scholarly journals Early Detection of Wild Rocket Tracheofusariosis Using Hyperspectral Image-Based Machine Learning

2021 ◽  
Vol 14 (1) ◽  
pp. 84
Author(s):  
Catello Pane ◽  
Gelsomina Manganiello ◽  
Nicola Nicastro ◽  
Francesco Carotenuto
Keyword(s):  
Machine Learning ◽  
Early Detection ◽  
Hyperspectral Image ◽  
Learning Algorithm ◽  
Vegetation Indices ◽  
Symptom Assessment ◽  
Hyperspectral Data ◽  
Cross Prediction ◽  
Average Accuracy ◽  
Wild Rocket

Fusarium oxysporum f. sp. raphani is responsible for wilting wild rocket (Diplotaxis tenuifolia L. [D.C.]). A machine learning model based on hyperspectral data was constructed to monitor disease progression. Thus, pathogenesis after artificial inoculation was monitored over a 15-day period by symptom assessment, qPCR pathogen quantification, and hyperspectral imaging. The host colonization by a pathogen evolved accordingly with symptoms as confirmed by qPCR. Spectral data showed differences as early as 5-day post infection and 12 hypespectral vegetation indices were selected to follow disease development. The hyperspectral dataset was used to feed the XGBoost machine learning algorithm with the aim of developing a model that discriminates between healthy and infected plants during the time. The multiple cross-prediction strategy of the pixel-level models was able to detect hyperspectral disease profiles with an average accuracy of 0.8. For healthy pixel detection, the mean Precision value was 0.78, the Recall was 0.88, and the F1 Score was 0.82. For infected pixel detection, the average evaluation metrics were Precision: 0.73, Recall: 0.57, and F1 Score: 0.63. Machine learning paves the way for automatic early detection of infected plants, even a few days after infection.

scholarly journals Quasiconformal Mapping Kernel Machine Learning-Based Intelligent Hyperspectral Data Classification for Internet Information Retrieval

2020 ◽  
Vol 2020 ◽  
pp. 1-14
Author(s):  
Jing Liu ◽  
Yulong Qiao
Keyword(s):  
Machine Learning ◽  
Quasiconformal Mapping ◽  
Kernel Function ◽  
Hyperspectral Image ◽  
Data Classification ◽  
Data Retrieval ◽  
Hyperspectral Data ◽  
The Internet ◽  
Discriminative Ability ◽  
Kernel Machine

Intelligent internet data mining is an important application of AIoT (Artificial Intelligence of Things), and it is necessary to construct large training samples with the data from the internet, including images, videos, and other information. Among them, a hyperspectral database is also necessary for image processing and machine learning. The internet environment provides abundant hyperspectral data resources, but the hyperspectral data have no class labels and no so high value for applications. So, it is important to label the class information for these hyperspectral data through machine learning-based classification. In this paper, we present a quasiconformal mapping kernel machine learning-based intelligent hyperspectral data classification algorithm for internet-based hyperspectral data retrieval. The contributions include three points: the quasiconformal mapping-based multiple kernel learning network framework is proposed for hyperspectral data classification, the Mahalanobis distance kernel function is as the network nodes with the higher discriminative ability than Euclidean distance-based kernel function learning, and the objective function of measuring the class discriminative ability is proposed to seek the optimal parameters of the quasiconformal mapping projection. Experiments show that the proposed scheme is effective for hyperspectral image classification and retrieval.

scholarly journals HYPERSPECTRAL HYPERION IMAGERY ANALYSIS AND ITS APPLICATION USING SPECTRAL ANALYSIS

2015 ◽  
Vol XL-3/W2 ◽  
pp. 169-175 ◽  
Author(s):  
W. Pervez ◽  
S. A. Khan ◽  
Valiuddin
Keyword(s):  
Machine Learning ◽  
Vegetation Index ◽  
Hyperspectral Image ◽  
Atmospheric Correction ◽  
Hyperspectral Data ◽  
Supervised Machine Learning ◽  
Spectral Signature ◽  
Processing Application ◽  
Significant Difference

Rapid advancement in remote sensing open new avenues to explore the hyperspectral Hyperion imagery pre-processing techniques, analysis and application for land use mapping. The hyperspectral data consists of 242 bands out of which 196 calibrated/useful bands are available for hyperspectral applications. Atmospheric correction applied to the hyperspectral calibrated bands make the data more useful for its further processing/ application. Principal component (PC) analysis applied to the hyperspectral calibrated bands reduced the dimensionality of the data and it is found that 99% of the data is held in first 10 PCs. Feature extraction is one of the important application by using vegetation delineation and normalized difference vegetation index. The machine learning classifiers uses the technique to identify the pixels having significant difference in the spectral signature which is very useful for classification of an image. Supervised machine learning classifier technique has been used for classification of hyperspectral image which resulted in overall efficiency of 86.6703 and Kappa co-efficient of 0.7998.

scholarly journals Früherkennung von Buchdruckerbefall dank Fern erkundung: Was ist schon möglich?

2020 ◽  
Vol 171 (1) ◽  
pp. 36-43 ◽  
Author(s):  
Luzia Götz ◽  
Achilleas Psomas ◽  
Harald Bugmann
Keyword(s):  
Remote Sensing ◽  
Early Detection ◽  
Bark Beetle ◽  
Vegetation Indices ◽  
Remote Sensing Data ◽  
Cost Effective ◽  
Hyperspectral Data ◽  
Time Saving ◽  
Federal Institute ◽  
Institute Of Technology

Early detection of bark beetle infestations by remote sensing: what is feasible today? Infestation by the Norway spruce (Picea abies) bark beetle (Ips typographus) in uniform forest stands of the high montane and subalpine stage is a major challenge for management. It is impossible to identify in time all susceptible or already infested spruces in the often steep terrain solely by terrestrial observations and to prevent the proliferation of the beetle. A time-saving, cost-effective and effective method for finding these spruces is necessary and remote sensing techniques appear promising. Therefore, we investigated the potential of hyperspectral remote sensing data for the early detection of stressed or infested spruces using a case study in the experimental forest of the Swiss Federal Institute of Technology Zurich (ETHZ) in Sedrun. The approach that we developed is based on a combination of field surveys, hyperspectral data, vegetation indices calculated from these and their classification into the three classes “dead”, “stressed” and “healthy” using Random Forests, a machine-learning approach. We demonstrate that stressed spruces can be identified with this approach, but it is not yet ready for operational use. In particular, a slope-specific calibration of the method is necessary, which makes practical application impossible.

scholarly journals Improving the Reliability of Mixture Tuned Matched Filtering Remote Sensing Classification Results Using Supervised Learning Algorithms and Cross-Validation

2018 ◽  
Vol 10 (11) ◽  
pp. 1675 ◽  
Author(s):  
Devin Routh ◽  
Lindsi Seegmiller ◽  
Charlie Bettigole ◽  
Catherine Kuhn ◽  
Chadwick D. Oliver ◽  
...  
Keyword(s):  
Supervised Learning ◽  
Cross Validation ◽  
Hyperspectral Image ◽  
Learning Algorithm ◽  
Learning Algorithms ◽  
Hyperspectral Data ◽  
Matched Filtering ◽  
User Input ◽  
Remote Sensing Classification ◽  
Supervised Learning Algorithms

Mixture tuned matched filtering (MTMF) image classification capitalizes on the increasing spectral and spatial resolutions of available hyperspectral image data to identify the presence, and potentially the abundance, of a given cover type or endmember. Previous studies using MTMF have relied on extensive user input to obtain a reliable classification. In this study, we expand the traditional MTMF classification by using a selection of supervised learning algorithms with rigorous cross-validation. Our approach removes the need for subjective user input to finalize the classification, ultimately enhancing replicability and reliability of the results. We illustrate this approach with an MTMF classification case study focused on leafy spurge (Euphorbia esula), an invasive forb in Western North America, using free 30-m hyperspectral data from the National Aeronautics and Space Administration’s (NASA) Hyperion sensor. Our protocol shows for our data, a potential overall accuracy inflation between 18.4% and 30.8% without cross-validation and according to the supervised learning algorithm used. We propose this new protocol as a final step for the MTMF classification algorithm and suggest future researchers report a greater suite of accuracy statistics to affirm their classifications’ underlying efficacies.

scholarly journals Early Detection of Type-2 Diabetes Using Federated Learning

2020 ◽  
pp. 257-267
Author(s):  
M. Lincy ◽  
A. Meena Kowshalya
Keyword(s):  
Machine Learning ◽  
Type 2 Diabetes ◽  
Early Detection ◽  
Data Privacy ◽  
Learning Algorithm ◽  
Learning Model ◽  
Learning Approach ◽  
Distributed Data ◽  
Privacy And Security

Data privacy and security are incredibly important in the healthcare industry. Federated learning is a new way of training a machine learning algorithm using distributed data which is not hosted in a centralized server. Numerous centralized machine learning models exists in literature but none offers privacy to users’ data. This paper proposes a federated learning approach for early detection of Type-2 Diabetes among patients. A simple federated architecture is exploited for early detection of Type-2 diabetes. We compare the proposed federated learning model against our centralised approach. Experimental results prove that the federated learning model ensures significant privacy over centralised learning model whereas compromising accuracy for a subtle extend.

Using variations in High Arctic vegetation spectral properties to predict various types of plant, soil, and environmental variables.

2021 ◽  
Author(s):  
Sandra Yaacoub
Keyword(s):  
Remote Sensing ◽  
Learning Algorithm ◽  
Vegetation Indices ◽  
Net Ecosystem Exchange ◽  
Environmental Parameters ◽  
High Arctic ◽  
Hyperspectral Data ◽  
Nutrient Concentrations ◽  
Polar Regions ◽  
Foliar Nitrogen

In comparison to other regions, the High Arctic is experiencing accelerated rates of warming (Meredith et al., 2019). Hyperspectral remote sensing may provide a way to monitor changes in productivity without having to make detailed ground-based measurements. During the 2017 field season researchers on Melville Island, Nunavut, collected in-situ hyperspectral data, plant nutrient concentrations, carbon dioxide gas exchange measurements, and various environmental parameters in a wet-sedge tundra environment. These data were processed with the overall objective of determining if spectral information may be used to quantify changes in productivity across the High Arctic. Using a random forest machine learning algorithm, wavelengths from the hyperspectral data were identified for use in nine vegetation indices (VIs) based on relationships to foliar nitrogen concentrations. Using linear regressions, these VIs were compared to the environmental parameters. Although none correlated significantly to foliar nitrogen, three VIs showed p-values < 0.05 (alpha = 0.05) consistently for the following variables: soil nitrate and ammonia concentrations, net ecosystem exchange (NEE), and gross primary productivity (GPP) values. This shows promise for the use of remote sensing techniques to aid in monitoring the High Arctic. Additional research within this field would help pave way towards increased certainty on the kinds of responses that are in store for these landscapes if warming is to continue at an accelerated rate. This may bring increased monitoring frequency and scale of environmental assessment across the High Arctic, granting communities influenced by warming additional tools to aid in safer regional navigation and improved emergency response preparedness.      References Meredith, M., Sommerkorn, M., Cassotta, S., Derksen, C., Ekaykin, A., Hollowed, A., Kofinas, G., Mackintosh, A., Melbourne-Thomas, J., Muelbert, M. M. C. M. M. C., Ottersen, G., Pritchard, H., & Schuur, E. A. G. E. A. G. (2019). Polar Regions. In H.-O. Pörtner, D. C. Roberts, V. Masson-Delmotte, P. Zhai, M. Tignor, E. Poloczanska, K. Mintenbeck, A. Alegría, M. Nicolai, A. Okem, J. Petzold, B. Rama, & N. M. Weyer (Eds.), IPCC Special Report on the Ocean and Cryosphere in a Changing Climate (pp. 203–320). https://www.ipcc.ch/srocc/chapter/chapter-3-2/

Semi-Supervised Classification for Hyperspectral Image Based on Tri-Training

2014 ◽  
Vol 687-691 ◽  
pp. 3644-3647 ◽  
Author(s):  
Li Guo Wang ◽  
Yue Shuang Yang ◽  
Ting Ting Lu
Keyword(s):  
Supervised Classification ◽  
Hyperspectral Image ◽  
Learning Algorithm ◽  
Hyperspectral Data ◽  
Data Sets ◽  
Hyperspectral Image Classification ◽  
Training Set ◽  
De Algorithm ◽  
Training Samples ◽  
Limited Training Samples

Hyperspectral image classification is difficult due to the high dimensional features but limited training samples. Tri-training learning is a widely used semi-supervised classification method that addresses the problem of lacking of labeled examples. In this paper, a novel semi-supervised learning algorithm based on tri-training method is proposed. The proposed algorithm combines margin sampling (MS) technique and differential evolution (DE) algorithm to select the most informative samples and perturb them randomly. Then the samples we obtained, which can fulfill the labeled data distribution and introduce diversity to multiple classifiers, are added to training set to train base classifiers for tri-training. The proposed algorithm is experimentally validated using real hyperspectral data sets, indicating that the combination of MS and DE can significantly reduce the need of labeled samples while achieving high accuracy compared with state-of-the-art algorithms.

Sign in / Sign up

Export Citation Format

Share Document