarity judgments for nonmetric multidimensional scaling: Rating Scale, Triads, Rank Order of Pairs, and Conditional Rank Order. The results indicate that: (1) when class structure is very striking in the attributes to be scaled, respondents under the Rating Scale method place significantly more weight on class structure than on continuously varying attributes in determining similarity; (2) nonmetric multidimensional scaling solutions account for a greater proportion of the variance in Rank Order of Pairs data than in data collected by the other methods studied, although the differences are so small that they would have little operational impact; and (3) the four methods do not differ significantly in test-retest reliability.

Students' Perceptions of the College Milieu

In order to examine perceptions of the social environment, 109 college undergraduates rated the similarity of all nonredundant pairs of 30 representative social situations. An additional 70 subjects rated each situation on 38 bipolar scales descriptive of the situation's perceived properties and the subject's typical behavior and affect in that situation. A nonmetric multidimensional scaling solution in four dimensions provided an optimal fit to the similarity data. The dimensions were interpreted as Interpersonal Intimacy, Group vs. Individual Activity, Social Isolation, and Behavioral Conformity. The findings are discussed in terms of their relationship to previous investigations of the perception of social episodes and their implications for person-situation interaction research.

Multidimensional Scaling Of Derived Dissimilarities.

In past research, a matrix of squared profile distances, δ, has sometimes been multidimensionally scaled rather than the matrix of original dissimilarities, D. It is thought that scaling solutions derived from δ have lower stress and enhanced interpretability when applied to data generated by sorting. Two experiments were performed to investigate the consequences of the delta transformation. First, random numbers resembling data collected by the method of sorting were simulated. Scaling solutions derived from δ matrices invariably had lower stress than solutions computed from the associated D matrices. This result suggests that the delta transformation may reduce stress irrespective of any change in interpretability. Simulated dissimilarity matrices were then generated from known stimulus configurations. It was found that: (1) nonmetric multidimensional scaling solutions for δ matrices had relatively lower stress; but under low error conditions (2) solution based on D were more closely related to the underlying configurations; and (3) determination of dimensionality by inspection of the stress plot was somewhat more difficult for solutions based on δ. These results can be understood by observing that the delta transformation tends to increase the size of large distances in the derived configurations relative to small distances.

Data Quality, Level of Aggregation, and Nonmetric Multidimensional Scaling Solutions

Data Quality, Level of Aggregation, and Nonmetric Multidimensional Scaling Solutions

Data Quality, Level of Aggregation, and Nonmetric Multidimensional Scaling Solutions

As the relative emphasis in nonmetric multidimensional scaling research shifts from techniques to applications, increasing attention is being paid to the quality of the input data and the extent of aggregation of individual data for analysis purposes. The overall objective of this article is to explore the effect on the scaling solution of quality of input data as measured by the reliability of the individual respondent's similarity judgments and the extent of aggregation across respondents. A conceptual structure for understanding these issues is developed first. Data from five separate nonmetric multidimensional scaling studies are used to illustrate the concepts. In conclusion some analysis procedures are suggested for coping with various combinations of stress and reliability in the data.

Variation among Multidimensional Scaling Solutions: An Examination of the Effect of Data Collection Differences

During the last few years, marketing researchers have begun to use nonmetric multidimensional scaling for analyzing similarity judgments, preference statements, and attribute ratings. The major thrust for many of the more methodological studies [6, 7, 20, 21, 26] has been the comparison of various data collection tasks with regard to the similarity of solutions from one scaling algorithm. Some investigators have concentrated on comparing the solutions from a number of scaling algorithms for one set of data [3, 8, 19], whereas others have compared the algorithms on the basis of Monte Carlo simulations [23, 25] and empirical manipulations [17, 24] of the basic model parameters. Another set of studies [2, 4, 9, 22] has compared two scaling algorithms across two or more types of data. The results of the algorithm comparisons have indicated consistently that the scaling programs produce very similar solutions. The results of the data collection task comparisons, however, have not been so consistent. Methods for directly judging proximity have produced similar solutions, but when direct and derived measures have been compared, only one of three studies [4, 9, 20] found that the solutions from the two types of proximity measures had similar spatial configurations. The author's study extends the research on multidimensional scaling comparisons by examining the relative effect of six different data collection tasks on nonmetric multidimensional scaling solutions.

A Numerical Taxonomic Study of Affinity Relationships in Cultivated Citrus and Its Close Relatives

The affinity relationships of 43 biotypes of cultivated Citrus-close relatives, interspecific and intergeneric hybrids, and clones of unknown origin-were studied to develop information for use in citrus breeding experiments. Intraspecific affinity was very high (87 to 98) in four of six cultivated Citrus species (C. aurantium, C. grandis, C. limon, and C. paradisi) but lower in C. reticulata (45 to 58) and in C. sinensis (37). Among Citrus species and relatives, the affinity pattern showed two main groups in Citrus and a third group consisting of Eremocitrus glauca and Microcitrus species. The larger Citrus group included five species (C. aurantium, C. grandis, C. paradisi, C. reticu- lata, and C. sinensis) and a smaller group of three (C. aurantifolia, C. limon, and C. medica). The charcteristics of C. grandis were domi- nant in interspecific hybrids. In hybrids of cultivated Citrus species and wild relatives, the characteristics of the latter were strongly domi- nant with one exception. The affinities of clones of unknown origin indicated probable hybrid origins of diverse genetic backgrounds. Comparisons of the data on the study clones were made with the major authoritative speculations on their derivations. Citrus grandis, C. medica, and C. reticulata are proposed as true biological species. Citrus aurantifolia, C. aurantium, C. limon, C. paradisi, and C. sinensis are proposed as unique, apomictically perpetuated biotypes of probable hybrid origin. A nonmetric multidimensional scaling solution is pre- sented to support, in part, the proposed systematic relationships. In- adequate sampling of the variation present in populations and a lack of appreciation of the effects of facultative apomixis on population samples and its relationship to genetic heterozygosity in Citrus have been the major obstacles in past efforts to produce an objective Citrus taxonomy.

BRIEF REPORT: ADDITIONAL DATA ON DISTORTION DUE TO AGGREGATION IN NONMETRIC MULTIDIMENSIONAL SCALING.

A previous research report investigated the effect of aggregation on nonmetric multidimensional scaling solutions in which the scaled stimuli were adjectives. Aggregate solution configurations were found to resemble substantially the configurations based on individual similarity data. However, recent replications on nonadjectival stimuli indicate substantial distortion due to aggregation. Preliminary conjectures are made about the adjective- object differences. The importance of the issue for multidimensional scaling is underscored by citing recent developments in scaling techniques.