Scattering Transform Framework for Unmixing of Hyperspectral Data

The scattering transform, which applies multiple convolutions using known filters targeting different scales of time or frequency, has a strong similarity to the structure of convolution neural networks (CNNs), without requiring training to learn the convolution filters, and has been used for hyperspectral image classification in recent research. This paper investigates the application of the scattering transform framework to hyperspectral unmixing (STFHU). While state-of-the-art research on unmixing hyperspectral data utilizing scattering transforms is limited, the proposed end-to-end method applies pixel-based scattering transforms and preliminary three-dimensional (3D) scattering transforms to hyperspectral images in the remote sensing scenario to extract feature vectors, which are then trained by employing the regression model based on the k-nearest neighbor (k-NN) to estimate the abundance of maps of endmembers. Experiments compare performances of the proposed algorithm with a series of existing methods in quantitative terms based on both synthetic data and real-world hyperspectral datasets. Results indicate that the proposed approach is more robust to additive noise, which is suppressed by utilizing the rich information in both high-frequency and low-frequency components represented by the scattering transform. Furthermore, the proposed method achieves higher accuracy for unmixing using the same amount of training data with all comparative approaches, while achieving equivalent performance to the best performing CNN method but using much less training data.

Download Full-text

An Incremental Isomap Method for Hyperspectral Dimensionality Reduction and Classification

Photogrammetric Engineering & Remote Sensing ◽

10.14358/pers.87.7.445 ◽

2021 ◽

Vol 87 (6) ◽

pp. 445-455

Author(s):

Yi Ma ◽

Zezhong Zheng ◽

Yutang Ma ◽

Mingcang Zhu ◽

Ran Huang ◽

...

Keyword(s):

Manifold Learning ◽

Nearest Neighbor ◽

Hyperspectral Image ◽

Hyperspectral Data ◽

Training Data ◽

Support Vector ◽

Data Sets ◽

K Nearest Neighbor ◽

Data Set ◽

Data Points

Many manifold learning algorithms conduct an eigen vector analysis on a data-similarity matrix with a size of N×N, where N is the number of data points. Thus, the memory complexity of the analysis is no less than O(N2). We pres- ent in this article an incremental manifold learning approach to handle large hyperspectral data sets for land use identification. In our method, the number of dimensions for the high-dimensional hyperspectral-image data set is obtained with the training data set. A local curvature varia- tion algorithm is utilized to sample a subset of data points as landmarks. Then a manifold skeleton is identified based on the landmarks. Our method is validated on three AVIRIS hyperspectral data sets, outperforming the comparison algorithms with a k–nearest-neighbor classifier and achieving the second best performance with support vector machine.

Download Full-text

AffinityNet: Semi-Supervised Few-Shot Learning for Disease Type Prediction

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v33i01.33011069 ◽

2019 ◽

Vol 33 ◽

pp. 1069-1076 ◽

Cited By ~ 2

Author(s):

Tianle Ma ◽

Aidong Zhang

Keyword(s):

Neural Network ◽

Deep Learning ◽

Network Model ◽

Nearest Neighbor ◽

Synthetic Data ◽

Genomic Data ◽

Training Data ◽

Great Success ◽

K Nearest Neighbor ◽

Neural Network Models

While deep learning has achieved great success in computer vision and many other fields, currently it does not work very well on patient genomic data with the “big p, small N” problem (i.e., a relatively small number of samples with highdimensional features). In order to make deep learning work with a small amount of training data, we have to design new models that facilitate few-shot learning. Here we present the Affinity Network Model (AffinityNet), a data efficient deep learning model that can learn from a limited number of training examples and generalize well. The backbone of the AffinityNet model consists of stacked k-Nearest-Neighbor (kNN) attention pooling layers. The kNN attention pooling layer is a generalization of the Graph Attention Model (GAM), and can be applied to not only graphs but also any set of objects regardless of whether a graph is given or not. As a new deep learning module, kNN attention pooling layers can be plugged into any neural network model just like convolutional layers. As a simple special case of kNN attention pooling layer, feature attention layer can directly select important features that are useful for classification tasks. Experiments on both synthetic data and cancer genomic data from TCGA projects show that our AffinityNet model has better generalization power than conventional neural network models with little training data.

Download Full-text

Detecting Bacterial Biofilms Using Fluorescence Hyperspectral Imaging and Various Discriminant Analyses

Sensors ◽

10.3390/s21062213 ◽

2021 ◽

Vol 21 (6) ◽

pp. 2213

Author(s):

Ahyeong Lee ◽

Saetbyeol Park ◽

Jinyoung Yoo ◽

Jungsook Kang ◽

Jongguk Lim ◽

...

Keyword(s):

Discriminant Analysis ◽

Hyperspectral Imaging ◽

Food Processing ◽

Nearest Neighbor ◽

Hyperspectral Image ◽

Uv Light ◽

Hyperspectral Images ◽

K Nearest Neighbor ◽

E Coli ◽

Discriminant Analyses

Biofilms formed on the surface of agro-food processing facilities can cause food poisoning by providing an environment in which bacteria can be cultured. Therefore, hygiene management through initial detection is important. This study aimed to assess the feasibility of detecting Escherichia coli (E. coli) and Salmonella typhimurium (S. typhimurium) on the surface of food processing facilities by using fluorescence hyperspectral imaging. E. coli and S. typhimurium were cultured on high-density polyethylene and stainless steel coupons, which are the main materials used in food processing facilities. We obtained fluorescence hyperspectral images for the range of 420–730 nm by emitting UV light from a 365 nm UV light source. The images were used to perform discriminant analyses (linear discriminant analysis, k-nearest neighbor analysis, and partial-least squares discriminant analysis) to identify and classify coupons on which bacteria could be cultured. The discriminant performances of specificity and sensitivity for E. coli (1–4 log CFU·cm−2) and S. typhimurium (1–6 log CFU·cm−2) were over 90% for most machine learning models used, and the highest performances were generally obtained from the k-nearest neighbor (k-NN) model. The application of the learning model to the hyperspectral image confirmed that the biofilm detection was well performed. This result indicates the possibility of rapidly inspecting biofilms using fluorescence hyperspectral images.

Download Full-text

k-Nearest Neighbor Learning with Graph Neural Networks

Mathematics ◽

10.3390/math9080830 ◽

2021 ◽

Vol 9 (8) ◽

pp. 830

Author(s):

Seokho Kang

Keyword(s):

Neural Network ◽

Nearest Neighbor ◽

Learning Algorithm ◽

Weighting Function ◽

High Sensitivity ◽

Training Data ◽

K Nearest Neighbor ◽

Main Challenge ◽

Benchmark Datasets ◽

Graph Neural Networks

k-nearest neighbor (kNN) is a widely used learning algorithm for supervised learning tasks. In practice, the main challenge when using kNN is its high sensitivity to its hyperparameter setting, including the number of nearest neighbors k, the distance function, and the weighting function. To improve the robustness to hyperparameters, this study presents a novel kNN learning method based on a graph neural network, named kNNGNN. Given training data, the method learns a task-specific kNN rule in an end-to-end fashion by means of a graph neural network that takes the kNN graph of an instance to predict the label of the instance. The distance and weighting functions are implicitly embedded within the graph neural network. For a query instance, the prediction is obtained by performing a kNN search from the training data to create a kNN graph and passing it through the graph neural network. The effectiveness of the proposed method is demonstrated using various benchmark datasets for classification and regression tasks.

Download Full-text

Android Malware Detection using Machine Learning

International Journal of Recent Technology and Engineering - 2 ◽

10.35940/ijrte.b1011.0982s1219 ◽

2020 ◽

Vol 8 (2S12) ◽

pp. 65-70

Keyword(s):

Machine Learning ◽

Nearest Neighbor ◽

Machine Learning Algorithms ◽

Training Data ◽

Machine Learning Techniques ◽

Support Vector ◽

K Nearest Neighbor ◽

User Interest ◽

Android Malware ◽

Android Malware Detection

Machine Learning is empowering many aspects of day-to-day lives from filtering the content on social networks to suggestions of products that we may be looking for. This technology focuses on taking objects as image input to find new observations or show items based on user interest. The major discussion here is the Machine Learning techniques where we use supervised learning where the computer learns by the input data/training data and predict result based on experience. We also discuss the machine learning algorithms: Naïve Bayes Classifier, K-Nearest Neighbor, Random Forest, Decision Tress, Boosted Trees, Support Vector Machine, and use these classifiers on a dataset Malgenome and Drebin which are the Android Malware Dataset. Android is an operating system that is gaining popularity these days and with a rise in demand of these devices the rise in Android Malware. The traditional techniques methods which were used to detect malware was unable to detect unknown applications. We have run this dataset on different machine learning classifiers and have recorded the results. The experiment result provides a comparative analysis that is based on performance, accuracy, and cost.

Download Full-text

Dimensionality Reduction with Unsupervised Feature Selection and Applying Non-Euclidean Norms for Classification Accuracy

Exploring Advances in Interdisciplinary Data Mining and Analytics ◽

10.4018/978-1-61350-474-1.ch006 ◽

2011 ◽

pp. 91-109

Author(s):

Amit Saxena ◽

John Wang

Keyword(s):

Classification Accuracy ◽

Nearest Neighbor ◽

Fitness Function ◽

Synthetic Data ◽

Feature Subset Selection ◽

Second Phase ◽

Data Sets ◽

Feature Subset ◽

K Nearest Neighbor ◽

Two Phase

This paper presents a two-phase scheme to select reduced number of features from a dataset using Genetic Algorithm (GA) and testing the classification accuracy (CA) of the dataset with the reduced feature set. In the first phase of the proposed work, an unsupervised approach to select a subset of features is applied. GA is used to select stochastically reduced number of features with Sammon Error as the fitness function. Different subsets of features are obtained. In the second phase, each of the reduced features set is applied to test the CA of the dataset. The CA of a data set is validated using supervised k-nearest neighbor (k-nn) algorithm. The novelty of the proposed scheme is that each reduced feature set obtained in the first phase is investigated for CA using the k-nn classification with different Minkowski metric i.e. non-Euclidean norms instead of conventional Euclidean norm (L2). Final results are presented in the paper with extensive simulations on seven real and one synthetic, data sets. It is revealed from the proposed investigation that taking different norms produces better CA and hence a scope for better feature subset selection.

Download Full-text

Attention-Based Residual Network with Scattering Transform Features for Hyperspectral Unmixing with Limited Training Samples

Remote Sensing ◽

10.3390/rs12030400 ◽

2020 ◽

Vol 12 (3) ◽

pp. 400 ◽

Cited By ~ 2

Author(s):

Zeng ◽

Ritz ◽

Zhao ◽

Lan

Keyword(s):

Neural Network ◽

Additive Noise ◽

Hyperspectral Data ◽

Training Data ◽

K Nearest Neighbors ◽

Practical Applications ◽

Hyperspectral Unmixing ◽

Scattering Transform ◽

Training Samples ◽

Limited Training Samples

This paper proposes a framework for unmixing of hyperspectral data that is based on utilizing the scattering transform to extract deep features that are then used within a neural network. Previous research has shown that using the scattering transform combined with a traditional K-nearest neighbors classifier (STFHU) is able to achieve more accurate unmixing results compared to a convolutional neural network (CNN) applied directly to the hyperspectral images. This paper further explores hyperspectral unmixing in limited training data scenarios, which are likely to occur in practical applications where the access to large amounts of labeled training data is not possible. Here, it is proposed to combine the scattering transform with the attention-based residual neural network (ResNet). Experimental results on three HSI datasets demonstrate that this approach provides at least 40% higher unmixing accuracy compared to the previous STFHU and CNN algorithms when using limited training data, ranging from 5% to 30%, are available. The use of the scattering transform for deriving features within the ResNet unmixing system also leads more than 25% improvement when unmixing hyperspectral data contaminated by additive noise.

Download Full-text

Business Intelligence using the K-Nearest Neighbor Algorithm to Analyze Customer Behavior in Online Crowdfunding Systems

E3S Web of Conferences ◽

10.1051/e3sconf/202020216005 ◽

2020 ◽

Vol 202 ◽

pp. 16005

Author(s):

Chashif Syadzali ◽

Suryono Suryono ◽

Jatmiko Endro Suseno

Keyword(s):

Business Intelligence ◽

Nearest Neighbor ◽

Customer Behavior ◽

Training Data ◽

Business Strategies ◽

Intelligence Analysis ◽

K Nearest Neighbor ◽

Nearest Neighbor Algorithm ◽

K Nearest Neighbor Algorithm

Customer behavior classification can be useful to assist companies in conducting business intelligence analysis. Data mining techniques can classify customer behavior using the K-Nearest Neighbor algorithm based on the customer's life cycle consisting of prospect, responder, active and former. Data used to classify include age, gender, number of donations, donation retention and number of user visits. The calculation results from 2,114 data in the classification of each customer’s category are namely active by 1.18%, prospect by 8.99%, responder by 4.26% and former by 85.57%. System accuracy using a range of K from K = 1 to K = 20 produces that the highest accuracy is 94.3731% at a value of K = 4. The results of the training data that produce a classification of user behavior can be used as a Business Intelligence analysis that is useful for companies in determining business strategies by knowing the target of optimal market.

Download Full-text

Identification of Leukemia Subtypes from Microscopic Images Using Convolutional Neural Network

Diagnostics ◽

10.3390/diagnostics9030104 ◽

2019 ◽

Vol 9 (3) ◽

pp. 104 ◽

Cited By ~ 11

Author(s):

Ahmed ◽

Yigit ◽

Isik ◽

Alpkocak

Keyword(s):

Machine Learning ◽

Data Augmentation ◽

Nearest Neighbor ◽

Learning Algorithms ◽

Machine Learning Algorithms ◽

Training Data ◽

Support Vector ◽

K Nearest Neighbor ◽

Data Set ◽

Leukemia Data

Leukemia is a fatal cancer and has two main types: Acute and chronic. Each type has two more subtypes: Lymphoid and myeloid. Hence, in total, there are four subtypes of leukemia. This study proposes a new approach for diagnosis of all subtypes of leukemia from microscopic blood cell images using convolutional neural networks (CNN), which requires a large training data set. Therefore, we also investigated the effects of data augmentation for an increasing number of training samples synthetically. We used two publicly available leukemia data sources: ALL-IDB and ASH Image Bank. Next, we applied seven different image transformation techniques as data augmentation. We designed a CNN architecture capable of recognizing all subtypes of leukemia. Besides, we also explored other well-known machine learning algorithms such as naive Bayes, support vector machine, k-nearest neighbor, and decision tree. To evaluate our approach, we set up a set of experiments and used 5-fold cross-validation. The results we obtained from experiments showed that our CNN model performance has 88.25% and 81.74% accuracy, in leukemia versus healthy and multiclass classification of all subtypes, respectively. Finally, we also showed that the CNN model has a better performance than other wellknown machine learning algorithms.

Download Full-text

3D modeling and inversion of VLF and VLF-R electromagnetic data

Geophysics ◽

10.1190/geo2011-0360.1 ◽

2012 ◽

Vol 77 (4) ◽

pp. WB219-WB231 ◽

Cited By ~ 7

Author(s):

P. Kaikkonen ◽

S. P. Sharma ◽

S. Mittal

Keyword(s):

Field Data ◽

Three Dimensional ◽

Synthetic Data ◽

Low Frequency ◽

Reliability And Validity ◽

Physical Parameters ◽

Model Parameters ◽

Data Inversion ◽

Inversion Procedure ◽

Using Data

Three-dimensional linearized nonlinear electromagnetic inversion is developed for revealing the subsurface conductivity structure using isolated very low frequency (VLF) and VLF-resistivity anomalies due to conductors that may be arbitrarily directed towards the measuring profiles and the VLF transmitter. We described the 3D model using a set of variables in terms of geometric and physical parameters. These model parameters were then optimized (parametric inversion) to obtain their best estimates to fit the observations. Two VLF transmitters, i.e., the [Formula: see text], [Formula: see text] (“E”) and the [Formula: see text], [Formula: see text] (“H”) polarizations, respectively, can be considered jointly in inversion. After inverting several noise-free and noisy synthetic data, the results revealed that the estimated model parameters and the functionality of the approach were very good and reliable. The inversion procedure also worked well for the field data. The reliability and validity of the results after the field data inversion have been checked using data from a shear zone associated with uranium mineralization.

Download Full-text