scholarly journals A Computational Procedure for the Recognition and Classification of Maize Leaf Diseases Out of Healthy Leaves Using Convolutional Neural Networks

2019 ◽  
Vol 1 (1) ◽  
pp. 119-131 ◽  
Author(s):  
Malusi Sibiya ◽  
Mbuyu Sumbwanyambe
Keyword(s):  
Smart Phone ◽  
Computational Procedure ◽  
Gray Leaf Spot ◽  
Laboratory Methods ◽  
Maize Leaf ◽  
Plant Leaf ◽  
Puccinia Sorghi ◽  
Vegetables And Fruits ◽  
Corn Leaf Blight

Plant leaf diseases can affect plant leaves to a certain extent that the plants can collapse and die completely. These diseases may drastically decrease the supply of vegetables and fruits to the market, and result in a low agricultural economy. In the literature, different laboratory methods of plant leaf disease detection have been used. These methods were time consuming and could not cover large areas for the detection of leaf diseases. This study infiltrates through the facilitated principles of the convolutional neural network (CNN) in order to model a network for image recognition and classification of these diseases. Neuroph was used to perform the training of a CNN network that recognised and classified images of the maize leaf diseases that were collected by use of a smart phone camera. A novel way of training and methodology was used to expedite a quick and easy implementation of the system in practice. The developed model was able to recognise three different types of maize leaf diseases out of healthy leaves. The northern corn leaf blight (Exserohilum), common rust (Puccinia sorghi) and gray leaf spot (Cercospora) diseases were chosen for this study as they affect most parts of Southern Africa’s maize fields.

scholarly journals A Computational Procedure for the Recognition and Classification of Maize Leaf Diseases out of Healthy Leaves Using Convolutional Neural Networks

2019 ◽  
Author(s):  
Malusi Sibiya ◽  
Mbuyu Sumbwanyambe
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Smart Phone ◽  
Computational Procedure ◽  
Gray Leaf Spot ◽  
Maize Leaf ◽  
Plant Leaf ◽  
Vegetables And Fruits ◽  
Corn Leaf Blight

Plant leaf diseases can affect the plants’ leaves to an extent that the plants can collapse and die completely. These diseases may drastically drop the supply of vegetables and fruits to the market, and result in a low agricultural economy. In the literature, different laboratory methods of plant leaf disease detection have been used. These methods were time consuming and could not cover large areas for the detection of leaf diseases. This study infiltrates through the facilitated principles of the Convolutional Neural Networks (CNN) in order to model a network for image recognition and classification of these diseases. Neuroph was used to perform the training of a CNN network that recognized and classified images of the maize leaf diseases that were collected by use of a smart phone camera. A novel way of training and the methodology used, expedite a quick and easy implementation of the system in practice. The developed model was able to recognize 3 different types of maize leaf diseases out of healthy leaves. The Northern Corn Leaf Blight (Exserohilum), Common Rust (Puccinia sorghi) and Gray Leaf Spot (Cerospora) diseases were chosen for this study as they affect most parts of Southern Africa’s maize fields.

scholarly journals Smartphone enabled Counterfeit Note Detection using Siamese Network

2019 ◽  
Vol 9 (2S) ◽  
pp. 598-604
Keyword(s):  
Neural Network ◽  
Feature Extraction ◽  
Data Augmentation ◽  
Feasible Solution ◽  
Smart Phone ◽  
Research Articles ◽  
Distinctive Features ◽  
Siamese Network ◽  
Processing Data

Counterfeit note has a disastrous impact on a country’s economy. The circulation of such fake notes not only diminishes the value of genuine note but also results in inflation. The feasible solution to this burning issue is to create awareness about the counterfeit notes among public and to equip them with a technology to detect fake notes on their own. Though there exist numerous research articles on detection of fake notes, they are not handy. The reason for this could be the unavailability or unaffordability in acquiring the equipment for the same. This paper proposes an approach whose implementation can easily be deployed on a smart phone and hence anyone with access to them can use the application to detect the fake notes. The proposed approach consists of the processing phases including image procurement, pre-processing, data augmentation, feature extraction and classification. ₹500 notes are considered for experimentation analysis. Out of 17 distinctive features, 3 such from the obverse side are considered to evaluate the genuineness of the note. Siamese neural network is employed to build a model for effective classification of the notes. The performance of the proposed approach is evaluated at 85% with respect to accuracy.

scholarly journals Hypothyroidism: a lecture for primary care physicians

2020 ◽  
pp. 124-130
Author(s):  
E. A. Panfilova ◽  
M. P. Isaeva ◽  
E. A. Troshina
Keyword(s):  
Primary Care Physicians ◽  
Primary Hypothyroidism ◽  
Point Of View ◽  
Age Group ◽  
Laboratory Methods ◽  
Pathological Conditions ◽  
Potential Benefits ◽  
Drug Doses ◽  
Principles Of Treatment

The prevalence of hypothyroidism in the population is high. The frequency of manifest hypothyroidism in the world, according to various data, is 0.2–2.0%, subclinical one – up to 10% for women and up to 3% for men, and in the older age group (over 70 years) reaches 14%, with the majority of cases of hypothyroidism accounted for primary hypothyroidism. Thus, a doctor of any specialty in his practice is likely to meet a patient with hypothyroidism: both with the established diagnosis, and face the need for differential diagnosis of various pathological conditions with hypothyroidism. This article presents a classification of hypothyroidism based on etiological aspects, describes the clinical picture of the disease, pays special attention to the so-called «masks» of hypothyroidism, which, in our view, can be useful for a doctor of any specialty, provides available methods for diagnosing this syndrome (special attention is paid to laboratory methods), as well as the goals and principles of treatment, highlights the need to monitor laboratory indicators in dynamics against the background of treatment. In addition, the features of correction of hypothyroidism during pregnancy are given. The article presents the peculiarities of selecting drug doses depending on the patient’s age and comorbidity. The distinctive feature and the purpose of this article, from our point of view, is its potential benefits not only for endocrinologists, but also for other health professionals.

scholarly journals Validation of Consensus Quantitative Trait Loci Associated with Resistance to Multiple Foliar Pathogens of Maize

2009 ◽  
Vol 99 (5) ◽  
pp. 540-547 ◽  
Author(s):  
Godfrey Asea ◽  
Bindiganavile S. Vivek ◽  
George Bigirwa ◽  
Patrick E. Lipps ◽  
Richard C. Pratt
Keyword(s):  
Quantitative Trait Loci ◽  
Disease Severity ◽  
Quantitative Trait ◽  
Gray Leaf Spot ◽  
Sub Saharan Africa ◽  
Maize Production ◽  
Resistant Parent ◽  
Trait Loci ◽  
Sub Saharan ◽  
Corn Leaf Blight

Maize production in sub-Saharan Africa incurs serious losses to epiphytotics of foliar diseases. Quantitative trait loci conditioning partial resistance (rQTL) to infection by causal agents of gray leaf spot (GLS), northern corn leaf blight (NCLB), and maize streak have been reported. Our objectives were to identify simple-sequence repeat (SSR) molecular markers linked to consensus rQTL and one recently identified rQTL associated with GLS, and to determine their suitability as tools for selection of improved host resistance. We conducted evaluations of disease severity phenotypes in separate field nurseries, each containing 410 F2:3 families derived from a cross between maize inbred CML202 (NCLB and maize streak resistant) and VP31 (a GLS-resistant breeding line) that possess complimentary rQTL. F2:3 families were selected for resistance based on genotypic (SSR marker), phenotypic, or combined data and the selected F3:4 families were reevaluated. Phenotypic values associated with SSR markers for consensus rQTL in bins 4.08 for GLS, 5.04 for NCLB, and 1.04 for maize streak significantly reduced disease severity in both generations based on single-factor analysis of variance and marker-interval analysis. These results were consistent with the presence of homozygous resistant parent alleles, except in bin 8.06, where markers were contributed by the NCLB-susceptible parent. Only one marker associated with resistance could be confirmed in bins 2.09 (GLS) and 3.06 (NCLB), illustrating the need for more robust rQTL discovery, fine-mapping, and validation prior to undertaking marker-based selection.

scholarly journals Effect of Maize Hybrid and Foliar Fungicides on Yield Under Low Foliar Disease Severity Conditions

2015 ◽  
Vol 105 (8) ◽  
pp. 1080-1089 ◽  
Author(s):  
Sally O. Mallowa ◽  
Paul D. Esker ◽  
Pierce A. Paul ◽  
Carl A. Bradley ◽  
Venkata R. Chapara ◽  
...  
Keyword(s):  
Disease Severity ◽  
Field Trials ◽  
Gray Leaf Spot ◽  
Growth Stages ◽  
Lower Yield ◽  
Fungicide Application ◽  
Cercospora Zeae Maydis ◽  
Physiological Benefits ◽  
Foliar Fungicide ◽  
Corn Leaf Blight

Foliar fungicide use in the U.S. Corn Belt increased in the last decade; however, questions persist pertaining to its value and sustainability. Multistate field trials were established from 2010 to 2012 in Illinois, Iowa, Ohio, and Wisconsin to examine how hybrid and foliar fungicide influenced disease intensity and yield. The experimental design was in a split-split plot with main plots consisting of hybrids varying in resistance to gray leaf spot (caused by Cercospora zeae-maydis) and northern corn leaf blight (caused by Setosphaera turcica), subplots corresponding to four application timings of the fungicide pyraclostrobin, and sub-subplots represented by inoculations with either C. zeae-maydis, S. turcica, or both at two vegetative growth stages. Fungicide application (VT/R1) significantly reduced total disease severity relative to the control in five of eight site-years (P < 0.05). Disease was reduced by approximately 30% at Wisconsin in 2011, 20% at Illinois in 2010, 29% at Iowa in 2010, and 32 and 30% at Ohio in 2010 and 2012, respectively. These disease severities ranged from 0.2 to 0.3% in Wisconsin in 2011 to 16.7 to 22.1% in Illinois in 2010. The untreated control had significantly lower yield (P < 0.05) than the fungicide-treated in three site-years. Fungicide application increased the yield by approximately 6% at Ohio in 2010, 5% at Wisconsin in 2010 and 6% in 2011. Yield differences ranged from 8,403 to 8,890 kg/ha in Wisconsin 2011 to 11,362 to 11,919 kg/ha in Wisconsin 2010. Results suggest susceptibility to disease and prevailing environment are important drivers of observed differences. Yield increases as a result of the physiological benefits of plant health benefits under low disease were not consistent.

scholarly journals Survey on Detection and Classification of Plant Leaf Disease in Agriculture Environment

IARJSET ◽  
2017 ◽  
Vol 4 (4) ◽  
pp. 137-139
Author(s):  
Prof. Patil Ashish ◽  
Patil Tanuja
Keyword(s):  
Plant Leaf ◽  
Leaf Disease

scholarly journals Classification of Activities of Daily living using Smart Phones

2019 ◽  
Vol 8 (3) ◽  
pp. 2984-2988
Keyword(s):  
Activities Of Daily Living ◽  
Daily Living ◽  
Human Life ◽  
Smart Phone ◽  
Smart Phones ◽  
Machine Learning Techniques ◽  
Accelerometer Sensor ◽  
Learning Techniques ◽  
Direct Input

Smart phones have become an integral part of everyday human life. These phones are packed with various sensors for different purposes. Most of them are used for understanding the environment in which the user uses the phone so that the device could respond rapidly. Indirectly the phone extracts context information of the users like the activity performed using accelerometer and gyroscope sensors. This information can be used for a variety of applications like home automation, smart environment, etc to perform automatic changes to the environment without direct input from the user. This paper deals with the classification of activities of daily living like walking, jogging, sitting, standing, upstairs and downstairs using the data collected from accelerometer sensor within the smart phone. A comparative analysis has been performed on different machine learning techniques for activity classification.

scholarly journals Real-Time Plant Health Assessment via implementing Cloud-Based Scalable Transfer Learning on AWS DeepLens

2020 ◽  
Author(s):  
Asim Khan ◽  
Umair Nawaz ◽  
Anwaar Ulhaq ◽  
Randall W. Robinson
Keyword(s):  
Real Time ◽  
Transfer Learning ◽  
Fruits And Vegetables ◽  
Early Stage ◽  
Economic Loss ◽  
Disease Diagnosis ◽  
Data Set ◽  
Plant Leaf ◽  
Leaf Disease

In the Agriculture sector, control of plant leaf diseases is crucial as it influences the quality and production of plant species with an impact on the economy of any country. Therefore, automated identification and classification of plant leaf disease at an early stage is essential to reduce economic loss and to conserve the specific species. Previously, to detect and classify plant leaf disease, various Machine Learning models have been proposed; however, they lack usability due to hardware incompatibility, limited scalability and inefficiency in practical usage. Our proposed DeepLens Classification and Detection Model (DCDM) approach deal with such limitations by introducing automated detection and classification of the leaf diseases in fruits (apple, grapes, peach and strawberry) and vegetables (potato and tomato) via scalable transfer learning on A.W.S. SageMaker and importing it on A.W.S. DeepLens for real-time practical usability. Cloud integration provides scalability and ubiquitous access to our approach. Our experiments on extensive image data set of healthy and unhealthy leaves of fruits and vegetables showed an accuracy of 98.78% with a real-time diagnosis of plant leaves diseases. We used forty thousand images for the training of deep learning model and then evaluated it on ten thousand images. The process of testing an image for disease diagnosis and classification using A.W.S. DeepLens on average took 0.349s, providing disease information to the user in less than a second.

scholarly journals Convolutional Neural Network for Classification of Android Applications Represented as Grayscale Images

2019 ◽  
Vol 8 (12S) ◽  
pp. 835-843
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
High Performance ◽  
Smart Phone ◽  
Convolution Neural Network ◽  
Android Malware ◽  
Android Applications ◽  
Conventional Solution ◽  
Grayscale Images

A rapid dissemination of Android operating system in smart phone market has resulted in an exponential growth of threats to mobile applications. Various studies have been carried out in academia and industry for the identification and classification of malicious applications using machine learning and deep learning algorithms. Convolution Neural Network is a deep learning technique which has gained popularity in speech and image recognition. The conventional solution for identifying Android malware needs learning based on pre-extracted features to preserve high performance for detecting Android malware. In order to reduce the efforts and domain expertise involved in hand-feature engineering, we have generated the grayscale images of AndroidManifest.xml and classes.dex files which are extracted from the Android package and applied Convolution Neural Network for classifying the images. The experiments are conducted on a recent dataset of 1747 malicious Android applications. The results indicate that classes.dex file gives better results as compared to the AndroidManifest.xml and also demonstrate that model performs better as the image become larger.

Sign in / Sign up

Export Citation Format

Share Document