Adaptive 3DCNN-based Interpretable Ensemble Model for Early Diagnosis of Alzheimer's Disease

Adaptive interpretable ensemble model based on three-dimensional Convolutional Neural Network (3DCNN) and Genetic Algorithm (GA), i.e., 3DCNN+EL+GA, was proposed to differentiate the subjects with Alzheimer's Disease (AD) or Mild Cognitive Impairment (MCI) and further identify the discriminative brain regions significantly contributing to the classifications in a data-driven way. Plus, the discriminative brain sub-regions at a voxel level were further located in these achieved brain regions, with a gradient-based attribution method designed for CNN. Besides disclosing the discriminative brain sub-regions, the testing results on the datasets from the Alzheimer's Disease Neuroimaging Initiative (ADNI) and the Open Access Series of Imaging Studies (OASIS) indicated that 3DCNN+EL+GA outperformed other state-of-the-art deep learning algorithms and that the achieved discriminative brain regions (e.g., the rostral hippocampus, caudal hippocampus, and medial amygdala) were linked to emotion, memory, language, and other essential brain functions impaired early in the AD process. Future research is needed to examine the generalizability of the proposed method and ideas to discern discriminative brain regions for other brain disorders, such as severe depression, schizophrenia, autism, and cerebrovascular diseases, using neuroimaging.

Convolutional neural network-based automatic classification for incomplete antibody reaction intensity in solid phase anti-human globulin test image

The precise classification of incomplete antibody reaction intensity (IARI) in hydrogel chromatography medium high density medium solid-phase Coombs test is essential for haemolytic disease screening. However, an automatic and contactless method is required for accurate classification of IARI. Here, we present a deep ensemble learning model that integrates five different convolutional neural networks into a single model for IARI classification. A dataset, including 1628 IARI images and corresponding labels of IARI categories ((-), (1 +), (2 +), (3 +), and (4 +)), was used. We trained our model using 1302 IARIs and validated its performance using 326 IARIs. The proposed model achieved 100%, 99.4%, 99.4%, 100%, and 100% accuracies in the ( −), (1 +), (2 +), (3 +), and (4 +) categories, respectively. The results were compared with those of manual classification by immunologists (average accuracy: 99.8% vs. 88.3%, p < 0.01). Following model assistance, all three immunologists achieved increased accuracy (average accuracy: + 6.1%), with the average accuracy of junior immunologists maximum increasing by 11.3%. The time required for model classification was 0.094 s·image^–1, whereas that required manually was 5.528 s·image^–1. The proposed model can thus substantially improve the accuracy and efficiency of IARI classification and facilitate the automation of haemolytic disease screening equipment.

Metaheuristic Ensemble Pruning via Greedy-based Optimization Selection

Ensemble selection is a crucial problem for ensemble learning (EL) to speed up the predictive model, reduce the storage space requirements and to further improve prediction accuracy. Diversity among individual predictors is widely recognized as a key factor to successful ensemble selection (ES), while the ultimate goal of ES is to improve its predictive accuracy and generalization of the ensemble. Motivated by the problems stated in previous, we have devised a novel hybrid layered based greedy ensemble reduction (HLGER) architecture to delete the predictor with lowest accuracy and diversity with evaluation function according to the diversity metrics. Experimental investigations are conducted based on benchmark time series data sets, support vectors regression algorithm utilized as base learner to generate homogeneous ensemble, HLGER uses locally weight ensemble (LWE) strategies to provide a final ensemble prediction. The experimental results demonstrate that, in comparison with benchmark ensemble pruning techniques, HLGER achieves significantly superior generalization performance.

A New Residual Dense Network for Dance Action Recognition From Heterogeneous View Perception

At present, part of people's body is in the state of sub-health, and more people pay attention to physical exercise. Dance is a relatively simple and popular activity, it has been widely concerned. The traditional action recognition method is easily affected by the action speed, illumination, occlusion and complex background, which leads to the poor robustness of the recognition results. In order to solve the above problems, an improved residual dense neural network method is used to study the automatic recognition of dance action images. Firstly, based on the residual model, the features of dance action are extracted by using the convolution layer and pooling layer. Then, the exponential linear element (ELU) activation function, batch normalization (BN) and Dropout technology are used to improve and optimize the model to mitigate the gradient disappearance, prevent over-fitting, accelerate convergence and enhance the model generalization ability. Finally, the dense connection network (DenseNet) is introduced to make the extracted dance action features more rich and effective. Comparison experiments are carried out on two public databases and one self-built database. The results show that the recognition rate of the proposed method on three databases are 99.98, 97.95, and 0.97.96%, respectively. It can be seen that this new method can effectively improve the performance of dance action recognition.

ANN-Based Estimation of Low-Latitude Monthly Ocean Latent Heat Flux by Ensemble Satellite and Reanalysis Products

Ocean latent heat flux (LHF) is an essential variable for air–sea interactions, which establishes the link between energy balance, water and carbon cycle. The low-latitude ocean is the main heat source of the global ocean and has a great influence on global climate change and energy transmission. Thus, an accuracy estimation of high-resolution ocean LHF over low-latitude area is vital to the understanding of energy and water cycle, and it remains a challenge. To reduce the uncertainties of individual LHF products over low-latitude areas, four machine learning (ML) methods (Artificial Neutral Network (ANN), Random forest (RF), Bayesian Ridge regression and Random Sample Consensus (RANSAC) regression) were applied to estimate low-latitude monthly ocean LHF by using two satellite products (JOFURO-3 and GSSTF-3) and two reanalysis products (MERRA-2 and ERA-I). We validated the estimated ocean LHF using 115 widely distributed buoy sites from three buoy site arrays (TAO, PIRATA and RAMA). The validation results demonstrate that the performance of LHF estimations derived from the ML methods (including ANN, RF, BR and RANSAC) were significantly better than individual LHF products, indicated by R² increasing by 3.7–46.4%. Among them, the LHF estimation using the ANN method increased the R² of the four-individual ocean LHF products (ranging from 0.56 to 0.79) to 0.88 and decreased the RMSE (ranging from 19.1 to 37.5) to 11 W m⁻². Compared to three other ML methods (RF, BR and RANSAC), ANN method exhibited the best performance according to the validation results. The results of relative uncertainty analysis using the triangle cornered hat (TCH) method show that the ensemble LHF product using ML methods has lower relative uncertainty than individual LHF product in most area. The ANN was employed to implement the mapping of annual average ocean LHF over low-latitude at a spatial resolution of 0.25° during 2003–2007. The ocean LHF fusion products estimated from ANN methods were 10–30 W m⁻² lower than those of the four original ocean products (MERRA-2, JOFURO-3, ERA-I and GSSTF-3) and were more similar to observations.

Early Detection of Alzheimer's Disease Using Magnetic Resonance Imaging: A Novel Approach Combining Convolutional Neural Networks and Ensemble Learning

Early detection is critical for effective management of Alzheimer's disease (AD) and screening for mild cognitive impairment (MCI) is common practice. Among several deep-learning techniques that have been applied to assessing structural brain changes on magnetic resonance imaging (MRI), convolutional neural network (CNN) has gained popularity due to its superb efficiency in automated feature learning with the use of a variety of multilayer perceptrons. Meanwhile, ensemble learning (EL) has shown to be beneficial in the robustness of learning-system performance via integrating multiple models. Here, we proposed a classifier ensemble developed by combining CNN and EL, i.e., the CNN-EL approach, to identify subjects with MCI or AD using MRI: i.e., classification between (1) AD and healthy cognition (HC), (2) MCIc (MCI patients who will convert to AD) and HC, and (3) MCIc and MCInc (MCI patients who will not convert to AD). For each binary classification task, a large number of CNN models were trained applying a set of sagittal, coronal, or transverse MRI slices; these CNN models were then integrated into a single ensemble. Performance of the ensemble was evaluated using stratified fivefold cross-validation method for 10 times. The number of the intersection points determined by the most discriminable slices separating two classes in a binary classification task among the sagittal, coronal, and transverse slice sets, transformed into the standard Montreal Neurological Institute (MNI) space, acted as an indicator to assess the ability of a brain region in which the points were located to classify AD. Thus, the brain regions with most intersection points were considered as those mostly contributing to the early diagnosis of AD. The result revealed an accuracy rate of 0.84 ± 0.05, 0.79 ± 0.04, and 0.62 ± 0.06, respectively, for classifying AD vs. HC, MCIc vs. HC, and MCIc vs. MCInc, comparable to previous reports and a 3D deep learning approach (3D-SENet) based on a more state-of-the-art and popular Squeeze-and-Excitation Networks model using channel attention mechanism. Notably, the intersection points accurately located the medial temporal lobe and several other structures of the limbic system, i.e., brain regions known to be struck early in AD. More interestingly, the classifiers disclosed multiple patterned MRI changes in the brain in AD and MCIc, involving these key regions. These results suggest that as a data-driven method, the combined CNN and EL approach can locate the most discriminable brain regions indicated by the trained ensemble model while the generalization ability of the ensemble model was maximized to successfully capture AD-related brain variations early in the disease process; it can also provide new insights into understanding the complex heterogeneity of whole-brain MRI changes in AD. Further research is needed to examine the clinical implication of the finding, capability of the advocated CNN-EL approach to help understand and evaluate an individual subject's disease status, symptom burden and progress, and the generalizability of the advocated CNN-EL approach to locate the most discriminable brain regions in the detection of other brain disorders such as schizophrenia, autism, and severe depression, in a data-driven way.