Majority Vote Algorithm Research Articles

Classification using semantic feature and machine learning: Land-use case application

Land cover classification has interested recent works especially for deforestation, urban are monitoring and agricultural land use. Traditional classification approaches have limited accuracy especially for non-heterogeneous land cover. Thus, using machine may improve the classification accuracy. The presented paper deals with the land-use scene recognition on very high-resolution remote sensing imagery. We proposed a new framework based on semantic features, handcrafted features and machine learning classifiers decisions. The method starts by semantic feature extraction using a convolutional neural network. Handcraft features are also extracted based on color and multi-resolution characteristics. Then, the classification stage is processed by three learning machine algorithms. The final classification result performed by majority vote algorithm. The idea behind is to take advantages from semantic features and handcrafted features. The second scope is to use the decision fusion to enhance the classification result. Experimentation results show that the proposed method provides good accuracy and trustable tool for land use image identification.

Abstract 255: TransVAF: A transfer learning approach for recognize genomic mutations with various tumor purity and clonal proportions

Abstract Mutation detection, via genomic sequencing, has become a routine in cancer diagnosis and precision treatments. Although the existing bioinformatics approaches alter the algorithms and strategies for the detection, they always rely on the combinations of statistical features on a set of overlapped reads to recognize the real mutations from false positives. It may be the Achilles heel of such recognition mechanisms, that their preset thresholds are often stiff and ambiguous and the feature combinations with adaptive thresholds could only be enabled by machine learning frameworks. Unfortunately, the learning models have to overcome the challenges caused by tumor heterogeneity. For mutations from different subclones, most of the sequencing features associate with the tumor purity and clonal proportions. It introduces complicated interactions among the features and breaks the independent co-distribution assumption of classic learning models. In addition, both the tumor purity and clonal proportions are variables, thus, any training sets cannot enumerate all possible values. These challenges hurt the specificities of the existing approaches applying to cancer sequencing data. Here, we propose an approach for the scenario of various tumor purity and clonal proportions. The proposed approach incorporates a comprehensive set of the features according to the existing strategies. Then, it requires at least two training sets with different proportions. For any given set, we have fixed tumor purity and clonal proportions. The framework first trains the models according to one set. The trained models focus on the associations between the features and true mutations. These models are defined as a source domain. Next, when the other set is input for training, the framework not only trains another source domain, but focuses on the transformations among the features between the source domains as well. Now, when another fixed tumor purity and clonal proportions are considered, the framework is able to generate, maybe roughly, the models for the new group of the purity and proportions according to the source domains and the transformations. To enhance the performance, we propose to integrate a few source domains to control the systematic errors during the transfer processes. The Boyer-Moore majority-vote algorithm is introduced to achieve the integration. We have carried out a series of experiments on both simulated and real datasets, and compared to the state-of-the-art approaches, including MuTect2, Sentieon, VarScan2, Freebayes and SiNVICT. The results demonstrated that the proposed method adapts well to different diluted sequencing signals and can significantly reduce the false positive. It is implemented as TransVAF. The software package has been uploaded at https://github.com/TrinaZ/TL-fpFilter for academic usage only. Citation Format: Tian Zheng, Jiayin Wang, Xiao Xiao, Xiaoyan Zhu, Xuanping Zhang, Xin Lai, Yanfang Guan, Xin Yi. TransVAF: A transfer learning approach for recognize genomic mutations with various tumor purity and clonal proportions [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2021; 2021 Apr 10-15 and May 17-21. Philadelphia (PA): AACR; Cancer Res 2021;81(13_Suppl):Abstract nr 255.

AUTOMATED CLASSIFICATION OF SOLITARY PULMONARY NODULES USING CONVOLUTIONAL NEURAL NETWORK BASED ON TRANSFER LEARNING STRATEGY

This study aimed to propose an effective malignant solitary pulmonary nodule classification method based on improved Faster R-CNN and transfer learning strategy. In practice, the existing solitary pulmonary nodule classification methods divide the lung cancer images into two categories only: normal and cancerous. This study proposed the deep convolution neural network to classify the computed tomography (CT) images of lung cancer into four categories: lung adenocarcinoma, lung squamous cell carcinoma, metastatic lung cancer, and normal types of lung cancer. Some high-resolution lung CT images have unnecessary characters such as a large number of high-density continuity features, small-size lung nodule targets, CT image background complexity, and so forth. In this study, the CT image sub-block preprocessing strategy was used to extract nodule features for enhancement and alleviate the aforementioned problems. The experimental results showed that the proposed system was effective in resolving issues such as high false-positive rate and long classification time cost based on the original Faster R-CNN detection method. Meanwhile, the transfer learning strategy was used to improve the classification efficiency so as to avoid the overfitting problem caused by a few labeled samples of lung cancer datasets. The classification results were integrated using the majority vote algorithm. The classification results of the lung CT imaging showed that the proposed method had an average detection accuracy of 89.7% and reduced the rate of misdiagnosis to meet the clinical needs.

Majority Vote Cascading: A Semi-Supervised Framework for Improving Protein Function Prediction.

A method to improve protein function prediction for sparsely annotated PPI networks is introduced. The method extends the DSD majority vote algorithm introduced by Cao et al. to give confidence scores on predicted labels and to use predictions of high confidence to predict the labels of other nodes in subsequent rounds. We call this a majority vote cascade. Several cascade variants are tested in a stringent cross-validation experiment on PPI networks from S. cerevisiae and D. melanogaster, and we show that for many different settings with several alternative confidence functions, cascading improves the accuracy of the predictions. A list of the most confident new label predictions in the two networks is also reported. Code and networks for the cross-validation experiments appear at http://bcb.cs.tufts.edu/cascade.

Intra-Annual Sentinel-2 Time-Series Supporting Grassland Habitat Discrimination

The present study aims to discriminate four semi-arid grassland habitats in a Mediterranean Natura 2000 site, Southern Italy, involving 6210/E1.263, 62A0/E1.55, 6220/E1.434 and X/E1.61-E1.C2-E1.C4 (according to Annex I of the European Habitat Directive/EUropean Nature Information System (EUNIS) taxonomies). For this purpose, an intra-annual time-series of 30 Sentinel-2 images, embedding phenology information, were investigated for 2018. The methodology adopted was based on a two-stage workflow employing a Support Vector Machine classifier. In the first stage only four Sentinel-2 multi-season images were analyzed, to provide an updated land cover map from where the grassland layer was extracted. The layer obtained was then used for masking the input features to the second stage. The latter stage discriminated the four grassland habitats by analyzing several input features configurations. These included multiple spectral indices selected from the time-series and the Digital Terrain Model. The results obtained from the different input configurations selected were compared to evaluate if the phenology information from time-series could improve grassland habitats discrimination. The highest F1 values (95.25% and 80.27%) were achieved for 6210/E1.263 and 6220/E1.434, respectively, whereas the results remained stable (97,33%) for 62A0/E1.55 and quite low (75,97%) for X/E1.61-E1.C2-E1.C4. However, since for all the four habitats analyzed no single configuration resulted effective, a Majority Vote algorithm was applied to achieve a reduction in classification uncertainty.

Find truth in the hands of the few: acquiring specific knowledge with crowdsourcing

Crowdsourcing has been a helpful mechanism to leverage human intelligence to acquire useful knowledge. However, when we aggregate the crowd knowledge based on the currently developed voting algorithms, it often results in common knowledge that may not be expected. In this paper, we consider the problem of collecting specific knowledge via crowdsourcing. With the help of using external knowledge base such as WordNet, we incorporate the semantic relations between the alternative answers into a probabilistic model to determine which answer is more specific. We formulate the probabilistic model considering both worker’s ability and task’s difficulty from the basic assumption, and solve it by the expectation-maximization (EM) algorithm. To increase algorithm compatibility, we also refine our method into semi-supervised one. Experimental results show that our approach is robust with hyper-parameters and achieves better improvement than majority voting and other algorithms when more specific answers are expected, especially for sparse data.

Multi-scale deep feature learning network with bilateral filtering for SAR image classification

Synthetic aperture radar (SAR) image classification using deep neural network has drawn great attention, which generally requires various layers of deep model for feature learning. However, a deeper neural network will result in overfitting with limited training samples. In this paper, a multi-scale deep feature learning network with bilateral filtering (MDFLN-BF) is proposed for SAR image classification, which aims to extract discriminative features and reduce the requirement of labeled samples. In the proposed framework, MDFLN is proposed to extract features from SAR image on multiple scales, where the SAR image is stratified into different scales and a full convolutional network is utilized to extract features from each scale sub-image. Then, features of multiple scales are classified by multiple softmax classifiers and combined by majority vote algorithm. Further, bilateral filtering is developed to optimize the classification map based on spatial relation, which aims to improve the spatial smoothness. Experiments are tested on three SAR images with different sensors, bands, resolutions, and polarizations in order to prove the generalization ability. It is demonstrated that the proposed MDFLN-BF is able to yield superior results than other related deep networks.

Atlas-based liver segmentation for nonhuman primate research.

Certain viral infectious diseases cause systemic damage and the liver is an important organ affected directly by the virus and/or the hosts' response to the virus. Medical imaging indicates that the liver damage is heterogenous, and therefore, quantification of these changes requires analysis of the entire organ. Delineating the liver in preclinical imaging studies is a time-consuming and difficult task that would benefit from automated liver segmentation. A nonhuman primate atlas-based liver segmentation method was developed to support quantitative image analysis of preclinical research. A set of 82 computed tomography (CT) scans of nonhuman primates with associated manual contours delineating the liver was generated from normal and abnormal livers. The proposed technique uses rigid and deformable registrations, a majority vote algorithm, and image post-processing operations to automate the liver segmentation process. This technique was evaluated using Dice similarity, Hausdorff distance measures, and Bland-Altman plots. Automated segmentation results compare favorably with manual contouring, achieving a median Dice score of 0.91. Limits of agreement from Bland-Altman plots indicate that liver changes of 3 Hounsfield units (CT) and 0.4 SUVmean (positron emission tomography) are detectable using our automated method of segmentation, which are substantially less than changes observed in the host response to these viral infectious diseases. The proposed atlas-based liver segmentation technique is generalizable to various sizes and species of nonhuman primates and facilitates preclinical infectious disease research studies. While the image analysis software used is commercially available and facilities with funding can access the software to perform similar nonhuman primate liver quantitative analyses, the approach can be implemented in open-source frameworks as there is nothing proprietary about these methods.

Asynchronous Prediction of Human Gait Intention in a Pseudo Online Paradigm Using Wavelet Transform.

Prediction of human voluntary gait intention is a very significant task to ensure direct cortical control of real-life assistive technologies for locomotion rehabilitation. Neurophysiological studies provide that human voluntary gait intention is represented by slow DC potentials and power shifts in specific frequency ranges of brain wave, which can be detected 1.5- 2 seconds before the actual onset. The goal of this study was to determine whether it is possible to reliably detect the intention of voluntary gait 'starting' and 'stopping' intention before it takes place. A computational algorithm was designed to implement asynchronous prediction of gait intention in an offline and pseudo-online environment using support vector machine. Six healthy subjects participated in the study and performed self- paced voluntary gait cycles. A combination of advanced wavelet transform algorithms resulted in 88.23± 1.59% accuracy, 85.42± 4.03% sensitivity and 90.24± 2.78% specificity for intention of start detection and 87.04± 1.72% accuracy, 82.69± 4.13% sensitivity and 89.59± 3.04% specificity for intention to stop walking in offline testing. Additionally, the wavelet transform methods accompanied with threshold regulation and majority voting algorithm resulted in a True Positive Rate of 85.5± 5.0% and 81.2± 3.3% for 'start' and 'stop' prediction with 6.8± 0.7 and 9.4± 1.0 False Positives per Minute respectively in pseudo online testing. The average detection latencies were -1002 ± 603 ms and -943 ± 603 ms, respectively, for 'start' and 'stop' prediction. The study provides promising outcomes in terms of TPR, FP/min, and detection latency, which suggests that human voluntary gait intention can be predicted before the onset of movement.

TOD-CUP: a gene expression rank-based majority vote algorithm for tissue origin diagnosis of cancers of unknown primary.

Gene expression profiling holds great potential as a new approach to histological diagnosis and precision medicine of cancers of unknown primary (CUP). Batch effects and different data types greatly decrease the predictive performance of biomarker-based algorithms, and few methods have been widely applied to identify tissue origin of CUP up to now. To address this problem and assist in more precise diagnosis, we have developed a gene expression rank-based majority vote algorithm for tissue origin diagnosis of CUP (TOD-CUP) of most common cancer types. Based on massive tissue-specific RNA-seq data sets (10553) found in The Cancer Genome Atlas (TCGA), 538 feature genes (biomarkers) were selected based on their gene expression ranks and used to predict tissue types. The top scoring pairs (TSPs) classifier of the tumor type was optimized by the TCGA training samples. To test the prediction accuracy of our TOD-CUP algorithm, we analyzed (1) two microarray data sets (1029 Agilent and 2277 Affymetrix/Illumina chips) and found 91% and 94% prediction accuracy, respectively, (2) RNA-seq data from five cancer types derived from 141 public metastatic cancer tumor samples and achieved 94% accuracy and (3) a total of 25 clinical cancer samples (including 14 metastatic cancer samples) were able to classify 24/25 samples correctly (96.0% accuracy). Taken together, the TOD-CUP algorithm provides a powerful and robust means to accurately identify the tissue origin of 24 cancer types across different data platforms. To make the TOD-CUP algorithm easily accessible for clinical application, we established a Web-based server for tumor tissue origin diagnosis (http://ibi. zju.edu.cn/todcup/).

The dependence of the majority voting decision-making probabilities on a multi-expert binary system experts number

The article presents the analytical results of the decision-making by the majority voting algorithm (MVA). Particular attention is paid to the case of an even number of experts. The conditional probabilities of the MVA for two hypotheses are given for an even number of experts and their properties are investigated depending on the conditional probability of decision-making by independent experts of equal qualifications and on their number. An approach to calculating the probabilities of the correct solution of the MVA with unequal values of the conditional probabilities of accepting hypotheses of each statistically mutually independent expert is proposed. The findings are illustrated by numerical and graphical calculations.

Towards Benthic Habitat 3D Mapping Using Machine Learning Algorithms and Structures from Motion Photogrammetry

The accurate classification and 3D mapping of benthic habitats in coastal ecosystems are vital for developing management strategies for these valuable shallow water environments. However, both automatic and semiautomatic approaches for deriving ecologically significant information from a towed video camera system are quite limited. In the current study, we demonstrate a semiautomated framework for high-resolution benthic habitat classification and 3D mapping using Structure from Motion and Multi View Stereo (SfM-MVS) algorithms and automated machine learning classifiers. The semiautomatic classification of benthic habitats was performed using several attributes extracted automatically from labeled examples by a human annotator using raw towed video camera image data. The Bagging of Features (BOF), Hue Saturation Value (HSV), and Gray Level Co-occurrence Matrix (GLCM) methods were used to extract these attributes from 3000 images. Three machine learning classifiers (k-nearest neighbor (k-NN), support vector machine (SVM), and bagging (BAG)) were trained by using these attributes, and their outputs were assembled by the fuzzy majority voting (FMV) algorithm. The correctly classified benthic habitat images were then geo-referenced using a differential global positioning system (DGPS). Finally, SfM-MVS techniques used the resulting classified geo-referenced images to produce high spatial resolution digital terrain models and orthophoto mosaics for each category. The framework was tested for the identification and 3D mapping of seven habitats in a portion of the Shiraho area in Japan. These seven habitats were corals (Acropora and Porites), blue corals (H. coerulea), brown algae, blue algae, soft sand, hard sediments (pebble, cobble, and boulders), and seagrass. Using the FMV algorithm, we achieved an overall accuracy of 93.5% in the semiautomatic classification of the seven habitats.

Robust Classification of Intramuscular EMG Signals to Aid the Diagnosis of Neuromuscular Disorders.

Goal: This article presents the design and validation of an accurate automatic diagnostic system to classify intramuscular EMG (iEMG) signals into healthy, myopathy, or neuropathy categories to aid the diagnosis of neuromuscular diseases. Methods: First, an iEMG signal is decimated to produce a set of “disjoint” downsampled signals, which are decomposed by the lifting wavelet transform (LWT). The Higuchi's fractal dimensions (FDs) of LWT coefficients in the subbands are computed. The FDs of LWT subband coefficients are fused with one-dimensional local binary pattern derived from each downsampled signal. Next, a multilayer perceptron neural network (MLPNN) determines the class labels of downsampled signals. Finally, the sequence of class labels is fed to the Boyer-Moore majority vote (BMMV) algorithm, which assigns a class to every iEMG signal. Results: The MLPNN-BMMV classifier was experimented with 250 iEMG signals belonging to three categories. The performance of the classifier was validated in comparison with state-of-the-art approaches. The MLPNN-BMMV has resulted in impressive performance measures (%) using a 10-fold cross-validation—accuracy = n}{}99.87pm 0.25, sensitivity (normal) = n}{}99.97pm 0.13, sensitivity (myopathy) = n}{}99.68pm 0.95, sensitivity (neuropathy) = n}{}99.76pm 0.66, specificity (normal) = n}{}99.72pm 0.61, specificity (myopathy) = n}{}99.98pm 0.10, and specificity (neuropathy) = n}{}99.96pm 0.14—surpassing the existing approaches. Conclusions: A future research direction is to validate the classifier performance with diverse iEMG datasets, which would lead to the design of an affordable real-time expert system for neuromuscular disorder diagnosis.

Predicting Stock Market Trends using Hybrid SVM Model and LSTM with Sentiment Determination using Natural Language Processing

In the financial world, stock trading is one of the most crucial activities. Investors make educated guesses to predict stock market trends by analyzing news, studying the company history, industrial history and a lot of other data. successfully predicting the stock market trends and investing in the right shares at the right time can maximize the investor’s profit or at least minimize the losses. Stock market price data is generated in huge volumes and is affected by various diverse factors. This work proposes two models to predict the stock market prices. The first model is an LSTM model that employs a backpropagation optimized LSTM network to forecast future stock prices. The second model is a hybrid model that combines an SVM model, KNN model and a Random Forest classifier using the Majority Voting algorithm to predict stock market trends. Both models have a sentiment analyzer to factor the news influencing the stock market using Natural Language Processing (NLP). The project aims to help investors who are new to the stock market and don’t possess sufficient knowledge to make share investments as well the experienced investors by predicting stock market trends.

MOP: Predicting Multiple Output in Multi-Sharing System

Cloud computing is relatively advanced field in which we believe resource utilization hasn't yet been optimized to its complete potential and inaccuracy of prediction leads to several minutes of delays in instant resource allocation due to scarcity of resources in Multi-Sharing System. In this paper, we develop Extraction of Transaction Log Files to Predict Multiple Output (MOP) in Multi-Sharing System based on resource utilization for higher accuracy using prediction techniques Random Forest and majority voting algorithms. The goal is to gratify upcoming resource demands and to avoid over or under provisioning of resources. The accuracy results show that the proposed model provides higher accuracy in predicting resource utilization for upcoming resource demands and prediction cost and time are reduced.

The Design of the Majority Voting Algorithm Based on Search Engine for the Text Copyright Detection Crawler

With the rapid development of the Internet era, it is very common for the websites to illegally reproduce the written works, which is a special form of copyright infringement with the characteristic of high covertness, fast speed and extensive influence. This behavior seriously violates the information website dissemination copyright of the authors and their authorized publishing websites, which has extremely serious damage to the healthy development of the text industry! To this end, the four state departments of State Copyright Administration, State Internet Information Office, Ministry of Industry and Information Technology, and Ministry of Public Security jointly carry out several times of “Jian Wang” actions to conduct the special harnessing and combating of network piracy. Against the phenomena of online illegally reproduction written works, and through researching the Internet crawler and the websites with illegally reproduction written works, this paper puts forward the text copyright detection crawler system based on search engines and majority voting algorithm.

Hyperspectral Image Classification in the Presence of Noisy Labels

Label information plays an important role in a supervised hyperspectral image classification problem. However, current classification methods all ignore an important and inevitable problem-labels may be corrupted and collecting clean labels for training samples is difficult and often impractical. Therefore, how to learn from the database with noisy labels is a problem of great practical importance. In this paper, we study the influence of label noise on hyperspectral image classification and develop a random label propagation algorithm (RLPA) to cleanse the label noise. The key idea of RLPA is to exploit knowledge (e.g., the superpixel-based spectral-spatial constraints) from the observed hyperspectral images and apply it to the process of label propagation. Specifically, the RLPA first constructs a spectral-spatial probability transform matrix (SSPTM) that simultaneously considers the spectral similarity and superpixel-based spatial information. It then randomly chooses some training samples as “clean” samples and sets the rest as unlabeled samples, and propagates the label information from the “clean” samples to the rest unlabeled samples with the SSPTM. By repeating the random assignment (of “clean” labeled samples and unlabeled samples) and propagation, we can obtain multiple labels for each training sample. Therefore, the final propagated label can be calculated by a majority vote algorithm. Experimental studies show that the RLPA can reduce the level of noisy label and demonstrates the advantages of our proposed method over four major classifiers with a significant margin-the gains in terms of the average overall accuracy, average accuracy, and kappa are impressive, e.g., 9.18%, 9.58%, and 0.1043. The MATLAB source code is available at https://github.com/junjun-jiang/RLPA.

Application of majority voting and consensus voting algorithms in N-version software

N-version programming is one of the most common techniques which is used to improve the reliability of software by building in fault tolerance, redundancy and decreasing common cause failures. N different equivalent software versions are developed by N different and isolated workgroups by considering the same software specifications. The versions solve the same task and return results that have to be compared to determine the correct result. Decisions of N different versions are evaluated by a voting algorithm or the so-called voter. In this paper, two of the most commonly used software voting algorithms such as the majority voting algorithm and the consensus voting algorithm are studied. The distinctive features of Nversion programming with majority voting and N-version programming with consensus voting are described. These two algorithms make a decision about the correct result on the base of the agreement matrix. However, if the equivalence relation on the agreement matrix is not satisfied it is impossible to make a decision. It is shown that the agreement matrix can be transformed into an appropriate form by using the Boolean compositions when the equivalence relation is satisfied.

An Innovative Emotion Assessment using Physiological Signals Based on The Combination Mechanism

The main purpose of this paper is the assessment of emotions using Electroencephalogram (EEG) and peripheral physiological signals and improve recognition accuracy of emotional states using combination mechanism. At the first step, according to the type of signals, effective features were extracted in the time and frequency domains; then, by using the Fisher’s Linear Discriminant (FLD) method, the most effective features were selected. Based on these features, six classifiers were used: Support Vector Machine (SVM), Nearest Mean (NM), K-Nearest Neighborhood (K-NN), 1-Nearest Neighborhood (1-NN), FLD and Linear Discriminant Analysis (LDA). They classified emotions in two classes (low and high) through arousal, valence and liking dimensions. The leave-one-out cross-validation (LOOCV) method has been implemented to evaluate the performance of classifiers. To enhance the accuracy of classification, combination at feature and classifier levels were performed. Via the concatenation method, combination at feature level was done. Then, by Majority voting, Fixed and Stacking algorithms, combination at classifier level were implemented. Results showed that these classifiers were selected properly and comparing with previous works, good improvements were achieved by them. Finally, by using combination methods, obtained recognition accuracy was much more reliable and combination at classifier level resulted in significant improvement

Exploring point-of-interest data from social media for artificial surface validation with decision trees

ABSTRACTArtificial surfaces represent one of the key land cover types, and validation is an indispensable component of land cover mapping that ensures data quality. Traditionally, validation has been carried out by confronting the produced land cover map with reference data, which is collected through field surveys or image interpretation. However, this approach has limitations, including high costs in terms of money and time. Recently, geo-tagged photos from social media have been used as reference data. This procedure has lower costs, but the process of interpreting geo-tagged photos is still time-consuming. In fact, social media point of interest (POI) data, including geo-tagged photos, may contain useful textual information for land cover validation. However, this kind of special textual data has seldom been analysed or used to support land cover validation. This paper examines the potential of textual information from social media POIs as a new reference source to assist in artificial surface validation without photo recognition and proposes a validation framework using modified decision trees. First, POI datasets are classified semantically to divide POIs into the standard taxonomy of land cover maps. Then, a decision tree model is built and trained to classify POIs automatically. To eliminate the effects of spatial heterogeneity on POI classification, the shortest distances between each POI and both roads and villages serve as two factors in the modified decision tree model. Finally, a data transformation based on a majority vote algorithm is then performed to convert the classified points into raster form for the purposes of applying confusion matrix methods to the land cover map. Using Beijing as a study area, social media POIs from Sina Weibo were collected to validate artificial surfaces in GlobeLand30 in 2010. A classification accuracy of 80.68% was achieved through our modified decision tree method. Compared with a classification method without spatial heterogeneity, the accuracy is 10% greater. This result indicates that our modified decision tree method displays considerable skill in classifying POIs with high spatial heterogeneity. In addition, a high validation accuracy of 92.76% was achieved, which is relatively close to the official result of 86.7%. These preliminary results indicate that social media POI datasets are valuable ancillary data for land cover validation, and our proposed validation framework provides opportunities for land cover validation with low costs in terms of money and time.