RF Classifier Research Articles

How Relevant is High-Cadence Earth Observation for Maize Crop Phenology Classification?

Crop phenology can be defined as the study of biological processes such as emergence, flowering, and senescence that are associated with and affected by environmental growing conditions. The ability to reliably detect crop phenology and its spatial-temporal variability is critical for farmers, policymakers, and government agencies, since it has implications for the entire food chain. Currently, two methods are the most used to report crop phenology. Land surface phenology provides insight into the overall trend, whereas USDA-NASS weekly reports provide insight into the development of specific crops at the regional level. High-cadence earth observations may be able to improve the accuracy of these estimations and bring more precise crop phenology classifications closer to what farmers need. The use of robust classifiers (e.g., random forest, RF) to manage large data sets is required to successfully achieve this goal. This study compared the output of an RF classifier model using weather, two different satellite sources (Planet Fusion; PF and Sentinel-2; S-2), and ground truth data to improve maize (Zea mays L.) crop phenology classification during the 2017 growing season in Kansas. Our findings indicate that high-cadence (PF) data can enhance crop classification metrics (f1-score = 0.94) as compared to S-2 (f1-score = 0.86). This study emphasizes the significance of very high temporal resolution (daily) earth observation data for agricultural crop monitoring and decision-making tools.

Classification of Stroke Severity Using Clinically Relevant Symmetric Gait Features Based on Recursive Feature Elimination With Cross-Validation

Stroke is a leading cause of disability among elderly individuals, and gait impairment is a typical characteristic related to the stroke severity experienced by patients. The aim of this study is to propose a novel stroke severity classification method using symmetric gait features with recursive feature elimination with cross-validation (RFECV). An experiment was conducted on data acquired from thirteen chronic stroke patients and eighteen elderly participants. They walked on a treadmill at four different speeds based on their preferred speed. In this study, symmetric gait features representing the ratio between the left- and right-side values were used as inputs along with the general gait features that did not completely contain the patients’ gait characteristics. We used four different machine learning (ML) techniques to determine the optimal subset for differentiating between the elderly and stroke groups according to severity based on RFECV. To verify the performance of RFECV and the symmetric gait features, four different feature sets were used: 1) all forty-five general features, 2) all twenty-one symmetric features, 3) the optimal general feature subset obtained by using RFECV, and 4) the optimal symmetric feature subset obtained by using RFECV. It was confirmed that the classification performance increased when symmetric gait data and the RFECV technique were applied. The best classification result was obtained by RF-RFECV with an RF classifier derived from the symmetric features (accuracy: 96.01%). The findings of this study can help clinicians diagnose the stroke severity experienced by patients based on information obtained using ML technology.

Predicting spatial and seasonal patterns of wildlife–vehicle collisions in high-risk areas

Context Vehicle collisions with wildlife can injure or kill animals, threaten human safety, and threaten the viability of rare species. This has led to a focus in road-ecology research on identifying the key predictors of ‘road-kill’ risk, with the goal of guiding management to mitigate its impact. However, because of the complex and context-dependent nature of the causes of risk exposure, modelling road-kill data in ways that yield consistent recommendations has proven challenging. Aim Here we used a multi-model machine-learning approach to identify the spatio-temporal predictors, such as traffic volume, road shape, surrounding vegetation and distance to human settlements, associated with road-kill risk. Methods We collected data on the location, identity and wildlife body size of each road mortality across four seasons along eight roads in southern Tasmania, a ‘road-kill hotspot’ of management concern. We focused on three large-bodied and frequently affected crepuscular Australian marsupial herbivore species, the rufous-bellied pademelon (Thylogale billardierii), Bennett’s wallaby (Macropus rufogriseus) and the bare-nosed wombat (Vombatus ursinus). We fit the point-location data using ‘lasso-regularisation’ of a logistic generalised linear model (LL-GLM) and out-of-bag optimisation of a decision-tree-based ‘random forests’ (RF) algorithm for optimised predictions. Results The RF model, with high-level feature interactions, yielded superior out-of-sample prediction results to the linear additive model, with a RF classification accuracy of 84.8% for the 871 road-kill observations and a true skill statistic of 0.708, compared with 61.2% and 0.205 for the LL-GLM. The lasso rejected road visibility and human density, ranking roadside vegetation type and presence of barrier fencing as the most influential predictors of road-kill locality. Conclusions Forested areas with no roadside barrier fence along curved sections of road posed the highest risk to animals. Seasonally, the frequency of wildlife–vehicle collisions increased notably for females during oestrus, when they were more dispersive and so had a higher encounter rate with roads. Implications These findings illustrate the value of using a combination of attributive and predictive modelling using machine learning to rank and interpret a complexity of possible predictors of road-kill risk, as well as offering a guide to practical management interventions that can mitigate road-related hazards.

Tertiary wavelet model based automatic epilepsy classification system

PurposeThis work proposes a tertiary wavelet model based automatic epilepsy classification system using electroencephalogram (EEG) signals.Design/methodology/approachIn this paper, a three-stage system has been proposed for automated classification of epilepsy signals. In the first stage, a tertiary wavelet model uses the orthonormal M-band wavelet transform. This model decomposes EEG signals into three bands of different frequencies. In the second stage, the decomposed EEG signals are analyzed to find novel statistical features. The statistical values of the features are demonstrated using multi-parameters graph comparing normal and epileptic signals. In the last stage, the features are inputted to different conventional classifiers that classify pre-ictal, inter-ictal (epileptic with seizure-free interval) and ictal (seizure) EEG segments.FindingsFor the proposed system the performance of five different classifiers, namely, KNN, DT, XGBoost, SVM and RF is evaluated for the University of BONN data set using different performance parameters. It is observed that RF classifier gives the best performance among the above said classifiers, with an average accuracy of 99.47%.Originality/valueEpilepsy is a neurological condition in which two or more spontaneous seizures occur repeatedly. EEG signals are widely used and it is an important method for detecting epilepsy. EEG signals contain information about the brain's electrical activity. Clinicians manually examine the EEG waveforms to detect epileptic anomalies, which is a time-consuming and error-prone process. An automated epilepsy classification system is proposed in this paper based on combination of signal processing (tertiary wavelet model) and novel features-based classification using the EEG signals.

Brain Cancer Prediction Based on Novel Interpretable Ensemble Gene Selection Algorithm and Classifier

The growth of abnormal cells in the brain causes human brain tumors. Identifying the type of tumor is crucial for the prognosis and treatment of the patient. Data from cancer microarrays typically include fewer samples with many gene expression levels as features, reflecting the curse of dimensionality and making classifying data from microarrays challenging. In most of the examined studies, cancer classification (Malignant and benign) accuracy was examined without disclosing biological information related to the classification process. A new approach was proposed to bridge the gap between cancer classification and the interpretation of the biological studies of the genes implicated in cancer. This study aims to develop a new hybrid model for cancer classification (by using feature selection mRMRe as a key step to improve the performance of classification methods and a distributed hyperparameter optimization for gradient boosting ensemble methods). To evaluate the proposed method, NB, RF, and SVM classifiers have been chosen. In terms of the AUC, sensitivity, and specificity, the optimized CatBoost classifier performed better than the optimized XGBoost in cross-validation 5, 6, 8, and 10. With an accuracy of , the optimized CatBoost classifier is more accurate than the CatBoost classifier without optimization, which is . By using hybrid algorithms, SVM, RF, and NB automatically become more accurate. Furthermore, in terms of accuracy, SVM and RF () achieve equivalent and higher classification accuracy than NB (). The findings of relevant biomedical studies confirm the findings of the selected genes.

Machine learning model for predicting Major Depressive Disorder using RNA-Seq data: optimization of classification approach.

Considering human brain disorders, Major Depressive Disorder (MDD) is seen as a lethal disease in which a person goes to the extent of suicidal behavior. Physical detection of MDD patients is less precise but machine learning can aid in improved classification of disease. The present research included three RNA-seq data classes to classify DEGs and then train key gene data using a randomforest machine learning method. The three classes in the sample are 29 CON (sudden death healthy control), 21 MDD-S (a Major DepressiveDisorder Suicide) being included in the second group, and 9 MDD (non-suicides MDD) which are included in the third group. With PCA analysis, 99 key genes were obtained. 47.1% data variability is given by these 99 genes. The model training of 99 genes indicated improved classification. The RF classification model has an accuracy of 61.11% over test data and 97.56% over train data. It was also noticed that the RF method offered greater accuracy than the KNN method. 99 genes were annotated using DAVID and ClueGo packages. Some of the important pathways and function observed in the study were glutamatergic synapse, GABA receptor activation, long-term synaptic depression, and morphine addiction. Out Of 99 genes, four genes, namely DLGAP1, GNG2, GRIA1, and GRIA4, were found to be predominantly involved in the glutamatergic synapse pathway. Another substantial link was observed in the GABA receptor activation involving the following two genes, GABBR2 and GNG2. Also, the genes found responsible for long-term synaptic depressionwere GRIA1, MAPT, and PTEN. There was another finding of morphine addiction which comprises three genes, namely GABBR2, GNG2, and PDE4D. For massive datasets, this approach will act as the gold standard. The cases of CON, MDD, and MDD-S are physically distinct. There was dysregulation in the expression level of 12 genes. The 12 genes act as a possible biomarker for Major Depressive Disorder and open up a new path for depressed subjects to explore further.

A large-scale, long time-series (1984‒2020) of soybean mapping with phenological features: Heilongjiang Province as a test case

ABSTRACT Soybean is one of the most important crops in the world. There were dramatic changes in soybean plantation in China in recent decades. Heilongjiang Province has the greatest acreage of soybean plantation in China. Therefore, it is taken as a representative soybean region in this study for monitoring purposes. A 30-m dataset that mapped the areas of soybean planting in Heilongjiang Province was produced, for the period of 1984 ~ 2020, based on Landsat-5/7/8 images and the Google Earth Engine (GEE) platform. Maps were made with a random forest classifier and had overall accuracies better than 84%. The areas planted with soybean were calculated at both the provincial and city level and these were compared with the areas obtained from official statistics. At the provincial level, for more than 85% of the time periods, the areas given in the official statistics fell within the confidence intervals of the estimates. At the city level, soybean areas were also in good agreement with the statistical data in most years giving average R2 values as 0.75. These results demonstrate the effectiveness of using phenological features extracted by a double-logistic model and a linear harmonic model with the RF classifier to obtain a long time-series of soybean maps without using samples obtained by field measurements every year.

Evaluation of Machine Learning Algorithms for Object-Based Mapping of Landslide Zones Using UAV Data

Landslides are a critical geological phenomenon with devastating and catastrophic consequences. With the recent advancements in the geoinformation domain, landslide documentation and inventorization can be achieved with automated workflows using aerial platforms such as unmanned aerial vehicles (UAVs). As a result, ultra-high-resolution datasets are available for analysis at low operational costs. In this study, different segmentation and classification approaches were utilized for object-based landslide mapping. An integrated object-based image analysis (OBIA) workflow is presented incorporating orthophotomosaics and digital surface models (DSMs) with expert-based and machine learning (ML) algorithms. For segmentation, trial and error tests and the Estimation of Scale Parameter 2 (ESP 2) tool were implemented for the evaluation of different scale parameters. For classification, machine learning algorithms (K- Nearest Neighbor, Decision Tree, and Random Forest) were assessed with the inclusion of spectral, spatial, and contextual characteristics. For the ML classification of landslide zones, 60% of the reference segments have been used for training and 40% for validation of the models. The quality metrics of Precision, Recall, and F1 were implemented to evaluate the models’ performance under the different segmentation configurations. Results highlight higher performances for landslide mapping when DSM information was integrated. Hence, the configuration of spectral and DSM layers with the RF classifier resulted in the highest classification agreement with an F1 value of 0.85.

Mapping flood by the object-based method using backscattering coefficient and interference coherence of Sentinel-1 time series

The SAR has the ability of all-weather and all-time data acquisition, it can penetrate the cloud and is not affected by extreme weather conditions, and the acquired images have better contrast and rich texture information. This paper aims to investigate the use of an object-oriented classification approach for flood information monitoring in floodplains using backscattering coefficients and interferometric coherence of Sentinel-1 data under time series. Firstly, the backscattering characteristics and interference coherence variation characteristics of SAR time series are used to analyze whether the flood disaster information can be accurately reflected and provide the basis for selecting input classification characteristics of subsequent SAR images. Subsequently, the contribution rate index of the RF model is used to calculate the importance of each index in time series to convert the selected large number of classification features into low dimensional feature space to improve the classification accuracy and reduce the data redundancy. Finally, the SAR image features in each period after multi-scale segmentation and feature selection are jointly used as the input features of RF classification to extract and segment the water in the study area to monitor floods' spatial distribution and dynamic characteristics. The results showed that the various attributes of backscatter coefficients and interferometric coherence under time series could accurately correspond with the actual flood risk, and the combined use of backscattering coefficient and interferometric coherence for flood extraction can significantly improve the accuracy of flood information extraction. Overall, the object-based random forest method using the backscattering coefficient and interference coherence of Sentinel-1 time series for flood extraction advances our understanding of flooding's temporal and spatial dynamics, essential for the timely adoption of adaptation and mitigation strategies for loss reduction.

Pixel- vs. Object-Based Landsat 8 Data Classification in Google Earth Engine Using Random Forest: The Case Study of Maiella National Park

With the general objective of producing a 2018–2020 Land Use/Land Cover (LULC) map of the Maiella National Park (central Italy), useful for a future long-term LULC change analysis, this research aimed to develop a Landsat 8 (L8) data composition and classification process using Google Earth Engine (GEE). In this process, we compared two pixel-based (PB) and two object-based (OB) approaches, assessing the advantages of integrating the textural information in the PB approach. Moreover, we tested the possibility of using the L8 panchromatic band to improve the segmentation step and the object’s textural analysis of the OB approach and produce a 15-m resolution LULC map. After selecting the best time window of the year to compose the base data cube, we applied a cloud-filtering and a topography-correction process on the 32 available L8 surface reflectance images. On this basis, we calculated five spectral indices, some of them on an interannual basis, to account for vegetation seasonality. We added an elevation, an aspect, a slope layer, and the 2018 CORINE Land Cover classification layer to improve the available information. We applied the Gray-Level Co-Occurrence Matrix (GLCM) algorithm to calculate the image’s textural information and, in the OB approaches, the Simple Non-Iterative Clustering (SNIC) algorithm for the image segmentation step. We performed an initial RF optimization process finding the optimal number of decision trees through out-of-bag error analysis. We randomly distributed 1200 ground truth points and used 70% to train the RF classifier and 30% for the validation phase. This subdivision was randomly and recursively redefined to evaluate the performance of the tested approaches more robustly. The OB approaches performed better than the PB ones when using the 15 m L8 panchromatic band, while the addition of textural information did not improve the PB approach. Using the panchromatic band within an OB approach, we produced a detailed, 15-m resolution LULC map of the study area.

Expert cancer model using supervised algorithms with a LASSO selection approach

One of the most critical issues of the mortality rate in the medical field in current times is breast cancer. Nowadays, a large number of men and women is facing cancer-related deaths due to the lack of early diagnosis systems and proper treatment per year. To tackle the issue, various data mining approaches have been analyzed to build an effective model that helps to identify the different stages of deadly cancers. The study successfully proposes an early cancer disease model based on five different supervised algorithms such as logistic regression (henceforth LR), decision tree (henceforth DT), random forest (henceforth RF), Support vector machine (henceforth SVM), and K-nearest neighbor (henceforth KNN). After an appropriate preprocessing of the dataset, least absolute shrinkage and selection operator (LASSO) was used for feature selection (FS) using a 10-fold cross-validation (CV) approach. Employing LASSO with 10-fold cross-validation has been a novel steps introduced in this research. Afterwards, different performance evaluation metrics were measured to show accurate predictions based on the proposed algorithms. The result indicated top accuracy was received from RF classifier, approximately 99.41% with the integration of LASSO. Finally, a comprehensive comparison was carried out on Wisconsin breast cancer (diagnostic) dataset (WBCD) together with some current works containing all features.

Semi-Supervised Classification of the State of Operation in Self-Lubricating Journal Bearings Using a Random Forest Classifier

For a tribological experiment involving a steel shaft sliding in a self-lubricating bronze bearing, a semi-supervised machine learning method for the classification of the state of operation is proposed. During the translatory oscillating motion, the system may undergo different states of operation from normal to critical, showing self-recovering behaviour. A Random Forest classifier was trained on individual cycles from the lateral force data from four distinct experimental runs in order to distinguish between four states of operation. The labelling of the individual cycles proved to be crucial for a high prediction accuracy of the trained RF classifier. The proposed semi-supervised approach allows choosing within a range between automatically generated labels and full manual labelling by an expert user. The algorithm was at the current state used for ex post classification of the state of operation. Considering the results from the ex post analysis and providing a sufficiently sized training dataset, online classification of the state of operation of a system will be possible. This will allow taking active countermeasures to stabilise the system or to terminate the experiment before major damage occurs.

A Machine Learning-Based Fall Risk Assessment Model for Inpatients.

Falls are one of the most common accidents among inpatients and may result in extended hospitalization and increased medical costs. Constructing a highly accurate fall prediction model could effectively reduce the rate of patient falls, further reducing unnecessary medical costs and patient injury. This study applied data mining techniques on a hospital's electronic medical records database comprising a nursing information system to construct inpatient-fall-prediction models for use during various stages of inpatient care. The inpatient data were collected from 15 inpatient wards. To develop timely and effective fall prediction models for inpatients, we retrieved the data of multiple-time assessment variables at four points during hospitalization. This study used various supervised machine learning algorithms to build classification models. Four supervised learning and two classifier ensemble techniques were selected for model development. The results indicated that Bagging+RF classifiers yielded optimal prediction performance at all four points during hospitalization. This study suggests that nursing personnel should be aware of patients' risk factors based on comprehensive fall risk assessment and provide patients with individualized fall prevention interventions to reduce inpatient fall rates.

Potential of Hybrid CNN-RF Model for Early Crop Mapping with Limited Input Data

When sufficient time-series images and training data are unavailable for crop classification, features extracted from convolutional neural network (CNN)-based representative learning may not provide useful information to discriminate crops with similar spectral characteristics, leading to poor classification accuracy. In particular, limited input data are the main obstacles to obtain reliable classification results for early crop mapping. This study investigates the potential of a hybrid classification approach, i.e., CNN-random forest (CNN-RF), in the context of early crop mapping, that combines the automatic feature extraction capability of CNN with the superior discrimination capability of an RF classifier. Two experiments on incremental crop classification with unmanned aerial vehicle images were conducted to compare the performance of CNN-RF with that of CNN and RF with respect to the length of the time-series and training data sizes. When sufficient time-series images and training data were used for the classification, the accuracy of CNN-RF was slightly higher or comparable with that of CNN. In contrast, when fewer images and the smallest training data were used at the early crop growth stage, CNN-RF was substantially beneficial and the overall accuracy increased by maximum 6.7%p and 4.6%p in the two study areas, respectively, compared to CNN. This is attributed to its ability to discriminate crops from features with insufficient information using a more sophisticated classifier. The experimental results demonstrate that CNN-RF is an effective classifier for early crop mapping when only limited input images and training samples are available.

Detailed and automated classification of land use/land cover using machine learning algorithms in Google Earth Engine

All the supervised classification methods need sufficient and efficient samples, which are commonly labeled by visual inspection. In this study, to resolve the issues of insufficient training samples and time-consuming, a novel method for detailed and automated LULC classification by LC_Type1 of MCD12Q1 IGBP schemes in the GEE cloud platform was proposed based on the RF and CART classifiers. The results present that the validation overall accuracy of the RF classifier is higher than the CART, 87.24% in Australia, and 85.18% in the USA, respectively. The automated classification results of the RF classifier are more concentrated than CART, which the RF classifier is more suitable for this automated method. Moreover, the proposed method can accomplish accurate, detailed, and automated LULC classification based on the GEE which is making satellite imagery computing an efficient, flexible, and fast process. The workflow provides a reliable method for detailed, automated, and remotely LULC classification.

Myocardial Infarction Prediction Using Hybrid Machine Learning Techniques

The myocardial infarction prediction is an important task in health care domain in the current days. So, Prediction of cardiovascular diseases is a critical challenge in the area of clinical data analysis. It is difficult to predict myocardial infarction prediction by physicians with huge health records. To overcome this complexity we need to implement the automatic heard disease prediction system to notify the patient and get to recovery from the disease. Here to gaining the automatic system we are using machine learning techniques to easily performing myocardial infarction prediction. The machine learning techniques can be split into multiple types like unsupervised and supervised learning classifier. The supervised learning techniques working with structured data which is recommended to implement this classifiers. So, in this system we are using supervised learning techniques namely KNN, RF, NN, DT, NB, and SVM classifiers. To predict myocardial infarction, this system is using training dataset which is accessing from UCI ML repository. As well as this system is comparing accuracy performance between various machine learning algorithms and accuracy results with graphical presentation. This makes the accessing of the risk of the disease in the early stages and can try to save the patient without having any loss.

Comparison of PBIA and GEOBIA classification methods in classifying turbidity in reservoirs

Our goal is to compare the performance of Classification and Regression Tree, Naive Bayes and Random Forest algorithms, from supervised image classification, and approaches on Pixel-Based Image analysis (PBIA) and Geographic Object-Based Image Analysis (GEOBIA), to classify turbidity in reservoirs. Tod do so, we use Landsat 8 image and bands and spectral indices, as predictive parameters, as well as the classification algorithms based on PBIA and GEOBIA. The Brazilian Itaipu reservoir was adopted, as a case study. Our results show that the RF classifier obtained the highest accuracy in both classification approaches, followed by CART and NB. The KA and OA indices of the GEOBIA classifications were superior to the PBIA classifications in both algorithms. This study contributes with an approach to quickly and accurately delineating turbidity spectral limits in reservoirs.

WITHDRAWN: Video event classification using KNN classifier with hybrid features

Event detection from videos has become a demanding and challenging subject with the creation of huge video data. Detection of complex interesting events automatically in user generated videos is a difficult job because of its features that differ from video broadcasting. We present an effective technique for detecting actions or events in UCF 101 video large scale data. Histogram equalization is initially used on UCF101 database for contrast enhancement in the pre processing stage. In the later stage gradient local ternary pattern, histogram of oriented gradient and tamuras features are extracted from the enhanced images to accomplish feature extraction. Finally k nearest neighbor (KNN) classifier is used to classify the events. In this work we compared Random Forest classifier with KNN classifier in terms of accuracy, specificity, sensitivity, false discovery rate, false omission rate and error rate. KNN gave 90.25% accuracy where as Random forest classifier yielded 77.18% accuracy. The result exhibits that KNN classifier gives better performance than RF classifier.

Smartphone-based Identification of Critical Levels of Glycated Hemoglobin A1c using Transdermal Optical Imaging

Abstract: Worldwide, the prevalence of diabetes has continued to increase rapidly. This gives rise to concerns regarding appropriate diabetes management to ensure optimal glycemic control. Untreated or uncontrolled diabetes can lead to a host of complications, such as cardiovascular diseases, an increased likelihood of morbidity and mortality (Deshpande, Harris-Hayes, & Schootman, 2008). A challenging problem which arises in diabetes management is the limitations of current blood glucose monitoring techniques. Electronic medical devices can potentially overcome the persistent problems in the healthcare industry. Thus, for this study, it was of interest to investigate whether advanced machine learning methods and Anura, a smartphone-based transdermal optical imaging technology (TOI) that assess health markers, can be a viable solution for diabetes management. Objectives: To examine the validity of TOI and a novel machine algorithm for diabetes prediction (i.e diabetes and non-diabetes). We compared the diabetes classification from TOI’s obtained glycated hemoglobin A1c (HbA1c) concentrations against data obtained from FDA approved blood immunoassay. Methods: In the present study, we used a kitchen sink random forest machine algorithm for diabetes prediction. The data set was obtained from 513 participants recruited during their annual physical examination at the Health Management Center of The Affiliated Hospital of Hangzhou Normal University, China. This included participant’s TOI and blood immunoassay determined HbA1c concentrations. To validate the model, pristine testing was done on 400 pristine participants pseudo randomly selected during 20 trials of training/testing. Results: The confusion matrix found TOI to have a classification accuracy of 66%, and the ROC curve of the RF classifier found TOI to have a ROC AUC of 0.69. Conclusions: The present study provides evidence for the potential use of the TOI technology, Anura, for contactless, non-invasive, and inexpensive assessments of diabetes.

Localization and Diagnosis of Attention-Deficit/Hyperactivity Disorder.

In this paper, a random-forest-based method was proposed for the classification and localization of Attention-Deficit/Hyperactivity Disorder (ADHD), a common neurodevelopmental disorder among children. Experimental data were magnetic resonance imaging (MRI) from the public case-control dataset of 3D images for ADHD-200. Each MRI image was a 3D-tensor of size. All 3D matrices (MRI) were segmented into the slices from each of three orthogonal directions. Each slice from the same position of the same direction in the training set was converted into a vector, and all these vectors were composed into a designed matrix to train the random forest classification algorithm; then, the well-trained RF classifier was exploited to give a prediction label in correspondence direction and position. Diagnosis and location results can be obtained upon the intersection of these three prediction matrices. The performance of our proposed method was illustrated on the dataset from New York University (NYU), Kennedy Krieger Institute (KKI) and full datasets; the results show that the proposed methods can archive more accuracy identification in discrimination of ADHD, and can be extended to the other practices of diagnosis. Moreover, another suspected region was found at the first time.