Convergent learning-based model for leukemia classification from gene expression.

Microarray data analysis is a major challenging field of research in recent days. Machine learning-based automated gene data classification is an essential aspect for diagnosis of gene related any malfunctions and diseases. As the size of the data is very large, it is essential to design a suitable classifier that can process huge amount of data. Deep learning is one of the advanced machine learning techniques to mitigate these types of problems. Due the presence of more number of hidden layers, it can easily handle the big amount of data. We have presented a method of classification to understand the convergence of training deep neural network (DNN). The assumptions are taken as the inputs do not degenerate and the network is over-parameterized. Also the number of hidden neurons is sufficiently large. Authors in this piece of work have used DNN for classifying the gene expressions data. The dataset used in the work contains the bone marrow expressions of 72 leukemia patients. A five-layer DNN classifier is designed for classifying acute lymphocyte (ALL) and acute myelocytic (AML) samples. The network is trained with 80% data and rest 20% data is considered for validation purpose. Proposed DNN classifier is providing a satisfactory result as compared to other classifiers. Two types of leukemia are classified with 98.2% accuracy, 96.59% sensitivity, and 97.9% specificity. The different types of computer-aided analyses of genes can be helpful to genetic and virology researchers as well in future generation.

Hyperspectral Image Classification: Potentials, Challenges, and Future Directions.

Recent imaging science and technology discoveries have considered hyperspectral imagery and remote sensing. The current intelligent technologies, such as support vector machines, sparse representations, active learning, extreme learning machines, transfer learning, and deep learning, are typically based on the learning of the machines. These techniques enrich the processing of such three-dimensional, multiple bands, and high-resolution images with their precision and fidelity. This article presents an extensive survey depicting machine-dependent technologies' contributions and deep learning on landcover classification based on hyperspectral images. The objective of this study is three-fold. First, after reading a large pool of Web of Science (WoS), Scopus, SCI, and SCIE-indexed and SCIE-related articles, we provide a novel approach for review work that is entirely systematic and aids in the inspiration of finding research gaps and developing embedded questions. Second, we emphasize contemporary advances in machine learning (ML) methods for identifying hyperspectral images, with a brief, organized overview and a thorough assessment of the literature involved. Finally, we draw the conclusions to assist researchers in expanding their understanding of the relationship between machine learning and hyperspectral images for future research.

Computational Intelligence for Observation and Monitoring: A Case Study of Imbalanced Hyperspectral Image Data Classification.

Imbalance in hyperspectral images creates a crisis in its analysis and classification operation. Resampling techniques are utilized to minimize the data imbalance. Although only a limited number of resampling methods were explored in the previous research, a small quantity of work has been done. In this study, we propose a novel illustrative study of the performance of the existing resampling techniques, viz. oversampling, undersampling, and hybrid sampling, for removing the imbalance from the minor samples of the hyperspectral dataset. The balanced dataset is classified in the next step, using the tree-based ensemble classifiers by including the spectral and spatial features. Finally, the comparative study is performed based on the statistical analysis of the outcome obtained from those classifiers that are discussed in the results section. In addition, we applied a new ensemble hybrid classifier named random rotation forest to our dataset. Three benchmark hyperspectral datasets: Indian Pines, Salinas Valley, and Pavia University, are applied for performing the experiments. We have taken precision, recall, F score, Cohen kappa, and overall accuracy as assessment metrics to evaluate our model. The obtained result shows that SMOTE, Tomek Links, and their combinations stand out to be the more optimized resampling strategies. Moreover, the ensemble classifiers such as rotation forest and random rotation ensemble provide more accuracy than others of their kind.

Diastolic Dysfunction Is a Predictor of Poor Survival in Patients with Decompensated Cirrhosis.

BACKGROUND: Left ventricular diastolic dysfunction (LVDD) appears to be the earliest cardiac disturbance in cirrhosis patients. There are many previous reports reporting the significance of severity of LVDD on the outcome of liver transplantation or TIPS insertion, a few Indian studies have addressed the role of LVDD on survival in decompensated cirrhosis. The objective of this study is to assess the effect of LVDD on the survival of decompensated cirrhotic patients. METHODS: We prospectively evaluated 92 decompensated cirrhotic patients from April 2015 to March 2017 at IMS and SUM Hospital, Bhubaneswar, India. 2D echocardiography with tissue Doppler imaging was used to evaluate cardiac function, as per the American society of echocardiography guidelines. The primary endpoint was to evaluate the effect of LVDD on overall mortality. RESULTS: Ninety-two decompensated cirrhotic patients were evaluated in this prospective cohort study. Twenty-eight out of 92 patients (30%) died due to liver-related complications after a follow-up of 24 months. The decompensated cirrhotic patients with MELD score ≥ 15 had a significantly higher E/e' ratio (11.94 ± 4.24 vs. 8.74 ± 3.32, p < 0.001) suggesting severe LV dysfunction in advanced cirrhosis. Patients with E/e' ratio > 10 had significantly higher MELD score and Child-Pugh score (19.88 ± 7.72 vs. 14.31 ± 5.83; 10.25 ± 1.74 vs. 9.02 ± 1.74, p < 0.01, respectively) as compared to theE/e' ratio < 10 group. In Cox proportional hazard multivariate analysis, E/e' ≥ 10 (HR 2.72, 95% CI 1.07-6.9, p = 0.03) and serum albumin (HR 0.32, 95% CI 0.14-0.7, p < 0.01) were found to be independent predictors of mortality in decompensated cirrhotic patients. CONCLUSION: : The presence of LVDD and low serum albumin were independent predictors of mortality in decompensated cirrhotic patients. Hence, LVDD is an indicator of advanced cirrhosis and mortality.

Optimization of Skewed Data Using Sampling-Based Preprocessing Approach.

In the past few years, classification has undergone some major evolution. With a constant surge of the amount of data gathered from different sources, efficient processing and analysis of data is becoming difficult. Due to the uneven distribution of data among classes, data classification with machine-learning techniques has become more tedious. While most algorithms focus on major data samples, they ignore the minor class data. Thus, the data-skewing issue is one of the critical problems that need attention of researchers. The paper stresses upon data preprocessing using sampling techniques to overcome the data-skewing problem. Here, three different sampling techniques such as Resampling, SpreadSubSampling, and SMOTE are implemented to reduce this uneven data distribution issue and classified with the K-nearest neighbor algorithm. The performance of classification is evaluated with various performance metrics to determine the efficiency of classification.

EAGA-MLP-An Enhanced and Adaptive Hybrid Classification Model for Diabetes Diagnosis.

Disease diagnosis is a critical task which needs to be done with extreme precision. In recent times, medical data mining is gaining popularity in complex healthcare problems based disease datasets. Unstructured healthcare data constitutes irrelevant information which can affect the prediction ability of classifiers. Therefore, an effective attribute optimization technique must be used to eliminate the less relevant data and optimize the dataset for enhanced accuracy. Type 2 Diabetes, also called Pima Indian Diabetes, affects millions of people around the world. Optimization techniques can be applied to generate a reliable dataset constituting of symptoms that can be useful for more accurate diagnosis of diabetes. This study presents the implementation of a new hybrid attribute optimization algorithm called Enhanced and Adaptive Genetic Algorithm (EAGA) to get an optimized symptoms dataset. Based on readings of symptoms in the optimized dataset obtained, a possible occurrence of diabetes is forecasted. EAGA model is further used with Multilayer Perceptron (MLP) to determine the presence or absence of type 2 diabetes in patients based on the symptoms detected. The proposed classification approach was named as Enhanced and Adaptive-Genetic Algorithm-Multilayer Perceptron (EAGA-MLP). It is also implemented on seven different disease datasets to assess its impact and effectiveness. Performance of the proposed model was validated against some vital performance metrics. The results show a maximum accuracy rate of 97.76% and 1.12 s of execution time. Furthermore, the proposed model presents an F-Score value of 86.8% and a precision of 80.2%. The method is compared with many existing studies and it was observed that the classification accuracy of the proposed Enhanced and Adaptive-Genetic Algorithm-Multilayer Perceptron (EAGA-MLP) model clearly outperformed all other previous classification models. Its performance was also tested with seven other disease datasets. The mean accuracy, precision, recall and f-score obtained was 94.7%, 91%, 89.8% and 90.4%, respectively. Thus, the proposed model can assist medical experts in accurately determining risk factors of type 2 diabetes and thereby help in accurately classifying the presence of type 2 diabetes in patients. Consequently, it can be used to support healthcare experts in the diagnosis of patients affected by diabetes.