Predictive Model for Maize Stem Borers’ Classification in Precision Farming

This paper presents Predictive Model for Stem Borers’ classification in Precision Farming. The recent announcement of the aggressive attack of stem borers (Spodoptera species) to maize crops in Africa is alarming. These species migrate in large numbers and feed on maize leaf, stem, and ear of corn. The male of these species are the target because after mating with their female counterpart, thousands of eggs are laid which produces larvae that create the havoc. Currently, Nigerian farmers find it difficult to distinguish between these targeted species (Fall Armyworm-FAW, African Armyworm-AAW and Egyptian cotton leaf worm-ECLW only) because they look alike in appearance. For these reasons, the network model that would predict the presence of these species in the maize farm to farmers is proposed. The maize species were captured using delta pheromone traps and laboratory breeding for each category. The captured images were pre-processed and stored in an online Google drive image dataset folder created. The convolutional neural network (CNN) model for classifying these targeted maize moths was designed from the scratch. The Google Colab platform with Python libraries was used to train the model called MothNet. The images of the FAW, AAW, and ECLW were inputted to the designed MothNet model during learning process. Dropout and data augmentation were added to the architecture of the model for an efficient prediction. After training the MothNet model, the validation accuracy achieved was 90.37% with validation loss of 24.72%, and training accuracy 90.8% with loss of 23.25%, and the training occurred within 5minutes 33seconds. Due to the small amount of images gathered (1674), the model prediction on each image was of low confident. Because of this, transfer learning was deployed and Resnet 50 pretrained model selected and modified. The modified ResNet-50 model was fine-tuned and tested. The model validation accuracy achieved was 99.21%, loss of 3.79%, and training accuracy of 99.75% with loss of 2.55% within 10mins 5 seconds. Hence, MothNet model can be improved on by gathering more images and retraining the system for optimum performance while modified ResNet 50 is recommended to be integrated in Internet of Things device for maize moths’ classification on-site.

Download Full-text

Constituency Agents and British Party Politics

British Journal of Political Science ◽

10.1017/s0007123400008310 ◽

1975 ◽

Vol 5 (4) ◽

pp. 459-476 ◽

Cited By ~ 1

Author(s):

Robert Frasure ◽

Allan Kornberg

Keyword(s):

Party Politics ◽

Office Work ◽

Job Descriptions ◽

Large Numbers ◽

History Of ◽

And Training

We began by reviewing the history of agency and by describing the two major parties' procedures for recruiting and training agents. Not surprisingly, the perceptions that agents have of their roles is not entirely congruent with official perceptions. Approximately 20 per cent of the agents of both parties felt that the performance of various representational functions was the most important part of their job although these tasks are not included in official job descriptions. Moreover, although a majority of the agents in each party believed that their most important job was to build and maintain constituency organizations capable of winning elections, the majority of their time was not spent on this task. Conservative agents seemingly spent a disproportionate amount of time doing routine office work, whereas over 40 per cent of the Labour agents spent much of their time trying to raise the funds that paid their salaries. Large numbers of agents in both parties agreed that raising money in their constituencies was a difficult and largely unrewarding task.

Download Full-text

Spodoptera frugiperda (fall armyworm).

10.1079/cpc.29810.20210102715 ◽

2021 ◽

Author(s):

Ivan Rwomushana

Keyword(s):

Spodoptera Frugiperda ◽

Host Plants ◽

Indian Subcontinent ◽

Fall Armyworm ◽

Climatic Conditions ◽

Vegetable Crops ◽

Large Numbers ◽

Significant Damage ◽

Lepidopteran Pest ◽

The Ideal

Abstract The fall armyworm, Spodoptera frugiperda, is a lepidopteran pest that feeds in large numbers on the leaves, stems and reproductive parts of more than 350 plant species, causing major damage to economically important cultivated grasses such as maize, rice, sorghum, sugarcane and wheat but also other vegetable crops and cotton. Native to the Americas, it has been repeatedly intercepted at quarantine in Europe and was first reported from Africa in 2016 where it caused significant damage to maize crops. In 2018, S. frugiperda was first reported from the Indian subcontinent (Ganiger et al., 2018; Sharanabasappa Kalleshwaraswamy et al., 2018). It has since invaded Bangladesh, Thailand, Myanmar, China and Sri Lanka (IPPC, 2018b, 2019; FAO, 2019c). The ideal climatic conditions for fall armyworm present in many parts of Africa and Asia, and the abundance of suitable host plants suggests the pest can produce several generations in a single season, and is likely to lead to the pest becoming endemic.

Download Full-text

Research on Cultural Factors in Global E-Learning

Encyclopedia of Distance Learning, Second Edition ◽

10.4018/978-1-60566-198-8.ch259 ◽

2011 ◽

pp. 1758-1765

Author(s):

Donald Stepich ◽

Seung Youn (Yonnie) Chyung ◽

Allison Smith-Hobbs

Keyword(s):

Global Economy ◽

Cultural Dimensions ◽

Web Page ◽

Large Numbers ◽

Learning Programs ◽

E Learning ◽

Traditional Classroom Instruction ◽

And Performance ◽

And Training ◽

Theoretical Overview

Simply put, e-learning refers to Internet-based learning. E-learning can take place by reading a piece of information, such as a Web page, or completing a package of instruction, both of which are designed to impact learning and performance (Rosenberg, 2000). E-learning has rapidly gained momentum, especially in large international companies, due to the globalization of business. Businesses in the current global economy need to provide fast-changing information to large numbers of employees and customers at dispersed locations more efficiently than ever (Rosenberg, 2000). Although traditional classroom instruction is still the primary mode for delivering training (Sugrue, 2003), e-learning enables the delivery of content to global locations in a timely manner (Hartley, 2001). Although e-learning promises learning opportunities for anyone, anytime, and anywhere, reliably producing successful learning outcomes is a challenge. Unfortunately, e-learning programs often suffer high dropout rates (Wang, Foucar-Szocki, Griffin, O’Connor, & Sceiford, 2003). There are various reasons for this, but with e-learning, “the lack of cultural adaptation is a leading reason why e-learning fails to work” (Dunn & Marinetti, n.d.). This article addresses e-learning as a method for both education and training in a global economy, and it questions how e-learning can effectively reach a multicultural audience. It provides a theoretical overview of various cultural dimensions, and addresses the importance of considering multicultural factors and strategies in the design of e-learning.

Download Full-text

Cotton Leaf Curl Virus Disease Predictive Model Based on Environmental Variables

Improvement of Crops in the Era of Climatic Changes ◽

10.1007/978-1-4614-8824-8_13 ◽

2014 ◽

pp. 323-335

Author(s):

Safdar Ali ◽

M. Aslam Khan ◽

Shahbaz Talib Sahi ◽

M. Atiq ◽

A. Hannan

Keyword(s):

Predictive Model ◽

Environmental Variables ◽

Virus Disease ◽

Cotton Leaf ◽

Model Based ◽

Cotton Leaf Curl Virus ◽

Leaf Curl Virus ◽

Leaf Curl

Download Full-text

Promoter CpG density predicts downstream gene loss-of-function intolerance

10.1101/2020.02.15.936351 ◽

2020 ◽

Cited By ~ 1

Author(s):

Leandros Boukas ◽

Hans T. Bjornsson ◽

Kasper D. Hansen

Keyword(s):

Predictive Model ◽

Gene Loss ◽

Cpg Islands ◽

Joint Analysis ◽

Loss Of Function ◽

Large Numbers ◽

Human Genes ◽

Individual Contributions ◽

The Individual ◽

Prevailing View

AbstractThe aggregation and joint analysis of large numbers of exome sequences has recently made it possible to de-rive estimates of intolerance to loss-of-function (LoF) variation for human genes. Here, we demonstrate strong and widespread coupling between genic LoF-intolerance and promoter CpG density across the human genome. Genes downstream of the most CpG-rich pro-moters (top 10% CpG density) have a 67.2% probability of being highly LoF-intolerant, using the LOEUF metric from gnomAD. This is in contrast to 7.4% of genes downstream of the most CpG-poor (bottom 10% CpG density) promoters. Combining promoter CpG density with exonic and promoter conservation explains 33.4% of the variation in LOEUF, and the contribution of CpG density exceeds the individual contributions of exonic and promoter conservation. We leverage this to train a simple and easily interpretable predictive model that out-performs other existing predictors and allows us to classify 1,760 genes – which currently lack reliable LOEUF estimates – as highly LoF-intolerant or not. These predictions have the potential to aid in the interpretation of novel patient variants. Moreover, our results reveal that high CpG density is not merely a generic feature of human promoters, but is preferentially encountered at the promoters of the most selectively constrained genes, calling into question the prevailing view that CpG islands are not subject to selection.

Download Full-text

CPSC: Conformal prediction with shrunken centroids for efficient prediction reliability quantification and data augmentation, a case in alternative herbal medicine classification with electronic nose

IEEE Transactions on Instrumentation and Measurement ◽

10.1109/tim.2021.3134321 ◽

2022 ◽

pp. 1-1

Author(s):

Li Liu ◽

Xianghao Zhan ◽

Xikai Yang ◽

Xiaoqing Guan ◽

...

Keyword(s):

Herbal Medicine ◽

Electronic Nose ◽

Data Augmentation ◽

Conformal Prediction ◽

Efficient Prediction ◽

Prediction Reliability

Download Full-text

Tree Structure and Pruning Response of Six Peach Growth Forms

Journal of the American Society for Horticultural Science ◽

10.21273/jashs.119.3.378 ◽

1994 ◽

Vol 119 (3) ◽

pp. 378-382 ◽

Cited By ~ 14

Author(s):

D. Bassi ◽

A. Dima ◽

R. Scorza

Keyword(s):

Prunus Persica ◽

Medium Density ◽

Growth Forms ◽

Training Requirements ◽

Training Systems ◽

Large Numbers ◽

Slender Spindle ◽

Branch Density ◽

And Training ◽

Intermediate Amount

The response of young, nonbearing peach [Prunus persica (L.) Batsch] trees to pruning was studied in six distinct growth forms including semidwarf, spur-type, upright, columnar or pillar, weeping, and standard. Two years after field planting, pillar and upright trees were trained to slender spindle. Semidwarf, spur-type, and standard trees were trained to the open or delayed vase form. Weeping trees were pruned in a manner similar to the Lepage hedge for pear. Branch density before pruning was highest in semidwarf, spur-type, and upright trees and lowest in pillar trees. Standard, semidwarf, and spur-type trees reacted similarly to pruning, but semidwarf trees produced as much wood in the following season as had been pruned off, and produced large numbers of fruiting branches. The small size of semidwarf trees suggested their use for medium-density plantings (MDPs). Pillar trees needed only light pruning. No major cuts were necessary and many fruiting branches were produced even on nonpruned trees. The pillar canopy was 60% thinner and required 50% fewer pruning cuts than the standard canopy and may be particularly suited to high-density plantings (HDPs). The upper canopy of weeping trees grew more than most other forms. They were intermediate in branch density and required an intermediate amount of pruning. Most striking was the unique canopy form of weeping trees, which may be used in developing new training systems. The results of this study suggest that new growth forms have the potential to reduce pruning and training requirements for peach, particularly in MDPs and HDPs. This potential suggests further investigation and exploitation of alternate peach tree growth forms.

Download Full-text

Effective Data Augmentation and Training Techniques for Improving Deep Learning in Plant Leaf Disease Recognition

Applied Science and Engineering Progress ◽

10.14416/j.asep.2021.01.003 ◽

2021 ◽

Author(s):

Prem Enkvetchakul ◽

Olarik Surinta

Keyword(s):

Plant Disease ◽

Data Augmentation ◽

Recognition System ◽

Deep Convolutional Neural Networks ◽

Plant Leaf ◽

Training Techniques ◽

Leaf Disease ◽

Training Technique ◽

Augmentation Techniques ◽

And Training

Plant disease is the most common problem in agriculture. Usually, the symptoms appear on leaves of the plants which allow farmers to diagnose and prevent the disease from spreading to other areas. An accurate and consistent plant disease recognition system can help prevent the spread of diseases and save maintenance costs. In this research, we present a plant leaf disease recognition system using two deep convolutional neural networks (CNNs); MobileNetV2 and NasNetMobile. These CNN architectures are designed to be suitable for smartphones due to the models being small. We have experimented on training techniques; online, offline, and mixed training techniques on two plant leaf diseases. As for data augmentation techniques, we found that the combination of rotation, shift, and zoom techniques significantly increases the performance of the CNN architectures. The experimental results show that the most accurate algorithm for plant leaf disease recognition is NASNetMobile architecture using transfer learning. Additionally, the most accurate result is obtained when combining the offline training technique with data augmentation techniques.

Download Full-text