The tobacco growing area is an important aspect for the consistency of cigarette aroma and the control of cigarette quality. The fragrance of tobacco leaves would be different for climates and planting environments, such as soil and rainfalls. Accurately discriminating tobacco growing areas is very important to maintain the specifications of cigarettes. In this thesis, the relationship between tobacco near-infrared (NIR) spectra and growing areas is studied. Soft computing models and statistical classifiers are established, and the performance of the developed classifiers are compared in the prediction accuracy and in evaluations derived from confusion matrix. An artificial neural network (ANN) classifier and a statistical model are firstly developed. The best prediction accuracy of ANN model reaches to 79.3% in 226 training samples and 78.7% in 66 testing samples, respectively, which are 2.2% and 4.5% higher than the best results of the conventional statistical model in training (77.1%) and in testing (74.2%), respectively. A support vector machine (SVM) model is proposed to investigate the characteristics of growing areas based on risk error minimum, and produces a higher classification accuracy than ANN model does, demonstrating the effectiveness and robustness of SVM model. In addition, a genetic algorithm (GA) optimized SVM (GA-SVM) model is proposed for taking the influence of the interaction of individual inputs on the performance of classifiers into account. With the application of GA, the sensitive input subset is identified and used to discrimination models. The simulation results demonstrate that the GA-SVM model has the best performance among the other developed models, and the model complexity is simplified, which is shown by requiring fewer inputs to achieve the equivalent prediction accuracy. The GA-SVM classifier is preferred for solving multi-category problems. / Prof. Simon X. Yang

This study investigates how well the Regional Atmospheric Modelling System (RAMS) simulates the sea breeze from False Bay (False Bay sea breeze) at a small resolution of 200m. It describes the influence of the sea breeze in the Stellenbosch wine growing district focusing on temperature, relative humidity and wind speed and direction through three case studies, using three different synoptic conditions. The RAMS simulations are verified against measurements done by automatic weather stations in the study area for all three case studies. The first synoptic condition investigated is when light onshore flow occurred over the south-western Cape. The RAMS model simulated the vertical and horizontal structure of the sea breeze from False Bay very well. However RAMS predicted the onset of the sea breeze 3 hours earlier than the AWS data predicted. The flow was off-shore in the second case study. The RAMS simulations as well as the observed data from the automatic weather stations, showed the two sea breezes influencing the study area, one from Table Bay, west of Stellenbosch, and one from False Bay. In this case study the model simulated the flatter head and stronger False Bay sea breeze. The third case study investigated the influence of strong onshore synoptic conditions, in which the model and observed values showed that no sea breeze developed from False Bay. From the three case studies it was found that the sea breeze is influenced by the synoptic flow and that the sea breeze causes cooling of between 3°C and 16°C and relative humidity (RH) increase of between 16 – 57% depending on the synoptic flow. RAMS was able to simulate the sea breeze theoretically correct and has the potential to be used to identify climatological areas in the wine growing areas of the Western Cape. / Dissertation (MSc)--University of Pretoria, 2007. / Geography, Geoinformatics and Meteorology / Unrestricted

Submitted by Maria Beatriz Vieira (mbeatriz.vieira@gmail.com) on 2017-03-03T15:08:57Z No. of bitstreams: 2 license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) dissertacao_silvio_bueno_paulikevis.pdf: 429329 bytes, checksum: e990045e878260218f1a34a5dabc8e62 (MD5) / Approved for entry into archive by Aline Batista (alinehb.ufpel@gmail.com) on 2017-03-09T17:57:26Z (GMT) No. of bitstreams: 2 dissertacao_silvio_bueno_paulikevis.pdf: 429329 bytes, checksum: e990045e878260218f1a34a5dabc8e62 (MD5) license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) / Approved for entry into archive by Aline Batista (alinehb.ufpel@gmail.com) on 2017-03-09T17:58:23Z (GMT) No. of bitstreams: 2 dissertacao_silvio_bueno_paulikevis.pdf: 429329 bytes, checksum: e990045e878260218f1a34a5dabc8e62 (MD5) license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) / Made available in DSpace on 2017-03-09T17:58:38Z (GMT). No. of bitstreams: 2 dissertacao_silvio_bueno_paulikevis.pdf: 429329 bytes, checksum: e990045e878260218f1a34a5dabc8e62 (MD5) license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) Previous issue date: 2014-08-15 / Sem bolsa / O presente trabalho teve como objetivo realizar um levantamento do tamanho da indústria de sementes de soja, bem como as cultivares e tratos culturais utilizados. Foi empregado um questionário com dez perguntas fechadas e duas abertas, aplicadas via telefone, aos agricultores do município de Pedra Preta – MT, totalizando oito entrevistas, das dez empresas cadastradas no Ministério da Agricultura Pecuária e Abastecimento (MAPA). As entrevistas ocorreram no período de fevereiro a abril de 2014. Conclui-se que o negócio semente de soja é amplo a ponto de ter empresas cultivando mais de 50 mil hectares, além de conseguir observar que as cultivares mais utilizadas são transgênicas. Observou- se que 88% das empresas realizam semeadura na safrinha, utilizando cultivares de ciclos precoce e semi-precoce, totalizando 63% da área cultivada. / This study aimed to survey the size of the seed soybean industry as well as cultivars and used cultural treatments. Was employee a questionnaire with ten closed questions and two open, applied via telephone, farmers in the of Pedra Preta city – MT, totaling eight interviews, of ten companies registered at the Ministry of Agriculture Livestock and Supply (MAPA). The interviews took place in the period from February to April 2014. It is concluded that the soybean seed business is broad as to have companies cultivating more than 50 thousand hectares and to observe that the most used cultivars are transgenic. It was observed that 88% of companies in the crop sowing off-season, using cultivars of early cycles and semi-early, totaling 63% of the cultivated area.