Honeydew honey represents about 60% of the annual honey production, mainly pine and fir honey, in Europe and more than 70% of the annual honey production in Greece. Pine honey produced from the honeydew secretions of Marchalina hellenica (Coccoidea: Marchalinidae) is the main category of honeydew honey in Greece, representing about 60% of the annual honey production. In the past, the rate of honeydew production by Marchalina hellenica was believed to be regular and steady every year. However, beekeepers have noted a decrease in the quantity of honeydew in recent years. Therefore, the establishment of a forecasting model of honeydew flow will be of great benefit to beekeepers, honey bees, and the rural economy. In the present work, we employ the Cumulative Logit Model to prove that temperature, and more specifically the number of cold days in February, is a significant parameter to the life cycle of Marchalina hellenica and construct a statistically significant forecasting model.
Cotton constitutes a significant commercial crop and a widely traded commodity around the world. The accurate prediction of its yield quantity could lead to high economic benefits for farmers as well as for the rural national economy. In this research, we propose a multiple-input neural network model for the prediction of cotton’s production. The proposed model utilizes as inputs three different kinds of data (soil data, cultivation management data, and yield management data) which are treated and handled independently. The significant advantages of the selected architecture are that it is able to efficiently exploit mixed data, which usually requires being processed separately, reduces overfitting, and provides more flexibility and adaptivity for low computational cost compared to a classical fully-connected neural network. An empirical study was performed utilizing data from three consecutive years from cotton farms in Central Greece (Thessaly) in which the prediction performance of the proposed model was evaluated against that of traditional neural network-based and state-of-the-art models. The numerical experiments revealed the superiority of the proposed approach.
27 July 2020 in Methodology and Computing in Applied Probability
During the last decade, many researchers have focused on proving identities that reveal the relation between Fibonacci and Lucas numbers. Very recently, one of these identities has been generalized to the case of Fibonacci and Lucas numbers of order k. In the present work, we state and prove a new identity regarding an alternating sum of Fibonacci and Lucas numbers of order k. Our result generalizes recent works in this direction.