Majority Voting Scheme Research Articles

Towards automatic diagnosis of rheumatic heart disease on echocardiographic exams through video-based deep learning.

Rheumatic heart disease (RHD) affects an estimated 39 million people worldwide and is the most common acquired heart disease in children and young adults. Echocardiograms are the gold standard for diagnosis of RHD, but there is a shortage of skilled experts to allow widespread screenings for early detection and prevention of the disease progress. We propose an automated RHD diagnosis system that can help bridge this gap. Experiments were conducted on a dataset with 11646 echocardiography videos from 912 exams, obtained during screenings in underdeveloped areas of Brazil and Uganda. We address the challenges of RHD identification with a 3D convolutional neural network (C3D), comparing its performance with a 2D convolutional neural network (VGG16) that is commonly used in the echocardiogram literature. We also propose a supervised aggregation technique to combine video predictions into a single exam diagnosis. The proposed approach obtained an accuracy of 72.77% for exam diagnosis. The results for the C3D were significantly better than the ones obtained by the VGG16 network for videos, showing the importance of considering the temporal information during the diagnostic. The proposed aggregation model showed significantly better accuracy than the majority voting strategy and also appears to be capable of capturing underlying biases in the neural network output distribution, balancing them for a more correct diagnosis. Automatic diagnosis of echo-detected RHD is feasible and, with further research, has the potential to reduce the workload of experts, enabling the implementation of more widespread screening programs worldwide.

Robust discriminative feature subspace analysis for kinship verification

Kinship verification using single image of a person is a challenging task for real-world applications. In this paper, we propose a novel robust discriminative feature subspace analysis (RDFSA) method to address single sample per person (SSPP) problem in kinship verification. The proposed RDFSA method takes advantages of facial symmetry and patch-based analysis to extract discriminative features for kinship verification. Each face image is firstly divided into two halves about bilateral symmetry axis, and each halved face is then partitioned into equal sized non-overlapping patches. Multiple image-sets are formed by grouping these patches according to their positions at each halved face. Then, an SSPP is formulated as an RDFSA problem and a feature subspace is learned by maximizing inter-class separation and minimizing intra-class variance for different patches in each image-set. For a given test image pair, similarity is computed for each feature subspace and majority voting strategy is employed to determine if a given image pair is kin related or not. Proposed RDFSA method is extensively evaluated on different publicly available kinship datasets to validate kinship accuracy. Experimental results show that RDFSA achieves competitive accuracy on all kinship datasets while performing kinship verification under unconstrained environment.

Active galactic nuclei catalog from the AKARI NEP-Wide field

Context. The north ecliptic pole (NEP) field provides a unique set of panchromatic data that are well suited for active galactic nuclei (AGN) studies. The selection of AGN candidates is often based on mid-infrared (MIR) measurements. Such methods, despite their effectiveness, strongly reduce the breadth of resulting catalogs due to the MIR detection condition. Modern machine learning techniques can solve this problem by finding similar selection criteria using only optical and near-infrared (NIR) data. Aims. The aim of this study is to create a reliable AGN candidates catalog from the NEP field using a combination of optical SUBARU/HSC and NIR AKARI/IRC data and, consequently, to develop an efficient alternative for the MIR-based AKARI/IRC selection technique. Methods. We tested set of supervised machine learning algorithms for the purposes of carrying out an efficient process for AGN selection. The best models were compiled into a majority voting scheme, which used the most popular classification results to produce the final AGN catalog. An additional analysis of the catalog properties was performed as a spectral energy distribution fitting via the CIGALE software. Results. The obtained catalog of 465 AGN candidates (out of 33 119 objects) is characterized by 73% purity and 64% completeness. This new classification demonstrates a suitable consistency with the MIR-based selection. Moreover, 76% of the obtained catalog can be found solely using the new method due to the lack of MIR detection for most of the new AGN candidates. The training data, codes, and final catalog are available via the github repository. The final catalog of AGN candidates is also available via the CDS service. Conclusions. The new selection methods presented in this paper are proven to be a better alternative for the MIR color AGN selection. Machine learning techniques not only show similar effectiveness, but also involve less demanding optical and NIR observations, substantially increasing the extent of available data samples.

Ramanujan Periodic Subspace Based Epileptic EEG Signals Classification

Epilepsy is a chronic brain disorder that is characterized by intermittent epileptic seizures that can be identified in an electroencephalogram (EEG) signal. This letter proposes a low computational complex method to classify epileptic EEG signals by using a suitable Ramanujan periodic subspace (RPS). Initially, this method divides the given single-channel EEG signal into multiple nonoverlapping EEG blocks, which are projected onto a particular RPS. The energy of the projection is used as a feature to classify each block into epileptic or nonepileptic, using an SVM binary classifier. Here, in order to choose that particular RPS, a few sample blocks from the epileptic (ictal), interictal, and healthy EEG signal are projected onto the divisor RPSs of that block. The difference between the average subspace energy of healthy versus ictal or interictal versus ictal blocks is used as a measure to choose the suitable RPS. Finally, the class of each block of the EEG signal is combined using the majority voting scheme to classify the epileptic EEG signal. A publicly available benchmark EEG database from Bonn University, Germany, is used to evaluate the performance of the proposed method. Furthermore, the EEG signals are added with white Gaussian noise and ocular artifact for testing the robustness of the method against noise. Evaluation results in terms of accuracy, sensitivity, specificity, and F-score demonstrate that the proposed method is comparable with the state-of-the-art techniques and also robust against artifacts and noise.

Combining microfluidics with machine learning algorithms for RBC classification in rare hereditary hemolytic anemia

Combining microfluidics technology with machine learning represents an innovative approach to conduct massive quantitative cell behavior study and implement smart decision-making systems in support of clinical diagnostics. The spleen plays a key-role in rare hereditary hemolytic anemia (RHHA), being the organ responsible for the premature removal of defective red blood cells (RBCs). The goal is to adapt the physiological spleen filtering strategy for in vitro study and monitoring of blood diseases through RBCs shape analysis. Then, a microfluidic device mimicking the slits of the spleen red pulp area and video data analysis are combined for the characterization of RBCs in RHHA. This microfluidic unit is designed to evaluate RBC deformability by maintaining them fixed in planar orientation, allowing the visual inspection of RBC’s capacity to restore their original shape after crossing microconstrictions. Then, two cooperative learning approaches are used for the analysis: the majority voting scheme, in which the most voted label for all the cell images is the class assigned to the entire video; and the maximum sum of scores to decide the maximally scored class to assign. The proposed platform shows the capability to discriminate healthy controls and patients with an average efficiency of 91%, but also to distinguish between RHHA subtypes, with an efficiency of 82%.

Proposing Two Hybrid Data Mining Models for Discovering Students' Mental Health Problems

Mental health is an important issue for university students. The objective of this article was to apply and compare the different classification methods for students’ mental health problems. Furthermore, it presents an ensemble classification method to improve the accuracy of classifiers and assist psychologists in the decision making process. For this, 10 different classifiers were applied for classifying students into two groups. In addition, two methods of combining the classifiers are presented. In the first proposed method, the classifiers were selected based on their accuracy, and then voting was carried out based on maximum probability. In the second proposed method, the methods were combined based on the fields of the confusion table, and the voting was carried out based on majority voting scheme. These two methods were evaluated in two ways. Focusing on the accuracy and the maximum probability voting, the accuracy of the first method was 92.24%, whereas in the second method, it was 95.97%. Further, using confusion table and majority voting applied to the entire dataset, the accuracy reached 96.66%. The results are promising to assist the process of mental health assessment of students.

Aircraft Detection in High Spatial Resolution Remote Sensing Images Combining Multi-Angle Features Driven and Majority Voting CNN

Aircraft is a means of transportation and weaponry, which is crucial for civil and military fields to detect from remote sensing images. However, detecting aircraft effectively is still a problem due to the diversity of the pose, size, and position of the aircraft and the variety of objects in the image. At present, the target detection methods based on convolutional neural networks (CNNs) lack the sufficient extraction of remote sensing image information and the post-processing of detection results, which results in a high missed detection rate and false alarm rate when facing complex and dense targets. Aiming at the above questions, we proposed a target detection model based on Faster R-CNN, which combines multi-angle features driven and majority voting strategy. Specifically, we designed a multi-angle transformation module to transform the input image to realize the multi-angle feature extraction of the targets in the image. In addition, we added a majority voting mechanism at the end of the model to deal with the results of the multi-angle feature extraction. The average precision (AP) of this method reaches 94.82% and 95.25% on the public and private datasets, respectively, which are 6.81% and 8.98% higher than that of the Faster R-CNN. The experimental results show that the method can detect aircraft effectively, obtaining better performance than mature target detection networks.

A novel multi-class imbalanced EEG signals classification based on the adaptive synthetic sampling (ADASYN) approach.

BackgroundBrain signals (EEG—Electroencephalography) are a gold standard frequently used in epilepsy prediction. It is crucial to predict epilepsy, which is common in the community. Early diagnosis is essential to reduce the treatment process of the disease and to keep the process healthier.MethodsIn this study, a five-classes dataset was used: EEG signals from different individuals, healthy EEG signals from tumor document, EEG signal with epilepsy, EEG signal with eyes closed, and EEG signal with eyes open. Four different methods have been proposed to classify five classes of EEG signals. In the first approach, the EEG signal was first divided into four different bands (beta, alpha, theta, and delta), and then 25 time-domain features were extracted from each band, and the main EEG signal and these extracted features were combined to obtain 125-time domain features (feature extraction). Using the Random Forests classifier, EEG activities were classified into five classes. In the second approach, each One-Against-One (OVO) approach with 125 attributes was split into ten parts, pairwise, and then each piece was classified with the Random Forests classifier. The majority voting scheme was used to combine decisions from the ten classifiers. In the third proposed method, each One-Against-All (OVA) approach with 125 attributes was divided into five parts, and then each piece was classified with the Random Forests classifier. The majority voting scheme was used to combine decisions from the five classifiers. In the fourth proposed approach, each One-Against-All (OVA) approach with 125 attributes was divided into five parts. Since each piece obtained had an imbalanced data distribution, an adaptive synthetic (ADASYN) sampling approach was used to stabilize each piece. Then, each balanced piece was classified with the Random Forests classifier. To combine the decisions obtanied from each classifier, the majority voting scheme has been used.ResultsThe first approach achieved 71.90% classification success in classifying five-class EEG signals. The second approach achieved a classification success of 91.08% in classifying five-class EEG signals. The third method achieved 89% success, while the fourth proposed approach achieved 91.72% success. The results obtained show that the proposed fourth approach (the combination of the ADASYN sampling approach and Random Forest Classifier) achieved the best success in classifying five class EEG signals. This proposed method could be used in the detection of epilepsy events in the EEG signals.

Adaptive tuning of SLIC parameter K

The well-known simple linear iterative clustering (SLIC) is the most effective among the existing algorithms for superpixel segmentation, which requires manual tuning of the number of superpixels K. The optimal value of the parameter K of the SLIC algorithm for a given image is yet an open issue. In this work, we present granulometry and quality metrics based methods for adaptive tuning of the parameter K. The proposed granulometric method exploits the weighted average of the image pattern spectrum for the adaptive tuning of the parameter K. In the quality metrics method, we use majority voting scheme based on information, texture and ground truth independent quality metrics. The experimental results demonstrate that the K SLIC superpixels from the proposed methods achieved good boundary adherence of the ground truth for the images with high value of the compactness.

Recurrent autonomous autoencoder for intelligent DDoS attack mitigation within the ISP domain.

The continuous advancement of DDoS attack technology and an increasing number of IoT devices connected on 5G networks escalate the level of difficulty for DDoS mitigation. A growing number of researchers have started to utilise Deep Learning algorithms to improve the performance of DDoS mitigation systems. Real DDoS attack data has no labels, and hence, we present an intelligent attack mitigation (IAM) system, which takes an ensemble approach by employing Recurrent Autonomous Autoencoders (RAA) as basic learners with a majority voting scheme. The RAA is a target-driven, distributionenabled, and imbalanced clustering algorithm, which is designed to work with the ISP’s blackholing mechanism for DDoS flood attack mitigation. It can dynamically select features, decide a reference target (RT), and determine an optimal threshold to classify network traffic. A novel Comparison-Max Random Walk algorithm is used to determine the RT, which is used as an instrument to direct the model to classify the data so that the predicted positives are close or equal to the RT. We also propose Estimated Evaluation Metrics (EEM) to evaluate the performance of unsupervised models. The IAM system is tested with UDP flood, TCP flood, ICMP flood, multi-vector and a real UDP flood attack data. Additionally, to check the scalability of the IAM system, we tested it on every subdivided data set for distributed computing. The average Recall on all data sets was above 98%.

Integrated Learning: Screening Optimal Biomarkers for Identifying Preeclampsia in Placental mRNA Samples.

Preeclampsia (PE) is a maternal disease that causes maternal and child death. Treatment and preventive measures are not sound enough. The problem of PE screening has attracted much attention. The purpose of this study is to screen placental mRNA to obtain the best PE biomarkers for identifying patients with PE. We use Limma in the R language to screen out the 48 differentially expressed genes with the largest differences and used correlation-based feature selection algorithms to reduce the dimensionality and avoid attribute redundancy arising from too many mRNA samples participating in the classification. After reducing the mRNA attributes, the mRNA samples are sorted from large to small according to information gain. In this study, a classifier model is designed to identify whether samples had PE through mRNA in the placenta. To improve the accuracy of classification and avoid overfitting, three classifiers, including C4.5, AdaBoost, and multilayer perceptron, are used. We use the majority voting strategy integrated with the differentially expressed genes and the genes filtered by the best subset method as comparison methods to train the classifier. The results show that the classification accuracy rate has increased from 79% to 82.2%, and the number of mRNA features has decreased from 48 to 13. This study provides clues for the main PE biomarkers of mRNA in the placenta and provides ideas for the treatment and screening of PE.

Hilbert Transform and Statistical Analysis for Channel Selection and Epileptic Seizure Prediction

This paper is concerned with Electroencephalography (EEG) seizure prediction, which means the detection of the pre-ictal state prior to ictal activity occurrence. The basic idea of the proposed approach for EEG seizure prediction is to work on the signals in the Hilbert domain. The operation in the Hilbert domain guarantees working on the low-pass spectra of EEG signal segments to avoid artifacts. Signal attributes in the Hilbert domain including amplitude, derivative, local mean, local variance, and median are analyzed statistically to perform the channel selection and seizure prediction tasks. Pre-defined prediction and false-alarm probabilities are set to select the channels, the attributes, and bins of probability density functions (PDFs) that can be useful for seizure prediction. Due to the multi-channel nature of this process, there is a need for a majority voting strategy to take a decision for each signal segment. Simulation results reveal an average prediction rate of 96.46%, an average false-alarm rate of 0.028077/h and an average prediction time of 60.1595 min for a 90-min prediction horizon.

Predictive Syndrome Based Low Complexity Joint Iterative Detection-Decoding Algorithm for Non-Binary LDPC Codes

This paper addresses the problem of decoding non-binary low density parity check codes(LDPC) over finite field GF(q) using symbol flipping approach. To achieve low complexity reliable communication, three new algorithms for improving the bit error rate performance of the non-binary LDPC decoder are presented. The first type is the symbol flipping decoding algorithm using a flipping function based on the channel reliability to identify the least reliable symbol position. In this algorithm, if the predicted symbol value satisfies the check sum, then the value is declared as correct otherwise the value is adjusted and sent back to the QAM detector. Algorithms 2 in this paper is an improvement to iterative joint detection-decoding algorithm by using the method of iterative hard decision based majority logic to select the new candidate symbol value. The feedback value to the QAM detector is adjusted by using Euclidean distance between the current symbol and the newly selected symbol value. Algorithm 3 is a low complexity version of Algorithm 2 which is derived by applying a majority voting scheme. In the majority voting scheme, symbols are short listed first by voting and all the computation are carried out only for the short listed least reliable symbols which significantly lowers the processing complexity. Numerical results and complexity analysis show that the proposed methods have good bit error rate versus complexity trade-off for various applications when compared with some existing algorithms.

An Ensemble Model for Fake Online Review Detection Based on Data Resampling, Feature Pruning, and Parameter Optimization

With the widespread of fake online reviews, the detection of fake reviews has become a hot research issue. Despite the efforts of existing studies on fake review detection, the issues of imbalanced data and feature pruning still lack sufficient attention. To address these gaps, the present study proposes an ensemble model for the detection of fake online reviews. The model consists of four steps, and the first three steps are proposed to optimize the base classifiers: (i) Data resampling: We propose a novel way to address the data imbalance problem by combining the resampling and the grid search technique. (ii) Feature pruning: We propose an ablation study to drop unimportant features. (iii) Parameters optimization: We apply the grid search algorithm to determine suitable values of the relevant parameters for each base classifier. (iv) Classifier ensembling: We apply majority voting and stacking strategies to integrate the optimized base classifiers. The proposed data resampling method is also applied for the meta-classifier in the stacking ensemble model. This study produces advances in terms of combining different methods or algorithms into a model and the results show that the proposed ensemble model outperforms some existing techniques, thereby providing a new way to solve the data imbalance and feature pruning issues in the field of fake review detection.

Новая интеллектуальная система для обнаружения сахарного диабета 2-го типа с модифицированной функцией потерь и регуляризацией

Type 2 Diabetes (T2DM) makes up about 90% of diabetes cases, as well as tough restriction on continuous monitoring and detecting become one of key aspects in T2DM. This research aims to develop an ensemble of several machine learning and deep learning models for early detection of T2DM with high accuracy. With high diversity of models, the ensemble will provide more excessive performance than single models. Methodology: The proposed system is modified enhanced ensemble of machine learning models for T2DM prediction. It is composed of Logistic Regression, Random Forest, SVM and Deep Neural Network models to generate a modified ensemble model. Results: The output of each model in the modified ensemble is used to figure out the final output of the system. The datasets being used for these models include Practice Fusion HER, Pima Indians diabetic's data, UCI AIM94 Dataset and CA Diabetes Prevalence 2014. In comparison to the previous solutions, the proposed ensemble model solution exposes the effectiveness of accuracy, sensitivity, and specificity. It provides an accuracy of 87.5% from 83.51% in average, sensitivity of 35.8% from 29.59% as well as specificity of 98.9% from 96.27%. The processing time of the proposed model solution with 96.6ms is faster than the state-of-the-art with 97.5ms. Conclusion: The proposed modified enhanced system in this work improves the overall prediction capability of T2DM using an ensemble of several machine learning and deep learning models. A majority voting scheme utilizes the output from several models to make the final accurate prediction. Regularization function in this work is modified in order to include the regularization of all the models in ensemble, that helps prevent the overfitting and encourages the generalization capacity of the proposed system.

A Novel Multi-Stage Ensemble Model With a Hybrid Genetic Algorithm for Credit Scoring on Imbalanced Data

Credit scoring models are the cornerstone of the modern financial industry. After years of development, artificial intelligence and machine learning have led to the transformation of traditional credit scoring models based on statistics. In this study, a novel multi-stage ensemble model with a hybrid genetic algorithm is proposed to achieve accurate and stable credit prediction. To alleviate the adverse effects of imbalanced data in credit scoring models, the Instance Hardness Threshold method is extended using a majority voting strategy to deal with data imbalance. To eliminate redundant and irrelevant features in the dataset and select well-performing base classifiers, a new hybrid genetic algorithm is proposed to obtain the optimal feature subset and base classifier subset. To aggregate the predictive power of the base classifiers, a stacking approach is adopted to integrate the optimal base classifiers into the ensemble model. The proposed model is tested on three standard imbalanced credit scoring datasets, compared with similar state-of-the-art approaches, and evaluated using four well-known evaluation indicators. The experimental results prove the effectiveness of the proposed model and demonstrate its superiority.

Extracting Family History of Patients From Clinical Narratives: Exploring an End-to-End Solution With Deep Learning Models.

BackgroundPatients’ family history (FH) is a critical risk factor associated with numerous diseases. However, FH information is not well captured in the structured database but often documented in clinical narratives. Natural language processing (NLP) is the key technology to extract patients’ FH from clinical narratives. In 2019, the National NLP Clinical Challenge (n2c2) organized shared tasks to solicit NLP methods for FH information extraction.ObjectiveThis study presents our end-to-end FH extraction system developed during the 2019 n2c2 open shared task as well as the new transformer-based models that we developed after the challenge. We seek to develop a machine learning–based solution for FH information extraction without task-specific rules created by hand.MethodsWe developed deep learning–based systems for FH concept extraction and relation identification. We explored deep learning models including long short-term memory-conditional random fields and bidirectional encoder representations from transformers (BERT) as well as developed ensemble models using a majority voting strategy. To further optimize performance, we systematically compared 3 different strategies to use BERT output representations for relation identification.ResultsOur system was among the top-ranked systems (3 out of 21) in the challenge. Our best system achieved micro-averaged F1 scores of 0.7944 and 0.6544 for concept extraction and relation identification, respectively. After challenge, we further explored new transformer-based models and improved the performances of both subtasks to 0.8249 and 0.6775, respectively. For relation identification, our system achieved a performance comparable to the best system (0.6810) reported in the challenge.ConclusionsThis study demonstrated the feasibility of utilizing deep learning methods to extract FH information from clinical narratives.

Hybrid classification of diffuse liver diseases in ultrasound images using deep convolutional neural networks

Despite the fact that liver biopsy is considered to be the gold standard for detecting diffuse liver diseases, it is an invasive method with numerous side effects. Diffuse liver diagnosis using ultrasound imaging may be influenced by Physician subjectivity. Therefore, an accurate classification of liver diseases remains a notable demand. In this study, to categorize the liver status, a novel deep classifier, comprised of pre-trained deep convolutional neural networks (CNNs) is proposed. Several networks, namely ResNeXt, ResNet18, ResNet34, ResNet50, and AlexNet which concatenated with fully connected networks (FCNs) are used. Extracted deep features using transfer learning can provide sufficient classification information. An FCN can then put images into different states of the disease, namely normal liver, liver hepatitis, and cirrhosis. Two-class (normal/cirrhosis, normal/hepatitis, and cirrhosis/hepatitis) and three-class (normal/cirrhosis/hepatitis) classifiers were trained to distinguish these liver images. Since two-class classifiers showed better performance compared to the three-class classifiers, a hybrid classifier is proposed so as to integrate the weighted probabilities of the classes obtained by means of each individual classifier. Then, a majority voting strategy is employed to select the class with a higher score. The experimental results show an accuracy of 86.4% using ResNet50 with a hybrid classifier for liver images which were classified into three classes. In the distinction between normal and cirrhosis liver as well as normal and hepatitis liver, the results demonstrate the sensitivity and specificity of the first group to be 90.9% and 86.4% and the latter group shows the sensitivity of 90.9%, and specificity of 81.8%.

Novel Bounds on the Probability of Misclassification in Majority Voting: Leveraging the Majority Size

Majority voting is often employed as a tool to increase the robustness of data-driven decisions and control policies, a fact which calls for rigorous, quantitative evaluations of the limits and the potentials of majority voting schemes. This letter focuses on the case where the voting agents are binary classifiers and introduces novel bounds on the probability of misclassification conditioned on the size of the majority. We show that these bounds can be much smaller than the traditional upper bounds on the probability of misclassification. These bounds can be used in a `Probably Approximately Correct' (PAC) setting, which allows for a practical implementation.

Traffic Control Recognition with Speed-Profiles: A Deep Learning Approach

Accurate information of traffic regulators at junctions is important for navigating and driving in cities. However, such information is often missing, incomplete or not up-to-date in digital maps due to the high cost, e.g., time and money, for data acquisition and updating. In this study we propose a crowdsourced method that harnesses the light-weight GPS tracks from commuting vehicles as Volunteered Geographic Information (VGI) for traffic regulator detection. We explore the novel idea of detecting traffic regulators by learning the movement patterns of vehicles at regulated locations. Vehicles’ movement behavior was encoded in the form of speed-profiles, where both speed values and their sequential order during movement development were used as features in a three-class classification problem for the most common traffic regulators: traffic-lights, priority-signs and uncontrolled junctions. The method provides an average weighting function and a majority voting scheme to tolerate the errors in the VGI data. The sequence-to-sequence framework requires no extra overhead for data processing, which makes the method applicable for real-world traffic regulator detection tasks. The results showed that the deep-learning classifier Conditional Variational Autoencoder can predict regulators with 90% accuracy, outperforming a random forest classifier (88% accuracy) that uses the summarized statistics of movement as features. In our future work images and augmentation techniques can be leveraged to generalize the method’s ability for classifying a greater variety of traffic regulator classes.