Considering the low accuracy of prediction in the positive samples and poor overall classification effects caused by unbalanced sample data of MicroRNA (miRNA) target, we proposes a support vector machine (SVM)-integration of under-sampling and weight (IUSM) algorithm in this paper, an under-sampling based on the ensemble learning algorithm. The algorithm adopts SVM as learning algorithm and AdaBoost as integration framework, and embeds clustering-based under-sampling into the iterative process, aiming at reducing the degree of unbalanced distribution of positive and negative samples. Meanwhile, in the process of adaptive weight adjustment of the samples, the SVM-IUSM algorithm eliminates the abnormal ones in negative samples with robust sample weights smoothing mechanism so as to avoid over-learning. Finally, the prediction of miRNA target integrated classifier is achieved with the combination of multiple weak classifiers through the voting mechanism. The experiment revealed that the SVM-IUSW, compared with other algorithms on unbalanced dataset collection, could not only improve the accuracy of positive targets and the overall effect of classification, but also enhance the generalization ability of miRNA target classifier.
With the increasing number of electrocardiogram (ECG) data, extensive application requirements of computer-aided ECG analysis have occurred. In the paper, we propose a variety of strategies to improve the performance of clinical ECG classification algorithm based on Lead Convolutional Neural Network (LCNN). Firstly, we obtained two classifiers by using different preprocessing methods and training methods in the study. Then, we applied the multiple output prediction method to both of them independently. Finally, the Bayesian approach was employed to fuse them. Tests conducted using more than 150 000 ECG records showed that the proposed method had an accuracy of 85.04% and the area under receiver operating characteristic curve (AUC) was 0.918 5, which significantly outperforms traditional methods based on feature extraction techniques.
Parkinson's disease (PD) diagnosis based on speech data has been proved to be an effective way in recent years. There are still some problems on preprocessing samples, ensemble learning, and so on. The problems can further cause misleading of classifiers, unsatisfactory classification accuracy and stability. This paper proposed a new diagnosis algorithm of PD by combining multi-edit sample selection method and random forest. At the end of it, this paper presents a group of experiments carried out with the newest public datasets. Experimental results showed that this proposed algorithm realized the classification of the samples and the subjects of PD. Furthermore, it achieved average classification accuracy of 100% and obtained improvement of up to 29.44% compared to those provided by the subjects. This paper proposes a new speech diagnosis algorithm for PD based on instance selection; and the method algorithm has a higher and more stable classification accuracy, compared with the other algorithms.
Feature representation is the crucial factor for the magnetic resonance imaging (MRI) based computer-aided diagnosis (CAD) of Parkinson’s disease (PD). Deep polynomial network (DPN) is a novel supervised deep learning algorithm, which has excellent feature representation for small dataset. In this work, a stacked DPN (SDPN) based ensemble learning framework is proposed for diagnosis of PD, which can improve diagnostic accuracy for small dataset. In the proposed framework, SDPN was performed on each subset of extracted features from MRI images to generate new feature representation. The support vector machine (SVM) was then adopted to perform classification task on each subset. The ensemble learning algorithm was then performed on all the SVM classifiers to generate the final diagnosis for PD. The experimental results on the Parkinson’s Progression Markers Initiative dataset (PPMI) showed that the proposed algorithm achieved the classification accuracy, sensitivity and specificity of 90.15%, 85.48% and 93.27%, respectively, with the brain network features, and it also got the classification accuracy of 87.18%, sensitivity of 86.90% and specificity of 87.27% on the multi-view features extracted from different brain regions. Moreover, the proposed algorithm outperformed other algorithms on the MRI dataset from PPMI. It suggests that the proposed SDPN-based ensemble learning framework has the feasibility and effectiveness for the CAD of PD.
Methods for achieving diagnosis of Parkinson’s disease (PD) based on speech data mining have been proven effective in recent years. However, due to factors such as the degree of disease of the data collection subjects and the collection equipment and environment, there are different categories of sample aliasing in the sample space of the acquired data set. Samples in the aliased area are difficult to be identified effectively, which seriously affects the classification accuracy of the algorithm. In order to solve this problem, a partition bagging ensemble learning is proposed in this article, which measures the aliasing degree of the sample by designing the the ratio of sample centroid distance metrics and divides the training set into multiple subsets. And then the method of transfer training of misclassified samples is used to adjust the results of subset partitioning. Finally, the optimized weights of each sub-classifier are used to integrate the test results. The experimental results show that the classification accuracy of the proposed method is significantly improved on two public datasets and the increasement of mean accuracy is up to 25.44%. This method not only effectively improves the classification accuracy of PD speech dataset, but also increases the sample utilization rate, providing a new idea for the diagnosis of PD.
Alzheimer's disease (AD) is a typical neurodegenerative disease, which is clinically manifested as amnesia, loss of language ability and self-care ability, and so on. So far, the cause of the disease has still been unclear and the course of the disease is irreversible, and there has been no cure for the disease yet. Hence, early prognosis of AD is important for the development of new drugs and measures to slow the progression of the disease. Mild cognitive impairment (MCI) is a state between AD and healthy controls (HC). Studies have shown that patients with MCI are more likely to develop AD than those without MCI. Therefore, accurate screening of MCI patients has become one of the research hotspots of early prognosis of AD. With the rapid development of neuroimaging techniques and deep learning, more and more researchers employ deep learning methods to analyze brain neuroimaging images, such as magnetic resonance imaging (MRI), for early prognosis of AD. Hence, in this paper, a three-dimensional multi-slice classifiers ensemble based on convolutional neural network (CNN) and ensemble learning for early prognosis of AD has been proposed. Compared with the CNN classification model based on a single slice, the proposed classifiers ensemble based on multiple two-dimensional slices from three dimensions could use more effective information contained in MRI to improve classification accuracy and stability in a parallel computing mode.
Neuroimaging technologies have been applied to the diagnosis of schizophrenia. In order to improve the performance of the single-modal neuroimaging-based computer-aided diagnosis (CAD) for schizophrenia, an ensemble learning algorithm based on learning using privileged information (LUPI) was proposed in this work. Specifically, the extreme learning machine based auto-encoder (ELM-AE) was first adopted to learn new feature representation for the single-modal neuroimaging data. Random project algorithm was then performed on the learned high-dimensional features to generate several new feature subspaces. After that, multiple feature pairs were built among these subspaces to work as source domain and target domain, respectively, which were used to train multiple support vector machine plus (SVM+) classifier. Finally, a strong classifier is learned by combining these SVM+ classifiers for classification. The proposed algorithm was evaluated on a public schizophrenia neuroimaging dataset, including the data of structural magnetic resonance imaging (sMRI) and functional MRI (fMRI). The results showed that the proposed algorithm achieved the best diagnosis performance. In particular, the classification accuracy, sensitivity and specificity of the proposed algorithm were 72.12% ± 8.20%, 73.50% ± 15.44% and 70.93% ± 12.93%, respectively, on the sMRI data, and it also achieved the classification accuracy of 72.33% ± 8.95%, sensitivity of 68.50% ± 16.58% and specificity of 75.73% ± 16.10% on the fMRI data. The proposed algorithm overcomes the problem that the traditional LUPI methods need the additional privileged information modality as source domain. It can be directly applied to the single-modal data for classification, and also can improve the classification performance. Therefore, it suggests that the proposed algorithm will have wider applications.
Both feature representation and classifier performance are important factors that determine the performance of computer-aided diagnosis (CAD) systems. In order to improve the performance of ultrasound-based CAD for breast cancers, a novel multiple empirical kernel mapping (MEKM) exclusivity regularized machine (ERM) ensemble classifier algorithm based on self-paced learning (SPL) is proposed, which simultaneously promotes the performance of both feature representation and the classifier. The proposed algorithm first generates multiple groups of features by MEKM to enhance the ability of feature representation, which also work as the kernel transform in multiple support vector machines embedded in ERM. The SPL strategy is then adopted to adaptively select samples from easy to hard so as to gradually train the ERM classifier model with improved performance. This algorithm is verified on a B-mode ultrasound dataset and an elastography ultrasound dataset, respectively. The results show that the classification accuracy, sensitivity and specificity on B-mode ultrasound are (86.36±6.45)%, (88.15±7.12)%, and (84.52±9.38)%, respectively, and the classification accuracy, sensitivity and specificity on elastography ultrasound are (85.97±3.75)%, (85.93±6.09)%, and (86.03±5.88)%, respectively. It indicates that the proposed algorithm can effectively improve the performance of ultrasound-based CAD for breast cancers with the potential for application.
Speech feature learning is the core and key of speech recognition method for mental illness. Deep feature learning can automatically extract speech features, but it is limited by the problem of small samples. Traditional feature extraction (original features) can avoid the impact of small samples, but it relies heavily on experience and is poorly adaptive. To solve this problem, this paper proposes a deep embedded hybrid feature sparse stack autoencoder manifold ensemble algorithm. Firstly, based on the prior knowledge, the psychotic speech features are extracted, and the original features are constructed. Secondly, the original features are embedded in the sparse stack autoencoder (deep network), and the output of the hidden layer is filtered to enhance the complementarity between the deep features and the original features. Third, the L1 regularization feature selection mechanism is designed to compress the dimensions of the mixed feature set composed of deep features and original features. Finally, a weighted local preserving projection algorithm and an ensemble learning mechanism are designed, and a manifold projection classifier ensemble model is constructed, which further improves the classification stability of feature fusion under small samples. In addition, this paper designs a medium-to-large-scale psychotic speech collection program for the first time, collects and constructs a large-scale Chinese psychotic speech database for the verification of psychotic speech recognition algorithms. The experimental results show that the main innovation of the algorithm is effective, and the classification accuracy is better than other representative algorithms, and the maximum improvement is 3.3%. In conclusion, this paper proposes a new method of psychotic speech recognition based on embedded mixed sparse stack autoencoder and manifold ensemble, which effectively improves the recognition rate of psychotic speech.