Visualization of multiple influences on ocellar flight control in giant honeybees with the data-mining tool Viscovery SOMine

Abstract

Viscovery SOMine is a software tool for advanced analysis and monitoring of numerical data sets. It was developed for professional use in business, industry, and science and to support dependency analysis, deviation detection, unsupervised clustering, nonlinear regression, data association, pattern recognition, and animated monitoring. Based on the concept of self-organizing maps (SOMs), it employs a robust variant of unsupervised neural networks-namely, Kohonen's Batch-SOM, which is further enhanced with a new scaling technique for speeding up the learning process. This tool provides a powerful means by which to analyze complex data sets without prior statistical knowledge. The data representation contained in the trained SOM is systematically converted to be used in a spectrum of visualization techniques, such as evaluating dependencies between components, investigating geometric properties of the data distribution, searching for clusters, or monitoring new data. We have used this software tool to analyze and visualize multiple influences of the ocellar system on free-flight behavior in giant honeybees. Occlusion of ocelli will affect orienting reactivities in relation to flight target, level of disturbance, and position of the bee in the flight chamber; it will induce phototaxis and make orienting imprecise and dependent on motivational settings. Ocelli permit the adjustment of orienting strategies to environmental demands by enforcing abilities such as centering or flight kinetics and by providing independent control of posture and flight course.Data sets collected from biological, psychological, and social experiments or data taken from social, economic, or marketing systems often contain hidden information that is difficult to extract. This is the starting point for a number of analysis methods, commonly known by the term data mining. Widely used traditional methods, such as statistical algorithms, mainly reproduce dependencies within data in a limited way, since they are mostly based on linear principles and a priori assumptions. Such methods imply that it would be extremely difficult to interactively explore high-dimensional, complex data distributions and their underlying nonlinear relationships.Newer models, such as supervised neural network techniques, impose high demands on tuning the underlying algorithms (e.g., in order to design the network topology), which very often demand much effort and a timeconsuming trial-and-error process, owing to the complexity ofreal-world applications. On the other hand, statisticalThe investigation of the ocellar role in flight control was supported by Austrian Scientific Foundation Grant P8746-BIO. The second author has a financial interest in the software described in this article. The authors thank Elisabeth Jaquemar for final improvements of the English. Correspondence concerning this article should be addressed to G. Kastberger, Institute of Zoology, Department of Neurobiology, KarlFranzens University, A80 I0 Graz, Austria (e-mail: gerald.kastberger@ kfunigraz.ac...

Online prediction of product titer and solubility of recombinant proteins in Escherichia coli fed‐batch cultivations

“…The Viscovery Profiler® 4.0 (Eudaptics GmbH Vienna, Austria) software was applied to select significant input variables based on the Pearson correlation coefficient. The selection criterion was a correlation coefficient of >0.9 and < −0.9.…”

Phytochemical Informatics of Traditional Chinese Medicine and Therapeutic Relevance

“…In case of the tetracylic (e.g., lanostane and dammarane) triterpenes, we can distinguish between the glycosides (22), which are associated with Tonify Qi, Stop Bleeding, and Wind Heat, and aglycones (3, 11, and 19), which have a greater affinity for Drain Dampness and Shen categories. The pentacyclic (e.g., oleanane and ursane) triterpenes (7, 9, 13, and 34) are meanwhile found in Wind Heat, Wind Damp, Toxic Heat, and Drain Dampness categories.…”

“…Training was carried out using ViscoVery SOMine Version 4.0 (Eudaptics Software, Vienna) which employs a modified, faster version of Kohonen's original algorithm. 22 Nodes were then clustered via SOM-Ward clustering, which simultaneously incorporates information on map topology with traditional Ward clustering. 23 Since this procedure is not widely known, details of the algorithm are given in the Supporting Information.…”

An Ensemble Empirical Mode Decomposition, Self-Organizing Map, and Linear Genetic Programming Approach for Forecasting River Streamflow

“…Equation (6) is designed to make nodes closer to the BMU learn more than nodes further away. For this study, the commercial software Viscovery SOMine [33] was implemented to perform SOM data clustering.…”