A daily harvest prediction model of cherry tomatoes by mining from past averaging data and using topological case-based modeling

Hoshi, Takehiko; Sasaki, Taro; Tsutsui, Hiroaki; Watanabe, Tsutomu; Tagawa, Fujio

doi:10.1016/s0168-1699(00)00142-3

Cited by 11 publications

(4 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Neural network models. The NN models accommodate the nonlinear relationship between inputs and output (Hoshi et al, 2000). It appears that the nonlinear nature of these inputs has been elucidated by using NN modeling, which had R 2 values of 0.59 and 0.52 in training and testing, respectively.…”

Section: Discussionmentioning

confidence: 99%

“…First, the time series analysis provided some significant inputs that other methods may have failed to detect. Second, NN models can confirm the practicality of time series analysis and be used to elucidate the nonlinear nature of the contributing inputs (Hoshi et al, 2000). Third, the nature of the inputs can be explored by fitting a regression model with and without transformed input parameters.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Combined Analysis to Characterize Yield Pattern of Greenhouse-grown Red Sweet Peppers

Lin¹,

Frey²,

Nigh³

et al. 2009

horts

View full text Add to dashboard Cite

Understanding the irregular yield pattern of greenhouse-grown sweet peppers (Capsicum annuum L.) has been a challenge to researchers and greenhouse producers. Experimental data from 4 years, each consisting of 26 production weeks, were used in a time series analysis, neural network (NN) modeling, and regression analysis. Time series analysis revealed that weekly yield was influenced by yields from the preceding 2 weeks (Yd_1 and Yd_2), cumulative light 2 and 4 weeks prior (L_2 and L_4), and average 24-h air temperature 5 weeks prior (T_5). Cumulative light (L) data were transformed into kL by dividing by 1000 for subsequent NN modeling and regression analysis. These five inputs were used to establish a NN model, which illustrated the positive influence of Yd_1, kL_4, and kL_2 and negative influence of Yd_2 and T_5. Again, these five inputs were used in a regression analysis illustrating the positive influence of Yd_1 and the negative influence of Yd_2. Each input was further modified to include its squared value before entering the regression, which resulted in significant inputs of Yd_1, Yd_1 squared, and Yd_2 squared. Among these three analyses, the most consistent parameters were Yd_1 and Yd_2, confirming that the irregular yield pattern of greenhouse-grown peppers is of a biological nature. Environmental factors kL_2, kL_4, and T_5 did not show a consistent effect on yield in all three analyses, indicating yield pattern is less influenced by growing environment.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Combined Analysis to Characterize Yield Pattern of Greenhouse-grown Red Sweet Peppers

Lin¹,

Frey²,

Nigh³

et al. 2009

horts

View full text Add to dashboard Cite

show abstract

“…The prediction of maize yield was reported by O'Neal et al (2002) with an overall root mean square error (RMSE) of 10.5%. Hoshi et al (2000) attempted to model the daily yield of cherry tomato grown in greenhouses by using a blackbox approach (i.e., data mining). Lin (2002) suggested NN models for predicting the final fresh weight of lettuce based on environmental parameters and canopy cover.…”

mentioning

confidence: 99%

Neural network modelling to predict weekly yields of sweet peppers in a commercial greenhouse

Lin¹,

Hill²

2008

Can. J. Plant Sci.

View full text Add to dashboard Cite

Lin, W. C. and Hill, B. D. 2008. Neural network modelling to predict weekly yields of sweet peppers in a commercial greenhouse. Can. J. Plant Sci. 88: 531Á536. The production of greenhouse-grown sweet pepper (Capsicum annuum L.) is irregular with a peak-and-valley pattern of weekly yields. We monitored the yields and environment in a commercial greenhouse in British Columbia over six (2000Á2005) growing seasons. Light was defined as cumulative light over the current week, with L_1, L_2, L_3, L_4, L_5 and L_6 representing light over previous weeks. Temperature (AvgT) was defined as the current weekly average of 24-h air temperatures, with T_1, T_2 and T_3 representing temperatures over previous weeks. Inputs were also created for the current weekly yield (Y) and previous weekly yields (Y_1, Y_2, Y_3 and Y_4). Neural network (NN) modelling with up to 21 inputs was used to predict yields 1 wk (Y'1) and 2 wk (Y'2) in advance of the actual fruit harvest. Data for five different years were combined for model training with the year to be predicted held separate as a validation set. The best models used 13 inputs to predict Y'1 with an average R 2 of 0.66 over the 6 yr. Y_4, Y-Y_1, Y_1, L_1, Y, Y_3, Y-Y_3 and wk (of the year) were important inputs. The environmental inputs were of lesser importance, which suggests that the cyclic nature of pepper yields is inherent in the pepper biology. Predicting Y'2 was more difficult with an average R 2 of 0.59 over the 6 yr. NN have good potential for predicting pepper yields.Key words: Capsicum annuum L., flushing, fruit, greenhouse production, neural networks Lin, W. C. et Hill, B. D. 2008. Pre´vision du rendement du poivron dans une serre commerciale par mode´lisation sur re´seau neuronal. Can. J. Plant Sci. 88: 531Á536. La culture du poivron (Capsicum annuum L.) en serre donne des re´sultats irre´guliers avec un rendement hebdomadaire en dents de scie. Les auteurs ont e´tudie´le rendement et l'environnement de cette culture dans une serre commerciale de la Colombie-Britannique durant six saisons ve´ge´tatives (de 2000 a`2005). Pour la lumie`re, les auteurs ont utilise´la luminosite´cumulative de la semaine courante, L_1, L_2, L_3, L_4, L_5 et L_6 correspondant a`cette valeur pour les semaines ante´rieures. La tempe´rature (AvgT) e´tait e´gale a`la moyenne de la tempe´rature ambiante pendant 24 h pour la semaine en cours, T_1, T_2 et T_3 correspondant a`cette valeur pour les semaines ante´rieures. Les auteurs ont aussi cre´e´des intrants pour le rendement de la semaine courante (Y) et de la semaine ante´rieure (Y_1, Y_2, Y_3 et Y_4). La mode´lisation sur re´seau neuronal avec un maximum de 21 parame`tres permet de pre´voir le rendement des poivrons une semaine (Y'1) et deux semaines (Y'2) avant la re´colte proprement dite. Les auteurs ont combine´les donne´es de cinq anne´es pour former le mode`le, l'anne´e pour lesquelles les pre´visions devaient eˆtre calcule´es servant a`la validation. Les meilleurs re´sultats sont obtenus avec 13 parame`tres et le mode`le a pre´vu Y'1 avec ...

show abstract

“…However, to infer relevant knowledge from this information, knowledge discovery (knowledge extraction) with data-mining techniques (extraction rules), which have been demonstrated to be the best tools for agricultural and environmental systems, are used (Hoshi et al, 2000;Poch et al, 2004;Kawano et al, 2005).…”

Section: Introductionmentioning

confidence: 99%

Building a fuzzy logic information network and a decision-support system for olive cultivation in Andalusia [Spain]

Delgado

Aranda

Calero

et al. 2008

Span. j. agric. res.

View full text Add to dashboard Cite

In Southern Spain, olive (Olea europaea L.) growing is an important part of the economy, especially in the provinces of Jaén, Córdoba and Granada. This work proposes the first stages of an Information and Decision-Support System (IDSS) for providing different types of users (farmers, agricultural engineers, public services, etc.) with information on olive growing and the environment, and also assisting in decision-making. The main purposes of the project reported in this paper are to process uncertain or imprecise data, such as those concerning the environment or crops, and combine user data with other scientific-experimental data. The possibility of storing agricultural and ecological information in fuzzy relational databases, vital to the development of an IDSS is described. The information will be processed using knowledge extraction tools (fuzzy data-mining) that will allow rules on expert knowledge for assessing suitability of land to be developed and making thematic maps with the aid of Geographic Information Systems. Flexible querying will allow the users to collect information interactively from databases, while user information is constantly added. Flexible querying of databases, land suitability and thematic maps may be used to help in decisionmaking.Additional key words: expert systems, flexible querying, fuzzy data-mining, fuzzy relational databases, knowledge extraction, user knowledge. ResumenConstrucción de un sistema de información y de ayuda a la decisión mediante lógica difusa para el cultivo del olivar en Andalucía El cultivo del olivo (Olea europaea L.) tiene una enorme importancia económica en la zona sur de España y concretamente en las provincias de Jaén, Córdoba y Granada. En este trabajo se propone la construcción de un sistema de información y ayuda a la toma de decisión (IDSS) que permita en el futuro a distintos tipos de usuarios (agricultores, agrónomos, administraciones públicas, etc.) obtener y manejar información sobre el cultivo de olivar y el soporte ambiental del mismo, así como ayudar en la toma de decisiones. Los principales objetivos desarrollados en este trabajo son el tratamiento de datos inciertos e imprecisos, como es el caso de la información ambiental y sobre cultivos, y la fusión de datos sobre cultivo y otros de carácter científico-experimental. Se describe la posibilidad de almacenar la información de carácter agronómico y ecológico en bases de datos relacionales, que es vital para el desarrollo de un IDSS. La información será procesada a través de herramientas de extracción de conocimiento (minería de datos difusa) y permitirá sobre la base del conocimiento experto el desarrollo de reglas para la clasificación de aptitud del terreno y para la obtención de mapas temáticos con la ayuda de Sistemas de Información Geográfica. La consulta flexible permitirá a los distintos usuarios la consulta interactiva de toda la información almacenada en las bases de datos, así como una implementación constante de las mismas. La consulta flexible de bases de datos, la idonei...

show abstract

A daily harvest prediction model of cherry tomatoes by mining from past averaging data and using topological case-based modeling

Cited by 11 publications

References 5 publications

Combined Analysis to Characterize Yield Pattern of Greenhouse-grown Red Sweet Peppers

Combined Analysis to Characterize Yield Pattern of Greenhouse-grown Red Sweet Peppers

Neural network modelling to predict weekly yields of sweet peppers in a commercial greenhouse

Building a fuzzy logic information network and a decision-support system for olive cultivation in Andalusia [Spain]

Contact Info

Product

Resources

About