Estimating the Fruit Weight of an Eggplant (Solanummelongena) (Coursework Sample)

First name Last name
Professor’s Name
Course Number
Date
Estimating the fruit weight of an eggplant (Solanummelongena) employing artificial neural network
Abstract
While computing for the variation level of a certain character in comparison to others, it would be significant and very helpful to initially consider approximating the relation amid inconstant factors. This study intends to research on the various outcomes of diverse phenologic and agronomic features on the entirely-produced mass of eggplant fruit. For this study, some of the considered phenologic and agronomic factors are length of the plant, fruit length and weight, width of the plant, fruit quantity per plant, weight to length ratio of the fruit, total yield, total flowering days remaining, days to initial harvest, canopy temperature, RWC (relative water content) and chlorophyll. While conducting the study, each plant was experimented upon as a self-sustaining entity. The experimentation entails a criterion to predict the produce of melon via utilization of displaying instrument, for this case an ANNs (Artificial Neutral Networks). For this study, the cultivars were computed for using utmost efficacy and accuracy (MSD=2.35, R2=93%, and EMP=2.01). A final analysis of sensitivity was conducted with the excellent network for products yield, length to width ratio of the fruit and total yield exhibited the highest impact on fruit weight.
Key words: Eggplant,Fruit weight, ANN (Artificial Neural Networks), Sensitivity analysis
Introduction
A global vision of attaining the worldwide food requirements for the increased population has been recently regarded as being very important. For the purposes of improving production efficiency, professionals in the agricultural field have embraced crop models and decision tools in addition to advanced technology in agriculture. Recently, several practitioners of production agriculture have portrayed much interest in developing and improving crop yield, hence making the sector more interesting and promising in terms of crop production. Owing to the swift progress in technology, agriculture is becoming more affordable due to development of predictive tools and crop models ADDIN EN.CITE Shearer20001(Shearer, 2000)1117Shearer, S.AThomasson, J.AMueller, T.GFulton, J.PHiggins, S.FSamson, SYield prediction using a neural network classifier trained using soil landscape features and soil fertility data,Proceeding of Annual International Meeting, Midwest Express Center, Milwaukee, WisconsinProceeding of Annual International Meeting, Midwest Express Center, Milwaukee, Wisconsin2000(Sheareretal., 2000). Eggplant, equally identified as Brinjal, Aubergine or Guinea squash is among the non-tuberous night shade family Solanaceaespecies, as stipulated by Kantharajah and Golegaonkar (2004).
While assessing the yield capability of any eggplant variety, it is essential to consider all possible yield causal factors, while there is the need to examine the connection level of various quantitative qualities as a way of solving any possible issues. Having attained the above, it is easy to instigate an effectual selection program since yield is an attribute with intricate nature that varies due to several factors. It is evident that artificial neutral networks criterion is the best statistical tool that can be utilized in approximating the quality and grade of such connections while estimating the probable yield ADDIN EN.CITE Naroui Rad20153(Naroui Rad, 2015)3317Naroui Rad, Mohammad Rezakoohkan, ShiraliFanaei, Hamid RezaPahlavan Rad, Mohammad RezaApplication of Artificial Neural Networks to predict the final fruit weight and random forest to select important variables in native population of melon (Cucumis melo L.)Sci HortiSci Horti108-112181MelonArtificial Neural Network (ANN)Fruit weightModelSistanRandom forest20150304-4238/science/article/pii/S0304423814005743http://dx.doi.org/10.1016/j.scienta.2014.10.025(Naroui Radet al., 2015). The apposite facts regarding these plant’s aspects plus their relation with the ultimate quantity and quality of the fruit yielded can be of importance to the farmers, more so while making earlier financial decisions ADDIN EN.CITE Naroui Rad20104(Naroui Rad, 2010)4417Naroui Rad, MRAllahdoo, MFanaei , HRStudy of some yield traits relationship in melon germplasm gene bank of iran by correlation and factor analysis Iranian Journal of HorticultureIranian Journal of Horticulture27-32812010(Naroui Rad et al., 2010). Several studies have conducted comparative analysis for an eggplant’s fruit production with respect to its morpho-phenological properties and components of the plants utilizing multivariate assessment for instance MLP (multiple linear regressions), FA (factor analysis), and PA (path analysis), among other approaches ADDIN EN.CITE Shinde20125(Nabavi-Pelesaraei, 2013; Shinde, 2012)5517Shinde, K.GBirajdar, U.MBhalekar, M.NPatil, B.TCorrelation and path analysis in eggplant (Solanum melongena L.)Vegetable. SciVegetable. Sci108-1103912012Nabavi-Pelesaraei201366617Nabavi-Pelesaraei, ASadeghzadeh, AMir Hossein, PGhasemi Mobtaker, HEnergy flow modeling, economic and sensitivity analysis of eggplant production in Guilan province of IranInt. J. Agric &Crop. SciInt. J. Agric &Crop. Sci3006-30155242013(Nabavi-Pelesaraeiet al., 2013; Shindeet al., 2012).
The standard weight of the fruit exhibited indirect positive impact on with respect to the fruit’s breadth and width, number of initial branches, duration to 50% flowering, and the duration to initial harvest. Consecutively, this weight had significant negative impacts on the height of the plant, fruit girth, quantity of fruits per plant and harvest duration. Additionally, the harvest duration was considered positive, while the average weight of the fruit, fruit length, height of the plant, total number of initial branches, duration to initial 50%flowering, and duration to initial harvest were negative. It is therefore important to consider the indirect impact of such aspects on brinjal for the purposes of perfecting the brinjal’s program ADDIN EN.CITE Shinde20125(Shinde et al., 2012)5517Shinde, K.GBirajdar, U.MBhalekar, M.NPatil, B.TCorrelation and path analysis in eggplant (Solanum melongena L.)Vegetable. SciVegetable. Sci108-1103912012(Shinde et al., 2012). The leading disadvantage realized by employing regression-based approaches is their inability to capture the vastly nonlinear and intricate connection amid seed yield and the pertinent properties of the crop plant.
Contrary to customary approaches such as PA and MLR methods, the use of AI (artificial intelligence) approaches such as ANFIS (adaptive neuro-fuzzy inference system), ANN (artificial neutral networks) and genetic expression programming have been recently employed by scholars and researchers in agricultural science PEVuZE5vdGU+PENpdGU+PEF1dGhvcj5FbWFtZ2hvbGl6YWRlaDwvQXV0aG9yPjxZZWFyPjIwMTU8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...