Biology, agriculture and nutrition (10 articles)

Pixel clustering in spatial data mining; an example study with Kumeu wine region in New Zealand

Shanmuganathan, S. (2013).

437 888 pixels describing wine regions are identified on a GIS map of New Zealand. The pixels are then clustered with respect to corresponding geo-coded data for landscape, microclimate and soil properties using Viscovery SOMine. For detailed micro-scale analysis, the pixels belonging to Kumeu wine regions are selected and another self-organizing-map model is calculated and compared to the general model.

Computer aided identification of biological specimens using self-organizing maps

Dean, E. J. (2003).

This master thesis is concerned with the correct classification of different Acacia species. Self-organizing maps were chosen for this purpose, since they handle partial information particularly well. Viscovery SOMine is used throughout the thesis to calculate several classification models and analyze the connection in taxonomy of Acacia species.

Modelling the seasonal climate effects on grapevine yield at different spatial and unconventional temporal scales

Shanmuganathan, S., Sallis, P., & Narayanan, A. (2010).

In this article, the connection between microclimate, grape yield and wine quality is investigated. Viscovery SOMine is used to cluster the different vintages according to quality and visualize the corresponding weather data. The self-organizing map results are compared to regression and discriminative analysis.

Metabolite profiling of spinach (Spinacia oleracea L.) leaves by altering the ratio of NH4+ / NO3- in the culture solution

Okazaki, K., Oka, N., Shinano, T., Osaki, M., & Takebe, M. (2009). Soil science and plant nutrition, 55(4), 496-504.

The influence of different nitrogen suppliers on the metabolite profiles of spinach leaves is analyzed. A cluster analysis is conducted with Viscovery SOMine, ordering the 53 identified metabolites into six distinct clusters.

Use of neural networks to detect minor and major pathogens that cause bovine mastitis

Hassan, K. J., Samarasinghe, S., & Lopez-Benavides, M. G. (2009). Journal of dairy science, 92(4), 1493-1499.

Viscovery SOMine and a multi-layer perceptron are both used to detect bacterial pathogens in 4852 cow milk samples. The Viscovery model provides better agreement with results from conventional microbiological methods and may be used in future in-line milking systems to detect bovine mastitis at early stages.

Differences in the Metabolite Profiles of Spinach (Spinacia oleracea L.) Leaf in Different Concentrations of Nitrate in the Culture Solution

Okazaki, K., Oka, N., Shinano, T., Osaki, M., & Takebe, M. (2008). Plant and cell physiology, 49(2), 170-177.

Metabolite profiling using gas chromatography-mass spectrometry is used to evaluate the effect of nitrogen levels on spinach tissue, comparing two cultivars that differ in their ability to use nitrogen. Self-organizing-map (SOM) analysis using Viscovery SOMine is used to describe changes in the metabolites of mature spinach leaves. Both PCA and SOM reveal that metabolites are broadly divided into two types, correlating either positively or negatively with plant nitrogen content. The simple and co-coordinated metabolic stream, containing both general and spinach-specific aspects of plant nitrogen content, will be useful in future research on such topics as the detection of environmental effects on spinach through comprehensive metabolic profiling.

Individuality of wing patterning in giant honey bees (Apis laboriosa)

Kastberger, G., Radloff, S., & Kranner, G. (2003). Apidologie, 34(3), 311-318.

This study investigates whether individual worker bees of a single Apis laboriosa colony can be re-identified by their wing patterns alone. Re-identification is carried out by self-organizing-map (SOM) reclassification and conventional discriminant analysis (DA) using the protocols of recognition (data for training and testing the model are equal or slightly modified by white noise), and prediction (test data are unknown to the model). SOM recognition of wing shaping is found to be more robust than that resulting from DA. The SOM prediction capacity is tested using four test-training data ratios and reaches 90% under a two-step reclassification protocol.

Breeding Rubus cultivars for high anthocyanin content and high antioxidant capacity

McGhie, T. K., Hall, H. K., Ainge, G. D., & Mowat, A. D. (2001, July). In VIII International Rubus and Ribes Symposium 585 (pp. 495-500).

Anthocyanin content and antioxidant activity from HortResearch Rubus clones are assessed, and a diverse range of anthocyanins and total anthocyanin content are reported. These data could be used to improve commercial production of high-health Rubus crops with significantly higher anthocyanin content and antioxidant capacity than found in existing cultivars.

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

Kastberger, G., & Kranner, G. (2000). Behavior Research Methods, Instruments, & Computers, 32(1), 157-168.

Viscovery SOMine is used to analyze and visualize multiple influences of the ocellar system on free-flight behavior in giant honeybees. Occlusion of ocelli affects orienting reactivities in relation to flight target, level of disturbance, and position of the bee in the flight chamber; occlusion induces phototaxis and renders 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.

Visualising spatial patterns in fruit quality and productivity of persimmon orchards using self organising maps

Mowat, A. (2000).

Fruit quality and productivity datasets obtained over two seasons from 24 New Zealand persimmon orchards are analyzed. Viscovery SOMine is used to construct a 2000 node self-organizing map (Kohonen, 1997) from input features (latitude, longitude, and growing region) obtained from each orchard replicate. By depicting fruit quality and tree productivity over the map, spatial patterns between orchards can be observed. In addition, climatic data from regional meteorological stations are associated with the map.