scholarly journals Detection and Classification of Overlapping Cell Nuclei in Cytology Effusion Images Using a Double-Strategy Random Forest

2018 ◽  
Vol 8 (9) ◽  
pp. 1608 ◽  
Author(s):  
Khin Win ◽  
Somsak Choomchuay ◽  
Kazuhiko Hamamoto ◽  
Manasanan Raveesunthornkiat
Keyword(s):  
Feature Extraction ◽  
Random Forest ◽  
Performance Metrics ◽  
Superior Performance ◽  
New Combination ◽  
Final Decision ◽  
Cell Detection ◽  
Cell Nuclei ◽  
Dominant Feature

Due to the close resemblance between overlapping and cancerous nuclei, the misinterpretation of overlapping nuclei can affect the final decision of cancer cell detection. Thus, it is essential to detect overlapping nuclei and distinguish them from single ones for subsequent quantitative analyses. This paper presents a method for the automated detection and classification of overlapping nuclei from single nuclei appearing in cytology pleural effusion (CPE) images. The proposed system is comprised of three steps: nuclei candidate extraction, dominant feature extraction, and classification of single and overlapping nuclei. A maximum entropy thresholding method complemented by image enhancement and post-processing was employed for nuclei candidate extraction. For feature extraction, a new combination of 16 geometrical and 10 textural features was extracted from each nucleus region. A double-strategy random forest was performed as an ensemble feature selector to select the most relevant features, and an ensemble classifier to differentiate between overlapping nuclei and single ones using selected features. The proposed method was evaluated on 4000 nuclei from CPE images using various performance metrics. The results were 96.6% sensitivity, 98.7% specificity, 92.7% precision, 94.6% F1 score, 98.4% accuracy, 97.6% G-mean, and 99% area under curve. The computation time required to run the entire algorithm was just 5.17 s. The experiment results demonstrate that the proposed algorithm yields a superior performance to previous studies and other classifiers. The proposed algorithm can serve as a new supportive tool in the automated diagnosis of cancer cells from cytology images.

Screening and Diagnosis of Autism Spectrum Disorder via Assistive Tools

2022 ◽  
pp. 1-21
Author(s):  
Gurkan Tuna ◽  
Ayşe Tuna
Keyword(s):  
Autism Spectrum Disorder ◽  
Random Forest ◽  
Performance Metrics ◽  
Autism Spectrum ◽  
Repetitive Behaviors ◽  
Spectrum Disorder ◽  
K Nearest Neighbors ◽  
Medical Test ◽  
And Behavior

Autism spectrum disorder (ASD) is a challenging developmental condition that involves restricted and/or repetitive behaviors and persistent challenges in social interaction and speech and nonverbal communication. There is not a standard medical test used to diagnose ASD; therefore, diagnosis is made by looking at the child's developmental history and behavior. In recent years, due to the increase in diagnosed cases of ASD, researchers proposed software-based tools to aid in and expedite the diagnosis. Considering the fact that most of these tools rely on the use of classifiers, in study, random forest, decision tree, k-nearest neighbors, and zero rule algorithms are used as classifiers, and their performances are compared using well-known performance metrics. As proven in the study, random forest algorithm can provide higher accuracy than the others in the classification of ASD and can be integrated into a computer- or humanoid-robot-based system for automated prescreening and diagnosis of ASD in preschool children groups.

Classifying Images of Drought-Affected Area Using Deep Belief Network, kNN, and Random Forest Learning Techniques

2018 ◽  
pp. 102-119 ◽  
Author(s):  
Sanjiban Sekhar Roy ◽  
Pulkit Kulshrestha ◽  
Pijush Samui
Keyword(s):  
Random Forest ◽  
Performance Metrics ◽  
Deep Belief Network ◽  
Machine Learning Algorithms ◽  
Nearest Neighbour ◽  
Data Set ◽  
Belief Network ◽  
Learning Techniques ◽  
Severe Shortage

Drought is a condition of land in which the ground water faces a severe shortage. This condition affects the survival of plants and animals. Drought can impact ecosystem and agricultural productivity, severely. Hence, the economy also gets affected by this situation. This paper proposes Deep Belief Network (DBN) learning technique, which is one of the state of the art machine learning algorithms. This proposed work uses DBN, for classification of drought and non-drought images. Also, k nearest neighbour (kNN) and random forest learning methods have been proposed for the classification of the same drought images. The performance of the Deep Belief Network(DBN) has been compared with k nearest neighbour (kNN) and random forest. The data set has been split into 80:20, 70:30 and 60:40 as train and test. Finally, the effectiveness of the three proposed models have been measured by various performance metrics.

scholarly journals Meta-XGBoost for Hyperspectral Image Classification Using Extended MSER-Guided Morphological Profiles

2020 ◽  
Vol 12 (12) ◽  
pp. 1973
Author(s):  
Alim Samat ◽  
Erzhu Li ◽  
Wei Wang ◽  
Sicong Liu ◽  
Cong Lin ◽  
...  
Keyword(s):  
Random Forest ◽  
Image Classification ◽  
Classification Accuracy ◽  
Regression Tree ◽  
Superior Performance ◽  
Gradient Boosting ◽  
Support Vector ◽  
Adaptive Boosting ◽  
Extreme Gradient Boosting

To investigate the performance of extreme gradient boosting (XGBoost) in remote sensing image classification tasks, XGBoost was first introduced and comparatively investigated for the spectral-spatial classification of hyperspectral imagery using the extended maximally stable extreme-region-guided morphological profiles (EMSER_MPs) proposed in this study. To overcome the potential issues of XGBoost, meta-XGBoost was proposed as an ensemble XGBoost method with classification and regression tree (CART), dropout-introduced multiple additive regression tree (DART), elastic net regression and parallel coordinate descent-based linear regression (linear) and random forest (RaF) boosters. Moreover, to evaluate the performance of the introduced XGBoost approach with different boosters, meta-XGBoost and EMSER_MPs, well-known and widely accepted classifiers, including support vector machine (SVM), bagging, adaptive boosting (AdaBoost), multi class AdaBoost (MultiBoost), extremely randomized decision trees (ExtraTrees), RaF, classification via random forest regression (CVRFR) and ensemble of nested dichotomies with extremely randomized decision tree (END-ERDT) methods, were considered in terms of the classification accuracy and computational efficiency. The experimental results based on two benchmark hyperspectral data sets confirm the superior performance of EMSER_MPs and EMSER_MPs with mean pixel values within region (EMSER_MPsM) compared to that for morphological profiles (MPs), morphological profile with partial reconstruction (MPPR), extended MPs (EMPs), extended MPPR (EMPPR), maximally stable extreme-region-guided morphological profiles (MSER_MPs) and MSER_MPs with mean pixel values within region (MSER_MPsM) features. The proposed meta-XGBoost algorithm is capable of obtaining better results than XGBoost with the CART, DART, linear and RaF boosters, and it could be an alternative to the other considered classifiers in terms of the classification of hyperspectral images using advanced spectral-spatial features, especially from generalized classification accuracy and model training efficiency perspectives.

scholarly journals Convolutional Rebalancing Network for the Classification of Large Imbalanced Rice Pest and Disease Datasets in the Field

2021 ◽  
Vol 12 ◽  
Author(s):  
Guofeng Yang ◽  
Guipeng Chen ◽  
Cong Li ◽  
Jiangfan Fu ◽  
Yang Guo ◽  
...  
Keyword(s):  
Feature Extraction ◽  
Feature Fusion ◽  
Classification Performance ◽  
Superior Performance ◽  
Imbalanced Dataset ◽  
Pests And Diseases ◽  
Rice Pests ◽  
Rice Pest ◽  
Image Datasets

The accurate classification of crop pests and diseases is essential for their prevention and control. However, datasets of pest and disease images collected in the field usually exhibit long-tailed distributions with heavy category imbalance, posing great challenges for a deep recognition and classification model. This paper proposes a novel convolutional rebalancing network to classify rice pests and diseases from image datasets collected in the field. To improve the classification performance, the proposed network includes a convolutional rebalancing module, an image augmentation module, and a feature fusion module. In the convolutional rebalancing module, instance-balanced sampling is used to extract features of the images in the rice pest and disease dataset, while reversed sampling is used to improve feature extraction of the categories with fewer images in the dataset. Building on the convolutional rebalancing module, we design an image augmentation module to augment the training data effectively. To further enhance the classification performance, a feature fusion module fuses the image features learned by the convolutional rebalancing module and ensures that the feature extraction of the imbalanced dataset is more comprehensive. Extensive experiments in the large-scale imbalanced dataset of rice pests and diseases (18,391 images), publicly available plant image datasets (Flavia, Swedish Leaf, and UCI Leaf) and pest image datasets (SMALL and IP102) verify the robustness of the proposed network, and the results demonstrate its superior performance over state-of-the-art methods, with an accuracy of 97.58% on rice pest and disease image dataset. We conclude that the proposed network can provide an important tool for the intelligent control of rice pests and diseases in the field.

scholarly journals Animal fiber imagery classification using a combination of random forest and deep learning methods

2021 ◽  
Vol 16 ◽  
pp. 155892502110093
Author(s):  
Yaolin Zhu ◽  
Jiameng Duan ◽  
Tong Wu
Keyword(s):  
Feature Extraction ◽  
Random Forest ◽  
Textile Industry ◽  
Microscopic Images ◽  
Automatic Feature Extraction ◽  
High Level ◽  
Backward Propagation ◽  
Images Recognition ◽  
Wool Industry

Feature extraction is a key step in animal fiber microscopic images recognition that plays an important role in the wool industry and textile industry. To improve the accuracy of wool and cashmere microscopic images classification, a hybrid model based on Convolutional Neural Network (CNN) and Random Forest (RF) is proposed for automatic feature extraction and classification of animal fiber microscopic images. First, use CNN to learn the representative high-level features from animal fiber images, then add dropout layers to avoid over-fitting. And the backward propagation algorithm are used to optimize the CNN structure. Random forest, which is robust and has strong generalization ability, is introduced for the classification of animal fiber microscopic images to obtain the final results. The study shows that, the proposed method has better generalization performance and higher classification accuracy than other classification methods.

scholarly journals Classification of handwritten Javanese script using random forest algorithm

2021 ◽  
Vol 10 (3) ◽  
pp. 1308-1315
Author(s):  
Mohammad Arif Rasyidi ◽  
Taufiqotul Bariyah ◽  
Yohanes Indra Riskajaya ◽  
Ayunda Dwita Septyani
Keyword(s):  
Feature Extraction ◽  
Random Forest ◽  
Predictive Model ◽  
Histogram Of Oriented Gradients ◽  
Random Forest Algorithm ◽  
Forest Model ◽  
Black And White ◽  
Image Conversion ◽  
Image Dataset

The ability to read and write Javanese scripts is one of the most important competencies for students to have in order to preserve the Javanese language as one of the Indonesian cultures. In this study, we developed a predictive model for 20 Javanese characters using the random forest algorithm as the basis for developing Javanese script learning media for students. In building the model, we used an extensive handwritten image dataset and experimented with several different preprocessing methods, including image conversion to black-and-white, cropping, resizing, thinning, and feature extraction using histogram of oriented gradients. From the experiment, it can be seen that the resulting random forest model is able to classify Javanese characters very accurately with accuracy, precision, and recall of 97.7%.

Classification of urban environments using feature extraction and random forest

2017 ◽  
Author(s):  
Camila Souza dos Anjos ◽  
Marielcio Goncalves Lacerda ◽  
Leidiane do Livramento Andrade ◽  
Roberto Neves Salles
Keyword(s):  
Feature Extraction ◽  
Random Forest ◽  
Urban Environments
Sign in / Sign up

Export Citation Format

Share Document