scholarly journals Computer Tools for Diagnosing Citrus Leaf Symptoms (Part 2): Smartphone Apps for Expert Diagnosis of Citrus Leaf Symptoms

EDIS ◽  
2020 ◽  
Vol 2020 (5) ◽  
Author(s):  
Arnold Schumann ◽  
Laura Waldo ◽  
Perseveranca Mungofa ◽  
Chris Oswalt
Keyword(s):  
Nutrient Management ◽  
Fine Tuning ◽  
Nutrient Deficiencies ◽  
Computer Tools ◽  
Citrus Leaf ◽  
Visual Identification ◽  
Important Diagnostic Tool ◽  
Citrus Leaves ◽  
Trained Neural Network ◽  
Leaf Symptoms

Visual identification of nutrient deficiencies in foliage is an important diagnostic tool for fine-tuning nutrient management of citrus. This new 2-page article describes a new smartphone app that uses a trained neural network to identify disease and pest symptoms on citrus leaves through your phone's camera. Written by Arnold Schumann, Laura Waldo, Perseveranca Mungofa, and Chris Oswalt, and published by the UF/IFAS Department of Soil and Water Sciences.https://edis.ifas.ufl.edu/ss691

scholarly journals Computer Tools for Diagnosing Citrus Leaf Symptoms (Part 1): Diagnosis and Recommendation Integrated System (DRIS)

EDIS ◽  
2020 ◽  
Vol 2020 (4) ◽  
Author(s):  
Arnold Schumann
Keyword(s):  
Integrated System ◽  
Nutrient Concentrations ◽  
Web Tool ◽  
Computer Tools ◽  
Citrus Leaf ◽  
Leaf Nutrient Concentrations ◽  
Florida Citrus ◽  
Soil And Water ◽  
Leaf Symptoms

This new 2-page article provides instructions for using the Diagnosis and Recommendation Integrated System, or DRIS, a web tool designed for analyzing leaf nutrient concentrations of Florida citrus. Written by Arnold Schumann and published by the UF/IFAS Department of Soil and Water Sciences.

Combining Self-supervised Learning and Active Learning for Disfluency Detection

2022 ◽  
Vol 21 (3) ◽  
pp. 1-25
Author(s):  
Shaolei Wang ◽  
Zhongyuan Wang ◽  
Wanxiang Che ◽  
Sendong Zhao ◽  
Ting Liu
Keyword(s):  
Neural Network ◽  
Active Learning ◽  
Supervised Learning ◽  
Large Scale ◽  
Training Data ◽  
Fine Tuning ◽  
Training Dataset ◽  
Performance Gap ◽  
Annotation Costs ◽  
Trained Neural Network

Spoken language is fundamentally different from the written language in that it contains frequent disfluencies or parts of an utterance that are corrected by the speaker. Disfluency detection (removing these disfluencies) is desirable to clean the input for use in downstream NLP tasks. Most existing approaches to disfluency detection heavily rely on human-annotated data, which is scarce and expensive to obtain in practice. To tackle the training data bottleneck, in this work, we investigate methods for combining self-supervised learning and active learning for disfluency detection. First, we construct large-scale pseudo training data by randomly adding or deleting words from unlabeled data and propose two self-supervised pre-training tasks: (i) a tagging task to detect the added noisy words and (ii) sentence classification to distinguish original sentences from grammatically incorrect sentences. We then combine these two tasks to jointly pre-train a neural network. The pre-trained neural network is then fine-tuned using human-annotated disfluency detection training data. The self-supervised learning method can capture task-special knowledge for disfluency detection and achieve better performance when fine-tuning on a small annotated dataset compared to other supervised methods. However, limited in that the pseudo training data are generated based on simple heuristics and cannot fully cover all the disfluency patterns, there is still a performance gap compared to the supervised models trained on the full training dataset. We further explore how to bridge the performance gap by integrating active learning during the fine-tuning process. Active learning strives to reduce annotation costs by choosing the most critical examples to label and can address the weakness of self-supervised learning with a small annotated dataset. We show that by combining self-supervised learning with active learning, our model is able to match state-of-the-art performance with just about 10% of the original training data on both the commonly used English Switchboard test set and a set of in-house annotated Chinese data.

scholarly journals An Agricultural Tele-Monitoring Method in Detecting Nutrient Deficiencies of Oil Palm Leaf

2018 ◽  
Vol 7 (4.11) ◽  
pp. 266
Author(s):  
Muhammad Asraf H. ◽  
Nooritawati Md Tahir ◽  
Nur Dalila K.A. ◽  
Aini Hussain
Keyword(s):  
Oil Palm ◽  
Predictive Value ◽  
Nutrient Management ◽  
Absolute Error ◽  
Performance Measure ◽  
Image Processing Technique ◽  
Nutritional Deficiencies ◽  
Support Vector ◽  
Nutrient Deficiencies ◽  
Monitoring Method

Nutrient management in oil palm plantation is considered as one of the prominent issues especially for smallholder farmer. The nutrient contained in the tress has always been neglected and untreated and these may cause the trees to suffer from nutrient deficiencies. Therefore, in leveraging the oil yield at the maximum, a telemonitoring system is developed to assess and monitor the lack of nutrients for respective trees. This is done using image processing technique and artificial intelligence in detecting the nutritional deficiencies by analyzing the leaf. The categorization focused by classifying into four major types either as magnesium deficiencies, potassium deficiencies, nitrogen deficiencies or healthy that is based on the oil palm’s leaf surface. This is achieved by extracting the features namely number of red pixels, entropy and correlations. Further, two classifiers specifically support vector machine and artificial neural network is used for classification purpose along with performance measure using accuracy(ACC), Mean Square Error (MSE), Mean Absolute Error (MAE), Sensitivity (SN), Specificity (SP), Positive Predictive Value (PPV), Negative Predictive Value (NPV) based on ten-fold cross-validation. Results attained showed that the best classifier is SVM using RBF kernel (SVM-RBF) that is capable to accurately recognize the nutrient deficiencies with 100% accuracy. 

scholarly journals EFFECT OF INTEGRATED NUTRIENT MANAGEMENT ON NUTRIENT USE EFFICIENCY OF MAJOR NUTRIENTS: A REVIEW

2021 ◽  
Vol 21 (No 1) ◽  
Author(s):  
Barkha . ◽  
Ananya Chakraborty
Keyword(s):  
Crop Production ◽  
Nutrient Management ◽  
Nutrient Use Efficiency ◽  
Mineral Fertilizer ◽  
Utilization Efficiency ◽  
Nutrient Deficiencies ◽  
Nutrient Sources ◽  
Organic Nutrient ◽  
Nutrient Use ◽  
Use Efficiency

Nutrient use efficiency (NUE) is an important concept in the evaluation of crop production systems. With emerging nutrient deficiencies under intensive agriculture, there is a need to improve NUE. One of the approaches to enhance it is by judicious use of fertilizers (adequate rate, effective source, methods and time of application) as well as inclusion of organic manures. Organic nutrient sources are very effective but as their availability is not sufficient to meet the nutrient demand, we have to integrate both organic and inorganic sources of nutrients together in order to achieve higher NUE. Common measures of NUE include Partial Factor Productivity (PFP), Agronomic Efficiency (AE), Apparent Recovery Efficiency (RE), Physiological Efficiency (PE) and Internal Utilization Efficiency (IE). Mineral Fertilizer Equivalent (MFE) is another parameter that can be used to assess short term release of nutrients (mainly nitrogen) from organic nutrient sources

THE RAINFED LOWLAND RICE RESEARCH CONSORTIUM: A MULTI-INSTITUTIONAL APPROACH FOR SUSTAINABLE PRODUCTIVITY INCREASES IN ASIAN RICE-BASED SYSTEMS

1999 ◽  
Vol 35 (2) ◽  
pp. 115-125 ◽  
Author(s):  
R. S. ZEIGLER
Keyword(s):  
Nutrient Management ◽  
Agricultural Research ◽  
Lowland Rice ◽  
Yield Potential ◽  
Multidisciplinary Teams ◽  
Nutrient Deficiencies ◽  
Rice Varieties ◽  
Asian Rice ◽  
Rainfed Lowland ◽  
Research Consortium

Input-responsive, high yielding rice varieties and associated technologies responsible for the doubling of yields on irrigated lands in Asia have not suited the area of more than 40 million hectares of Asian rainfed lowland rice. These environments are home to some of the poorest rural populations in South and Southeast Asia, and the rice crops are subject to drought, prolonged submergence from uncontrolled flooding and nutrient deficiencies. Farmers grow unimproved varieties and these, combined with abiotic stresses and low inputs, result in grain yields often less than 2 t ha−1. The International Rice Research Institute (IRRI) and National Agricultural Research Systems (NARS) have recently joined to form the Rainfed Lowland Rice Research Consortium in order to identify, prioritize and execute strategic research that addresses critical yield and productivity constraints. Principal intervention points for achieving sustainable yield increases are in developing drought- and submergence-tolerant germplasm with good yield potential, improved nutrient management under stress conditions, water use-efficient crop establishment practices, and understanding farmers' approaches to risk management. Multidisciplinary teams of IRRI and NARS scientists execute research at sites selected across the region to represent the key sets of constraints.

scholarly journals Assessing Multi-Micronutrients Deficiency in Agricultural Soils of India

2021 ◽  
Vol 13 (16) ◽  
pp. 9136
Author(s):  
Arvind Kumar Shukla ◽  
Sanjib Kumar Behera ◽  
Chandra Prakash ◽  
Ashok Kumar Patra ◽  
Ch Srinivasa Rao ◽  
...  
Keyword(s):  
Nutritional Quality ◽  
Crop Production ◽  
Management Practices ◽  
Nutrient Management ◽  
Agricultural Soils ◽  
Nutrient Use Efficiency ◽  
Crop Productivity ◽  
Nutrient Deficiencies ◽  
Agricultural Produce ◽  
The Right

The deficiencies of nutrient elements and inappropriate nutrient management practices in agricultural soils of the world is one of the reasons for low crop productivity, reduced nutritional quality of agricultural produce, and animal/human malnutrition. We carried out the present study to evaluate the single and multi-nutrient deficiencies of sulfur (S) and micronutrients (zinc (Zn), boron (B), iron (Fe), copper (Cu) and manganese (Mn)) in agricultural soils of India for their effective management to achieve sustainable crop production, improved nutritional quality in crops and better animal/human health. Altogether, 24,2827 surface soil samples (0 to 15 cm depth) were collected from the agriculture fields of 615 districts in 28 states of India and were analyzed for available S and micronutrient concentration. The concentration of available S and micronutrients varied widely. There were variable and widespread deficiencies of S and micronutrients in different states. The deficiencies of S, Zn and B were higher compared to the deficiencies of Fe, Cu and Mn. There were occurrences of two-nutrient (namely S + Zn, Zn + B, S + B, Zn + Fe Zn + Mn, S + Fe, Zn + Cu and Fe + B), three-nutrient (namely S + Zn + B, S + Zn + B and Zn + Fe + B) and four-nutrient (namely Zn + Fe + Cu + Mn and Zn + Fe + Cu + Mn + B) deficiencies in different extents. This information could be used by various stakeholders for production, supply and application of the right kind of fertilizers in different districts, states and agro-ecological regions of India for better crop production, crop nutritional quality, nutrient use efficiency and soil and environmental health. This will also help in a greater way to address the issue of malnutrition in human/animals.

scholarly journals Uji Efektifitas Ekstrak Daun Jeruk Nipis (Citrus aurantifolia) Dalam Menghambat Pertumbuhan Larva Aedes spp

2014 ◽  
Vol 2 (1) ◽  
Author(s):  
Dio K. Prijadi
Keyword(s):  
Mortality Rate ◽  
Leaf Extract ◽  
Hemorrhagic Fever ◽  
Natural Material ◽  
Citrus Aurantifolia ◽  
Citrus Leaf ◽  
Hemorrhagic Fever Virus ◽  
Experimental Laboratory ◽  
Good Potential ◽  
Citrus Leaves

Abstrak: Nyamuk Aedes spp adalah vektor utama dari virus Demam Berdarah Dengue. Pemberantasan vektor dengan menggunakan larvasida kimiawi di nilai masih memiliki banyak kekurangan dan dapat mencemari lingkungan sehingga dikembangkanlah bahan larvasida yang lebih alami. Salah satu bahan yang alami dengan penggunaan daun jeruk nipis (Citrus aurantifolia). Daun jeruk nipis mengandung zat limonoida yang di nilai beracun bagi larva nyamuk. Tujuan Penelitian: Penelitian ini bertujuan untuk mengetahui efek pemberian larvasida ekstrak daun jeruk nipis dalam menghambat pertumbuhan Aedes spp. Metode penelitian : Penelitian ini bersifat deskriptif dengan cara eksperimental laboratorium. Sampel yang digunakan adalah larva nyamuk Aedes spp instar III yang diambil dari kelurahan Malalayang Manado. Dosis yang di gunakan adalah dosis yang telah terbukti efektif dari penellitian-penelitian yang telah dilakukan sebelumya yaitu 100mg per liter air. Hasil Penelitian : Berdasarkan hasil penelitian yang di dapatkan larvasida ekstrak daun jeruk memiliki daya bunuh pada percobaan pertama sebesar 32 ekor jentik dari 50 jentik, percobaan kedua dengan 34 ekor jentik dari 50 jentik dan percobaan ketiga dengan 34 ekor jentik dari 50 jentik. Rata-rata tingkat mortalitas sebesar 67% terhadap larva Aedes spp. Kesimpulan : Ekstrak daun jeruk nipis cukup efektif sebagai larvasida.Kata kunci: Larvasida , Citrus aurantifolia ,  Aedes spp.  Abstract: Aedes spp are the main vectors of Dengue Hemorrhagic Fever virus. Vector elimination using chemical larvicides still has many disadvantage and can pollute the environment because of that there is some research that develop  natural material for larvacides. One of the natural material for larvacides is citrus leaves (Citrus aurantifolia). Citrus leaves contain Limonoida a substances that toxic to mosquito larvae. Objective : This study aimed to determine the effect of larvicides citrus leaf extract in inhibiting the growth of Aedes spp. Methods : The research is using descriptive methods  by an experimental laboratory. The samples used were instar III larvae of Aedes spp are taken from Malalayang Manado. The dose used is the dose that has been shown to be effective from another research that has been done before is 100mg on liter of water. Eksperiment Results :Based on the results of the observation the citrus leaf extract has mortality rate on first eksperiment 32 larvae from total of 50 larvae, the second eksperiment 34 larvae from total of 50 larvae and the third eksperiment 34 larvae from total of 50 larvae. The average mortality rate is 67% against the larvae of Aedes spp. Conclustion : Citrus leaft ekstrack has a good potential as a larvacides. Key words: Larvacides , Citrus aurantifolia ,  Aedes spp.

scholarly journals Revisiting Low-Resolution Images Retrieval with Attention Mechanism and Contrastive Learning

2021 ◽  
Vol 11 (15) ◽  
pp. 6783
Author(s):  
Thanh-Vu Dang ◽  
Gwang-Hyun Yu ◽  
Jin-Young Kim
Keyword(s):  
Image Retrieval ◽  
Feature Space ◽  
Attention Mechanism ◽  
Fine Tuning ◽  
Low Resolution ◽  
Retrieval Task ◽  
Learning Framework ◽  
Visual Descriptors ◽  
Common Technique ◽  
Trained Neural Network

Recent empirical works reveal that visual representation learned by deep neural networks can be successfully used as descriptors for image retrieval. A common technique is to leverage pre-trained models to learn visual descriptors by ranking losses and fine-tuning with labeled data. However, retrieval systems’ performance significantly decreases when querying images of lower resolution than the training images. This study considered a contrastive learning framework fine-tuned on features extracted from a pre-trained neural network encoder equipped with an attention mechanism to address the image retrieval task for low-resolution image retrieval. Our method is simple yet effective since the contrastive learning framework drives similar samples close to each other in feature space by manipulating variants of their augmentations. To benchmark the proposed framework, we conducted quantitative and qualitative analyses of CARS196 (mAP = 0.8804), CUB200-2011 (mAP = 0.9379), and Stanford Online Products datasets (mAP = 0.9141) and analyzed their performances.

scholarly journals Do Not Have Enough Data? Deep Learning to the Rescue!

2020 ◽  
Vol 34 (05) ◽  
pp. 7383-7390 ◽  
Author(s):  
Ateret Anaby-Tavor ◽  
Boaz Carmeli ◽  
Esther Goldbraich ◽  
Amir Kantor ◽  
George Kour ◽  
...  
Keyword(s):  
Text Classification ◽  
Data Augmentation ◽  
State Of The Art ◽  
Language Model ◽  
Original Data ◽  
Fine Tuning ◽  
Initial Training ◽  
Series Of Experiments ◽  
Classification Tasks ◽  
Trained Neural Network

Based on recent advances in natural language modeling and those in text generation capabilities, we propose a novel data augmentation method for text classification tasks. We use a powerful pre-trained neural network model to artificially synthesize new labeled data for supervised learning. We mainly focus on cases with scarce labeled data. Our method, referred to as language-model-based data augmentation (LAMBADA), involves fine-tuning a state-of-the-art language generator to a specific task through an initial training phase on the existing (usually small) labeled data. Using the fine-tuned model and given a class label, new sentences for the class are generated. Our process then filters these new sentences by using a classifier trained on the original data. In a series of experiments, we show that LAMBADA improves classifiers' performance on a variety of datasets. Moreover, LAMBADA significantly improves upon the state-of-the-art techniques for data augmentation, specifically those applicable to text classification tasks with little data.

Sign in / Sign up

Export Citation Format

Share Document