Hyperspectral Image Classification with Capsule Network Using Limited Training Samples

Deep learning techniques have boosted the performance of hyperspectral image (HSI) classification. In particular, convolutional neural networks (CNNs) have shown superior performance to that of the conventional machine learning algorithms. Recently, a novel type of neural networks called capsule networks (CapsNets) was presented to improve the most advanced CNNs. In this paper, we present a modified two-layer CapsNet with limited training samples for HSI classification, which is inspired by the comparability and simplicity of the shallower deep learning models. The presented CapsNet is trained using two real HSI datasets, i.e., the PaviaU (PU) and SalinasA datasets, representing complex and simple datasets, respectively, and which are used to investigate the robustness or representation of every model or classifier. In addition, a comparable paradigm of network architecture design has been proposed for the comparison of CNN and CapsNet. Experiments demonstrate that CapsNet shows better accuracy and convergence behavior for the complex data than the state-of-the-art CNN. For CapsNet using the PU dataset, the Kappa coefficient, overall accuracy, and average accuracy are 0.9456, 95.90%, and 96.27%, respectively, compared to the corresponding values yielded by CNN of 0.9345, 95.11%, and 95.63%. Moreover, we observed that CapsNet has much higher confidence for the predicted probabilities. Subsequently, this finding was analyzed and discussed with probability maps and uncertainty analysis. In terms of the existing literature, CapsNet provides promising results and explicit merits in comparison with CNN and two baseline classifiers, i.e., random forests (RFs) and support vector machines (SVMs).

Download Full-text

DeepVF: a deep learning-based hybrid framework for identifying virulence factors using the stacking strategy

Briefings in Bioinformatics ◽

10.1093/bib/bbaa125 ◽

2020 ◽

Cited By ~ 2

Author(s):

Ruopeng Xie ◽

Jiahui Li ◽

Jiawei Wang ◽

Wei Dai ◽

André Leier ◽

...

Keyword(s):

Neural Networks ◽

Deep Learning ◽

Virulence Factors ◽

Bacterial Genome ◽

Machine Learning Algorithms ◽

Gradient Boosting ◽

Support Vector ◽

Wide Range ◽

Extreme Gradient Boosting ◽

Hybrid Framework

Abstract Virulence factors (VFs) enable pathogens to infect their hosts. A wealth of individual, disease-focused studies has identified a wide variety of VFs, and the growing mass of bacterial genome sequence data provides an opportunity for computational methods aimed at predicting VFs. Despite their attractive advantages and performance improvements, the existing methods have some limitations and drawbacks. Firstly, as the characteristics and mechanisms of VFs are continually evolving with the emergence of antibiotic resistance, it is more and more difficult to identify novel VFs using existing tools that were previously developed based on the outdated data sets; secondly, few systematic feature engineering efforts have been made to examine the utility of different types of features for model performances, as the majority of tools only focused on extracting very few types of features. By addressing the aforementioned issues, the accuracy of VF predictors can likely be significantly improved. This, in turn, would be particularly useful in the context of genome wide predictions of VFs. In this work, we present a deep learning (DL)-based hybrid framework (termed DeepVF) that is utilizing the stacking strategy to achieve more accurate identification of VFs. Using an enlarged, up-to-date dataset, DeepVF comprehensively explores a wide range of heterogeneous features with popular machine learning algorithms. Specifically, four classical algorithms, including random forest, support vector machines, extreme gradient boosting and multilayer perceptron, and three DL algorithms, including convolutional neural networks, long short-term memory networks and deep neural networks are employed to train 62 baseline models using these features. In order to integrate their individual strengths, DeepVF effectively combines these baseline models to construct the final meta model using the stacking strategy. Extensive benchmarking experiments demonstrate the effectiveness of DeepVF: it achieves a more accurate and stable performance compared with baseline models on the benchmark dataset and clearly outperforms state-of-the-art VF predictors on the independent test. Using the proposed hybrid ensemble model, a user-friendly online predictor of DeepVF (http://deepvf.erc.monash.edu/) is implemented. Furthermore, its utility, from the user’s viewpoint, is compared with that of existing toolkits. We believe that DeepVF will be exploited as a useful tool for screening and identifying potential VFs from protein-coding gene sequences in bacterial genomes.

Download Full-text

Blood Stain Classification with Hyperspectral Imaging and Deep Neural Networks

Sensors ◽

10.3390/s20226666 ◽

2020 ◽

Vol 20 (22) ◽

pp. 6666

Author(s):

Kamil Książek ◽

Michał Romaszewski ◽

Przemysław Głomb ◽

Bartosz Grabowski ◽

Michał Cholewa

Keyword(s):

Neural Network ◽

Neural Networks ◽

Deep Learning ◽

Hyperspectral Imaging ◽

Network Architecture ◽

Confusion Matrix ◽

Hyperspectral Data ◽

Matrix Analysis ◽

Support Vector ◽

Test Set

In recent years, growing interest in deep learning neural networks has raised a question on how they can be used for effective processing of high-dimensional datasets produced by hyperspectral imaging (HSI). HSI, traditionally viewed as being within the scope of remote sensing, is used in non-invasive substance classification. One of the areas of potential application is forensic science, where substance classification on the scenes is important. An example problem from that area—blood stain classification—is a case study for the evaluation of methods that process hyperspectral data. To investigate the deep learning classification performance for this problem we have performed experiments on a dataset which has not been previously tested using this kind of model. This dataset consists of several images with blood and blood-like substances like ketchup, tomato concentrate, artificial blood, etc. To test both the classic approach to hyperspectral classification and a more realistic application-oriented scenario, we have prepared two different sets of experiments. In the first one, Hyperspectral Transductive Classification (HTC), both a training and a test set come from the same image. In the second one, Hyperspectral Inductive Classification (HIC), a test set is derived from a different image, which is more challenging for classifiers but more useful from the point of view of forensic investigators. We conducted the study using several architectures like 1D, 2D and 3D convolutional neural networks (CNN), a recurrent neural network (RNN) and a multilayer perceptron (MLP). The performance of the models was compared with baseline results of Support Vector Machine (SVM). We have also presented a model evaluation method based on t-SNE and confusion matrix analysis that allows us to detect and eliminate some cases of model undertraining. Our results show that in the transductive case, all models, including the MLP and the SVM, have comparative performance, with no clear advantage of deep learning models. The Overall Accuracy range across all models is 98–100% for the easier image set, and 74–94% for the more difficult one. However, in a more challenging inductive case, selected deep learning architectures offer a significant advantage; their best Overall Accuracy is in the range of 57–71%, improving the baseline set by the non-deep models by up to 9 percentage points. We have presented a detailed analysis of results and a discussion, including a summary of conclusions for each tested architecture. An analysis of per-class errors shows that the score for each class is highly model-dependent. Considering this and the fact that the best performing models come from two different architecture families (3D CNN and RNN), our results suggest that tailoring the deep neural network architecture to hyperspectral data is still an open problem.

Download Full-text

Classification of Hyperspectral Image Based on Double-Branch Dual-Attention Mechanism Network

Remote Sensing ◽

10.3390/rs12030582 ◽

2020 ◽

Vol 12 (3) ◽

pp. 582 ◽

Cited By ~ 4

Author(s):

Rui Li ◽

Shunyi Zheng ◽

Chenxi Duan ◽

Yang Yang ◽

Xiqi Wang

Keyword(s):

Deep Learning ◽

Hyperspectral Image ◽

State Of The Art ◽

Attention Mechanism ◽

Superior Performance ◽

Feature Maps ◽

Spatial Features ◽

Training Samples ◽

Series Of Experiments

In recent years, researchers have paid increasing attention on hyperspectral image (HSI) classification using deep learning methods. To improve the accuracy and reduce the training samples, we propose a double-branch dual-attention mechanism network (DBDA) for HSI classification in this paper. Two branches are designed in DBDA to capture plenty of spectral and spatial features contained in HSI. Furthermore, a channel attention block and a spatial attention block are applied to these two branches respectively, which enables DBDA to refine and optimize the extracted feature maps. A series of experiments on four hyperspectral datasets show that the proposed framework has superior performance to the state-of-the-art algorithm, especially when the training samples are signally lacking.

Download Full-text

Investigating Deep Feedforward Neural Networks for Classification of Transposon-Derived piRNAs

10.1101/2020.04.08.032755 ◽

2020 ◽

Author(s):

Alisson Hayasi da Costa ◽

Renato Augusto C. dos Santos ◽

Ricardo Cerri

Keyword(s):

Neural Networks ◽

Deep Learning ◽

State Of The Art ◽

Feedforward Neural Networks ◽

The State ◽

Machine Learning Algorithms ◽

Support Vector ◽

Advantages And Disadvantages ◽

Large Application

AbstractPIWI-Interacting RNAs (piRNAs) form an important class of non-coding RNAs that play a key role in the genome integrity through the silencing of transposable elements. However, despite their importance and the large application of deep learning in computational biology for classification tasks, there are few studies of deep learning and neural networks for piRNAs prediction. Therefore, this paper presents an investigation on deep feedforward networks models for classification of transposon-derived piRNAs. We analyze and compare the results of the neural networks in different hyperparameters choices, such as number of layers, activation functions and optimizers, clarifying the advantages and disadvantages of each configuration. From this analysis, we propose a model for human piRNAs classification and compare our method with the state-of-the-art deep neural network for piRNA prediction in the literature and also traditional machine learning algorithms, such as Support Vector Machines and Random Forests, showing that our model has achieved a great performance with an F-measure value of 0.872, outperforming the state-of-the-art method in the literature.

Download Full-text

AN APPROACH TO ACCELERATE THE TRAINING OF CONVOLUTIONAL NEURAL NETWORKS BY TUNING THE HYPERPARAMETERS OF LEARNING

Computer Systems and Information Technologies ◽

10.31891/csit-2020-2-5 ◽

2020 ◽

Vol 2 (2) ◽

pp. 32-37

Author(s):

P. RADIUK ◽

Keyword(s):

Neural Networks ◽

Deep Learning ◽

Convolutional Neural Networks ◽

Video Processing ◽

Network Architecture ◽

Random Search ◽

Machine Learning Algorithms ◽

Language Recognition ◽

Data Set ◽

Training Time

Over the last decade, a set of machine learning algorithms called deep learning has led to significant improvements in computer vision, natural language recognition and processing. This has led to the widespread use of a variety of commercial, learning-based products in various fields of human activity. Despite this success, the use of deep neural networks remains a black box. Today, the process of setting hyperparameters and designing a network architecture requires experience and a lot of trial and error and is based more on chance than on a scientific approach. At the same time, the task of simplifying deep learning is extremely urgent. To date, no simple ways have been invented to establish the optimal values of learning hyperparameters, namely learning speed, sample size, data set, learning pulse, and weight loss. Grid search and random search of hyperparameter space are extremely resource intensive. The choice of hyperparameters is critical for the training time and the final result. In addition, experts often choose one of the standard architectures (for example, ResNets and ready-made sets of hyperparameters. However, such kits are usually suboptimal for specific practical tasks. The presented work offers an approach to finding the optimal set of hyperparameters of learning ZNM. An integrated approach to all hyperparameters is valuable because there is an interdependence between them. The aim of the work is to develop an approach for setting a set of hyperparameters, which will reduce the time spent during the design of ZNM and ensure the efficiency of its work. In recent decades, the introduction of deep learning methods, in particular convolutional neural networks (CNNs), has led to impressive success in image and video processing. However, the training of CNN has been commonly mostly based on the employment of quasi-optimal hyperparameters. Such an approach usually requires huge computational and time costs to train the network and does not guarantee a satisfactory result. However, hyperparameters play a crucial role in the effectiveness of CNN, as diverse hyperparameters lead to models with significantly different characteristics. Poorly selected hyperparameters generally lead to low model performance. The issue of choosing optimal hyperparameters for CNN has not been resolved yet. The presented work proposes several practical approaches to setting hyperparameters, which allows reducing training time and increasing the accuracy of the model. The article considers the function of training validation loss during underfitting and overfitting. There are guidelines in the end to reach the optimization point. The paper also considers the regulation of learning rate and momentum to accelerate network training. All experiments are based on the widespread CIFAR-10 and CIFAR-100 datasets.

Download Full-text

Wheat Lodging Detection from UAS Imagery Using Machine Learning Algorithms

Remote Sensing ◽

10.3390/rs12111838 ◽

2020 ◽

Vol 12 (11) ◽

pp. 1838 ◽

Cited By ~ 8

Author(s):

Zhao Zhang ◽

Paulo Flores ◽

C. Igathinathane ◽

Dayakar L. Naik ◽

Ravi Kiran ◽

...

Keyword(s):

Neural Network ◽

Machine Learning ◽

Deep Learning ◽

Standard Deviation ◽

Learning Algorithm ◽

Learning Algorithms ◽

Machine Learning Algorithms ◽

Superior Performance ◽

Support Vector ◽

Unmanned Aerial Systems

The current mainstream approach of using manual measurements and visual inspections for crop lodging detection is inefficient, time-consuming, and subjective. An innovative method for wheat lodging detection that can overcome or alleviate these shortcomings would be welcomed. This study proposed a systematic approach for wheat lodging detection in research plots (372 experimental plots), which consisted of using unmanned aerial systems (UAS) for aerial imagery acquisition, manual field evaluation, and machine learning algorithms to detect the occurrence or not of lodging. UAS imagery was collected on three different dates (23 and 30 July 2019, and 8 August 2019) after lodging occurred. Traditional machine learning and deep learning were evaluated and compared in this study in terms of classification accuracy and standard deviation. For traditional machine learning, five types of features (i.e. gray level co-occurrence matrix, local binary pattern, Gabor, intensity, and Hu-moment) were extracted and fed into three traditional machine learning algorithms (i.e., random forest (RF), neural network, and support vector machine) for detecting lodged plots. For the datasets on each imagery collection date, the accuracies of the three algorithms were not significantly different from each other. For any of the three algorithms, accuracies on the first and last date datasets had the lowest and highest values, respectively. Incorporating standard deviation as a measurement of performance robustness, RF was determined as the most satisfactory. Regarding deep learning, three different convolutional neural networks (simple convolutional neural network, VGG-16, and GoogLeNet) were tested. For any of the single date datasets, GoogLeNet consistently had superior performance over the other two methods. Further comparisons between RF and GoogLeNet demonstrated that the detection accuracies of the two methods were not significantly different from each other (p > 0.05); hence, the choice of any of the two would not affect the final detection accuracies. However, considering the fact that the average accuracy of GoogLeNet (93%) was larger than RF (91%), it was recommended to use GoogLeNet for wheat lodging detection. This research demonstrated that UAS RGB imagery, coupled with the GoogLeNet machine learning algorithm, can be a novel, reliable, objective, simple, low-cost, and effective (accuracy > 90%) tool for wheat lodging detection.

Download Full-text

A study of deep learning approaches for medication and adverse drug event extraction from clinical text

Journal of the American Medical Informatics Association ◽

10.1093/jamia/ocz063 ◽

2019 ◽

Vol 27 (1) ◽

pp. 13-21 ◽

Cited By ~ 11

Author(s):

Qiang Wei ◽

Zongcheng Ji ◽

Zhiheng Li ◽

Jingcheng Du ◽

Jingqi Wang ◽

...

Keyword(s):

Machine Learning ◽

Deep Learning ◽

Learning Algorithms ◽

Joint Model ◽

Machine Learning Algorithms ◽

Entity Recognition ◽

Superior Performance ◽

Drug Event ◽

Support Vector ◽

Learning Approaches

AbstractObjectiveThis article presents our approaches to extraction of medications and associated adverse drug events (ADEs) from clinical documents, which is the second track of the 2018 National NLP Clinical Challenges (n2c2) shared task.Materials and MethodsThe clinical corpus used in this study was from the MIMIC-III database and the organizers annotated 303 documents for training and 202 for testing. Our system consists of 2 components: a named entity recognition (NER) and a relation classification (RC) component. For each component, we implemented deep learning-based approaches (eg, BI-LSTM-CRF) and compared them with traditional machine learning approaches, namely, conditional random fields for NER and support vector machines for RC, respectively. In addition, we developed a deep learning-based joint model that recognizes ADEs and their relations to medications in 1 step using a sequence labeling approach. To further improve the performance, we also investigated different ensemble approaches to generating optimal performance by combining outputs from multiple approaches.ResultsOur best-performing systems achieved F1 scores of 93.45% for NER, 96.30% for RC, and 89.05% for end-to-end evaluation, which ranked #2, #1, and #1 among all participants, respectively. Additional evaluations show that the deep learning-based approaches did outperform traditional machine learning algorithms in both NER and RC. The joint model that simultaneously recognizes ADEs and their relations to medications also achieved the best performance on RC, indicating its promise for relation extraction.ConclusionIn this study, we developed deep learning approaches for extracting medications and their attributes such as ADEs, and demonstrated its superior performance compared with traditional machine learning algorithms, indicating its uses in broader NER and RC tasks in the medical domain.

Download Full-text

A deep neural network approach to predicting clinical outcomes of neuroblastoma patients

10.1101/750364 ◽

2019 ◽

Author(s):

Léon-Charles Tranchevent ◽

Francisco Azuaje ◽

Jagath C. Rajapakse

Keyword(s):

Neural Network ◽

Neural Networks ◽

Deep Learning ◽

Clinical Outcomes ◽

Deep Neural Network ◽

Superior Performance ◽

Support Vector ◽

Disease Etiology ◽

Topological Features ◽

Wide Range

AbstractThe availability of high-throughput omics datasets from large patient cohorts has allowed the development of methods that aim at predicting patient clinical outcomes, such as survival and disease recurrence. Such methods are also important to better understand the biological mechanisms underlying disease etiology and development, as well as treatment responses. Recently, different predictive models, relying on distinct algorithms (including Support Vector Machines and Random Forests) have been investigated. In this context, deep learning strategies are of special interest due to their demonstrated superior performance over a wide range of problems and datasets. One of the main challenges of such strategies is the “small n large p” problem. Indeed, omics datasets typically consist of small numbers of samples and large numbers of features relative to typical deep learning datasets. Neural networks usually tackle this problem through feature selection or by including additional constraints during the learning process.We propose to tackle this problem with a novel strategy that relies on a graph-based method for feature extraction, coupled with a deep neural network for clinical outcome prediction. The omics data are first represented as graphs whose nodes represent patients, and edges represent correlations between the patients’ omics profiles. Topological features, such as centralities, are then extracted from these graphs for every node. Lastly, these features are used as input to train and test various classifiers.We apply this strategy to four neuroblastoma datasets and observe that models based on neural networks are more accurate than state of the art models (DNN: 85%-87%, SVM/RF: 75%-82%). We explore how different parameters and configurations are selected in order to overcome the effects of the small data problem as well as the curse of dimensionality. Our results indicate that the deep neural networks capture complex features in the data that help predicting patient clinical outcomes.

Download Full-text

Generalising Better: Applying Deep Learning to Integrate Deleteriousness Prediction Scores for Whole-Exome SNV Studies

10.1101/126532 ◽

2017 ◽

Author(s):

Ilia Korvigo ◽

Andrey Afanasyev ◽

Nikolay Romashchenko ◽

Mihail Skoblov

Keyword(s):

Neural Networks ◽

Deep Learning ◽

Hardware Acceleration ◽

Scoring Systems ◽

Classification Performance ◽

Machine Learning Algorithms ◽

Support Vector ◽

Whole Exome ◽

Generalisation Ability

AbstractMany automatic classifiers were introduced to aid inference of phenotypical effects of uncategorised nsSNVs (nonsynonymous Single Nucleotide Variations) in theoretical and medical applications. Lately, several meta-estimators have been proposed that combine different predictors, such as PolyPhen and SIFT, to integrate more information in a single score. Although many advances have been made in feature design and machine learning algorithms used, the shortage of high-quality reference data along with the bias towards intensively studied in vitro models call for improved generalisation ability in order to further increase classification accuracy and handle records with insufficient data. Since a meta-estimator basically combines different scoring systems with highly complicated nonlinear relationships, we investigated how deep learning (supervised and unsupervised), which is particularly efficient at discovering hierarchies of features, can improve classification performance. While it is believed that one should only use deep learning for high-dimensional input spaces and other models (logistic regression, support vector machines, Bayesian classifiers, etc) for simpler inputs, we still believe that the ability of neural networks to discover intricate structure in highly heterogenous datasets can aid a meta-estimator. We compare the performance with various popular predictors, many of which are recommended by the American College of Medical Genetics and Genomics (ACMG), as well as available deep learning-based predictors. Thanks to hardware acceleration we were able to use a computationally expensive genetic algorithm to stochastically optimise hyper-parameters over many generations. Overfitting was hindered by noise injection and dropout, limiting coadaptation of hidden units. Although we stress that this work was not conceived as a tool comparison, but rather an exploration of the possibilities of deep learning application in ensemble scores, our results show that even relatively simple modern neural networks can significantly improve both prediction accuracy and coverage. We provide open-access to our finest model at http://score.generesearch.ru.

Download Full-text

A Very Large-Scale Bioactivity Comparison of Deep Learning and Multiple Machine Learning Algorithms for Drug Discovery

10.26434/chemrxiv.12781241 ◽

2020 ◽

Author(s):

Thomas R. Lane ◽

Daniel H. Foil ◽

Eni Minerali ◽

Fabio Urbina ◽

Kimberley M. Zorn ◽

...

Keyword(s):

Machine Learning ◽

Neural Networks ◽

Deep Learning ◽

Drug Discovery ◽

Deep Neural Networks ◽

Learning Algorithms ◽

Machine Learning Algorithms ◽

Support Vector ◽

Learning Methods ◽

Machine Learning Methods

Machine learning methods are attracting considerable attention from the pharmaceutical industry for use in drug discovery and applications beyond. In recent studies we have applied multiple machine learning algorithms, modeling metrics and in some cases compared molecular descriptors to build models for individual targets or properties on a relatively small scale. Several research groups have used large numbers of datasets from public databases such as ChEMBL in order to evaluate machine learning methods of interest to them. The largest of these types of studies used on the order of 1400 datasets. We have now extracted well over 5000 datasets from CHEMBL for use with the ECFP6 fingerprint and comparison of our proprietary software Assay CentralTM with random forest, k-Nearest Neighbors, support vector classification, naïve Bayesian, AdaBoosted decision trees, and deep neural networks (3 levels). Model performance <a>was</a> assessed using an array of five-fold cross-validation metrics including area-under-the-curve, F1 score, Cohen’s kappa and Matthews correlation coefficient. <a>Based on ranked normalized scores for the metrics or datasets all methods appeared comparable while the distance from the top indicated Assay CentralTM and support vector classification were comparable. </a>Unlike prior studies which have placed considerable emphasis on deep neural networks (deep learning), no advantage was seen in this case where minimal tuning was performed of any of the methods. If anything, Assay CentralTM may have been at a slight advantage as the activity cutoff for each of the over 5000 datasets representing over 570,000 unique compounds was based on Assay CentralTMperformance, but support vector classification seems to be a strong competitor. We also apply Assay CentralTM to prospective predictions for PXR and hERG to further validate these models. This work currently appears to be the largest comparison of machine learning algorithms to date. Future studies will likely evaluate additional databases, descriptors and algorithms, as well as further refining methods for evaluating and comparing models.

Download Full-text