ABSTRACT
Deep neural networks have been successfully applied to generate predictive patterns from medical and diagnostic data. This paper presents an approach for assessing persons with Alzheimer's disease (AD) mild cognitive impairment (MCI), compared with normal control (NC) persons, using the zoom-in neural network (ZNN) deep-learning algorithm. ZNN stacks a set of zoom-in learning units (ZLUs) in a feedforward hierarchy without backpropagation. The resting-state fMRI (rs-fMRI) dataset for AD assessments was obtained from the Alzheimer's Disease Neuroimaging Initiative (ADNI). The Automated Anatomical Labeling (AAL-90) atlas, which provides 90 neuroanatomical functional regions, was used to assess and detect the implicated regions in the course of AD. The features of the ZNN are extracted from the 140-time series rs-fMRI voxel values in a region of the brain. ZNN yields the three classification accuracies of AD versus MCI and NC, NC versus AD and MCI, and MCI versus AD and NC of 97.7%, 84.8%, and 72.7%, respectively, with the seven discriminative regions of interest (ROIs) in the AAL-90.
Subject(s)
Alzheimer Disease , Cognitive Dysfunction , Deep Learning , Humans , Alzheimer Disease/diagnostic imaging , Neural Networks, Computer , Cognitive Dysfunction/diagnostic imaging , Magnetic Resonance Imaging/methodsABSTRACT
In this study, we propose a method to automatically find features from a dataset that are effective for classification or prediction, using a new method called multi-agent reinforcement learning and a guide agent. Each feature of the dataset has one of the main and guide agents, and these agents decide whether to select a feature. Main agents select the optimal features, and guide agents present the criteria for judging the main agents' actions. After obtaining the main and guide rewards for the features selected by the agents, the main agent that behaves differently from the guide agent updates their Q-values by calculating the learning reward delivered to the main agents. The behavior comparison helps the main agent decide whether its own behavior is correct, without using other algorithms. After performing this process for each episode, the features are finally selected. The feature selection method proposed in this study uses multiple agents, reducing the number of actions each agent can perform and finding optimal features effectively and quickly. Finally, comparative experimental results on multiple datasets show that the proposed method can select effective features for classification and increase classification accuracy.
Subject(s)
Algorithms , Learning , RewardABSTRACT
Finding the minimum number of appropriate biomarkers for specific targets such as a lung cancer has been a challenging issue in bioinformatics. We propose a hierarchical two-phase framework for selecting appropriate biomarkers that extracts candidate biomarkers from the cancer microarray datasets and then selects the minimum number of appropriate biomarkers from the extracted candidate biomarkers datasets with a specific neuro-fuzzy algorithm, which is called a neural network with weighted fuzzy membership function (NEWFM). In this context, as the first phase, the proposed framework is to extract candidate biomarkers by using a Bhattacharyya distance method that measures the similarity of two discrete probability distributions. Finally, the proposed framework is able to reduce the cost of finding biomarkers by not receiving medical supplements and improve the accuracy of the biomarkers in specific cancer target datasets.
Subject(s)
Choice Behavior , Datasets as Topic , Decision Making, Computer-Assisted , Fuzzy Logic , Genes, Neoplasm , Microarray AnalysisABSTRACT
Naive Bayesian (NB) network classifier is a simple and well-known type of classifier, which can be easily induced from a DNA microarray data set. However, a strong conditional independence assumption of NB network sometimes can lead to weak classification performance. In this paper, we propose a new approach of interactive naive Bayesian (INB) network to weaken the conditional independence of NB network and classify cancers using DNA microarray data set. We selected the differently expressed genes (DEGs) to reduce the dimension of the microarray data set. Then, an interactive parent which has the biggest influence among all DEGs is searched for each DEG. And then we calculate a weight to represent the interactive relationship between a DEG and its parent. Finally, the gene-gene interaction network is constructed. We experimentally test the INB network in terms of classification accuracy using leukemia and colon DNA microarray data sets, then we compare it with the NB network. The INB network can get higher classification accuracies than NB network. And INB network can show the gene-gene interactions visually.
Subject(s)
Bayes Theorem , Models, Statistical , Neoplasm Proteins/metabolism , Neoplasms/metabolism , Pattern Recognition, Automated/methods , Protein Interaction Mapping/methods , Computer Simulation , Fuzzy Logic , Gene Expression Regulation, Neoplastic/genetics , High-Throughput Nucleotide Sequencing/methods , Humans , Models, Biological , Neoplasm Proteins/genetics , Neoplasms/genetics , Neural Networks, Computer , Oligonucleotide Array Sequence Analysis/methods , Signal Transduction/geneticsABSTRACT
In the data mining field, classification is a very crucial technology, and the Bayesian classifier has been one of the hotspots in classification research area. However, assumptions of Naive Bayesian and Tree Augmented Naive Bayesian (TAN) are unfair to attribute relations. Therefore, this paper proposes a new algorithm named Fuzzy Naive Bayesian (FNB) using neural network with weighted membership function (NEWFM) to extract regulated relations and weights. Then, we can use regulated relations and weights to construct a regulated network. Finally, we will classify the heart and Haberman datasets by the FNB network to compare with experiments of Naive Bayesian and TAN. The experiment results show that the FNB has a higher classification rate than Naive Bayesian and TAN.
Subject(s)
Algorithms , Bayes Theorem , Decision Support Systems, Clinical , Diagnosis, Computer-Assisted/methods , Fuzzy Logic , Machine Learning , Pattern Recognition, Automated/methods , Reproducibility of Results , Sensitivity and SpecificityABSTRACT
This paper proposes new combined methods to classify normal and epileptic seizure EEG signals using wavelet transform (WT), phase-space reconstruction (PSR), and Euclidean distance (ED) based on a neural network with weighted fuzzy membership functions (NEWFM). WT, PSR, ED, and statistical methods that include frequency distributions and variation, were implemented to extract 24 initial features to use as inputs. Of the 24 initial features, 4 minimum features with the highest accuracy were selected using a non-overlap area distribution measurement method supported by the NEWFM. These 4 minimum features were used as inputs for the NEWFM and this resulted in performance sensitivity, specificity, and accuracy of 96.33%, 100%, and 98.17%, respectively. In addition, the area under Receiver Operating Characteristic (ROC) curve was used to measure the performances of NEWFM both without and with feature selections.
Subject(s)
Brain/physiopathology , Diagnosis, Computer-Assisted/methods , Electroencephalography/methods , Epilepsy/diagnosis , Epilepsy/physiopathology , Pattern Recognition, Automated/methods , Wavelet Analysis , Algorithms , Brain Mapping/methods , Epilepsy/classification , Neural Networks, Computer , Reproducibility of Results , Sensitivity and SpecificityABSTRACT
Fuzzy neural networks (FNNs) have been successfully applied to generate predictive rules for medical or diagnostic data. This brief presents an approach to detect premature ventricular contractions (PVCs) using the neural network with weighted fuzzy membership functions (NEWFMs). The NEWFM classifies normal and PVC beats by the trained bounded sum of weighted fuzzy membership functions (BSWFMs) using wavelet transformed coefficients from the MIT-BIH PVC database. The eight generalized coefficients, locally related to the time signal, are extracted by the nonoverlap area distribution measurement method. The eight generalized coefficients are used for the three PVC data sets with reliable accuracy rates of 99.80%, 99.21%, and 98.78%, respectively, which means that the selected features are less dependent on the data sets. It is shown that the locations of the eight features are not only around the QRS complex that represents ventricular depolarization in the electrocardiogram (ECG) containing a Q wave, an R wave, and an S wave, but also the QR segment from the Q wave to the R wave has more discriminate information than the RS segment from the R wave to the S wave. The BSWFMs of the eight features trained by NEWFM are shown visually, which makes the features explicitly interpretable. Since each BSWFM combines multiple weighted fuzzy membership functions into one using the bounded sum, the eight small-sized BSWFMs can realize real-time PVC detection in a mobile environment.