ABSTRACT The seed deterioration process during storage is inevitable, but it can be slowed down using packaging that reduces the influence of the external environment on stored corn seeds. Therefore, this study aimed to evaluate the physiological quality of corn seeds stored in different packages and subjected to storage conditions in the central region of Brazil. Thirty-seven corn genotypes were analyzed in three storage environments: multiwall paper, 10 °C temperature, and 40% relative air humidity; multiwall paper under uncontrolled conditions; and hermetic packaging under uncontrolled conditions. The results of germination, water content, electrical conductivity, accelerated aging, soilless cold test, and field emergence test were used. Physiological quality assessments indicated that storage under conditions of 10 °C temperature and 40% relative air humidity is more efficient in preserving corn seeds' physiological quality than packaging in an uncontrolled environment. inevitable Therefore Brazil Thirtyseven Thirty seven environments 1 C 40 germination content conductivity aging used 4

ABSTRACT Seed processing is a crucial stage in obtaining high-quality seed lots. The use of spiral separator is a common method for classification of soybean seeds by shape. The objective of this work was to evaluate the effect of processing soybean seeds in a static spiral separator on their physical and physiological quality, considering prior seed size classification. A randomized block experimental design was used, in a 2 × 4 factorial arrangement consisted of two soybean cultivars (60I62 IPRO and 62R63) and four seed size classifications (unclassified, and classified in 5-, 6-, and 7-mm mesh sieves), with three replicates. The samples were cleaned, separated, and individually processed in a static spiral separator with capacity of up to 1,200 kg h-¹. The results indicated that the 60I62 IPRO cultivar had higher percentage of discarded seeds, but better physiological potential than those of the 62R63 cultivar, denoting lower efficacy of the separator for this cultivar. Classified seeds, especially those in the 7-mm mesh sieve, had higher percentage and quality of qualified seeds. Discarded seeds from the 6- and 7-mm mesh sieves showed better physiological quality. The seed shapes of the evaluated soybean cultivars showed varied responses to processing in the static spiral separator. highquality high lots shape used I (60I6 R unclassified, unclassified (unclassified 5, 5 , 5- 6, 6 7mm mm 7 sieves, sieves) replicates cleaned separated 1200 1 200 1,20 h¹. h¹ h ¹. ¹ h-¹ 60I6 62R6 sieve (60I 120 20 1,2 h- 60I 62R 12 1,

RESUMO O processamento de sementes é uma das etapas para obter os melhores lotes de sementes. O separador espiral é uma classificação por forma, comum em sementes de soja. O objetivo deste estudo foi avaliar o uso do processamento e a qualidade física e fisiológica das sementes de soja usando um separador espiral estático, com base na classificação prévia das sementes. Utilizou-se um delineamento em blocos casualizados com esquema fatorial 2 × 4, correspondendo a duas cultivares (60I62 IPRO e 62R63) e quatro tamanhos de peneira (sem classificação, 5, 6 e 7 mm), com três repetições. Após a limpeza e separação, as amostras foram processadas individualmente em um separador espiral estático com capacidade de até 1.200 kg h-¹. Os resultados indicaram que a cultivar 60I62 IPRO teve maior descarte, mas melhor potencial fisiológico do que a 62R63, sugerindo que o separador foi menos eficiente para esta cultivar. As sementes classificadas, especialmente aquelas com peneira de 7 mm, tiveram melhor aproveitamento e qualidade. O material descartado das peneiras de 6 e 7 mm apresentou melhor qualidade fisiológica. As formas das sementes das cultivares variaram em sua resposta ao processamento no separador espiral estático. forma Utilizouse Utilizou se 4 I (60I6 62R63 R sem 5 , mm) repetições separação 1200 1 200 1.20 h¹. h¹ h ¹. ¹ h-¹ 60I6 descarte classificadas (60I 62R6 120 20 1.2 h- 60I 62R 12 1.

ABSTRACT The ranking of seed lots is a fundamental process for all companies in the seed industry. This work aims to demonstrate data mining methods for ranking sorghum seed lots during the seed processing through analysis of quality control data. Germination and cold tests were performed to verify the physiological quality of the lots. Seed samples from each lot were evaluated in two moments: post-cleaning and finished product (ready for marketing). The results after pre-processing totaled 188 rows of data with six attributes, encompassing 150 lots accepted for marketing, 6 rejected, and 32 intermediate lots. The classifiers used were J48, Random Forest, Classification Via Regression, Naive Bayes, Multilayer Perceptron, and IBk. The Resample filter was used for adjustment of the data. The k-fold technique was used for training, with ten folds. The metrics of Accuracy, Precision, Recall, F-measure, and ROC Area were used to verify the accuracy of the algorithms. The results obtained were used to determine the best machine-learning algorithm. IBk and J48 presented the highest accuracy of data; the IBk technique presented the best results. The Resample filter was essential for solving the data imbalance problem. Sorghum seed lots can be classified with great accuracy and precision through artificial intelligence and machine learning technique. industry moments postcleaning post cleaning ready marketing. marketing . marketing) preprocessing pre 18 attributes 15 rejected 3 J Forest Regression Bayes Perceptron kfold k fold training folds Accuracy Precision Recall Fmeasure, Fmeasure F measure, measure F-measure algorithms machinelearning algorithm J4 problem 1

RESUMO A classificação de lotes de sementes é um processo fundamental para todas as empresas do setor sementeiro. O objetivo do trabalho é demonstrar os métodos de mineração de dados de ranqueamento de lotes de sementes de sorgo durante o processo de beneficiamento, através de análises de dados do controle de qualidade. Os testes realizados foram germinação e teste de frio, com o objetivo de verificar a qualidade fisiológica dos lotes. As amostras de sementes de cada lote foram avaliadas em dois momentos: póslimpeza e produto acabado (pronto para comercialização). Os dados gerados, após o pré-processamento, totalizaram 188 linhas com seis atributos, contabilizando 150 lotes aceitos para comercialização, seis rejeitados e 32 denominados intermediários. Os classificadores utilizados foram J48, Random Forest, Classification Via Regression, Naive Bayes, Multilayer Perceptron e IBk. Utilizou-se o filtro Resample para ajustamento dos dados. A técnica empregada para treinamento foi a k-fold, com 10 folds. Para verificar a precisão dos algoritmos foram utilizadas as métricas de Acurácia, Precisão, Recall, F-measure e Área ROC. Com os resultados obtidos determinou-se o melhor algoritmo de aprendizagem de máquina. Verificou-se que o IBk e o J48 obtiveram maior acurácia nos dados, sendo que a técnica de IBk obteve o melhor resultado. O filtro Resample foi importante para resolver o problema do desequilíbrio dos dados. Concluímos ser possível classificar lotes de sementes de sorgo com grande acurácia e precisão através de inteligência artificial e sua técnica de aprendizado de máquina. sementeiro beneficiamento frio momentos pronto comercialização. comercialização . comercialização) gerados préprocessamento, préprocessamento pré processamento, processamento pré-processamento 18 atributos 15 3 intermediários J Forest Regression Bayes Utilizouse Utilizou se kfold, kfold k fold, fold k-fold 1 folds Acurácia Precisão Recall Fmeasure F measure ROC determinouse determinou máquina Verificouse Verificou J4 resultado

ABSTRACT To enhance speed and agility in interpreting physiological quality tests of seeds, The use of algorithms has emerged. This study aimed to identify suitable machine learning models to assist in the precise management of seed lot quality. Soybean lots from two companies were assessed using the Supplied Test Set, Cross-Validation (with 8, 10, and 12 folds), and Percentage Split (with 66% and 70%) methods. Variables analyzed through Tetrazolium tests included vigor, viability, mechanical damage, moisture damage, bed bug damage, and water content. Method performance was determined by Kappa, Precision, and ROC Area metrics. Classification Via Regression and J48 algorithms were employed. The technique utilizing 66% of data for training achieved 93.55% accuracy, with Precision and ROC Area reaching 94.50% for the J48 algorithm. Applying the cross-validation method with 10 folds resulted in 90.22% of correctly classified instances, with a ROC Area outcome like the previous method. Tetrazolium Vigor was the primary attribute used. However, these results are specific to this study's database, and careful planning is necessary to select the most effective application methods. seeds emerged Set CrossValidation Cross Validation 8 1 folds, , folds) 66 70% 70 methods vigor viability damage content Kappa metrics J J4 employed 9355 93 55 93.55 accuracy 9450 94 50 94.50 algorithm crossvalidation cross validation 9022 90 22 90.22 instances used However studys s database 6 7 935 9 5 93.5 945 94.5 902 2 90.2 93. 94. 90.

ABSTRACT The widespread adoption of sensor technology has made it a standard practice for obtaining precise and timely information during the harvest and post-harvest periods. One sensor that has gained popularity for post-harvest seed monitoring is the MQ-3, which identifies ethanol in the air as products undergo fermentation. However, these sensors typically require a stable operation. This study aimed to assess the stabilization time of an MQ-3 sensor when measuring ethanol levels in anaerobic bean seeds. We used six bean seed samples, each with an average moisture content of around 14%. We employed a completely randomized experimental design with nine repetitions for each sample. Every repetition consisted of 25 bean seeds placed in sealed flasks containing 70 mL of distilled water. This setup induced anoxic conditions within the flask, promoting anaerobic respiration in the seeds. After 24 hours, we exposed an air sample to the MQ-3 sensor and took readings at various time intervals (12-14, 19-21, 36-38, 68-70, 130-132, 192-194, 314-316, 616-618 seconds). The average stabilization time for the MQ-3 sensor while quantifying ethanol concentrations in the bean samples were approximately 23 seconds. The sensor demonstrated efficacy, convenience, and rapidity in assessing ethanol levels in anaerobic bean seeds. postharvest post periods MQ3, MQ3 MQ 3, 3 fermentation However operation MQ- 14 14% 2 7 water flask hours 1214, 1214 12 14, (12-14 1921, 1921 19 21, 21 19-21 3638, 3638 36 38, 38 36-38 6870, 6870 68 70, 68-70 130132, 130132 130 132, 132 130-132 192194, 192194 192 194, 194 192-194 314316, 314316 314 316, 316 314-316 616618 616 618 616-61 seconds . seconds) efficacy convenience 1 121 (12-1 19-2 363 36-3 687 6 68-7 13013 13 130-13 19219 192-19 31431 31 314-31 61661 61 616-6 (12- 19- 36- 68- 1301 130-1 192-1 3143 314-3 6166 616- (12 130- 192- 314- (1 (

RESUMO O armazenamento é uma prática fundamental no controle da qualidade fisiológica das sementes, pois é um método que pode preservar sua viabilidade e vigor por mais tempo. Assim, o objetivo do presente estudo foi avaliar o armazenamento de sementes de grão-de-bico em diferentes embalagens, ambientes e períodos. O delineamento inteiramente casualizado foi utilizado em esquema fatorial 2 × 2 × 4, sendo dois tipos de embalagens (hermética e papel Kraft®), dois ambientes de armazenamento (ambiente de câmara fria e ambiente convencional) e quatro períodos de armazenamento (0, 45, 90 e 135 dias), com quatro repetições. As sementes foram acondicionadas em sacos de papel Kraft® e embalagens herméticas, e armazenadas por 135 dias nos ambientes: câmara fria (14,5 °C e umidade relativa do ar de 65%) e ambiente convencional (sem controle de temperatura e umidade relativa do ar). A cada 45 dias, as sementes foram submetidas às seguintes avaliações: determinação do teor de água, germinação, primeira contagem de germinação e envelhecimento acelerado. Em geral, a manutenção da qualidade fisiológica das sementes de grão de bico foi verificada em embalagens de papel Kraft® e em ambiente de câmara fria. O armazenamento de sementes de grão de bico em embalagens herméticas deve ser realizado com sementes com 7% de umidade, independente do ambiente de armazenamento. As embalagens mantiveram a qualidade fisiológica das sementes de grão de bico por até 45 dias, independente do ambiente de armazenamento.

ABSTRACT Storage is a fundamental practice in the control of the physiological quality of seeds, as it is a method that can preserve their viability and vigor for a longer period. Thus, the objective of the present study was to evaluate the storage of chickpea seeds in different packagings, environments, and periods. The completely randomized design was used in a 2 × 2 × 4 factorial scheme, corresponding to two types of packaging (hermetic and Kraft® paper), two storage environments (cold chamber environment and conventional environment), and four storage periods (0, 45, 90, and 135 days), with four replicates. The seeds were placed in Kraft® paper bags and hermetic packagings and stored for 135 days in the environments: cold chamber (14.5 °C and relative air humidity of 65%) and conventional environment (no temperature and relative air humidity control). Every 45 days, seeds were subjected to the following evaluations: determination of water content, germination, first germination count and accelerated aging. In general, the maintenance of the physiological quality of chickpea seeds was verified in Kraft® paper packagings and the cold chamber environment. Storage of chickpea seeds in hermetic packaging must be carried out with seeds with 7% moisture, regardless of the storage environment. The packagings maintained the physiological quality of chickpea seeds for up to 45 days, regardless of the storage environment.

RESUMO No setor de produção de sementes, é imprescindível o uso de equipamentos rápidos e práticos que auxiliem nos processos de tomada de decisão. Assim, o uso de sensores que podem capturar informações para auxiliar na agricultura tem contribuído significativamente para o cultivo da soja em todo o mundo, sendo utilizado em diversas etapas, seja em pré ou pós-colheita. Objetivou-se desenvolver um protótipo de um etilômetro com sensor MQ-3 e avaliar seu tempo de estabilização quando utilizado em lotes de sementes de soja submetidos à hipóxia. A pesquisa foi realizada com 10 lotes de sementes de soja, oriundas de cinco cultivares (NS 8383 RR, SOY Peso RR, M 8372 IPRO, M8644 IPRO e M8808 IPRO), a qual foi dividida em duas etapas, a primeira correspondendo ao desenvolvimento do equipamento de aferição do etanol com o sensor MQ-3 e a segunda relacionada ao tempo de estabilização do sensor (3, 6, 9, 12, 15, 18, 21, 24, 27 e 30 s) em sementes de soja submetidas ao processo de anaerobiose. O equipamento, bem como o sensor MQ-3 apresentaram estabilidade de aferição média aos 16 s após seu acionamento, sendo recomendado esse tempo para o uso do etilômetro em sementes de soja. Por meio desse mesmo sensor MQ-3, é possível, com eficiência, a detecção de etanol presente no ar liberado por sementes de soja durante o processo de anaerobiose.

ABSTRACT In the seed production sector, it is essential to use fast and practical equipment to help decision-making processes. Thus, the use of sensors that can capture information to assist in agriculture has contributed significantly to soybean cultivation worldwide, being used in several stages, whether pre-harvest or post-harvest. Thus, this study aimed to develop a prototype of ethylometer with an MQ-3 sensor and to evaluate its stabilization time when used in soybean seed lots submitted to hypoxia. The research was carried out with 10 lots of soybean seeds from five cultivars (NS 8383 RR, SOY Peso RR, M 8372 IPRO, M8644 IPRO and M8808 IPRO) and was divided into two stages. The first one corresponds to the development of the ethanol measuring equipment with an MQ-3 sensor, and the second one to measurement of the sensor’s stabilization time (3, 6, 9, 12, 15, 18, 21, 24, 27, and 30 s) in soybean seeds submitted to anaerobiosis. The equipment and the MQ-3 sensor showed the stability of average measurement at 16 s after activation. This time is recommended for use of the ethylometer in soybean seeds. Through the MQ-3 sensor, it is possible to efficiently detect ethanol present in the air released by soy seeds during the anaerobic process.

ABSTRACT The seed sector faces several challenges when it comes to ensuring a quick and accurate decision making when working with large amounts of data on physiological quality of seed lots, which makes the process time-consuming and inefficient. Thus, artificial intelligence (AI) emerges as a new technological option in the seed sector to solve database problems in the post-harvest stages. This study aims to use machine learning to classify maize seed lots. Data were obtained from eight maize seed crops from a private company. These data were mined using the following classifiers: J48 (DecisionTree), RandomForest, CVR (ClassificationViaRegression ) , lBk (lazy.IBK), MLP (MultiLayerPercepton), and NäiveBayes. Cross-validation was used for data measurement, with the data set, including training and testing data, being divided into 10 subsets. The described steps were performed using the Weka software. It is concluded that results obtained allow the classification of maize seed lots with high accuracy and precision, and these algorithms can better classify the maize seed lot through vigor attributes, thus enabling more accurate decision making based on vigor tests on a reduced evaluation time.

ABSTRACT New, efficient, low-cost techniques for image processing and alternative machine learning for seed processing are of academic and industrial interest. This study aims to identify fissures in bark and peeled rice seeds using X-ray and RGB image processing techniques and machine learning. Samples of three batches of rice seeds were used: a batch of seeds not subjected to drying (peeled seed), and the other two comprised of dried seeds, one containing seeds with husk and another containing huskless seeds; each sample comprised 100 seeds. Images in X-ray and RGB formats were provided in the sequence processed in ImageJ software and introduced in the machine learning software, where they were pre-processed using the appropriate filters and then classified by the J48 and linear discriminant analysis (LDA) classifiers. X-ray images obtained using differentiated equipment allow the identification of cracks in rice seeds using image processing techniques and the LDA classifier. Capturing images using RGB is a viable alternative. Using filters, either individually or in combination, may constitute an adequate alternative for rice seed classification.

ABSTRACT The seed germination and vigor evaluation are essential for the sowing sector to measure the performance of different seed lots and improve the efficiency of storage and sowing processes. However, the analysis of various tests to determine seed quality generates a large amount of information, making it almost impossible for humans to perform a quick and effective quality control analysis. Therefore, the objective of this study was to evaluate the differences in the physiological quality of soybean seeds in different cultivars using machine learning techniques to rank the lots based on their quality. Three cultivars were used, and the analysis was germination, accelerated aging, tetrazolium treatment, seedling emergence, and 1000 seed weight from 65 lots were measured. The lots were evaluated in two phases, one immediately after harvest and the other after six months of storage. Random forest, multi-layer perceptron, J48, and classification via regression classifiers were used, aided by the feature resampler technique. Random forest and classification via regression obtained the highest accuracy, and the random forest technique obtained the best results. Therefore, it is possible to classify soybean seed lots with great accuracy and precision using artificial intelligence and machine learning techniques.

RESUMO A adoção de técnicas e equipamentos laboratoriais rápidos e confiáveis para a escolha dos melhores lotes de sementes para comercialização influenciará a produção de soja com qualidade fisiológica superior, entre outras áreas do setor. Diante disto, objetivou-se avaliar as concentrações de CO2 produzido por sementes de soja embebidas em água e comprovar a eficácia de um novo equipamento que auxilie na seleção de lotes com diferentes níveis de vigor. Para avaliação da qualidade física e fisiológica das sementes, oito lotes de soja foram avaliados com os seguintes testes: teor de água, peso de mil sementes, primeira contagem de germinação, germinação, condutividade elétrica, emergência e respiração avaliadas pelo aparelho Pettenkoffer e com equipamento projetado para medir CO2 em sementes. Os resultados foram submetidos à análise de variância com médias comparadas pelo teste de Tukey a p ≤ 0,05. Os métodos convencionais evidenciaram diferenças significativas do vigor e viabilidade em sementes de soja. O equipamento desenvolvido se mostrou eficiente na detecção de CO2 produzido pelas sementes embebidas em água durante 8 horas. As leituras de CO2 com o equipamento apresentaram resultados satisfatórios para predizer o vigor em sementes de soja por meio da respiração.

ABSTRACT The adoption of quick and reliable laboratory techniques and equipment to choose the best seed lots for marketing will influence the production of soybeans with superior physiological quality, among other areas in the sector. Therefore, the objective of this study was to evaluate the CO2 concentrations produced by water-soaked soybean seeds and to verify the effectiveness of new equipment to help choose lots with different vigor levels. To evaluate the physical and physiological quality of the seeds, eight soybean lots were evaluated with the following tests: water content, weight of thousand seeds, first germination count, germination, electrical conductivity, emergence, and respiration evaluated by the Pettenkoffer apparatus and with equipment designed to measure CO2 in seeds. The results were subjected to analysis of variance with means compared by Tukey’s test at p ≤ 0.05. Conventional methods showed significant differences in vigor and viability in soybean seeds. The equipment designed was efficient in detecting CO2 produced by seeds soaked in water for 8 hours. The CO2 readings with the equipment presented satisfactory results to predict the vigor in soybean seeds through respiration.

RESUMO As características dos materiais utilizados nas embalagens para armazenamento de sementes podem influenciar negativamente no processo de deterioração, acarretando problemas futuros no período de armazenamento e na emergência em campo. Desta forma, objetivou-se avaliar a qualidade fisiológica de sementes de soja, armazenadas em diferentes embalagens com ou sem adição de CO2 (atmosfera modificada) em diferentes períodos e condições ambientais não controladas. Para a realização do experimento foi utilizado um lote de sementes de soja da cultivar SYN 1059 RR. Utilizou-se um delineamento inteiramente casualizado em esquema de parcelas subdivididas, com três tipos de embalagens (embalagem permeável, embalagem hermética dentro da embalagem permeável e embalagem hermética dentro da embalagem permeável com injeção de CO2) na parcela principal e seis períodos de armazenamento (zero, 45, 90, 135, 180 e 225 dias) na subparcela, com quatro repetições para cada tratamento, totalizando 72 unidades experimentais. Foram utilizadas embalagens de papel multifoliado, hermética e hermética com injeção de CO2, armazenadas por 225 dias e avaliação em intervalos regulares de 45 dias. A cada período, as sementes foram submetidas aos testes de grau de umidade, germinação, emergência de plântulas, envelhecimento acelerado e condutividade elétrica. A embalagem hermética, com e sem injeção de CO2, diminui a velocidade da deterioração das sementes de soja. A embalagem hermética permite uma maior qualidade fisiológica das sementes de soja comparativamente à embalagem permeável, no período de armazenamento de até 180 dias sob condições ambientais não controladas. A adição de CO2 no interior de embalagens herméticas favorece a manutenção da qualidade fisiológica de sementes de soja no armazenamento.

ABSTRACT The characteristics of materials used in packages for seed storage may have a negative influence in the deterioration process, causing future problems during the period of storage and in emergence in the field. In this study, the objective was to evaluate the physiological quality of soybean seeds, stored in different packages with and without the addition of CO2 (modified atmosphere), for different periods of storage and in uncontrolled environmental conditions. In order to carry out the experiment, a completely randomized design was used in a split-plot scheme, with three types of packages (permeable, hermetic package inside the permeable package and hermetic package inside the permeable package with CO2 injection) in the main plot and six storage periods (zero, 45, 90, 135, 180 and 225 days) in the subplot, with four repetitions, totaling 72 experimental units. In hermetic packages multi-layer paper was used with or without CO2 injection, stored them for 225 days and performed an assessment at regular intervals of 45 days. At each period, the seeds were submitted to tests for moisture content, germination, seedling emergence, accelerated aging and electrical conductivity. The hermetic package, with and without CO2 injection, decreases the speed of deterioration of soybean seeds. The hermetic package allows a higher physiological quality of soybeans compared to the permeable package, with a storage period of up to 180 days under uncontrolled environmental conditions. The addition of CO2 inside the hermetic packages favors the maintenance of the physiological quality of soybean seeds in storage.

ABSTRACT The aim of this research was to study the linear correlations and spatial distribution between soil attributes and productivity and physiological quality of wheat seeds. Soil samples were collected at georeferenced points in an area of 41 ha with a rectangular grid of 100 × 100 m to determine soil fertility. Grain productivity, number of ears m-2, protein content, and physiological seed quality were assessed. The results were submitted to Pearson's correlation analysis, descriptive statistics, and geostatistics. Phosphorus content presented a high spatial variability, with a coefficient of variation of 97.79%. Protein content, number of ears, and SMP index presented low values of coefficient of variation, indicating their low spatial variability. Physiological seed quality was not correlated with soil attributes. Wheat productivity showed a strong correlation between calcium and soil organic matter contents, as verified by analyzing the spatial distribution maps. The analysis of the spatial distribution maps of soil nutrients is a tool that can contribute to farmers’ decision making in the management of crop fertilization aiming at increasing productivity.

ABSTRACT Currently, the domestic agricultural sector has become increasingly professionalized; therefore, measures aimed at safety in the workplace and monitoring of environmental risks have been gaining major importance in this scenario. Thus, this study aimed at assessing internal environmental conditions of four soybean processing plants (SPPs) operating with a screen-air machine, densimetric table and with or without spiral separator. These plants are in the state of Rio Grande do Sul (Brazil), being assessed on site considering every feature related to machinery and equipment, as well as technological level. Field evaluations comprised measurements of noise, illuminance and suspended dust. Results showed that none of the SPPs is in full accordance with current laws for the investigated parameters, among which noise level is what most threatens the environmental conditions. Moreover, lightening conditions are unsatisfactory since the environments are extremely dark, not reaching minimal standard. Regarding the suspended dust is possible to claim that there is an emerging risk.

O uso da mesa densimétrica pode resultar no aprimoramento da qualidade de sementes de diversas espécies, evidenciando superioridade dos atributos de qualidade das sementes coletadas nas posições superiores em relação às posições inferiores da zona de descarga da mesa densimétrica. A disponibilidade de informações sobre sementes de tabaco, particularmente sobre a ação da mesa densimétrica, não tem sido contemplada na literatura. O presente trabalho foi realizado com o objetivo de avaliar a influência de diferentes regulagens na mesa densimétrica sobre a qualidade de sementes de tabaco. O eixo terminal de descarga da mesa densimétrica, com largura de 50 cm, foi dividido em quatro partes mais a bica de saída de pedra. Os tratamentos constituíram-se nas frações semente original (obtida no depósito da alimentação) e sementes pesadas, (parte alta), intermediária alta, intermediária baixa e semente leve (baixa) e bica de saída de pedras da zona de descarga da mesa densimétrica. Cada combinação de regulagens constitui-se em um ajuste independente, totalizando sete ajustes. A mesa densimétrica, nos ajustes com mais alta oscilação, apresenta eficiência no aprimoramento da qualidade fisiológica de lotes de sementes de tabaco, pela remoção da fração descarregada na parte baixa da zona de descarga.

The use of gravity table can result in improved quality of seeds of several species, demonstrating the superiority of the quality attributes of seeds collected in the top positions in relation to the lower positions of the discharge zone of the gravity table. The availability of information on tobacco seeds, particularly on the action of gravity table, has not been addressed in the literature. The present study was to evaluate the influence of different regulations in the gravity table on the quality of tobacco seeds. The terminal edge of the machine of 50 cm width was divided into four parts plus the outlet for stones. The treatments were in the following fractions: original seed (obtained in the feed hopper), heavy seed (at the top), middle high, intermediate, and light seed (lower part), and the stones outlet of the gravity table. Each combination of regulation was in an independent adjustment with a total of seven adjusts. The gravity table, in the adjustments with high oscillation, was efficient in improving the physiological quality of seed lots of tobacco, by removing the fraction of light seeds discharged at the bottom of the terminal edge.