Hyperspectral Image Classification Based on Improved Rotation Forest Algorithm

Lv, Fei; Han, Min

doi:10.3390/s18113601

Cited by 7 publications

(3 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…If the feature mappings of ELM are unknown for individuals, a kernel trick is performed andKELM has been developed [15]. Figure 3 demonstrated the architecture of KELM.…”

Section: A Kernel Extreme Learning Machinementioning

confidence: 99%

Epileptic Seizure Detection using Simulated Annealing based Optimal Feature Subset Selection with Kernel Extreme Learning Machine Classification Model

2020

IJATCSE

View full text Add to dashboard Cite

Electroencephalogram (EEG) signal based epileptic seizure detection is a hot research area, which identifies the non-stationary progresses of brain actions. Typically, the epilepsy is detected by doctors based on the visual examination of EEG signals consumes more time and highly sensitive to noise. Presently, machine learning (ML) techniques finds useful to predict the existence of epileptic seizure from EEG signals. This paper aims to develop a ML based Epileptic seizure detection model in EEG signals. The proposed model involves three major processes namely preprocessing, feature selection and classification. Initially, the EEG signal undergoes preprocessing in two ways namely data normalization, and class labeling. Next, simulated annealing (SA) is applied as a feature selector to choose an optimal set of features. At last, kernel extreme learning machine (KELM) based classification process takes place to detect and classify the existence of EEG. A detailed simulation analysis takes place to inspect the performance of the SA-KELM model. The experimental outcome stated that the SA-KELM model has offered maximum detection performance under the classification of multiple classes with the maximum sensitivity of 57.27%, specificity of 89.32%, accuracy of 82.91%, F-score of 57.29% and kappa of 46.62%.

show abstract

“…If the feature mappings of ELM are unknown for individuals, a kernel trick is performed andKELM has been developed [15]. Figure 3 demonstrated the architecture of KELM.…”

Section: A Kernel Extreme Learning Machinementioning

confidence: 99%

Epileptic Seizure Detection using Simulated Annealing based Optimal Feature Subset Selection with Kernel Extreme Learning Machine Classification Model

2020

IJATCSE

View full text Add to dashboard Cite

show abstract

“…In [15], a classification method, called improved Rotation Forest (ROF) is proposed. In this method, Non-negative matrix factorization (NMF) is used to do feature segmentation to get more effective data.…”

Section: A Meta-ensemble Classifier Approach: Randommentioning

confidence: 99%

A Meta-Ensemble Classifier Approach: Random Rotation Forest

Taşçı

2019

Balkan Journal of Electrical and Computer Engineering

View full text Add to dashboard Cite

Ensemble learning is a popular and intensively studied field in machine learning and pattern recognition to increase the performance of the classification. Random forest is very important for giving fast and effective results. On the other hand, Rotation Forest can get better performance than Random Forest. In this study, we present a meta-ensemble classifier, called Random Rotation Forest to utilize and combine the advantages of two classifiers (e.g. Rotation Forest and Random Forest). In the experimental studies, we use three base learners (namely, J48, REPTree, and Random Forest) and two metalearners (namely, Bagging and Rotation Forest) for ensemble classification on five datasets in UCI Machine Learning Repository. The experimental results indicate that Random Rotation Forest gives promising results according to base learners and bagging ensemble approaches in terms of accuracy rates, AUC, precision, recall, and F-measure values. Our method can be used for image/pattern recognition and machine learning problems.

show abstract

“…The RoF adopts a principal component analysis (PCA) of feature subtests to reconstruct full feature space and to improve the diversity of all base classifiers, distinguishing it from the RF. Moreover, the RoF has been used for optical and Fully Polarimetric Synthetic Aperture Radar remote sensing classification, and it has been demonstrated that the RoF achieves a higher level of classification accuracy than the RF [21,22]. However, regardless of the many types of classification methods available, each method presents its own advantages and weaknesses [23].…”

Section: Introductionmentioning

confidence: 99%

Intercropping Classification From GF-1 and GF-2 Satellite Imagery Using a Rotation Forest Based on an SVM

Liu

Chen

2019

IJGI

View full text Add to dashboard Cite

Remote sensing has been widely used in vegetation cover research but is rarely used for intercropping area monitoring. To investigate the efficiency of Chinese Gaofen satellite imagery, in this study the GF-1 and GF-2 of Moyu County south of the Tarim Basin were studied. Based on Chinese GF-1 and GF-2 satellite imagery features, this study has developed a comprehensive feature extraction and intercropping classification scheme. Textural features derived from a Gray level co-occurrence matrix (GLCM) and vegetation features derived from multi-temporal GF-1 and GF-2 satellites were introduced and combined into three different groups. The rotation forest method was then adopted based on a Support Vector Machine (RoF-SVM), which offers the advantage of using an SVM algorithm and that boosts the diversity of individual base classifiers by a rotation forest. The combined spectral-textural-multitemporal features achieved the best classification result. The results were compared with those of the maximum likelihood classifier, support vector machine and random forest method. It is shown that the RoF-SVM algorithm for the combined spectral-textural-multitemporal features can effectively classify an intercropping area (overall accuracy of 86.87% and kappa coefficient of 0.78), and the classification result effectively eliminated salt and pepper noise. Furthermore, the GF-1 and GF-2 satellite images combined with spectral, textural, and multi-temporal features can provide sufficient information on vegetation cover located in an extremely complex and diverse intercropping area.

show abstract

Hyperspectral Image Classification Based on Improved Rotation Forest Algorithm

Cited by 7 publications

References 38 publications

Epileptic Seizure Detection using Simulated Annealing based Optimal Feature Subset Selection with Kernel Extreme Learning Machine Classification Model

Epileptic Seizure Detection using Simulated Annealing based Optimal Feature Subset Selection with Kernel Extreme Learning Machine Classification Model

A Meta-Ensemble Classifier Approach: Random Rotation Forest

Intercropping Classification From GF-1 and GF-2 Satellite Imagery Using a Rotation Forest Based on an SVM

Contact Info

Product

Resources

About